Special Cases

28
2021.9
【2021 Application Example】 Fongyu Uses AI Knowledge-based Fish Farming to Effectively Increase Aquatic Production by 10%

Fisheries is an important industry in an island economy However, the fish farming industry has faced severe challenges in recent years, including climate change, labor shortage, and rising costs In particular, nearly 110,000 workers in agriculture will retire due to old age over the next 10 years For this reason, the need for aquaculture to move towards smart farming is becoming increasingly urgent Founded in 2014, Fongyu Corp Ltd has developed a unique eco-friendly farming model based on its own fish farming It uses AI knowledge-based fish farming to effectively increase aquatic product production by 10, and reduced labor cost by 15 The word "Fongyu" has a profound meaning "Fong" represents good mountains and "Yu" represents good water, and is the hope that companies will allow Taiwan to always have good mountains and good waterIt is also a homophone for "having a full figure," expressing the hope that products will give consumers a full and healthy body and mind The founder of the company, Liu Chien-Shen, has been through the difficult entrepreneurial journey of becoming an apprentice in fish farming, raising funds, renting fish farms, establishing a fish farming company, building a brand, and expanding sales Labor shortage and aging workers are hidden worries in the fish farming industry Currently, fish farms in Taiwan are still mainly traditional fish farms, and farming techniques are still passed down through word-of-mouth In addition, the labor shortage and average age of workers exceeding 60 years old has made it impossible to effectively stably improve productivity and yield This farming method makes it difficult to prevent and control diseases, and greatly increases the possibility of excessive use of drugs, environmental pollution, and water quality and ecological damage, creating a vicious cycle that lowers the quality of fish farming In addition, 651 of workers in Taiwan's fish farming industry are inadequately skilled With limited support from IoT sensors, traditional fish farmers still mainly rely on their own experience and knowledge for water quality management, feeding, and disease detection Fish farming management relies heavily on the ability of individual fishermen Once experienced workers retire, the industry will not only face the issue of succession, but also the difficult of stably supplying a certain amount of harvest that meets quality standards This may cause a dilemma for the entire industry from fish farming to sales In order to improve the pain point of inability to pass on experience in fish farming, and at the same time create a "digital" foundation for fish farming, the top priority must be to collect farming behavior data and develop AI services as an important starting point Fishery digital twin technology helps fishermen transition to smart farming With the assistance of the Institute for Information Technology III, Fongyu implemented the "fishery digital twin" technology to dynamically adjust the farming schedule In other words, the fish farming schedule is adjusted according to the species, habits, and variables of the fish The use of AI in fish farming not only effectively increase aquatic production by 10, but also reduced labor cost by 15 In terms of specific methods, we first digitalized the fish ponds, feed, and decision-making behavior for each species, such as sea bass and Taiwan tilapia, and recorded the seasonal temperature changes from releasing seedlings to harvesting, all of which were digitalized, gradually recording the experience and methods of experienced workers into a rich database Based on the recorded data, we analyzed the compound variables to find the best farming behavior and generate a dynamic farming schedule The records for each pool provide data on workers' experience However, fish farming behavior generally relies on rules of thumb Even experienced fish farmers cannot ensure that they will find the best solution Therefore, new methods are proposed to solve this issue That is, "to determine the best fish farming behavior by predicting the interaction with water quality and past data on feeding, and evaluating fish farming behavior based on water quality and fish farming," and provide fishermen with the most intuitive recommendations through daily schedules To continue optimizing the dynamic fish farming calendar on a rolling basis, iterations of the model will be developed through the three-step cycle 1 Input the current fish farming calendar into the model 2 The model predicts the future environment 3 Shortcomings of the fish farming calendar are corrected based on the future environment to obtain a new version of the fish farming calendar In the process, the experience of aquaculture experts is used to establish the causal relationship between fish farming behavior and the environment The establishment of a dynamic fish farming process and technology-based fish farming recommendation services provide a traceable and detailed fish farming process It is one of the few technologies that can digitalize fish farming Fishermen can quickly and easily record their daily behaviors to build knowledge without taking up too much time, but in the long run it can reduce labor cost by 15 and increase output and revenue by an average of 10 Smart fish farming has achieved outstanding results, reducing labor cost by 15 and increasing output by 10 At the same time, the fish farming calendar can also be extended to different aquatic species, such as white shrimp, milkfish, clams, and Taiwan tilapia, to produce fish farming schedules for ponds with different specifications, and the harvested aquatic species can be traced according to different specifications, establishing vertically integrated services for safe food products Fongyu's main products are divided into two categories One is aquaculture modules, including fry, feed, materials and probiotics, production planning and processes, and monitoring, which can be sold separately or exported as modules The high-quality aquatic products produced by Fongyu have repeatedly won awards Figure Fongyursquos official website The other category is high-quality aquatic products, including seabass fillets, seabass balls, oil-free seabass balls, seabass dumplings, and seabass soup The products have won various awards, including the top ten souvenirs in Pingtung in 2017, "Barramundi Fillet" won the 2017 Eatender of the Council of Agriculture COA, "Oil-Free Barramundi Fillet" won the 2018 Eatender Gold Food Award of the COA, and "Dumplings of Barramundi" and "Barramundi Broth" won the 2019 Eatender of the COA The consecutive awards represent that the "quality" of Fongyursquos aquatic products can be seen and eaten with peace of mind In addition, Fongyu has exclusive fingerlings that meet international needs, such as Pure seawater cultured tilapia fingerlings and seawater Taiwan tilapia fingerlings from selective breeding FY-01 are items that aquaculture companies in many countries are looking forward to The company also has aquaculture modules, disease monitoring tools, and feeding materials designed in accordance with the environment, in order to provide customers with more stable income

2021-09-28
【2021 Application Example】 HRT Technology Improves Production Efficiency by 20% Through AOI Detection of Defects in VCSEL Packaging

In 2017, the launch of the iPhone X made 3D sensor technology used in Face ID highly popular, which drove the development of VCSEL, a core component in the 3D sensor module In the detection of defects in incoming packaged VCSEL, the use of AI inference models can solve the industry's issue with low yield and improve reliability to 95 VCSEL technology currently can be used in many applications and various end consumer markets, including robots, mobile devices, surveillance, drones, and ARVR VCSELs are a good solution in applications that require high-speed modulation capabilities, such as cameras and biometrics VCSEL technology has a wide range ofnbsp applications, including in drones Pictured Zoyi Technology's Agricultural Drone VCSEL technology has a wide range of applications, AI technology assists in defect detection HRT Technology stated that the packaged VCSEL market is also facing strong price competition from competitors, and needs to further reduce costs and enhance product competitiveness One of the key problems is the replacement of glass lens with epoxy resin lens The production of traditional glass lenses has high yield, but the cost is higher than that of epoxy resin lenses Due to the cutting process of epoxy resin, the side wall of cutting lines can easily have rough edges, causing it to be oversized The release of stress caused by heat during the mounting process will directly cause the optical lens to break HRT Technology pointed out that the incoming inspection of VCSEL epoxy resin lenses is very important Under the constraints of packaging space, the space for fitting the package and optical lens is limited Moreover, the optical lenses will be confined to a metal frame If the dimensional tolerances are properly controlled, stress release due to heat during mounting can easily cause the optical lens to break, resulting in a yield loss of up to 10 in the VCSEL package reliability verification, resulting in an increase in production costs In order to solve the problems above, HRT Technology hopes to use AI to monitor the size and appearance defects of epoxy resin components in the VCSEL epoxy resin lens incoming stage, verifying whether their dimensions meet specifications, whether the cutting edges are smooth, and whether there are any defects in their appearance Since traditional incoming material inspection requires a rough visual inspection by humans to distinguish the quality The problem of image collection needs to be solved first to successfully collect image data Therefore, HRT Technology first developed an Automated Optical Inspection AOI device, which includes X, Y, Z three-axis motion, high-resolution cameras, and related control software to automatically record images After collecting the image data, opencv aligns the test image and a normal image to determine differences between the two images, and then pixel mapping is used to compare the pixel area to complete initial screening Manual labeling is carried out according to the image classification above, including samples that are normal, have defects in appearance, or have different shape characteristics, and then algorithm training and verification is carried out Residual neural network ResNet or other related algorithms are used for deep learning to identify the quality of lenses Implementation of AOI inspection improves production efficiency by 20 and above Comparing the differences before and after the implementation of AI image inspection, the incoming VCSEL lens inspection before implementation only involved manual inspection of the appearance The lens is packaged on the VCSEL package that has completed die bonding After passing the general light up test, the final reliability test high temperature reflow is performed Failed samples go into the rework process However, after the implementation of AOI inspection, it can screen defective lenses sooner and reduce the cost of subsequent materials input, it can also reduce the need for rework due to failure, improving yield to 95 and above in the reliability verification This is expected to help companies reduce production costs by 10 and increase production efficiency by 20 and above The difference before and after implementing AI image detection HRT Technology pointed out that this technology is an AI application developed based on tiny images It uses deep learning algorithms to identify defects in the images The trained network automatically classifies image data to predetermined categories Defect categories can be determined through reference images, so cumbersome programming is not required In the industrial machine vision environment, deep learning is mainly used for classification tasks in applications, such as inspection of industrial products or identification of parts In the future, with the development of IoT wearable devices and the trend of energy saving, the size of optoelectronic components will continue to shrink This technology can be applied to the detection of defects in the appearance of other tiny optoelectronic components in the future

2021-12-05
【2021 Application Example】 AI Complements the Disruption of Traditional Industry Experience: Production Forecast Analysis in Plastic Recycling Process

As the number of veteran craftsmen in traditional industries diminishes In Taiwan, SMEs have always played a central role in Taiwan's industry, accompanying Taiwan through various 'economic miracles' periods But as time progresses, the old masters gradually became elderly craftsmen Coupled with the phenomenon of fewer children and changes in the overall industrial structure, fewer and fewer of the new generation are willing to enter traditional industries Now, it can be observed that the main combination on most SMEs' operational fields is formed by 'elder craftsmen' together with 'foreign workers' These experienced craftsmen, who act as living dictionaries of field experience, suffer from a lack of successors to continue the tradition, leading to a growing difficulty in sustaining on-site experience transfer in traditional industries The limits of traditional hands-on process optimization are in sight Located in Tainan Baoan Industrial District, 'Tangxian Company' was established in 1972, initially manufacturing high-quality weaving equipment It possesses the capability to manufacture machinery, and in recent years it has actively developed environmentally friendly plastic recycling equipment in response to international green energy, recycling, and environmental protection demands Ultimately, they have successfully developed low energy consumption, low waste, high purity, and high output recycling granulators with a sleek and efficient machine design supplemented by advanced intelligent control technology Tangxian Company's self-developed plastic recycling granulator equipment However, in the production process of plastic recycling, when faced with hundreds of material types and dozens of process temperatures, speed settings, what is faced is thousands of possible parameter combinations Previously, the adjustment of various production process conditions was reliant on the on-site staff the experience of the craftsmen Thus, during the transition of production of different incoming materials such as PET, PP, PE, a significant amount of raw materials would be wasted during the trial phase The professional information gap in traditional industries Tangxian Company recognizes the importance of data In the past, although process parameters were recorded, due to a lack of data capabilities at the time, it was primarily in paper form, manually written down by the operating staff, accumulating a large amount of paper data However, this also meant a lack of scientifically accurate and detailed information available for real-time reference and adjustment Process parameters logbook, records the state of about a dozen machines and production figures hourly In quality control as well, due to a lack of control over the quality of output and monitoring and feedback mechanisms for unit time production, it becomes difficult to predict the profit conditions of each batch Production management can only estimate and average cost and productivity changes over the process from the outcomes, without being able to objectively and timely restore the production conditions to reasonableness or make clearer adjustments when facing quality abnormalities Site reality left image shows recycled scraps right image shows pellet production Taiwanese manufacturers possess strong machinery manufacturing capabilities, and many modern machines now have data capabilities, recording real-time status and information via IoT But is the infrastructure of the factory's on-site and information systems ready yet When the Old Master Meets AI With government referral, Tangxian Company partnered with a Taiwanese data science company, working together to integrate AI services and optimize internal processes using AI They started with a medium-sized plastic recycling production line within the factory as a trial field After establishing a successful benchmark, this model was expanded to larger plastic recycling machinery within the factory to continue verification and application Initially, both parties converted the past handwritten paper data into digital format using OCR supplemented by manual correction Tangxian Company also worked with the supplier of the human-machine interface of the machinery to integrate the control panel and parameter data into the factory's database, allowing real-time monitoring of machine status and eliminating the complexities and potential errors of manual transcription Panel of plastic recycling granulation machine, showing current process temperatures, speeds, and power usage Meanwhile, the Taiwanese data science company further modeled dozens of parameter data through AI, conducting scenario analysis to simulate various production possibilities under environmental parameters and material inputs, identifying key characteristic parameters and providing parameter adjustment recommendations to decrease costs during the trial phase Applying data analysis to traditional industry machinery processes After the old master receives the raw materials, they only need to enter the relevant material characteristic parameters, and the system automatically generates recommended process parameters After small adjustments by the old master, they proceed with the trial production of the material, effectively reducing the waste of materials, water, electricity, and manpower caused by incorrect attempts Moreover, Tangxian Company has proactively deployed the concept of 'production pedigree' in the plastic recycling process, allowing the batch's raw materials and process parameters to be accessed by scanning a QRCode Production and sales pedigree of plastic recycling pelletizing Taiwan's SMEs have strong machinery capabilities, just waiting for the 'east wind' of data From industrial revolutions 20 to 30, even 40, many Taiwanese SMEs face challenges in transitions not just in upgrading machinery, but after investing in modern equipment and generating data, they do not know how to utilize it effectively It is impractical for these manufacturers to develop a specialized data analysis department on their own meanwhile, Taiwan also has many innovative teams with strong software capabilities in AI and data analysis, possessing the technology but lacking the field and data Therefore, if the traditional industries of Taiwan could be fully integrated with the innovative teams in AI and data analysis, it would not only address the current challenges of manpower and experience transfer faced by traditional industries but also advance Taiwan's development and application of AI significantly「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

2021-01-21
【2021 Application Example】 AI Analysis Cloud Service Platform for Remote Sensing Big Data Enables the Smooth Application of Satellite Remote Sensing Images

Although satellite remote sensing images can make all surface objects visible, it still requires a lot of time and manpower to be truly applied to the industry In order to effectively solve the problems that customers face in digesting huge amounts of image data and eliminate technical obstacles for cross-domain users to process satellite remote sensing images, ThinkTron has developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" as a new beginning for cross-domain AI applications for spatial information In recent years, in response to the impact of industrial globalization, Taiwan's agriculture has continued to transition towards technology-based and higher quality, improving the yield and quality of crops by solving problems, such as microclimate impacts and pest and disease control The demand of agriculture on images has expanded endlessly to accurately grasp the growing environment of crops In the early years when UAVs unmanned aerial vehicles were not yet popular, manual field surveys were the most basic but most labor-intensive work With the emergence of UAV drones, aerial photography operations might not be difficult, but the range that can be photographed is limited Furthermore, surveying expertise is required to accurately capture spatial information At this time, the use of satellite remote sensing data may break away from the past imagination of using image data Taiwan Space Agency TASA ODC data warehouse services In the past ten years, with the breakthrough of modern satellite remote sensing application technology, Digital Earth has become a new trend in global data collection Countries have developed data cube image storage technology, and the development of smart agriculture has become one of the largest image users Determining planting distribution is the first step in understanding crop yields Free satellite remote sensing images, powerful data warehousing support, and the team's robust image recognition technology are important supports for accelerating agricultural transformation Using satellite remote sensing image data can accelerate the development of smart agriculture However, in the past, it was difficult to extract large-area crop distribution through satellite remote sensing images, not to mention the cost If you wanted to use free information, you had to visit all websites of international space agencies, look through the wide variety of satellite specifications, and carefully evaluate the sensor specifications, image resolution, and revisit cycle After finding suitable images, you had to look at them one by one to filter the ones you need Next is downloading dozens of images that are often several hundreds of Megabytes MB each, which might exceed the capacity of your computer Also, after overcoming image access and preparing data, you must then start to confirm the downloaded image products and which bands you want, because the image you see is not just an image file jpg or png, but rather complex multi-spectral information, attribute fields and coordinate information It takes a lot of effort just to confirm the correct information Facing GIS software packages with complex functions is the start of another trouble The complex image pre-processing process and the inflexible machine learning package greatly reduce the efficiency of analyzing data After finally getting the results of crop identification, you might find that the best time for using map information may have already passed The above-mentioned complex and time-consuming satellite image processing problems are precisely the pain points of the market ThinkTron expanded from traditional machine learning to modern deep learning applications, and developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" under the GeoAI framework, breaking through the constraints of details in the spatial information for customers Differences between the process before and after introducing the AI analysis cloud service platform ThinkTron said that Taiwan's ODC Open Data Cube system has been completed and began providing services after years of efforts from the Taiwan Space Agency TASA, formally becoming aligned with international trends The powerful warehousing technology allows users to easily capture and use image data of a specific time and spatial range according to their needs The warehouse stores multiple satellite image resources from international space agencies, including the ESA's Sentinel-1 one image every 6 days, Sentinel-2 one image every 6 days, USGS's Landsat-7 one image every 16 days, Landsat-8 one image every 16 days, and the domestic Formosat-2 one image every day and Formosat-5 one image every 2 days ThinkTron develops satellite image recognition tools based on Python Breaking free from the limitations of GIS Geographic Information System software packages, ThinkTron integrated GDAL Geospatial Data Abstraction Library based on Python, and considered computing efficiency and parallel processing when developing all tools required for satellite image processing and image recognition modeling, including coordinate system and data format conversion, grid and vector data interaction, and data intra-difference and normalization All of the tools are designed with AI applications in mind, and some commonly used tools are packaged into an open source package under the name TronGisPy to benefit the technical community ThinkTron utilized the team's understanding of satellite remote sensing images and the collected tagged data crop distribution maps to preset the image recognition modeling process, the required training data specifications, and dataset definitions This is imported into the machine learning LightGBM or deep learning CNN framework that was completed in advance, and the entire training process to be performed in the Web GIS interface, providing users with partial flexibility to freely filter images, confirm spatial and temporal ranges, select models, and adjust hyperparameters In addition to the operation of training models, it also provides historical models to output identification results, and finally displays the identification results of crop distribution on the Web GIS map In fact, agriculture is not the only industry that needs satellite remote sensing applications AI applications of spatial information have also appeared in various fields as companies in different industries aim to enhance their global competitiveness For example, surveying and mapping companies that have a large amount of map data can use the AI analysis cloud service platform to store map data while also accelerating the efficiency of digital mapping Under the severe global climate change and the risk of strong earthquakes, there is a wide variety industrial insurance, agricultural insurance, financial insurance, or disaster insurance are all inseparable from spatial information The use of remote sensing image recognition to understand insurance targets has long been an international trend AI Analysis Cloud Service Architecture for Remote Sensing Big Data

2021-11-28

Records of Application Example

【導入案例】「展覽自動配對系統」對準目標客群行銷效益高
【2020 Application Example】 The "Automated Exhibition Matching System" is highly effective in targeting customer groups for marketing!

Of the hundreds of activities, which one is your favorite There is a wide variety of activities every day in Taiwan, including forums, exhibitions, lectures, and free experiences Event organizers need to use their own media event official website, Facebook, Instagram, event websites, and pay media for marketing, but often do not know where the target customer is, and cannot accurately estimate the number of attendees Records of people's participation in various activities are used through this "Automated Exhibition Matching System," and the data is analyzed to predict what type of activities users like It automatically matches activities with users to provide fast, easy, and accurate marketing and promotion methods There are many types of activity themes, marketing and advertising costs are high, but results are poor A domestic curation company is working with township offices and tourism service providers in the marketing of rural villages It organizes a variety of activities every year, such as agricultural product exhibitions, rural experiences, parent-child themed experience days, and agricultural specialty product marketing Due to the vastly different characteristics of participants in the activities, which have different themes, effective and accurate market cannot be carried out when promoting the activities, which can easily lead to a significant increase in marketing expenses and low matching rate For example, when the curator organizes an exhibition with 200 booths in the venue, the overall marketing cost is about NT800,000 to NT12 million, in which construction of the official website, marketing on the event website, and text message notifications account for about NT400,000 to NT600,000, but the event's matching rate is less than 20, and precision marketing aimed at the target customer group cannot be carried out After adopting the "Automated Exhibition Matching System," it can automatically select suitable customer groups for push notifications Depending on the scale of the event and the exhibition period, the system rental fee is only about NT200,000 to NT300,000, significantly reducing event promotion costs Precision smart marketing, distributing coupons to target groups The "Automated Exhibition Matching System" currently has an accuracy of 82 and can effectively screen target consumers In terms of module accuracy, large amounts of data and data that no longer contains noise will be used to further improve the accuracy in the future Coupons will be distributed to target groups, so that groups that receive the coupons will actually participate in the event After adding value through AI, the system can replace the manual random distribution of coupons without a specific target The AI module can automatically adjust the weights to more accurately lock on to the target group The weighted formula uses the CRM system of the curation company to output analysis of member behavior in the past In the second stage, the AI weighted formula will be used to find the best calculation formula for different activity categories through automatic correction Service Framework of the Automated Exhibition Matching System During the implementation period, Fengchun Technology was troubled by the problem of "the AI classifier module training and learning not finding the best solution" After discussions with AI engineers, the company found that a shortcoming of "back-propagation neural network" is that it only finds the "local" best solution rather than the "global" best result during learning The goal of improving accuracy can be achieved by increasing the number of training times and adjusting parameters Expand system functions, connect member databases, and conduct behavioral analysis The "Exhibition Event Matching System" mainly provides event organizers, independent curators and the public with event matching Next, the platform functions will be expanded for use by event participants, and the accuracy of the AI classifier will be improved In the future, an ocean culture exhibition will be organized with the ocean industry, and use this system to find ocean culture promoters, connecting and expanding member databases for behavioral analysis

【導入案例】「AI麵包辨識系統」,機器一掃,價格瞬間幫你算好
【2020 Application Example】 AI Bread Recognition System, machine scans, and the price is instantly calculated for you!

A brilliant idea transforming AI facial recognition technology As artificial intelligence develops, more and more industries are embracing AI technology, even subtly entering into people's lives As most bakeries sell freshly made bread and pastries, which typically do not have barcodes, they rely on cashiers to visually identify each item and enter the type and price of the bread Thus, inspired by AI facial recognition technology, if such artificial intelligence could identify hundreds of types of bread, it could enhance checkout efficiency Diverse handmade breads delight customers but challenge clerks A local bakery has over 100 types of bread, regularly updating or adding new products, offering customers a variety of choices this poses a challenge for cashiers It takes two months to train a cashier, but even after they start, there's still a 5 to 10 error rate due to bread recognition mistakes each month, especially during peak checkout times after work, causing bottlenecks and further errors due to the stress on cashiers The difficulty in training cashiers and the lack of precision in the checkout process have long troubled businesses When baking meets artificial intelligence, it sparks a marvelous retail experience In typical bakeries, bread is sold 'naked' immediately after baking and then 'packaged' when it cools to room temperature Both methods require cashiers to recognize and remember the prices and undergo two months of training before they can work the cash register Even then, there is still a 5 to 10 error rate each month My Dee Bakery, with its extensive range of over 100 bread types, poses a significant challenge for cashiers Due to Yun Kui Technology Co, Ltd's expertise in developing iPad POS systems, which are designed to be simple, convenient, and easy to use, they allow businesses to check out efficiently and accurately Therefore, integrating the existing POS system with AI image recognition capabilities enables businesses to carry out transactions more efficiently and precisely AI bread recognition model operational schematic Image provided by Yun Kui Technology The execution can be simplified into eight steps, which include 1 Data collection Take bread image data at bakeries 2 Image annotation The image data is handed over to Mu Kesi Co, Ltd for manual annotation 3 AI modeling and training Managed by Mu Kesi, who adjusts AI models and training 4 iPad POS adjustment Simultaneous adjustments of the UI interface on the POS side and backend integration with the AI model 5 Start testing Once Mu Kesi reaches over 95 recognition accuracy with current data, formal integration testing begins 6 Real scene testing Move to the bakery to gather data and verify the correct recognition rates 7 Planning real scene application accessories When recognition accuracy exceeds 98, design accessories for on-site checkout, such as remote cameras and projection light sources 8 Official Application Integration with electronic receipts goes live POS machine AI bread recognition checkout process Start recognition - Recognition complete - Checkout - Confirm checkout, takes only 3 seconds Image provided by Yun Kui Technology AI bread recognition system, making multitasking easy After adding AI capabilities, not only can it save upfront training time and costs for bakery cashiers and reduce costs from recognition errors, but it can also speed up the checkout process and efficiency, increasing customer satisfaction This can later be promoted to various retail industries, expanding the new map of smart retail Before and after comparison chart of the bread checkout process with AI valuation Image provided by Yun Kui Technology「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】「AI智能廁所品質監控平台」,降低客戶對廁所髒亂申訴次數及提升人員調度有效性
【2020 Application Example】 AI Smart Toilet Quality Monitoring Platform, reducing customer complaints about dirty toilets and enhancing staff scheduling effectiveness

Best practices in AIIoT implementation As our country enters the first year of 5G commercialization this year, the integration of the Internet of Things with artificial intelligence to transmit data with zero delay will enable everyone to effectively manage all data Toilet 'odor monitoring' has become the best platform A certain chain supermarket in the country has 47 stores nationwide and in recent years, as competition in the supermarket industry intensifies, some stores plan seating areas and toilets for customer use Currently, the average number of customer complaints about toilet cleanliness in a certain store of the chain supermarket is about 10 times per month, which is notably higher than other stores, thus they hope to solve the problem of high complaint rates through artificial intelligence Customers frequently complain about dirty toilets The toilets of a certain store of the chain supermarket are inspected at 12 PM and 6 PM daily, and cleaned during the night shift Customer service staff often receive complaints about the dirty and smelly toilet environment, causing the need to constantly deploy manpower for toilet maintenance To achieve a 100 odor-free toilet, it would be necessary to employ a cleaning staff member permanently present in the toilet, however, this solution is too costly and wastes manpower Through a collaboration between Guo Xing Information Co, Ltd and the chain supermarket, the National Taichung University of Science and Technology AI team was commissioned to address this vexing issue using IoT and AI technologies IoT Monitoring x AI Manpower Dispatch Guo Xing Information equipped the toilet door locks with IoT sensory devices, and installed 'odor sensors' and 'air temperature and humidity sensors' outside the cubicles By monitoring the behavior, frequency, and timing of door usage, it predicts the cleanliness of the cubicle If a person opens the toilet door and closes it quickly, and if more than three consecutive people exhibit the same behavior, it predicts that the cubicle is dirty enough to require cleaning In terms of manpower dispatch, the system predicts staffing needs based on user frequency, holidays, and festive events, dynamically adjusts manpower reserves, and calculates the minimum staffing needed to maintain toilet comfort Service architecture of the Smart Toilet Quality Monitoring Platform This 'Smart Toilet Quality Monitoring Platform' is installed in the open-area toilets of business premises, collecting data such as usage frequency, time, odor intensity, air temperature, and humidity, and transmitting it to the platform for AI data analysis This enables management to understand the real-time usage, frequency, and dirtiness of the toilets, providing alerts to dispatch cleaning staff and take responsive actions It also assists managers in environmental quality monitoring and dirty conditions predictive dispatching Through historical data analysis, it suggests dynamic manpower deployment during different time intervals for effective human resource management and utilization Smart toilet detection, reducing cleaning labor costs After field tests of the Enhanced AI Smart Toilet Monitoring Platform, the retailer found the real-time monitoring and alert features extremely practical and is willing to continue using them Regarding 'reducing the number of complaints', a one-month data validation showed a significant effect, while 'dynamic manpower dispatch' is still under evaluation and validation After a month of data evaluation, a noticeable improvement was found in 'monitoring toilet usage' and 'reducing complaints' After trial use by the retailer, they are also willing to continue using the system In the future, notifications will be made according to 'usage time' to prevent accidents within the cubicles There will also be future deployments and promotions priced at low, mid, and high levels「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】AI抗疫 武漢肺炎檢疫 效率提高6倍
【2020 Application Example】 AI Fights Pandemic: 6 Times Efficiency Increase in Wuhan Pneumonia Quarantine

Combatting the epidemic is like fighting a fire With the increasing influx of returning residents, the pressure of Wuhan virus quarantine is mounting, consuming more time Shortening quarantine times will positively benefit disease prevention efforts At a hospital in Southern Taiwan, the 'Smart Medical Clinical Decision Support System' has helped reduce the time taken for high-risk patients from entry at the quarantine station to clinical decisions by doctors It originally took about 2 and a half hours, but now it's down to less than 30 minutes, increasing the quarantine efficiency by 5 to 6 times and significantly reducing the risk of cross-infection between medical personnel and patients, as well as the manpower needed for quarantine As waves of overseas students densely return to Taiwan, not only the Central Epidemic Command Center, but also various medical institutions are tightening up, closely monitoring every quarantined individual There are also concerns about the potential infection risks to colleagues, which is exhausting At this point, employing AI technology to enhance quarantine efficiency is indeed a great blessing for the medical units and the health of the nation AI-Assisted Medicine Multiplies, Becoming a Hero in Pandemic Control To combat the severe pandemic of novel coronavirus, the hospital has integrated various smart medical techs and developed the 'Smart Medical Clinical Decision Support System', raising quarantine efficiency by 5 to 6 times It has shortened the time taken for high-risk patients from entering the quarantine station to doctors making clinical decisions from 2 and a half hours to less than 30 minutes, effectively reducing the risk of cross-infections The 'Smart Medical Clinical Decision Support System' implemented by the hospital includes three components front-end automation of medical records, AI-assisted interpretation of chest X-rays for diagnosing pneumonia, and continuous updates of clinical decisions based on the latest epidemic data provided by the health department This significantly enhances the hospital's response and decision-making ability in quarantine and epidemic prevention, and greatly benefits Taiwan's anti-epidemic efforts through the multiplicative effect of AI-assisted medicine National Cheng Kung University collaborates with the hospital, using smart medical technology to enhance quarantine efficiency Photo source Official website In the aspect of medical record automation, existing medical institutions often use traditional paper or verbal reporting, which potentially increases the risk of contact infections among medical staff and patients The automated medical records system in this hospital allows patients to fill out their own medical history, including travel, occupation, contacts, and clustering, using tablet computers These records are uploaded to the electronic medical record system, enabling immediate access by medical staff to make clinical decisions Each tablet is disinfected with alcohol after every use, reducing the risk of cross-infection and enhancing the efficiency of the quarantine station The hospital's Wuhan pneumonia screening shows a sensitivity and accuracy of up to 80 and 90, respectively The 'Chest X-Ray AI Interpretation for Pneumonia System Model' developed by the hospital's Department of Radiology, with active participation from Professor Yong-Nian Sun's team at the College of Electrical Engineering and Computer Science Utilizing a tuberculosis X-ray AI auto-interpretation model developed by a previous AI biotech medical innovation research center project, it was adapted to the hospitals' pneumonia imaging data The collaboration between the parties ensured rapid completion Currently assisting in over 152 suspected Wuhan pneumonia screenings, sensitivities and accuracies of up to 80 and 90 have been achieved, respectively Moreover, for students conducting in-home quarantine at school dormitories, the university has adopted a smart monitoring approach with a 'Warm Heart Smart Bracelet' developed by a cross-disciplinary team, which continuously monitors quarantined individuals' body temperatures and heart rates as indicators for predicting symptoms When a rise in body temperature is detected, individuals can proactively confirm abnormal symptoms via a smartphone app and be prompted to seek medical attention Currently, bracelets are collected weekly and data is centrally uploaded to a cloud platform by the management staff for ongoing tracking, wholly enhancing the level of pandemic control internally and externally The university's cross-disciplinary team uses 'Warm Heart Smart Bracelets' to implement home quarantine policies effectively Photo source Official website「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】紡織業挑戰快時尚,AI庫存預測降低三成五誤差率
【2020 Application Example】 Textile Industry Challenges Fast Fashion, AI Inventory Forecast Reduces Error Rate by 35%

Fast fashion in clothing, small quantities, diverse styles, short delivery times The textile industry faces the impact of the fast fashion trend among clothing brands, affecting the entire supply chain Global brand channels are promoting zero inventory, short delivery periods, and small-scale customization Balancing production time, quality, and cost is challenging Often, there is a discrepancy between ODM predictions and actual demands from brand owners, causing issues in material management and excessive inventory costs Due to inaccurate demand forecasts from customers, it often leads to difficulties in material preparation Excessive materials can increase leftover stock, while insufficient materials may delay delivery This project aims to establish an AI-based material demand forecast model specifically for major domestic manufacturers AI calculates sales trends to further predict demand The advisory team collaborates with Shentong Information Technology to mainly use the LSTM algorithm for the AI foundation The goal is to predict the next sales cycle based on past sales records, utilizing simple regression to complex 'Time Series Analysis' in statistics Usually, a period's sales volume closely relates to the previous period's, unless there is a major event, in which case it would typically follow a pattern There are various patterns of sales volume forecasts, including revenue, profit, customer counts, park visits, sales numberamount, etc This will take the example of a factory's monthly shipment batches, using the LSTM model to predict the next month's shipment batches Material Demand Analysis Execution Framework This project plans to establish a customer-specific material demand AI prediction model During the planning phase, three different machine learning algorithms were used to prototype the AI model Logistic Regression Algorithm Gradient Boosting Algorithm Deep Learning Algorithm Material Demand AI Prediction Model Planning Demand forecast error reduced from a maximum of 70 to 35, significantly reducing inventory volumes This project estimates customer demands, required material types, supply sources, and customer delivery dates using machine learning to establish a primary material procurement prediction system It reduces the prediction error of demand from the top five international customers from a high of 70 to 35, significantly lessening the amount of inventory needed「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】RPA機器人,加速15倍電商工作效率
【2020 Application Example】 RPA Robots, Accelerating E-commerce Work Efficiency by 15 Times

Labor-intensive, prone to oversights and errors, low shipping efficiency A domestic hook-and-loop tape traditional manufacturing transformation and brand management company has expanded new markets and business opportunities through the e-commerce platform model This requires reliance on substantial labor for product listing, order organizing, inventory management, and shipment tracking This results in limited product varieties and quantities that can be handled, and manual data entry is often prone to oversights or errors, affecting shipping efficiency and customer satisfaction, which is critical for the competitive advantage of the business in e-commerce Internally, many operations rely heavily on repetitive tasks across various computer systems, web pages, emails, etc Currently listed on 15 e-commerce platforms, updating single e-commerce information alone requires 2-3 months over 200 items, making rapid expansion difficult limited by manpower, product information is not detailed enough, leading to doubts in e-commerce reviews, affecting orders and subsequent satisfaction Presently, orders are only confirmed once a day, leading to an information gap of up to 24 hours Annually, there are over ten thousand orders to process into shipment orders, typically accumulating for 15-30 days before once grouping deductions from inventory, resulting in always inaccurate stock levels Streamlined Client Interface, Accelerating Implementation Efficiency The mentoring team collaborates with Ruijing Engineering Technology to integrate AI and RPA technologies through a web-based architecture Robotic Process Automation RPA applications are not installed on the local desktop but are stored on a server and accessed only when needed by the user This technology, known as Thin Client, provides higher performance and security compared to the Thick Client, which requires downloading applications and data to the local desktop The Thin Client does not require downloads on the local machine RPA collaborative service features include Web Scraping Complex web data collection and arrangement Email manipulation Data analysis and disassembly of content and attachments Web operation Precise and rapid web operations or filling in specific fields Application operation Timed positioning operations of other window applications Data processing Data format conversion, decomposition, and reassembly File Exchange Management Timed file production, adddeletemodify, FTP uploaddownload Database operation Heterogeneous database data exchange, read or write to a specific DB Data recognition Fixed format field data processing screenshot, snapshot, alphanumeric text parsing and recognition Scheduling Can be timed, repeated, cross-process all the above processes Alert mechanism Email, Line Notification etc designated or broadcast notification Software Robot Technology Solution Execution Architecture AI software robots enhance the processing speed of orders, inventory management, and purchasing in manufacturing operations, developing automated services to avoid data duplication and input errors, and seamlessly integrating processes across systems operating 247 The war room panel facilitates statistical analysis and real-time sales conditions on each e-commerce platform, predicting and optimizing product inventory Direct Purchase Order Process Automation Robot E-commerce Information War Room Statistical Analysis Dashboard Software Zero Errors, Reducing Costs by 15 to 90 面對快速變化又競爭激烈的市場環境,更需要減少重複性、低產值的工作,將人力運用在更高價值的工作上。 Facing a rapidly changing and highly competitive market environment, it is essential to reduce repetitive, low-value tasks, focusing manpower on higher-value work RPA software robots are 15 times more efficient than indirect staff, also enhancing process quality to near-zero error rate execution quality, offering opportunities to reduce costs by 15 to 90 Since it doesn't require significant changes to existing workflows, businesses generally do not need to spend substantial manpower on retraining or adapting to new workflows, which contributes to a higher acceptance rate among businesses Even in software deployment, it only takes about 4-5 weeks to go live「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】AOI封銲製程全面檢測AI化,減少50篩檢量
【2020 Application Example】 Full Inspection AI Implementation in AOI Sealing Process, Reducing Screening Volume by 50%

Miniaturization of products, client demands full inspection A listed electronic component manufacturer in Taichung, responding to the 5G era injecting new growth momentum into the quartz component industry, especially under the explosion of 5G opportunities, the importance of quartz components will play a more crucial role than in the past in consumer products As frequency components move towards miniaturization and at the same time demand high precision, the manufacturing processes are more susceptible to subtle factors, necessitating manufacturers to manage comprehensive data across all aspects including human, machine, material, method, and environment to quickly identify key defective factors in complex production environments Differing perceptions of defects, difficulty in enhancing quality consistency With the trend of miniaturization and complexity of electronic components, visual inspection on the production line has four main functions including measurement, identification, positioning, and inspection, with inspection being the most challenging part as most electronics manufacturers still rely on traditional manual visual inspection Taking the PCB industry, where Automated Optical Inspection AOI technology has the highest penetration rate, as an example, a research institution once investigated and found that when two individuals inspect the same PCBA board four times, their mutual agreement rate was less than 28, and the self-agreement rate was only about 44 Due to differing perceptions of defects among on-site personnel, even automated machine vision can still lead to inconsistencies in product quality due to system settings or differences among quality control staff 偲捷科技檢測AI化,降低過篩率2030 With the support of the advisory team, collaboration with Sijie Technology aimed at the defects in the sealing process Based on CNN Convolutional Neural Network, the integration of multiple models introduced an AI recognition module to aid in the optimization of subsequent AOI tests, aiming to improve the accuracy of inspection equipment It is estimated that after introducing AI visual recognition, the over-screening rate could be effectively reduced to 2030 Thus, the industry, needing smarter inspection systems, has started applying AI technology to assist AOI equipment in optimizing subsequent screening tests AI-powered AOI Inspection Solution Cross-Model Design Concept Sealing AOI Inspection Trial Results Reducing false rejects, cutting manual screening workload by 50 The project, through a deep learning network architecture, reclassifies defects detected including true and false defects, and further classifies them to reduce the false reject rate of the traditional AOI solution This is anticipated to further aid manual inspectors in reducing more than 50 of the inspection screening volume, addressing current production line issues of relying heavily on manual re-inspection and low efficiency Future goals include integrating robotic arms for automatic loading and unloading, and analyzing defect causes to optimize production process parameters「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】處方箋智慧辨識 社區藥局藥師的小幫手
【2020 Application Example】 Intelligent Prescription Recognition: A Helpful Tool for Community Pharmacy Pharmacists

AI is thriving in healthcare services, where pharmacists in community pharmacies are essential for providing drug knowledge and pharmaceutical services However, these pharmacists often spend much time manually processing prescription entries into systems, which takes away from the time they could spend on drug education, medication effectiveness tracking, and other professional services How can AI help community pharmacies to support pharmacists Tedious, time-consuming, and repetitive tasks, and AI solutions Pharmacy operations are under threat from new market dynamics and limited profit-making modes, making digital upgrades challenging for single-pharmacist community pharmacies Pharmacists, taking on multiple roles to understand the health levels of community residents, face tedious, time-consuming, and highly repetitive tasks that hinder the quality of service and make it difficult to respond to customers non-stop all year round Smart Pharmacist Assistant Service Platform Enabled by Jiankangli Technology's smart pharmacist assistant service platform's system architecture, paired with the mobile application 'Smart Good Doctor' and the backend system 'Smart Good Pharmacist', along with the integration of external development feature resources 'OCR Prescription Recognition' and 'RPA Process Automation Training Module RPA library' Primarily applied in clinics and pharmacies at the primary healthcare level, this aims to solve various operational challenges and pain points It includes using digital technology to improve work efficiency, bridging the gap between the public and medical institutions, enhancing the medical relationship, achieving better operational and manpower benefits Additionally, it enhances medication safety for the public and improves their knowledge on medications, while also reducing the daily burden on pharmacists in pharmaceutical services Smart Pharmacist Assistant Project In the current stage, the Institute for Information Industry's team is guiding the integration of pharmacy information system vendors with AI startups, focusing on the development of intelligent prescription image recognition technologies, along with drug image recognition and smart drug scheduling reminder technologies as key research areas This has led to the implementation of practical deployments in 12 community pharmacies in Greater Taipei With the help of the Taiwan Young Pharmacists Association in promoting these technologies, over 100 community pharmacy proprietors have expressed interest in adopting such technologies Once the integration of these service platform systems is complete, it will become a model for promoting AI services in Taiwan's community pharmacy pharmaceutical services「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】AI助被動元件建構最佳AOI參數模型,降低過篩元件生產成本,年省250萬元
【2020 Application Example】 AI Helps Establish the Best AOI Parameter Model for Passive Components, Reducing Production Costs of Over-Screened Components, Saving NT$2.5 million Annually

Traditional AOI uses limited sample images for inspection, facing the problem of high over-screening rates In the electronic component manufacturing industry, AOI Automated Optical Inspection equipment is often used to measure defects in product appearance For a long time, AOI measurement equipment has used limited sample images in image processing to compare the appearance of products from different external light sources and angles This comparison method can automatically screen for defects in product appearance However, due to current technical limitations, there are often problems with light source parameter adjustment between product batches If an inexperienced technician handles these adjustments, it will lead to a decrease in machine utilization rate and high over-screening rates The maturity of AI image machine learning has brought new opportunities for the AOI process In terms of Taiwan's passive components, chip resistors and MLCC currently rank in the top two worldwide in terms of market share in 2019 In the long term, various car manufacturers have launched electric vehicles and smart vehicles, and various countries have also developed 5G-related equipment, which will further increase future shipments of passive components Therefore, besides expanding new product lines, how to help existing products enhance their competitiveness will be the key to the industry's future international competition AOI inspection is one of the common stations in the passive component process, limited sample images are used in the current stage to compare the appearance However, when switching between product batches, there are often problems with light source parameter adjustment, and the condition of these adjustments will affect the over-screening mis-screening of good products in each batch In each batch of defective products in the industry, on average over-screening mis-screening occurs 20 of the time Relying on the guidance capabilities of the Southern Taiwan Industry Promotion Center, which has been deeply involved in Southern Taiwan for more than a decade, the company was matched with the AI image recognition technology unit of the Industrial Technology Research Institute ITRI to address the pain points of the passive component industry, reducing over-screening in the AOI process and also reduce errors caused by manual adjustment Using image recognition technology to reduce the occurrence of AOI over-screening The technical unit of the ITRI that participated this time used image recognition technology to develop AOI technology for passive component processes in the establishment of AI modules In the development process, the company in this case first provided product appearance images and corresponding adjustment parameters, and then used the adjustment logic of current production line personnel to construct a product data set and further establish an AI model When planning the production line test, the first priority is image recognition rate Image detection and tag search are combined with comparison by an AI module to output AOI adjustment parameters for reference by online personnel Image analysis diagram In the future, we also hope to use the help of machine learning to complete the AI learning curve for machine parameter adjustment, further reduce the over-screening rate of product appearance defect detection, simultaneously solve the gap in on-site professional and technical talent, and increase product yield Scenarios before and after implementing machine learning Implementing AI applications in processes to lay the foundation for developing unmanned factories In the future, we hope the guidance of AI HUB will accelerate the application of advanced process technology and establish AI indicators for each station of the passive component process, which will help domestic production of high quality passive component products and increase product yields and prices It will use innovative thinking to increase the added value of the industry and continue to lead the passive component industry forward

rows
Rows:73, 9 pages