:::

【2020 Solutions】 'Knowledge Graphs' create health education angels, answering all questions faced during pregnancy

Artificial Intelligence (AI) is evolving rapidly. Traditional scripted response smart customer services are no longer sufficient. Emerging from this is the use of Knowledge Graphs in smart assistants. Through knowledge graphs, these smart assistants can provide exhaustive, tailored customer service, helping consumers efficiently and effortlessly find their desired products. The most common AI applications in daily life are smart customer services or smart assistants. For smart customer services, the aim is mainly to address customer inquiries, but they often face the issue of providing too generic and rigid responses, lacking flexibility.

Utilizing knowledge graphs to establish smart assistants

To develop a smooth-questioning smart assistant, it's crucial to optimize technologies such as natural language processing, semantic analysis engines, multi-turn dialogues, context awareness, emotion recognition, and personalization. Supported by the Economic Ministry's Technology Department, the Institute for Information Industry’s Service Innovation Research Institute has developed tools for domain knowledge construction and management. These tools assist in transforming corporate websites, databases, and documents into corporate knowledge graphs using AI recognition models. When used in smart customer service, if the customer query is vague, it can proactively ask follow-up questions based on the knowledge graph and provide precise answers through multiple dialogue rounds, saving on professional labor costs and response time, and delivering better consumer service experiences. Chen Bing-Yi, head of the Institute, points out that simple smart assistants operate by connecting to fixed APIs and responding based on predefined data formats, which is straightforward for queries like tracking shipments through Line or Facebook Messenger. However, for more flexible customer issues such as cancer insurance clauses, credit card application terms, or legal advice, more complex technologies are required. Technically, AI must convert unstructured data from documents, websites, or even social media into patterns that computers can understand, i.e., establishing corporate knowledge graphs. In simple terms, knowledge graphs are primarily built by extracting all significant texts and marking the relationships between them, automatically creating relational graphs among all individuals, events, and objects. For example, the computer can extract and determine the relation between Nantou and Oolong Tea as 'Origin' from social data, and link 50 Lan's products to Oolong Tea as 'Product'. Once a consumer wishes to know 'Where does 50 Lan’s Oolong tea come from?', the system can infer using the knowledge graph and provide 'Nantou' as the response, making customer service smarter and more professional. Additionally, smart assistants no longer passively receive queries; they can actively notify and remind consumers, for instance, notifying pregnant women of important prenatal tests they need to undergo through Line and Facebook Messenger, ensuring no tests are missed and enhancing safety. The smart assistants developed by the Institute are being progressively applied across retail, finance, and medical sectors including applications such as querying credit card benefits, product specifications, and medical education advice, with several companies already having successfully implemented these practices. Plans are in place to integrate external social data or open up knowledge graphs for future development, continuing to collaborate with partners to advance the application of knowledge graphs in various new forms of AI services.

Applications of Knowledge Graphs: Health Education Angel Chatbot

New mothers often face a multitude of questions during pregnancy, such as morning sickness, diet, fetal health, and prenatal check-up considerations, affecting their sleep, personal health, and potentially impacting fetal health. The Service Innovation Research Institute, in collaboration with Hua Xin Health Technology, uses AI technology to process health education manuals from the Ministry of Health and Welfare and community discussion articles. This initiative aims to build a Health Education Angel using natural language processing and knowledge graph technologies specifically for addressing various issues encountered during pregnancy.

The institute and Hua Xin Health Technology have collaborated to develop the Health Education Angel chatbot to answer various questions during pregnancy.

▲ The institute and Hua Xin Health Technology have collaborated to develop the Health Education Angel chatbot to answer various questions during pregnancy.

If there are questions related to prenatal examinations, they can be inquired through 'Prenatal Examination ABC', where the system will provide information about whether certain prenatal tests are chargeable and the diseases they can screen for. If there are concerns regarding dietary and health status during pregnancy, 'Pregnancy Encyclopedia' can be utilized. By posing questions in natural language, the system will offer the most relevant expert answers. Additionally, information about valuable pregnancy resources and welfare assistance is available for pregnant mothers to consult.

The Health Education Angel can pose questions in natural language, and the system will provide the most relevant expert responses.

▲ The Health Education Angel can pose questions in natural language, and the system will provide the most relevant expert responses.

「Translated content is generated by ChatGPT and is for reference only. Translation date:2024-05-19」

Recommend Cases

【解決方案】小柿智檢 以「AOIAI」雙劍合璧,軟加硬體千錘百鍊 打通外觀瑕疵檢測任督二脈
Xiaoshi Intelligent Inspection uses the two swords of "AOI + AI" to combine software and hardware to open up the two channels of appearance defect detection and supervision.

Quality inspection, like a double-edged sword, has always been a favorite and painful subject for Taiwanese manufacturers When AI deep learning enters the industrial visual inspection of traditional manufacturing industries, it can not only save inspection manpower investment, solve the problem of inconsistent manual visual standards, overcome the limited visual recognition and defect detection blind spots of traditional automatic optical inspection AOI, and also enable real-time traceability Causes of quality problems The overall AIAOI visual inspection solution developed by Xiaoshi Intelligent Inspection integrates software and hardware to create efficient appearance defect detection capabilities, helping electronics OEM customers create high-efficiency products with a miss detection rate of less than 1 and an overkill rate of less than 3 Check the level Xiaoshi Intelligent Inspection was established in 2020 Although it is a new venture two years ago, it did not start from scratch Founder and CEO Hong Peijun and the core team have been deeply involved in Foxconn factories for many years and participated in countless smart factory-related solutions and process improvements , has profound AI deep learning development capabilities, and accumulated rich experience in world-class AI application implementation Seeing that AI industrial inspection must be the last mile for the manufacturing industry to move towards Industry 40, Hong Peijun resolutely decided to implement AI deep learning technology in the field of smart manufacturing with high output value, and specialized in the development of AI industrial visual inspection For the manufacturing industry, product inspection is the most important part of all quality control, but traditional industrial inspection faces two major pain points 1 Manual visual inspection Today, more than 95 of the entire manufacturing industry still relies on manual visual inspection Inspection makes it difficult for manual visual quality inspection standards to be consistent, and visual inspection of fine objects, such as passive components or highly reflective components, will cause long-term vision damage 2 Traditional AOI automatic optical inspection The product has limited visual recognition capabilities and blind spots in defect detection Among them, the detection of appearance defects such as scratches, oil stains, dirt or hair and other unexpected subtle defects has always been a problem in AOI applications Insurmountable difficulties AIAOI visual inspection overall solution is a great boon for appearance defect detection When designing the product roadmap of Xiaoshi Zhikan, customer group positioning and strengthening customer product services and value were important indicators Moreover, appearance defect detection has always been an unresolved pain in the manufacturing industry, Hong Peijun said With industrial quality inspection AI software as the core, Xiaoshi Intelligent Inspection provides an overall solution for AIAOI visual inspection It mainly promotes three major products, including "QVI-T AI deep learning inspection modeling platform software" and "AI six-sided defect inspection and screening machine" ” and “AI Industrial Quality Inspection Platform” The main customer groups served are semiconductor packaging and testing, EMS electronics foundry, small metal parts processing and other industries with high production capacity and high gross profit margin In response to customer needs, Xiaoshi Intelligent Inspection provides corresponding software and hardware services, combining self-developed AI deep learning software and hardware quality inspection equipment to reduce the manual visual burden on the production line and effectively improve the production quality of the factory In order to help equipment manufacturers and technical engineers with development capabilities accurately grasp product appearance defect detection, Xiaoshi Intelligent Inspection independently developed QVI-T deep learning detection software, which can provide customers with defect location, defect classification, defect segmentation, anomaly detection and text recognition Key functions such as this are different from the fixed detection methods of traditional software Algorithms can be refined based on different industrial detection methods and different APIs can be developed to connect devices with different lenses The software design of this platform is very lightweight It is a SaaS software built on public cloudprivate cloud It mainly involves simple image uploading, labeling, training modeling, and verification testing After completion, users can download models, SDKs, APIs, and reports Effectively help customers achieve AI inference functions Currently, most of the industrial inspection services on the market are traditional AOI software industrial inspection machines, which can only measure product contours such as the head and length of fasteners, etc, and cannot truly provide detection of subtle product surface defects such as screw head cracks and tooth damage There is a lack of such high-precision defect detection companies in the market, Hong Peijun observed Xiaoshi Intelligent Inspection developed and independently built the "AI six-sided defect detection and screening machine" from customized services in the past to providing standardized services for customers at the current stage It provides standardized testing services for fasteners in measurement and surface defects, as well as passive components High-speed surface defect detection of similar products This professional machine uses the AI deep learning AOI composite algorithm technology independently developed by Xiaoshi Intelligent Inspection Through parallel computing technology, it can achieve model inference up to 3 milliseconds per picture, and realize multiple complex defect detection on the electrodes and body of passive components This professional machine is mainly used for the inspection of fasteners, small metal parts and passive components In terms of competitiveness in the industry, the software hardware integration provided by the AI six-sided defect inspection and screening professional machine is an important core competitive advantage of Xiaoshi Intelligent Inspection It is not as simple as it sounds Hong Peijun said with emotion that this special machine is very important in the industrial inspection industry Commonly known as the highly integrated integration of optical mechanisms, electronic controls, software and algorithms, the process requires continuous optimization and iteration, and requires multiple client verifications and modifications After a long period of hard work, the technical threshold has also been raised The AI six-sided defect detection and screening professional machine will be the main product promotion direction of Xiaoshi Intelligent Inspection in the next 3-5 years It is believed that AI combined with measurement technology and surface defect detection will be an important source of core competitiveness of Xiaoshi Intelligent Inspection, Hong Peijun said AI six-sided defect detection and screening professional machine will be the main product promotion direction of Xiaoshi Intelligent Inspection in the next 3-5 years Faced with the booming development of Industry 40 in smart factories, customers often ask "Does quality inspection data have secondary use value" Hong Peijun said that the "AI Industrial Quality Inspection Platform" launched by Xiaoshi Intelligent Inspection has a machine learning mechanism , which can be used for secondary use of quality inspection data to provide customers with multiple functions including real-time monitoring and early warning of production quality, quality traceability analysis, quality factor assessment, process parameter prediction and recommendation Taking the successful introduction into the automotive parts factory as an example, through the prediction and recommendation of process parameters provided by the AI industrial quality inspection platform, when we know the product defects, we build a set of models based on the experience of past masters, coupled with the network connection data from the previous stage, After integration, we have process data, incoming material data, and quality inspection data We can predict whether these machine parameters have run out, and we can recommend whether the process parameters of certain sections should be adjusted up or down Through the AI industrial quality inspection platform, Xiaoshi Intelligent Inspection can help customers connect visual quality inspection results, process data and acceptance standards with the existing MES system of the customer's factory to improve production quality, improve efficiency and reduce costs In terms of business model, Xiaoshi Zhiqian also provides a software subscription system for the deep learning detection modeling platform software It provides public cloud customers with traffic subscription and charges based on the amount of image uploads, while private cloud customers adopt an annual license fee license charging mechanism In addition, the company also provides customers with a buyout charging mechanism for the overall solution equipment, and provides a one-year warranty, after which consumables and software update maintenance fees are charged annually Going in the opposite direction, using both hard and soft methods, with a missed detection rate of less than 1 and rapid modeling in 15 minutes Faced with various small-volume and multi-sample inspection needs in the manufacturing industry, general AI deep learning visual inspection usually requires customers to collect a large number of photos of defective products, which is time-consuming to label, and also causes customers to have difficulty in importing AI, and defective products cannot be collected The introduction cycle is long and implementation is full of risks If there are not enough bad samples, the model will be inaccurate Kosaki Chikan goes in the opposite direction and uses its product "AI Visual Inspection Model Development Tool" to train models through pictures of good products provided by customers It is relatively easy for AI to learn good products, no labeling is required, and the time can be quickly compressed to complete the modeling Take the implementation of IPC electronics industry - AAEON Technology as an example In order to reduce the manpower input of the quality inspection station in the PCBA production line and have standardized quality inspection, Xiaoshi Intelligent Inspection provides an overall solution for PCBA AI visual inspection software and hardware services, and conduct in-line inspection on the factory's highly automated assembly line, effectively saving inspection manpower investment, improving the standardization of quality inspection rates, and improving the problem of inconsistent standards caused by manual visual inspection Through the introduction of AI visual inspection software and hardware integrated solutions, we have effectively helped customers maintain an overkill rate of less than 3 in the past two years, and achieved high-efficiency performance with a missed detection rate of less than 1 In addition, this solution allows practitioners who do not understand AI to quickly operate modeling By installing the modeling tool on the device, when the customer has a new product number and needs to create a model, he only needs to provide 10 pictures of good products to scan under the device It only takes 15 minutes to quickly train the model In terms of product core strategic layout, compared with market competitors who rely solely on general software services to seize all manufacturing markets, it is not feasible to apply it to industrial inspection Hong Peijun has observed over the past 10 years and believes that only software hardware can With technical thresholds and focusing on one industry and field, only by adopting a standardized company's AI six-sided defect detection and screening special machine can it be replicated and scaled up, and the company can truly continue to move towards optimization and create product competitiveness, even if there are other competing products It’s not easy to compete for this pie, Hong Peijun said Xiaoshi Intelligent Inspection’s overall AIAOI visual inspection solution creates rapid modeling and excellent results for customers with a missed detection rate of less than 1 The most competitive AIAOI overall solution provider with global presence For new entrepreneurs, facing business expansion is a challenge every day Hong Peijun said that small companies are easily snatched away by large companies, company talents are poached by high salaries, lack of deep customer relationships, and the business team is not large enough, etc How to overcome this Hong Peijun believes that the key to success and competitiveness of a new start-up company is to be diligent in making up for mistakes, provide better services, provide more immediate feedback, and create more professional solutions to convince customers Since its establishment in 2020, Xiaoshi Intelligent Inspection has always gone against the grain in terms of product core strategic layout, surpassing the competitive market among its peers, and actively taking root in the overall solution of AI visual inspection software and hardware Hong Peijun hopes that Xiaoshi Intelligent Inspection will become the world's most competitive AIAOI overall solution provider for the electronics and semiconductor industries in the future, and provide the top AIAOI professional machines and equipment to the electronics and semiconductor industry customer base Hong Peijun said that the technical capabilities of the company's AI six-sided defect detection and screening professional machine have reached the top domestic level In order to speed up the research and development of professional machines to become more standardized and sell them to overseas markets, the company will conduct a fundraising plan at this stage, hoping to use legal persons such as the Capital Strategy Council to assist in more business connections and fundraising channels For the medium and long-term goals, Xiaoshi Intelligent Inspection will lay out the global market including mainland China and Southeast Asian countries At the same time, it will follow the international footsteps of major OEMs in global layout Under the target inspection project, it will continue to develop specialty products and spread towards the international field 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

這是一張圖片。 This is a picture.
AI Defect Intelligent Detection - Energy Reduction Smart Monitoring Solutions

AIIntelligent Defect Detection-Smart Monitoring Solution to Reduce Process Energy Consumption When there are over2ten thousand chip resistors on a ceramic substrate, how should one quickly detect defects The answer isUsingAIto detect。 In the era of rapid technological development, Leike proudly announces significant advances in its laser processing technology, thanks to the innovative applications of artificial intelligenceAILeike is committed to integrating advancedAItechnology into laser processing machines, and in2019year, in collaboration with partners, developed the world's first laser machining system that integratesAItechnology, and on this basis further developed in2023year the first ceramic substrate inspection machine that integratesAOIAILASERtechnology Smart Ceramic Substrate Inspection Machine Through the introduction ofAIand machine learning, along with the accumulation of big data samples, the system becomes smarter, which has led to improved product yield within one year5dramatically reducing the inspection time from originally2minutesper piece to just20secondsper piece, drastically lowering inspection costs, enabling efficient initial detection and post-laser marking to reduce waste in subsequent processes, diminishing overall carbon emissions of the site, allowing the automatic generation of detailed inspection reports for data analysis and optimization, which helps increase equipment capacity, reduce human error, enhancing the value of Leike's equipment, and strengthening the international competitiveness of the country's electromechanical industry Leike CorporationLaser TekFounded in1988year, and officially listed as a publicly traded company in2002year Since its establishment, it has become a leading global service provider and manufacturer of electronic packaging materials,SMDElectronic Packaging Materials,SMTinspection equipment, and laser systems Leike's general manager, with years of laser integration experience, observed that passive component customers can produce over20With many years of laser integration experience, he observed that the production capacity of passive component customers can exceed10billionSMDcomponents every month, but withSMDcomponents per month However, as component sizes continue to miniaturize, defect detection during production becomes increasingly challenging With thousands to millions of components on a single ceramic substrate, and as component sizes decrease and their laser processing positions become smaller, the difficulty of detection increases, making production inspection a critical process R-SMD Production Inspection Process AOIproblems of yield overkill relying onAIfor oversight, Yet,AOIthe inspection machine is a widespread and mature type, but the high accuracy on the marketAOIuses a technique that captures small images in a single shot and stitches them into a larger image Although accurate, this method requires more time for small-sizedSMDcomponents, which are more likely to be influenced by environmental factors like lighting and vibration that can cause misjudgments as a result,AOIyield rate can only be estimated by sampling, and components with poor sampling yield are not removed individually but discarded together with good ones manual re-inspection not only increases costs, but the lack of unified inspection standards ultimately results in about2-5products that are not detected as defective enter the subsequent manufacturing process monthly at least2,000thousands of such defective componentsSMDthat were not initially detected causing ongoing printing and machining inspections in subsequent processes Regardless of the waste of ink materials and energy, which increases the cost burden, this also accelerates equipment wear and shortens operational life Each stage of waste increases the site's carbon emissions, unfavorably impacting the company's carbon footprint Post-Adjustment Sample Photo Example 0402 TraditionalAOI High false positive rates in Automatic Optical Inspection AOI are a major production issue for manufacturers, particularly in the passive components industry where 'it's better to mistakenly reject a hundred than miss one'—a high standard, often leading to AOI setting extremely high parameters which makes devices overly sensitive Excessive stringency in data parameter settings can lead to high false positive rates For instance, if the dirt contamination on passive components resembles the color of the printing layers,AOI the misjudgment rate could reach 7 percent Contamination Dirt and Print Layer Color SimilarityAOIProne to Misjudgment Raytek stands apart from otherAOIsuppliers by discarding the stitching of small images or line scanning, effectively preventing data loss and discrepancies caused by hardware or environmental conditions during image processing It employs a large-array photodetector coupled with custom high-resolution lenses, using specialized imaging for composite processing Throughout this process, each pixel of the photodetector contains light information captured from various positions By combining this data, the image resolution and detail are enhanced, reaching a resolution of millions, and with multiple automatic light adjustments, a single shot can manage7070mmachieving an image resolution up to5umobtaining clear images, then throughSmart-AItechniques for analysis and selection Three Innovative Methods to Achieve Rapid InspectionSmart -AI Raytek's General Manager shares, rapidly implementingAItechnology and reducing inspection computation time, further developingSmart-AIthree major approaches Method one, initially useAOIto quickly separate good products from those with controversial defects, focusing the detection on the minority of defective identifications Method two, an automated labeling platform simplifies the training issue by using cameras to collect data from machines, automatic labeling replaces manual labeling, progressively training to improve accuracy The simpler the problem, the less data needed for training Method three,AOIandAIDual-track Advancement In the smart manufacturing process, relying solely onAOIorAIis not enough to accomplish the task alone, it must be preceded byAOIfirst marking the characteristics, distinguishing between good and defective parts, then usingAIa method for labeling and training Subsequently, by utilizing a repeating cascade effect, the detection benefits are greater as more training data accumulates,AOIreducing the ratio of errors,AIand gradually increasing the accuracy ratio Post Adjustment Object Detection and Training Through three major methods gradually building system reliability, and categorizing data for defect sorting, ultimatelyAIreturning the judgement results to the main system, utilizing laser machining to control truly defective products at the front end of the process, reducing the inflow of defective products into other stations, thus minimizing losses due to repeated tests or reprocessing Leading in smart laser equipment, chooseLASERTEKthe right one Continuously developed by the Taiwanese brand Raytek, combiningAIsmart detection and laser processing equipment to progressively build a smart monitoring solution stack from raw materials, products, testing, laser equipment, etc, aiming at reducing the energy consumption of the production process, implementing semiconductor advancements, substrates and component processing among other fields, producing equipment products capable of meeting the end-user demands under low carbon conditions, rapidly and with quality products and services expanding both domestic and international markets, enhancing the global competitiveness of localMade in TaiwanMITequipment 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」

【解決方案】2秒鐘完成結帳動作 Viscovery AI影像辨識助攻智慧零售
Complete checkout in 1 second, Viscovery AI image recognition assists smart retail

Artificial intelligence AI has gradually changed the way various industries operate in recent years However, most of the work is still done by humans, with AI playing a supporting role This has led to emergence of the term "AI Copilot," which stands for "AI-driven tools or assistants" that aim to assist users in completing various tasks and improve productivity and efficiency The concept of AI Copilot comes from the role of "co-pilot" During flight, the co-pilot assists the main pilot in completing various tasks to ensure flight safety and efficiency In fact, there have been signs of various "machines" beginning to play the role of "copilot" in different fields since the Industrial Revolution, assisting humans in completing heavy physical and repetitive tasks, greatly improving factory production efficiency, and driving rapid economic development Following the advancement of computing equipment and breakthroughs in machine learning, deep learning, and image recognition technologies, the concept of AI Copilot has gradually taken shape The development of AI Copilot marks the transition from "machine-assisted to AI-assisted" Early robots could only complete preset repetitive tasks, but today's AI copilot can learn and adapt to new environments and tasks, and continuously optimize its performance in practical applications This transformation not only changes human-machine interactions, but also has a profound impact on various industries The application scope of AI copilot covers various industries, including finance, healthcare, manufacturing, education, retail, etc, and are everywhere to be seen Application of AI copilot in the retail industry AI image recognition checkout In the retail industry, the application of AI copilot has begun to show concrete results Take Viscovery's AI image recognition checkout system as an example This system is a type of AI copilot model that helps store clerks speed up checkout or assists consumers in simplifying the self-service checkout process The store clerk needs to scan the product barcodes one by one in the regular checkout method If a product does not have a barcode, such as bread and meals, the clerk needs to first visually confirm the items, and then input them into the POS checkout system one by one Based on actual measurements at a chain bakery, it takes 22 seconds for an experienced clerk from "visual recognition" to "entering product information of a plate of 6 items into the checkout system" New clerks may need even more time In addition, according to a Japanese bakery operator, it takes 1 to 2 months to train employees to become familiar with products Now with AI image recognition technology, store clerks let AI handle the "product recognition" step, and AI will play the role of copilot, quickly identifying items within 1 second, speeding up checkout to save 50 of checkout time, and optimizing customers'shopping experience The time cost of training employees to identify bread can also be effectively shortened Even for products with barcodes, AI can quickly identify multiple items in one second, which is more efficient than scanning barcodes one by one The self-checkout system "assisted" by AI image recognition allows consumers to successfully complete shopping without the help of store clerks, eliminating the trouble of swiping barcodes or searching for items on the screen, which improves the shopping experience In a time when store clerks are hard to hire due to labor shortage, this also helps stores reduce operating costs AI quickly identifies multiple checkout items in just one second Source of image Viscovery Recently, startups dedicated to developing AI image recognition checkout solutions have emerged in various countries The most lightweight solution currently known is in Taiwan It can be immediately used by installing a Viscovery lens and a tablet installed with Viscovery AI image recognition software at the checkout counter to connect to the store's existing POS checkout system There are various integration methods, including plug-and-play and API solutions integrated with the store's POS system Viscovery AI image recognition system can be painlessly integrated with the store's existing POS system Source of image Viscovery Example of AI image recognition checkout Currently, the Viscovery AI image recognition system is being used in bakery chains in Taiwan, Chinese noodle shops in Singapore, micromarkets in department stores in Sendai, Japan, and Japanese bakeries and cake shops Over 7 million transactions were completed through this AI system, which identified more than 40 million items These use cases demonstrate the extensive application of the Viscovery AI image recognition system in the retail industry In the future, the company will continue to explore the various possibilities of using Vision AI in retail and catering nbsp The Viscovery AI image recognition system is already being used in bakeries, cake shops, restaurants, and convenience stores in Japan, Singapore, and Taiwan Source of image Viscovery