Have you had your morning coffee yet Over the past decade, Taiwan has gradually formed a coffee drinking culture With the advancement of AI technology, autonomous coffee roasters can now rely on AI for precise location setting while also cultivating a loyal customer base Let's see how this is done According to the International Coffee Organization ICO, Taiwanese consume approximately 285 billion cups of coffee annually, with the coffee market in Taiwan estimated at 80 billion TWD, growing about 20 each year In recent years, the 'drinking coffee' culture in Taiwan has become synonymous with popularity, with coffee being the most frequently chosen daily beverage by 65 of the population Coffee enthusiasts, particularly the more avid ones, are willing to pay more for coffee beans that suit their tastes An increasing number of unmanned drink kiosks have also begun to appear in the Taiwanese beverage market Unmanned coffee beverage shops face difficulties in expanding quickly, primarily due to two major issues one is the appropriateness of customer flow and machine placement locations which still rely on manual analysis the second is penetrating the market of mid to high-end coffee lovers accurately AI resolves two major challenges for autonomous coffee roasters suitable placement and cultivating a loyal customer base To tackle these issues and help autonomous coffee roasters quickly break into the market, Raysharp Electronics intends to implement AI for people flow counting analysis and unfamiliar face recognition These technologies aim to calculate the crowd size at potential roaster locations and classify consumers by gender and age for more precise market analysis They also provide multiple choices for the roasting of raw coffee beans, offering a more customized service tailored to the needs and tastes of professional coffee aficionados with a pack of 'high-quality roasted beans' Since 2018, the rise of unmanned stores has been mainly due to owners wanting to reduce persistently rising rent and personnel costs However, the initial assessment of store locations still requires hourly labor expenses for manual estimation of customer flow, leading to possible miscalculations of both on-site consumers and passerby traffic These inaccuracies may prevent precise real-time analysis of customer flow, or even misguided estimations of operational efficacy after a trial run, thus missing the optimal timing for loss-preventing location retraction Raysharp Electronics introduces autonomous coffee roasters equipped with AI-based people counting analysis and facial recognition Raysharp Electronics combines AI people counting analysis and facial recognition with the coffee trend known as 'black gold', addressing the preferences of numerous coffee connoisseurs in Taiwan who enjoy personally selecting coffee beans at bulk stores and frequenting high-quality grinding cafes or chain coffee shops A new concept for the first autonomous coffee roaster offering choices based on the origin, variety, and roasting methods of coffee beans has emerged AI coffee roasters enhance customer loyalty and materials management efficiency by 20 For the advanced development of autonomous coffee roasters, Raysharp Electronics engineers have equipped the AI NVIDIA development platform on the basis of TCNNFacenet Through AI, tens of thousands of images related to gender and age are used for sample training, allowing even first-time coffee roasting customers to be easily classified using unfamiliar face recognition This gains consumer trust, enhances willingness to use, and allows for recording purchase information and future product recommendations, leading to consumer purchase behavior analysis This information helps owners tailor future material preparation based on consumer preferences for different coffee beans, reducing raw material transportation and storage issues, and improving material management efficiency by 20 Moreover, by placing these autonomous coffee roasters in high-traffic areas, owners can use cameras to capture the crowd and assess whether the machine location has an adequate customer base, quickly analyzing whether to reposition the machines, and more easily targeting the best locations for middle and high-end coffee lovers The unmanned coffee roaster features a professional roasting mode interface, providing options based on the origin and variety of coffee beans, their roasting methods light, medium, deep, and related temperature, wind speed, and timing settings If improvement needs arise during the process, engineers can adjust firmware parameters and also assist in integration with the owner's ordering system Staff members briefly describe the operation of the autonomous coffee roaster 'Black Gold' penetrates deeper into coffee shops, science parks, and commercial buildings through AI This autonomous coffee roaster targets coffee connoisseurs and can be placed in middle to high-end coffee shops to roast more customized coffee beans than those available in bulk stores Upon completing a batch of coffee beans, it immediately provides them to professional technicians within the coffee shops for grinding and manual brewing The remaining roasted beans can also be taken home for brewing and enjoyment It also adds value to coffee shops by better understanding consumer preferences for coffee beans and launching more customer-attracting drink promotions and appropriate inventory management In addition to coffee shops, the autonomous coffee roaster can also utilize AI-based people counting analysis to precisely set up near scientific parks and commercial buildings, offering high-quality coffee beans for office brewing to internal employees with high coffee consumption needs Furthermore, implementing a physical membership system can initiate coffee bean purchase promotions or periodic payment incentives, thus attracting new clients and cultivating existing customer loyalty and retention The operation interface of the smart autonomous coffee roaster「Translated content is generated by ChatGPT and is for reference only Translation date：2024-05-19」

Search for a specific person, find someone with a suitcase entering the factory in Gao'an area Color features of the person and the object confirmed, person in blue and black top, suitcase in black color, throughCCTV the intelligent video search system, by setting object and color retrieval conditions, it can successfully locate three video clips containing the target subject This greatly aids operational staff in finding the target items, and through this system, search speed can far surpass manual effort6fold Pain Points The CSE-Kaohsiung Plant is densely equippedCCTVto monitor every corner of the plant area, but when an incidenthappens, it's impossible within a limited time throughCCTVvideo playback to find the incident, the implications and risks behind this are self-evident Many areas that are usually unmanned can easily become security blind spots Thus, how to monitor a vast plant area more intelligently and effectively is one of the crucial aspects of building a smart plant for the semiconductor industry The AES Plant in Kaohsiung covers a vast area, with many important sites requiring monitoring of personnel movements to ensure corporate secrets and employee safety 1 Automated production lines and warehouses In semiconductor enterprises’ automated production lines and warehouses, oftenAGV（Automated Guided VehicleAGVs automated guided vehicles travel at high speeds if plant personnel inadvertently enterAGVthe moving area and cannot issue a warning to the person, then the regrettable accidents that occur will be too late to reverse 2 Material and product storage areas Materials used in semiconductor-related processes are costly if areas storing materials or products are breached, there is a risk of loss of high-value materialsproducts 3 High-security areas Trade secrets relate to the core technological competitiveness of semiconductor-related enterprises if someone breaches the high-security areas, there is a risk of corporate secrets being leaked The safety of trade secrets has always been one of the most critical issues for semiconductor enterprises 4 Loading docks At AESLButthe dock area often has loading vehicles coming and going if someone intrudes into the dock area, there is a risk of vehicle collisions and accidents Additionally, goods awaiting shipment at the dock area could be stolen or potentially damaged from collisions, thus causing significant reputation and financial losses for the company, further leading to production and shipping inconvenience When an abnormal event occurs, how to quickly search for the relevant key footage from massive data Many important locations within the AES Kaohsiung Plant need to be equippedCCTVfor safety checks, butCCTVWith thousands to tens of thousands of cameras, manually searching through footage for an event requires laborious frame-by-frame review which is time-consuming and inefficient In light of advancements in computer vision, it's beneficial to utilizeAIto replace manual playback and searching Problem Scenario Object Detection The data source for object detection comprises two parts Open-source datasetsOIDv4and AES Kaohsiung PlantCCTVImage files For these files, search for usable data, specificallyOIDv4image files For these files, extract the defined nine major categories of objects for training data among them, two object categories, knives and gasoline barrels, were not found inOIDv4found usable data for knives and gasoline barrels, while the remaining seven categories of objects are available fromOIDv4useful training data found for the remaining seven categories of objects, all marked Regarding the Kaohsiung PlantCCTVimage files, select some frames Frame of the footage, and manually annotate the objects to be_detected for training and testing data Nine Major Objects Color Recognition The data source for color recognition is divided into two partsInternet image screenshots, and Kaohsiung PlantCCTVimage files Currently, no publicly available open-source datasets specifically for color recognition applications have been found, so images are collected from the web Search the web for images of the defined nine major object categories, save the images after separating the objects from the background, keeping only the object sections, and mark the images according to color Additionally, for the Kaohsiung PlantCCTVimage files, use the already-markedbounding boxextractCCTVimage files from variousFramesections of objects identified by color, and finally, visually identifiable images are marked according to color Each object category has its specific color definition, depending on the usual colors seen in these objects in real life Dynamic Ignore during Training FromOIDv4during the training of the object detection pilot model, since each image in this dataset is only marked for a single category, but the image may contain other desired detection categories unmarked For such cases, dynamic ignore techniques will be employed during training to avoid confusion Next, use the extracted training data from the Kaohsiung Plant toFine-Tuneenhance the detection rate of the object in specific designated areas Finally, select the model that computes the lowest loss value in the test set during the training process as the main object_detection model Dynamic Ignoring AIHelp You View CCTV The intelligent video search system primarily serves as an assistive system for searching surveillance footage, capable of speeding up the process of finding target events by setting search conditions for objects By simply defining the search conditions, you can quickly produce thumbnails of critical objects and playback for review, shortening the time required for manual case retrieval of the past The search time is quickly6doubled, allowing the front-end security unit to use this platform to strengthen the first line of risk management supervision and take timely preventive measures 「Translated content is generated by ChatGPT and is for reference only Translation date：2024-12-12」