system

Abstract

The system according to this embodiment aims to automatically generate and assign relevant tags from product images and text. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, and an assignment unit. The analysis unit analyzes the content of an image of a product or text related to a product. The generation unit generates tags based on the information analyzed by the analysis unit. The assignment unit assigns the tags generated by the generation unit to the product.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the work of manually assigning related tags from product images and texts is complicated and difficult to perform efficiently.

[0005] The system according to the embodiment aims to automatically generate and assign related tags from product images and texts.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, a generation unit, and an assignment unit. The analysis unit analyzes the content of a product image or text related to the product. The generation unit generates tags based on the information analyzed by the analysis unit. The assignment unit assigns the tags generated by the generation unit to the product. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate and assign relevant tags from product images and text. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An automated tagging system according to an embodiment of the present invention is a system that analyzes the content of images and text and automatically generates relevant tags. The automated tagging system has a function to prioritize the assignment of highly relevant tags by referring to the user's search history and purchase history, and further incorporates a user feedback function to improve the accuracy of the tags. First, the automated tagging system analyzes the content of the product's image or text related to the product. For example, the automated tagging system analyzes the content of the image or text in detail and extracts the characteristics of the product. It analyzes the color and shape from the product's image, and the product's description and reviews from the text. Next, the automated tagging system generates tags based on the analyzed information. For example, if an image of a red shirt is analyzed, tags such as "red," "shirt," and "fashion" are generated. The generated tags are assigned to the product. The generated tags are associated with the product and displayed when the user searches for the product. Furthermore, the automated tagging system acquires the user's behavior history. For example, the automated tagging system collects the user's search history and purchase history. If the user searches for "red shirt," that search history is acquired. Based on the acquired behavior history, it prioritizes the assignment of highly relevant tags. For example, if a user has a search history for "red shirt," tags such as "red" and "shirt" will be prioritized. The automatic tagging system also accepts user feedback. For instance, if a user provides feedback that the tag "red" is inappropriate for a "red shirt," the system will revise the tag based on that information. In this way, a system is realized that analyzes the content of images and text and automatically generates and assigns highly relevant tags based on the user's behavior history and feedback. As a result, the automatic tagging system can analyze the content of images and text and automatically generate and assign relevant tags.

[0029] The automated tagging system according to this embodiment comprises an analysis unit, a generation unit, and an assignment unit. The analysis unit analyzes the content of product images or text related to products. The analysis unit analyzes the color and shape of products using, for example, an image analysis algorithm. The analysis unit analyzes product descriptions and reviews using, for example, a text analysis method. The analysis unit analyzes the meaning of text using, for example, natural language processing technology. The generation unit generates tags based on the information analyzed by the analysis unit. The generation unit generates, for example, keyword tags based on the analyzed information. The generation unit generates, for example, category tags based on the analyzed information. The generation unit generates, for example, attribute tags based on the analyzed information. The assignment unit assigns the tags generated by the generation unit to products. The assignment unit associates the generated tags with products, for example. The assignment unit registers the generated tags in a product database, for example. The assignment unit makes the generated tags visible when a user searches for them, for example. Thus, the automated tagging system according to this embodiment can analyze the content of product images and text and automatically generate and assign relevant tags.

[0030] The analysis unit analyzes product images or text content related to products. Specifically, it uses image analysis algorithms to analyze the color and shape of products. For example, it uses a convolutional neural network (CNN) to extract features from product images and identify attributes such as color, shape, and pattern. This allows for the acquisition of detailed information based on the product's appearance. It also uses text analysis techniques to analyze product descriptions and reviews. For example, it uses morphological analysis to segment the text and analyze the meaning and relationships of each word. Furthermore, it uses natural language processing techniques to analyze the meaning of the text. For example, it uses generative AI to extract important keywords and phrases from product descriptions and reviews to understand product characteristics and user evaluations. As a result, the analysis unit can acquire product information from multiple perspectives using both images and text and perform detailed analysis. By combining these technologies, the analysis unit can grasp product characteristics with high accuracy and provide the information necessary for subsequent tag generation.

[0031] The generation unit generates tags based on the information analyzed by the analysis unit. Specifically, it generates keyword tags based on the analyzed information. For example, it generates keyword tags such as "red" and "round" based on the product's color and shape. It also generates tags such as "highly rated" and "popular product" based on important keywords extracted from the product description and reviews. Furthermore, it generates category tags based on the analyzed information. For example, it generates category tags such as "home appliances" and "fashion" based on the product's use and category. This allows users to narrow down their search by category when searching for products. Furthermore, it generates attribute tags based on the analyzed information. For example, it generates attribute tags such as "waterproof" and "lightweight" based on the product's characteristics and functions. The generation unit can use machine learning algorithms to automatically generate these tags. For example, it can use supervised learning to learn tag generation patterns from past data and generate appropriate tags for new products. As a result, the generation unit can generate a variety of tags with high accuracy based on the information provided by the analysis unit, accurately representing the characteristics of the products.

[0032] The tagging unit assigns tags generated by the generation unit to products. Specifically, it associates the generated tags with products. For example, it adds the generated tags to each product entry in the product database. It also registers the generated tags in the product database. This allows the product database to store related tag information along with detailed information about each product. Furthermore, it ensures that the generated tags are displayed when users search for them. For example, if a user searches for "waterproof," products with the corresponding tag will be displayed in the search results. The tagging unit can integrate with database management systems and search engines to automate these tagging processes. For example, it can create indexes to efficiently manage tag information and respond quickly to search queries. This allows the tagging unit to efficiently and effectively assign generated tags to products, improving user convenience when searching for products. Furthermore, the tagging unit can also update and delete tags. For example, if new information is analyzed or product characteristics change, it updates the tags accordingly to reflect the latest information. This ensures that the tagging unit always maintains the latest tag information and provides accurate information to users.

[0033] The acquisition unit can acquire the user's activity history with respect to the product. For example, the acquisition unit can acquire the user's search history for the product. For example, the acquisition unit can acquire the user's purchase history for the product. For example, the acquisition unit can acquire the user's browsing history for the product. Based on the activity history acquired by the acquisition unit, the generation unit can preferentially assign tags that are highly relevant to the user from among the generated tags to the product. For example, if the user has a history of searching for "red shirt," the generation unit will preferentially assign tags such as "red" and "shirt." For example, if the user has a history of purchasing "sports equipment," the generation unit will preferentially assign tags such as "sports" and "exercise." For example, if the user has a history of browsing "electronic devices," the generation unit will preferentially assign tags such as "electronic devices" and "gadgets." This allows for the preferential assignment of highly relevant tags based on the user's activity history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's activity history into AI and generate data for preferentially assigning highly relevant tags.

[0034] The feedback unit can receive feedback from users. For example, the feedback unit can receive comments from users about the appropriateness of tags. For example, the feedback unit can receive evaluations of tags from users. For example, the feedback unit can receive responses from users to questionnaires. The tagging unit can change the tags assigned to products based on the feedback. For example, if a user provides feedback that the tag "red" is inappropriate for a "red shirt," the tagging unit will correct the tag based on that information. For example, if a user provides feedback that the tag "exercise" is inappropriate for "sports equipment," the tagging unit will correct the tag based on that information. For example, if a user provides feedback that the tag "gadget" is inappropriate for "electronic devices," the tagging unit will correct the tag based on that information. This allows for improvement of tag accuracy based on user feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user feedback data into AI to generate data for evaluating the appropriateness of tags.

[0035] The acquisition unit can acquire search history, which is the history of when a user has searched for a product, or purchase history, which is the history of when a user has purchased a product, as behavioral history. For example, the acquisition unit can acquire the history of when a user has searched for "red shirt". For example, the acquisition unit can acquire the history of when a user has purchased "sports equipment". For example, the acquisition unit can acquire the history of when a user has searched for "electronic devices". By acquiring the user's search history and purchase history, it becomes possible to assign tags based on behavioral history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input the user's search history and purchase history into AI and generate data for generating highly relevant tags.

[0036] The tagging unit can assign a tag corresponding to the first product to the second product and a tag corresponding to the second product to the first product if the same user has taken action on both the first and second products. For example, if a user searches for "red shirt" and "blue shirt," the tagging unit will assign the "blue shirt" tag to "red shirt" and the "red shirt" tag to "blue shirt." For example, if a user purchases "sports equipment" and "outdoor equipment," the tagging unit will assign the "outdoor equipment" tag to "sports equipment" and the "sports equipment" tag to "outdoor equipment." For example, if a user views "electronic devices" and "home appliances," the tagging unit will assign the "home appliances" tag to "electronic devices" and the "electronic devices" tag to "home appliances." This allows relevant tags to be assigned to multiple products based on the user's browsing history. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input user behavior history data into the AI ​​and generate data for creating relevant tags.

[0037] The tagging unit can assign tags related to the attributes of users who have interacted with a product. For example, the tagging unit can assign tags based on the user's age. For example, the tagging unit can assign tags based on the user's gender. For example, the tagging unit can assign tags based on the user's place of residence. This allows tags related to products to be assigned based on the user's attributes. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input user attribute data into AI and generate data for generating relevant tags.

[0038] The analysis unit can correct the analysis results based on the product's background information during image analysis. For example, the analysis unit can analyze the scenery in the background of the product and correct the product's characteristics. For example, the analysis unit can analyze the location where the product was photographed and correct the product's characteristics. For example, the analysis unit can analyze the date and time the product was photographed and correct the product's characteristics. This improves the accuracy of image analysis based on the product's background information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the product's background information into AI and generate data to correct the analysis results.

[0039] The analysis unit can enhance its analysis results by referring to product reviews and ratings during text analysis. For example, the analysis unit can analyze user comments to enhance product features. For example, the analysis unit can analyze rating scores to enhance product features. For example, the analysis unit can analyze review dates and times to enhance product features. This allows the accuracy of text analysis to be improved by referring to product reviews and ratings. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product review and rating data into AI to generate data to enhance the analysis results.

[0040] The analysis unit can estimate the usage scenario of a product during image analysis and reflect this in the analysis results. For example, if the product is used outdoors, the analysis unit analyzes the natural environment in the background and generates outdoor-related tags. For example, if the product is used indoors, the analysis unit analyzes the furniture and interior and generates home decor-related tags. For example, if the product is used at an event, the analysis unit analyzes the type of event and generates party and festival-related tags. By estimating the usage scenario of the product, it is possible to generate more relevant tags. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product usage scenario data into AI and generate data to reflect in the analysis results.

[0041] The analysis unit can enhance the analysis results by referencing relevant trend information for products during text analysis. For example, the analysis unit can refer to the latest fashion trends and add relevant keywords to the analysis results. For example, the analysis unit can refer to current market trends and reflect high-demand product categories in the analysis results. For example, the analysis unit can refer to trends on social media and include popular hashtags in the analysis results. This improves the accuracy of text analysis by referencing relevant trend information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input trend information data into AI to generate data to enhance the analysis results.

[0042] The analysis unit can correct the analysis results by referring to the product's manufacturer information during image analysis. For example, if the product's manufacturer has a high rating, the analysis unit can add quality-related tags. For example, if the manufacturer is located in a specific region, the analysis unit can add tags related to that region. For example, if the manufacturer is a specific brand, the analysis unit can add tags related to that brand. This improves the accuracy of image analysis by referring to the product's manufacturer information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input manufacturer information data into AI and generate data to correct the analysis results.

[0043] The analysis unit can enhance the analysis results by referring to relevant patent information of the product during text analysis. For example, if there are patents related to the product, the analysis unit will include that patent information in the analysis results. For example, the analysis unit will analyze the technical content of the patent and add technical tags. For example, the analysis unit will refer to the applicant information of the patent and include the company name and researcher name in the tags. This improves the accuracy of text analysis by referring to relevant patent information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input patent information data into AI and generate data to enhance the analysis results.

[0044] The generation unit can adjust the level of detail of tags when generating tags, taking into account the market value of the product. For example, the generation unit can generate detailed tags for expensive products, standard tags for general products, and simplified tags for inexpensive products. By adjusting the level of detail of tags based on the market value of the product, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input market value data of products into AI and generate data for adjusting the level of detail of tags.

[0045] The generation unit can apply different generation algorithms depending on the product category when generating tags. For example, the generation unit can apply an algorithm that generates tags based on color and style to products in the fashion category. For example, the generation unit can apply an algorithm that generates tags based on function and specifications to products in the electronics category. For example, the generation unit can apply an algorithm that generates tags based on ingredients and taste to products in the food category. By applying different generation algorithms depending on the product category, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product category data into AI and generate data for applying different generation algorithms.

[0046] The generation unit can determine the priority of tags based on the product's sales period when generating tags. For example, the generation unit can prioritize generating tags based on the latest trends for new products. For example, the generation unit can prioritize generating seasonal tags for seasonal products. For example, the generation unit can prioritize generating tags related to discounts and benefits for sale products. By determining the priority of tags based on the product's sales period, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product sales period data into AI and generate data for determining tag priority.

[0047] The generation unit can adjust the order of tags based on product relevance when generating tags. For example, the generation unit may display the most relevant tags first. For example, the generation unit may display less relevant tags later. For example, the generation unit may prioritize displaying highly relevant tags based on the user's search history. This allows for the generation of more appropriate tags by adjusting the order of tags based on product relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product relevance data into AI and generate data for adjusting the order of tags.

[0048] The tagging unit can select the most appropriate tags by referring to the user's past behavior history when assigning tags. For example, the tagging unit can select tags based on keywords the user has searched for in the past. For example, the tagging unit can select tags based on products the user has purchased in the past. For example, the tagging unit can select tags based on products the user has rated in the past. This allows for the selection of more appropriate tags based on the user's past behavior history. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's past behavior history data into AI to generate data for selecting the most appropriate tags.

[0049] The tagging unit can customize tags based on the current market conditions of a product when assigning tags. For example, the tagging unit assigns demand-related tags to products with high market demand. For example, the tagging unit assigns scarcity-related tags to products with low market supply. For example, the tagging unit assigns trend-related tags based on market trends. This allows for the assignment of more appropriate tags by customizing them based on the market conditions of a product. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input market condition data for a product into AI and generate data for customizing tags.

[0050] The tagging unit can select the most appropriate tags when assigning tags, taking into account the user's geographical location information. For example, if the user is in a specific region, the tagging unit will assign tags related to that region. For example, if the user is traveling, the tagging unit will assign tags related to the travel destination. For example, if the user is at home, the tagging unit will assign tags related to home. This allows for the selection of more appropriate tags based on the user's geographical location information. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's geographical location data into AI to generate data for selecting the most appropriate tags.

[0051] The tagging unit can analyze the user's social media activity and suggest tags when assigning tags. For example, the tagging unit can suggest tags based on what the user has shared on social media. For example, the tagging unit can suggest tags based on the accounts the user follows on social media. For example, the tagging unit can suggest tags based on posts the user has liked on social media. This allows for the suggestion of more appropriate tags based on the user's social media activity. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's social media activity data into AI and generate data for suggesting tags.

[0052] The data acquisition unit can analyze the user's past behavior history and select the optimal data acquisition method. For example, the data acquisition unit can acquire behavior history based on keywords the user has frequently searched for in the past. For example, the data acquisition unit can acquire behavior history based on products the user has purchased in the past. For example, the data acquisition unit can acquire behavior history based on products the user has rated in the past. This allows the system to select the optimal data acquisition method based on the user's past behavior history. Some or all of the above processing in the data acquisition unit may be performed using AI, for example, or without AI. For example, the data acquisition unit can input the user's past behavior history data into AI and generate data for selecting the optimal data acquisition method.

[0053] The acquisition unit can filter the behavioral history based on the user's current living situation and areas of interest when acquiring it. For example, the acquisition unit acquires relevant behavioral history based on the user's current living situation. For example, the acquisition unit acquires relevant behavioral history based on the user's areas of interest. For example, the acquisition unit combines the user's current living situation and areas of interest to acquire the most relevant behavioral history. This makes it possible to acquire more relevant behavioral history based on the user's current living situation and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's living situation and areas of interest data into AI to generate data for filtering.

[0054] The acquisition unit can prioritize the acquisition of highly relevant history by considering the user's geographical location information when acquiring activity history. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of activity history related to that region. For example, if the user is traveling, the acquisition unit will prioritize the acquisition of activity history related to the travel destination. For example, if the user is at home, the acquisition unit will prioritize the acquisition of activity history related to home. This allows for the acquisition of more relevant activity history based on the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into AI to generate data for prioritizing the acquisition of highly relevant history.

[0055] The acquisition unit can analyze the user's social media activity and acquire relevant history when acquiring behavioral history. For example, the acquisition unit can acquire behavioral history based on content shared by the user on social media. For example, the acquisition unit can acquire behavioral history based on accounts followed by the user on social media. For example, the acquisition unit can acquire behavioral history based on posts liked by the user on social media. This makes it possible to acquire more relevant behavioral history based on the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into AI and generate data for acquiring relevant history.

[0056] The feedback unit can select the optimal response when it receives feedback by referring to the user's past feedback history. For example, the feedback unit can select a response based on the feedback the user has provided in the past. For example, the feedback unit can select the optimal response from the user's past feedback history. For example, the feedback unit can analyze the user's past feedback history and select the most appropriate response. This allows for the selection of a more appropriate response based on the user's past feedback history. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's past feedback history data into AI to generate data for selecting the optimal response.

[0057] The feedback unit can provide the most appropriate response when it receives feedback, taking into account the user's current location. For example, if the user is in a specific region, the feedback unit will provide a response relevant to that region. For example, if the user is traveling, the feedback unit will provide a response relevant to their travel destination. For example, if the user is at home, the feedback unit will provide a response relevant to their home. This allows for the provision of a more appropriate response based on the user's current location. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's location data into AI to generate data for providing the most appropriate response.

[0058] The feedback unit can provide the optimal response when receiving feedback, taking into account the user's device information. For example, if the user is using a smartphone, the feedback unit will provide a response optimized for smartphones. For example, if the user is using a tablet, the feedback unit will provide a response optimized for tablets. For example, if the user is using a smartwatch, the feedback unit will provide a response optimized for smartwatches. This allows for the provision of a more appropriate response based on the user's device information. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user device information data into AI and generate data to provide the optimal response.

[0059] The feedback unit can provide multilingual feedback when it receives feedback, depending on the user's language settings. The feedback unit can, for example, automatically set the language of the feedback based on the language settings of the user's device. The feedback unit can, for example, provide a language switching function if the user uses multiple languages. The feedback unit can, for example, provide feedback in a language selected by the user. This allows for the provision of more appropriate feedback based on the user's language settings. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's language setting data into AI and generate data for providing multilingual feedback.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The generation unit can adjust the level of detail of tags when generating tags, taking into account the market value of the product. For example, the generation unit can generate detailed tags for expensive products, standard tags for general products, and simplified tags for inexpensive products. By adjusting the level of detail of tags based on the market value of the product, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input market value data of products into AI and generate data for adjusting the level of detail of tags.

[0062] The analysis unit can correct the analysis results based on the product's background information during image analysis. For example, the analysis unit can analyze the scenery in the background of the product and correct the product's characteristics. For example, the analysis unit can analyze the location where the product was photographed and correct the product's characteristics. For example, the analysis unit can analyze the date and time the product was photographed and correct the product's characteristics. This improves the accuracy of image analysis based on the product's background information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the product's background information into AI and generate data to correct the analysis results.

[0063] The tagging unit can select the most appropriate tags when assigning tags, taking into account the user's geographical location information. For example, if the user is in a specific region, the tagging unit will assign tags related to that region. For example, if the user is traveling, the tagging unit will assign tags related to the travel destination. For example, if the user is at home, the tagging unit will assign tags related to home. This allows for the selection of more appropriate tags based on the user's geographical location information. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's geographical location data into AI to generate data for selecting the most appropriate tags.

[0064] The analysis unit can enhance its analysis results by referring to product reviews and ratings during text analysis. For example, the analysis unit can analyze user comments to enhance product features. For example, the analysis unit can analyze rating scores to enhance product features. For example, the analysis unit can analyze review dates and times to enhance product features. This allows the accuracy of text analysis to be improved by referring to product reviews and ratings. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product review and rating data into AI to generate data to enhance the analysis results.

[0065] The generation unit can apply different generation algorithms depending on the product category when generating tags. For example, the generation unit can apply an algorithm that generates tags based on color and style to products in the fashion category. For example, the generation unit can apply an algorithm that generates tags based on function and specifications to products in the electronics category. For example, the generation unit can apply an algorithm that generates tags based on ingredients and taste to products in the food category. By applying different generation algorithms depending on the product category, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product category data into AI and generate data for applying different generation algorithms.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The analysis unit analyzes the product image or the content of the text related to the product. For example, the analysis unit uses image analysis algorithms to analyze the color and shape of the product, and text analysis methods to analyze the product description and reviews. It also uses natural language processing technology to analyze the meaning of the text. Step 2: The generation unit generates tags based on the information analyzed by the analysis unit. For example, the generation unit generates keyword tags, category tags, and attribute tags based on the analyzed information. Step 3: The tagging unit assigns the tags generated by the generation unit to the products. For example, the tagging unit associates the generated tags with the products, registers them in the product database, and makes them visible when users search for them.

[0068] (Example of form 2) An automated tagging system according to an embodiment of the present invention is a system that analyzes the content of images and text and automatically generates relevant tags. The automated tagging system has a function to prioritize the assignment of highly relevant tags by referring to the user's search history and purchase history, and further incorporates a user feedback function to improve the accuracy of the tags. First, the automated tagging system analyzes the content of the product's image or text related to the product. For example, the automated tagging system analyzes the content of the image or text in detail and extracts the characteristics of the product. It analyzes the color and shape from the product's image, and the product's description and reviews from the text. Next, the automated tagging system generates tags based on the analyzed information. For example, if an image of a red shirt is analyzed, tags such as "red," "shirt," and "fashion" are generated. The generated tags are assigned to the product. The generated tags are associated with the product and displayed when the user searches for the product. Furthermore, the automated tagging system acquires the user's behavior history. For example, the automated tagging system collects the user's search history and purchase history. If the user searches for "red shirt," that search history is acquired. Based on the acquired behavior history, it prioritizes the assignment of highly relevant tags. For example, if a user has a search history for "red shirt," tags such as "red" and "shirt" will be prioritized. The automatic tagging system also accepts user feedback. For instance, if a user provides feedback that the tag "red" is inappropriate for a "red shirt," the system will revise the tag based on that information. In this way, a system is realized that analyzes the content of images and text and automatically generates and assigns highly relevant tags based on the user's behavior history and feedback. As a result, the automatic tagging system can analyze the content of images and text and automatically generate and assign relevant tags.

[0069] The automated tagging system according to this embodiment comprises an analysis unit, a generation unit, and an assignment unit. The analysis unit analyzes the content of product images or text related to products. The analysis unit analyzes the color and shape of products using, for example, an image analysis algorithm. The analysis unit analyzes product descriptions and reviews using, for example, a text analysis method. The analysis unit analyzes the meaning of text using, for example, natural language processing technology. The generation unit generates tags based on the information analyzed by the analysis unit. The generation unit generates, for example, keyword tags based on the analyzed information. The generation unit generates, for example, category tags based on the analyzed information. The generation unit generates, for example, attribute tags based on the analyzed information. The assignment unit assigns the tags generated by the generation unit to products. The assignment unit associates the generated tags with products, for example. The assignment unit registers the generated tags in a product database, for example. The assignment unit makes the generated tags visible when a user searches for them, for example. Thus, the automated tagging system according to this embodiment can analyze the content of product images and text and automatically generate and assign relevant tags.

[0070] The analysis unit analyzes product images or text content related to products. Specifically, it uses image analysis algorithms to analyze the color and shape of products. For example, it uses a convolutional neural network (CNN) to extract features from product images and identify attributes such as color, shape, and pattern. This allows for the acquisition of detailed information based on the product's appearance. It also uses text analysis techniques to analyze product descriptions and reviews. For example, it uses morphological analysis to segment the text and analyze the meaning and relationships of each word. Furthermore, it uses natural language processing techniques to analyze the meaning of the text. For example, it uses generative AI to extract important keywords and phrases from product descriptions and reviews to understand product characteristics and user evaluations. As a result, the analysis unit can acquire product information from multiple perspectives using both images and text and perform detailed analysis. By combining these technologies, the analysis unit can grasp product characteristics with high accuracy and provide the information necessary for subsequent tag generation.

[0071] The generation unit generates tags based on the information analyzed by the analysis unit. Specifically, it generates keyword tags based on the analyzed information. For example, it generates keyword tags such as "red" and "round" based on the product's color and shape. It also generates tags such as "highly rated" and "popular product" based on important keywords extracted from the product description and reviews. Furthermore, it generates category tags based on the analyzed information. For example, it generates category tags such as "home appliances" and "fashion" based on the product's use and category. This allows users to narrow down their search by category when searching for products. Furthermore, it generates attribute tags based on the analyzed information. For example, it generates attribute tags such as "waterproof" and "lightweight" based on the product's characteristics and functions. The generation unit can use machine learning algorithms to automatically generate these tags. For example, it can use supervised learning to learn tag generation patterns from past data and generate appropriate tags for new products. As a result, the generation unit can generate a variety of tags with high accuracy based on the information provided by the analysis unit, accurately representing the characteristics of the products.

[0072] The tagging unit assigns tags generated by the generation unit to products. Specifically, it associates the generated tags with products. For example, it adds the generated tags to each product entry in the product database. It also registers the generated tags in the product database. This allows the product database to store related tag information along with detailed information about each product. Furthermore, it ensures that the generated tags are displayed when users search for them. For example, if a user searches for "waterproof," products with the corresponding tag will be displayed in the search results. The tagging unit can integrate with database management systems and search engines to automate these tagging processes. For example, it can create indexes to efficiently manage tag information and respond quickly to search queries. This allows the tagging unit to efficiently and effectively assign generated tags to products, improving user convenience when searching for products. Furthermore, the tagging unit can also update and delete tags. For example, if new information is analyzed or product characteristics change, it updates the tags accordingly to reflect the latest information. This ensures that the tagging unit always maintains the latest tag information and provides accurate information to users.

[0073] The acquisition unit can acquire the user's activity history with respect to the product. For example, the acquisition unit can acquire the user's search history for the product. For example, the acquisition unit can acquire the user's purchase history for the product. For example, the acquisition unit can acquire the user's browsing history for the product. Based on the activity history acquired by the acquisition unit, the generation unit can preferentially assign tags that are highly relevant to the user from among the generated tags to the product. For example, if the user has a history of searching for "red shirt," the generation unit will preferentially assign tags such as "red" and "shirt." For example, if the user has a history of purchasing "sports equipment," the generation unit will preferentially assign tags such as "sports" and "exercise." For example, if the user has a history of browsing "electronic devices," the generation unit will preferentially assign tags such as "electronic devices" and "gadgets." This allows for the preferential assignment of highly relevant tags based on the user's activity history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's activity history into AI and generate data for preferentially assigning highly relevant tags.

[0074] The feedback unit can receive feedback from users. For example, the feedback unit can receive comments from users about the appropriateness of tags. For example, the feedback unit can receive evaluations of tags from users. For example, the feedback unit can receive responses from users to questionnaires. The tagging unit can change the tags assigned to products based on the feedback. For example, if a user provides feedback that the tag "red" is inappropriate for a "red shirt," the tagging unit will correct the tag based on that information. For example, if a user provides feedback that the tag "exercise" is inappropriate for "sports equipment," the tagging unit will correct the tag based on that information. For example, if a user provides feedback that the tag "gadget" is inappropriate for "electronic devices," the tagging unit will correct the tag based on that information. This allows for improvement of tag accuracy based on user feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user feedback data into AI to generate data for evaluating the appropriateness of tags.

[0075] The acquisition unit can acquire search history, which is the history of when a user has searched for a product, or purchase history, which is the history of when a user has purchased a product, as behavioral history. For example, the acquisition unit can acquire the history of when a user has searched for "red shirt". For example, the acquisition unit can acquire the history of when a user has purchased "sports equipment". For example, the acquisition unit can acquire the history of when a user has searched for "electronic devices". By acquiring the user's search history and purchase history, it becomes possible to assign tags based on behavioral history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input the user's search history and purchase history into AI and generate data for generating highly relevant tags.

[0076] The tagging unit can assign a tag corresponding to the first product to the second product and a tag corresponding to the second product to the first product if the same user has taken action on both the first and second products. For example, if a user searches for "red shirt" and "blue shirt," the tagging unit will assign the "blue shirt" tag to "red shirt" and the "red shirt" tag to "blue shirt." For example, if a user purchases "sports equipment" and "outdoor equipment," the tagging unit will assign the "outdoor equipment" tag to "sports equipment" and the "sports equipment" tag to "outdoor equipment." For example, if a user views "electronic devices" and "home appliances," the tagging unit will assign the "home appliances" tag to "electronic devices" and the "electronic devices" tag to "home appliances." This allows relevant tags to be assigned to multiple products based on the user's browsing history. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input user behavior history data into the AI ​​and generate data for creating relevant tags.

[0077] The tagging unit can assign tags related to the attributes of users who have interacted with a product. For example, the tagging unit can assign tags based on the user's age. For example, the tagging unit can assign tags based on the user's gender. For example, the tagging unit can assign tags based on the user's place of residence. This allows tags related to products to be assigned based on the user's attributes. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input user attribute data into AI and generate data for generating relevant tags.

[0078] The analysis unit can correct the analysis results based on the product's background information during image analysis. For example, the analysis unit can analyze the scenery in the background of the product and correct the product's characteristics. For example, the analysis unit can analyze the location where the product was photographed and correct the product's characteristics. For example, the analysis unit can analyze the date and time the product was photographed and correct the product's characteristics. This improves the accuracy of image analysis based on the product's background information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the product's background information into AI and generate data to correct the analysis results.

[0079] The analysis unit can enhance its analysis results by referring to product reviews and ratings during text analysis. For example, the analysis unit can analyze user comments to enhance product features. For example, the analysis unit can analyze rating scores to enhance product features. For example, the analysis unit can analyze review dates and times to enhance product features. This allows the accuracy of text analysis to be improved by referring to product reviews and ratings. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product review and rating data into AI to generate data to enhance the analysis results.

[0080] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is excited, the analysis unit can increase the accuracy of the analysis and extract detailed information. For example, if the user is relaxed, the analysis unit can maintain normal accuracy and extract standard information. For example, if the user is stressed, the analysis unit can decrease the accuracy of the analysis and extract simplified information. By adjusting the accuracy of the analysis based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and generate data to adjust the accuracy of the analysis.

[0081] The analysis unit can estimate the usage scenario of a product during image analysis and reflect this in the analysis results. For example, if the product is used outdoors, the analysis unit analyzes the natural environment in the background and generates outdoor-related tags. For example, if the product is used indoors, the analysis unit analyzes the furniture and interior and generates home decor-related tags. For example, if the product is used at an event, the analysis unit analyzes the type of event and generates party and festival-related tags. By estimating the usage scenario of the product, it is possible to generate more relevant tags. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product usage scenario data into AI and generate data to reflect in the analysis results.

[0082] The analysis unit can enhance the analysis results by referencing relevant trend information for products during text analysis. For example, the analysis unit can refer to the latest fashion trends and add relevant keywords to the analysis results. For example, the analysis unit can refer to current market trends and reflect high-demand product categories in the analysis results. For example, the analysis unit can refer to trends on social media and include popular hashtags in the analysis results. This improves the accuracy of text analysis by referencing relevant trend information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input trend information data into AI to generate data to enhance the analysis results.

[0083] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is excited, the analysis unit will prioritize analyzing the latest product information. If the user is relaxed, the analysis unit will prioritize analyzing past purchase history. If the user is stressed, the analysis unit will prioritize analyzing simple information. By determining the priority of analysis based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and generate data for determining the priority of analysis.

[0084] The analysis unit can correct the analysis results by referring to the product's manufacturer information during image analysis. For example, if the product's manufacturer has a high rating, the analysis unit can add quality-related tags. For example, if the manufacturer is located in a specific region, the analysis unit can add tags related to that region. For example, if the manufacturer is a specific brand, the analysis unit can add tags related to that brand. This improves the accuracy of image analysis by referring to the product's manufacturer information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input manufacturer information data into AI and generate data to correct the analysis results.

[0085] The analysis unit can enhance the analysis results by referring to relevant patent information of the product during text analysis. For example, if there are patents related to the product, the analysis unit will include that patent information in the analysis results. For example, the analysis unit will analyze the technical content of the patent and add technical tags. For example, the analysis unit will refer to the applicant information of the patent and include the company name and researcher name in the tags. This improves the accuracy of text analysis by referring to relevant patent information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input patent information data into AI and generate data to enhance the analysis results.

[0086] The generation unit can estimate the user's emotions and adjust the way the generated tags are expressed based on the estimated user emotions. For example, if the user is relaxed, the generation unit will generate tags with soft expressions. For example, if the user is excited, the generation unit will generate tags with emphasized expressions. For example, if the user is stressed, the generation unit will generate tags with simple and easy-to-understand expressions. In this way, by adjusting the way tags are expressed based on the user's emotions, more appropriate tags can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user emotion data into the generation AI and generate data to adjust the way tags are expressed.

[0087] The generation unit can adjust the level of detail of tags when generating tags, taking into account the market value of the product. For example, the generation unit can generate detailed tags for expensive products, standard tags for general products, and simplified tags for inexpensive products. By adjusting the level of detail of tags based on the market value of the product, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input market value data of products into AI and generate data for adjusting the level of detail of tags.

[0088] The generation unit can apply different generation algorithms depending on the product category when generating tags. For example, the generation unit can apply an algorithm that generates tags based on color and style to products in the fashion category. For example, the generation unit can apply an algorithm that generates tags based on function and specifications to products in the electronics category. For example, the generation unit can apply an algorithm that generates tags based on ingredients and taste to products in the food category. By applying different generation algorithms depending on the product category, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product category data into AI and generate data for applying different generation algorithms.

[0089] The generation unit can estimate the user's emotions and adjust the length of the tags it generates based on the estimated emotions. For example, if the user is in a hurry, the generation unit generates short tags. For example, if the user is relaxed, the generation unit generates detailed tags. For example, if the user is excited, the generation unit generates long, emphasized tags. By adjusting the tag length based on the user's emotions, more appropriate tags can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into a generation AI and generate data for adjusting the tag length.

[0090] The generation unit can determine the priority of tags based on the product's sales period when generating tags. For example, the generation unit can prioritize generating tags based on the latest trends for new products. For example, the generation unit can prioritize generating seasonal tags for seasonal products. For example, the generation unit can prioritize generating tags related to discounts and benefits for sale products. By determining the priority of tags based on the product's sales period, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product sales period data into AI and generate data for determining tag priority.

[0091] The generation unit can adjust the order of tags based on product relevance when generating tags. For example, the generation unit may display the most relevant tags first. For example, the generation unit may display less relevant tags later. For example, the generation unit may prioritize displaying highly relevant tags based on the user's search history. This allows for the generation of more appropriate tags by adjusting the order of tags based on product relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product relevance data into AI and generate data for adjusting the order of tags.

[0092] The tagging unit can estimate the user's emotions and adjust the tagging method based on the estimated emotions. For example, if the user is relaxed, the tagging unit will assign detailed tags. For example, if the user is in a hurry, the tagging unit will assign simplified tags. For example, if the user is excited, the tagging unit will assign emphasized tags. This allows for more appropriate tags to be assigned by adjusting the tagging method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tagging unit may be performed using AI or not. For example, the tagging unit can input user emotion data into a generative AI and generate data to adjust the tagging method.

[0093] The tagging unit can select the most appropriate tags by referring to the user's past behavior history when assigning tags. For example, the tagging unit can select tags based on keywords the user has searched for in the past. For example, the tagging unit can select tags based on products the user has purchased in the past. For example, the tagging unit can select tags based on products the user has rated in the past. This allows for the selection of more appropriate tags based on the user's past behavior history. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's past behavior history data into AI to generate data for selecting the most appropriate tags.

[0094] The tagging unit can customize tags based on the current market conditions of a product when assigning tags. For example, the tagging unit assigns demand-related tags to products with high market demand. For example, the tagging unit assigns scarcity-related tags to products with low market supply. For example, the tagging unit assigns trend-related tags based on market trends. This allows for the assignment of more appropriate tags by customizing them based on the market conditions of a product. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input market condition data for a product into AI and generate data for customizing tags.

[0095] The tagging unit can estimate the user's emotions and determine the priority of tag assignment based on the estimated user emotions. For example, if the user is relaxed, the tagging unit will prioritize assigning detailed tags. For example, if the user is in a hurry, the tagging unit will prioritize assigning simplified tags. For example, if the user is excited, the tagging unit will prioritize assigning emphasized tags. This allows for the assignment of more appropriate tags by determining the priority of tag assignment based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tagging unit may be performed using AI or not using AI. For example, the tagging unit can input user emotion data into a generative AI and generate data for determining the priority of tag assignment.

[0096] The tagging unit can select the most appropriate tags when assigning tags, taking into account the user's geographical location information. For example, if the user is in a specific region, the tagging unit will assign tags related to that region. For example, if the user is traveling, the tagging unit will assign tags related to the travel destination. For example, if the user is at home, the tagging unit will assign tags related to home. This allows for the selection of more appropriate tags based on the user's geographical location information. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's geographical location data into AI to generate data for selecting the most appropriate tags.

[0097] The tagging unit can analyze the user's social media activity and suggest tags when assigning tags. For example, the tagging unit can suggest tags based on what the user has shared on social media. For example, the tagging unit can suggest tags based on the accounts the user follows on social media. For example, the tagging unit can suggest tags based on posts the user has liked on social media. This allows for the suggestion of more appropriate tags based on the user's social media activity. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's social media activity data into AI and generate data for suggesting tags.

[0098] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring behavioral history based on the estimated user emotions. For example, if the user is relaxed, the acquisition unit acquires behavioral history periodically. For example, if the user is in a hurry, the acquisition unit acquires behavioral history in real time. For example, if the user is excited, the acquisition unit acquires behavioral history frequently. By adjusting the timing of acquiring behavioral history based on the user's emotions, more appropriate behavioral history can be acquired. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input user emotion data into a generative AI and generate data to adjust the timing of acquiring behavioral history.

[0099] The data acquisition unit can analyze the user's past behavior history and select the optimal data acquisition method. For example, the data acquisition unit can acquire behavior history based on keywords the user has frequently searched for in the past. For example, the data acquisition unit can acquire behavior history based on products the user has purchased in the past. For example, the data acquisition unit can acquire behavior history based on products the user has rated in the past. This allows the system to select the optimal data acquisition method based on the user's past behavior history. Some or all of the above processing in the data acquisition unit may be performed using AI, for example, or without AI. For example, the data acquisition unit can input the user's past behavior history data into AI and generate data for selecting the optimal data acquisition method.

[0100] The acquisition unit can filter the behavioral history based on the user's current living situation and areas of interest when acquiring it. For example, the acquisition unit acquires relevant behavioral history based on the user's current living situation. For example, the acquisition unit acquires relevant behavioral history based on the user's areas of interest. For example, the acquisition unit combines the user's current living situation and areas of interest to acquire the most relevant behavioral history. This makes it possible to acquire more relevant behavioral history based on the user's current living situation and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's living situation and areas of interest data into AI to generate data for filtering.

[0101] The acquisition unit can estimate the user's emotions and determine the priority of the behavioral history to acquire based on the estimated user emotions. For example, if the user is relaxed, the acquisition unit will prioritize acquiring past behavioral history. For example, if the user is in a hurry, the acquisition unit will prioritize acquiring recent behavioral history. For example, if the user is excited, the acquisition unit will prioritize acquiring behavioral history related to a specific event. This allows for the acquisition of more appropriate behavioral history by prioritizing behavioral history based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input user emotion data into a generative AI and generate data for determining the priority of behavioral history.

[0102] The acquisition unit can prioritize the acquisition of highly relevant history by considering the user's geographical location information when acquiring activity history. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of activity history related to that region. For example, if the user is traveling, the acquisition unit will prioritize the acquisition of activity history related to the travel destination. For example, if the user is at home, the acquisition unit will prioritize the acquisition of activity history related to home. This allows for the acquisition of more relevant activity history based on the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into AI to generate data for prioritizing the acquisition of highly relevant history.

[0103] The acquisition unit can analyze the user's social media activity and acquire relevant history when acquiring behavioral history. For example, the acquisition unit can acquire behavioral history based on content shared by the user on social media. For example, the acquisition unit can acquire behavioral history based on accounts followed by the user on social media. For example, the acquisition unit can acquire behavioral history based on posts liked by the user on social media. This makes it possible to acquire more relevant behavioral history based on the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into AI and generate data for acquiring relevant history.

[0104] The feedback unit can estimate the user's emotions and adjust how feedback is received based on the estimated emotions. For example, if the user is relaxed, the feedback unit will accept detailed feedback. If the user is in a hurry, the feedback unit will accept simplified feedback. If the user is excited, the feedback unit will accept emphasized feedback. This allows for more appropriate feedback to be received by adjusting how feedback is received based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not using AI. For example, the feedback unit can input user emotion data into a generative AI and generate data to adjust how feedback is received.

[0105] The feedback unit can select the optimal response when it receives feedback by referring to the user's past feedback history. For example, the feedback unit can select a response based on the feedback the user has provided in the past. For example, the feedback unit can select the optimal response from the user's past feedback history. For example, the feedback unit can analyze the user's past feedback history and select the most appropriate response. This allows for the selection of a more appropriate response based on the user's past feedback history. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's past feedback history data into AI to generate data for selecting the optimal response.

[0106] The feedback unit can provide the most appropriate response when it receives feedback, taking into account the user's current location. For example, if the user is in a specific region, the feedback unit will provide a response relevant to that region. For example, if the user is traveling, the feedback unit will provide a response relevant to their travel destination. For example, if the user is at home, the feedback unit will provide a response relevant to their home. This allows for the provision of a more appropriate response based on the user's current location. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's location data into AI to generate data for providing the most appropriate response.

[0107] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. For example, if the user is relaxed, the feedback unit will prioritize detailed feedback. If the user is in a hurry, the feedback unit will prioritize simplified feedback. If the user is excited, the feedback unit will prioritize emphasized feedback. This allows for more appropriate feedback to be received by prioritizing feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input user emotion data into a generative AI to generate data for determining the priority of feedback.

[0108] The feedback unit can provide the optimal response when receiving feedback, taking into account the user's device information. For example, if the user is using a smartphone, the feedback unit will provide a response optimized for smartphones. For example, if the user is using a tablet, the feedback unit will provide a response optimized for tablets. For example, if the user is using a smartwatch, the feedback unit will provide a response optimized for smartwatches. This allows for the provision of a more appropriate response based on the user's device information. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user device information data into AI and generate data to provide the optimal response.

[0109] The feedback unit can provide multilingual feedback when it receives feedback, depending on the user's language settings. The feedback unit can, for example, automatically set the language of the feedback based on the language settings of the user's device. The feedback unit can, for example, provide a language switching function if the user uses multiple languages. The feedback unit can, for example, provide feedback in a language selected by the user. This allows for the provision of more appropriate feedback based on the user's language settings. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's language setting data into AI and generate data for providing multilingual feedback.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is excited, the analysis unit will prioritize analyzing the latest product information. If the user is relaxed, the analysis unit will prioritize analyzing past purchase history. If the user is stressed, the analysis unit will prioritize analyzing simple information. By determining the priority of analysis based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and generate data for determining the priority of analysis.

[0112] The generation unit can adjust the level of detail of tags when generating tags, taking into account the market value of the product. For example, the generation unit can generate detailed tags for expensive products, standard tags for general products, and simplified tags for inexpensive products. By adjusting the level of detail of tags based on the market value of the product, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input market value data of products into AI and generate data for adjusting the level of detail of tags.

[0113] The tagging unit can estimate the user's emotions and adjust the tagging method based on the estimated emotions. For example, if the user is relaxed, the tagging unit will assign detailed tags. For example, if the user is in a hurry, the tagging unit will assign simplified tags. For example, if the user is excited, the tagging unit will assign emphasized tags. This allows for more appropriate tags to be assigned by adjusting the tagging method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tagging unit may be performed using AI or not. For example, the tagging unit can input user emotion data into a generative AI and generate data to adjust the tagging method.

[0114] The analysis unit can correct the analysis results based on the product's background information during image analysis. For example, the analysis unit can analyze the scenery in the background of the product and correct the product's characteristics. For example, the analysis unit can analyze the location where the product was photographed and correct the product's characteristics. For example, the analysis unit can analyze the date and time the product was photographed and correct the product's characteristics. This improves the accuracy of image analysis based on the product's background information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the product's background information into AI and generate data to correct the analysis results.

[0115] The generation unit can estimate the user's emotions and adjust the way the generated tags are expressed based on the estimated user emotions. For example, if the user is relaxed, the generation unit will generate tags with soft expressions. For example, if the user is excited, the generation unit will generate tags with emphasized expressions. For example, if the user is stressed, the generation unit will generate tags with simple and easy-to-understand expressions. In this way, by adjusting the way tags are expressed based on the user's emotions, more appropriate tags can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user emotion data into the generation AI and generate data to adjust the way tags are expressed.

[0116] The tagging unit can select the most appropriate tags when assigning tags, taking into account the user's geographical location information. For example, if the user is in a specific region, the tagging unit will assign tags related to that region. For example, if the user is traveling, the tagging unit will assign tags related to the travel destination. For example, if the user is at home, the tagging unit will assign tags related to home. This allows for the selection of more appropriate tags based on the user's geographical location information. Some or all of the above processing in the tagging unit may be performed using AI, for example, or without AI. For example, the tagging unit can input the user's geographical location data into AI to generate data for selecting the most appropriate tags.

[0117] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring behavioral history based on the estimated user emotions. For example, if the user is relaxed, the acquisition unit acquires behavioral history periodically. For example, if the user is in a hurry, the acquisition unit acquires behavioral history in real time. For example, if the user is excited, the acquisition unit acquires behavioral history frequently. By adjusting the timing of acquiring behavioral history based on the user's emotions, more appropriate behavioral history can be acquired. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input user emotion data into a generative AI and generate data to adjust the timing of acquiring behavioral history.

[0118] The analysis unit can enhance its analysis results by referring to product reviews and ratings during text analysis. For example, the analysis unit can analyze user comments to enhance product features. For example, the analysis unit can analyze rating scores to enhance product features. For example, the analysis unit can analyze review dates and times to enhance product features. This allows the accuracy of text analysis to be improved by referring to product reviews and ratings. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input product review and rating data into AI to generate data to enhance the analysis results.

[0119] The generation unit can apply different generation algorithms depending on the product category when generating tags. For example, the generation unit can apply an algorithm that generates tags based on color and style to products in the fashion category. For example, the generation unit can apply an algorithm that generates tags based on function and specifications to products in the electronics category. For example, the generation unit can apply an algorithm that generates tags based on ingredients and taste to products in the food category. By applying different generation algorithms depending on the product category, more appropriate tags can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input product category data into AI and generate data for applying different generation algorithms.

[0120] The feedback unit can estimate the user's emotions and adjust how feedback is received based on the estimated emotions. For example, if the user is relaxed, the feedback unit will accept detailed feedback. If the user is in a hurry, the feedback unit will accept simplified feedback. If the user is excited, the feedback unit will accept emphasized feedback. This allows for more appropriate feedback to be received by adjusting how feedback is received based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not using AI. For example, the feedback unit can input user emotion data into a generative AI and generate data to adjust how feedback is received.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The analysis unit analyzes the product image or the content of the text related to the product. For example, the analysis unit uses image analysis algorithms to analyze the color and shape of the product, and text analysis methods to analyze the product description and reviews. It also uses natural language processing technology to analyze the meaning of the text. Step 2: The generation unit generates tags based on the information analyzed by the analysis unit. For example, the generation unit generates keyword tags, category tags, and attribute tags based on the analyzed information. Step 3: The tagging unit assigns the tags generated by the generation unit to the products. For example, the tagging unit associates the generated tags with the products, registers them in the product database, and makes them visible when users search for them.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] For example, the analysis unit, generation unit, assignment unit, acquisition unit, and feedback unit are implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12, and analyzes the content of images and text. The generation unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12, and generates tags based on the analyzed information. The assignment unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and assigns the generated tags to products. The acquisition unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12, and acquires the user's behavior history. The feedback unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and receives feedback from the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] For example, the analysis unit, generation unit, assignment unit, acquisition unit, and feedback unit are implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12, and analyzes the content of images and text. The generation unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12, and generates tags based on the analyzed information. The assignment unit is implemented by the control unit 46A of the smart glasses 214 or the identification processing unit 290 of the data processing unit 12, and assigns the generated tags to products. The acquisition unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12, and acquires the user's behavior history. The feedback unit is implemented by the control unit 46A of the smart glasses 214 or the identification processing unit 290 of the data processing unit 12, and receives feedback from the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] For example, the analysis unit, generation unit, assignment unit, acquisition unit, and feedback unit are implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12, and analyzes the content of images and text. The generation unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12, and generates tags based on the analyzed information. The assignment unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and assigns the generated tags to products. The acquisition unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12, and acquires the user's behavior history. The feedback unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and receives feedback from the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] For example, the analysis unit, generation unit, assignment unit, acquisition unit, and feedback unit are implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12, and analyzes the content of images and text. The generation unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12, and generates tags based on the analyzed information. The assignment unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and assigns the generated tags to products. The acquisition unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12, and acquires the user's behavior history. The feedback unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and receives feedback from the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) An analysis unit that analyzes the content of product images or text related to products, A generation unit that generates tags based on the information analyzed by the analysis unit, The system includes an attachment unit that attaches the tags generated by the generation unit to the product. A system characterized by the following features. (Note 2) It includes an acquisition unit that acquires the user's behavioral history regarding the aforementioned product, The generating unit is Based on the behavioral history acquired by the acquisition unit, Of the tags generated by the generation unit, tags that are highly relevant to the user are given priority and assigned to the product. The system described in Appendix 1, characterized by the features described herein. (Note 3) It also includes a feedback section to receive feedback from users. The aforementioned attachment unit is, Based on the aforementioned feedback, Change the tags attached to the product. The system described in Appendix 1, characterized by the features described herein. (Note 4) The acquisition unit is, As for the aforementioned behavioral history, The system retrieves the user's search history (the history of products the user has searched for) or their purchase history (the history of products the user has purchased). The system described in Appendix 2, characterized by the features described herein. (Note 5) The aforementioned attachment unit is, If the same user performs actions on both the first and second products, A tag corresponding to the first product is attached to the second product. A tag corresponding to the second product is attached to the first product. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned attachment unit is, Tags are assigned to users who interacted with a product, based on their attributes. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, During image analysis, The analysis results are corrected based on the product's background information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, During text analysis, Enhance your analysis results by referring to product reviews and ratings. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, To estimate the user's emotions, Adjust the accuracy of the analysis based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During image analysis, Estimate the usage scenarios of the product and reflect them in the analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During text analysis, Enhance your analysis results by referencing relevant trend information for the product. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, To estimate the user's emotions, Prioritize analysis based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During image analysis, Correct the analysis results by referring to the product manufacturer's information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During text analysis, Enhance analysis results by referring to patent information related to the product. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is To estimate the user's emotions, Adjust the way tags are expressed based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating tags, Adjust the level of detail on the tags to reflect the market value of the product. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating tags, Apply different generation algorithms depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is To estimate the user's emotions, Adjust the length of tags generated based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating tags, Prioritize tags based on when the product was released. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating tags, Adjust the order of tags based on product relevance. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned attachment unit is, To estimate the user's emotions, Adjust the tagging method based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned attachment unit is, When adding tags, The system selects the most suitable tags by referencing the user's past behavior history. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned attachment unit is, When adding tags, Customize tags based on the current market conditions of the product. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned attachment unit is, To estimate the user's emotions, The priority of tag assignment is determined based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned attachment unit is, When adding tags, Select the optimal tag considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned attachment unit is, When adding tags, Analyze users' social media activity and suggest tags. The system described in Appendix 1, characterized by the features described herein. (Note 27) The acquisition unit is, To estimate the user's emotions, Adjust the timing of behavioral history acquisition based on estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 28) The acquisition unit is, By analyzing the user's past behavior history, Select the optimal acquisition method. The system described in Appendix 2, characterized by the features described herein. (Note 29) The acquisition unit is, When acquiring behavioral history, Filtering is performed based on the user's current lifestyle and areas of interest. The system described in Appendix 2, characterized by the features described herein. (Note 30) The acquisition unit is, To estimate the user's emotions, Prioritize the behavioral history to be retrieved based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 31) The acquisition unit is, When acquiring behavioral history, Prioritize retrieving highly relevant history by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 32) The acquisition unit is, When acquiring behavioral history, Analyze users' social media activity and retrieve relevant history. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned feedback unit is To estimate the user's emotions, We adjust how we accept feedback based on estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned feedback unit is When receiving feedback, Refer to the user's past feedback history to select the most appropriate response. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned feedback unit is When receiving feedback, Providing the optimal response while considering the user's current location. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned feedback unit is To estimate the user's emotions, Prioritize feedback based on estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned feedback unit is When receiving feedback, We provide the optimal solution by taking into account the user's device information. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned feedback unit is When receiving feedback, Provides multilingual feedback based on the user's language settings. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the content of product images or text related to products, A generation unit that generates tags based on the information analyzed by the analysis unit, The system includes an attachment unit that attaches the tags generated by the generation unit to the product. A system characterized by the following features.

2. It includes an acquisition unit that acquires the user's behavioral history regarding the aforementioned product, The generating unit is Based on the behavioral history acquired by the acquisition unit, Of the tags generated by the generation unit, tags that are highly relevant to the user are given priority and assigned to the product. The system according to feature 1.

3. It also includes a feedback section to receive feedback from users. The aforementioned attachment unit is, Based on the aforementioned feedback, Change the tags attached to the product. The system according to feature 1.

4. The acquisition unit is, As for the aforementioned behavioral history, The system retrieves the user's search history (the history of products the user has searched for) or their purchase history (the history of products the user has purchased). The system according to feature 2.

5. The aforementioned attachment unit is, If the same user performs actions on both the first and second products, A tag corresponding to the first product is attached to the second product. A tag corresponding to the second product is attached to the first product. The system according to feature 1.

6. The aforementioned attachment unit is, Tags are assigned to users who interacted with a product, based on their attributes. The system according to feature 1.

7. The aforementioned analysis unit, During image analysis, The analysis results are corrected based on the product's background information. The system according to feature 1.

8. The aforementioned analysis unit, During text analysis, Enhance your analysis results by referring to product reviews and ratings. The system according to feature 1.

9. The aforementioned analysis unit, Estimate the user's emotions, Adjust the accuracy of the analysis based on the estimated user's sentiment. The system according to feature 1.

Images