system

Abstract

The system according to this embodiment aims to streamline e-commerce site operations and propose appropriate targeting strategies and marketing measures. [Solution] The system according to the embodiment comprises a product registration support unit, a targeting proposal unit, and a data analysis unit. The product registration support unit automatically analyzes product information and images and assists in uploading them in an appropriate format. The targeting proposal unit analyzes purchase history and behavioral data based on the information analyzed by the product registration support unit and proposes an appropriate targeting strategy. The data analysis unit analyzes site data in real time based on the strategy proposed by the targeting proposal unit and proposes optimal marketing measures.

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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 in EC site operation, it takes a lot of time and effort for product registration, promotion creation, and data analysis, and efficient operation is difficult.

[0005] The system according to the embodiment aims to improve the efficiency of EC site operation and propose appropriate targeting strategies and marketing measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a product registration support unit, a targeting proposal unit, and a data analysis unit. The product registration support unit automatically analyzes product information and images and assists in uploading them in an appropriate format. The targeting proposal unit analyzes purchase history and behavioral data based on the information analyzed by the product registration support unit and proposes an appropriate targeting strategy. The data analysis unit analyzes site data in real time based on the strategy proposed by the targeting proposal unit and proposes optimal marketing measures. [Effects of the Invention]

[0007] The system according to this embodiment can streamline e-commerce site operations and propose appropriate targeting strategies and marketing measures. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also 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) The e-commerce operation support system according to an embodiment of the present invention is a system that utilizes AI to streamline the operation of e-commerce (EC) sites. The EC operation support system uses AI to automatically analyze product information and images and assist in uploading them in the appropriate format. This enables automatic editing of product images and automatic generation of text, significantly reducing the effort required for product registration. Next, the AI ​​analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. This allows for the automatic creation and execution of personalized promotions. Furthermore, the AI ​​analyzes site data in real time and proposes optimal marketing measures. For example, it can read data from access analysis tools and report improvement suggestions. First, the AI ​​automatically analyzes product information and images and assists in uploading them in the appropriate format. At this time, it automatically adjusts the quality of product images and automatically generates product descriptions. For example, when adding a new product, the AI ​​can automatically edit images and generate appropriate descriptions, significantly reducing the effort required from the operator. Next, the AI ​​analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. For example, it can provide promotional information related to a product to customers who have purchased that specific product. This maximizes promotional effectiveness and increases sales. Furthermore, AI analyzes site data in real time and proposes optimal marketing strategies. For example, it can read data from access analytics tools, analyze site access data and user behavior, and identify areas for improvement. This optimizes the site and improves the user experience. This system allows e-commerce site operators to focus on the quality of their products and services. For example, they can concentrate on product development and create effective marketing strategies. They are also freed from the complexities of data analysis, which can lead to increased sales. In this way, utilizing AI can significantly improve the efficiency of e-commerce site operations. Operators are freed from tedious daily tasks and can concentrate on larger strategies and service improvements. Moreover, the increased efficiency of e-commerce site operations can lead to sustainable growth.This allows the e-commerce operation support system to streamline the operation of e-commerce sites, enabling operators to focus on the quality of their products and services.

[0029] The e-commerce operation support system according to this embodiment comprises a product registration support unit, a targeting proposal unit, and a data analysis unit. The product registration support unit automatically analyzes product information and images and assists in uploading them in an appropriate format. For example, the product registration support unit automatically collects product information, analyzes images, and converts them into an appropriate format. The product registration support unit can also automatically adjust image quality and automatically generate product descriptions. For example, the product registration support unit automatically adjusts image resolution and corrects color tones. The product registration support unit can also generate appropriate descriptions based on product characteristics. The targeting proposal unit analyzes purchase history and behavioral data based on the information analyzed by the product registration support unit and proposes an appropriate targeting strategy. For example, the targeting proposal unit analyzes purchase history and provides relevant promotional information to customers who have purchased specific products. The targeting proposal unit can also analyze behavioral data and propose personalized promotions based on customer interests. For example, the targeting proposal unit analyzes customer browsing history and proposes products that may be of interest to the customer. The Data Analysis Department analyzes site data in real time based on the strategies proposed by the Targeting Proposal Department and proposes optimal marketing measures. For example, the Data Analysis Department reads data from access analysis tools and analyzes site access data and user behavior. The Data Analysis Department can also identify areas for improvement based on the analysis results and propose specific improvement plans. For example, the Data Analysis Department analyzes page views and time spent on the site and proposes measures to improve the user experience. As a result, the e-commerce operation support system according to this embodiment can significantly reduce the effort required for product registration by automatically analyzing product information and images and assisting in uploading them in the appropriate format, analyze purchase history and behavioral data to propose appropriate targeting strategies, and analyze site data in real time to propose optimal marketing measures.

[0030] The Product Registration Support Department automatically analyzes product information and images and assists in uploading them in the appropriate format. Specifically, the Product Registration Support Department automatically collects product information, analyzes images, and converts them into the appropriate format. For example, product information is automatically obtained from the manufacturer's database and website, and information such as product name, price, and description is extracted. In image analysis, AI is used to recognize the content of the image and perform actions such as background removal, cropping, resolution adjustment, and color correction. This makes product images visually appealing and attractive to consumers. The Product Registration Support Department can also generate appropriate introductory text based on the product's characteristics. For example, AI analyzes the product's characteristics and automatically generates an introductory text that includes the product's advantages, usage instructions, and target users. This introductory text is optimized for search engines (SEO) by appropriately placing keywords to improve search engine rankings. Furthermore, the Product Registration Support Department supports multiple languages, making it suitable for international e-commerce site operations. As a result, the Product Registration Support Department can efficiently and efficiently upload product information and images with high quality, significantly reducing the burden on e-commerce site operators.

[0031] The Targeting Proposal Department analyzes purchase history and behavioral data based on information analyzed by the Product Registration Support Department and proposes appropriate targeting strategies. Specifically, the Targeting Proposal Department analyzes customers' purchase history and provides relevant promotional information to customers who have purchased specific products. For example, it might propose promotions for new sportswear and accessories to customers who have previously purchased sporting goods. The Targeting Proposal Department can also analyze customer behavioral data and propose personalized promotions based on customer interests. For example, it might analyze a customer's browsing history and focus promotions on products in a specific category for customers who are interested in that category. Furthermore, the Targeting Proposal Department uses AI to predict customer behavior patterns and develop strategies to increase future purchasing intent. For example, if a customer frequently views a particular product, it can encourage purchases by providing special offers and discounts related to that product. In this way, the Targeting Proposal Department can provide optimal promotions for each individual customer, achieving increased sales and customer satisfaction.

[0032] The Data Analysis Department analyzes website data in real time based on the strategies proposed by the Targeting Proposal Department and proposes optimal marketing measures. Specifically, the Data Analysis Department reads data from access analysis tools and analyzes website access data and user behavior. For example, it analyzes metrics such as page views, time on site, bounce rate, and conversion rate to evaluate website performance. The Data Analysis Department can also identify areas for improvement based on the analysis results and propose specific improvement plans. For example, if a particular page has a high bounce rate, it will propose measures to improve the user experience by reviewing the content and design of that page. Furthermore, the Data Analysis Department can use AI to analyze data and discover trends and patterns. For example, if there is a tendency for access to be concentrated at certain times or days of the week, it can achieve effective marketing by conducting promotions tailored to those times. In addition, the Data Analysis Department can continuously monitor the effectiveness of marketing measures based on real-time updated data and modify measures as needed. As a result, the Data Analysis Department can always propose optimal marketing measures based on the latest information and maximize the performance of the e-commerce site.

[0033] It features an automatic product image editing function that automatically adjusts the quality of product images. For example, the automatic product image editing function automatically analyzes product images and adjusts the resolution. It can also correct color tones and adjust brightness. For example, it can automatically adjust the color tone of an image to bring out the appeal of the product. Furthermore, it can automatically crop unnecessary parts of an image. For example, it can automatically remove the background to highlight only the product. By automatically adjusting the quality of product images, it can streamline the editing process and improve the quality of product images.

[0034] The system includes an automatic text generation unit that automatically generates product descriptions. This unit generates appropriate descriptions based on, for example, the product's features. It can analyze product information and generate text that highlights the product's appeal. For example, it generates descriptions that emphasize the product's features and advantages. Furthermore, it can generate detailed descriptions that include instructions for use and precautions. For example, it generates text explaining how to use and maintain the product. This automatic generation of product descriptions significantly reduces the effort required for product registration and allows for efficient provision of product information.

[0035] The system includes a personalized promotion creation unit that automatically creates and executes personalized promotions. For example, this unit analyzes customer purchase history and behavioral data to create promotions optimized for individual customers. It can also suggest specific products and services based on customer interests. For instance, it creates promotions related to products a customer has previously purchased. Furthermore, based on customer behavioral data, it can suggest new products that customers might be interested in. For example, it analyzes a customer's browsing history and suggests related products. This allows for the automatic creation and execution of personalized promotions, maximizing promotional effectiveness and increasing sales.

[0036] The system includes an access analysis tool data loading unit that reads data from access analysis tools and reports improvement suggestions. Based on the analysis results, the access analysis tool data loading unit can identify areas for improvement on the site and report specific improvement suggestions. For example, the access analysis tool data loading unit can analyze page views and time spent on the site and propose measures to improve the user experience. It can also analyze bounce rates and conversion rates and report improvement suggestions to improve site performance. For example, the access analysis tool data loading unit can propose measures to reduce the bounce rate on specific pages. In this way, by reading data from access analysis tools and reporting improvement suggestions, the site can be optimized and the user experience can be improved.

[0037] The system includes an improvement proposal reporting section that reports on suggested improvements. For example, this section analyzes site data and reports specific improvement suggestions. It can propose measures to improve the user experience. For instance, it can identify areas for UI / UX improvement and report specific improvement suggestions. Furthermore, it can propose measures to improve site performance. For example, it can propose measures to improve page loading speed. By reporting improvement suggestions, the system can optimize the site and improve the user experience.

[0038] The product registration support unit can apply different analysis algorithms depending on the product category when acquiring product information. For example, in the case of electronic devices, the product registration support unit can apply an analysis algorithm that emphasizes technical specifications. In the case of fashion items, the product registration support unit can also apply an analysis algorithm based on design and materials. For example, in the case of food products, the product registration support unit can apply an analysis algorithm based on ingredients and expiration dates. By applying an analysis algorithm appropriate to the product category, the accuracy of the analysis can be improved. Some or all of the above processing in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0039] The product registration support unit can improve the accuracy of its analysis by referring to past analysis data when analyzing product information. For example, the product registration support unit can improve the accuracy by referring to product data of the same category that has been analyzed in the past. The product registration support unit can also improve accuracy by adjusting the analysis algorithm based on past analysis results. For example, the product registration support unit can improve the accuracy by reflecting past user feedback. In this way, the accuracy of the analysis can be improved by referring to past analysis data. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without using AI. For example, the product registration support unit can input past analysis data into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0040] The Product Registration Support Department can adjust its analysis method based on the product's sales region when analyzing product information. For example, for products intended for the Japanese market, the Product Registration Support Department applies a Japanese analysis algorithm. For products intended for the European and American markets, the Product Registration Support Department can also apply an English analysis algorithm. For example, for multilingual products, the Product Registration Support Department applies an analysis algorithm corresponding to each language. This allows for improved analysis accuracy by adjusting the analysis method based on the product's sales region. Some or all of the above-described processes in the Product Registration Support Department may be performed using AI, for example, or without AI. For example, the Product Registration Support Department can input product sales region information into a generating AI and have the generating AI perform region-specific analysis.

[0041] The product registration support unit can improve the accuracy of its analysis by considering the brand information of the product when analyzing product information. For example, the product registration support unit can improve the accuracy of its analysis by referring to the brand's official information. The product registration support unit can also improve the accuracy by adjusting the analysis algorithm based on the brand's past sales data. For example, the product registration support unit can improve the accuracy of its analysis by considering the brand information of the product. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input brand information into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0042] The targeting proposal unit can apply different analysis algorithms to each product category when analyzing purchase history. For example, the targeting proposal unit can apply an analysis algorithm that emphasizes technical specifications to the purchase history of electronic devices. For example, the targeting proposal unit can also apply an analysis algorithm based on design and materials to the purchase history of fashion items. For example, the targeting proposal unit can apply an analysis algorithm based on ingredients and expiration dates to the purchase history of food products. By applying different analysis algorithms to each product category, the accuracy of the analysis can be improved. Some or all of the above processing in the targeting proposal unit may be performed using AI, for example, or without AI. For example, the targeting proposal unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0043] The targeting suggestion unit can improve the accuracy of its suggestions by referring to past targeting data when analyzing purchase history. For example, the targeting suggestion unit can improve the accuracy of its suggestions by referring to successful targeting strategies in the past. The targeting suggestion unit can also improve accuracy by adjusting its analysis algorithm based on past targeting data. For example, the targeting suggestion unit can improve the accuracy of its suggestions by reflecting past user feedback. In this way, the accuracy of suggestions can be improved by referring to past targeting data. Some or all of the above processes in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input past targeting data into a generating AI and have the generating AI perform the improvement of the suggestion accuracy.

[0044] The targeting suggestion unit can propose a targeting strategy that takes into account the user's geographical location when analyzing purchase history. For example, if the user lives in an urban area, the targeting suggestion unit will propose a targeting strategy for urban areas. If the user lives in a suburban area, the targeting suggestion unit can also propose a targeting strategy for suburban areas. For example, if the user frequently visits a particular area, the targeting suggestion unit will propose a targeting strategy for that area. This improves the accuracy of the targeting strategy by taking into account the user's geographical location. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's geographical location information into a generating AI and have the generating AI execute the targeting strategy proposal.

[0045] The targeting suggestion unit can analyze a user's social media activity when analyzing purchase history and propose targeting strategies. For example, if a user frequently mentions a particular brand, the targeting suggestion unit can propose a targeting strategy related to that brand. If a user participates in a particular event, the targeting suggestion unit can also propose a targeting strategy related to that event. For example, if a user has a particular interest, the targeting suggestion unit can propose a targeting strategy related to that interest. This allows for improved accuracy of targeting strategies by analyzing the user's social media activity. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's social media data into a generating AI and have the generating AI execute targeting strategy proposals.

[0046] The data analysis unit can improve the accuracy of its analysis by referring to past analysis data when analyzing site data. For example, the data analysis unit can improve the accuracy by referring to data of the same category that has been analyzed in the past. The data analysis unit can also improve accuracy by adjusting the analysis algorithm based on past analysis results. For example, the data analysis unit can improve the accuracy by reflecting past user feedback. In this way, the accuracy of the analysis can be improved by referring to past analysis data. Some or all of the above processes in the data analysis unit may be performed using AI, for example, or without using AI. For example, the data analysis unit can input past analysis data into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0047] The data analysis unit can improve the accuracy of its analysis by integrating different data sources when analyzing site data. The data analysis unit can also improve the accuracy of its analysis by integrating social media data with purchase history. For example, the data analysis unit can improve the accuracy of its analysis by integrating external market data with site data. Thus, the accuracy of the analysis can be improved by integrating different data sources. Some or all of the above-described processes in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input different data sources into a generating AI and have the generating AI perform the data integration.

[0048] The data analysis unit can adjust its analysis method when analyzing site data, taking into account the user's geographical location. For example, if the user lives in an urban area, the data analysis unit can apply an analysis method suited for urban areas. If the user lives in a suburban area, the data analysis unit can also apply an analysis method suited for suburban areas. For example, if the user frequently visits a particular area, the data analysis unit can apply an analysis method suited for that area. This improves the accuracy of the analysis by taking into account the user's geographical location. Some or all of the above processing in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the analysis method.

[0049] The data analysis unit can improve the accuracy of its analysis by considering the user's device information when analyzing site data. For example, if the user is using a smartphone, the data analysis unit applies a smartphone-specific analysis method. If the user is using a tablet, the data analysis unit can also apply a tablet-specific analysis method. For example, if the user is using a desktop, the data analysis unit applies a desktop-specific analysis method. This improves the accuracy of the analysis by considering the user's device information. Some or all of the above processing in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input the user's device information into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0050] The automated product image editing unit can apply different editing algorithms depending on the product category when editing product images. For example, in the case of electronic devices, the automated product image editing unit can apply an editing algorithm that emphasizes technical specifications. In the case of fashion items, the automated product image editing unit can also apply an editing algorithm based on design and materials. For example, in the case of food products, the automated product image editing unit can apply an editing algorithm based on ingredients and expiration dates. This improves editing accuracy by applying an editing algorithm appropriate to the product category. Some or all of the above processing in the automated product image editing unit may be performed using AI, for example, or without AI. For example, the automated product image editing unit can input product category information into a generating AI and have the generating AI perform editing according to the category.

[0051] The automated product image editing unit can adjust its editing method based on the product's sales region when editing product images. For example, for products intended for the Japanese market, the automated product image editing unit applies an editing method that suits Japanese culture and trends. For products intended for the European and American markets, the automated product image editing unit can also apply an editing method that suits European and American culture and trends. For example, for multi-region products, the automated product image editing unit applies an editing method that suits the culture and trends of each region. This improves editing accuracy by adjusting the editing method based on the product's sales region. Some or all of the above processing in the automated product image editing unit may be performed using AI, for example, or without AI. For example, the automated product image editing unit can input product sales region information into a generating AI and have the generating AI perform region-specific editing.

[0052] The automated text generation unit can apply different generation algorithms depending on the product category when generating text. For example, in the case of electronic devices, the automated text generation unit can apply a generation algorithm that emphasizes technical specifications. In the case of fashion items, the automated text generation unit can also apply a generation algorithm based on design and materials. For example, in the case of food products, the automated text generation unit can apply a generation algorithm based on ingredients and expiration dates. This improves generation accuracy by applying a generation algorithm appropriate to the product category. Some or all of the above-described processes in the automated text generation unit may be performed using AI, for example, or without AI. For example, the automated text generation unit can input product category information into a generation AI and have the generation AI perform generation according to the category.

[0053] The automated text generation unit can adjust its generation method based on the product's sales region when generating text. For example, for products intended for the Japanese market, the automated text generation unit applies a Japanese text generation algorithm. For products intended for the European and American markets, the automated text generation unit can also apply an English text generation algorithm. For example, for multilingual products, the automated text generation unit applies a text generation algorithm corresponding to each language. This improves generation accuracy by adjusting the generation method based on the product's sales region. Some or all of the above-described processes in the automated text generation unit may be performed using AI, for example, or without AI. For example, the automated text generation unit can input product sales region information into a generation AI and have the generation AI perform region-specific generation.

[0054] The Personalized Promotion Creation Unit can apply different creation algorithms depending on the product category when creating promotions. For example, in the case of electronic devices, the Personalized Promotion Creation Unit can apply a promotion creation algorithm that emphasizes technical specifications. In the case of fashion items, the Personalized Promotion Creation Unit can also apply a promotion creation algorithm based on design and materials. For example, in the case of food products, the Personalized Promotion Creation Unit can apply a promotion creation algorithm based on ingredients and expiration dates. This improves the accuracy of promotions by applying a creation algorithm appropriate to the product category. Some or all of the above processing in the Personalized Promotion Creation Unit may be performed using AI, for example, or without AI. For example, the Personalized Promotion Creation Unit can input product category information into a generating AI and have the generating AI perform creation according to the category.

[0055] The personalized promotion creation unit can adjust its creation method when creating promotions, taking into account the user's geographical location information. For example, if the user lives in an urban area, the personalized promotion creation unit will create a promotion for urban areas. If the user lives in a suburban area, the personalized promotion creation unit can also create a promotion for suburban areas. For example, if the personalized promotion creation unit frequently visits a particular area, it will create a promotion for that area. This improves the accuracy of promotions by taking into account the user's geographical location information. Some or all of the above processing in the personalized promotion creation unit may be performed using AI, for example, or without AI. For example, the personalized promotion creation unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the creation method.

[0056] The data loading unit of the access analysis tool can improve loading accuracy by integrating different data sources when loading access analysis data. The data loading unit can also improve loading accuracy by integrating social media data and purchase history. For example, the data loading unit can improve loading accuracy by integrating external market data and site data. Thus, loading accuracy can be improved by integrating different data sources. Some or all of the above processing in the data loading unit of the access analysis tool may be performed using AI, for example, or without AI. For example, the data loading unit of the access analysis tool can input different data sources into a generating AI and have the generating AI perform the data integration.

[0057] The access analysis tool data loading unit can adjust the loading method when loading access analysis data, taking into account the user's geographical location information. For example, if the user lives in an urban area, the access analysis tool data loading unit can apply a data loading method for urban areas. If the user lives in a suburban area, the access analysis tool data loading unit can also apply a data loading method for suburban areas. For example, if the user frequently visits a particular area, the access analysis tool data loading unit can apply a data loading method for that area. This improves loading accuracy by taking the user's geographical location information into account. Some or all of the above processing in the access analysis tool data loading unit may be performed using AI, for example, or without AI. For example, the access analysis tool data loading unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the loading method.

[0058] The improvement suggestion reporting unit can improve the accuracy of its reports by referring to past report data when reporting improvement suggestions. For example, the improvement suggestion reporting unit can improve report accuracy by referring to data of the same category that has been reported in the past. The improvement suggestion reporting unit can also improve accuracy by adjusting the reporting algorithm based on past report results. For example, the improvement suggestion reporting unit can improve report accuracy by reflecting past user feedback. In this way, report accuracy can be improved by referring to past report data. Some or all of the above processing in the improvement suggestion reporting unit may be performed using AI, for example, or without using AI. For example, the improvement suggestion reporting unit can input past report data into a generating AI and have the generating AI perform the improvement of report accuracy.

[0059] The improvement suggestion reporting unit can adjust its reporting method when reporting improvement suggestions, taking into account the user's geographical location information. For example, if the user lives in an urban area, the improvement suggestion reporting unit will apply a reporting method optimized for urban areas. If the user lives in a suburban area, the improvement suggestion reporting unit can also apply a reporting method optimized for suburban areas. For example, if the user frequently visits a particular area, the improvement suggestion reporting unit will apply a reporting method optimized for that area. This improves the accuracy of the report by taking into account the user's geographical location information. Some or all of the above processing in the improvement suggestion reporting unit may be performed using AI, for example, or without AI. For example, the improvement suggestion reporting unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the reporting method.

[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 product registration support unit can improve the accuracy of its analysis by considering the brand information of the product when acquiring product information. For example, the product registration support unit can improve the accuracy of its analysis by referring to the brand's official information. The product registration support unit can also improve the accuracy by adjusting the analysis algorithm based on the brand's past sales data. For example, the product registration support unit can improve the accuracy of its analysis by considering the brand evaluation of the brand. In this way, the accuracy of the analysis can be improved by considering the brand information of the product. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without using AI. For example, the product registration support unit can input brand information into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0062] The data analysis unit can improve the accuracy of its analysis by integrating different data sources when analyzing site data. The data analysis unit can also improve the accuracy of its analysis by integrating social media data with purchase history. For example, the data analysis unit can improve the accuracy of its analysis by integrating external market data with site data. Thus, the accuracy of the analysis can be improved by integrating different data sources. Some or all of the above-described processes in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input different data sources into a generating AI and have the generating AI perform the data integration.

[0063] The Personalized Promotion Creation Unit can apply different creation algorithms depending on the product category when creating promotions. For example, in the case of electronic devices, the Personalized Promotion Creation Unit can apply a promotion creation algorithm that emphasizes technical specifications. In the case of fashion items, the Personalized Promotion Creation Unit can also apply a promotion creation algorithm based on design and materials. For example, in the case of food products, the Personalized Promotion Creation Unit can apply a promotion creation algorithm based on ingredients and expiration dates. This improves the accuracy of promotions by applying a creation algorithm appropriate to the product category. Some or all of the above processing in the Personalized Promotion Creation Unit may be performed using AI, for example, or without AI. For example, the Personalized Promotion Creation Unit can input product category information into a generating AI and have the generating AI perform creation according to the category.

[0064] The product registration support unit can apply different analysis algorithms depending on the product category when acquiring product information. For example, in the case of electronic devices, the product registration support unit can apply an analysis algorithm that emphasizes technical specifications. In the case of fashion items, the product registration support unit can also apply an analysis algorithm based on design and materials. For example, in the case of food products, the product registration support unit can apply an analysis algorithm based on ingredients and expiration dates. By applying an analysis algorithm appropriate to the product category, the accuracy of the analysis can be improved. Some or all of the above processing in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0065] The targeting suggestion unit can propose a targeting strategy that takes into account the user's geographical location when analyzing purchase history. For example, if the user lives in an urban area, the targeting suggestion unit will propose a targeting strategy for urban areas. If the user lives in a suburban area, the targeting suggestion unit can also propose a targeting strategy for suburban areas. For example, if the user frequently visits a particular area, the targeting suggestion unit will propose a targeting strategy for that area. This improves the accuracy of the targeting strategy by taking into account the user's geographical location. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's geographical location information into a generating AI and have the generating AI execute the targeting strategy proposal.

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

[0067] Step 1: The product registration support unit automatically analyzes product information and images and assists in uploading them in the appropriate format. Specifically, it automatically collects product information, analyzes images, and converts them to the appropriate format. It also automatically adjusts image quality and generates product descriptions. For example, it automatically adjusts image resolution and corrects color tones. It can also generate appropriate descriptions based on the product's characteristics. Step 2: The Targeting Proposal Department analyzes purchase history and behavioral data based on the information analyzed by the Product Registration Support Department and proposes an appropriate targeting strategy. Specifically, it analyzes purchase history and provides relevant promotional information to customers who have purchased specific products. It also analyzes behavioral data and proposes personalized promotions based on customer interests. For example, it analyzes a customer's browsing history and suggests products that they might be interested in. Step 3: The Data Analysis Department analyzes site data in real time based on the strategy proposed by the Targeting Proposal Department and proposes optimal marketing measures. Specifically, they read data from access analysis tools and analyze site access data and user behavior. Based on the analysis results, they identify areas for improvement and propose specific improvement plans. For example, they analyze page views and time spent on the site and propose measures to improve the user experience.

[0068] (Example of form 2) The e-commerce operation support system according to an embodiment of the present invention is a system that utilizes AI to streamline the operation of e-commerce (EC) sites. The EC operation support system uses AI to automatically analyze product information and images and assist in uploading them in the appropriate format. This enables automatic editing of product images and automatic generation of text, significantly reducing the effort required for product registration. Next, the AI ​​analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. This allows for the automatic creation and execution of personalized promotions. Furthermore, the AI ​​analyzes site data in real time and proposes optimal marketing measures. For example, it can read data from access analysis tools and report improvement suggestions. First, the AI ​​automatically analyzes product information and images and assists in uploading them in the appropriate format. At this time, it automatically adjusts the quality of product images and automatically generates product descriptions. For example, when adding a new product, the AI ​​can automatically edit images and generate appropriate descriptions, significantly reducing the effort required from the operator. Next, the AI ​​analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. For example, it can provide promotional information related to a product to customers who have purchased that specific product. This maximizes promotional effectiveness and increases sales. Furthermore, AI analyzes site data in real time and proposes optimal marketing strategies. For example, it can read data from access analytics tools, analyze site access data and user behavior, and identify areas for improvement. This optimizes the site and improves the user experience. This system allows e-commerce site operators to focus on the quality of their products and services. For example, they can concentrate on product development and create effective marketing strategies. They are also freed from the complexities of data analysis, which can lead to increased sales. In this way, utilizing AI can significantly improve the efficiency of e-commerce site operations. Operators are freed from tedious daily tasks and can concentrate on larger strategies and service improvements. Moreover, the increased efficiency of e-commerce site operations can lead to sustainable growth.This allows the e-commerce operation support system to streamline the operation of e-commerce sites, enabling operators to focus on the quality of their products and services.

[0069] The e-commerce operation support system according to this embodiment comprises a product registration support unit, a targeting proposal unit, and a data analysis unit. The product registration support unit automatically analyzes product information and images and assists in uploading them in an appropriate format. For example, the product registration support unit automatically collects product information, analyzes images, and converts them into an appropriate format. The product registration support unit can also automatically adjust image quality and automatically generate product descriptions. For example, the product registration support unit automatically adjusts image resolution and corrects color tones. The product registration support unit can also generate appropriate descriptions based on product characteristics. The targeting proposal unit analyzes purchase history and behavioral data based on the information analyzed by the product registration support unit and proposes an appropriate targeting strategy. For example, the targeting proposal unit analyzes purchase history and provides relevant promotional information to customers who have purchased specific products. The targeting proposal unit can also analyze behavioral data and propose personalized promotions based on customer interests. For example, the targeting proposal unit analyzes customer browsing history and proposes products that may be of interest to the customer. The Data Analysis Department analyzes site data in real time based on the strategies proposed by the Targeting Proposal Department and proposes optimal marketing measures. For example, the Data Analysis Department reads data from access analysis tools and analyzes site access data and user behavior. The Data Analysis Department can also identify areas for improvement based on the analysis results and propose specific improvement plans. For example, the Data Analysis Department analyzes page views and time spent on the site and proposes measures to improve the user experience. As a result, the e-commerce operation support system according to this embodiment can significantly reduce the effort required for product registration by automatically analyzing product information and images and assisting in uploading them in the appropriate format, analyze purchase history and behavioral data to propose appropriate targeting strategies, and analyze site data in real time to propose optimal marketing measures.

[0070] The Product Registration Support Department automatically analyzes product information and images and assists in uploading them in the appropriate format. Specifically, the Product Registration Support Department automatically collects product information, analyzes images, and converts them into the appropriate format. For example, product information is automatically obtained from the manufacturer's database and website, and information such as product name, price, and description is extracted. In image analysis, AI is used to recognize the content of the image and perform actions such as background removal, cropping, resolution adjustment, and color correction. This makes product images visually appealing and attractive to consumers. The Product Registration Support Department can also generate appropriate introductory text based on the product's characteristics. For example, AI analyzes the product's characteristics and automatically generates an introductory text that includes the product's advantages, usage instructions, and target users. This introductory text is optimized for search engines (SEO) by appropriately placing keywords to improve search engine rankings. Furthermore, the Product Registration Support Department supports multiple languages, making it suitable for international e-commerce site operations. As a result, the Product Registration Support Department can efficiently and efficiently upload product information and images with high quality, significantly reducing the burden on e-commerce site operators.

[0071] The Targeting Proposal Department analyzes purchase history and behavioral data based on information analyzed by the Product Registration Support Department and proposes appropriate targeting strategies. Specifically, the Targeting Proposal Department analyzes customers' purchase history and provides relevant promotional information to customers who have purchased specific products. For example, it might propose promotions for new sportswear and accessories to customers who have previously purchased sporting goods. The Targeting Proposal Department can also analyze customer behavioral data and propose personalized promotions based on customer interests. For example, it might analyze a customer's browsing history and focus promotions on products in a specific category for customers who are interested in that category. Furthermore, the Targeting Proposal Department uses AI to predict customer behavior patterns and develop strategies to increase future purchasing intent. For example, if a customer frequently views a particular product, it can encourage purchases by providing special offers and discounts related to that product. In this way, the Targeting Proposal Department can provide optimal promotions for each individual customer, achieving increased sales and customer satisfaction.

[0072] The Data Analysis Department analyzes website data in real time based on the strategies proposed by the Targeting Proposal Department and proposes optimal marketing measures. Specifically, the Data Analysis Department reads data from access analysis tools and analyzes website access data and user behavior. For example, it analyzes metrics such as page views, time on site, bounce rate, and conversion rate to evaluate website performance. The Data Analysis Department can also identify areas for improvement based on the analysis results and propose specific improvement plans. For example, if a particular page has a high bounce rate, it will propose measures to improve the user experience by reviewing the content and design of that page. Furthermore, the Data Analysis Department can use AI to analyze data and discover trends and patterns. For example, if there is a tendency for access to be concentrated at certain times or days of the week, it can achieve effective marketing by conducting promotions tailored to those times. In addition, the Data Analysis Department can continuously monitor the effectiveness of marketing measures based on real-time updated data and modify measures as needed. As a result, the Data Analysis Department can always propose optimal marketing measures based on the latest information and maximize the performance of the e-commerce site.

[0073] It features an automatic product image editing function that automatically adjusts the quality of product images. For example, the automatic product image editing function automatically analyzes product images and adjusts the resolution. It can also correct color tones and adjust brightness. For example, it can automatically adjust the color tone of an image to bring out the appeal of the product. Furthermore, it can automatically crop unnecessary parts of an image. For example, it can automatically remove the background to highlight only the product. By automatically adjusting the quality of product images, it can streamline the editing process and improve the quality of product images.

[0074] The system includes an automatic text generation unit that automatically generates product descriptions. This unit generates appropriate descriptions based on, for example, the product's features. It can analyze product information and generate text that highlights the product's appeal. For example, it generates descriptions that emphasize the product's features and advantages. Furthermore, it can generate detailed descriptions that include instructions for use and precautions. For example, it generates text explaining how to use and maintain the product. This automatic generation of product descriptions significantly reduces the effort required for product registration and allows for efficient provision of product information.

[0075] The system includes a personalized promotion creation unit that automatically creates and executes personalized promotions. For example, this unit analyzes customer purchase history and behavioral data to create promotions optimized for individual customers. It can also suggest specific products and services based on customer interests. For instance, it creates promotions related to products a customer has previously purchased. Furthermore, based on customer behavioral data, it can suggest new products that customers might be interested in. For example, it analyzes a customer's browsing history and suggests related products. This allows for the automatic creation and execution of personalized promotions, maximizing promotional effectiveness and increasing sales.

[0076] The system includes an access analysis tool data loading unit that reads data from access analysis tools and reports improvement suggestions. Based on the analysis results, the access analysis tool data loading unit can identify areas for improvement on the site and report specific improvement suggestions. For example, the access analysis tool data loading unit can analyze page views and time spent on the site and propose measures to improve the user experience. It can also analyze bounce rates and conversion rates and report improvement suggestions to improve site performance. For example, the access analysis tool data loading unit can propose measures to reduce the bounce rate on specific pages. In this way, by reading data from access analysis tools and reporting improvement suggestions, the site can be optimized and the user experience can be improved.

[0077] The system includes an improvement proposal reporting section that reports on suggested improvements. For example, this section analyzes site data and reports specific improvement suggestions. It can propose measures to improve the user experience. For instance, it can identify areas for UI / UX improvement and report specific improvement suggestions. Furthermore, it can propose measures to improve site performance. For example, it can propose measures to improve page loading speed. By reporting improvement suggestions, the system can optimize the site and improve the user experience.

[0078] The product registration support unit can estimate the user's emotions and adjust the analysis method of product information and images based on the estimated user emotions. For example, if the user is stressed, the product registration support unit can apply a simpler analysis method to shorten the analysis time. If the user is relaxed, the product registration support unit can also perform a more detailed analysis to extract more information. For example, if the user is in a hurry, the product registration support unit can prioritize the analysis of only the most important information. By adjusting the analysis method of product information and images based on the user's emotions, optimal analysis tailored to the user's situation becomes possible. 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 product registration support unit may be performed using AI, for example, or not using AI. For example, the product registration support unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0079] The product registration support unit can apply different analysis algorithms depending on the product category when acquiring product information. For example, in the case of electronic devices, the product registration support unit can apply an analysis algorithm that emphasizes technical specifications. In the case of fashion items, the product registration support unit can also apply an analysis algorithm based on design and materials. For example, in the case of food products, the product registration support unit can apply an analysis algorithm based on ingredients and expiration dates. By applying an analysis algorithm appropriate to the product category, the accuracy of the analysis can be improved. Some or all of the above processing in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0080] The product registration support unit can improve the accuracy of its analysis by referring to past analysis data when analyzing product information. For example, the product registration support unit can improve the accuracy by referring to product data of the same category that has been analyzed in the past. The product registration support unit can also improve accuracy by adjusting the analysis algorithm based on past analysis results. For example, the product registration support unit can improve the accuracy by reflecting past user feedback. In this way, the accuracy of the analysis can be improved by referring to past analysis data. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without using AI. For example, the product registration support unit can input past analysis data into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0081] The product registration support unit can estimate the user's emotions and adjust the timing of product information and image uploads based on those emotions. For example, if the user is stressed, the product registration support unit can delay the upload to reduce the burden. If the user is relaxed, the product registration support unit can also upload immediately. For example, if the user is in a hurry, the product registration support unit can complete the upload in the shortest possible time. By adjusting the timing of product information and image uploads based on the user's emotions, it becomes possible to perform optimal uploads according to the user's situation. 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 product registration support unit may be performed using AI, for example, or not using AI. For example, the product registration support unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the upload timing.

[0082] The Product Registration Support Department can adjust its analysis method based on the product's sales region when analyzing product information. For example, for products intended for the Japanese market, the Product Registration Support Department applies a Japanese analysis algorithm. For products intended for the European and American markets, the Product Registration Support Department can also apply an English analysis algorithm. For example, for multilingual products, the Product Registration Support Department applies an analysis algorithm corresponding to each language. This allows for improved analysis accuracy by adjusting the analysis method based on the product's sales region. Some or all of the above-described processes in the Product Registration Support Department may be performed using AI, for example, or without AI. For example, the Product Registration Support Department can input product sales region information into a generating AI and have the generating AI perform region-specific analysis.

[0083] The product registration support unit can improve the accuracy of its analysis by considering the brand information of the product when analyzing product information. For example, the product registration support unit can improve the accuracy of its analysis by referring to the brand's official information. The product registration support unit can also improve the accuracy by adjusting the analysis algorithm based on the brand's past sales data. For example, the product registration support unit can improve the accuracy of its analysis by considering the brand information of the product. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input brand information into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0084] The targeting suggestion unit can estimate the user's emotions and adjust the method of suggesting targeting strategies based on the estimated user emotions. For example, if the user is stressed, the targeting suggestion unit may suggest a simple targeting strategy. If the user is relaxed, the targeting suggestion unit may also suggest a detailed targeting strategy. For example, if the user is in a hurry, the targeting suggestion unit may suggest a targeting strategy that can be implemented quickly. By adjusting the method of suggesting targeting strategies based on the user's emotions, it becomes possible to provide optimal suggestions tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or not using AI. For example, the targeting suggestion unit can input user emotion data into the generative AI and have the generative AI adjust the suggestion method.

[0085] The targeting proposal unit can apply different analysis algorithms to each product category when analyzing purchase history. For example, the targeting proposal unit can apply an analysis algorithm that emphasizes technical specifications to the purchase history of electronic devices. For example, the targeting proposal unit can also apply an analysis algorithm based on design and materials to the purchase history of fashion items. For example, the targeting proposal unit can apply an analysis algorithm based on ingredients and expiration dates to the purchase history of food products. By applying different analysis algorithms to each product category, the accuracy of the analysis can be improved. Some or all of the above processing in the targeting proposal unit may be performed using AI, for example, or without AI. For example, the targeting proposal unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0086] The targeting suggestion unit can improve the accuracy of its suggestions by referring to past targeting data when analyzing purchase history. For example, the targeting suggestion unit can improve the accuracy of its suggestions by referring to successful targeting strategies in the past. The targeting suggestion unit can also improve accuracy by adjusting its analysis algorithm based on past targeting data. For example, the targeting suggestion unit can improve the accuracy of its suggestions by reflecting past user feedback. In this way, the accuracy of suggestions can be improved by referring to past targeting data. Some or all of the above processes in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input past targeting data into a generating AI and have the generating AI perform the improvement of the suggestion accuracy.

[0087] The targeting suggestion unit can estimate the user's emotions and prioritize targeting strategies based on those emotions. For example, if the user is stressed, the targeting suggestion unit will prioritize simple and effective targeting strategies. If the user is relaxed, the targeting suggestion unit may also prioritize detailed targeting strategies. For example, if the user is in a hurry, the targeting suggestion unit will prioritize targeting strategies that can be implemented quickly. This allows for optimal prioritization based on the user's emotions, tailored to their specific situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the targeting suggestion unit may be performed using AI or not. For example, the targeting suggestion unit can input user emotion data into a generative AI and have the generative AI perform the priority determination.

[0088] The targeting suggestion unit can propose a targeting strategy that takes into account the user's geographical location when analyzing purchase history. For example, if the user lives in an urban area, the targeting suggestion unit will propose a targeting strategy for urban areas. If the user lives in a suburban area, the targeting suggestion unit can also propose a targeting strategy for suburban areas. For example, if the user frequently visits a particular area, the targeting suggestion unit will propose a targeting strategy for that area. This improves the accuracy of the targeting strategy by taking into account the user's geographical location. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's geographical location information into a generating AI and have the generating AI execute the targeting strategy proposal.

[0089] The targeting suggestion unit can analyze a user's social media activity when analyzing purchase history and propose targeting strategies. For example, if a user frequently mentions a particular brand, the targeting suggestion unit can propose a targeting strategy related to that brand. If a user participates in a particular event, the targeting suggestion unit can also propose a targeting strategy related to that event. For example, if a user has a particular interest, the targeting suggestion unit can propose a targeting strategy related to that interest. This allows for improved accuracy of targeting strategies by analyzing the user's social media activity. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's social media data into a generating AI and have the generating AI execute targeting strategy proposals.

[0090] The data analysis unit can estimate the user's emotions and adjust the display method of the data analysis based on the estimated user emotions. For example, if the user is stressed, the data analysis unit can provide a simple and highly visible display method. If the user is relaxed, the data analysis unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the data analysis unit can provide a concise display method. By adjusting the display method of the data analysis based on the user's emotions, it becomes possible to provide an optimal display according to the user's situation. 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 data analysis unit may be performed using AI, for example, or not using AI. For example, the data analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0091] The data analysis unit can improve the accuracy of its analysis by referring to past analysis data when analyzing site data. For example, the data analysis unit can improve the accuracy by referring to data of the same category that has been analyzed in the past. The data analysis unit can also improve accuracy by adjusting the analysis algorithm based on past analysis results. For example, the data analysis unit can improve the accuracy by reflecting past user feedback. In this way, the accuracy of the analysis can be improved by referring to past analysis data. Some or all of the above processes in the data analysis unit may be performed using AI, for example, or without using AI. For example, the data analysis unit can input past analysis data into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0092] The data analysis unit can improve the accuracy of its analysis by integrating different data sources when analyzing site data. The data analysis unit can also improve the accuracy of its analysis by integrating social media data with purchase history. For example, the data analysis unit can improve the accuracy of its analysis by integrating external market data with site data. Thus, the accuracy of the analysis can be improved by integrating different data sources. Some or all of the above-described processes in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input different data sources into a generating AI and have the generating AI perform the data integration.

[0093] The data analysis unit can estimate the user's emotions and determine the priority of data analysis based on the estimated emotions. For example, if the user is stressed, the data analysis unit will prioritize simple and effective data analysis. If the user is relaxed, the data analysis unit may also prioritize detailed data analysis. For example, if the user is in a hurry, the data analysis unit will prioritize data analysis that can be performed quickly. This allows for optimal prioritization based on the user's emotions, tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data analysis unit may be performed using AI or not. For example, the data analysis unit can input user emotion data into a generative AI and have the generative AI perform the priority determination.

[0094] The data analysis unit can adjust its analysis method when analyzing site data, taking into account the user's geographical location. For example, if the user lives in an urban area, the data analysis unit can apply an analysis method suited for urban areas. If the user lives in a suburban area, the data analysis unit can also apply an analysis method suited for suburban areas. For example, if the user frequently visits a particular area, the data analysis unit can apply an analysis method suited for that area. This improves the accuracy of the analysis by taking into account the user's geographical location. Some or all of the above processing in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the analysis method.

[0095] The data analysis unit can improve the accuracy of its analysis by considering the user's device information when analyzing site data. For example, if the user is using a smartphone, the data analysis unit applies a smartphone-specific analysis method. If the user is using a tablet, the data analysis unit can also apply a tablet-specific analysis method. For example, if the user is using a desktop, the data analysis unit applies a desktop-specific analysis method. This improves the accuracy of the analysis by considering the user's device information. Some or all of the above processing in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input the user's device information into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0096] The automated product image editing unit can estimate the user's emotions and adjust the editing method based on those emotions. For example, if the user is stressed, the automated product image editing unit can apply a simple editing method to reduce editing time. If the user is relaxed, the automated product image editing unit can perform detailed editing and extract more information. For example, if the user is in a hurry, the automated product image editing unit can prioritize editing only the most important information. By adjusting the editing method based on the user's emotions, it becomes possible to perform optimal editing according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the automated product image editing unit may be performed using AI or not. For example, the automated product image editing unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the editing method.

[0097] The automated product image editing unit can apply different editing algorithms depending on the product category when editing product images. For example, in the case of electronic devices, the automated product image editing unit can apply an editing algorithm that emphasizes technical specifications. In the case of fashion items, the automated product image editing unit can also apply an editing algorithm based on design and materials. For example, in the case of food products, the automated product image editing unit can apply an editing algorithm based on ingredients and expiration dates. This improves editing accuracy by applying an editing algorithm appropriate to the product category. Some or all of the above processing in the automated product image editing unit may be performed using AI, for example, or without AI. For example, the automated product image editing unit can input product category information into a generating AI and have the generating AI perform editing according to the category.

[0098] The automated product image editing unit can estimate the user's emotions and adjust the editing timing based on those emotions. For example, if the user is stressed, the automated product image editing unit can delay the editing timing to reduce the user's burden. If the user is relaxed, the automated product image editing unit can also perform editing immediately. For example, if the user is in a hurry, the automated product image editing unit will complete the editing in the shortest possible time. By adjusting the editing timing of product images based on the user's emotions, it becomes possible to edit at the optimal timing according to the user's situation. 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 automated product image editing unit may be performed using AI, or not using AI. For example, the automated product image editing unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the editing timing.

[0099] The automated product image editing unit can adjust its editing method based on the product's sales region when editing product images. For example, for products intended for the Japanese market, the automated product image editing unit applies an editing method that suits Japanese culture and trends. For products intended for the European and American markets, the automated product image editing unit can also apply an editing method that suits European and American culture and trends. For example, for multi-region products, the automated product image editing unit applies an editing method that suits the culture and trends of each region. This improves editing accuracy by adjusting the editing method based on the product's sales region. Some or all of the above processing in the automated product image editing unit may be performed using AI, for example, or without AI. For example, the automated product image editing unit can input product sales region information into a generating AI and have the generating AI perform region-specific editing.

[0100] The automated text generation unit can estimate the user's emotions and adjust the expression of the text based on the estimated emotions. For example, if the user is stressed, the automated text generation unit will apply a simple and intuitive expression. If the user is relaxed, the automated text generation unit can also apply a detailed and rich expression. For example, if the user is in a hurry, the automated text generation unit will apply a concise expression that gets straight to the point. By adjusting the expression of the text based on the user's emotions, it becomes possible to provide the optimal expression according to the user's situation. 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 these examples. Some or all of the above processing in the automated text generation unit may be performed using AI, for example, or not using AI. For example, the automated text generation unit can input user emotion data into the generation AI and have the generation AI perform the adjustment of the expression.

[0101] The automated text generation unit can apply different generation algorithms depending on the product category when generating text. For example, in the case of electronic devices, the automated text generation unit can apply a generation algorithm that emphasizes technical specifications. In the case of fashion items, the automated text generation unit can also apply a generation algorithm based on design and materials. For example, in the case of food products, the automated text generation unit can apply a generation algorithm based on ingredients and expiration dates. This improves generation accuracy by applying a generation algorithm appropriate to the product category. Some or all of the above-described processes in the automated text generation unit may be performed using AI, for example, or without AI. For example, the automated text generation unit can input product category information into a generation AI and have the generation AI perform generation according to the category.

[0102] The automated text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is stressed, the automated text generation unit will generate a short, concise text. If the user is relaxed, the automated text generation unit can also generate a longer text with detailed explanations. For example, if the user is in a hurry, the automated text generation unit will generate a short text that can be read quickly. By adjusting the length of the text based on the user's emotions, it becomes possible to generate text of the optimal length according to the user's situation. 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 automated text generation unit may be performed using AI, for example, or not using AI. For example, the automated text generation unit can input user emotion data into the generation AI and have the generation AI adjust the length of the text.

[0103] The automated text generation unit can adjust its generation method based on the product's sales region when generating text. For example, for products intended for the Japanese market, the automated text generation unit applies a Japanese text generation algorithm. For products intended for the European and American markets, the automated text generation unit can also apply an English text generation algorithm. For example, for multilingual products, the automated text generation unit applies a text generation algorithm corresponding to each language. This improves generation accuracy by adjusting the generation method based on the product's sales region. Some or all of the above-described processes in the automated text generation unit may be performed using AI, for example, or without AI. For example, the automated text generation unit can input product sales region information into a generation AI and have the generation AI perform region-specific generation.

[0104] The personalized promotion creation unit can estimate the user's emotions and adjust the way the promotion is presented based on those emotions. For example, if the user is stressed, the personalized promotion creation unit can create a simple and intuitive promotion. If the user is relaxed, the personalized promotion creation unit can also create a detailed and rich promotion. For example, if the user is in a hurry, the personalized promotion creation unit can create a concise and to-the-point promotion. By adjusting the way the promotion is presented based on the user's emotions, it becomes possible to create the optimal promotion for the user's situation. 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 personalized promotion creation unit may be performed using AI, or not using AI. For example, the personalized promotion creation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the presentation.

[0105] The Personalized Promotion Creation Unit can apply different creation algorithms depending on the product category when creating promotions. For example, in the case of electronic devices, the Personalized Promotion Creation Unit can apply a promotion creation algorithm that emphasizes technical specifications. In the case of fashion items, the Personalized Promotion Creation Unit can also apply a promotion creation algorithm based on design and materials. For example, in the case of food products, the Personalized Promotion Creation Unit can apply a promotion creation algorithm based on ingredients and expiration dates. This improves the accuracy of promotions by applying a creation algorithm appropriate to the product category. Some or all of the above processing in the Personalized Promotion Creation Unit may be performed using AI, for example, or without AI. For example, the Personalized Promotion Creation Unit can input product category information into a generating AI and have the generating AI perform creation according to the category.

[0106] The personalized promotion creation unit can estimate the user's emotions and determine the priority of promotions based on those emotions. For example, if the user is stressed, the personalized promotion creation unit will prioritize simple and effective promotions. If the user is relaxed, the personalized promotion creation unit may also prioritize detailed promotions. For example, if the user is in a hurry, the personalized promotion creation unit will prioritize promotions that can be executed quickly. This allows for optimal prioritization based on the user's emotions, tailored to their specific situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the personalized promotion creation unit may be performed using AI or not. For example, the personalized promotion creation unit can input user emotion data into a generative AI and have the generative AI determine the priorities.

[0107] The personalized promotion creation unit can adjust its creation method when creating promotions, taking into account the user's geographical location information. For example, if the user lives in an urban area, the personalized promotion creation unit will create a promotion for urban areas. If the user lives in a suburban area, the personalized promotion creation unit can also create a promotion for suburban areas. For example, if the personalized promotion creation unit frequently visits a particular area, it will create a promotion for that area. This improves the accuracy of promotions by taking into account the user's geographical location information. Some or all of the above processing in the personalized promotion creation unit may be performed using AI, for example, or without AI. For example, the personalized promotion creation unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the creation method.

[0108] The access analysis tool data loading unit can estimate the user's emotions and adjust the method of loading access analysis data based on the estimated user emotions. For example, if the user is stressed, the access analysis tool data loading unit can provide a simple and highly visual data loading method. If the user is relaxed, the access analysis tool data loading unit can also provide a data loading method that includes detailed information. For example, if the user is in a hurry, the access analysis tool data loading unit can provide a concise data loading method. By adjusting the method of loading access analysis data based on the user's emotions, it becomes possible to load data optimally according to the user's situation. 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 access analysis tool data loading unit may be performed using AI, for example, or without AI. For example, the access analysis tool data loading unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the loading method.

[0109] The data loading unit of the access analysis tool can improve loading accuracy by integrating different data sources when loading access analysis data. The data loading unit can also improve loading accuracy by integrating social media data and purchase history. For example, the data loading unit can improve loading accuracy by integrating external market data and site data. Thus, loading accuracy can be improved by integrating different data sources. Some or all of the above processing in the data loading unit of the access analysis tool may be performed using AI, for example, or without AI. For example, the data loading unit of the access analysis tool can input different data sources into a generating AI and have the generating AI perform the data integration.

[0110] The access analysis tool data loading unit can estimate the user's emotions and adjust the timing of data loading based on the estimated emotions. For example, if the user is stressed, the access analysis tool data loading unit can delay the loading time to reduce the burden. If the user is relaxed, the access analysis tool data loading unit can load the data immediately. For example, if the user is in a hurry, the access analysis tool data loading unit will load the data in the shortest possible time. By adjusting the timing of data loading based on the user's emotions, it becomes possible to load the data at the optimal timing according to the user's situation. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 access analysis tool data loading unit may be performed using AI, for example, or without AI. For example, the access analysis tool data loading unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the loading timing.

[0111] The access analysis tool data loading unit can adjust the loading method when loading access analysis data, taking into account the user's geographical location information. For example, if the user lives in an urban area, the access analysis tool data loading unit can apply a data loading method for urban areas. If the user lives in a suburban area, the access analysis tool data loading unit can also apply a data loading method for suburban areas. For example, if the user frequently visits a particular area, the access analysis tool data loading unit can apply a data loading method for that area. This improves loading accuracy by taking the user's geographical location information into account. Some or all of the above processing in the access analysis tool data loading unit may be performed using AI, for example, or without AI. For example, the access analysis tool data loading unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the loading method.

[0112] The improvement suggestion reporting unit can estimate the user's emotions and adjust the method of reporting the improvement suggestions based on the estimated emotions. For example, if the user is stressed, the improvement suggestion reporting unit can provide a simple and easy-to-read report. If the user is relaxed, the improvement suggestion reporting unit can also provide a report that includes detailed information. For example, if the user is in a hurry, the improvement suggestion reporting unit can provide a report that gets straight to the point. By adjusting the method of reporting the improvement suggestions based on the user's emotions, it becomes possible to provide an optimal report tailored to the user's situation. 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 improvement suggestion reporting unit may be performed using AI, for example, or not using AI. For example, the improvement suggestion reporting unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the reporting method.

[0113] The improvement suggestion reporting unit can improve the accuracy of its reports by referring to past report data when reporting improvement suggestions. For example, the improvement suggestion reporting unit can improve report accuracy by referring to data of the same category that has been reported in the past. The improvement suggestion reporting unit can also improve accuracy by adjusting the reporting algorithm based on past report results. For example, the improvement suggestion reporting unit can improve report accuracy by reflecting past user feedback. In this way, report accuracy can be improved by referring to past report data. Some or all of the above processing in the improvement suggestion reporting unit may be performed using AI, for example, or without using AI. For example, the improvement suggestion reporting unit can input past report data into a generating AI and have the generating AI perform the improvement of report accuracy.

[0114] The improvement suggestion reporting unit can estimate the user's emotions and determine the priority of improvement suggestions based on those emotions. For example, if the user is stressed, the improvement suggestion reporting unit will prioritize simple and effective suggestions. If the user is relaxed, the improvement suggestion reporting unit may also prioritize detailed suggestions. For example, if the user is in a hurry, the improvement suggestion reporting unit will prioritize suggestions that can be implemented quickly. This allows for optimal prioritization based on the user's emotions, tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the improvement suggestion reporting unit may be performed using AI or not. For example, the improvement suggestion reporting unit can input user emotion data into a generative AI and have the generative AI perform the priority determination.

[0115] The improvement suggestion reporting unit can adjust its reporting method when reporting improvement suggestions, taking into account the user's geographical location information. For example, if the user lives in an urban area, the improvement suggestion reporting unit will apply a reporting method optimized for urban areas. If the user lives in a suburban area, the improvement suggestion reporting unit can also apply a reporting method optimized for suburban areas. For example, if the user frequently visits a particular area, the improvement suggestion reporting unit will apply a reporting method optimized for that area. This improves the accuracy of the report by taking into account the user's geographical location information. Some or all of the above processing in the improvement suggestion reporting unit may be performed using AI, for example, or without AI. For example, the improvement suggestion reporting unit can input the user's geographical location information into a generating AI and have the generating AI perform the adjustment of the reporting method.

[0116] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0117] The product registration support unit can improve the accuracy of its analysis by considering the brand information of the product when acquiring product information. For example, the product registration support unit can improve the accuracy of its analysis by referring to the brand's official information. The product registration support unit can also improve the accuracy by adjusting the analysis algorithm based on the brand's past sales data. For example, the product registration support unit can improve the accuracy of its analysis by considering the brand evaluation of the brand. In this way, the accuracy of the analysis can be improved by considering the brand information of the product. Some or all of the above processes in the product registration support unit may be performed using AI, for example, or without using AI. For example, the product registration support unit can input brand information into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0118] The targeting suggestion unit can estimate the user's emotions and adjust the method of suggesting targeting strategies based on the estimated user emotions. For example, if the user is stressed, the targeting suggestion unit may suggest a simple targeting strategy. If the user is relaxed, the targeting suggestion unit may also suggest a detailed targeting strategy. For example, if the user is in a hurry, the targeting suggestion unit may suggest a targeting strategy that can be implemented quickly. By adjusting the method of suggesting targeting strategies based on the user's emotions, it becomes possible to provide optimal suggestions tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or not using AI. For example, the targeting suggestion unit can input user emotion data into the generative AI and have the generative AI adjust the suggestion method.

[0119] The data analysis unit can improve the accuracy of its analysis by integrating different data sources when analyzing site data. The data analysis unit can also improve the accuracy of its analysis by integrating social media data with purchase history. For example, the data analysis unit can improve the accuracy of its analysis by integrating external market data with site data. Thus, the accuracy of the analysis can be improved by integrating different data sources. Some or all of the above-described processes in the data analysis unit may be performed using AI, for example, or without AI. For example, the data analysis unit can input different data sources into a generating AI and have the generating AI perform the data integration.

[0120] The automated product image editing unit can estimate the user's emotions and adjust the editing method based on those emotions. For example, if the user is stressed, the automated product image editing unit can apply a simple editing method to reduce editing time. If the user is relaxed, the automated product image editing unit can perform detailed editing and extract more information. For example, if the user is in a hurry, the automated product image editing unit can prioritize editing only the most important information. By adjusting the editing method based on the user's emotions, it becomes possible to perform optimal editing according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the automated product image editing unit may be performed using AI or not. For example, the automated product image editing unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the editing method.

[0121] The automated text generation unit can estimate the user's emotions and adjust the expression of the text based on the estimated emotions. For example, if the user is stressed, the automated text generation unit will apply a simple and intuitive expression. If the user is relaxed, the automated text generation unit can also apply a detailed and rich expression. For example, if the user is in a hurry, the automated text generation unit will apply a concise expression that gets straight to the point. By adjusting the expression of the text based on the user's emotions, it becomes possible to provide the optimal expression according to the user's situation. 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 these examples. Some or all of the above processing in the automated text generation unit may be performed using AI, for example, or not using AI. For example, the automated text generation unit can input user emotion data into the generation AI and have the generation AI perform the adjustment of the expression.

[0122] The Personalized Promotion Creation Unit can apply different creation algorithms depending on the product category when creating promotions. For example, in the case of electronic devices, the Personalized Promotion Creation Unit can apply a promotion creation algorithm that emphasizes technical specifications. In the case of fashion items, the Personalized Promotion Creation Unit can also apply a promotion creation algorithm based on design and materials. For example, in the case of food products, the Personalized Promotion Creation Unit can apply a promotion creation algorithm based on ingredients and expiration dates. This improves the accuracy of promotions by applying a creation algorithm appropriate to the product category. Some or all of the above processing in the Personalized Promotion Creation Unit may be performed using AI, for example, or without AI. For example, the Personalized Promotion Creation Unit can input product category information into a generating AI and have the generating AI perform creation according to the category.

[0123] The data analysis unit can estimate the user's emotions and adjust the display method of the data analysis based on the estimated user emotions. For example, if the user is stressed, the data analysis unit can provide a simple and highly visible display method. If the user is relaxed, the data analysis unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the data analysis unit can provide a concise display method. By adjusting the display method of the data analysis based on the user's emotions, it becomes possible to provide an optimal display according to the user's situation. 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 data analysis unit may be performed using AI, for example, or not using AI. For example, the data analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0124] The product registration support unit can apply different analysis algorithms depending on the product category when acquiring product information. For example, in the case of electronic devices, the product registration support unit can apply an analysis algorithm that emphasizes technical specifications. In the case of fashion items, the product registration support unit can also apply an analysis algorithm based on design and materials. For example, in the case of food products, the product registration support unit can apply an analysis algorithm based on ingredients and expiration dates. By applying an analysis algorithm appropriate to the product category, the accuracy of the analysis can be improved. Some or all of the above processing in the product registration support unit may be performed using AI, for example, or without AI. For example, the product registration support unit can input product category information into a generating AI and have the generating AI perform analysis according to the category.

[0125] The targeting suggestion unit can propose a targeting strategy that takes into account the user's geographical location when analyzing purchase history. For example, if the user lives in an urban area, the targeting suggestion unit will propose a targeting strategy for urban areas. If the user lives in a suburban area, the targeting suggestion unit can also propose a targeting strategy for suburban areas. For example, if the user frequently visits a particular area, the targeting suggestion unit will propose a targeting strategy for that area. This improves the accuracy of the targeting strategy by taking into account the user's geographical location. Some or all of the above processing in the targeting suggestion unit may be performed using AI, for example, or without AI. For example, the targeting suggestion unit can input the user's geographical location information into a generating AI and have the generating AI execute the targeting strategy proposal.

[0126] The access analysis tool data loading unit can estimate the user's emotions and adjust the method of loading access analysis data based on the estimated user emotions. For example, if the user is stressed, the access analysis tool data loading unit can provide a simple and highly visual data loading method. If the user is relaxed, the access analysis tool data loading unit can also provide a data loading method that includes detailed information. For example, if the user is in a hurry, the access analysis tool data loading unit can provide a concise data loading method. By adjusting the method of loading access analysis data based on the user's emotions, it becomes possible to load data optimally according to the user's situation. 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 access analysis tool data loading unit may be performed using AI, for example, or without AI. For example, the access analysis tool data loading unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the loading method.

[0127] The following briefly describes the processing flow for example form 2.

[0128] Step 1: The product registration support unit automatically analyzes product information and images and assists in uploading them in the appropriate format. Specifically, it automatically collects product information, analyzes images, and converts them to the appropriate format. It also automatically adjusts image quality and generates product descriptions. For example, it automatically adjusts image resolution and corrects color tones. It can also generate appropriate descriptions based on the product's characteristics. Step 2: The Targeting Proposal Department analyzes purchase history and behavioral data based on the information analyzed by the Product Registration Support Department and proposes an appropriate targeting strategy. Specifically, it analyzes purchase history and provides relevant promotional information to customers who have purchased specific products. It also analyzes behavioral data and proposes personalized promotions based on customer interests. For example, it analyzes a customer's browsing history and suggests products that they might be interested in. Step 3: The Data Analysis Department analyzes site data in real time based on the strategy proposed by the Targeting Proposal Department and proposes optimal marketing measures. Specifically, they read data from access analysis tools and analyze site access data and user behavior. Based on the analysis results, they identify areas for improvement and propose specific improvement plans. For example, they analyze page views and time spent on the site and propose measures to improve the user experience.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] Each of the multiple elements described above, including the product registration support unit, targeting proposal unit, data analysis unit, and automatic product image editing unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the product registration support unit is implemented by the control unit 46A of the smart device 14, which automatically analyzes product information and images and assists in uploading them in the appropriate format. The targeting proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes site data in real time and proposes optimal marketing measures. The automatic product image editing unit is implemented by the control unit 46A of the smart device 14, which automatically analyzes product images and adjusts the resolution and color tone. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0133] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the product registration support unit, targeting proposal unit, data analysis unit, and automatic product image editing unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the product registration support unit is implemented by the control unit 46A of the smart glasses 214, which automatically analyzes product information and images and assists in uploading them in the appropriate format. The targeting proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes site data in real time and proposes optimal marketing measures. The automatic product image editing unit is implemented by the control unit 46A of the smart glasses 214, which automatically analyzes product images and adjusts the resolution and color tone. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0149] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the product registration support unit, targeting proposal unit, data analysis unit, and automatic product image editing unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the product registration support unit is implemented by the control unit 46A of the headset terminal 314, which automatically analyzes product information and images and assists in uploading them in the appropriate format. The targeting proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes site data in real time and proposes optimal marketing measures. The automatic product image editing unit is implemented by the control unit 46A of the headset terminal 314, which automatically analyzes product images and adjusts the resolution and color tone. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0165] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.).

[0178] 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.

[0179] 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.

[0180] 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.

[0181] Each of the multiple elements described above, including the product registration support unit, targeting proposal unit, data analysis unit, and automatic product image editing unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the product registration support unit is implemented by the control unit 46A of the robot 414, which automatically analyzes product information and images and assists in uploading them in the appropriate format. The targeting proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes site data in real time and proposes optimal marketing measures. The automatic product image editing unit is implemented by the control unit 46A of the robot 414, which automatically analyzes product images and adjusts the resolution and color tone. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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."

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] (Note 1) The Product Registration Support Department automatically analyzes product information and images and assists in uploading them in the appropriate format. Based on the information analyzed by the aforementioned Product Registration Support Department, the Targeting Proposal Department analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The system comprises a data analysis unit that analyzes site data in real time based on the strategy proposed by the targeting proposal unit and proposes the optimal marketing measures. A system characterized by the following features. (Note 2) It features an automatic product image editing function that automatically adjusts the quality of product images. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an automatic text generation unit that automatically generates product description text. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a personalized promotion creation unit that automatically creates and executes personalized promotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes an access analysis tool data reading unit that reads data from access analysis tools and reports improvement suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes an improvement proposal reporting section for reporting improvement proposals. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned product registration support department, The system estimates the user's emotions and adjusts the analysis methods for product information and images based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned product registration support department, When retrieving product information, different analysis algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned product registration support department, When analyzing product information, we improve the accuracy of the analysis by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned product registration support department, The system estimates user sentiment and adjusts the timing of product information and image uploads based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned product registration support department, When analyzing product information, the analysis method is adjusted based on the product's sales region. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned product registration support department, When analyzing product information, we improve the accuracy of the analysis by taking into account the product's brand information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned targeting proposal unit, We estimate user sentiment and adjust how we propose targeting strategies based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned targeting proposal unit, When analyzing purchase history, different analysis algorithms are applied to each product category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned targeting proposal unit, When analyzing purchase history, we improve the accuracy of recommendations by referring to past targeting data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned targeting proposal unit, We estimate user sentiment and prioritize targeting strategies based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned targeting proposal unit, When analyzing purchase history, we propose targeting strategies that take into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned targeting proposal unit, When analyzing purchase history, we analyze users' social media activity to propose targeting strategies. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned data analysis unit, It estimates the user's emotions and adjusts how data analysis is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned data analysis unit, When analyzing website data, we refer to past analysis data to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned data analysis unit, When analyzing website data, integrating different data sources improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned data analysis unit, We estimate user emotions and prioritize data analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned data analysis unit, When analyzing website data, we adjust the analysis method to take into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned data analysis unit, When analyzing website data, we improve analysis accuracy by taking into account user device information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned automatic editing unit for product images is: The system estimates the user's emotions and adjusts the editing method of product images based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned automatic editing unit for product images is: When editing product images, different editing algorithms are applied depending on the product category. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned automatic editing unit for product images is: The system estimates the user's emotions and adjusts the timing of product image editing based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned automatic editing unit for product images is: When editing product images, adjust the editing method based on the product's sales region. The system described in Appendix 2, characterized by the features described herein. (Note 29) The automatic generation unit for the aforementioned draft text is: It estimates the user's emotions and adjusts the wording of the text based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The automatic generation unit for the aforementioned draft text is: When generating text, different generation algorithms are applied depending on the product category. The system described in Appendix 3, characterized by the features described herein. (Note 31) The automatic generation unit for the aforementioned draft text is: It estimates the user's emotions and adjusts the length of the text based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The automatic generation unit for the aforementioned draft text is: When generating text, the generation method is adjusted based on the product's sales region. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned Personalized Promotion Creation Department We estimate user sentiment and adjust the way promotions are presented based on that estimated sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 34) The aforementioned Personalized Promotion Creation Department When creating a promotion, apply different creation algorithms depending on the product category. The system described in Appendix 4, characterized by the features described herein. (Note 35) The aforementioned Personalized Promotion Creation Department We estimate user sentiment and prioritize promotions based on that estimated sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned Personalized Promotion Creation Department When creating a promotion, adjust the creation method to take into account the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned access analysis tool data reading unit is: It estimates the user's emotions and adjusts how access analytics data is loaded based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 38) The aforementioned access analysis tool data reading unit is: When importing access analytics data, integrate different data sources to improve import accuracy. The system described in Appendix 5, characterized by the features described herein. (Note 39) The aforementioned access analysis tool data reading unit is: It estimates the user's emotions and adjusts the timing of loading access analytics data based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 40) The aforementioned access analysis tool data reading unit is: When importing access analytics data, the import method is adjusted to take into account the user's geographical location. The system described in Appendix 5, characterized by the features described herein. (Note 41) The aforementioned improvement proposal report section, We estimate user sentiment and adjust the reporting method for improvement suggestions based on the estimated user sentiment. The system described in Appendix 6, characterized by the features described herein. (Note 42) The aforementioned improvement proposal report section, When reporting improvement suggestions, we refer to past report data to improve report accuracy. The system described in Appendix 6, characterized by the features described herein. (Note 43) The aforementioned improvement proposal report section, The system estimates user emotions and prioritizes improvement suggestions based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 44) The aforementioned improvement proposal report section, When reporting improvement suggestions, adjust the reporting method to take into account the user's geographical location. The system described in Appendix 6, characterized by the features described herein. [Explanation of Symbols]

[0201] 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. The Product Registration Support Department automatically analyzes product information and images and assists in uploading them in the appropriate format. Based on the information analyzed by the aforementioned Product Registration Support Department, the Targeting Proposal Department analyzes purchase history and behavioral data and proposes an appropriate targeting strategy. The system comprises a data analysis unit that analyzes site data in real time based on the strategy proposed by the targeting proposal unit and proposes the optimal marketing measures. A system characterized by the following features.

2. It features an automatic product image editing function that automatically adjusts the quality of product images. The system according to feature 1.

3. It includes an automatic text generation unit that automatically generates product description text. The system according to feature 1.

4. It includes a personalized promotion creation unit that automatically creates and executes personalized promotions. The system according to feature 1.

5. It includes an access analysis tool data reading unit that reads data from access analysis tools and reports improvement suggestions. The system according to feature 1.

6. It includes an improvement proposal reporting section for reporting improvement proposals. The system according to feature 1.

7. The aforementioned product registration support department, The system estimates the user's emotions and adjusts the analysis methods for product information and images based on those estimated emotions. The system according to feature 1.

8. The aforementioned product registration support department, When retrieving product information, different analysis algorithms are applied depending on the product category. The system according to feature 1.

9. The aforementioned product registration support department, When analyzing product information, we improve the accuracy of the analysis by referring to past analysis data. The system according to feature 1.

Images