System

Abstract

An object of a system according to an embodiment is to detect a plurality of listings of the same product and appropriately deal with the plurality of listings.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, a warning unit, and a deletion unit. The collection unit collects the exhibition data. The analysis unit analyzes the data collected by the collection unit and detects a plurality of exhibition of the same product. The warning unit issues a warning for a plurality of exhibition of the same commodity detected by the analysis unit. The deletion unit automatically deletes a plurality of exhibition of the same commodity detected by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it is difficult to prevent search results from being dominated by multiple listings of the same product, and there is room for improvement.

[0005] The system according to the embodiment aims to detect multiple listings of the same product and deal with them appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a warning unit, and a deletion unit. The collection unit collects listing data. The analysis unit analyzes the data collected by the collection unit and detects multiple listings of the same product. The warning unit issues a warning about multiple listings of the same product detected by the analysis unit. The deletion unit automatically deletes multiple listings of the same product detected by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect multiple listings of the same product and deal with them appropriately. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple 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), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention prevents multiple listings of the same product from dominating search results in a commerce service. This system collects listing data from each store and uses AI to detect multiple listings of the same product and issue a warning or automatically remove them. For example, the system collects listing data from each store, including detailed data such as product name, product description, price, and images. The system then analyzes the collected data using AI to detect multiple listings of the same product. The AI ​​analyzes data such as product name, product description, and images to determine whether the listings are the same product. For example, listings with the same product name, similar product descriptions, or identical images can be determined to be the same product. Furthermore, the system issues a warning or automatically removes the detected multiple listings of the same product. For example, if multiple listings of the same product are detected, a warning message is sent to the store. Alternatively, the system can automatically remove duplicate listings. This prevents multiple listings of the same product from dominating search results. This allows the system to achieve significant returns with minimal effort. Using AI significantly reduces manual review work and efficiently detects and handles multiple listings of the same product. This improves the quality of search results and enhances user convenience. It also provides a fair competitive environment for stores.

[0029] A commerce service system according to an embodiment includes a collection unit, an analysis unit, a warning unit, and a deletion unit. The collection unit collects listing data for each store. The collection unit collects detailed data, such as product names, product descriptions, prices, and images. For example, the collection unit collects data on products listed by each store on an e-commerce site. The collection unit can also collect data using, for example, an API. The collection unit can also collect data using web scraping technology. The analysis unit analyzes the data collected by the collection unit to detect multiple listings of the same product. The analysis unit, for example, uses AI to analyze data such as product names, product descriptions, and images to determine whether the products are the same. For example, the analysis unit analyzes product descriptions using natural language processing technology to determine whether the products are the same. The analysis unit can also analyze product images using image recognition technology to determine whether the products are the same. The warning unit issues a warning for multiple listings of the same product detected by the analysis unit. For example, if multiple listings of the same product are detected, the warning unit sends a warning message to the store. The warning message is sent by, for example, email, in-app notification, or the like. The deletion unit automatically deletes multiple listings of the same product detected by the analysis unit. For example, when multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit performs deletion based on, for example, the timing of deletion and the selection criteria for items to be deleted. This allows the commerce service system according to the embodiment to prevent search results from being dominated by multiple listings of the same product and to take efficient measures.

[0030] The collection unit can collect product names, product descriptions, prices, images, and detailed data. Detailed data includes, but is not limited to, product specifications and user reviews. The collection unit collects detailed data such as product names, product descriptions, prices, and images. The collection unit can also collect data using, for example, an API. The collection unit can also collect data using web scraping technology. For example, the collection unit collects data on products listed by each store on an e-commerce site. By collecting detailed data, multiple listings of the same product can be accurately detected. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the collected data into a generation AI and have the generation AI analyze the data.

[0031] The analysis unit can analyze product names, product descriptions, images, and data to determine whether the products are the same. The analysis unit can analyze product descriptions using, for example, natural language processing technology to determine whether the products are the same. For example, the analysis unit can analyze the text of the product descriptions to detect subtle differences. The analysis unit can also analyze product images using image recognition technology to determine whether the products are the same. For example, the analysis unit can integrate and analyze multiple product images taken from different angles. The analysis unit can also remove the background from the product images and extract and analyze the features of the product itself. The analysis unit can also analyze different parts of the product images and integrate them to determine whether the products are the same. This allows for efficient detection of multiple listings of the same product by analyzing data such as product names, product descriptions, and images. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data such as product names, product descriptions, and images into a generation AI and have the generation AI determine whether the products are the same.

[0032] The warning unit may send a warning message to a store when multiple listings of the same product are detected. The warning message may include, but is not limited to, specific examples of violations and methods for remediation related to multiple listings of the same product. For example, the warning unit may send a warning message to a store when multiple listings of the same product are detected. The warning message may be sent by email, in-app notification, or other means. The warning unit may optimize the timing of sending the warning message to match the store's operating hours. The warning unit may also include specific examples of violations and methods for remediation in the content of the warning message. For example, the warning unit may include specific examples of violations related to multiple listings of the same product in the warning message. The warning unit may also include specific methods for remediating the violation in the warning message. In this way, sending a warning message when multiple listings of the same product are detected can prompt the store to take action quickly. Some or all of the above-described processing by the warning unit may be performed using, for example, AI, or may be performed without AI. For example, the warning unit may input the store's operating hours and past violation history into the generation AI, and cause the generation AI to optimize the content and timing of the warning message.

[0033] The deletion unit can automatically delete duplicate listings when multiple listings of the same product are detected. The deletion unit performs deletion based on, for example, the timing of deletion and criteria for selecting items to be deleted. For example, when multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit can also automatically notify the store of the reason for deletion when deleting items. The deletion unit can also store a deletion history and use it for future analysis and improvement. For example, the deletion unit can store the deletion history in a database and use it for future analysis. The deletion unit can also improve the deletion algorithm based on the deletion history. Furthermore, the deletion unit can back up and save related product data when deleting items. For example, the deletion unit backs up and saves related product data before deleting items. This can improve the quality of search results by automatically deleting items when multiple listings of the same product are detected. Some or all of the above-described processing by the deletion unit can be performed using, for example, AI, or without AI. For example, the deletion unit can input the timing of deletion and criteria for selecting items to be deleted to the generation AI and have the generation AI perform the deletion.

[0034] The collection unit can analyze the sales history of each store and focus on collecting listing data for a specific period. For example, the collection unit can analyze the sales history of each store over the past year and collect listing data for a specific season or event period. For example, the collection unit can analyze the monthly sales data of each store and collect listing data for periods when sales increased sharply. The collection unit can also analyze the weekly sales data of each store and collect data on items listed on specific days of the week. This enables more effective countermeasures by focusing on collecting listing data for a specific period. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input sales history data into a generation AI and cause the generation AI to collect listing data for a specific period.

[0035] The collection unit can collect product reviews and ratings, associate them with the listing data, and analyze them. For example, the collection unit can automatically collect product reviews and ratings from the listing pages of each store and associate them with the listing data. For example, the collection unit can use an API to obtain product reviews and ratings from each store's database and associate them with the listing data. The collection unit can also use web scraping technology to collect product reviews and ratings from each store's website and associate them with the listing data. This enables more accurate analysis by collecting product reviews and ratings and analyzing them in association with the listing data. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input product review and rating data into a generation AI and have the generation AI associate the data with the listing data.

[0036] The analysis unit can enhance the natural language processing of product descriptions to detect subtle differences. The analysis unit can, for example, use the latest natural language processing (NLP) models to analyze product descriptions and detect subtle differences. For example, the analysis unit can analyze the text of product descriptions to detect synonyms and contextual differences. The analysis unit can also implement contextual analysis to calculate the similarity of product descriptions and detect subtle differences. Furthermore, the analysis unit can segment the text of product descriptions and calculate the similarity of each segment to detect subtle differences. This enhances the natural language processing of product descriptions, making it possible to detect subtle differences and more accurately identify multiple listings of the same product. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the text data of product descriptions into a generation AI and have the generation AI detect subtle differences.

[0037] The analysis unit can improve the accuracy of analysis by integrating images of different angles and backgrounds when analyzing product images. For example, the analysis unit integrates and analyzes multiple product images taken from different angles. For example, the analysis unit removes the background of the product image and extracts and analyzes the features of the product itself. The analysis unit can also analyze different parts of the product image and integrate them to determine whether they are the same product. Furthermore, the analysis unit can use an image recognition algorithm to integrate images of different angles and backgrounds to improve the accuracy of analysis. In this way, by integrating and analyzing images of different angles and backgrounds, the accuracy of determining whether the product is the same can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input product image data to a generation AI and have the generation AI perform an integrated analysis of images of different angles and backgrounds.

[0038] The warning unit can optimize the timing of sending the warning message to match the store's operating hours. For example, the warning unit transmits the warning message to match the store's business hours. For example, the warning unit transmits the warning message during times when the store is most active. The warning unit can also analyze the store's past activity patterns and transmit the warning message at the optimal timing. This allows the effectiveness of the warning to be maximized by transmitting the warning message to match the store's operating hours. Some or all of the above-described processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input store operating hours data into the generation AI and cause the generation AI to optimize the timing of sending the warning message.

[0039] The warning unit can include specific examples of violations and methods of improvement in the content of the warning message. For example, the warning unit can include specific examples of violations related to multiple listings of the same product in the warning message. For example, the warning unit can include specific methods for improving the violation in the warning message. The warning unit can also include specific methods of improvement in the warning message by referring to past examples of violations. In this way, by including specific examples of violations and methods of improvement, the store can take appropriate measures. Some or all of the above-mentioned processing in the warning unit can be performed using AI, for example, or can be performed without using AI. For example, the warning unit can input data on past violations into a generation AI and cause the generation AI to generate the content of the warning message.

[0040] The warning unit can analyze the warning message sending history and learn effective warning methods. For example, the warning unit can analyze the warning message sending history of past messages and identify effective warning methods. For example, the warning unit can learn effective warning message patterns and reflect them in future warning messages. The warning unit can also customize the optimal warning method for each store based on the warning message sending history. In this way, by analyzing the warning message sending history, effective warning methods can be learned and reflected in future warnings. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input warning message sending history data into a generation AI and cause the generation AI to learn effective warning methods.

[0041] The deletion unit can automatically notify the store of the reason for deletion when deleting content. For example, the deletion unit automatically notifies the store of the reason for deletion when deletion is performed. For example, the deletion unit notifies the store of the reason for deletion using an API. The deletion unit can also notify the store of the reason for deletion using web scraping technology. By automatically notifying the store of the reason for deletion, the store can understand the reason for deletion and work to prevent recurrence. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the reason for deletion data into a generation AI and have the generation AI notify the reason for deletion.

[0042] The deletion unit can store the deletion history and use it for future analysis and improvement. For example, the deletion unit can store the deletion history in a database and use it for future analysis. For example, the deletion unit can improve the deletion algorithm based on the deletion history. The deletion unit can also analyze the deletion history and identify effective deletion methods. In this way, storing the deletion history can be useful for future analysis and improvement. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the deletion history data to a generation AI and have the generation AI improve the deletion algorithm.

[0043] The deletion unit can back up and store related product data when deleting. For example, the deletion unit backs up and stores related product data before deletion. For example, the deletion unit uses an API to back up related product data. The deletion unit can also use web scraping technology to back up related product data. By backing up and storing related product data, the data can be restored as needed. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input related product data to a generation AI and have the generation AI perform backup and storage.

[0044] When deleting content, the deletion unit can adjust the strictness of the deletion by referring to the store's past violation history. The deletion unit, for example, adjusts the strictness of the deletion based on the store's past violation history. For example, the deletion unit performs deletion by referring to the strictness of deletion for past violations. The deletion unit can also analyze the store's violation history and determine the optimal deletion method. In this way, by referring to the store's past violation history, it is possible to adjust the appropriate strictness of the deletion. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the store's violation history data into a generation AI and cause the generation AI to adjust the strictness of the deletion.

[0045] When deleting content, the deletion unit can take appropriate action by taking into account the geographical location information of the store. The deletion unit can take appropriate action based on, for example, the store's location information. For example, the deletion unit can use an API to obtain the store's geographical location information and take appropriate action. The deletion unit can also use web scraping technology to collect store location information and take appropriate action. This allows appropriate action to be taken by taking into account the store's geographical location information. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can input the store's geographical location information data into a generation AI and have the generation AI take appropriate action.

[0046] The deletion unit can improve the accuracy of deletion by comparing related product data with other stores when deleting. For example, before deletion, the deletion unit compares the related product data with other stores to improve accuracy. For example, the deletion unit uses an API to compare the related product data with other stores. The deletion unit can also use web scraping technology to compare the related product data with other stores. This allows the accuracy of deletion to be improved by comparing the related product data with other stores. Some or all of the above-described processing by the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the related product data to a generation AI and cause the generation AI to compare it with other stores.

[0047] The analysis unit can analyze fluctuations in commodity prices and detect price manipulation of the same commodity. The analysis unit, for example, analyzes historical commodity price data and detects abnormal price fluctuations. For example, the analysis unit detects the possibility of price manipulation when the price of the same commodity fluctuates significantly in a short period of time. The analysis unit can also analyze commodity price fluctuation patterns and detect signs of price manipulation. In this way, price manipulation of the same commodity can be detected by analyzing commodity price fluctuations. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input historical commodity price data into the generation AI and cause the generation AI to detect price manipulation.

[0048] The analysis unit can analyze the product sales history and detect abnormal listing patterns over a specific period. For example, the analysis unit can analyze the product sales history and detect abnormal listing patterns over a specific period. For example, the analysis unit can construct an algorithm for detecting abnormal listing patterns based on the product sales history data. The analysis unit can also analyze the product sales history in real time and detect abnormal listing patterns. In this way, by analyzing the product sales history, abnormal listing patterns over a specific period can be detected. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input product sales history data to a generation AI and cause the generation AI to detect abnormal listing patterns.

[0049] The analysis unit can improve the accuracy of identifying identical products by referring to product-related literature and patent information. The analysis unit, for example, analyzes product-related literature to improve the accuracy of identifying identical products. For example, the analysis unit can improve the accuracy of identifying identical products by referring to patent information. The analysis unit can also integrate and analyze product-related literature and patent information to improve the accuracy of identifying identical products. This makes it possible to improve the accuracy of identifying identical products by referring to product-related literature and patent information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input product-related literature and patent information data into the generation AI and cause the generation AI to improve the accuracy of identifying identical products.

[0050] When sending a warning message, the warning unit can customize the content by referring to the store's past violation history. The warning unit customizes the content of the warning message based on, for example, the store's past violation history. For example, the warning unit adjusts the content by referring to warning messages for past violations. The warning unit can also analyze the store's violation history and create an optimal warning message. This makes it possible to send an appropriate warning message by referring to the store's past violation history. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the store's violation history data into a generation AI and cause the generation AI to customize the content of the warning message.

[0051] When transmitting a warning message, the warning unit can transmit the warning message in an appropriate language, taking into account the store's geographical location information. The warning unit transmits the warning message in an appropriate language, for example, based on the store's location information. For example, the warning unit can use an API to obtain the store's geographical location information and transmit the warning message in the appropriate language. The warning unit can also use web scraping technology to collect store location information and transmit the warning message in the appropriate language. This allows the warning message to be transmitted in the appropriate language by taking into account the store's geographical location information. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the store's geographical location information data into a generation AI and cause the generation AI to transmit a warning message in the appropriate language.

[0052] When sending a warning message, the warning unit can adjust the severity of the warning by taking into account the sales performance of the store. The warning unit adjusts the severity of the warning message, for example, based on the sales performance of the store. For example, the warning unit sends a strict warning message to a store with a high sales performance. The warning unit can also send a flexible warning message to a store with a low sales performance. This makes it possible to adjust the severity of the warning appropriately by taking into account the sales performance of the store. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input sales performance data of the store into the generation AI and cause the generation AI to adjust the severity of the warning message.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The analysis unit enhances the natural language processing of product descriptions to detect subtle differences. For example, it uses the latest natural language processing (NLP) models to analyze product descriptions and detect synonyms and contextual differences. It can also introduce contextual analysis to calculate the similarity of product descriptions to detect subtle differences. It can also segment the text of product descriptions and calculate the similarity of each part to detect subtle differences. By enhancing the natural language processing of product descriptions, it can detect subtle differences and more accurately identify multiple listings of the same product.

[0055] The analysis unit can analyze fluctuations in product prices and detect price manipulation of the same product. For example, it can analyze historical product price data to detect abnormal price fluctuations. For example, if the price of the same product fluctuates significantly in a short period of time, it can detect the possibility of price manipulation. It can also analyze product price fluctuation patterns to detect signs of price manipulation. This makes it possible to detect price manipulation of the same product by analyzing product price fluctuations.

[0056] The deletion unit can adjust the strictness of deletion by referring to the store's past violation history when deleting content. For example, the deletion unit adjusts the strictness of deletion based on the store's past violation history. For example, deletion is performed by referring to the strictness of deletion for past violations. The deletion unit can also analyze the store's violation history and determine the optimal deletion method. In this way, the strictness of deletion can be adjusted appropriately by referring to the store's past violation history.

[0057] The collection unit can analyze the sales history of each store and focus on collecting listing data for a specific period. For example, it can analyze the sales history of each store for the past year and collect listing data for a specific season or event period. For example, it can analyze the monthly sales data of each store and collect listing data for periods when sales increased sharply. It can also analyze the weekly sales data of each store and collect data on items listed on specific days of the week. This allows for more effective measures by focusing on collecting listing data for a specific period.

[0058] The analysis unit can improve the accuracy of determining identical products by referring to product-related literature and patent information. For example, the analysis unit can analyze product-related literature to improve the accuracy of determining identical products. For example, the analysis unit can refer to patent information to improve the accuracy of determining identical products. It can also analyze product-related literature and patent information in an integrated manner to improve the accuracy of determining identical products. This makes it possible to improve the accuracy of determining identical products by referring to product-related literature and patent information.

[0059] The deletion unit can improve the accuracy of deletion by comparing related product data with other stores when deleting. For example, before deletion, the related product data is compared with other stores to improve accuracy. For example, an API is used to compare the related product data with other stores. Alternatively, web scraping technology can be used to compare the related product data with other stores. In this way, the accuracy of deletion can be improved by comparing the related product data with other stores.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The collection unit collects listing data from each store. The collection unit collects detailed data such as product names, product descriptions, prices, and images. The collection unit collects data on products listed by each store on the e-commerce site. The collection unit can collect data using an API or web scraping technology. Step 2: The analysis unit analyzes the data collected by the collection unit and detects multiple listings of the same product. The analysis unit uses AI to analyze data such as product names, product descriptions, and images to determine whether the products are the same. For example, it can use natural language processing technology to analyze product descriptions and determine whether the products are the same. It can also use image recognition technology to analyze product images and determine whether the products are the same. Step 3: The warning unit issues a warning about multiple listings of the same product detected by the analysis unit. If multiple listings of the same product are detected, the warning unit sends a warning message to the store. The warning message is sent by email, in-app notification, or other means. Step 4: The deletion unit automatically deletes multiple listings of the same product detected by the analysis unit. When multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit performs deletion based on the timing of deletion and the selection criteria for items to be deleted.

[0062] (Example 2) A system according to an embodiment of the present invention prevents multiple listings of the same product from dominating search results in a commerce service. This system collects listing data from each store and uses AI to detect multiple listings of the same product and issue a warning or automatically remove them. For example, the system collects listing data from each store, including detailed data such as product name, product description, price, and images. The system then analyzes the collected data using AI to detect multiple listings of the same product. The AI ​​analyzes data such as product name, product description, and images to determine whether the listings are the same product. For example, listings with the same product name, similar product descriptions, or identical images can be determined to be the same product. Furthermore, the system issues a warning or automatically removes the detected multiple listings of the same product. For example, if multiple listings of the same product are detected, a warning message is sent to the store. Alternatively, the system can automatically remove duplicate listings. This prevents multiple listings of the same product from dominating search results. This allows the system to achieve significant returns with minimal effort. Using AI significantly reduces manual review work and efficiently detects and handles multiple listings of the same product. This improves the quality of search results and enhances user convenience. It also provides a fair competitive environment for stores.

[0063] A commerce service system according to an embodiment includes a collection unit, an analysis unit, a warning unit, and a deletion unit. The collection unit collects listing data for each store. The collection unit collects detailed data, such as product names, product descriptions, prices, and images. For example, the collection unit collects data on products listed by each store on an e-commerce site. The collection unit can also collect data using, for example, an API. The collection unit can also collect data using web scraping technology. The analysis unit analyzes the data collected by the collection unit to detect multiple listings of the same product. The analysis unit, for example, uses AI to analyze data such as product names, product descriptions, and images to determine whether the products are the same. For example, the analysis unit analyzes product descriptions using natural language processing technology to determine whether the products are the same. The analysis unit can also analyze product images using image recognition technology to determine whether the products are the same. The warning unit issues a warning for multiple listings of the same product detected by the analysis unit. For example, if multiple listings of the same product are detected, the warning unit sends a warning message to the store. The warning message is sent by, for example, email, in-app notification, or the like. The deletion unit automatically deletes multiple listings of the same product detected by the analysis unit. For example, when multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit performs deletion based on, for example, the timing of deletion and the selection criteria for items to be deleted. This allows the commerce service system according to the embodiment to prevent search results from being dominated by multiple listings of the same product and to take efficient measures.

[0064] The collection unit can collect product names, product descriptions, prices, images, and detailed data. Detailed data includes, but is not limited to, product specifications and user reviews. The collection unit collects detailed data such as product names, product descriptions, prices, and images. The collection unit can also collect data using, for example, an API. The collection unit can also collect data using web scraping technology. For example, the collection unit collects data on products listed by each store on an e-commerce site. By collecting detailed data, multiple listings of the same product can be accurately detected. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the collected data into a generation AI and have the generation AI analyze the data.

[0065] The analysis unit can analyze product names, product descriptions, images, and data to determine whether the products are the same. The analysis unit can analyze product descriptions using, for example, natural language processing technology to determine whether the products are the same. For example, the analysis unit can analyze the text of the product descriptions to detect subtle differences. The analysis unit can also analyze product images using image recognition technology to determine whether the products are the same. For example, the analysis unit can integrate and analyze multiple product images taken from different angles. The analysis unit can also remove the background from the product images and extract and analyze the features of the product itself. The analysis unit can also analyze different parts of the product images and integrate them to determine whether the products are the same. This allows for efficient detection of multiple listings of the same product by analyzing data such as product names, product descriptions, and images. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data such as product names, product descriptions, and images into a generation AI and have the generation AI determine whether the products are the same.

[0066] The warning unit may send a warning message to a store when multiple listings of the same product are detected. The warning message may include, but is not limited to, specific examples of violations and methods for remediation related to multiple listings of the same product. For example, the warning unit may send a warning message to a store when multiple listings of the same product are detected. The warning message may be sent by email, in-app notification, or other means. The warning unit may optimize the timing of sending the warning message to match the store's operating hours. The warning unit may also include specific examples of violations and methods for remediation in the content of the warning message. For example, the warning unit may include specific examples of violations related to multiple listings of the same product in the warning message. The warning unit may also include specific methods for remediating the violation in the warning message. In this way, sending a warning message when multiple listings of the same product are detected can prompt the store to take action quickly. Some or all of the above-described processing by the warning unit may be performed using, for example, AI, or may be performed without AI. For example, the warning unit may input the store's operating hours and past violation history into the generation AI, and cause the generation AI to optimize the content and timing of the warning message.

[0067] The deletion unit can automatically delete duplicate listings when multiple listings of the same product are detected. The deletion unit performs deletion based on, for example, the timing of deletion and criteria for selecting items to be deleted. For example, when multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit can also automatically notify the store of the reason for deletion when deleting items. The deletion unit can also store a deletion history and use it for future analysis and improvement. For example, the deletion unit can store the deletion history in a database and use it for future analysis. The deletion unit can also improve the deletion algorithm based on the deletion history. Furthermore, the deletion unit can back up and save related product data when deleting items. For example, the deletion unit backs up and saves related product data before deleting items. This can improve the quality of search results by automatically deleting items when multiple listings of the same product are detected. Some or all of the above-described processing by the deletion unit can be performed using, for example, AI, or without AI. For example, the deletion unit can input the timing of deletion and criteria for selecting items to be deleted to the generation AI and have the generation AI perform the deletion.

[0068] The collection unit can estimate a user's emotions and determine an appropriate priority for the data to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions using an emotion analysis algorithm. For example, the collection unit analyzes user behavior data to estimate the user's emotions. The collection unit can also determine the priority for the data to be collected based on the estimated user emotions. For example, if the user is dissatisfied, the collection unit prioritizes collecting particularly problematic listing data. If the user is satisfied, the collection unit can collect normal listing data to maintain overall balance. Furthermore, if the user is excited, the collection unit can prioritize collecting data related to specific categories or trending products. This allows for more appropriate data to be collected by prioritizing data based on the user's emotions. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input user emotion data into a generation AI and have the generation AI determine the priority of the data.

[0069] The collection unit can analyze the sales history of each store and focus on collecting listing data for a specific period. For example, the collection unit can analyze the sales history of each store over the past year and collect listing data for a specific season or event period. For example, the collection unit can analyze the monthly sales data of each store and collect listing data for periods when sales increased sharply. The collection unit can also analyze the weekly sales data of each store and collect data on items listed on specific days of the week. This enables more effective countermeasures by focusing on collecting listing data for a specific period. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input sales history data into a generation AI and cause the generation AI to collect listing data for a specific period.

[0070] The collection unit can collect product reviews and ratings, associate them with the listing data, and analyze them. For example, the collection unit can automatically collect product reviews and ratings from the listing pages of each store and associate them with the listing data. For example, the collection unit can use an API to obtain product reviews and ratings from each store's database and associate them with the listing data. The collection unit can also use web scraping technology to collect product reviews and ratings from each store's website and associate them with the listing data. This enables more accurate analysis by collecting product reviews and ratings and analyzing them in association with the listing data. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input product review and rating data into a generation AI and have the generation AI associate the data with the listing data.

[0071] The analysis unit can enhance the natural language processing of product descriptions to detect subtle differences. The analysis unit can, for example, use the latest natural language processing (NLP) models to analyze product descriptions and detect subtle differences. For example, the analysis unit can analyze the text of product descriptions to detect synonyms and contextual differences. The analysis unit can also implement contextual analysis to calculate the similarity of product descriptions and detect subtle differences. Furthermore, the analysis unit can segment the text of product descriptions and calculate the similarity of each segment to detect subtle differences. This enhances the natural language processing of product descriptions, making it possible to detect subtle differences and more accurately identify multiple listings of the same product. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the text data of product descriptions into a generation AI and have the generation AI detect subtle differences.

[0072] The analysis unit can improve the accuracy of analysis by integrating images of different angles and backgrounds when analyzing product images. For example, the analysis unit integrates and analyzes multiple product images taken from different angles. For example, the analysis unit removes the background of the product image and extracts and analyzes the features of the product itself. The analysis unit can also analyze different parts of the product image and integrate them to determine whether they are the same product. Furthermore, the analysis unit can use an image recognition algorithm to integrate images of different angles and backgrounds to improve the accuracy of analysis. In this way, by integrating and analyzing images of different angles and backgrounds, the accuracy of determining whether the product is the same can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input product image data to a generation AI and have the generation AI perform an integrated analysis of images of different angles and backgrounds.

[0073] The warning unit can estimate the user's emotions and adjust the content of the warning message based on the estimated user emotions. The warning unit, for example, estimates the user's emotions using an emotion analysis algorithm. For example, the warning unit analyzes the user's behavioral data to estimate the user's emotions. The warning unit can also adjust the content of the warning message based on the estimated user emotions. For example, the warning unit can send a stern warning message if the user is dissatisfied. The warning unit can also send a normal warning message if the user is satisfied. Furthermore, the warning unit can also send a warning message that calls attention if the user is excited. This enables more effective warnings by adjusting the content of the warning message based on the user's emotions. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the user's emotion data into a generation AI and have the generation AI adjust the content of the warning message.

[0074] The warning unit can optimize the timing of sending the warning message to match the store's operating hours. For example, the warning unit transmits the warning message to match the store's business hours. For example, the warning unit transmits the warning message during times when the store is most active. The warning unit can also analyze the store's past activity patterns and transmit the warning message at the optimal timing. This allows the effectiveness of the warning to be maximized by transmitting the warning message to match the store's operating hours. Some or all of the above-described processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input store operating hours data into the generation AI and cause the generation AI to optimize the timing of sending the warning message.

[0075] The warning unit can include specific examples of violations and methods of improvement in the content of the warning message. For example, the warning unit can include specific examples of violations related to multiple listings of the same product in the warning message. For example, the warning unit can include specific methods for improving the violation in the warning message. The warning unit can also include specific methods of improvement in the warning message by referring to past examples of violations. In this way, by including specific examples of violations and methods of improvement, the store can take appropriate measures. Some or all of the above-mentioned processing in the warning unit can be performed using AI, for example, or can be performed without using AI. For example, the warning unit can input data on past violations into a generation AI and cause the generation AI to generate the content of the warning message.

[0076] The warning unit can analyze the warning message sending history and learn effective warning methods. For example, the warning unit can analyze the warning message sending history of past messages and identify effective warning methods. For example, the warning unit can learn effective warning message patterns and reflect them in future warning messages. The warning unit can also customize the optimal warning method for each store based on the warning message sending history. In this way, by analyzing the warning message sending history, effective warning methods can be learned and reflected in future warnings. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input warning message sending history data into a generation AI and cause the generation AI to learn effective warning methods.

[0077] The deletion unit can automatically notify the store of the reason for deletion when deleting content. For example, the deletion unit automatically notifies the store of the reason for deletion when deletion is performed. For example, the deletion unit notifies the store of the reason for deletion using an API. The deletion unit can also notify the store of the reason for deletion using web scraping technology. By automatically notifying the store of the reason for deletion, the store can understand the reason for deletion and work to prevent recurrence. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the reason for deletion data into a generation AI and have the generation AI notify the reason for deletion.

[0078] The deletion unit can store the deletion history and use it for future analysis and improvement. For example, the deletion unit can store the deletion history in a database and use it for future analysis. For example, the deletion unit can improve the deletion algorithm based on the deletion history. The deletion unit can also analyze the deletion history and identify effective deletion methods. In this way, storing the deletion history can be useful for future analysis and improvement. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the deletion history data to a generation AI and have the generation AI improve the deletion algorithm.

[0079] The deletion unit can back up and store related product data when deleting. For example, the deletion unit backs up and stores related product data before deletion. For example, the deletion unit uses an API to back up related product data. The deletion unit can also use web scraping technology to back up related product data. By backing up and storing related product data, the data can be restored as needed. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input related product data to a generation AI and have the generation AI perform backup and storage.

[0080] The deletion unit can estimate a user's emotions and determine appropriate deletion priorities based on the estimated user emotions. The deletion unit, for example, estimates a user's emotions using an emotion analysis algorithm. For example, the deletion unit can analyze user behavioral data to estimate a user's emotions. The deletion unit can also determine deletion priorities based on the estimated user emotions. For example, the deletion unit can prioritize deletion of problematic listings when a user is dissatisfied. The deletion unit can also perform deletion with normal priority when a user is satisfied. Furthermore, the deletion unit can prioritize deletion of listings related to a specific category or trending products when a user is excited. This enables more appropriate deletion by determining deletion priorities based on user emotions. Some or all of the above-described processing by the deletion unit may be performed using, for example, AI, or without AI. For example, the deletion unit can input user emotion data into a generation AI and have the generation AI determine the deletion priorities.

[0081] When deleting content, the deletion unit can adjust the strictness of the deletion by referring to the store's past violation history. The deletion unit, for example, adjusts the strictness of the deletion based on the store's past violation history. For example, the deletion unit performs deletion by referring to the strictness of deletion for past violations. The deletion unit can also analyze the store's violation history and determine the optimal deletion method. In this way, by referring to the store's past violation history, it is possible to adjust the appropriate strictness of the deletion. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the store's violation history data into a generation AI and cause the generation AI to adjust the strictness of the deletion.

[0082] When deleting content, the deletion unit can take appropriate action by taking into account the geographical location information of the store. The deletion unit can take appropriate action based on, for example, the store's location information. For example, the deletion unit can use an API to obtain the store's geographical location information and take appropriate action. The deletion unit can also use web scraping technology to collect store location information and take appropriate action. This allows appropriate action to be taken by taking into account the store's geographical location information. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can input the store's geographical location information data into a generation AI and have the generation AI take appropriate action.

[0083] The deletion unit can improve the accuracy of deletion by comparing related product data with other stores when deleting. For example, before deletion, the deletion unit compares the related product data with other stores to improve accuracy. For example, the deletion unit uses an API to compare the related product data with other stores. The deletion unit can also use web scraping technology to compare the related product data with other stores. This allows the accuracy of deletion to be improved by comparing the related product data with other stores. Some or all of the above-described processing by the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can input the related product data to a generation AI and cause the generation AI to compare it with other stores.

[0084] The analysis unit can estimate a user's emotions and appropriately adjust the analysis algorithm based on the estimated user emotions. The analysis unit, for example, estimates a user's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes user behavior data to estimate the user's emotions. The analysis unit can also adjust the analysis algorithm based on the estimated user emotions. For example, if a user is dissatisfied, the analysis unit can adjust the algorithm to prioritize analyzing problematic listing data. If a user is satisfied, the analysis unit can also adjust the algorithm to prioritize analyzing normal listing data. Furthermore, if a user is excited, the analysis unit can adjust the algorithm to prioritize analyzing data related to a specific category or trending products. This allows for more appropriate analysis by adjusting the analysis algorithm based on the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input user emotion data into a generation AI and cause the generation AI to adjust the analysis algorithm.

[0085] The analysis unit can analyze fluctuations in commodity prices and detect price manipulation of the same commodity. The analysis unit, for example, analyzes historical commodity price data and detects abnormal price fluctuations. For example, the analysis unit detects the possibility of price manipulation when the price of the same commodity fluctuates significantly in a short period of time. The analysis unit can also analyze commodity price fluctuation patterns and detect signs of price manipulation. In this way, price manipulation of the same commodity can be detected by analyzing commodity price fluctuations. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input historical commodity price data into the generation AI and cause the generation AI to detect price manipulation.

[0086] The analysis unit can analyze the product sales history and detect abnormal listing patterns over a specific period. For example, the analysis unit can analyze the product sales history and detect abnormal listing patterns over a specific period. For example, the analysis unit can construct an algorithm for detecting abnormal listing patterns based on the product sales history data. The analysis unit can also analyze the product sales history in real time and detect abnormal listing patterns. In this way, by analyzing the product sales history, abnormal listing patterns over a specific period can be detected. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input product sales history data to a generation AI and cause the generation AI to detect abnormal listing patterns.

[0087] The analysis unit can improve the accuracy of identifying identical products by referring to product-related literature and patent information. The analysis unit, for example, analyzes product-related literature to improve the accuracy of identifying identical products. For example, the analysis unit can improve the accuracy of identifying identical products by referring to patent information. The analysis unit can also integrate and analyze product-related literature and patent information to improve the accuracy of identifying identical products. This makes it possible to improve the accuracy of identifying identical products by referring to product-related literature and patent information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input product-related literature and patent information data into the generation AI and cause the generation AI to improve the accuracy of identifying identical products.

[0088] The warning unit can estimate the user's emotions and determine an appropriate priority for the warning message based on the estimated user's emotions. The warning unit, for example, estimates the user's emotions using an emotion analysis algorithm. For example, the warning unit can analyze the user's behavioral data to estimate the user's emotions. The warning unit can also determine the priority of the warning message based on the estimated user's emotions. For example, the warning unit can set a high priority for the warning message if the user is dissatisfied. The warning unit can also send a warning message with a normal priority if the user is satisfied. Furthermore, the warning unit can adjust the priority of the warning message if the user is excited. This enables more effective warnings by determining the priority of the warning message based on the user's emotions. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input user's emotion data into a generation AI and have the generation AI determine the priority of the warning message.

[0089] When sending a warning message, the warning unit can customize the content by referring to the store's past violation history. The warning unit customizes the content of the warning message based on, for example, the store's past violation history. For example, the warning unit adjusts the content by referring to warning messages for past violations. The warning unit can also analyze the store's violation history and create an optimal warning message. This makes it possible to send an appropriate warning message by referring to the store's past violation history. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the store's violation history data into a generation AI and cause the generation AI to customize the content of the warning message.

[0090] When transmitting a warning message, the warning unit can transmit the warning message in an appropriate language, taking into account the store's geographical location information. The warning unit transmits the warning message in an appropriate language, for example, based on the store's location information. For example, the warning unit can use an API to obtain the store's geographical location information and transmit the warning message in the appropriate language. The warning unit can also use web scraping technology to collect store location information and transmit the warning message in the appropriate language. This allows the warning message to be transmitted in the appropriate language by taking into account the store's geographical location information. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the store's geographical location information data into a generation AI and cause the generation AI to transmit a warning message in the appropriate language.

[0091] When sending a warning message, the warning unit can adjust the severity of the warning by taking into account the sales performance of the store. The warning unit adjusts the severity of the warning message, for example, based on the sales performance of the store. For example, the warning unit sends a strict warning message to a store with a high sales performance. The warning unit can also send a flexible warning message to a store with a low sales performance. This makes it possible to adjust the severity of the warning appropriately by taking into account the sales performance of the store. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input sales performance data of the store into the generation AI and cause the generation AI to adjust the severity of the warning message.

[0092] The deletion unit can estimate a user's emotions and adjust the appropriate timing of deletion based on the estimated user emotions. The deletion unit, for example, estimates the user's emotions using an emotion analysis algorithm. For example, the deletion unit can analyze user behavioral data to estimate the user's emotions. The deletion unit can also adjust the timing of deletion based on the estimated user emotions. For example, the deletion unit can delete items quickly if the user is dissatisfied. The deletion unit can also delete items at a normal timing if the user is satisfied. Furthermore, the deletion unit can prioritize deleting listings related to a specific category or trending products if the user is excited. This allows for more appropriate timing of deletion by adjusting the timing of deletion based on the user's emotions. Some or all of the above-described processing by the deletion unit may be performed using, for example, AI, or may be performed without AI. For example, the deletion unit can input user emotion data into a generation AI and cause the generation AI to adjust the timing of deletion. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, warning unit, and deletion unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects listing data for each store using the communication I / F 44 of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data using AI. The warning unit is realized, for example, by the control unit 46A of the smart device 14, and sends a warning message when multiple listings of the same product are detected. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically deletes duplicate listings. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, warning unit, and deletion unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects listing data for each store using the communication I / F 44 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using AI. The warning unit is realized, for example, by the control unit 46A of the smart glasses 214 and sends a warning message when multiple listings of the same product are detected. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically deletes duplicate listings. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, warning unit, and deletion unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects listing data for each store using the communication I / F 44 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data using AI. The warning unit is realized, for example, by the control unit 46A of the headset type terminal 314, and sends a warning message when multiple listings of the same product are detected. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically deletes duplicate listings. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, warning unit, and deletion unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects listing data for each store using the communication I / F 44 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data using AI. The warning unit is realized, for example, by the control unit 46A of the robot 414, and sends a warning message when multiple listings of the same product are detected. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically deletes duplicate listings.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The analysis unit enhances the natural language processing of product descriptions to detect subtle differences. For example, it uses the latest natural language processing (NLP) models to analyze product descriptions and detect synonyms and contextual differences. It can also introduce contextual analysis to calculate the similarity of product descriptions to detect subtle differences. It can also segment the text of product descriptions and calculate the similarity of each part to detect subtle differences. By enhancing the natural language processing of product descriptions, it can detect subtle differences and more accurately identify multiple listings of the same product.

[0095] The collection unit can estimate the user's emotions and determine an appropriate priority order for the data to be collected based on the estimated user's emotions. For example, the collection unit can estimate the user's emotions using an emotion analysis algorithm. The collection unit can analyze the user's behavioral data to estimate the user's emotions. The collection unit can also determine the priority order for the data to be collected based on the estimated user's emotions. For example, if the user is dissatisfied, it can prioritize collecting particularly problematic listing data. If the user is satisfied, it can collect normal listing data to maintain an overall balance. Furthermore, if the user is excited, it can prioritize collecting data related to a specific category or trending products. In this way, by prioritizing data based on the user's emotions, more appropriate data can be collected.

[0096] The analysis unit can analyze fluctuations in product prices and detect price manipulation of the same product. For example, it can analyze historical product price data to detect abnormal price fluctuations. For example, if the price of the same product fluctuates significantly in a short period of time, it can detect the possibility of price manipulation. It can also analyze product price fluctuation patterns to detect signs of price manipulation. This makes it possible to detect price manipulation of the same product by analyzing product price fluctuations.

[0097] The warning unit can estimate the user's emotions and adjust the content of the warning message based on the estimated user emotions. For example, the user's emotions can be estimated using an emotion analysis algorithm. The user's behavioral data can be analyzed to estimate the user's emotions. The content of the warning message can also be adjusted based on the estimated user emotions. For example, if the user is dissatisfied, a stern warning message can be sent. If the user is satisfied, a normal warning message can be sent. Furthermore, if the user is excited, a warning message that calls for caution can be sent. This allows for more effective warnings by adjusting the content of the warning message based on the user's emotions.

[0098] The deletion unit can adjust the strictness of deletion by referring to the store's past violation history when deleting content. For example, the deletion unit adjusts the strictness of deletion based on the store's past violation history. For example, deletion is performed by referring to the strictness of deletion for past violations. The deletion unit can also analyze the store's violation history and determine the optimal deletion method. In this way, the strictness of deletion can be adjusted appropriately by referring to the store's past violation history.

[0099] The analysis unit can estimate the user's emotions and appropriately adjust the analysis algorithm based on the estimated user emotions. For example, the user's emotions are estimated using an emotion analysis algorithm. The user's behavioral data is analyzed to estimate the user's emotions. The analysis algorithm can also be adjusted based on the estimated user emotions. For example, if the user is dissatisfied, the algorithm can be adjusted to prioritize analyzing problematic listing data. Also, if the user is satisfied, the algorithm can be adjusted to prioritize analyzing normal listing data. Furthermore, if the user is excited, the algorithm can be adjusted to prioritize analyzing data related to specific categories or trending products. In this way, adjusting the analysis algorithm based on the user's emotions enables more appropriate analysis.

[0100] The collection unit can analyze the sales history of each store and focus on collecting listing data for a specific period. For example, it can analyze the sales history of each store for the past year and collect listing data for a specific season or event period. For example, it can analyze the monthly sales data of each store and collect listing data for periods when sales increased sharply. It can also analyze the weekly sales data of each store and collect data on items listed on specific days of the week. This allows for more effective measures by focusing on collecting listing data for a specific period.

[0101] The deletion unit can estimate the user's emotions and determine an appropriate deletion priority based on the estimated user's emotions. For example, the user's emotions can be estimated using an emotion analysis algorithm. The user's behavioral data can be analyzed to estimate the user's emotions. The deletion priority can also be determined based on the estimated user's emotions. For example, if the user is dissatisfied, problematic listings can be deleted first. If the user is satisfied, deletion can be performed with normal priority. Furthermore, if the user is excited, listings related to a specific category or trending products can be deleted first. Thus, by determining the deletion priority based on the user's emotions, more appropriate deletion is possible.

[0102] The analysis unit can improve the accuracy of determining identical products by referring to product-related literature and patent information. For example, the analysis unit can analyze product-related literature to improve the accuracy of determining identical products. For example, the analysis unit can refer to patent information to improve the accuracy of determining identical products. It can also analyze product-related literature and patent information in an integrated manner to improve the accuracy of determining identical products. This makes it possible to improve the accuracy of determining identical products by referring to product-related literature and patent information.

[0103] The deletion unit can improve the accuracy of deletion by comparing related product data with other stores when deleting. For example, before deletion, the related product data is compared with other stores to improve accuracy. For example, an API is used to compare the related product data with other stores. Alternatively, web scraping technology can be used to compare the related product data with other stores. In this way, the accuracy of deletion can be improved by comparing the related product data with other stores.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The collection unit collects listing data from each store. The collection unit collects detailed data such as product names, product descriptions, prices, and images. The collection unit collects data on products listed by each store on the e-commerce site. The collection unit can collect data using an API or web scraping technology. Step 2: The analysis unit analyzes the data collected by the collection unit and detects multiple listings of the same product. The analysis unit uses AI to analyze data such as product names, product descriptions, and images to determine whether the products are the same. For example, it can use natural language processing technology to analyze product descriptions and determine whether the products are the same. It can also use image recognition technology to analyze product images and determine whether the products are the same. Step 3: The warning unit issues a warning about multiple listings of the same product detected by the analysis unit. If multiple listings of the same product are detected, the warning unit sends a warning message to the store. The warning message is sent by email, in-app notification, or other means. Step 4: The deletion unit automatically deletes multiple listings of the same product detected by the analysis unit. When multiple listings of the same product are detected, the deletion unit automatically deletes the duplicate listings. The deletion unit performs deletion based on the timing of deletion and the selection criteria for items to be deleted.

[0106] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0128] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] 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.

[0169] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects listing data; an analysis unit that analyzes the data collected by the collection unit and detects multiple listings of the same product; a warning unit that issues a warning regarding multiple listings of the same product detected by the analysis unit; a deletion unit that automatically deletes multiple listings of the same product detected by the analysis unit; A system characterized by:

2. The collecting unit Collect product name, description, price, images and detailed data 2. The system of claim 1.

3. The analysis unit Analyze the product name or description, images, and data to determine whether the products are the same 2. The system of claim 1.

4. The warning unit If multiple listings of the same product are detected, a warning message will be sent to the store.

2. The system of claim 1.

5. The deletion unit If multiple listings for the same product are found, the duplicate listings will be automatically deleted.

2. The system of claim 1.

6. The collecting unit Estimate the user's emotions and determine the appropriate priority of data to be collected based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit Analyze the sales history of each store and focus on collecting listing data for a specific period 2. The system of claim 1.

8. The collecting unit Collect product reviews and ratings, correlate them with your listing data, and analyze them 2. The system of claim 1.

Images