System

Abstract

An object of a system according to an embodiment is to improve the efficiency of a product listing process and to support the setting of an appropriate price and the selection of an appropriate FURIMA site.SOLUTION: A system includes a reception part, a measurement part, a calculation part, a creation part, an advice part, a selection part, and a management part. The reception unit receives a photograph of a product from a user. The measurement unit measures a product size based on the photograph received by the reception unit. The calculation unit calculates a delivery charge based on the product size measured by the measurement unit. The creation part creates a commodity introduction sentence based on the delivery charge calculated by the calculation part. An advice part advises a proper price on the basis of the commodity introduction sentence created by the creation part. The selection unit selects an appropriate FURIMA site based on the appropriate price advised by the advice unit. The management part performs simultaneous exhibition management of the plurality of commodities on the basis of the FURIA site selected by the selection part.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, when listing a product, it was difficult to efficiently measure the size, calculate shipping costs, and set an appropriate price, which was time-consuming.

[0005] The system according to the embodiment aims to streamline the product listing process and to support the setting of appropriate prices and the selection of appropriate flea market sites. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a measurement unit, a calculation unit, a creation unit, an advice unit, a selection unit, and a management unit. The reception unit receives product photos from a user. The measurement unit measures the product size based on the photo received by the reception unit. The calculation unit calculates a shipping fee based on the product size measured by the measurement unit. The creation unit creates a product description based on the shipping fee calculated by the calculation unit. The advice unit advises on a fair price based on the product description created by the creation unit. The selection unit selects an appropriate flea market site based on the fair price advised by the advice unit. The management unit manages the simultaneous listing of multiple products based on the flea market site selected by the selection unit. [Effects of the Invention]

[0007] The system according to the embodiment can streamline the process of listing products and assist in setting appropriate prices and selecting appropriate flea market sites. [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) The app of an embodiment of the present invention is a system that allows users to simply take a photo of an item they want to sell using a predetermined procedure. The app measures the item's size, calculates shipping fees, creates a product description, recommends appropriate pricing, selects the optimal flea market site, and manages the simultaneous listing of multiple items. It also helps organize unwanted items and suggests bundled sales and bartering. For example, a user takes a photo of the item they want to sell using a predetermined procedure. The photo is then input into a generation AI. The generation AI automatically measures the item's size from the photo and calculates shipping fees. For example, it measures the item's height, width, and depth and calculates shipping fees based on that information. Next, the generation AI automatically creates a product description. For example, it generates a description that includes the item's features, condition, and usage. This allows users to easily create an attractive product description. Furthermore, the generation AI advises on the appropriate price for the item. It uses market data to analyze the prices at which similar items are traded and suggests an appropriate price. This allows users to set an appropriate price. The generation AI also suggests which flea market site to list the item on for the most efficient results. For example, the app selects the optimal site based on sales trends and fees on a specific flea market site. It also manages sales when listing multiple items simultaneously. For example, it can centrally manage inventory, sales tracking, and sales tallying. This app also helps users organize unwanted items. For example, it offers suggestions for bundle sales and bartering, helping users efficiently dispose of unwanted items. The generative AI analyzes the items the user owns and suggests bundle sales and bartering. This allows the app to measure the items, calculate shipping fees, create product descriptions, advise on appropriate prices, select the optimal flea market site, manage the simultaneous listing of multiple items, organize unwanted items, and suggest bundle sales and bartering, all in one go. For example, users can quickly and accurately take photos of the items they want to sell, and the app automatically processes the information, significantly reducing the user's effort. It also allows users to efficiently dispose of unwanted items and sell them at the right price.

[0029] A sales support system according to an embodiment includes a reception unit, a measurement unit, a calculation unit, a creation unit, an advice unit, a selection unit, and a management unit. The reception unit receives product photos from a user. Product photos from a user may include, but are not limited to, images in JPEG or PNG format, resolution, and shooting conditions. The reception unit, for example, uploads product photos taken by the user to an app. The reception unit can also automatically adjust the resolution and shooting conditions of the photos. For example, the reception unit converts low-resolution photos to high-resolution and adjusts the brightness and contrast appropriately. The measurement unit uses generative AI to measure the product size based on the photos received by the reception unit. The measurement unit can measure the height, width, and depth of the product using image analysis technology. For example, the measurement unit detects the outline of the product and measures the length of each side. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit applies a measurement algorithm specifically for circular products to circular products. The calculation unit calculates the shipping fee based on the product size measured by the measurement unit. The calculation unit calculates the shipping fee based on, for example, the weight and size of the product and the delivery destination. For example, the calculation unit measures the weight of the product and calculates the shipping fee based on the distance to the delivery destination. The calculation unit can also improve the accuracy of the calculation by referring to the user's past shipping fee data. For example, the calculation unit improves the accuracy of the calculation based on data on shipping fees paid by the user in the past. The creation unit uses a generation AI to create a product description text based on the shipping fee calculated by the calculation unit. The creation unit generates a text that includes, for example, the product's features, condition, and usability. For example, the creation unit analyzes a photo of the product and extracts the product's features to generate a text. The creation unit can also apply different text generation methods depending on the product category. For example, in the case of an electronic device, the creation unit applies a text generation method specifically for electronic devices. The advice unit uses a generation AI to advise on an appropriate price based on the product description text created by the creation unit. The advice unit advises on an appropriate price based on, for example, market data. For example, the advice unit analyzes the trading prices of similar products and suggests an appropriate price.The advice unit can also improve the accuracy of the advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of the advice based on price data previously set by the user. The selection unit selects the optimal flea market site based on the appropriate price advised by the advice unit. The selection unit selects the optimal site by taking into account, for example, sales and fees on a specific flea market site. For example, the selection unit preferentially selects flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items previously listed by the user. The management unit manages the simultaneous listing of multiple items based on the flea market site selected by the selection unit. The management unit, for example, manages inventory, tracks sales, and tally sales. For example, the management unit sets an inventory tracking method, inventory update frequency, inventory evaluation criteria, etc., and performs inventory management. The management unit also sets a sales data collection method, sales evaluation criteria, etc., and tracks sales. Furthermore, the management unit sets the sales data collection method, aggregation frequency, aggregation evaluation criteria, etc., and aggregates the sales data. As a result, the sales support system according to the embodiment can measure the product size, calculate the shipping fee, create a product description, advise on the appropriate price, select the most suitable flea market site, and manage the simultaneous listing of multiple products all at once, simply by the user taking a photo of the product.

[0030] The management unit can manage inventory, track sales, and tally sales. The management unit manages inventory by, for example, setting an inventory tracking method, inventory update frequency, and inventory evaluation criteria. For example, the management unit periodically checks inventory quantities and issues an alert when inventory falls below a certain level. The management unit also tracks sales by setting a sales data collection method and sales evaluation criteria. For example, the management unit records the sales volume and sales speed of each product and identifies high-selling and low-selling products. The management unit also sets a sales data collection method, aggregation frequency, and aggregation evaluation criteria, and tally sales. For example, the management unit aggregates sales data daily, weekly, and monthly and analyzes sales trends. This enables inventory management, sales tracking, and sales aggregation. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without AI. For example, the management department can input inventory data and sales data into the generation AI and have the generation AI perform inventory management, sales tracking, and sales aggregation.

[0031] The management unit can organize unnecessary items. For example, the management unit creates a list of products owned by the user and identifies unnecessary items. For example, the management unit evaluates the frequency of use and condition of products owned by the user and lists unnecessary items. The management unit can also suggest methods for disposing of unnecessary items. For example, the management unit suggests disposal methods such as recycling, donation, and disposal. The management unit can also create a schedule for efficiently organizing unnecessary items. For example, the management unit sets a date for organizing unnecessary items according to the user's convenience. This makes it possible to organize unnecessary items. Some or all of the above-mentioned processing in the management unit may be performed using, or without, AI. For example, the management unit can input a list of products owned by the user into a generation AI and have the generation AI identify unnecessary items and suggest disposal methods.

[0032] The management unit can propose set sales. For example, the management unit selects products suitable for set sales from among the products owned by the user. For example, the management unit proposes set sales by combining highly related products. The management unit can also set prices for set sales. For example, the management unit compares the prices of individual sales with the prices of set sales and proposes the optimal price to the user. The management unit can also propose promotion methods for set sales. For example, the management unit plans advertisements and campaigns for set sales and proposes them to the user. This makes it possible to propose set sales. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input data on products owned by the user into a generation AI and have the generation AI execute set sales proposals, pricing, and promotion methods.

[0033] The management unit can make barter proposals. For example, the management unit selects products suitable for bartering from among the products owned by the user. For example, the management unit matches products that the user no longer needs with products offered by other users. The management unit can also set the conditions for the barter. For example, the management unit evaluates the value and condition of the products to be exchanged and proposes fair exchange conditions. The management unit can also manage the barter process. For example, the management unit adjusts the schedule for shipping and receiving the products to be exchanged and notifies the user. This makes it possible to propose bartering. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input data on products owned by the user into the generation AI and have the generation AI perform barter proposals, set conditions, and manage the process.

[0034] The measurement unit can measure the height, width, and depth of a product using image analysis technology. For example, the measurement unit can detect the outline of a product using image analysis technology and measure the length of each side. For example, the measurement unit can automatically measure the height, width, and depth of a product. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit can apply a measurement algorithm specifically for circular products to circular products. The measurement unit can also improve the accuracy of the measurement by referring to the user's past measurement results. For example, the measurement unit can improve the accuracy of the measurement based on the user's past measurement results. This makes it possible to accurately measure the size of a product using image analysis technology. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without AI. For example, the measurement unit can input image data of a product into a generation AI and have the generation AI measure the size of the product.

[0035] The advice unit can advise a fair price based on market data. For example, the advice unit analyzes the prices at which similar products are traded based on market data and proposes a fair price. For example, the advice unit sets a price taking into consideration the condition of the product and supply and demand. The advice unit can also improve the accuracy of its advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of its advice based on price data previously set by the user. This enables appropriate pricing by advising a fair price based on market data. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data into a generation AI and have the generation AI execute advice on a fair price.

[0036] The selection unit can select an appropriate site by taking into consideration sales and fees on a specific flea market site. The selection unit, for example, selects the optimal site based on sales data and fees on the specific flea market site. For example, the selection unit prioritizes selecting flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items the user has previously listed. This enables efficient listing by selecting the optimal site by taking into consideration sales and fees on the specific flea market site. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data and fee data on flea market sites into the generation AI and cause the generation AI to select the optimal flea market site.

[0037] The reception unit can analyze the user's past photo reception history and select an appropriate reception method. For example, the reception unit prioritizes and suggests reception methods that the user has frequently used in the past. For example, the reception unit stores the user's past photo reception history in a database and analyzes frequently used reception methods. The reception unit can also suggest the optimal reception method for a specific time period based on the user's past reception history. For example, the reception unit chronologically analyzes the user's past reception history to identify the optimal reception method for a specific time period. The reception unit can also customize the optimal reception method based on the user's past feedback. For example, the reception unit analyzes feedback provided by the user in the past and optimizes the reception method. This improves user convenience by selecting the optimal reception method based on the user's past history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's past photo reception history data into a generation AI and have the generation AI select the optimal reception method.

[0038] When receiving photos, the reception unit may filter them based on the user's current projects and areas of interest. For example, the reception unit may preferentially receive photos related to projects currently underway by the user. For example, the reception unit may store the user's project information in a database and identify related photos. The reception unit may also filter and receive related photos based on the user's areas of interest. For example, the reception unit may acquire the user's areas of interest from profile information and identify related photos. The reception unit may also preferentially receive related photos by referring to the user's past project history. For example, the reception unit may analyze the user's past project history and identify related photos. In this way, by filtering based on the user's projects and areas of interest, highly relevant photos can be preferentially received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's project information and area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0039] When accepting a photo, the acceptance unit can select an appropriate acceptance means depending on the user's input method. For example, if the user uses voice input, the acceptance unit accepts the photo using voice recognition technology. For example, the acceptance unit records the user's voice with a microphone and converts it into text data using voice recognition technology. Furthermore, if the user uses text input, the acceptance unit can also accept the photo using text analysis technology. For example, the acceptance unit analyzes the text entered by the user and processes the photo. Furthermore, if the user uses image input, the acceptance unit can also accept the photo using image analysis technology. For example, the acceptance unit analyzes images uploaded by the user and processes the photo. This improves user convenience by selecting the optimal acceptance means depending on the user's input method. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without AI. For example, the acceptance unit can input the user's voice data, text data, and image data into a generation AI and have the generation AI select the optimal acceptance means.

[0040] When accepting photos, the reception unit can prioritize accepting highly relevant photos by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes accepting photos related to that area. For example, the reception unit acquires the user's geographical location information from GPS data and identifies relevant photos. The reception unit can also prioritize accepting photos related to locations close to the user's current location. For example, the reception unit tracks the user's current location in real time and identifies relevant photos in the vicinity. The reception unit can also prioritize accepting highly relevant photos by referring to the user's past location information. For example, the reception unit analyzes the user's past location information and identifies relevant photos. This improves user convenience by prioritizing the acceptance of highly relevant photos by taking into account the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to identify relevant photos.

[0041] The reception unit may analyze the user's social media activity and receive related photos when receiving photos. The reception unit, for example, prioritizes receiving photos shared by the user on social media. For example, the reception unit may link the user's social media accounts and identify shared photos. The reception unit may also analyze the user's social media activity and receive related photos. For example, the reception unit may analyze the user's posts, the number of likes, the number of followers, etc. to identify related photos. The reception unit may also prioritize receiving related photos based on the activity of the user's friends on social media. For example, the reception unit may identify photos shared by the user's friends and receive related photos. This improves user convenience by analyzing the user's social media activity and receiving related photos. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit may input the user's social media data into a generation AI and cause the generation AI to identify related photos.

[0042] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a photo. The reception unit, for example, suggests an optimal reception method based on feedback provided by the user in the past. For example, the reception unit stores the user's past feedback in a database and analyzes it. The reception unit can also analyze the user's past feedback and customize the reception method. For example, the reception unit analyzes the content of the user's feedback and optimizes the reception procedure. The reception unit can also optimize the reception procedure by referring to the user's past feedback. For example, the reception unit simplifies the reception procedure based on the user's feedback. This improves user convenience by customizing the reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into a generation AI and have the generation AI customize the reception method.

[0043] The measurement unit can apply different measurement algorithms based on the shape and material of the product during measurement. For example, if the product is circular, the measurement unit applies a measurement algorithm specifically for circular products. For example, the measurement unit detects the outline of the product and measures the diameter of the circular product. Furthermore, if the product is made of metal, the measurement unit can apply a measurement algorithm specifically for metal. For example, the measurement unit performs measurements taking into account the reflective characteristics of metal products. Furthermore, if the product is made of cloth, the measurement unit can apply a measurement algorithm specifically for cloth. For example, the measurement unit performs measurements taking into account the flexibility of cloth products. In this way, by applying different measurement algorithms based on the shape and material of the product, the accuracy of the measurement is improved. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product shape and material data into the generation AI and cause the generation AI to apply the measurement algorithm.

[0044] The measurement unit can improve the accuracy of the measurement by referring to the user's past measurement results during measurement. The measurement unit improves the accuracy of the measurement, for example, based on the user's past measurement results. For example, the measurement unit stores the user's past measurement results in a database and analyzes them. The measurement unit can also analyze the user's past measurement history to optimize the accuracy of the measurement. For example, the measurement unit adjusts the measurement algorithm by referring to the user's past measurement data. This improves the reliability of the measurement by improving the accuracy of the measurement by referring to the user's past measurement results. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input the user's past measurement result data into the generation AI and cause the generation AI to improve the accuracy of the measurement.

[0045] The measurement unit can apply different measurement methods depending on the product category during measurement. For example, in the case of an electronic device, the measurement unit applies a measurement method dedicated to the electronic device. For example, the measurement unit accurately measures the external dimensions of the electronic device. Furthermore, in the case of clothing, the measurement unit can also apply a measurement method dedicated to clothing. For example, the measurement unit accurately measures the size and shape of the clothing. Furthermore, in the case of furniture, the measurement unit can also apply a measurement method dedicated to furniture. For example, the measurement unit accurately measures the dimensions and shape of the furniture. In this way, by applying different measurement methods depending on the product category, the accuracy of the measurement is improved. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product category data into the generation AI and cause the generation AI to apply the measurement method.

[0046] The measurement unit can determine the priority of measurements based on the submission time of the products during measurement. For example, the measurement unit prioritizes measurements of products with upcoming submission deadlines. For example, the measurement unit stores the submission deadlines of products in a database and identifies products with upcoming submission deadlines. The measurement unit can also postpone measurements of products with distant submission deadlines. For example, the measurement unit optimizes the measurement schedule based on the submission deadlines. This enables efficient measurements by determining the priority of measurements based on the submission time of products. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product submission time data into the generation AI and have the generation AI determine the measurement priority.

[0047] The measurement unit can adjust the order of measurements based on the relevance of products during measurement. The measurement unit, for example, prioritizes measurement of highly related products. For example, the measurement unit stores the relevance of products in a database and identifies highly related products. The measurement unit can also postpone measurement of less related products. For example, the measurement unit optimizes the order of measurements based on the relevance of products. This enables efficient measurement by adjusting the order of measurements based on the relevance of products. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product relevance data into a generation AI and cause the generation AI to adjust the order of measurements.

[0048] The measurement unit can adjust the level of detail of the measurement according to the user's level of expertise during measurement. For example, if the user has expertise, the measurement unit provides detailed measurement results. For example, the measurement unit stores the user's level of expertise in a database and provides detailed measurement results. The measurement unit can also provide simplified measurement results if the user does not have expertise. For example, the measurement unit adjusts the level of detail of the measurement based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the measurement according to the user's level of expertise. Some or all of the above-mentioned processing in the measurement unit may be performed using AI, for example, or may be performed without using AI. For example, the measurement unit can input the user's expertise level data to the generation AI and cause the generation AI to adjust the level of detail of the measurement.

[0049] The calculation unit can apply different calculation algorithms based on the weight and size of the product during calculation. For example, if the product is lightweight, the calculation unit applies a calculation algorithm designed specifically for lightweight products. For example, the calculation unit measures the weight of the product and calculates the shipping fee for lightweight products. Furthermore, if the product is large, the calculation unit can also apply a calculation algorithm designed specifically for large products. For example, the calculation unit measures the size of the product and calculates the shipping fee for large items. Furthermore, if the product is medium-sized, the calculation unit can also apply a calculation algorithm designed specifically for medium-sized items. For example, the calculation unit measures the weight and size of the product and calculates the shipping fee for medium-sized items. This improves the accuracy of calculating shipping fees by applying different calculation algorithms based on the weight and size of the product. Some or all of the above-described processing in the calculation unit may be performed using, or without, AI. For example, the calculation unit can input product weight and size data into the generation AI and cause the generation AI to apply the calculation algorithm.

[0050] The calculation unit can improve the accuracy of the calculation by referring to the user's past shipping fee data during calculation. The calculation unit improves the accuracy of the calculation, for example, based on data on shipping fees paid by the user in the past. For example, the calculation unit stores the user's past shipping fee data in a database and analyzes it. The calculation unit can also analyze the user's past shipping fee history to optimize the calculation accuracy. For example, the calculation unit adjusts the calculation algorithm by referring to the user's past shipping fee data. This improves the reliability of the shipping fee by improving the calculation accuracy by referring to the user's past shipping fee data. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the user's past shipping fee data into the generation AI and cause the generation AI to improve the calculation accuracy.

[0051] The calculation unit can apply different calculation methods depending on the delivery destination of the product when calculating. For example, in the case of domestic delivery, the calculation unit applies a calculation method dedicated to domestic delivery. For example, if the delivery destination of the product is domestic, the calculation unit calculates the domestic delivery fee. In addition, the calculation unit can also apply a calculation method dedicated to international delivery in the case of international delivery. For example, if the delivery destination of the product is international, the calculation unit calculates the international delivery fee. In addition, in the case of delivery to a specific region, the calculation unit can apply a calculation method dedicated to that region. For example, if the delivery destination of the product is a specific region, the calculation unit calculates the delivery fee for that region. In this way, by applying different calculation methods depending on the delivery destination of the product, the accuracy of calculating the delivery fee is improved. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product delivery destination data into a generation AI and cause the generation AI to apply the calculation method.

[0052] During calculation, the calculation unit can determine the priority of shipping fees based on the submission time of the product. The calculation unit, for example, prioritizes the calculation of shipping fees for products with upcoming submission deadlines. For example, the calculation unit stores the product submission deadlines in a database and identifies products with upcoming submission deadlines. The calculation unit can also postpone the calculation of shipping fees for products with distant submission deadlines. For example, the calculation unit optimizes the shipping fee calculation schedule based on the submission deadlines. This enables efficient calculation of shipping fees by determining the priority of shipping fees based on the submission time of the product. Some or all of the above-described processing by the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product submission time data into a generation AI and have the generation AI determine the priority of shipping fees.

[0053] The calculation unit can adjust the order of shipping fees based on the relevance of products during calculation. The calculation unit, for example, prioritizes the calculation of shipping fees for highly related products. For example, the calculation unit stores the relevance of products in a database and identifies highly related products. The calculation unit can also postpone the calculation of shipping fees for less related products. For example, the calculation unit optimizes the order of calculation of shipping fees based on the relevance of products. This enables efficient calculation of shipping fees by adjusting the order of shipping fees based on the relevance of products. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product relevance data into a generation AI and have the generation AI adjust the order of shipping fees.

[0054] The calculation unit can adjust the level of detail of the shipping fee according to the user's level of expertise during calculation. For example, if the user has expertise, the calculation unit provides a detailed calculation result of the shipping fee. For example, the calculation unit stores the user's level of expertise in a database and provides a detailed calculation result of the shipping fee. The calculation unit can also provide a simplified calculation result of the shipping fee if the user does not have expertise. For example, the calculation unit adjusts the level of detail of the shipping fee based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the shipping fee according to the user's level of expertise. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the shipping fee.

[0055] The creation unit can apply different sentence generation algorithms based on the characteristics and condition of the product during creation. For example, if the product is new, the creation unit applies a sentence generation algorithm specifically for new products. For example, the creation unit stores the product's condition in a database and applies a sentence generation algorithm specifically for new products. Furthermore, if the product is used, the creation unit can also apply a sentence generation algorithm specifically for used products. For example, the creation unit generates sentences taking into account the product's usage and condition. Furthermore, if the product is an antique, the creation unit can apply a sentence generation algorithm specifically for antiques. For example, the creation unit generates sentences taking into account the product's history and value. In this way, by applying different sentence generation algorithms based on the product's characteristics and condition, the accuracy of the product introduction sentences is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input product feature and condition data into the generation AI and cause the generation AI to apply a sentence generation algorithm.

[0056] The creation unit can improve the accuracy of the text by referring to the user's past introductory texts when creating the text. The creation unit, for example, improves the accuracy of the text based on introductory texts created by the user in the past. For example, the creation unit stores the user's past introductory texts in a database and analyzes them. The creation unit can also analyze the user's past introductory texts and optimize the text generation algorithm. For example, the creation unit adjusts the way the text is expressed by referring to the user's past introductory texts. This improves the accuracy of the text by referring to the user's past introductory texts, thereby improving the reliability of the product introductory text. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the user's past introductory text data into a generation AI and cause the generation AI to improve the accuracy of the text.

[0057] The creation unit can apply different sentence generation methods depending on the product category during creation. For example, in the case of electronic devices, the creation unit applies a sentence generation method dedicated to electronic devices. For example, the creation unit generates sentences taking into account the features and specifications of the electronic devices. In addition, the creation unit can also apply a sentence generation method dedicated to clothing in the case of clothing. For example, the creation unit generates sentences taking into account the size and material of the clothing. In addition, the creation unit can also apply a sentence generation method dedicated to furniture in the case of furniture. For example, the creation unit generates sentences taking into account the design and function of the furniture. In this way, by applying different sentence generation methods depending on the product category, the accuracy of the product introduction sentences is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input product category data into the generation AI and cause the generation AI to apply the sentence generation method.

[0058] The creation unit can determine the priority of texts based on the submission time of the product when they are created. For example, the creation unit prioritizes the creation of introduction texts for products with upcoming submission deadlines. For example, the creation unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The creation unit can also postpone introduction texts for products with distant submission deadlines. For example, the creation unit optimizes the schedule for creating texts based on the submission deadlines. This enables efficient text creation by determining the priority of texts based on the submission time of the product. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input product submission time data into a generation AI and have the generation AI determine the priority of texts.

[0059] The creation unit can adjust the order of sentences based on the relevance of the products when creating them. The creation unit, for example, prioritizes creating introduction sentences for highly relevant products. For example, the creation unit stores product relevance in a database and identifies highly relevant products. The creation unit can also postpone introduction sentences for less relevant products. For example, the creation unit optimizes the order of sentence creation based on product relevance. This enables efficient sentence creation by adjusting the order of sentences based on product relevance. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input product relevance data into a generation AI and have the generation AI adjust the order of sentences.

[0060] The creation unit can adjust the use of technical terms in the sentences during creation according to the user's level of expertise. For example, if the user has technical expertise, the creation unit provides sentences that use a lot of technical terms. For example, the creation unit stores the user's level of expertise in a database and provides sentences that use a lot of technical terms. The creation unit can also provide simplified sentences if the user does not have technical expertise. For example, the creation unit adjusts the use of technical terms in the sentences based on the user's level of expertise. This improves user convenience by adjusting the use of technical terms in the sentences according to the user's level of expertise. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the user's level of expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the sentences.

[0061] When providing advice, the advice unit can apply different advice algorithms based on market data for the product. For example, if the product is expensive, the advice unit applies an advice algorithm dedicated to high-priced products. For example, the advice unit stores market data for the product in a database and applies an advice algorithm dedicated to high-priced products. Furthermore, if the product is low-priced, the advice unit can also apply an advice algorithm dedicated to low-priced products. For example, the advice unit advises an appropriate price for low-priced products based on the market data for the product. Furthermore, if the product is medium-priced, the advice unit can also apply an advice algorithm dedicated to medium-priced products. For example, the advice unit advises an appropriate price for medium-priced products based on the market data for the product. In this way, by applying different advice algorithms based on the market data for the product, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data for the product into a generation AI and cause the generation AI to apply an advice algorithm.

[0062] When providing advice, the advice unit can improve the accuracy of the advice by referring to the user's past pricing data. The advice unit improves the accuracy of the advice, for example, based on price data previously set by the user. For example, the advice unit stores the user's past pricing data in a database and analyzes it. The advice unit can also analyze the user's past pricing history to optimize the accuracy of the advice. For example, the advice unit adjusts the advice algorithm by referring to the user's past pricing data. This improves the accuracy of the advice by referring to the user's past pricing data, thereby improving the reliability of the fair price. Some or all of the above-mentioned processing in the advice unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice unit can input the user's past pricing data into the generation AI and cause the generation AI to improve the accuracy of the advice.

[0063] When providing advice, the advice unit can apply different advice methods depending on the product category. For example, in the case of electronic devices, the advice unit applies an advice method dedicated to electronic devices. For example, the advice unit advises an appropriate price based on market data for electronic devices. In addition, in the case of clothing, the advice unit can also apply an advice method dedicated to clothing. For example, the advice unit advises an appropriate price based on market data for clothing. In addition, in the case of furniture, the advice unit can also apply an advice method dedicated to furniture. For example, the advice unit advises an appropriate price based on market data for furniture. In this way, by applying different advice methods depending on the product category, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product category data into the generation AI and cause the generation AI to apply the advice method.

[0064] When providing advice, the advice unit can determine the priority of fair prices based on the submission date of the product. The advice unit, for example, prioritizes fair price advice for products with an upcoming submission deadline. For example, the advice unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The advice unit can also postpone fair price advice for products with a distant submission deadline. For example, the advice unit optimizes a fair price advice schedule based on the submission deadline. This enables efficient advice by determining the priority of fair prices based on the submission date of the product. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product submission date data into a generation AI and have the generation AI determine the priority of fair prices.

[0065] The advice unit can adjust the order of fair prices based on the relevance of the products when providing advice. The advice unit, for example, prioritizes fair price advice for highly related products. For example, the advice unit stores product relevance in a database and identifies highly related products. The advice unit can also postpone fair price advice for less related products. For example, the advice unit optimizes the order of fair price advice based on the relevance of the products. This enables efficient advice by adjusting the order of fair prices based on the relevance of the products. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product relevance data into a generation AI and have the generation AI adjust the order of fair prices.

[0066] When providing advice, the advice unit can adjust the level of detail of the fair price according to the user's level of expertise. For example, if the user has expertise, the advice unit provides detailed advice on the fair price. For example, the advice unit stores the user's level of expertise in a database and provides detailed advice on the fair price. Furthermore, if the user does not have expertise, the advice unit can also provide simplified advice on the fair price. For example, the advice unit adjusts the level of detail of the fair price based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the fair price according to the user's level of expertise. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the fair price.

[0067] When making a selection, the selection unit can apply different selection algorithms based on sales data of the flea market sites. The selection unit, for example, applies an algorithm that prioritizes the selection of flea market sites with high sales. For example, the selection unit stores sales data of flea market sites in a database and identifies flea market sites with high sales. The selection unit can also apply an algorithm that postpones flea market sites with low sales. For example, the selection unit applies an algorithm that selects the optimal flea market site based on the sales data of the flea market sites. This improves the accuracy of selecting the optimal flea market site by applying different selection algorithms based on the sales data of the flea market sites. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data of flea market sites into the generation AI and cause the generation AI to apply the selection algorithm.

[0068] The selection unit can improve the accuracy of the selection by referring to the user's past listing data when making a selection. The selection unit improves the accuracy of the selection, for example, based on data on items the user has previously listed. For example, the selection unit stores the user's past listing data in a database and analyzes it. The selection unit can also analyze the user's past listing history to optimize the accuracy of the selection. For example, the selection unit adjusts the selection algorithm by referring to the user's past listing data. This improves the accuracy of the selection by referring to the user's past listing data, thereby improving the accuracy of the selection of the optimal flea market site. Some or all of the above-described processing by the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the user's past listing data into the generation AI and cause the generation AI to improve the accuracy of the selection.

[0069] The selection unit can apply different selection methods depending on the product category during selection. For example, in the case of electronic devices, the selection unit applies a selection method dedicated to electronic devices. For example, the selection unit selects the optimal flea market site based on market data for electronic devices. In addition, in the case of clothing, the selection unit can also apply a selection method dedicated to clothing. For example, the selection unit selects the optimal flea market site based on market data for clothing. In addition, in the case of furniture, the selection unit can also apply a selection method dedicated to furniture. For example, the selection unit selects the optimal flea market site based on market data for furniture. In this way, by applying different selection methods depending on the product category, the accuracy of selecting the optimal flea market site is improved. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input product category data into the generation AI and cause the generation AI to apply the selection method.

[0070] During selection, the selection unit can determine the priority of flea market sites based on the submission time of the products. For example, the selection unit prioritizes the selection of flea market sites for products with upcoming submission deadlines. For example, the selection unit stores the product submission deadlines in a database and identifies products with upcoming submission deadlines. The selection unit can also postpone the selection of flea market sites for products with distant submission deadlines. For example, the selection unit optimizes the flea market site selection schedule based on the submission deadlines. This enables efficient selection by determining the priority of flea market sites based on the submission time of the products. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit can input product submission time data into a generation AI and have the generation AI determine the priority of flea market sites.

[0071] The selection unit can adjust the order of flea market sites based on the relevance of the products during selection. The selection unit, for example, prioritizes the selection of flea market sites for highly relevant products. For example, the selection unit stores the relevance of the products in a database and identifies highly relevant products. The selection unit can also postpone the selection of flea market sites for less relevant products. For example, the selection unit optimizes the selection order of flea market sites based on the relevance of the products. This enables efficient selection by adjusting the order of flea market sites based on the relevance of the products. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input product relevance data into a generation AI and cause the generation AI to adjust the order of the flea market sites.

[0072] The selection unit can adjust the level of detail of the flea market site during selection according to the user's level of expertise. For example, if the user has expertise, the selection unit provides a detailed selection result of the flea market site. For example, the selection unit stores the user's level of expertise in a database and provides a detailed selection result of the flea market site. The selection unit can also provide a simplified selection result of the flea market site if the user does not have expertise. For example, the selection unit adjusts the level of detail of the flea market site based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the flea market site according to the user's level of expertise. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the flea market site.

[0073] During management, the management unit can apply different management algorithms based on product sales status data. For example, the management unit applies an algorithm that prioritizes inventory management of products with good sales status. For example, the management unit stores product sales status data in a database and identifies products with good sales status. The management unit can also apply an algorithm that postpones inventory management of products with poor sales status. For example, the management unit applies an optimal inventory management algorithm based on the product sales status data. In this way, by applying different management algorithms based on the product sales status data, the accuracy of inventory management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product sales status data into a generation AI and have the generation AI apply the management algorithm.

[0074] During management, the management unit can improve the accuracy of management by referring to the user's past sales data. The management unit improves the accuracy of management, for example, based on data of past sales by the user. For example, the management unit stores the user's past sales data in a database and analyzes it. The management unit can also analyze the user's past sales history to optimize the accuracy of management. For example, the management unit adjusts the management algorithm by referring to the user's past sales data. This improves the reliability of inventory management by improving the accuracy of management by referring to the user's past sales data. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI or without AI. For example, the management unit can input the user's past sales data into a generation AI and have the generation AI improve the accuracy of management.

[0075] During management, the management unit can apply different management methods depending on the product category. For example, in the case of electronic devices, the management unit applies a management method dedicated to electronic devices. For example, the management unit applies the optimal management method based on inventory data for the electronic devices. In addition, in the case of clothing, the management unit can also apply a management method dedicated to clothing. For example, the management unit applies the optimal management method based on inventory data for clothing. In addition, in the case of furniture, the management unit can also apply a management method dedicated to furniture. For example, the management unit applies the optimal management method based on inventory data for furniture. In this way, by applying different management methods depending on the product category, the accuracy of inventory management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product category data into a generation AI and have the generation AI apply the management method.

[0076] During management, the management unit can determine inventory management priorities based on the submission dates of products. For example, the management unit prioritizes inventory management of products with upcoming submission deadlines. For example, the management unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The management unit can also postpone inventory management of products with distant submission deadlines. For example, the management unit optimizes the inventory management schedule based on the submission deadlines. This enables efficient inventory management by determining inventory management priorities based on the submission dates of products. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product submission date data into a generation AI and have the generation AI determine the inventory management priorities.

[0077] During management, the management unit can adjust the inventory management order based on the relevance of products. The management unit, for example, prioritizes inventory management of highly related products. For example, the management unit stores the relevance of products in a database and identifies highly related products. The management unit can also postpone inventory management of less related products. For example, the management unit optimizes the inventory management order based on the relevance of products. This enables efficient inventory management by adjusting the inventory management order based on the relevance of products. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product relevance data into a generation AI and have the generation AI adjust the inventory management order.

[0078] During management, the management unit can adjust the level of detail of inventory management according to the user's level of expertise. For example, if the user has expertise, the management unit provides detailed inventory management results. For example, the management unit stores the user's level of expertise in a database and provides detailed inventory management results. The management unit can also provide simplified inventory management results if the user does not have expertise. For example, the management unit adjusts the level of detail of inventory management based on the user's level of expertise. This improves user convenience by adjusting the level of detail of inventory management according to the user's level of expertise. Some or all of the above-described processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of inventory management.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] The reception unit can analyze the user's past photo reception history and select an appropriate reception method. For example, it can prioritize and suggest reception methods that the user has frequently used in the past. For example, the reception unit can store the user's past photo reception history in a database and analyze the reception methods that the user has frequently used. The reception unit can also suggest the reception method that is optimal for a specific time period based on the user's past reception history. For example, the reception unit can analyze the user's past reception history in chronological order to identify the reception method that is optimal for a specific time period. The reception unit can also customize the optimal reception method based on the user's past feedback. For example, the reception unit can analyze feedback provided by the user in the past and optimize the reception method. This improves user convenience by selecting the optimal reception method based on the user's past history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's past photo reception history data into a generation AI and have the generation AI select the optimal reception method.

[0081] The calculation unit can apply different calculation algorithms based on the weight and size of the product during calculation. For example, if the product is lightweight, it applies a calculation algorithm designed specifically for lightweight products. For example, the calculation unit measures the weight of the product and calculates the shipping fee for lightweight products. Furthermore, if the product is large, it can apply a calculation algorithm designed specifically for large products. For example, the calculation unit measures the size of the product and calculates the shipping fee for large items. Furthermore, if the product is medium-sized, it can apply a calculation algorithm designed specifically for medium-sized items. For example, the calculation unit measures the weight and size of the product and calculates the shipping fee for medium-sized items. This improves the accuracy of calculating shipping fees by applying different calculation algorithms based on the weight and size of the product. Some or all of the above-described processing in the calculation unit may be performed using, or without, AI. For example, the calculation unit can input product weight and size data into the generation AI and cause the generation AI to apply the calculation algorithm.

[0082] When making a selection, the selection unit can apply different selection algorithms based on sales data of the flea market sites. For example, it applies an algorithm that prioritizes the selection of flea market sites with high sales. For example, the selection unit stores sales data of flea market sites in a database and identifies flea market sites with high sales. The selection unit can also apply an algorithm that postpones flea market sites with low sales. For example, the selection unit applies an algorithm that selects the optimal flea market site based on the sales data of the flea market sites. This improves the accuracy of selecting the optimal flea market site by applying different selection algorithms based on the sales data of the flea market sites. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data of flea market sites into the generation AI and cause the generation AI to apply the selection algorithm.

[0083] When receiving photos, the reception unit may filter them based on the user's current projects and areas of interest. For example, photos related to the user's ongoing projects may be preferentially received. For example, the reception unit may store the user's project information in a database and identify related photos. The reception unit may also filter and receive related photos based on the user's areas of interest. For example, the reception unit may acquire the user's areas of interest from profile information and identify related photos. The reception unit may also preferentially receive related photos by referring to the user's past project history. For example, the reception unit may analyze the user's past project history and identify related photos. In this way, by filtering based on the user's projects and areas of interest, highly relevant photos can be preferentially received. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's project information and area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0084] During measurement, the measurement unit can apply different measurement algorithms based on the shape and material of the product. For example, if the product is circular, it applies a measurement algorithm specifically for circular products. For example, the measurement unit detects the outline of the product and measures the diameter of the circular product. Furthermore, if the product is made of metal, the measurement unit can also apply a measurement algorithm specifically for metal. For example, the measurement unit performs measurements taking into account the reflective characteristics of metal products. Furthermore, if the product is made of cloth, the measurement unit can also apply a measurement algorithm specifically for cloth. For example, the measurement unit performs measurements taking into account the flexibility of cloth products. This improves measurement accuracy by applying different measurement algorithms based on the shape and material of the product. Some or all of the above-described processing in the measurement unit may be performed using, or without, AI. For example, the measurement unit can input product shape and material data into the generation AI and cause the generation AI to apply the measurement algorithm.

[0085] When providing advice, the advice unit can apply different advice algorithms based on market data for the product. For example, if the product is expensive, it applies an advice algorithm dedicated to high-priced products. For example, the advice unit stores the market data for the product in a database and applies an advice algorithm dedicated to high-priced products. In addition, if the product is low-priced, the advice unit can apply an advice algorithm dedicated to low-priced products. For example, the advice unit advises an appropriate price for low-priced products based on the market data for the product. In addition, if the product is medium-priced, the advice unit can apply an advice algorithm dedicated to medium-priced products. For example, the advice unit advises an appropriate price for medium-priced products based on the market data for the product. In this way, by applying different advice algorithms based on the market data for the product, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data for the product into a generation AI and cause the generation AI to apply an advice algorithm.

[0086] The processing flow of the first embodiment will be briefly explained below.

[0087] Step 1: The reception unit receives product photos from the user. Product photos from the user may include, but are not limited to, images in JPEG or PNG format, resolution, and shooting conditions. The reception unit, for example, uploads product photos taken by the user to the app. The reception unit can also automatically adjust the resolution and shooting conditions of the photos. For example, the reception unit converts low-resolution photos to high-resolution photos and adjusts the brightness and contrast appropriately. Step 2: The measurement unit uses the generation AI to measure the product size based on the photo received by the reception unit. The measurement unit measures the height, width, and depth of the product using, for example, image analysis technology. For example, the measurement unit detects the outline of the product and measures the length of each side. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit applies a measurement algorithm specifically for circular products to circular products. Step 3: The calculation unit calculates the shipping fee based on the product size measured by the measurement unit. The calculation unit calculates the shipping fee based on, for example, the weight and size of the product and the delivery destination. For example, the calculation unit measures the weight of the product and calculates the shipping fee based on the distance to the delivery destination. The calculation unit can also improve the accuracy of the calculation by referring to the user's past shipping fee data. For example, the calculation unit improves the accuracy of the calculation based on data on shipping fees paid by the user in the past. Step 4: The creation unit uses the generation AI to create a product introduction text based on the shipping fee calculated by the calculation unit. The creation unit generates text that includes, for example, the product's features, condition, and usability. For example, the creation unit analyzes a photo of the product and extracts the product's features to create the text. The creation unit can also apply different text generation methods depending on the product category. For example, in the case of an electronic device, the creation unit applies a text generation method specifically for electronic devices. Step 5: The advice unit uses the generation AI to advise on an appropriate price based on the product description text created by the creation unit. The advice unit advises on an appropriate price based on market data, for example. For example, the advice unit analyzes the prices at which similar products are traded and suggests an appropriate price. The advice unit can also improve the accuracy of its advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of its advice based on price data set by the user in the past. Step 6: The selection unit selects the optimal flea market site based on the appropriate price advised by the advice unit. The selection unit selects the optimal site, for example, taking into consideration sales and fees on a specific flea market site. For example, the selection unit preferentially selects flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items the user has listed in the past. Step 7: The management unit manages the simultaneous listing of multiple products based on the flea market site selected by the selection unit. The management unit, for example, manages inventory, tracks sales, and tally sales. For example, the management unit sets the inventory tracking method, inventory update frequency, inventory evaluation criteria, etc., and manages inventory. The management unit also sets the sales data collection method, sales evaluation criteria, etc., and tracks sales. Furthermore, the management unit sets the sales data collection method, aggregation frequency, aggregation evaluation criteria, etc., and tally sales.

[0088] (Example 2) The app of an embodiment of the present invention is a system that allows users to simply take a photo of an item they want to sell using a predetermined procedure. The app measures the item's size, calculates shipping fees, creates a product description, recommends appropriate pricing, selects the optimal flea market site, and manages the simultaneous listing of multiple items. It also helps organize unwanted items and suggests bundled sales and bartering. For example, a user takes a photo of the item they want to sell using a predetermined procedure. The photo is then input into a generation AI. The generation AI automatically measures the item's size from the photo and calculates shipping fees. For example, it measures the item's height, width, and depth and calculates shipping fees based on that information. Next, the generation AI automatically creates a product description. For example, it generates a description that includes the item's features, condition, and usage. This allows users to easily create an attractive product description. Furthermore, the generation AI advises on the appropriate price for the item. It uses market data to analyze the prices at which similar items are traded and suggests an appropriate price. This allows users to set an appropriate price. The generation AI also suggests which flea market site to list the item on for the most efficient results. For example, the app selects the optimal site based on sales trends and fees on a specific flea market site. It also manages sales when listing multiple items simultaneously. For example, it can centrally manage inventory, sales tracking, and sales tallying. This app also helps users organize unwanted items. For example, it offers suggestions for bundle sales and bartering, helping users efficiently dispose of unwanted items. The generative AI analyzes the items the user owns and suggests bundle sales and bartering. This allows the app to measure the items, calculate shipping fees, create product descriptions, advise on appropriate prices, select the optimal flea market site, manage the simultaneous listing of multiple items, organize unwanted items, and suggest bundle sales and bartering, all in one go. For example, users can quickly and accurately take photos of the items they want to sell, and the app automatically processes the information, significantly reducing the user's effort. It also allows users to efficiently dispose of unwanted items and sell them at the right price.

[0089] A sales support system according to an embodiment includes a reception unit, a measurement unit, a calculation unit, a creation unit, an advice unit, a selection unit, and a management unit. The reception unit receives product photos from a user. Product photos from a user may include, but are not limited to, images in JPEG or PNG format, resolution, and shooting conditions. The reception unit, for example, uploads product photos taken by the user to an app. The reception unit can also automatically adjust the resolution and shooting conditions of the photos. For example, the reception unit converts low-resolution photos to high-resolution and adjusts the brightness and contrast appropriately. The measurement unit uses generative AI to measure the product size based on the photos received by the reception unit. The measurement unit can measure the height, width, and depth of the product using image analysis technology. For example, the measurement unit detects the outline of the product and measures the length of each side. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit applies a measurement algorithm specifically for circular products to circular products. The calculation unit calculates the shipping fee based on the product size measured by the measurement unit. The calculation unit calculates the shipping fee based on, for example, the weight and size of the product and the delivery destination. For example, the calculation unit measures the weight of the product and calculates the shipping fee based on the distance to the delivery destination. The calculation unit can also improve the accuracy of the calculation by referring to the user's past shipping fee data. For example, the calculation unit improves the accuracy of the calculation based on data on shipping fees paid by the user in the past. The creation unit uses a generation AI to create a product description text based on the shipping fee calculated by the calculation unit. The creation unit generates a text that includes, for example, the product's features, condition, and usability. For example, the creation unit analyzes a photo of the product and extracts the product's features to generate a text. The creation unit can also apply different text generation methods depending on the product category. For example, in the case of an electronic device, the creation unit applies a text generation method specifically for electronic devices. The advice unit uses a generation AI to advise on an appropriate price based on the product description text created by the creation unit. The advice unit advises on an appropriate price based on, for example, market data. For example, the advice unit analyzes the trading prices of similar products and suggests an appropriate price.The advice unit can also improve the accuracy of the advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of the advice based on price data previously set by the user. The selection unit selects the optimal flea market site based on the appropriate price advised by the advice unit. The selection unit selects the optimal site by taking into account, for example, sales and fees on a specific flea market site. For example, the selection unit preferentially selects flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items previously listed by the user. The management unit manages the simultaneous listing of multiple items based on the flea market site selected by the selection unit. The management unit, for example, manages inventory, tracks sales, and tally sales. For example, the management unit sets an inventory tracking method, inventory update frequency, inventory evaluation criteria, etc., and performs inventory management. The management unit also sets a sales data collection method, sales evaluation criteria, etc., and tracks sales. Furthermore, the management unit sets the sales data collection method, aggregation frequency, aggregation evaluation criteria, etc., and aggregates the sales data. As a result, the sales support system according to the embodiment can measure the product size, calculate the shipping fee, create a product description, advise on the appropriate price, select the most suitable flea market site, and manage the simultaneous listing of multiple products all at once, simply by the user taking a photo of the product.

[0090] The management unit can manage inventory, track sales, and tally sales. The management unit manages inventory by, for example, setting an inventory tracking method, inventory update frequency, and inventory evaluation criteria. For example, the management unit periodically checks inventory quantities and issues an alert when inventory falls below a certain level. The management unit also tracks sales by setting a sales data collection method and sales evaluation criteria. For example, the management unit records the sales volume and sales speed of each product and identifies high-selling and low-selling products. The management unit also sets a sales data collection method, aggregation frequency, and aggregation evaluation criteria, and tally sales. For example, the management unit aggregates sales data daily, weekly, and monthly and analyzes sales trends. This enables inventory management, sales tracking, and sales aggregation. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without AI. For example, the management department can input inventory data and sales data into the generation AI and have the generation AI perform inventory management, sales tracking, and sales aggregation.

[0091] The management unit can organize unnecessary items. For example, the management unit creates a list of products owned by the user and identifies unnecessary items. For example, the management unit evaluates the frequency of use and condition of products owned by the user and lists unnecessary items. The management unit can also suggest methods for disposing of unnecessary items. For example, the management unit suggests disposal methods such as recycling, donation, and disposal. The management unit can also create a schedule for efficiently organizing unnecessary items. For example, the management unit sets a date for organizing unnecessary items according to the user's convenience. This makes it possible to organize unnecessary items. Some or all of the above-mentioned processing in the management unit may be performed using, or without, AI. For example, the management unit can input a list of products owned by the user into a generation AI and have the generation AI identify unnecessary items and suggest disposal methods.

[0092] The management unit can propose set sales. For example, the management unit selects products suitable for set sales from among the products owned by the user. For example, the management unit proposes set sales by combining highly related products. The management unit can also set prices for set sales. For example, the management unit compares the prices of individual sales with the prices of set sales and proposes the optimal price to the user. The management unit can also propose promotion methods for set sales. For example, the management unit plans advertisements and campaigns for set sales and proposes them to the user. This makes it possible to propose set sales. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input data on products owned by the user into a generation AI and have the generation AI execute set sales proposals, pricing, and promotion methods.

[0093] The management unit can make barter proposals. For example, the management unit selects products suitable for bartering from among the products owned by the user. For example, the management unit matches products that the user no longer needs with products offered by other users. The management unit can also set the conditions for the barter. For example, the management unit evaluates the value and condition of the products to be exchanged and proposes fair exchange conditions. The management unit can also manage the barter process. For example, the management unit adjusts the schedule for shipping and receiving the products to be exchanged and notifies the user. This makes it possible to propose bartering. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input data on products owned by the user into the generation AI and have the generation AI perform barter proposals, set conditions, and manage the process.

[0094] The measurement unit can measure the height, width, and depth of a product using image analysis technology. For example, the measurement unit can detect the outline of a product using image analysis technology and measure the length of each side. For example, the measurement unit can automatically measure the height, width, and depth of a product. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit can apply a measurement algorithm specifically for circular products to circular products. The measurement unit can also improve the accuracy of the measurement by referring to the user's past measurement results. For example, the measurement unit can improve the accuracy of the measurement based on the user's past measurement results. This makes it possible to accurately measure the size of a product using image analysis technology. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without AI. For example, the measurement unit can input image data of a product into a generation AI and have the generation AI measure the size of the product.

[0095] The advice unit can advise a fair price based on market data. For example, the advice unit analyzes the prices at which similar products are traded based on market data and proposes a fair price. For example, the advice unit sets a price taking into consideration the condition of the product and supply and demand. The advice unit can also improve the accuracy of its advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of its advice based on price data previously set by the user. This enables appropriate pricing by advising a fair price based on market data. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data into a generation AI and have the generation AI execute advice on a fair price.

[0096] The selection unit can select an appropriate site by taking into consideration sales and fees on a specific flea market site. The selection unit, for example, selects the optimal site based on sales data and fees on the specific flea market site. For example, the selection unit prioritizes selecting flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items the user has previously listed. This enables efficient listing by selecting the optimal site by taking into consideration sales and fees on the specific flea market site. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data and fee data on flea market sites into the generation AI and cause the generation AI to select the optimal flea market site.

[0097] The reception unit can estimate the user's emotions and adjust the timing of photo acceptance based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit encourages the user to accept photos at a time when the user can relax. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is in a hurry, the reception unit can provide a simplified procedure for quickly accepting photos. For example, the reception unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is enjoying themselves, the reception unit can provide an interface that allows the user to enjoy taking photos. For example, the reception unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This adjusts the timing of photo acceptance according to the user's emotions, thereby reducing the user's stress. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate the user's emotions.

[0098] The reception unit can analyze the user's past photo reception history and select an appropriate reception method. For example, the reception unit prioritizes and suggests reception methods that the user has frequently used in the past. For example, the reception unit stores the user's past photo reception history in a database and analyzes frequently used reception methods. The reception unit can also suggest the optimal reception method for a specific time period based on the user's past reception history. For example, the reception unit chronologically analyzes the user's past reception history to identify the optimal reception method for a specific time period. The reception unit can also customize the optimal reception method based on the user's past feedback. For example, the reception unit analyzes feedback provided by the user in the past and optimizes the reception method. This improves user convenience by selecting the optimal reception method based on the user's past history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's past photo reception history data into a generation AI and have the generation AI select the optimal reception method.

[0099] When receiving photos, the reception unit may filter them based on the user's current projects and areas of interest. For example, the reception unit may preferentially receive photos related to projects currently underway by the user. For example, the reception unit may store the user's project information in a database and identify related photos. The reception unit may also filter and receive related photos based on the user's areas of interest. For example, the reception unit may acquire the user's areas of interest from profile information and identify related photos. The reception unit may also preferentially receive related photos by referring to the user's past project history. For example, the reception unit may analyze the user's past project history and identify related photos. In this way, by filtering based on the user's projects and areas of interest, highly relevant photos can be preferentially received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's project information and area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0100] When accepting a photo, the acceptance unit can select an appropriate acceptance means depending on the user's input method. For example, if the user uses voice input, the acceptance unit accepts the photo using voice recognition technology. For example, the acceptance unit records the user's voice with a microphone and converts it into text data using voice recognition technology. Furthermore, if the user uses text input, the acceptance unit can also accept the photo using text analysis technology. For example, the acceptance unit analyzes the text entered by the user and processes the photo. Furthermore, if the user uses image input, the acceptance unit can also accept the photo using image analysis technology. For example, the acceptance unit analyzes images uploaded by the user and processes the photo. This improves user convenience by selecting the optimal acceptance means depending on the user's input method. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without AI. For example, the acceptance unit can input the user's voice data, text data, and image data into a generation AI and have the generation AI select the optimal acceptance means.

[0101] The reception unit can estimate the user's emotions and determine the priority of photos to be received based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit postpones photos of lower importance. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the reception unit can prioritize photos of higher importance. For example, the reception unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the reception unit can prioritize photos that require quick processing. For example, the reception unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the emotion using an emotion estimation algorithm. This reduces the user's stress by prioritizing photos according to the user's emotions. Emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate the user's emotions.

[0102] When accepting photos, the reception unit can prioritize accepting highly relevant photos by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes accepting photos related to that area. For example, the reception unit acquires the user's geographical location information from GPS data and identifies relevant photos. The reception unit can also prioritize accepting photos related to locations close to the user's current location. For example, the reception unit tracks the user's current location in real time and identifies relevant photos in the vicinity. The reception unit can also prioritize accepting highly relevant photos by referring to the user's past location information. For example, the reception unit analyzes the user's past location information and identifies relevant photos. This improves user convenience by prioritizing the acceptance of highly relevant photos by taking into account the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to identify relevant photos.

[0103] The reception unit may analyze the user's social media activity and receive related photos when receiving photos. The reception unit, for example, prioritizes receiving photos shared by the user on social media. For example, the reception unit may link the user's social media accounts and identify shared photos. The reception unit may also analyze the user's social media activity and receive related photos. For example, the reception unit may analyze the user's posts, the number of likes, the number of followers, etc. to identify related photos. The reception unit may also prioritize receiving related photos based on the activity of the user's friends on social media. For example, the reception unit may identify photos shared by the user's friends and receive related photos. This improves user convenience by analyzing the user's social media activity and receiving related photos. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit may input the user's social media data into a generation AI and cause the generation AI to identify related photos.

[0104] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a photo. The reception unit, for example, suggests an optimal reception method based on feedback provided by the user in the past. For example, the reception unit stores the user's past feedback in a database and analyzes it. The reception unit can also analyze the user's past feedback and customize the reception method. For example, the reception unit analyzes the content of the user's feedback and optimizes the reception procedure. The reception unit can also optimize the reception procedure by referring to the user's past feedback. For example, the reception unit simplifies the reception procedure based on the user's feedback. This improves user convenience by customizing the reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into a generation AI and have the generation AI customize the reception method.

[0105] The measurement unit can estimate the user's emotions and adjust the accuracy of the measurement based on the estimated user emotions. For example, when the user is feeling stressed, the measurement unit increases the accuracy of the measurement to provide accurate results. For example, the measurement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, when the user is relaxed, the measurement unit can appropriately adjust the accuracy of the measurement to provide quick results. For example, the measurement unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, when the user is in a hurry, the measurement unit can optimize the accuracy of the measurement to provide quick results. For example, the measurement unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This adjusts the accuracy of the measurement according to the user's emotions, thereby reducing the user's stress. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0106] The measurement unit can apply different measurement algorithms based on the shape and material of the product during measurement. For example, if the product is circular, the measurement unit applies a measurement algorithm specifically for circular products. For example, the measurement unit detects the outline of the product and measures the diameter of the circular product. Furthermore, if the product is made of metal, the measurement unit can apply a measurement algorithm specifically for metal. For example, the measurement unit performs measurements taking into account the reflective characteristics of metal products. Furthermore, if the product is made of cloth, the measurement unit can apply a measurement algorithm specifically for cloth. For example, the measurement unit performs measurements taking into account the flexibility of cloth products. In this way, by applying different measurement algorithms based on the shape and material of the product, the accuracy of the measurement is improved. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product shape and material data into the generation AI and cause the generation AI to apply the measurement algorithm.

[0107] The measurement unit can improve the accuracy of the measurement by referring to the user's past measurement results during measurement. The measurement unit improves the accuracy of the measurement, for example, based on the user's past measurement results. For example, the measurement unit stores the user's past measurement results in a database and analyzes them. The measurement unit can also analyze the user's past measurement history to optimize the accuracy of the measurement. For example, the measurement unit adjusts the measurement algorithm by referring to the user's past measurement data. This improves the reliability of the measurement by improving the accuracy of the measurement by referring to the user's past measurement results. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input the user's past measurement result data into the generation AI and cause the generation AI to improve the accuracy of the measurement.

[0108] The measurement unit can apply different measurement methods depending on the product category during measurement. For example, in the case of an electronic device, the measurement unit applies a measurement method dedicated to the electronic device. For example, the measurement unit accurately measures the external dimensions of the electronic device. Furthermore, in the case of clothing, the measurement unit can also apply a measurement method dedicated to clothing. For example, the measurement unit accurately measures the size and shape of the clothing. Furthermore, in the case of furniture, the measurement unit can also apply a measurement method dedicated to furniture. For example, the measurement unit accurately measures the dimensions and shape of the furniture. In this way, by applying different measurement methods depending on the product category, the accuracy of the measurement is improved. Some or all of the above-mentioned processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product category data into the generation AI and cause the generation AI to apply the measurement method.

[0109] The measurement unit can estimate the user's emotions and determine the priority of measurements based on the estimated user emotions. For example, if the user is feeling stressed, the measurement unit postpones measurements of lower importance. For example, the measurement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the measurement unit can prioritize measurements of higher importance. For example, the measurement unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the measurement unit can prioritize measurements that require rapid processing. For example, the measurement unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. Thus, by determining the priority of measurements according to the user's emotions, the user's stress is reduced. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0110] The measurement unit can determine the priority of measurements based on the submission time of the products during measurement. For example, the measurement unit prioritizes measurements of products with upcoming submission deadlines. For example, the measurement unit stores the submission deadlines of products in a database and identifies products with upcoming submission deadlines. The measurement unit can also postpone measurements of products with distant submission deadlines. For example, the measurement unit optimizes the measurement schedule based on the submission deadlines. This enables efficient measurements by determining the priority of measurements based on the submission time of products. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product submission time data into the generation AI and have the generation AI determine the measurement priority.

[0111] The measurement unit can adjust the order of measurements based on the relevance of products during measurement. The measurement unit, for example, prioritizes measurement of highly related products. For example, the measurement unit stores the relevance of products in a database and identifies highly related products. The measurement unit can also postpone measurement of less related products. For example, the measurement unit optimizes the order of measurements based on the relevance of products. This enables efficient measurement by adjusting the order of measurements based on the relevance of products. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit can input product relevance data into a generation AI and cause the generation AI to adjust the order of measurements.

[0112] The measurement unit can adjust the level of detail of the measurement according to the user's level of expertise during measurement. For example, if the user has expertise, the measurement unit provides detailed measurement results. For example, the measurement unit stores the user's level of expertise in a database and provides detailed measurement results. The measurement unit can also provide simplified measurement results if the user does not have expertise. For example, the measurement unit adjusts the level of detail of the measurement based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the measurement according to the user's level of expertise. Some or all of the above-mentioned processing in the measurement unit may be performed using AI, for example, or may be performed without using AI. For example, the measurement unit can input the user's expertise level data to the generation AI and cause the generation AI to adjust the level of detail of the measurement.

[0113] The calculation unit can estimate the user's emotions and adjust the delivery fee calculation method based on the estimated user emotions. For example, if the user is feeling stressed, the calculation unit provides a simplified delivery fee calculation method. For example, the calculation unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. The calculation unit can also provide a detailed delivery fee calculation method if the user is relaxed. For example, the calculation unit records the user's voice and estimates the user's emotions using voice analysis technology. The calculation unit can also provide a method for quickly calculating the delivery fee if the user is in a hurry. For example, the calculation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This adjusts the delivery fee calculation method according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate emotions.

[0114] The calculation unit can apply different calculation algorithms based on the weight and size of the product during calculation. For example, if the product is lightweight, the calculation unit applies a calculation algorithm designed specifically for lightweight products. For example, the calculation unit measures the weight of the product and calculates the shipping fee for lightweight products. Furthermore, if the product is large, the calculation unit can also apply a calculation algorithm designed specifically for large products. For example, the calculation unit measures the size of the product and calculates the shipping fee for large items. Furthermore, if the product is medium-sized, the calculation unit can also apply a calculation algorithm designed specifically for medium-sized items. For example, the calculation unit measures the weight and size of the product and calculates the shipping fee for medium-sized items. This improves the accuracy of calculating shipping fees by applying different calculation algorithms based on the weight and size of the product. Some or all of the above-described processing in the calculation unit may be performed using, or without, AI. For example, the calculation unit can input product weight and size data into the generation AI and cause the generation AI to apply the calculation algorithm.

[0115] The calculation unit can improve the accuracy of the calculation by referring to the user's past shipping fee data during calculation. The calculation unit improves the accuracy of the calculation, for example, based on data on shipping fees paid by the user in the past. For example, the calculation unit stores the user's past shipping fee data in a database and analyzes it. The calculation unit can also analyze the user's past shipping fee history to optimize the calculation accuracy. For example, the calculation unit adjusts the calculation algorithm by referring to the user's past shipping fee data. This improves the reliability of the shipping fee by improving the calculation accuracy by referring to the user's past shipping fee data. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the user's past shipping fee data into the generation AI and cause the generation AI to improve the calculation accuracy.

[0116] The calculation unit can apply different calculation methods depending on the delivery destination of the product when calculating. For example, in the case of domestic delivery, the calculation unit applies a calculation method dedicated to domestic delivery. For example, if the delivery destination of the product is domestic, the calculation unit calculates the domestic delivery fee. In addition, the calculation unit can also apply a calculation method dedicated to international delivery in the case of international delivery. For example, if the delivery destination of the product is international, the calculation unit calculates the international delivery fee. In addition, in the case of delivery to a specific region, the calculation unit can apply a calculation method dedicated to that region. For example, if the delivery destination of the product is a specific region, the calculation unit calculates the delivery fee for that region. In this way, by applying different calculation methods depending on the delivery destination of the product, the accuracy of calculating the delivery fee is improved. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product delivery destination data into a generation AI and cause the generation AI to apply the calculation method.

[0117] The calculation unit can estimate the user's emotions and determine the priority of delivery fees based on the estimated user emotions. For example, if the user is feeling stressed, the calculation unit postpones the calculation of less important delivery fees. For example, the calculation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the calculation unit can prioritize the calculation of more important delivery fees. For example, the calculation unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the calculation unit can prioritize the calculation of delivery fees that require quick processing. For example, the calculation unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This reduces the user's stress by determining the priority of delivery fees according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate emotions.

[0118] During calculation, the calculation unit can determine the priority of shipping fees based on the submission time of the product. The calculation unit, for example, prioritizes the calculation of shipping fees for products with upcoming submission deadlines. For example, the calculation unit stores the product submission deadlines in a database and identifies products with upcoming submission deadlines. The calculation unit can also postpone the calculation of shipping fees for products with distant submission deadlines. For example, the calculation unit optimizes the shipping fee calculation schedule based on the submission deadlines. This enables efficient calculation of shipping fees by determining the priority of shipping fees based on the submission time of the product. Some or all of the above-described processing by the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product submission time data into a generation AI and have the generation AI determine the priority of shipping fees.

[0119] The calculation unit can adjust the order of shipping fees based on the relevance of products during calculation. The calculation unit, for example, prioritizes the calculation of shipping fees for highly related products. For example, the calculation unit stores the relevance of products in a database and identifies highly related products. The calculation unit can also postpone the calculation of shipping fees for less related products. For example, the calculation unit optimizes the order of calculation of shipping fees based on the relevance of products. This enables efficient calculation of shipping fees by adjusting the order of shipping fees based on the relevance of products. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input product relevance data into a generation AI and have the generation AI adjust the order of shipping fees.

[0120] The calculation unit can adjust the level of detail of the shipping fee according to the user's level of expertise during calculation. For example, if the user has expertise, the calculation unit provides a detailed calculation result of the shipping fee. For example, the calculation unit stores the user's level of expertise in a database and provides a detailed calculation result of the shipping fee. The calculation unit can also provide a simplified calculation result of the shipping fee if the user does not have expertise. For example, the calculation unit adjusts the level of detail of the shipping fee based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the shipping fee according to the user's level of expertise. Some or all of the above-mentioned processing in the calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calculation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the shipping fee.

[0121] The creation unit can estimate the user's emotions and adjust the expression of the product description text based on the estimated user emotions. For example, if the user is feeling stressed, the creation unit provides a simple and easy-to-understand expression. For example, the creation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the creation unit can provide a detailed and attractive expression. For example, the creation unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the creation unit can provide a concise expression that focuses on the main points. For example, the creation unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This adjusts the expression of the product description text according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0122] The creation unit can apply different sentence generation algorithms based on the characteristics and condition of the product during creation. For example, if the product is new, the creation unit applies a sentence generation algorithm specifically for new products. For example, the creation unit stores the product's condition in a database and applies a sentence generation algorithm specifically for new products. Furthermore, if the product is used, the creation unit can also apply a sentence generation algorithm specifically for used products. For example, the creation unit generates sentences taking into account the product's usage and condition. Furthermore, if the product is an antique, the creation unit can apply a sentence generation algorithm specifically for antiques. For example, the creation unit generates sentences taking into account the product's history and value. In this way, by applying different sentence generation algorithms based on the product's characteristics and condition, the accuracy of the product introduction sentences is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input product feature and condition data into the generation AI and cause the generation AI to apply a sentence generation algorithm.

[0123] The creation unit can improve the accuracy of the text by referring to the user's past introductory texts when creating the text. The creation unit, for example, improves the accuracy of the text based on introductory texts created by the user in the past. For example, the creation unit stores the user's past introductory texts in a database and analyzes them. The creation unit can also analyze the user's past introductory texts and optimize the text generation algorithm. For example, the creation unit adjusts the way the text is expressed by referring to the user's past introductory texts. This improves the accuracy of the text by referring to the user's past introductory texts, thereby improving the reliability of the product introductory text. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the user's past introductory text data into a generation AI and cause the generation AI to improve the accuracy of the text.

[0124] The creation unit can apply different sentence generation methods depending on the product category during creation. For example, in the case of electronic devices, the creation unit applies a sentence generation method dedicated to electronic devices. For example, the creation unit generates sentences taking into account the features and specifications of the electronic devices. In addition, the creation unit can also apply a sentence generation method dedicated to clothing in the case of clothing. For example, the creation unit generates sentences taking into account the size and material of the clothing. In addition, the creation unit can also apply a sentence generation method dedicated to furniture in the case of furniture. For example, the creation unit generates sentences taking into account the design and function of the furniture. In this way, by applying different sentence generation methods depending on the product category, the accuracy of the product introduction sentences is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input product category data into the generation AI and cause the generation AI to apply the sentence generation method.

[0125] The creation unit can estimate the user's emotions and adjust the length of the product description text based on the estimated user emotions. For example, if the user is feeling stressed, the creation unit can provide short, concise text to the point. For example, the creation unit can capture the user's facial expression with a camera and estimate the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the creation unit can provide longer text with detailed explanations. For example, the creation unit can record the user's voice and estimate the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the creation unit can provide concise, quickly readable text. For example, the creation unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's emotions using an emotion estimation algorithm. This reduces the user's stress by adjusting the length of the product description text according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0126] The creation unit can determine the priority of texts based on the submission time of the product when they are created. For example, the creation unit prioritizes the creation of introduction texts for products with upcoming submission deadlines. For example, the creation unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The creation unit can also postpone introduction texts for products with distant submission deadlines. For example, the creation unit optimizes the schedule for creating texts based on the submission deadlines. This enables efficient text creation by determining the priority of texts based on the submission time of the product. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input product submission time data into a generation AI and have the generation AI determine the priority of texts.

[0127] The creation unit can adjust the order of sentences based on the relevance of the products when creating them. The creation unit, for example, prioritizes creating introduction sentences for highly relevant products. For example, the creation unit stores product relevance in a database and identifies highly relevant products. The creation unit can also postpone introduction sentences for less relevant products. For example, the creation unit optimizes the order of sentence creation based on product relevance. This enables efficient sentence creation by adjusting the order of sentences based on product relevance. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input product relevance data into a generation AI and have the generation AI adjust the order of sentences.

[0128] The creation unit can adjust the use of technical terms in the sentences during creation according to the user's level of expertise. For example, if the user has technical expertise, the creation unit provides sentences that use a lot of technical terms. For example, the creation unit stores the user's level of expertise in a database and provides sentences that use a lot of technical terms. The creation unit can also provide simplified sentences if the user does not have technical expertise. For example, the creation unit adjusts the use of technical terms in the sentences based on the user's level of expertise. This improves user convenience by adjusting the use of technical terms in the sentences according to the user's level of expertise. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the user's level of expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the sentences.

[0129] The advice unit can estimate the user's emotions and adjust the method of advising the user on the appropriate price based on the estimated user emotions. For example, if the user is feeling stressed, the advice unit can provide a simplified method of advising the user on the appropriate price. For example, the advice unit can capture the user's facial expression with a camera and estimate the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the advice unit can provide a detailed method of advising the user on the appropriate price. For example, the advice unit can record the user's voice and estimate the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the advice unit can provide a method of quickly advising the user on the appropriate price. For example, the advice unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's emotions using an emotion estimation algorithm. This adjusts the method of advising the user on the appropriate price according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0130] When providing advice, the advice unit can apply different advice algorithms based on market data for the product. For example, if the product is expensive, the advice unit applies an advice algorithm dedicated to high-priced products. For example, the advice unit stores market data for the product in a database and applies an advice algorithm dedicated to high-priced products. Furthermore, if the product is low-priced, the advice unit can also apply an advice algorithm dedicated to low-priced products. For example, the advice unit advises an appropriate price for low-priced products based on the market data for the product. Furthermore, if the product is medium-priced, the advice unit can also apply an advice algorithm dedicated to medium-priced products. For example, the advice unit advises an appropriate price for medium-priced products based on the market data for the product. In this way, by applying different advice algorithms based on the market data for the product, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data for the product into a generation AI and cause the generation AI to apply an advice algorithm.

[0131] When providing advice, the advice unit can improve the accuracy of the advice by referring to the user's past pricing data. The advice unit improves the accuracy of the advice, for example, based on price data previously set by the user. For example, the advice unit stores the user's past pricing data in a database and analyzes it. The advice unit can also analyze the user's past pricing history to optimize the accuracy of the advice. For example, the advice unit adjusts the advice algorithm by referring to the user's past pricing data. This improves the accuracy of the advice by referring to the user's past pricing data, thereby improving the reliability of the fair price. Some or all of the above-mentioned processing in the advice unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice unit can input the user's past pricing data into the generation AI and cause the generation AI to improve the accuracy of the advice.

[0132] When providing advice, the advice unit can apply different advice methods depending on the product category. For example, in the case of electronic devices, the advice unit applies an advice method dedicated to electronic devices. For example, the advice unit advises an appropriate price based on market data for electronic devices. In addition, in the case of clothing, the advice unit can also apply an advice method dedicated to clothing. For example, the advice unit advises an appropriate price based on market data for clothing. In addition, in the case of furniture, the advice unit can also apply an advice method dedicated to furniture. For example, the advice unit advises an appropriate price based on market data for furniture. In this way, by applying different advice methods depending on the product category, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product category data into the generation AI and cause the generation AI to apply the advice method.

[0133] The advice unit can estimate the user's emotions and prioritize fair prices based on the estimated user emotions. For example, if the user is stressed, the advice unit postpones advice on fair prices that are less important. For example, the advice unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the advice unit can prioritize advice on fair prices that are more important. For example, the advice unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the advice unit can prioritize advice on fair prices that require quick processing. For example, the advice unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This prioritizes fair prices according to the user's emotions, thereby reducing the user's stress. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0134] When providing advice, the advice unit can determine the priority of fair prices based on the submission date of the product. The advice unit, for example, prioritizes fair price advice for products with an upcoming submission deadline. For example, the advice unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The advice unit can also postpone fair price advice for products with a distant submission deadline. For example, the advice unit optimizes a fair price advice schedule based on the submission deadline. This enables efficient advice by determining the priority of fair prices based on the submission date of the product. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product submission date data into a generation AI and have the generation AI determine the priority of fair prices.

[0135] The advice unit can adjust the order of fair prices based on the relevance of the products when providing advice. The advice unit, for example, prioritizes fair price advice for highly related products. For example, the advice unit stores product relevance in a database and identifies highly related products. The advice unit can also postpone fair price advice for less related products. For example, the advice unit optimizes the order of fair price advice based on the relevance of the products. This enables efficient advice by adjusting the order of fair prices based on the relevance of the products. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input product relevance data into a generation AI and have the generation AI adjust the order of fair prices.

[0136] When providing advice, the advice unit can adjust the level of detail of the fair price according to the user's level of expertise. For example, if the user has expertise, the advice unit provides detailed advice on the fair price. For example, the advice unit stores the user's level of expertise in a database and provides detailed advice on the fair price. Furthermore, if the user does not have expertise, the advice unit can also provide simplified advice on the fair price. For example, the advice unit adjusts the level of detail of the fair price based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the fair price according to the user's level of expertise. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the fair price.

[0137] The selection unit can estimate the user's emotions and adjust the method for selecting an appropriate flea market site based on the estimated user emotions. For example, if the user is feeling stressed, the selection unit provides a simplified method for selecting a flea market site. For example, the selection unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the selection unit can provide a detailed method for selecting a flea market site. For example, the selection unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the selection unit can provide a method for quickly selecting the optimal flea market site. For example, the selection unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This adjusts the method for selecting the optimal flea market site based on the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate emotions.

[0138] When making a selection, the selection unit can apply different selection algorithms based on sales data of the flea market sites. The selection unit, for example, applies an algorithm that prioritizes the selection of flea market sites with high sales. For example, the selection unit stores sales data of flea market sites in a database and identifies flea market sites with high sales. The selection unit can also apply an algorithm that postpones flea market sites with low sales. For example, the selection unit applies an algorithm that selects the optimal flea market site based on the sales data of the flea market sites. This improves the accuracy of selecting the optimal flea market site by applying different selection algorithms based on the sales data of the flea market sites. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data of flea market sites into the generation AI and cause the generation AI to apply the selection algorithm.

[0139] The selection unit can improve the accuracy of the selection by referring to the user's past listing data when making a selection. The selection unit improves the accuracy of the selection, for example, based on data on items the user has previously listed. For example, the selection unit stores the user's past listing data in a database and analyzes it. The selection unit can also analyze the user's past listing history to optimize the accuracy of the selection. For example, the selection unit adjusts the selection algorithm by referring to the user's past listing data. This improves the accuracy of the selection by referring to the user's past listing data, thereby improving the accuracy of the selection of the optimal flea market site. Some or all of the above-described processing by the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the user's past listing data into the generation AI and cause the generation AI to improve the accuracy of the selection.

[0140] The selection unit can apply different selection methods depending on the product category during selection. For example, in the case of electronic devices, the selection unit applies a selection method dedicated to electronic devices. For example, the selection unit selects the optimal flea market site based on market data for electronic devices. In addition, in the case of clothing, the selection unit can also apply a selection method dedicated to clothing. For example, the selection unit selects the optimal flea market site based on market data for clothing. In addition, in the case of furniture, the selection unit can also apply a selection method dedicated to furniture. For example, the selection unit selects the optimal flea market site based on market data for furniture. In this way, by applying different selection methods depending on the product category, the accuracy of selecting the optimal flea market site is improved. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input product category data into the generation AI and cause the generation AI to apply the selection method.

[0141] The selection unit can estimate the user's emotions and prioritize the optimal flea market sites based on the estimated user emotions. For example, if the user is feeling stressed, the selection unit postpones the selection of less important flea market sites. For example, the selection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the selection unit can prioritize the selection of more important flea market sites. For example, the selection unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the selection unit can prioritize the selection of flea market sites that require quick processing. For example, the selection unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This reduces the user's stress by prioritizing the optimal flea market sites according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, or without, an AI. For example, the selection unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0142] During selection, the selection unit can determine the priority of flea market sites based on the submission time of the products. For example, the selection unit prioritizes the selection of flea market sites for products with upcoming submission deadlines. For example, the selection unit stores the product submission deadlines in a database and identifies products with upcoming submission deadlines. The selection unit can also postpone the selection of flea market sites for products with distant submission deadlines. For example, the selection unit optimizes the flea market site selection schedule based on the submission deadlines. This enables efficient selection by determining the priority of flea market sites based on the submission time of the products. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit can input product submission time data into a generation AI and have the generation AI determine the priority of flea market sites.

[0143] The selection unit can adjust the order of flea market sites based on the relevance of the products during selection. The selection unit, for example, prioritizes the selection of flea market sites for highly relevant products. For example, the selection unit stores the relevance of the products in a database and identifies highly relevant products. The selection unit can also postpone the selection of flea market sites for less relevant products. For example, the selection unit optimizes the selection order of flea market sites based on the relevance of the products. This enables efficient selection by adjusting the order of flea market sites based on the relevance of the products. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input product relevance data into a generation AI and cause the generation AI to adjust the order of the flea market sites.

[0144] The selection unit can adjust the level of detail of the flea market site during selection according to the user's level of expertise. For example, if the user has expertise, the selection unit provides a detailed selection result of the flea market site. For example, the selection unit stores the user's level of expertise in a database and provides a detailed selection result of the flea market site. The selection unit can also provide a simplified selection result of the flea market site if the user does not have expertise. For example, the selection unit adjusts the level of detail of the flea market site based on the user's level of expertise. This improves user convenience by adjusting the level of detail of the flea market site according to the user's level of expertise. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of the flea market site.

[0145] The management unit can estimate the user's emotions and adjust the inventory management method based on the estimated user emotions. For example, if the user is feeling stressed, the management unit provides a simplified inventory management method. For example, the management unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the management unit can provide a detailed inventory management method. For example, the management unit records the user's voice and estimates the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the management unit can provide a method for quick inventory management. For example, the management unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This adjusts the inventory management method according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input the user's facial expression data and voice data into the generation AI and have the generation AI estimate the user's emotions.

[0146] During management, the management unit can apply different management algorithms based on product sales status data. For example, the management unit applies an algorithm that prioritizes inventory management of products with good sales status. For example, the management unit stores product sales status data in a database and identifies products with good sales status. The management unit can also apply an algorithm that postpones inventory management of products with poor sales status. For example, the management unit applies an optimal inventory management algorithm based on the product sales status data. In this way, by applying different management algorithms based on the product sales status data, the accuracy of inventory management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product sales status data into a generation AI and have the generation AI apply the management algorithm.

[0147] During management, the management unit can improve the accuracy of management by referring to the user's past sales data. The management unit improves the accuracy of management, for example, based on data of past sales by the user. For example, the management unit stores the user's past sales data in a database and analyzes it. The management unit can also analyze the user's past sales history to optimize the accuracy of management. For example, the management unit adjusts the management algorithm by referring to the user's past sales data. This improves the reliability of inventory management by improving the accuracy of management by referring to the user's past sales data. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI or without AI. For example, the management unit can input the user's past sales data into a generation AI and have the generation AI improve the accuracy of management.

[0148] During management, the management unit can apply different management methods depending on the product category. For example, in the case of electronic devices, the management unit applies a management method dedicated to electronic devices. For example, the management unit applies the optimal management method based on inventory data for the electronic devices. In addition, in the case of clothing, the management unit can also apply a management method dedicated to clothing. For example, the management unit applies the optimal management method based on inventory data for clothing. In addition, in the case of furniture, the management unit can also apply a management method dedicated to furniture. For example, the management unit applies the optimal management method based on inventory data for furniture. In this way, by applying different management methods depending on the product category, the accuracy of inventory management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product category data into a generation AI and have the generation AI apply the management method.

[0149] The management unit can estimate the user's emotions and determine inventory management priorities based on the estimated user emotions. For example, if the user is feeling stressed, the management unit postpones inventory management tasks with lower importance. For example, the management unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the management unit can prioritize inventory management tasks with higher importance. For example, the management unit records the user's voice and estimates their emotions using voice analysis technology. Furthermore, if the user is in a hurry, the management unit can prioritize inventory management tasks that require immediate processing. For example, the management unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates their emotions using an emotion estimation algorithm. This reduces the user's stress by determining inventory management priorities based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input the user's facial expression data and voice data into the generation AI and have the generation AI estimate the user's emotions.

[0150] During management, the management unit can determine inventory management priorities based on the submission dates of products. For example, the management unit prioritizes inventory management of products with upcoming submission deadlines. For example, the management unit stores product submission deadlines in a database and identifies products with upcoming submission deadlines. The management unit can also postpone inventory management of products with distant submission deadlines. For example, the management unit optimizes the inventory management schedule based on the submission deadlines. This enables efficient inventory management by determining inventory management priorities based on the submission dates of products. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product submission date data into a generation AI and have the generation AI determine the inventory management priorities.

[0151] During management, the management unit can adjust the inventory management order based on the relevance of products. The management unit, for example, prioritizes inventory management of highly related products. For example, the management unit stores the relevance of products in a database and identifies highly related products. The management unit can also postpone inventory management of less related products. For example, the management unit optimizes the inventory management order based on the relevance of products. This enables efficient inventory management by adjusting the inventory management order based on the relevance of products. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input product relevance data into a generation AI and have the generation AI adjust the inventory management order.

[0152] During management, the management unit can adjust the level of detail of inventory management according to the user's level of expertise. For example, if the user has expertise, the management unit provides detailed inventory management results. For example, the management unit stores the user's level of expertise in a database and provides detailed inventory management results. The management unit can also provide simplified inventory management results if the user does not have expertise. For example, the management unit adjusts the level of detail of inventory management based on the user's level of expertise. This improves user convenience by adjusting the level of detail of inventory management according to the user's level of expertise. Some or all of the above-described processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the level of detail of inventory management. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, measurement unit, calculation unit, creation unit, advice unit, selection unit, and management unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit can receive a user's photo or voice using the camera 42 or microphone 38B of the smart device 14. The measurement unit, realized, for example, by the specific processing unit 290 of the data processing device 12, measures the size of a product. The calculation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates a shipping fee. The creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, creates a product description text. The advice unit, realized, for example, by the specific processing unit 290 of the data processing device 12, advises on an appropriate price. The selection unit, realized, for example, by the specific processing unit 290 of the data processing device 12, selects an optimal flea market site. The management unit, realized, for example, by the specific processing unit 290 of the data processing device 12, manages the simultaneous listing of multiple products. The reception unit estimates the user's emotion using, for example, the camera 42 or the microphone 38B of the smart device 14, and adjusts the timing of receiving the photo based on the estimated emotion. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, measurement unit, calculation unit, creation unit, advice unit, selection unit, and management unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive a user's photo or voice using the camera 42 or microphone 238 of the smart glasses 214. The measurement unit, realized, for example, by the specific processing unit 290 of the data processing device 12, measures the size of a product. The calculation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates a shipping fee. The creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, creates a product description text. The advice unit, realized, for example, by the specific processing unit 290 of the data processing device 12, advises on an appropriate price. The selection unit, realized, for example, by the specific processing unit 290 of the data processing device 12, selects an optimal flea market site. The management unit, realized, for example, by the specific processing unit 290 of the data processing device 12, manages the simultaneous listing of multiple products. The reception unit estimates the user's emotions using, for example, the camera 42 and microphone 238 of the smart glasses 214, and adjusts the timing of receiving the photo based on the estimated emotions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, measurement unit, calculation unit, creation unit, advice unit, selection unit, and management unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit can receive a user's photo or voice using the camera 42 or microphone 238 of the headset-type terminal 314. The measurement unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and measures the size of a product. The calculation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and calculates a shipping fee. The creation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and creates a product description text. The advice unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and advises on an appropriate price. The selection unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and selects an optimal flea market site. The management unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and manages the simultaneous listing of multiple products. The reception unit estimates the user's emotions using, for example, the camera 42 or microphone 238 of the headset terminal 314, and adjusts the timing of receiving the photo based on the estimated emotions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, measurement unit, calculation unit, creation unit, advice unit, selection unit, and management unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive a user's photo or voice using the camera 42 or microphone 238 of the robot 414. The measurement unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and measures the size of the product. The calculation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and calculates the shipping fee. The creation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and creates a product description text. The advice unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and advises the user on an appropriate price. The selection unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and selects the most suitable flea market site. The management unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and manages the simultaneous listing of multiple products. The reception unit estimates the user's emotions using, for example, the camera 42 and microphone 238 of the robot 414, and adjusts the timing of receiving the photo based on the estimated emotions.

[0153] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0154] The reception unit can analyze the user's past photo reception history and select an appropriate reception method. For example, it can prioritize and suggest reception methods that the user has frequently used in the past. For example, the reception unit can store the user's past photo reception history in a database and analyze the reception methods that the user has frequently used. The reception unit can also suggest the reception method that is optimal for a specific time period based on the user's past reception history. For example, the reception unit can analyze the user's past reception history in chronological order to identify the reception method that is optimal for a specific time period. The reception unit can also customize the optimal reception method based on the user's past feedback. For example, the reception unit can analyze feedback provided by the user in the past and optimize the reception method. This improves user convenience by selecting the optimal reception method based on the user's past history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's past photo reception history data into a generation AI and have the generation AI select the optimal reception method.

[0155] The measurement unit can estimate the user's emotions and adjust the accuracy of the measurement based on the estimated user emotions. For example, if the user is feeling stressed, the measurement accuracy can be increased to provide accurate results. For example, the measurement unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the measurement unit can appropriately adjust the measurement accuracy to provide quick results. For example, the measurement unit can record the user's voice and estimate the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the measurement unit can optimize the measurement accuracy to provide quick results. For example, the measurement unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. This adjusts the measurement accuracy according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the measurement unit may be performed using, for example, AI, or may be performed without using AI. For example, the measurement unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0156] The calculation unit can apply different calculation algorithms based on the weight and size of the product during calculation. For example, if the product is lightweight, it applies a calculation algorithm designed specifically for lightweight products. For example, the calculation unit measures the weight of the product and calculates the shipping fee for lightweight products. Furthermore, if the product is large, it can apply a calculation algorithm designed specifically for large products. For example, the calculation unit measures the size of the product and calculates the shipping fee for large items. Furthermore, if the product is medium-sized, it can apply a calculation algorithm designed specifically for medium-sized items. For example, the calculation unit measures the weight and size of the product and calculates the shipping fee for medium-sized items. This improves the accuracy of calculating shipping fees by applying different calculation algorithms based on the weight and size of the product. Some or all of the above-described processing in the calculation unit may be performed using, or without, AI. For example, the calculation unit can input product weight and size data into the generation AI and cause the generation AI to apply the calculation algorithm.

[0157] The creation unit can estimate the user's emotions and adjust the way the product description text is presented based on the estimated user emotions. For example, if the user is feeling stressed, the creation unit can provide a simple and easy-to-understand way of expressing the user's emotions. For example, the creation unit can capture the user's facial expressions with a camera and estimate the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the creation unit can provide a detailed and appealing way of expressing the user's emotions. For example, the creation unit can record the user's voice and estimate the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the creation unit can provide a concise way of expressing the user's emotions that focuses on the main points. For example, the creation unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's emotions using an emotion estimation algorithm. This allows the user's stress to be reduced by adjusting the way the product description text is presented based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the user's facial expression data and voice data into the generation AI and cause the generation AI to estimate emotions.

[0158] When making a selection, the selection unit can apply different selection algorithms based on sales data of the flea market sites. For example, it applies an algorithm that prioritizes the selection of flea market sites with high sales. For example, the selection unit stores sales data of flea market sites in a database and identifies flea market sites with high sales. The selection unit can also apply an algorithm that postpones flea market sites with low sales. For example, the selection unit applies an algorithm that selects the optimal flea market site based on the sales data of the flea market sites. This improves the accuracy of selecting the optimal flea market site by applying different selection algorithms based on the sales data of the flea market sites. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input sales data of flea market sites into the generation AI and cause the generation AI to apply the selection algorithm.

[0159] The management unit can estimate the user's emotions and adjust the inventory management method based on the estimated user emotions. For example, if the user is feeling stressed, a simplified inventory management method is provided. For example, the management unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the management unit can provide a detailed inventory management method. For example, the management unit records the user's voice and estimates the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the management unit can provide a method for quick inventory management. For example, the management unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This adjusts the inventory management method according to the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input the user's facial expression data and voice data into the generation AI and have the generation AI estimate the user's emotions.

[0160] When receiving photos, the reception unit may filter them based on the user's current projects and areas of interest. For example, photos related to the user's ongoing projects may be preferentially received. For example, the reception unit may store the user's project information in a database and identify related photos. The reception unit may also filter and receive related photos based on the user's areas of interest. For example, the reception unit may acquire the user's areas of interest from profile information and identify related photos. The reception unit may also preferentially receive related photos by referring to the user's past project history. For example, the reception unit may analyze the user's past project history and identify related photos. In this way, by filtering based on the user's projects and areas of interest, highly relevant photos can be preferentially received. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's project information and area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0161] During measurement, the measurement unit can apply different measurement algorithms based on the shape and material of the product. For example, if the product is circular, it applies a measurement algorithm specifically for circular products. For example, the measurement unit detects the outline of the product and measures the diameter of the circular product. Furthermore, if the product is made of metal, the measurement unit can also apply a measurement algorithm specifically for metal. For example, the measurement unit performs measurements taking into account the reflective characteristics of metal products. Furthermore, if the product is made of cloth, the measurement unit can also apply a measurement algorithm specifically for cloth. For example, the measurement unit performs measurements taking into account the flexibility of cloth products. This improves measurement accuracy by applying different measurement algorithms based on the shape and material of the product. Some or all of the above-described processing in the measurement unit may be performed using, or without, AI. For example, the measurement unit can input product shape and material data into the generation AI and cause the generation AI to apply the measurement algorithm.

[0162] When providing advice, the advice unit can apply different advice algorithms based on market data for the product. For example, if the product is expensive, it applies an advice algorithm dedicated to high-priced products. For example, the advice unit stores the market data for the product in a database and applies an advice algorithm dedicated to high-priced products. In addition, if the product is low-priced, the advice unit can apply an advice algorithm dedicated to low-priced products. For example, the advice unit advises an appropriate price for low-priced products based on the market data for the product. In addition, if the product is medium-priced, the advice unit can apply an advice algorithm dedicated to medium-priced products. For example, the advice unit advises an appropriate price for medium-priced products based on the market data for the product. In this way, by applying different advice algorithms based on the market data for the product, the accuracy of the appropriate price advice is improved. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input market data for the product into a generation AI and cause the generation AI to apply an advice algorithm.

[0163] The selection unit can estimate the user's emotions and adjust the method for selecting an appropriate flea market site based on the estimated user emotions. For example, if the user is feeling stressed, a simplified method for selecting a flea market site is provided. For example, the selection unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the selection unit can provide a detailed method for selecting a flea market site. For example, the selection unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the selection unit can provide a method for quickly selecting the optimal flea market site. For example, the selection unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This adjusts the method for selecting the optimal flea market site based on the user's emotions, thereby reducing the user's stress. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate emotions.

[0164] The processing flow of the second embodiment will be briefly explained below.

[0165] Step 1: The reception unit receives product photos from the user. Product photos from the user may include, but are not limited to, images in JPEG or PNG format, resolution, and shooting conditions. The reception unit, for example, uploads product photos taken by the user to the app. The reception unit can also automatically adjust the resolution and shooting conditions of the photos. For example, the reception unit converts low-resolution photos to high-resolution photos and adjusts the brightness and contrast appropriately. Step 2: The measurement unit uses the generation AI to measure the product size based on the photo received by the reception unit. The measurement unit measures the height, width, and depth of the product using, for example, image analysis technology. For example, the measurement unit detects the outline of the product and measures the length of each side. The measurement unit can also apply different measurement algorithms based on the shape and material of the product. For example, the measurement unit applies a measurement algorithm specifically for circular products to circular products. Step 3: The calculation unit calculates the shipping fee based on the product size measured by the measurement unit. The calculation unit calculates the shipping fee based on, for example, the weight and size of the product and the delivery destination. For example, the calculation unit measures the weight of the product and calculates the shipping fee based on the distance to the delivery destination. The calculation unit can also improve the accuracy of the calculation by referring to the user's past shipping fee data. For example, the calculation unit improves the accuracy of the calculation based on data on shipping fees paid by the user in the past. Step 4: The creation unit uses the generation AI to create a product introduction text based on the shipping fee calculated by the calculation unit. The creation unit generates text that includes, for example, the product's features, condition, and usability. For example, the creation unit analyzes a photo of the product and extracts the product's features to create the text. The creation unit can also apply different text generation methods depending on the product category. For example, in the case of an electronic device, the creation unit applies a text generation method specifically for electronic devices. Step 5: The advice unit uses the generation AI to advise on an appropriate price based on the product description text created by the creation unit. The advice unit advises on an appropriate price based on market data, for example. For example, the advice unit analyzes the prices at which similar products are traded and suggests an appropriate price. The advice unit can also improve the accuracy of its advice by referring to the user's past pricing data. For example, the advice unit improves the accuracy of its advice based on price data set by the user in the past. Step 6: The selection unit selects the optimal flea market site based on the appropriate price advised by the advice unit. The selection unit selects the optimal site, for example, taking into consideration sales and fees on a specific flea market site. For example, the selection unit preferentially selects flea market sites with high sales. The selection unit can also improve the accuracy of the selection by referring to the user's past listing data. For example, the selection unit improves the accuracy of the selection based on data on items the user has listed in the past. Step 7: The management unit manages the simultaneous listing of multiple products based on the flea market site selected by the selection unit. The management unit, for example, manages inventory, tracks sales, and tally sales. For example, the management unit sets the inventory tracking method, inventory update frequency, inventory evaluation criteria, etc., and manages inventory. The management unit also sets the sales data collection method, sales evaluation criteria, etc., and tracks sales. Furthermore, the management unit sets the sales data collection method, aggregation frequency, aggregation evaluation criteria, etc., and tally sales.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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 AI 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0187] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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).

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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 AI 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.

[0200] 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.

[0201] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0202] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0203] 7, a 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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 AI 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.

[0217] 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.

[0218] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0224] 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."

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] [Explanation of symbols]

[0238] 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 reception unit that receives product photos from users; a measuring unit that measures the size of a product based on the photo received by the receiving unit; a calculation unit that calculates a shipping fee based on the product size measured by the measurement unit; a creating unit that creates a product introduction text based on the shipping fee calculated by the calculating unit; an advice unit that advises on an appropriate price based on the product introduction text created by the creation unit; a selection unit that selects an appropriate flea market site based on the appropriate price advised by the advice unit; a management unit that manages simultaneous listing of multiple products based on the flea market site selected by the selection unit; Equipped with A system characterized by:

2. The management unit Manage inventory, track sales, and tally sales 2. The system of claim 1.

3. The management unit Organize unnecessary items 2. The system of claim 1.

4. The management unit Propose a bundle sale 2. The system of claim 1.

5. The management unit Make a barter offer 2. The system of claim 1.

6. The measurement unit Image analysis technology is used to measure the height, width, and depth of products 2. The system of claim 1.

7. The advice unit Advising on fair prices based on market data 2. The system of claim 1.

8. The selection unit Select the appropriate site by taking into consideration sales trends and fees on specific flea market sites.

2. The system of claim 1.

9. The reception unit Estimate the user's emotions and adjust the timing of accepting photos based on the estimated user emotions.

2. The system of claim 1.

10. The reception unit Analyze the user's past photo reception history and select the appropriate reception method 2. The system of claim 1.

Images