Method, program and information processing system for supporting operations related to the operation of electronic commerce sites

Abstract

A method, program, and information processing system for supporting operations related to the operation of an electronic commerce site are provided to reduce the burden of registering information used for listing and searching for products on an EC site. [Solution] When an information processing system (1) receives a proposal request for proposing text (such as sentences or keywords used for listing and searching for products on an e-commerce site) for a single product, the information processing system (1) acquires one or more instruction sentences associated with classification information indicating the classification that applies to the single product, and generates a first prompt that instructs a generation AI to generate text based on the one or more instruction sentences. The information processing system (1) inputs the first prompt to a generation AI system (5), acquires from the generation AI system (5) the text generated in response to the first prompt, and displays it on a customer terminal device (3) as a response to the proposal request.

Description

[Technical Field]

[0001] The present invention relates to a method, a program, and an information processing system for supporting operations related to the operation of an electronic commerce site. [Background technology]

[0002] In recent years, it has become possible to purchase a variety of products using electronic commerce sites (hereinafter referred to as "EC sites"). Although it is possible to create an original EC site system, developing the various functions of an EC site from scratch is a significant burden, so in many cases, the desired EC site is created using an existing platform provided for building EC sites.

[0003] The following patent document describes a web server device that uses a database to generate and manage web pages for virtual stores, etc. In this web server device, a database stores a group of multiple content files consisting of data related to page content, and for each page, the correspondence between the page and the content file and link information with other pages. A template corresponding to the desired page is read from multiple templates prepared for each page type, and an HTML file corresponding to the desired page is generated by rewriting the variables in the template with the content of the content file or links. This makes it extremely easy to configure links between pages and update content, making it possible to manage and operate a web system without specialized knowledge of HTML, etc. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-169716 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to sell products on an e-commerce site, product information must be registered in the site's system. The product information that must be registered includes general information such as the product name, quantity, and price, as well as the product title and description to be displayed on the webpage, text to be set in webpage tags for SEO purposes, and search keywords. Of the product information that must be registered, the information displayed on the e-commerce site and the search information are particularly important elements that attract customers to the e-commerce site and lead them to purchase products, and have a significant impact on sales. This product information is generally registered manually by the business selling the product (or its contractor). Therefore, the task of determining appropriate product information (title, description, keywords, etc.) that will have a positive impact on sales and registering it in the system places a significant burden on businesses.

[0006] The present invention has been made in consideration of the above circumstances, and its purpose is to provide a method, program, and information processing system that supports operations related to the operation of an EC site, thereby reducing the burden of registering information used to list and search for products on the EC site. [Means for solving the problem]

[0007] A first aspect of the present invention is a method in which an information processing system performs processing to support tasks related to the operation of an e-commerce site, the information processing system having access to a storage device, the storage device storing a plurality of instructions each including instructions for causing a generation AI to generate text used to list and / or search for products on the e-commerce site, the text including at least one of one or more words and one or more sentences related to the products, and at least some of the instructions being associated with classification information indicating a predetermined classification of the product, and when a suggestion request to suggest text for a certain product is input, the method includes the steps of: acquiring one or more instructions associated with the classification information indicating a classification that applies to the certain product; generating a first prompt that instructs the generation AI to generate text based on the acquired one or more instructions; inputting the first prompt to the generation AI and acquiring from the generation AI text generated in response to the first prompt; and performing processing to display the acquired text on a display device as a response to the suggestion request.

[0008] A second aspect of the present invention is a program including instructions for causing an information processing system to perform processing that supports operations related to the operation of an e-commerce site, and the processing performed by the information processing system in accordance with the instructions includes each step of the method according to the first aspect.

[0009] A third aspect of the present invention is an information processing system that performs processing to support operations related to the operation of an e-commerce site, and includes a processing unit and a memory unit that stores instructions for causing the processing unit to perform processing, and the processing performed by the processing unit in accordance with the instructions includes each step of the method related to the first aspect above.

[0010] A fourth aspect of the present invention is an information processing system that performs processing to support operations related to the operation of an e-commerce site, and is an information processing system equipped with means for performing each step of the method related to the first aspect above. [Effects of the Invention]

[0011] According to the present invention, a method, a program, and an information processing system can be provided that support operations related to the operation of an e-commerce site, thereby reducing the burden of registering information used for listing and searching for products on an EC site. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a system according to this embodiment. [Figure 2] FIG. 2 is a flowchart illustrating an example of a process for purchasing a product listed on a web page. [Figure 3] FIG. 3 is a flowchart illustrating an example of a process for proposing text related to a product to be used for listing the product on an EC site. [Figure 4] FIG. 4 is a flowchart illustrating an example of a process for acquiring a command statement. [Figure 5] FIG. 5 is a flowchart illustrating another example of the process of acquiring a command statement. [Figure 6] FIG. 6 is a diagram showing an example of a first prompt generated based on an instruction sentence. [Figure 7] Fig. 7A is a diagram showing an example of a screen for registering a product description to be posted on a web page, and Fig. 7B is a diagram showing an example of a screen displaying a product description suggestion generated by a generation AI. [Figure 8] Fig. 8A is a diagram showing an example of a screen for registering a product title, keywords, and description to be set in a tag of a web page, and Fig. 8B is a diagram showing an example of a screen for registering keywords to be used in product searches on an e-commerce site. [Figure 9] FIG. 9 is a diagram showing a modified example of the configuration of the system according to this embodiment. [Figure 10] FIG. 10 is a flowchart illustrating a modified example of the process of proposing text related to a product to be used in listing the product on an EC site. [Figure 11] FIG. 11 is a diagram showing a modified example of the configuration of the system according to this embodiment. [Figure 12] FIG. 12 is a flowchart illustrating a modified example of the process of proposing text related to a product to be used in listing the product on an EC site. [Figure 13] FIG. 13 is a flowchart illustrating an example of a process for revising a reply created in response to an inquiry from a customer. [Figure 14] Fig. 14A is a diagram showing an example of a screen for inputting a reply to an inquiry from a customer, and Fig. 14B is a diagram showing an example of a screen for displaying the revision result of the reply. [Figure 15] FIG. 15 is a flowchart illustrating an example of a process for generating an answer to a question about the content of a business. [Figure 16] FIG. 16 is a diagram showing an example of a screen displaying answers to questions about the content of work. DETAILED DESCRIPTION OF THE INVENTION

[0013] Fig. 1 is a diagram showing an example of the configuration of a system according to this embodiment. The system shown in the example of Fig. 1 includes an information processing system 1 capable of communicating via a communication network 9 such as the Internet, a customer terminal device 3, an administrator terminal device 4, and a generation AI system 5. The information processing system 1 and the administrator terminal device 4 are an example of the information processing system of the present invention.

[0014] 1, the information processing system 1 is a system that performs processing as an e-commerce site, and the customer terminal device 3 is a device operated by customers who purchase products on the e-commerce site. For example, the information processing system 1 performs processing such as generating a web page listing products and displaying it on the customer terminal device 3, accepting product orders from the customer terminal device 3, making payments for the ordered transactions using a predetermined payment method, and arranging for the delivery of the ordered products.

[0015] 1, the administrator terminal device 4 is a device operated by an administrator who operates and manages the EC site implemented in the information processing system 1. For example, the information processing system 1 displays a screen for the administrator (administration screen) on the administrator terminal device 4, receives instructions from the administrator entered on this administration screen from the administrator terminal device 4, and performs processes related to the operation and management of the EC site (such as registering information about products) in accordance with the received instructions from the administrator.

[0016] Furthermore, in this embodiment, the information processing system 1 performs processing to support the operations (operations related to the operation of the EC site) performed by the administrator using the management screen of the administrator terminal device 4. That is, the information processing system 1 uses the generation AI functions of the generation AI system 5 to generate text (product descriptions, titles, product search keywords, etc. to be posted on web pages) used to list and search for products on the EC site, and displays the generated text on the administrator terminal device 4 to suggest it to the administrator. The administrator can refer to the suggested text and register product-related text required for the operation of the EC site in the information processing system 1.

[0017] In this specification, "goods" broadly refers to anything that can be bought and sold, and is not limited to goods (products, etc.), but also includes, for example, services, rights (securities, etc.), information, content, etc.

[0018] [Information Processing System 1] The information processing system 1 is a device that functions as an e-commerce site, and performs various processes related to e-commerce, such as generating web pages (code written in HTML, CSS, JavaScript, etc., image data, etc.) containing product information as a web server and displaying them on a customer terminal device 3, accepting product orders from the customer terminal device 3, making payments for the received orders using a predetermined payment method, and arranging for delivery of the ordered products. The information processing system 1 also performs processes related to the operation and management of the e-commerce site in response to instructions from an administrator terminal device 4, and processes supporting the administrator's work related to operation and management. For example, the information processing system 1 may include one or more computers. The information processing system 1 shown in the example of FIG. 1 includes a communication unit 11, a memory unit 12, and a processing unit 13.

[0019] The communication unit 11 communicates with other devices (customer terminal device 3, administrator terminal device 4, search system 6, generation AI system 7, etc.) via the communication network 9. The communication unit 11 includes a device (network interface card, etc.) that communicates in accordance with a predetermined communication standard such as Ethernet (registered trademark) or wireless LAN.

[0020] The storage unit 12 stores one or more programs 121 including instructions to be executed by the processing unit 13, data temporarily saved during processing by the processing unit 13, data used in processing by the processing unit 13, data obtained as a result of processing by the processing unit 13, etc. The storage unit 12 may include, for example, a main storage device (RAM, ROM, etc.) and an auxiliary storage device (flash memory, SSD, hard disk, memory card, optical disk, etc.). The storage unit 12 may be composed of one storage device or multiple storage devices. When the storage unit 12 is composed of multiple storage devices, each storage device is connected to the processing unit 13 via a computer bus or any other communication means.

[0021] The processing unit 13 controls the overall operation of the information processing system 1 and performs predetermined information processing. The processing unit 13 includes, for example, one or more processors (such as a central processing unit (CPU), a micro-processing unit (MPU), a digital signal processor (DSP), a graphics processing unit (GPU), or a neural network processing unit (NPU)) that perform processing according to instructions in one or more programs 121 stored in the storage unit 12. The processing unit 13 operates as one or more computers by the one or more processors executing instructions in one or more programs 121 stored in the storage unit 12. The information processing system 1 may include multiple computers, and at least a part of the processing according to this embodiment may be performed in cooperation with the multiple computers.

[0022] The processing unit 13 may include one or more dedicated hardware (such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA)) configured to realize a specific function. The processing unit 13 may perform all of the processing described in this embodiment on a computer, or may perform some of the processing on a computer and some of the dedicated hardware, or may perform all of the processing on dedicated hardware.

[0023] The program 121 may be recorded, for example, on a computer-readable recording medium (such as an optical disc, a memory card, a USB memory, or other non-transitory tangible medium). The processing unit 13 may read at least a portion of the one or more programs 121 recorded on such a recording medium using a recording medium reading device (such as an optical disc device) or an interface device (such as a USB interface), not shown, and write the read at least a portion of the one or more programs 121 to the storage unit 12. Alternatively, the processing unit 13 may download at least a portion of the one or more programs 121 from another device connected to the communication network 9 via the communication unit 11 and write the downloaded program to the storage unit 12. The one or more programs 121 may include instructions that cause the processing unit 13 to perform at least a portion of the processing according to this embodiment, which will be described later.

[0024] [Storage device 2] The storage device 2 stores various information used in the processing of the information processing system 1. The information processing system 1 and the storage device 2 can communicate via any communication path (such as a LAN, a dedicated line network, or the Internet). For example, the storage device 2 may be included in a file server, database server, or cloud server that accepts access from multiple devices, or may be a dedicated storage device accessible only to the information processing system 1. Alternatively, the storage device 2 may be a storage device connected to the processing unit 13 of the information processing system 1 via a computer bus. In the example of FIG. 1, the storage device 2 stores a customer database 21, a product database 22, an order history database 23, a classification database 24, an instruction statement database 25, and a business-related information database 28. In the following description, database may be abbreviated to "DB."

[0025] The customer DB 21 includes a plurality of pieces of customer information relating to customers who use the EC site of the information processing system 1. One piece of customer information includes information about one customer. One piece of customer information includes, for example, at least some of the following information: Information that identifies individual customers (customer identification information) Customer Personal Information (Example) Name, address, email address, phone number, age, gender, etc. Information about the delivery address of the product (Example) Name of delivery recipient, delivery address

[0026] The product DB 22 includes multiple pieces of product information related to products ordered on the EC site of the information processing system 1. One piece of product information includes information about one product. One piece of product information includes, for example, at least some of the following information: Information that identifies individual products (product identification information) Product name and model number Information about the product manufacturer and provider Information indicating the product classification Product price Product volume Product description Product images

[0027] The "classification" of a product may be a classification set based on any viewpoint, such as product attributes, use, function, quality, price range, brand family, manufacturer, or purchase point. One piece of product information may include information indicating two or more "classifications" from different viewpoints (or having an inclusive relationship such as a major classification or a medium classification). Furthermore, this "classification" may include a classification indicated by classification information registered in the classification DB 24, which will be described later. For example, the product information may include classification identification information, which will be described later, as information indicating the "classification."

[0028] The order history DB 23 includes multiple pieces of order history information related to the product ordering history of customers. One piece of order history information includes information about one product order placed by one customer. One piece of order history information includes, for example, at least some of the following information: Information that identifies individual orders (order identification information) Date and time of the order Customer identification information that identifies the customer who placed the order Product identification information indicating the product ordered -Quantity of products ordered Information about the delivery address of the product - The date and time when the product was delivered Order status (Example) Item is waiting for arrival, delivery arranged, in transit, delivery completed, return accepted, returned

[0029] The category DB 24 includes a plurality of categories of category information, each of which indicates one category of a product. Each category of category information indicates one category of a product. For example, each category of category information includes at least a part of the following information: Information that identifies each classification (classification identification information) -Information indicating the classification type (type information) Category name Classification explanation

[0030] The type of classification indicated by the type information indicates the inclusion relationship between the classifications. For example, suppose two types T1 and T2 are defined, and the classification of type T1 is a higher-level classification that includes the classification of type T2. In this case, if the classification information indicating the classification "cosmetics" includes type information of type T1, and the classification information indicating the classification "skin care" includes type information of type T2, it can be seen that the classification "cosmetics" includes the classification "skin care." Furthermore, in this case, if the classification information indicating the classification "makeup" includes type information of type T2, it can be seen that the classification "cosmetics" includes the classification "makeup," while the classification "skin care" and the classification "makeup" are in a peer relationship (they are included in the same classification and do not intersect with each other). In this way, by comparing the type information included in the classification information, it is possible to understand the inclusion relationship between the classifications.

[0031] The instruction DB 25 includes a plurality of pieces of instruction information related to instruction sentences that cause the generation AI to generate text used for listing and searching for products on the web pages of an e-commerce site. One piece of instruction information includes information related to one instruction sentence. For example, one piece of instruction information includes at least a portion of the following information: - Information that identifies individual instructions (instruction identification information) ·Instructions Information indicating one or more classifications (e.g., one or more classification identifiers) - Information indicating the purpose of the text to be generated by the generation AI (usage information)

[0032] Examples of uses of text include: - To post product-related text (titles, descriptions, etc.) on a web page - To set specific tags on web pages (title tag, meta description tag, meta keywords tag, etc.) for SEO purposes -Use as keywords for product searches on e-commerce sites

[0033] The business-related information DB 28 includes a plurality of business-related information items relating to the content of business performed by the administrator in relation to the operation of the EC site. Each piece of business-related information includes, for example, at least one of the following pieces of information: -Description of the e-commerce site operation work A set of numerical data (distributed representation) obtained by vectorizing the explanatory text

[0034] The explanatory text included in the business-related information may be, for example, text extracted from document data such as a manual relating to the operation of an EC site.

[0035] [Customer terminal device 3] The customer terminal device 3 is a device operated by a customer who browses or purchases products on the EC site. The customer terminal device 3 accesses the information processing system 1 (EC site) in accordance with the customer's operation and displays a web page on which the products are posted using a web browser. The customer terminal device 3 may be a device equipped with information and communication functions, such as a personal computer, tablet, or smartphone. The customer terminal device 3 has a communication unit, a memory unit, and a processing unit similar to the communication unit 11, memory unit 12, and processing unit 13 of the information processing system 1 described above, as well as an input unit and a display unit. The input unit is a device that inputs customer instructions to the processing unit and includes input devices such as a touch panel, mouse, keyboard, and microphone. The display unit is a device that displays images corresponding to the image data generated by the processing unit and includes display devices such as a liquid crystal display, an organic electroluminescence display, and a projector.

[0036] [Administrator terminal device 4] The administrator terminal device 4 is a device operated by an administrator who operates and manages the EC site using the information processing system 1. The administrator accesses the information processing system 1 according to the administrator's operation and displays a management screen for the administrator (see, for example, Figures 7A, 7B, 8A, and 8B, which will be described later). The administrator performs various tasks related to the operation and management of the EC site (such as registering product information, setting up web pages, responding to customer inquiries, setting up EC site functions, and checking information necessary for management) on the management screen displayed on the administrator terminal device 4. The administrator terminal device 4 may be a device equipped with an information communication function, such as a personal computer, tablet, or smartphone. The administrator terminal device 4 has, for example, the same configuration as the customer terminal device 3 described above (a communication unit, a memory unit, a processing unit, an input unit, and a display unit).

[0037] [Generative AI System 5] The generative AI system 5 is a system that provides generative artificial intelligence (AI) functions capable of generating text, images, etc. in response to given prompts, and is capable of communicating with the information processing system 1 via a communication network 9. The generative AI is an artificial intelligence configured to generate text, images (still images, video), etc. in response to given prompts by training an artificial neural network with a large number of parameters (e.g., billions to hundreds of billions) on a large amount of data (text data, image data, etc.). Examples of generative AI include the GPT series (Chat GPT, etc.) operated by OpenAI, Inc. in the United States, the Gemini series operated by Google, Inc. in the United States, and the Claude series operated by Anthropic, Inc. in the United States. In the example of FIG. 1, the information processing system 1 can access one generative AI system 5, but it may also be able to access two or more different generative AI systems 5.

[0038] An example of a process in which a customer purchases a product in the system having the above-described configuration will now be described with reference to the flowchart shown in FIG.

[0039] The customer terminal device 3 accesses a product search web page in the information processing system 1 and transmits a customer instruction (search keywords, etc.) requesting a search for a desired product to the information processing system 1 (ST100). In response to the product search instruction received from the customer terminal device 3, the information processing system 1 searches the product DB 22 for the target products and generates a web page listing the products found by the search (ST105). The information processing system 1 provides the generated search result web page to the customer terminal device 3 (ST110), and the customer terminal device 3 displays the provided web page (ST115).

[0040] When a customer inputs an instruction to put a desired product into the shopping cart at the customer terminal device 3 (ST120), the information processing system 1 adds the product instructed by the customer to the shopping cart (ST125).

[0041] When an instruction to order a product added to the shopping cart is input into the customer terminal device 3 (ST130), the information processing system 1 proceeds with a series of processes related to the purchase and sale of the product (ST135). For example, the information processing system 1 displays a screen on the customer terminal device 3 for specifying a payment method. When the payment method is specified on this screen, the information processing system 1 displays a screen on the customer terminal device 3 for final confirmation of the order details (product, quantity, delivery address, payment method). When an instruction to execute the order is input on the final confirmation screen, the information processing system 1 performs payment processing using a payment method such as a credit card in accordance with the order details. When the payment processing is completed, the information processing system 1 performs processing to arrange for the department in charge of shipping the product or a delivery company to ship and deliver the ordered product. When the product order is completed, the information processing system 1 updates the shopping cart so that the ordered product is deleted. The information processing system 1 also generates order history information for the ordered product and stores it in the order history DB 23 of the storage device 2 (ST140).

[0042] Next, a process for supporting operations related to the operation of an EC site will be described.

[0043] 1. Support for registering text used in product listings and searches

[0044] First, an example of a process for proposing text to be used for listing and searching for products on an EC site will be described with reference to the flowchart of FIG.

[0045] The administrator terminal device 4 transmits a proposal request to the information processing system 1 to propose text (text to be used for listing and searching for products on the EC site) for a certain product in accordance with instructions from the administrator input on a predetermined management screen (for example, FIGS. 7A, 8A, 8B, etc., which will be described later) (ST200). The request for proposing text may include, in addition to specifying the product, a specification of the use of the text (such as a title or description to be listed on a web page, a sentence or keyword to be set in a tag on the web page, or a keyword to be used for searching for products on the EC site).

[0046] When the information processing system 1 receives a proposal request from the administrator terminal device 4 to propose text for a product, it searches the instruction DB 25 for one or more instruction sentence information associated with classification information indicating the classification that applies to the product, and obtains an instruction sentence from the instruction sentence information found by the search (ST205).

[0047] FIG. 4 is a flowchart for explaining an example of the process (ST205) for acquiring a command statement. First, the information processing system 1 identifies classification information indicating a classification that applies to a product specified in a proposal request from the administrator terminal device 4 (ST300). For example, when product identification information for a product is specified in the proposal request from the administrator terminal device 4, the information processing system 1 identifies one or more classification information associated with the specified product identification information. That is, the information processing system 1 reads product information including the product identification information specified in the proposal request from the product DB 22, and identifies one or more classification information from among the multiple classification information registered in the classification DB 24 based on information indicating the product classification (e.g., classification identification information) included in the read product information. When the information indicating the product classification included in the product information is the name, description, etc. of the classification, the information processing system 1 may search the classification DB 24 for classification information including the same or closely related name, description, etc. of the classification, and identify the classification information based on the search results.

[0048] When one or more pieces of classification information are identified in step ST300, the information processing system 1 searches for instruction statement information associated with the one or more pieces of classification information from among the plurality of pieces of instruction statement information registered in the instruction statement DB 25, and acquires an instruction statement from the instruction statement information found by the search. In the example of Fig. 4, the information processing system 1 sequentially selects each of the plurality of pieces of instruction statement information registered in the instruction statement DB 25 (ST305, ST335, ST340), and performs the processes of steps ST310 to ST330 on the selected instruction statement information.

[0049] When the information processing system 1 selects one instruction sentence information in step ST305 (or ST340), it determines whether or not the selected instruction sentence information is associated with (contains) usage information (information indicating the usage of the text) (ST310). If usage information is not associated with the selected instruction sentence information (No in ST310), the information processing system 1 proceeds to step ST325, which will be described later.

[0050] If usage information is associated with the instruction statement information selected in step ST305 (or ST340) (Yes in ST310), the information processing system 1 determines whether the associated usage information indicates the usage specified in the proposal request (ST200) (ST315). If usage information indicating a usage different from the usage specified in the proposal request is associated with the instruction statement information (No in ST315), the information processing system 1 proceeds to step ST335, which will be described later.

[0051] If the use information indicating the use specified in the proposal request is associated with the instruction statement information (Yes in ST315), the information processing system 1 determines whether classification information is associated with (included in) the instruction statement information (ST320). If the classification information is associated with the instruction statement information (Yes in ST320), the information processing system 1 proceeds to the next step, ST325. If the classification information is not associated with the instruction statement information (No in ST320), the information processing system 1 acquires the instruction from the selected instruction statement information (ST330), and proceeds to step ST335.

[0052] In step ST325, the information processing system 1 determines whether the classification information associated with the selected instruction statement information is the same as the classification information identified in step ST300. That is, if each of the one or more classification information associated with the selected instruction statement information is the same as any of the one or more classification information identified in step ST300, the information processing system 1 determines that the classification information associated with the instruction statement information is the same as the classification information identified in step ST300 (Yes in ST325). If the classification information associated with the selected instruction statement information includes classification information different from the classification information identified in step ST300, the information processing system 1 determines that the classification information associated with the instruction statement information is different from the classification information identified in step ST300 (No in ST325).

[0053] If the classification information associated with the instruction statement information is the same as the classification information identified in step ST300 (Yes in ST325), the information processing system 1 acquires the instruction statement from the selected instruction statement information (ST330) and proceeds to step ST335. If the classification information associated with the instruction statement information is different from the classification information identified in step ST300 (No in ST325), the information processing system 1 does not acquire the instruction statement and proceeds to step ST335.

[0054] In step ST335, the information processing system 1 determines whether there is any instruction statement information that has not yet been selected (for which the processing in steps ST310 to ST330 has not been performed) among the multiple pieces of instruction statement information registered in the instruction statement DB 25. If there is any instruction statement information that has not yet been selected (Yes in ST335), the information processing system 1 selects one piece of instruction statement information from among them (ST340) and performs the processing in steps ST310 and thereafter for the selected instruction statement information. If the processing in steps ST310 to ST330 has been completed for each piece of instruction statement information in the instruction statement DB 25 (No in ST335), the information processing system 1 ends the processing for acquiring instruction statements.

[0055] FIG. 5 is a flowchart for explaining another example of the process (ST205) for acquiring a command statement. The flowchart shown in FIG. 5 is the same as the flowchart shown in FIG. 4 except that step ST325 in the flowchart shown in FIG. 4 is replaced with step ST325A.

[0056] 5, the information processing system 1 determines whether the classification information associated with the selected instruction statement information and the classification information identified in step ST300 satisfy a predetermined condition, similar to step ST325 already described. That is, in step ST325A, the information processing system 1 determines whether each of the one or more classification information associated with the selected instruction statement information satisfies one of the following two conditions (first condition, second condition):

[0057] First condition: The classification information is the same as any one of the one or more pieces of classification information identified in step ST300.

[0058] Second condition: The classification information includes type information indicating a type of a higher classification that includes the classification of the type indicated by the type information included in any one of the one or more pieces of classification information identified in step ST300.

[0059] In step ST325 (FIG. 4) already explained, it is determined whether each of the one or more pieces of classification information associated with the selected instruction sentence information satisfies a first condition. In contrast, in step ST325A of the modified example, it is determined whether either the first condition or a second condition relating to the inclusion relationship of the classifications is satisfied.

[0060] For example, assume that one or more pieces of classification information identified in step ST300 include classification information indicating the category "skin care," and the currently selected instruction sentence information is associated with classification information indicating the category "cosmetics." In this case, the classification information indicating the category "cosmetics" is different from the classification information indicating the category "skin care," and therefore does not satisfy the first condition. On the other hand, the type classification indicated by the type information included in the classification information indicating the category "cosmetics" is a higher-level classification that encompasses the type classification indicated by the type information included in the classification information indicating the category "skin care." In this case, the classification information indicating the category "cosmetics" satisfies the second condition with respect to the classification information indicating the category "skin care."

[0061] If each of the one or more pieces of classification information associated with the selected instruction sentence information satisfies the first condition or the second condition (Yes in ST325A), the information processing system 1 acquires the selected sentence from the selected instruction sentence information (ST330) and proceeds to step ST335. If at least one of the one or more pieces of classification information does not satisfy the first condition or the second condition (No in ST325A), the information processing system 1 proceeds to step ST335 without acquiring the instruction sentence.

[0062] 5, when generating text for a product that falls into a certain category, an instruction statement for a product in a higher category that includes the certain category can be acquired as an instruction statement for generating the text. This allows the first prompt (described later) to be generated so as to include an instruction statement that takes into account a higher-level perspective on the product, making it easier to generate appropriate text that matches the product specified in the proposal request.

[0063] In addition, if the purpose of the text to be generated by the generation AI in response to the proposal request has been determined (if the purpose of the text is not specified in the proposal request), the branching process (ST310 to ST320) according to the purpose information in the flowcharts shown in Figures 4 and 5 may be omitted, and the processing of steps ST325 to ST330 may be performed for each instruction sentence information.

[0064] Return to Figure 3. The information processing system 1 generates a first prompt that instructs the generation AI to generate text, based on the one or more instruction sentences acquired by the processing of step ST205 described above (ST220).

[0065] Fig. 6 is a diagram showing an example of a first prompt generated based on a command registered in the command DB 25. The table in the upper part of Fig. 6 shows a list of commands registered in the command DB 25. This table includes three commands prepared for three uses (product comments posted on a webpage, SEO words set in webpage tags for SEO purposes, and search keywords for products on an e-commerce site) and four commands prepared for four categories ("ABC (brand)," "DEF (brand)," "skincare (cosmetics type)," and "makeup (cosmetics type)").

[0066] The first row of the table shown in Figure 6 contains a directive that does not limit the use of the text or the classification of the product. This directive is always selected as the basic directive for generating the first prompt, regardless of the use of the text or the classification of the product.

[0067] The bottom row in Figure 6 shows an example of a first prompt that is generated when the text purpose is "product comment" and the classifications that apply to the product are "ABC (brand)" and "skin care (cosmetics type)." The first prompt shown in the example in Figure 6 is composed of one instruction sentence corresponding to the purpose "product comment," two instruction sentences corresponding to the classifications "ABC (brand)" and "skin care (cosmetics type)," and a basic instruction sentence that is not limited to the purpose or classification.

[0068] In the example of the first prompt shown in the lower part of Figure 6, information such as the product name, product provider, product price, product content, product description, etc. obtained from the product information (product DB22) is inserted below "# product information #".

[0069] Returning to Figure 3 again. The information processing system 1 inputs the first prompt generated in step ST220 to the generation AI system 5 (ST225). The generation AI system 5 generates text using the generation AI function based on the input first prompt (ST230). The information processing system 1 acquires the text generated in response to the first prompt from the generation AI system 5 (ST235). The information processing system 1 generates a management screen (e.g., a web page) including the text acquired from the generation AI system 5 (ST240) and provides it to the administrator terminal device 4. The administrator terminal device 4 displays the management screen provided by the information processing system 1 on a display device as a response to the proposal request (ST245).

[0070] 7A is a diagram showing an example of a screen for registering a product description (product comment) to be posted on a webpage of an EC site, and shows the management screen displayed on the administrator terminal device 4. Screen A shown in FIG. 7A includes an area A1 in which information about the target product (product name, product code) is entered, two input elements A2 and A3 (text input boxes) for entering product comments, an input element A7 (button) operated to register the product comment entered in input elements A2 and A3, and an input element A6 (button) operated to cancel the registration of the product comment and return to the previous screen. A general product comment using a relatively short sentence is entered in input element A2, and a product comment containing more detailed supplemental content than the one entered in input element A2 is entered in input element A3.

[0071] Furthermore, the screen A shown in FIG. 7A includes input elements A4 and A5 (buttons) that are operated when requesting the information processing system 1 to make a suggestion for each of the two product comments.

[0072] Figure 7B shows an example of a screen that is displayed on the administrator terminal device 4 in response to a product comment suggestion request when the request is sent to the information processing system 1 by operating input element A5. Screen B shown in Figure 7B includes an area B1 for posting the product comment generated by the generation AI, input element B2 (button) that is operated when copying the product comment generated by the generation AI to the clipboard, and input element B3 (button) that is operated when replacing the text entered in input element A3 of screen A (Figure 7A) with the product comment generated by the generation AI.

[0073] 8A shows an example of a screen for registering text (SEO words) to be set in tags of a webpage for SEO purposes. Screen C shown in FIG. 8A includes an area C1 for entering product information, three input elements C2 to C4 (text input boxes) for entering SEO words, an input element C10 (button) operated to register the SEO words entered in input elements C2 to C4, and an input element C9 (button) operated to cancel the registration of the SEO words. Input element C2 is used to enter a sentence related to the product title to be set in the title tag, input element C3 is used to enter keywords related to the product to be set in the meta keywords tag, and input element C4 is used to enter a description of the product to be set in the meta description tag.

[0074] 8A also includes input elements C6 to C8 (buttons) that are operated when requesting suggestions for each of the three SEO words from the information processing system 1. When these input elements are operated, a request for suggestion of SEO words is sent to the information processing system 1, and a screen including SEO words generated by the generation AI in response to the suggestion request is displayed on the administrator terminal device 4.

[0075] Fig. 8B shows an example of a screen for registering keywords (search keywords) used to search for products on an e-commerce site. Screen D shown in Fig. 8B includes an area D1 where product information is entered, an input element D2 (text input box) for inputting the search keyword, an input element D5 (button) that is operated to register the search keyword entered in input element D2, and an input element D4 (button) that is operated to cancel registration of the search keyword.

[0076] 8B also includes an input element D3 (button) that is operated when requesting the information processing system 1 to suggest search keywords. When the input element D3 is operated, a request for suggesting search keywords is sent to the information processing system 1, and a screen including search keywords generated by the generation AI in response to the suggestion request is displayed on the administrator terminal device 4.

[0077] As described above, according to this embodiment, when a proposal request for proposing text (text used for listing and searching for products) for a product is input from the administrator terminal device 4, one or more instruction sentences associated with classification information indicating the classification that applies to the product are obtained from the instruction sentence DB 25, and a first prompt is generated that instructs the generation AI to generate text based on the one or more instruction sentences obtained. The generated first prompt is input to the generation AI system 5, and text generated by the generation AI system 5 in response to the first prompt is obtained. The text obtained from the generation AI system 5 is then displayed on the display device of the administrator terminal device 4 as a response to the proposal request. This allows text to be automatically generated for listing and searching for products on an e-commerce site and proposed to the administrator, significantly reducing the administrator's burden in creating text.

[0078] According to this embodiment, the first prompt is generated based on an instruction sentence corresponding to the purpose specified in the proposal request, making it possible to automatically generate text for various purposes, thereby reducing the workload of the administrator.

[0079] According to this embodiment, classification information is associated in advance with product identification information, and this association is used to identify classification information that indicates a classification that applies to the product specified in the text proposal request. Therefore, by associating product identification information with classification information so that a classification that applies to the product is appropriately set, it is possible to obtain an appropriate instruction sentence that suits the product.

[0080] According to this embodiment, when a command sentence is associated with a plurality of pieces of classification information, if each of the plurality of pieces of classification information associated with the command sentence satisfies a condition (first condition) that the plurality of pieces of classification information is identical to one of the plurality of pieces of classification information that indicate a classification that applies to the product specified in the text proposal request, the command sentence is acquired as classification information for generating a first prompt. This makes it possible to use command sentences associated with the plurality of pieces of classification information to generate the first prompt, making it easier to set the association between the product classification and the command sentence in detail, and thus making it easier to generate appropriate text that matches the product specified in the proposal request.

[0081] According to this embodiment, if each of the classification information associated with the instruction sentence satisfies the first condition described above or the second condition that the classification information includes type information indicating a type of a higher-level classification that includes a type indicated by type information included in any one of one or more pieces of classification information indicating a classification that applies to the product specified in the text proposal request, the instruction sentence is acquired as classification information for generating a first prompt. This makes it possible to generate a first prompt for a product that falls into a lower-level classification that is included in the higher-level classification using an instruction sentence associated with the classification information indicating the higher-level classification. Because the first prompt can be generated to include an instruction sentence that takes into account a higher-level perspective regarding the product, it is easier to generate appropriate text that suits the product specified in the proposal request.

[0082] Next, a modified example of this embodiment relating to the generation of text used for listing and searching for products on an EC site will be described.

[0083] (Variation 1) Fig. 9 is a diagram showing a modified example of the configuration of the system according to this embodiment. The system shown in Fig. 9 is the same as the system shown in Fig. 1 except that a product-related information DB 26 is added to the storage device 2.

[0084] The product-related information DB 26 includes a plurality of product-related information pieces, each of which includes information related to a product. For example, one product-related information piece includes at least a part of the following information: ·Product description (Examples) Product manuals, specifications, technical documents, advertising and promotional materials, etc. One or more product identifiers

[0085] Fig. 10 is a flowchart for explaining a modified example of the process of suggesting text to be used for listing and searching for products on an e-commerce site. The flowchart shown in Fig. 10 is the same as the flowchart shown in Fig. 3 except that step ST210 is added and step ST220 is changed to step ST220A. The other steps in the flowchart shown in Fig. 10 are the same as those in the flowchart shown in Fig. 3.

[0086] In step ST210, the information processing system 1 acquires product-related information corresponding to the product specified in the text proposal request (ST200) from the product-related information DB 26. That is, when product identification information is specified in the text proposal request (ST200), the information processing system 1 acquires product-related information (including the product identification information) associated with the specified product identification information from the product-related information DB 26.

[0087] In step ST220A, the information processing system 1 generates a first prompt that instructs the generation AI to generate text based on one or more instruction sentences acquired by the processing of step ST205, similar to step ST220 (FIG. 3) already described. The information processing system 1 also provides the generation AI with an instruction using the instruction sentences, and generates a first prompt that presents the product-related information acquired in step ST210 to the generation AI as information to be referenced when generating text. For example, in the example of FIG. 6, the information processing system 1 may insert the product-related information acquired in step ST210 below "# product information #".

[0088] According to this variant, by having the generation AI refer to product-related information in the first prompt, more detailed information about the product is taken into account when generating the text, making it easier to generate appropriate text that matches the product specified in the proposal request.

[0089] (Variation 2) Fig. 11 is a diagram showing a modified example of the configuration of the system according to this embodiment. The system shown in Fig. 11 is the same as the system shown in Fig. 9 except that a classification-related information DB 27 is added to the storage device 2.

[0090] The category-related information DB 27 includes one or more category-related information items each including information related to the category of a product. For example, one category-related information item includes at least a part of the following information items: Classification explanation (Example 1) If the classification is a brand, a description of the brand concept (Example 2) Description of use when classification is product use Information indicating the classification to which the above description applies (e.g., classification identification information)

[0091] Fig. 12 is a flowchart for explaining a modified example of the process of suggesting text to be used for listing and searching for products on an e-commerce site. The flowchart shown in Fig. 12 is the same as the flowchart shown in Fig. 10 except that step ST215 is added and step ST220A is changed to step ST220B. The other steps in the flowchart shown in Fig. 12 are the same as those in the flowchart shown in Fig. 10.

[0092] In step ST215, the information processing system 1 acquires category-related information for the category that applies to the product specified in the text proposal request (ST200) from the category-related information DB 27. That is, the information processing system 1 acquires category-related information associated with the category information identified in step ST300 (FIGS. 4 and 5) in the process of acquiring the instruction sentence (ST205) from the category-related information DB 27 (category-related information including the same category identification information as the identified category information).

[0093] In step ST220B, the information processing system 1 generates a first prompt that includes the instruction sentence acquired in step ST205 and the product-related information acquired in step ST210, as in step ST220A (FIG. 10) already described, and further includes the category-related information acquired in step ST215. That is, the information processing system 1 generates a first prompt that presents the category-related information acquired in step ST215 to the generation AI as information to be referenced when generating text. For example, in the example of FIG. 6, the information processing system 1 may insert the category-related information acquired in step ST215 below "# product information #".

[0094] According to this variant, by having the generation AI refer to classification-related information in the first prompt, more detailed information about the product is taken into account when generating the text, making it easier to generate appropriate text that matches the product specified in the proposal request.

[0095] 2. Support in writing responses to customer inquiries

[0096] Next, an example of a process for revising a response written in response to a customer inquiry will be described with reference to the flowchart in Fig. 13. The system configuration for performing the process shown in Fig. 13 may be any of those shown in Fig. 1, Fig. 9, and Fig. 11.

[0097] The administrator terminal device 4 transmits to the information processing system 1 a revision request requesting that the information processing system 1 revise a reply created in response to a customer inquiry in accordance with instructions from the administrator input on a predetermined management screen (for example, FIG. 14A described later) (ST400). When the information processing system 1 receives the request to revise the reply from the administrator terminal device 4, it generates a second prompt instructing the information processing system 1 to revise the reply specified in the revision request (ST405). For example, the information processing system 1 generates a second prompt including predetermined revision instructions (such as "Please revise this to use more polite wording," "Please correct typos and omissions," "Please correct errors in grammar," etc.) and the reply specified in the revision request.

[0098] The information processing system 1 inputs the second prompt generated in step ST405 to the generation AI system 5 (ST410). The generation AI system 5 refines the answer sentence using the generation AI function based on the input second prompt, and generates a refined answer sentence as a result of the refinement (ST415). The information processing system 1 acquires the refined answer sentence generated in response to the second prompt from the generation AI system 5 (ST420). The information processing system 1 generates a management screen (e.g., a web page) including the refined answer sentence acquired from the generation AI system 5 (ST425), and provides it to the administrator terminal device 4. The administrator terminal device 4 displays the management screen provided by the information processing system 1 on a display device as a response to the refinement request (ST430).

[0099] 14A is a diagram showing an example of a screen for inputting a reply to an inquiry from a customer, and shows a management screen displayed on the administrator terminal device 4. Screen E shown in FIG. 14A includes a group of input elements E1 (radio buttons) for inputting the type and classification of the inquiry from the customer, input element E2 (text input box) for inputting the name of the administrator who will register the reply, input element E3 (text input box) for inputting the reply, input element E6 (button) operated to register the reply entered in input element E3, and input element E5 (button) operated to cancel the registration of the reply and return to the previous screen.

[0100] 14A also includes an input element E4 (button) that is operated when a request to revise the answer sentence input in the input element E3 is to be sent to the information processing system 1.

[0101] Figure 14B shows an example of a screen displayed on the administrator terminal device 4 as a response to a revision request when a request to revise an answer sentence is sent to the information processing system 1 by operating input element E4. Screen F shown in Figure 14B includes an area F1 for posting the revised answer sentence generated by the generation AI, input element F2 (button) operated when copying the revised answer sentence generated by the generation AI to the clipboard, and input element F3 (button) operated when replacing the answer sentence entered in input element E3 of screen E (Figure 14A) with the revised answer sentence generated by the generation AI.

[0102] According to this embodiment, the work of revising replies to customer inquiries can be omitted, thereby reducing the burden on the administrator involved in creating replies.

[0103] 3. Support for questions regarding work content

[0104] Next, an example of a process for generating answers to questions from an administrator regarding the details of the business of operating an EC site will be described with reference to the flowchart in Fig. 15. The system configuration for performing the process shown in Fig. 15 may be any of those shown in Fig. 1, Fig. 9, and Fig. 11.

[0105] The administrator terminal device 4 transmits an answer request for an answer to a question about the content of a business to the information processing system 1 in accordance with an administrator's instructions input on a predetermined management screen (for example, FIG. 16 described later) (ST500). When the information processing system 1 receives the answer request from the administrator terminal device 4, it searches the business-related information DB 28 for business-related information including an explanation related to the question specified in the answer request, and acquires the explanation from one or more pieces of business-related information found by the search (ST506). For example, the information processing system 1 vectorizes the question specified in the answer request and acquires a group of numerical data (distributed representation) indicating the characteristics of the question. The information processing system 1 calculates the similarity (for example, cosine similarity) between the vector of the question and the vector of the explanation included in the business-related information registered in the business-related information DB 28, and acquires one or more explanations with a relatively high similarity from the business-related information in the business-related information DB 28.

[0106] The information processing system 1 generates a third prompt (ST510) that instructs the user to generate an answer to the question based on one or more explanatory sentences acquired by the search in step ST505. For example, the information processing system 1 generates a third prompt that includes the question specified in the answer request and one or more explanatory sentences acquired by the search in step ST505.

[0107] The information processing system 1 inputs the third prompt generated in step ST510 to the generation AI system 5 (ST515). The generation AI system 5 generates an answer sentence to the question sentence using the generation AI function based on the input second prompt (ST520). The information processing system 1 acquires the answer sentence generated in response to the third prompt from the generation AI system 5 (ST525). The information processing system 1 generates a management screen (e.g., a web page) including the answer sentence acquired from the generation AI system 5 (ST530) and provides it to the administrator terminal device 4. The administrator terminal device 4 displays the management screen provided by the information processing system 1 on a display device as a response to the answer request (ST535).

[0108] Fig. 16 is a diagram showing an example of a screen that displays answers to questions about business operations. Screen G shown in Fig. 16 includes an area G1 that displays a question previously entered by the administrator, an area G2 that displays an answer generated by the generation AI in response to the question in area G1, an input element G3 (text input box) for the administrator to enter an additional question, and an input element G4 (button) that is operated when sending a request for an answer to the question entered in input element G3 to the information processing system 1.

[0109] According to this embodiment, based on the explanations of the business-related information registered in the business-related information DB28, appropriate answers to questions from the administrator regarding the operation of the EC site can be generated, thereby supporting the administrator in carrying out his or her work.

[0110] It should be noted that the present invention is not limited to the above-described embodiment, and includes various variations. Those skilled in the art can make various modifications and substitutions to the components of the above-described embodiment within the technical scope of the present invention or its equivalents.

[0111] In the above-described embodiment, an example is given in which text, etc. is generated using the generation AI functions provided by the generation AI system 5, but in another example of this embodiment, the information processing system 1 may also be given the generation AI functions.

[0112] The screens shown in the above-described figures are merely examples, and the components included in each screen and their arrangement can be changed as desired.

[0113] Some of the processing executed by the information processing system 1 in the above-described embodiment may be executed by other devices (such as the customer terminal device 3 and the administrator terminal device 4). In this case, it can be said that the processing as the information processing system according to this embodiment is executed by a system (computer system) including multiple computers configured by the information processing system 1 and other devices. The inventions described in the claims of the present application as originally filed are as follows: [1] A method in which an information processing system performs processing to support operations related to the operation of an e-commerce site, the information processing system is capable of accessing a storage device; the storage device stores a plurality of instruction sentences each including an instruction for causing a generation AI to generate text used to list and / or search for products on the e-commerce site, the text including at least one of one or more words and one or more sentences related to the products; At least some of the instruction sentences are associated with classification information indicating a predetermined classification of the product; When a suggestion request for suggesting the text for one of the products is input, acquiring one or more of the instruction sentences associated with the classification information indicating the classification that applies to the one of the products; generating a first prompt that instructs the generation AI to generate the text based on the one or more acquired instruction sentences; inputting the first prompt to the generation AI and obtaining the text generated in response to the first prompt from the generation AI; a step of performing a process of displaying the acquired text on a display device as a response to the suggestion request; A method having the following. [2] at least some of the instructions are associated with usage information indicating a predetermined usage of the text at the e-commerce site; the step of acquiring the instruction sentence includes, when the use of the text is specified in the proposal request requesting that the text be proposed for one of the products, acquiring one or more of the instruction sentences associated with the use information indicating the specified use; [1] The method described in [1]. [3] the storage device stores a plurality of pieces of product identification information, each of which is information for identifying one of the products; At least some of the product identification information is associated with one or more of the classification information; The step of obtaining the instruction sentence includes: When the product identification information of one of the products is specified in the proposal request requesting that the text be proposed for the one of the products, identifying one or more pieces of classification information associated with the specified product identification information; and obtaining one or more of the instruction sentences associated with the identified one or more of the classification information. [1] The method described in [1]. [4] In the step of acquiring the instruction sentence, acquiring the one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentences that satisfy a condition that each of the classification information associated with the instruction sentences is identical to any of the one or more pieces of classification information identified; [3] The method described in [3]. [5] the classification information includes type information indicating a type of the classification, The type indicates an inclusion relationship between the classifications, In the step of acquiring the instruction sentence, acquiring the one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentence that satisfies a first condition that each of the classification information associated with the instruction sentence is identical to any one of the one or more specified classification information, or a second condition that the classification information includes type information indicating a type of a higher classification that includes the classification of the type indicated by the type information included in any one of the one or more specified classification information, [3] The method described in [3]. [6] the storage device stores one or more pieces of product-related information, each of which contains information related to the product; At least some of the product-related information is associated with one or more of the product identification information; When the product identification information of one of the products is specified in the proposal request, acquiring the product-related information associated with the specified product identification information, the step of generating the first prompt includes, when the product-related information is acquired, generating the first prompt to present the acquired product-related information to the generation AI as information to be referenced when generating the text; [3] The method described in [3]. [7] the storage device stores one or more classification-related information items each including information related to the classification; At least some of the classification-related information is associated with one or more of the classification information; When one or more pieces of classification information are identified for the product identification information specified in the proposal request, acquiring the classification-related information associated with the identified one or more pieces of classification information, the step of generating the first prompt includes, when the classification-related information is acquired, generating the first prompt to present the acquired classification-related information to the generation AI as information to be referenced when generating the text; [3] The method described in [3]. [8] generating a second prompt instructing the user to revise a response created in response to an inquiry from a customer using the e-commerce site when a revision request is input; inputting the second prompt to the generation AI and obtaining, from the generation AI, a refined answer sentence generated in response to the second prompt; and performing a process of displaying the acquired revised answer sentence on a display device as a response to the revision request. [1] The method described in [1]. [9] the storage device stores one or more pieces of business-related information including explanatory text relating to the content of the business; When a request for an answer to a question about the content of the business is input, searching for the explanatory text related to the question in one or more of the business-related information; generating a third prompt that instructs the user to generate an answer to the question based on one or more of the explanatory sentences found by the search; inputting the third prompt to the generation AI, and obtaining the answer sentence generated in response to the third prompt from the generation AI; and performing a process of displaying the acquired answer sentence on a display device as a response to the answer request. [1] The method described in [1].

[10] A program including instructions for causing an information processing system to perform processing to support operations related to the operation of an e-commerce site, The processing performed by the information processing system in accordance with the instructions includes each step of the method described in any one of [1] to [9]. program.

[11] An information processing system that performs processing to support operations related to the operation of an e-commerce site, a processing unit; a storage unit that stores instructions for causing the processing unit to perform processing; The processing performed by the processing unit in accordance with the instructions includes each step of the method described in any one of [1] to [9]. Information processing system.

[12] An information processing system that performs processing to support operations related to the operation of an e-commerce site, [1] to [9], comprising a means for performing each step of the method described in any one of [1] to [9], Information processing system. [Explanation of symbols]

[0114] 1...information processing device, 11...communication unit, 12...storage unit, 121...program, 13...processing unit, 2...storage device, 21...customer DB, 22...product DB, 23...order history DB, 24...classification DB, 25...instruction statement DB, 26...product-related information DB, 27...classification-related information DB, 28...business-related information DB, 3...customer terminal device, 4...administrator terminal device, 5...generation AI system, 9...communication network

Claims

1. A method in which an information processing system performs processing to support operations related to the operation of an e-commerce site, the information processing system is capable of accessing a storage device; The storage device stores a plurality of instruction sentences each including an instruction for causing a generation AI to generate text used to list and / or search for products on the e-commerce site, the text including at least one of one or more words and one or more sentences related to the products; At least some of the instruction sentences are associated with classification information indicating a predetermined classification of the product; When a suggestion request for suggesting the text for one of the products is input, acquiring one or more of the instruction sentences associated with the classification information indicating the classification that applies to the one of the products; generating a first prompt instructing the generation AI to generate the text based on the one or more of the instruction sentences obtained; inputting the first prompt to the generating AI and obtaining the text generated in response to the first prompt from the generating AI; and performing a process of displaying the acquired text on a display device as a response to the suggestion request, the storage device stores a plurality of pieces of product identification information, each of which is information for identifying one of the products; At least some of the product identification information is associated with one or more of the classification information; The step of obtaining the instruction sentence includes: When the product identification information of one of the products is specified in the proposal request for proposing the text for the one of the products, identifying one or more of the classification information associated with the specified product identification information; and obtaining one or more of the instruction statements associated with the one or more identified classification information; the storage device stores one or more pieces of product-related information each containing information related to the product; At least some of the product-related information is associated with one or more of the product identification information; When the product identification information of one of the products is specified in the proposal request, acquiring the product-related information associated with the specified product identification information, The step of generating the first prompt includes, when the product-related information is acquired, generating the first prompt to present the acquired product-related information to the generation AI as information to be referenced when generating the text. method.

2. A method in which an information processing system performs processing to support operations related to the operation of an e-commerce site, the information processing system is capable of accessing a storage device; The storage device stores a plurality of instruction sentences each including an instruction for causing a generation AI to generate text used to list and / or search for products on the e-commerce site, the text including at least one of one or more words and one or more sentences related to the products; At least some of the instruction sentences are associated with classification information indicating a predetermined classification of the product; When a suggestion request for suggesting the text for one of the products is input, acquiring one or more of the instruction sentences associated with the classification information indicating the classification that applies to the one of the products; generating a first prompt instructing the generation AI to generate the text based on the one or more of the instruction sentences obtained; inputting the first prompt to the generating AI and obtaining the text generated in response to the first prompt from the generating AI; and performing a process of displaying the acquired text on a display device as a response to the suggestion request, the storage device stores a plurality of pieces of product identification information, each of which is information for identifying one of the products; At least some of the product identification information is associated with one or more of the classification information; The step of obtaining the instruction sentence includes: When the product identification information of one of the products is specified in the proposal request for proposing the text for the one of the products, identifying one or more of the classification information associated with the specified product identification information; and obtaining one or more of the instruction statements associated with the one or more identified classification information; the storage device stores one or more classification-related information items each including information related to the classification; At least some of the classification-related information is associated with one or more of the classification information; When one or more pieces of classification information are identified for the product identification information specified in the proposal request, acquiring the classification-related information associated with the identified one or more pieces of classification information, the step of generating the first prompt includes, when the classification-related information is acquired, generating the first prompt to present the acquired classification-related information to the generation AI as information to be referenced when generating the text. method.

3. at least some of the instructions are associated with usage information indicating a predetermined usage of the text at the e-commerce site; the step of acquiring the instruction sentence includes, when the use of the text is specified in the proposal request requesting that the text be proposed for one of the products, acquiring one or more of the instruction sentences associated with the use information indicating the specified use; The method of claim 1.

4. at least some of the instructions are associated with usage information indicating a predetermined usage of the text at the e-commerce site; the step of acquiring the instruction sentence includes, when the use of the text is specified in the proposal request requesting that the text be proposed for one of the products, acquiring one or more of the instruction sentences associated with the use information indicating the specified use; The method of claim 2.

5. In the step of acquiring the instruction sentence, acquiring one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentences that satisfy a condition that each of the classification information associated with the instruction sentences is identical to any of the one or more pieces of classification information identified; The method of claim 1.

6. In the step of acquiring the instruction sentence, acquiring one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentences that satisfy a condition that each of the classification information associated with the instruction sentences is identical to any of the one or more pieces of classification information identified; The method of claim 2.

7. the classification information includes type information indicating a type of the classification, The type indicates an inclusion relationship between the classifications, In the step of acquiring the instruction sentence, acquiring one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentence that satisfies a first condition that each of the classification information associated with the instruction sentence is identical to any one of the one or more specified classification information, or a second condition that the classification information includes type information indicating a type of a higher classification that includes the classification of the type indicated by the type information included in any one of the one or more specified classification information, The method of claim 1.

8. the classification information includes type information indicating a type of the classification, The type indicates an inclusion relationship between the classifications, In the step of acquiring the instruction sentence, acquiring one or more instruction sentences associated with the one or more pieces of classification information identified includes: acquiring the instruction sentence that satisfies a first condition that each of the classification information associated with the instruction sentence is identical to any one of the one or more specified classification information, or a second condition that the classification information includes type information indicating a type of a higher classification that includes the classification of the type indicated by the type information included in any one of the one or more specified classification information, The method of claim 2.

9. A program including instructions for causing an information processing system to perform processing to support operations related to the operation of an e-commerce site, The processing performed by the information processing system in accordance with the instructions includes each step of the method described in any one of claims 1 to 8. program.

10. An information processing system that performs processing to support operations related to the operation of an e-commerce site, a processing unit; a storage unit that stores instructions for causing the processing unit to perform processing; The processing performed by the processing unit in accordance with the instructions includes each step of the method described in any one of claims 1 to 8. Information processing system.

11. An information processing system that performs processing to support operations related to the operation of an e-commerce site, A method comprising: Information processing system.

Images