Information processing device, information processing method, and information processing program

Abstract

To support creation of an explaining sentence of merchandise exhibited by a user.SOLUTION: An information processing device comprises: a reception unit which receives merchandise information related to merchandise exhibited by a user from the user, in a platform in which the other user purchases the merchandise exhibited by the user; a generation unit which generates an explaining sentence, by inputting the merchandise information received by the reception unit, with respect to a model learned so as to output the explaining sentence of the merchandise indicated by the inputted merchandise information, on the basis of the inputted merchandise information, and a rule corresponding to the inputted merchandise information, when the merchandise information is inputted; and an output unit which outputs the explaining sentence generated by the generation unit to the user.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, a technique for managing product information in an e-commerce service has been known. As an example of such a technique, information on products currently listed in an online store is stored in an inventory table of a database, and based on the ISBN code in the inventory table, product information of other sellers who are listing the same product as the one the user is listing is obtained, and the user's listing price is calculated based on the listing prices of other sellers, and a technique for changing the listing price is known.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the above-described conventional technology does not always support the creation of a description of a product to be listed by a user.

[0005] For example, in the above-described conventional technology, it only changes the listing price based on the listing prices of other sellers, and does not always support the creation of a description of a product to be listed by a user.

[0006] The present application has been made in view of the above, and an object thereof is to support the creation of a description of a product to be listed by a user.

Means for Solving the Problems

[0007] The information processing device according to the present application is characterized by having, on a platform where other users purchase products listed by users, a receiving unit that receives product information from users regarding products listed by users, a generating unit that generates a description text by inputting the product information received by the receiving unit to a model that has been trained to output a description text of the product indicated by the input product information based on the input product information and rules corresponding to the input product information, and an output unit that outputs the description text generated by the generating unit to the user. [Effects of the Invention]

[0008] According to one embodiment of the system, it has the effect of assisting users in creating product descriptions for items they list for sale. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of the information processing device 10 according to the embodiment. [Figure 3] Figure 3 shows an example of the user information database 31. [Figure 4] Figure 4 shows an example of the rule database 32. [Figure 5] Figure 5 is a flowchart showing an example of the information processing procedure according to the embodiment. [Figure 6] Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10. [Modes for carrying out the invention]

[0010] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0011] [1. Embodiments] The information processing realized by the information processing device of this embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. In Figure 1, it is assumed that the information processing according to the embodiment is realized by the information processing device 10, which is an example of information processing according to this embodiment.

[0012] As shown in Figure 1, the information processing system 1 according to this embodiment includes an information processing device 10 and a user terminal 100. The information processing device 10 and the user terminal 100 are connected to each other via a network N (see, for example, Figure 2) by wire or wireless means so that they can communicate with each other. The network N is, for example, a WAN (Wide Area Network) such as the Internet. Note that the information processing system 1 shown in Figure 1 may include multiple information processing devices 10 and multiple user terminals 100.

[0013] The information processing device 10 shown in Figure 1 is an information processing device that performs information processing, and can be implemented, for example, by a server device or a cloud system. For example, the information processing device 10 provides a platform #1 (for example, an e-commerce service such as a flea market service or an auction service) where users can purchase products that users have listed for sale, and accepts registration of various types of information (for example, information about products that users list for sale) from users for the platform.

[0014] Furthermore, the information processing device 10 may also function as a web server providing websites related to various services, including services related to platform #1. The information processing device 10 may also be a device that distributes information to be displayed in applications related to various services installed on the user terminal 100. Alternatively, the information processing device 10 may be a server that distributes the application data itself.

[0015] Furthermore, the information processing device 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is written using, for example, a scripting language such as JavaScript (registered trademark) or a stylesheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 10 may also be considered as control information.

[0016] The user terminal 100 shown in Figure 1 is an information processing device used by the user. The user terminal 100 can be implemented as, for example, a smartphone, tablet, notebook PC (Personal Computer), desktop PC, mobile phone, or PDA (Personal Digital Assistant). The user terminal 100 displays information distributed by the information processing device 10, etc., using a web browser or application. Note that the example shown in Figure 1 illustrates the case where the user terminal 100 is a smartphone.

[0017] The following describes an example of information processing performed by the information processing device 10, using Figure 1. In the following description, it is assumed that the user terminal 100 is used by a user identified by the user ID "UID#1" (user U1). Furthermore, in the following description, user terminal 100 may be treated as identical to user U1. That is, in the following, user U1 can be read as user terminal 100.

[0018] First, the information processing device 10 receives product information about product #1 that user U1 offers on platform #1 from the user terminal 100 (step S1). For example, the information processing device 10 receives the information input on screen C1 provided to the user terminal 100 via platform #1 as the product information of product #1. To give a specific example, the information processing device 10 receives product information including an image of product #1 (product image), name (product title), category, brand, specification information (e.g., color, size, target age, etc. of product #1), status (e.g., "unused", "no obvious scratches or dirt", etc.).

[0019] Here, in the example of FIG. 1, it is assumed that user U1 has performed an operation (e.g., pressing the "Generate product description" button on screen C1) on the user terminal 100 to request the generation of a product description (product description text) of product #1 using a predetermined model. In such a case, the information processing device 10 generates a product description of product #1 using the product information of product #1 input on screen C1 and model #1 (step S2). For example, when product information is input, the information processing device 10 inputs the input product information to model #1 that has been learned to output a product description of the product indicated by the input product information based on the input product information and the rules corresponding to the input product information (in other words, among the prompts input to model #1, the rules for generating a product description, such as the tendency and structure of the product description generated by model #1 from the prompt), thereby generating a product description of product #1. [[ID=?]] [[ID=?]]

[0020] [[ID=?]] For example, in step S2, in response to the pressing of the "Generate product description" button by user U1, the information processing device 10 causes the user terminal 100 to display a screen C2 including a button B21 for instructing the generation of a product description, an area AR21 for displaying the product information input to model #1, and an area AR22 for inputting information such as information regarding the delivery of product #1 and the selling price.

[0021] It should be noted that the "?" in the ID in the translation is because the original ID seems to be incorrect or incomplete in the source text. But according to the requirements, it is preserved as it is.Here, let's assume that user U1 wishes to generate a description of product #1 using the product information displayed in area AR21 and presses button B21. In this case, the information processing device 10 generates the description by inputting the product information displayed in area AR21, the rules corresponding to that product information, and an instruction sentence that instructs the device to output the description of product #1 indicated by the product information according to the rules. For example, the information processing device 10 generates description #1 of product #1 based on rules that specify that the description of product #1 should be generated in a style corresponding to the product information displayed in area AR21 (e.g., product title, category, etc.).

[0022] To give a specific example, the information processing device 10 generates product description #1 for product #1 based on rules that indicate the style of descriptions for products related to product #1 among the products listed on platform #1 (for example, products similar to product #1 (for example, products with product titles similar to product #1's product title "AA"), products corresponding to product #1, or products belonging to the category "Games"). In addition, the information processing device 10 generates product description #1 for product #1 based on rules that indicate the style of descriptions for products related to product #1 that have been sold within a predetermined period (for example, one week) since being listed on platform #1 (in other words, descriptions that are likely to sell).

[0023] Model #1 is a model trained to output a response (explanatory text) corresponding to an input question (instructional text), and is a natural language processing language model such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Model #1 resides within the information processing device 10 and was independently created by the operator managing platform #1. It is desirable that the input information be kept confidential by training the model so that it is not used as a new response, thereby protecting personal information and other sensitive data.

[0024] Next, the information processing device 10 outputs the description #1 to the user terminal 100 (step S3). For example, the information processing device 10 displays screen C3 showing the description #1 on the user terminal 100. Then, user U1 uses the description #1, which they have modified or added to, to perform the operation to list product #1 on platform #1.

[0025] The information processing device 10 may also receive product information from the user in a conversational format and generate a description. For example, the information processing device 10 provides screen C4 to the user terminal 100 via platform #1. The information processing device 10 then displays a message regarding the provision of product information in area AR41 and receives the user's response to the message (for example, image P41, which is a product image, the product title "EE Sneakers Blue", and the category "Women's Sneakers") as product information. The information processing device 10 then displays the description generated based on the product information in area AR41 in area AR42. The information processing device 10 also displays buttons in area AR43 for receiving instructions from the user to modify the description displayed in area AR42 (for example, an "Add This" button to instruct the user to add product information, or a "Learn More" button to instruct the user to change the writing style).

[0026] As described above, the information processing device 10 according to this embodiment outputs a product description based on the product information received from the user. In this way, the information processing device 10 according to this embodiment can assist the user in creating a product description for listing.

[0027] Furthermore, users who are listing items for the first time on auction or flea market services may not know what to write in the description. In response to this, the information processing device 10 according to this embodiment can generate and output to the user a description that is suitable for the product or a description that is likely to sell, thus providing guidance on creating a description for users who are listing items for the first time.

[0028] [2. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various types of information. Examples of this are listed below.

[0029] [2-1. Regarding the specification of rules by users] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules specified by user U1. For example, the information processing device 10 receives a rule from user U1 indicating a writing style such as "concise writing style" or "natural writing style," and generates a description of product #1 in the writing style indicated by the specified rule.

[0030] Furthermore, the information processing device 10 may receive requests from user U1 for generating a description of product #1. The information processing device 10 may then generate a description of product #1 based on rules corresponding to the received requests.

[0031] [2-2. Rules based on the context of product sales] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules indicating the style of product descriptions for products that meet predetermined conditions when sold on platform #1. For example, if user U1 requests to sell product #1 within a predetermined period (e.g., one week), the information processing device 10 generates a description of product #1 based on rules indicating the style of product descriptions for products related to product #1 that have been sold on platform #1 within a predetermined period. Alternatively, if user U1 requests to sell product #1 for a predetermined price (e.g., 1000 yen) or more, the information processing device 10 generates a description of product #1 based on rules indicating the style of product descriptions for products related to product #1 that have been sold on platform #1 for a predetermined price or more.

[0032] [2-3. Rules tailored to the buyer] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules indicating the writing style of product descriptions purchased on platform #1 by buyers who meet certain conditions. For example, if user U1 requests to sell to a user with the attribute "female in her 20s", the information processing device 10 generates a description of product #1 based on rules indicating the writing style of product descriptions of related products purchased on platform #1 by users with the attribute "female in her 20s".

[0033] [2-4. Rules based on user attributes] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules indicating a writing style corresponding to a user having predetermined attributes. For example, if user U1 specifies a rule such as "writing style that a woman would likely write," the information processing device 10 generates a description of product #1 based on rules indicating a writing style for a description entered on platform #1 by a user with the attribute "female."

[0034] The information processing device 10 may also generate the description for product #1 based on rules indicating a writing style corresponding to the attributes of user U1. For example, if user U1's attribute is "female in her 20s," the information processing device 10 generates the description for product #1 based on rules indicating a writing style for descriptions entered by users with the attribute "female in her 20s" on platform #1.

[0035] Furthermore, the information processing device 10 may generate a description for product #1 based on a rule that indicates the style of the description for a product that meets predetermined sales conditions on platform #1 and corresponds to the attributes of user U1. If user U1's attribute is "female in her 20s", the information processing device 10 generates a description for product #1 based on a rule that indicates the style of the description for a product listed on platform #1 by a user with the attribute "female in her 20s" and sold within a predetermined period after being listed.

[0036] [2-5. Rules regarding the timing of listing items] In the example shown in Figure 1, the information processing device 10 may generate a description based on rules indicating a writing style corresponding to the time of year the product is listed. For example, the information processing device 10 generates a description of the product based on rules indicating a writing style corresponding to the season in which the product is used and the season in which the product is listed. To give a specific example, if the product "electric fan" is listed in the summer, the information processing device 10 generates a description that includes phrases such as "Perfect for this season."

[0037] [2-6. Rules regarding character count] In the example shown in Figure 1, the information processing device 10 may generate a description for product #1 based on a rule indicating the number of characters in the description. For example, the information processing device 10 generates a description for product #1 within the character limit defined on platform #1, within the character limit specified by user U1, or within the character limit of the description for a product whose sales status on platform #1 meets a predetermined condition (for example, a product that has been sold within a predetermined period after being listed).

[0038] [2-7. Prohibition of the use of specified character strings] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules indicating strings to be excluded from the description. For example, the information processing device 10 generates a description of product #1 without including strings that are contrary to public order and morals, or strings specified by the operator managing platform #1 (for example, strings that indicate other operators).

[0039] [2-8. Product information to be included in the description] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on a rule indicating product information not to be included in the description. For example, when the information processing device 10 generates a description of product #1 based on a rule indicating that the list price of the product should not be included in the description, if the product information for product #1 includes the list price of product #1, the information processing device 10 generates a description of product #1 without including the list price of product #1.

[0040] Furthermore, the information processing device 10 may generate a description of product #1 based on rules indicating the product information to be included in the description. For example, when the information processing device 10 generates a description of product #1 based on rules indicating that the product's condition should be included in the description, it generates the description of product #1 including the condition "unused".

[0041] [2-9. Regarding the generation of explanatory texts based on the user's writing style] In the example shown in Figure 1, the information processing device 10 may generate a description for product #1 based on the descriptions entered by user U1 for products previously listed on platform #1. For example, the information processing device 10 generates a description for product #1 based on rules indicating the writing style of descriptions previously entered by user U1. The information processing device 10 also generates a description for product #1 including predetermined information (e.g., shipping method) that was included in the descriptions previously entered by user U1.

[0042] [2-10. Regarding the generation of information-based explanatory texts for specified services] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on a rule indicating that it should include information about user U1's preferences. For example, the information processing device 10 estimates user U1's preferences (in other words, interests and concerns) based on user U1's usage history of various services, such as search queries entered by user U1 in a search service or content viewed by user U1 in a news service, and generates a description of product #1 that includes information indicating the estimated preferences of user U1.

[0043] Furthermore, in the example in Figure 1, the information processing device 10 may generate a description of product #1 based on a rule indicating that information regarding the scarcity of product #1 should be included. For example, the information processing device 10 estimates the scarcity of product #1 based on information regarding products related to product #1 that are sold on platform #1 or other e-commerce services, and generates a description of product #1 that includes the estimated scarcity information. To give a specific example, if products related to product #1 are selling for more than the list price on platform #1, the information processing device 10 generates a description of product #1 that includes information indicating that product #1 is highly scarce. Also, if products related to product #1 are out of stock on other e-commerce services, the information processing device 10 generates a description of product #1 that includes information indicating that product #1 is highly scarce.

[0044] Furthermore, the information processing device 10 may collect information other than that described above from various services and include it in the product description. For example, if the product listed by the user is a handmade product or a hobby-related product for which there is little information available, the information processing device 10 will collect supplementary information from various services and generate a product description that includes the collected information.

[0045] [2-11. Regarding the generation of product descriptions according to the category to which the product belongs] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on rules indicating a writing style corresponding to the sales history of the category to which product #1 belongs on platform #1. For example, the information processing device 10 generates a description of product #1 based on rules based on statistical information indicating the trend of products that sell well in the category to which product #1 belongs (for example, products that sell within a predetermined period after being listed). To give a specific example, the information processing device 10 generates a description of product #1 based on rules indicating the writing style of descriptions of popular products in the category to which product #1 belongs.

[0046] [2-12. Regarding the generation of product-specific descriptions related to the product] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on the writing style corresponding to the viewers of product #1 and related products. For example, the information processing device 10 generates a description of product #1 based on a rule that indicates the writing style corresponding to the most common attribute among users who viewed product #1 and related products. To give a specific example, if the largest proportion of users who viewed product #1 and related products have the attribute "women in their 20s," the information processing device 10 generates a description of product #1 on platform #1 using the writing style of product descriptions that are likely to sell to users with the attribute "women in their 20s" (for example, product descriptions of products that sold within a predetermined period).

[0047] [2-13. Generating product descriptions that are appropriate to the context of the items being listed] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on a rule that indicates the inclusion of contextual information regarding when user U1 purchased product #1. For example, the information processing device 10 generates a description of product #1 that includes contextual information regarding when user U1 purchased product #1 on platform #1 or other e-commerce services. Specifically, the information processing device 10 generates a description of product #1 that includes information indicating when, where, and for how much user U1 purchased product #1.

[0048] [2-14. Regarding the generation of explanatory text in response to the purchase of products with a specified relevance] In the example shown in Figure 1, the information processing device 10 may generate a description of product #1 based on a rule indicating that user U1 has purchased a product that has a predetermined relationship with product #1. For example, if user U1 purchases product #1 after purchasing product #2, which is an older model of a product related to product #1, on platform #1 or another e-commerce service, the information processing device 10 will generate a description of product #1 that includes a string such as "This is a replacement for product #2." Also, if user U1 purchases product #1 after purchasing product #3, which is a newer model of a product related to product #1, on platform #1 or another e-commerce service, the information processing device 10 will generate a description of product #1 that includes a string such as "This is a replacement for product #3."

[0049] [2-15. Extracting information from images] In the example shown in Figure 1, the information processing device 10 may not accept product information entered by user U1, but rather information extracted from an image of product #1 as product information. For example, the information processing device 10 accepts product information from user terminal 100 that includes the product title, category, brand, specifications, and condition of product #1, extracted from an image of product #1. Alternatively, the information processing device 10 may accept an image of product #1 from user terminal 100 and extract product information from that image.

[0050] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device 10 will be described using Figure 2. Figure 2 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. As shown in Figure 2, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0051] (Regarding Communications Section 20) The communication unit 20 is implemented, for example, by a NIC (Network Interface Card). The communication unit 20 is connected to the network N by wire or wireless connection and transmits and receives information with the user terminal 100, etc.

[0052] (Regarding memory unit 30) The storage unit 30 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. As shown in Figure 2, the storage unit 30 has a user information database 31, a rule database 32, and a model database 33.

[0053] (Regarding User Information Database 31) The user information database 31 stores various types of information about the user. Here, an example of the information stored in the user information database 31 will be explained using Figure 3. Figure 3 is a diagram illustrating an example of the user information database 31. In the example in Figure 3, the user information database 31 has items such as "User ID," "Attribute Information," "Usage History," "Purchase Information," and "Listed Product Information."

[0054] "User ID" indicates identification information used to identify the user. "Attribute Information" indicates the user's attributes (e.g., demographic attributes and psychographic attributes). "Usage History" indicates the user's usage history across various services. "Purchase Information" indicates information about products purchased by the user on Platform #1 or other e-commerce services, such as product name, category, price, and purchase date and time. "Listed Product Information" indicates information about products listed by the user on Platform #1, such as "Product ID," "Product Information," "Description," and "Sales Status."

[0055] "Product ID" indicates identification information used to identify a product. "Product Information" indicates information about the product. "Description" indicates a description of the product. "Sales Status" indicates the sales status of the product, and stores information such as the date and time the product was sold and the price at which it was sold.

[0056] In other words, Figure 3 shows an example where the user's attribute information, identified by the user ID "UID#1", is "Attribute Information#1", the usage history is "Usage History#1", and the purchase information is "Purchase Information#1", and the product listed by that user is identified by the product ID "SID#1", with product information being "Product Information#1", the description being "Description#1", and the sales status being "Sales Status#1".

[0057] (Regarding Rule Database 32) The rule database 32 stores information about the rules used when generating product descriptions. Here, an example of the information stored in the rule database 32 is illustrated using Figure 4. Figure 4 is a diagram illustrating an example of the rule database 32. In the example in Figure 4, the rule database 32 has items such as "Rule ID," "Rule Information," and "Application Conditions."

[0058] The "Rule ID" indicates identification information for identifying a rule. The "Rule Information" indicates information about the rule, such as the writing style of the description and the information to be included in the description. The "Application Conditions" indicate the conditions under which the rule indicated by the Rule Information applies, such as product information for the product to which the rule applies, and attribute information of the user who listed the product.

[0059] In other words, Figure 4 shows an example where the rule information for a rule identified by the rule ID "RID#1" is "Rule Information #1" and the application condition is "Application Condition #1".

[0060] (Regarding Model Database 33) The model database 33 stores a model that has been trained to output a product description based on the entered product information and the rules corresponding to that product information, when product information is entered.

[0061] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the memory device inside the information processing device 10 using RAM as the working area. Alternatively, the control unit 40 is a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). As shown in Figure 2, the control unit 40 according to this embodiment has a receiving unit 41, a generating unit 42, and an output unit 43, and realizes or executes the information processing functions and operations described below.

[0062] (Regarding Reception Desk 41) The reception unit 41 receives product information from users regarding products listed by users on a platform where other users can purchase products listed by users. For example, in the example in Figure 1, the reception unit 41 receives product information from user terminal 100 regarding product #1 listed by user U1 on platform #1 and stores it in the user information database 31.

[0063] Furthermore, the reception unit 41 may accept the user's answers to questions about the products they list as product information. For example, in the example in Figure 1, the reception unit 41 provides screen C4 via platform #1, displays a message regarding the provision of product information, and accepts the user's answer to that message as product information.

[0064] Furthermore, the reception unit 41 may also receive product information extracted from images of products listed by users. For example, in the example shown in Figure 1, the reception unit 41 receives product information from the user terminal that is extracted from an image of product #1, including the product title, category, brand, specifications, and condition of product #1.

[0065] (Regarding the generation unit 42) When product information is input, the generation unit 42 generates a description by inputting the product information received by the reception unit 41 to a model that has been trained to output a description of the product indicated by the input product information, based on the input product information and the rules corresponding to the input product information. For example, in the example in Figure 1, the generation unit 42 refers to the user information database 31, the rule database 32, and the model database 33, and inputs the product information of product #1 to model #1 to generate a description of product #1.

[0066] Furthermore, the generation unit 42 may generate a description based on rules specified by the user. For example, in the example in Figure 1, the generation unit 42 receives a rule specification from user U1 and generates a description of product #1 based on the specified rule.

[0067] Furthermore, the generation unit 42 may generate the description based on rules indicating a predetermined writing style. For example, in the example in Figure 1, the generation unit 42 generates the description of product #1 based on rules indicating a writing style such as "concise writing style" and "natural writing style".

[0068] Furthermore, the generation unit 42 may generate a description based on rules indicating the style of the description of a product that meets predetermined conditions when sold on the platform. For example, in the example in Figure 1, if user U1 requests "I want to sell product #1 within a predetermined period," the generation unit 42 generates a description of product #1 based on rules indicating the style of the description of a product related to product #1 that was sold on platform #1 within a predetermined period after being listed. Also, for example, if user U1 requests "I want to sell product #1 for a predetermined price or more," the generation unit 42 generates a description of product #1 based on rules indicating the style of the description of a product related to product #1 that was sold on platform #1 for a predetermined price or more.

[0069] Furthermore, the generation unit 42 may generate a description based on rules indicating the writing style of product descriptions purchased on the platform by buyers who meet certain conditions. For example, in the example in Figure 1, if user U1 requests to sell to a user with the attribute "female in her 20s", the generation unit 42 generates a description for product #1 based on rules indicating the writing style of product descriptions purchased on platform #1 by users with the attribute "female in her 20s" among products related to product #1.

[0070] Furthermore, the generation unit 42 may generate a description based on rules indicating a writing style corresponding to a user having predetermined attributes. For example, in the example in Figure 1, if user U1 specifies a rule such as "writing style that a woman would likely write," the generation unit 42 generates a description for product #1 based on rules indicating a writing style for a description entered on platform #1 by a user with the attribute "female."

[0071] Furthermore, the generation unit 42 may generate the description based on rules indicating a writing style corresponding to the user's attributes. For example, in the example in Figure 1, if the attribute of user U1 is "female in her 20s", the generation unit 42 generates the description for product #1 based on rules indicating a writing style for the description entered by a user with the attribute "female in her 20s" for a product listed on platform #1.

[0072] Furthermore, the generation unit 42 may generate a description based on a rule that indicates a writing style corresponding to the user's attributes and the writing style of a product description that meets predetermined conditions for sales on the platform. For example, in the example in Figure 1, if the attribute of user U1 is "female in her 20s", the generation unit 42 generates a description for product #1 based on a rule that indicates a writing style of a product listed on platform #1 by a user with the attribute "female in her 20s" and that sold within a predetermined period after being listed.

[0073] Furthermore, the generation unit 42 may generate the description based on rules indicating a writing style corresponding to the category to which the product listed by the user belongs. For example, in the example in Figure 1, the generation unit 42 generates the description #1 for product #1 based on rules such as those that specify that the description for product #1 should be generated in a writing style corresponding to the category of product #1.

[0074] Furthermore, the generation unit 42 may generate a description based on a rule that indicates the style of the description of a product in a category to which the product listed by the user belongs, and which is the style of the description of a product in that category that meets predetermined sales conditions on the platform. For example, in the example in Figure 1, the generation unit 42 generates description #1 for product #1 based on a rule that indicates the style of the description of a product in the category "Games" to which product #1 belongs that has been sold on platform #1 within a predetermined period of time since being listed.

[0075] Furthermore, the generation unit 42 may generate the description based on rules indicating a writing style corresponding to the time of year when the user lists the product. For example, in the example in Figure 1, the generation unit 42 generates the product description based on rules indicating a writing style corresponding to the season in which the product is used and the season in which the product is listed.

[0076] Furthermore, the generation unit 42 may generate the description based on rules indicating the number of characters in the description. For example, in the example in Figure 1, the generation unit 42 generates the description for product #1 within the character range defined on platform #1, within the character range specified by user U1, or within the character range of the description for a product whose sales status on platform #1 meets predetermined conditions.

[0077] Furthermore, the generation unit 42 may generate the description based on rules that indicate strings to be excluded from the description. For example, in the example in Figure 1, the generation unit 42 generates the description of product #1 without including strings that are contrary to public order and morals, or strings specified by the operator managing platform #1.

[0078] Furthermore, the generation unit 42 may generate a description based on rules indicating information that should not be included in the description from the product information received by the reception unit 41. For example, in the example in Figure 1, when the generation unit 42 generates a description for product #1 based on a rule indicating that the list price of the product should not be included in the description, if the product information for product #1 includes the list price of product #1, it generates a description for product #1 without including the list price of product #1.

[0079] Furthermore, the generation unit 42 may generate a description based on rules indicating which information to include in the description from the product information received by the reception unit 41. For example, in the example in Figure 1, when the generation unit 42 generates a description for product #1 based on a rule indicating that the product condition should be included in the description, it generates a description for product #1 that includes the condition "unused".

[0080] Furthermore, the generation unit 42 may generate a description based on rules indicating the writing style of descriptions entered by the user for products previously listed. For example, in the example in Figure 1, the generation unit 42 generates a description for product #1 based on rules indicating the writing style of descriptions entered by user U1 in the past.

[0081] Furthermore, the generation unit 42 may generate a description based on a rule indicating that it should include information about the user's preferences. For example, in the example in Figure 1, the generation unit 42 estimates the user's preferences based on the user's usage history of various services, such as search queries entered by the user U1 in a search service, or content viewed by the user U1 in a news service, and generates a description of product #1 that includes information indicating the estimated preferences of the user U1.

[0082] Furthermore, the generation unit 42 may generate a description based on a rule indicating that it should include information regarding the rarity of the product. For example, in the example in Figure 1, the generation unit 42 estimates the rarity of product #1 based on information regarding products related to product #1 that are sold on platform #1 or other e-commerce services, and generates a description of product #1 that includes the estimated rarity information.

[0083] Furthermore, the generation unit 42 may generate a description based on rules indicating a writing style corresponding to the sales history of the category to which the product belongs on the platform. For example, in the example in Figure 1, the generation unit 42 generates a description for product #1 based on rules based on statistical information indicating the trends of products that tend to sell well in the category to which product #1 belongs.

[0084] Furthermore, the generation unit 42 may generate the description based on rules that indicate the writing style corresponding to the viewer of the product and related products on the platform. For example, in the example in Figure 1, the generation unit 42 generates the description of product #1 based on rules that indicate the writing style corresponding to the most frequent attribute among the attributes of users who viewed product #1 and related products.

[0085] Furthermore, the generation unit 42 may generate a description based on a rule that indicates the inclusion of contextual information when the user purchased the product. For example, in the example in Figure 1, the generation unit 42 generates a description of product #1, including contextual information when user U1 purchased product #1 on platform #1 or other e-commerce services.

[0086] Furthermore, the generation unit 42 may generate a description based on a rule that indicates the inclusion of information regarding the purchase of products having a predetermined relationship with the user's product. For example, in the example in Figure 1, if user U1 purchases product #1 after purchasing product #2, which is an older model of a product related to product #1, on platform #1 or other e-commerce services, the generation unit 42 generates a description of product #1 that includes the string "This is a replacement for product #2." Also, if user U1 purchases product #1 after purchasing product #3, which is a newer model of a product related to product #1, on platform #1 or other e-commerce services, the generation unit 42 generates a description of product #1 that includes the string "This is a replacement for product #3."

[0087] Alternatively, the generation unit 42 may generate a description by inputting the product information received by the reception unit 41, a sentence indicating the rule corresponding to the product information, and an instruction sentence instructing the model to output a description of the product indicated by the product information according to the rule. For example, in the example in Figure 1, the generation unit 42 generates a description by inputting the product information displayed in area AR21, the rule corresponding to the product information, and an instruction sentence instructing the model to output a description of product #1 indicated by the product information according to the rule into model #1.

[0088] (Regarding output section 43) The output unit 43 outputs the explanatory text generated by the generation unit 42 to the user. For example, in the example in Figure 1, the output unit 43 outputs explanatory text #1 to the user terminal 100.

[0089] [4. Information Processing Flow] The information processing procedure of the information processing device 10 according to the embodiment will be explained using Figure 5. Figure 5 is a flowchart showing an example of the information processing procedure according to the embodiment.

[0090] As shown in Figure 5, the information processing device 10 determines whether or not it has received product information from the user regarding the product the user is listing on a platform where other users can purchase the product the user has listed (step S101). If product information has not been received (step S101; No), the information processing device 10 waits until product information is received.

[0091] On the other hand, if product information is received (Step S101; Yes), the information processing device 10 generates a description by inputting the received product information into a model that has been trained to output a description of the product indicated by the input product information, based on the input product information and the rules corresponding to the input product information (Step S102). Subsequently, the information processing device 10 outputs the generated description to the user (Step S103) and terminates the process.

[0092] [5. Variations] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0093] [5-1. Regarding the processing method] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above text and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0094] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0095] Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

[0096] [6. Effects] As described above, the information processing device 10 according to the embodiment includes a receiving unit 41, a generation unit 42, and an output unit 43. The receiving unit 41 receives product information from a user regarding a product that the user has listed for sale on a platform where other users purchase the product the user has listed. The generation unit 42 generates a description by inputting the product information received by the receiving unit 41 to a model that has been trained to output a description of the product indicated by the input product information, based on the input product information and the rules corresponding to the input product information. The generation unit 42 also generates a description by inputting the product information received by the receiving unit 41, a sentence indicating the rules corresponding to the product information, and an instruction sentence instructing the model to output a description of the product indicated by the product information according to the rules. The output unit 43 outputs the description generated by the generation unit 42 to the user.

[0097] As a result, the information processing device 10 according to this embodiment can output a product description based on the product information received from the user, thereby assisting the user in creating a product description for an item they are listing.

[0098] Furthermore, in the information processing device 10 according to this embodiment, for example, the reception unit 41 receives the user's answers to questions about the products the user is listing as product information. The reception unit 41 also receives product information extracted from images of the products the user is listing.

[0099] As a result, the information processing device 10 according to this embodiment can receive product information from users by various methods, thereby improving convenience.

[0100] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates an explanatory text based on rules specified by the user.

[0101] As a result, the information processing device 10 according to this embodiment can generate product descriptions based on rules arbitrarily specified by the user, and thus can generate descriptions that meet the user's needs.

[0102] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates an explanatory text based on a rule that indicates a predetermined writing style.

[0103] As a result, the information processing device 10 according to this embodiment can generate product descriptions based on various writing styles, thereby improving convenience.

[0104] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules that indicate the style of the product description when the context in which the product is sold on the platform satisfies predetermined conditions.

[0105] As a result, the information processing device 10 according to this embodiment can generate descriptions that meet the user's needs, such as wanting to sell the product quickly or wanting to sell it at a high price, thus enabling the generation of descriptions suitable for users who list products for sale.

[0106] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules that indicate the style of the description of a product purchased on the platform by a buyer who meets predetermined conditions.

[0107] As a result, the information processing device 10 according to this embodiment can generate a description that is suitable for the user who is listing the product, in order to meet the user's needs, such as what kind of users the user wants to sell the product to.

[0108] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a descriptive text based on a rule indicating a writing style corresponding to a user having predetermined attributes. The generation unit 42 also generates a descriptive text based on a rule indicating a writing style corresponding to the user's attributes. Furthermore, the generation unit 42 generates a descriptive text based on a rule indicating a writing style corresponding to the user's attributes and for a product whose sales status on the platform satisfies predetermined conditions.

[0109] As a result, the information processing device 10 according to the embodiment can generate explanatory text according to the user's attributes, thereby improving convenience.

[0110] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on a rule indicating a writing style corresponding to the category to which the product listed by the user belongs. The generation unit 42 also generates a description based on a rule indicating a writing style corresponding to the category to which the product listed by the user belongs, and which indicates a writing style for the description of a product in that category whose sales status on the platform meets predetermined conditions.

[0111] As a result, the information processing device 10 according to the embodiment can generate descriptive text according to the product category, thereby improving convenience.

[0112] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a descriptive text based on rules indicating a writing style corresponding to the time when the user lists the product.

[0113] As a result, the information processing device 10 according to the embodiment can generate a description that corresponds to the relationship between the product and the time when the product is listed for sale, thereby improving convenience.

[0114] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on a rule indicating the number of characters in the description. The generation unit 42 also generates a description based on a rule indicating strings not to be included in the description. The generation unit 42 also generates a description based on a rule indicating information not to be included in the description from the information indicated by the product information received by the reception unit 41. The generation unit 42 also generates a description based on a rule indicating information to be included in the description from the information indicated by the product information received by the reception unit 41.

[0115] As a result, the information processing device 10 according to the embodiment can generate a description in accordance with the regulations of the platform on which the product is listed and the requests of the user, thereby improving convenience.

[0116] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules that indicate the style of the description entered by the user for products previously listed for sale.

[0117] As a result, the information processing device 10 according to this embodiment can generate a new explanatory text based on the explanatory text entered by the user, thereby generating an explanatory text that is natural and comfortable for the user.

[0118] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a descriptive text based on a rule indicating that it includes information about the user's preferences. The generation unit 42 also generates a descriptive text based on a rule indicating that it includes information about the rarity of the product. The generation unit 42 also generates a descriptive text based on a rule indicating that it includes information based on the context in which the user purchased the product. The generation unit 42 also generates a descriptive text based on a rule indicating that it includes information about the user's purchase of products that have a predetermined relationship with the product.

[0119] As a result, the information processing device 10 according to this embodiment can include various types of information in the explanatory text, thereby enriching the content of the explanatory text.

[0120] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a descriptive text based on rules indicating a writing style corresponding to the sales history of the category to which the product belongs on the platform.

[0121] As a result, the information processing device 10 according to this embodiment can generate a descriptive text based on statistics in the product category, and therefore can generate an appropriate descriptive text for the product.

[0122] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates descriptive text based on rules that indicate the writing style corresponding to the product and related product viewers on the platform.

[0123] As a result, the information processing device 10 according to this embodiment can generate a description tailored to the viewer who is browsing the product being offered and related products, thus enabling the generation of a highly persuasive description.

[0124] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a descriptive text based on a rule that indicates the inclusion of information based on the context in which the user purchased the product.

[0125] [7. Hardware Configuration] Furthermore, the information processing device 10 according to each embodiment described above can be implemented by a computer 1000 having a configuration such as that shown in Figure 6. The following explanation will use the information processing device 10 as an example. Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10. The computer 1000 has a CPU 1100, ROM 1200, RAM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0126] The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400, and controls various parts. The ROM 1200 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0127] The HDD 1400 stores programs executed by the CPU 1100, as well as data used by such programs. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to network N in this embodiment) and sends it to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0128] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the data it generates to output devices via the input / output interface 1600.

[0129] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1300. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1300 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0130] For example, when computer 1000 functions as information processing device 10, the CPU 1100 of computer 1000 realizes the functions of control unit 40 by executing programs loaded on RAM 1300. The HDD 1400 stores the data from the storage device of information processing device 10. The CPU 1100 of computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0131] [8. Other] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0132] Furthermore, the configuration of the aforementioned information processing device 10 can be flexibly changed, for example, by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, depending on the function.

[0133] Furthermore, the term "part" in the claims can be replaced with "means," "circuit," etc. For example, "reception part" can be replaced with "reception means" or "reception circuit." [Explanation of symbols]

[0134] 10 Information Processing Devices 20 Communications Department 30 Storage section 31. User Information Database 32 Rule Database 33 Model Databases 40 Control Unit 41 Reception Department 42 Generation part 43 Output section 100 User Terminals

Claims

1. In a platform where users list items for sale and other users purchase them, there is a reception department that receives product information from users regarding the items they list, A generation unit generates a description by inputting the product information received by the reception unit, the rules indicated by the rule information corresponding to the application conditions that apply to the product information among the multiple pre-prepared rule information and their application conditions, and an instruction sentence that instructs the model to output a product description from the product information according to the rule, into a model trained to output an answer to an input question. An output unit that outputs the explanatory text generated by the generation unit to the user. It has, The aforementioned reception unit is Furthermore, the platform accepts requests from users for context regarding the sale of the product on the platform. The generating unit is Based on the aforementioned rules and the rules indicating the style of product descriptions that satisfy the requirements when sold on the platform, a description is generated. An information processing device characterized by the following:

2. The generating unit is Based on the aforementioned rules and the rules specified by the user, the explanatory text is generated. The information processing apparatus according to feature 1.

3. The generating unit is Based on the aforementioned rules and rules indicating a predetermined writing style, an explanatory text is generated. The information processing apparatus according to feature 1.

4. The generating unit is Based on the aforementioned rules and rules indicating the writing style of product descriptions purchased on the platform by buyers who meet certain conditions, a description is generated. The information processing apparatus according to feature 1.

5. The generating unit is Based on the aforementioned rules and rules indicating a writing style corresponding to a user with predetermined attributes, an explanatory text is generated. The information processing apparatus according to feature 1.

6. The generating unit is Based on the aforementioned rules and the rules indicating the writing style corresponding to the user's attributes, an explanatory text is generated. The information processing apparatus according to feature 1.

7. The generating unit is Based on the aforementioned rules and a rule indicating a writing style corresponding to the user's attributes, which is the writing style for product descriptions where the sales status on the platform meets predetermined conditions, a description is generated. The information processing apparatus according to feature 1.

8. The receiving unit is The product information indicating the category to which the aforementioned product belongs is received, The generating unit is Based on the rule information corresponding to the applicable conditions for the category indicated by the product information, and the rule indicating the style, a descriptive text is generated. The information processing apparatus according to feature 1.

9. The receiving unit is The product information indicating the category to which the aforementioned product belongs is received, The generating unit is Based on the rule information corresponding to the applicable conditions for the category indicated by the product information, which indicates the style of the product description for a product in that category whose sales status on the platform meets predetermined conditions, the description is generated. The information processing apparatus according to feature 1.

10. The generating unit is Based on the aforementioned rules and rules indicating the writing style corresponding to the time when the user lists the product, a description is generated. The information processing apparatus according to feature 1.

11. The generating unit is Based on the aforementioned rules and the rules indicating the number of characters in the description, the description is generated. The information processing apparatus according to feature 1.

12. The generating unit is Based on the aforementioned rules and the rules indicating strings to be excluded from the description, the description is generated. The information processing apparatus according to feature 1.

13. The generating unit is Based on the aforementioned rules and the rules that specify which information from the product information should not be included in the description, the description is generated. The information processing apparatus according to feature 1.

14. The generating unit is Based on the aforementioned rules and the rules that specify which information from the product information should be included in the description, the description is generated. The information processing apparatus according to feature 1.

15. The generating unit is Based on the aforementioned rules and the rules indicating the writing style of the descriptions entered by the user for items previously listed, a description is generated. The information processing apparatus according to feature 1.

16. The generating unit is Based on the aforementioned rules and the rules indicating that information regarding the user's preferences should be included, an explanatory text is generated. The information processing apparatus according to feature 1.

17. The generating unit is Based on the aforementioned rules and the rule indicating that information regarding the rarity of the product should be included, a description is generated. The information processing apparatus according to feature 1.

18. The generating unit is Based on the aforementioned rules and the rules indicating the writing style corresponding to the sales history of the category to which the product belongs on the platform, a description is generated. The information processing apparatus according to feature 1.

19. The generating unit is Based on the aforementioned rules and the rules on the platform that indicate the writing style appropriate for viewers of the product and related products, a description is generated. The information processing apparatus according to feature 1.

20. The generating unit is Based on the aforementioned rules and a rule indicating that the user should include contextual information about when the user purchased the product, a description is generated. The information processing apparatus according to feature 1.

21. The generating unit is Based on the aforementioned rules and a rule indicating that the user's purchase of products having a predetermined relationship with the aforementioned product, a description is generated. The information processing apparatus according to feature 1.

22. The aforementioned reception unit is The system accepts the user's answers to questions regarding the products they list as product information. The information processing apparatus according to feature 1.

23. The aforementioned reception unit is The system accepts product information extracted from images of products listed by the aforementioned user. The information processing apparatus according to feature 1.

24. A method of information processing performed by a computer, In a platform where users list items for sale and other users purchase them, there is a process for receiving product information from users regarding the items they list, A generation process for generating a description text involves inputting the product information received in the aforementioned reception process, the rules indicated by the rule information corresponding to the application conditions that apply to the product information among the multiple pre-prepared rule information and their application conditions, and an instruction sentence that instructs the model to output a product description text from the product information according to the rule, into a model trained to output an answer text in response to an input question text. Output step for outputting the explanatory text generated by the above generation step to the user; Includes, The aforementioned reception process is, Furthermore, the platform accepts requests from users for context regarding the sale of the product on the platform. The aforementioned generation step is Based on the aforementioned rules and the rules indicating the style of product descriptions that satisfy the requirements when sold on the platform, a description is generated. An information processing method characterized by the following:

25. In a platform where users list items for sale and other users purchase them, the process involves receiving product information from users regarding the items they list. A generation procedure for generating a description text involves inputting the product information received through the aforementioned reception procedure, the rules indicated by the rule information corresponding to the application conditions that apply to the product information among the multiple pre-prepared rule information and their application conditions, and an instruction sentence that instructs the model to output a product description text from the product information according to the rule, into a model trained to output an answer text in response to an input question text. Output procedure for outputting the explanatory text generated by the above generation procedure to the user, Have the computer run it, The aforementioned registration procedure is as follows: Furthermore, the platform accepts requests from users for context regarding the sale of the product on the platform. The aforementioned generation procedure is: Based on the aforementioned rules and the rules indicating the style of product descriptions that satisfy the requirements when sold on the platform, a description is generated. An information processing program characterized by the following features.

Images