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 device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known techniques for managing product information in electronic commerce services. One example of such a technique is to store information on products currently being offered at an online shop in an inventory table of a database, obtain listing information of other sellers who are offering the same product as the one being offered based on the ISBN code in the inventory table, calculate one's own listing price based on the listing prices of the other sellers, and change the listing price. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-4518 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional techniques are not necessarily able to assist users in creating descriptions for items they put up for sale.

[0005] For example, the above-mentioned conventional technology merely changes the selling price based on the selling prices of other sellers, and does not necessarily assist users in creating descriptions of the items they are selling.

[0006] The present application has been made in consideration of the above, and aims to support users in creating descriptions of products they list. [Means for solving the problem]

[0007] The information processing device of the present application is characterized in that it has a reception unit that receives product information about products listed by a user from a user on a platform where other users purchase products listed by the user, a generation unit that generates a description by inputting the product information received by the reception unit 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 rules corresponding to the input product information when product information is input, and an output unit that outputs the description generated by the generation unit to the user. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to provide an effect of assisting a user in creating a description of an item to be put up for sale. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of the user information database 31. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing an example of the rule database 32. As shown in FIG. [Diagram 5] FIG. 5 is a flowchart illustrating an example of a procedure of information processing according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. As shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0011] 1. Embodiment The information processing realized by the information processing device etc. of the present embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the information processing according to the embodiment. Note that in Fig. 1, the information processing etc. according to the embodiment is realized by an information processing device 10 which is an example of the information processing according to the present embodiment.

[0012] As shown in Fig. 1, an information processing system 1 according to an 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 Fig. 2, for example) so as to be able to communicate with each other by wire or wirelessly. The network N is, for example, a Wide Area Network (WAN) such as the Internet. Note that the information processing system 1 shown in Fig. 1 may include a plurality of information processing devices 10 and a plurality of user terminals 100.

[0013] 1 is an information processing device that performs information processing, and is realized by, for example, a server device, a cloud system, etc. For example, the information processing device 10 provides a platform #1 (for example, an electronic commerce service such as a flea market service or an auction service) where other users can purchase products that users have put up for sale, and accepts registration of various information (for example, information on products that users put up for sale) for the platform from users.

[0014] The information processing device 10 may have a function as a web server that provides websites related to various services including services related to the platform #1. The information processing device 10 may also be a device that distributes information to be displayed on applications related to various services installed in the user terminal 100 to the user terminal 100. The information processing device 10 may also 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 described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 10 may be regarded as the control information.

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

[0017] An example of information processing performed by information processing device 10 will be described below with reference to FIG. 1. In the following description, it is assumed that user terminal 100 is used by a user (user U1) identified by user ID "UID#1." In the following description, user terminal 100 may be regarded as the same as user U1. In other words, in the following description, user U1 may also be read as user terminal 100.

[0018] First, the information processing device 10 accepts product information on the product #1 that the user U1 puts up for sale on the platform #1 from the user terminal 100 (step S1). For example, the information processing device 10 accepts information entered on a screen C1 provided to the user terminal 100 via the platform #1 as product information for the product #1. As a specific example, the information processing device 10 accepts product information including information such as an image (product image) of the product #1, the name (product title), category, brand, specification information (e.g., the color, size, target age, etc. of the product #1), and condition (e.g., "unused" or "no noticeable scratches or stains"), etc.

[0019] Here, in the example of FIG. 1, it is assumed that the user U1 performs an operation on the user terminal 100 to the effect that he / she wishes to generate a description (product description) of the product #1 using a predetermined model (for example, pressing the "Generate product description" button on the screen C1). In such a case, the information processing device 10 generates a description of the product #1 using the product information of the product #1 inputted on the screen C1 and the model #1 (step S2). For example, when product information is inputted, the information processing device 10 generates a description of the product #1 by inputting the product information of the product #1 to the model #1 that has been trained to output a description of the product indicated by the inputted product information based on the inputted product information and the rules corresponding to the inputted product information (in other words, the rules for generating a description, such as the tendency and structure of the description generated by the model #1 from the prompts inputted to the model #1).

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

[0021] Here, it is assumed that user U1 desires 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 a description by inputting the product information displayed in area AR21, a rule corresponding to the product information, and an instruction sentence instructing to output a description of product #1 indicated by the product information in accordance with the rule to model #1. For example, the information processing device 10 generates description #1 of product #1 based on rules and the like that stipulate to generate a description of product #1 in a style corresponding to the product information (e.g., product title, category, etc.) displayed in area AR21.

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

[0023] Model #1 is a model trained to output an answer sentence (explanation sentence) corresponding to an input question sentence (instruction sentence), and is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). Model #1 is in information processing device 10 and was created independently by the business entity that manages platform #1. It is preferable that input information such as personal information is kept secret by training it so that it is not used as a new answer.

[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 causes the user terminal 100 to display a screen C3 showing the description #1. Then, the user U1 performs an operation to list the product #1 on the platform #1 using the description #1 that the user U1 has modified or added to.

[0025] The information processing device 10 may receive product information on a product from a user in a conversational format and generate an explanatory text. For example, the information processing device 10 provides the user terminal 100 with a screen C4 via the platform #1. The information processing device 10 then displays a message regarding the provision of product information in the area AR41 and receives the user's response to the message (for example, an image P41 that is a product image, a product title "EE sneakers blue", and a category "women's sneakers") as product information. The information processing device 10 then displays in the area AR42 an explanatory text generated based on the product information in the area AR41. The information processing device 10 also displays in the area AR43 buttons for receiving an instruction from the user to correct the explanatory text displayed in the area AR42 (for example, an "Add this" button for instructing the user to add product information, a "More details" button for instructing the user to change the writing style, etc.).

[0026] As described above, the information processing device 10 according to the embodiment outputs a description of a product indicated by the product information based on the product information received from a user. This allows the information processing device 10 according to the embodiment to support the user in creating a description of a product to be put up for sale.

[0027] In addition, a user who puts up an item for sale on an auction service or a flea market service for the first time may not know what to write in the description. In response to this, the information processing device 10 according to the embodiment can generate a description suitable for the item or a description that will sell well and output it to the user, so that the user who puts up an item for the first time can be given a guideline for creating a description.

[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 information. In this regard, examples are listed below.

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

[0030] Furthermore, the information processing device 10 may receive a request from the user U1 when generating a description of the product #1. Then, the information processing device 10 may generate a description of the product #1 based on a rule corresponding to the received request.

[0031] [2-2. Rules according to the product sales context] In the example of FIG. 1, the information processing device 10 may generate a description of the product #1 based on rules indicating the style of the description of a product whose context when sold on the platform #1 satisfies a predetermined condition. For example, when a request such as "I want to sell the product #1 within a predetermined period (e.g., one week)" is received from the user U1, the information processing device 10 generates a description of the product #1 based on rules indicating the style of the description of a product related to the product #1 that has been put up for sale on the platform #1 within a predetermined period. Also, for example, when a request such as "I want to sell the product #1 for a predetermined price (e.g., 1000 yen) or more" is received from the user U1, the information processing device 10 generates a description of the product #1 based on rules indicating the style of the description of a product related to the product #1 that has been sold on the platform #1 for a predetermined price or more.

[0032] [2-3. Rules for different buyers] In the example of Fig. 1, the information processing device 10 may generate a description of product #1 based on rules indicating the style of description of a product purchased on platform #1 by a purchaser who satisfies a predetermined condition. For example, when a request is received from user U1 to sell to a user with the attribute "woman in her 20s", the information processing device 10 generates a description of product #1 based on rules indicating the style of description of a product purchased on platform #1 by the attribute "woman in her 20s" among products related to product #1.

[0033] [2-4. Rules according to user attributes] In the example of Fig. 1, the information processing device 10 may generate a description of the product #1 based on a rule indicating a writing style corresponding to a user having a predetermined attribute. For example, when a rule such as "a writing style likely to be written by a woman" is accepted from the user U1, the information processing device 10 generates a description of the product #1 based on a rule indicating a writing style of a description inputted on the platform #1 by a user having the attribute "woman".

[0034] The information processing device 10 may generate the description of the product #1 based on a rule indicating a writing style corresponding to the attribute of the user U1. For example, if the attribute of the user U1 is "female in 20s", the information processing device 10 generates the description of the product #1 based on a rule indicating a writing style of a description entered by a user having the attribute "female in 20s" for a product put up for sale on the platform #1.

[0035] Furthermore, the information processing device 10 may generate a description of product #1 based on a rule indicating a writing style of a description of a product whose sales situation on platform #1 satisfies a predetermined condition and corresponds to the attribute of user U1. If the attribute of user U1 is "female in 20s", the information processing device 10 generates a description of product #1 based on a rule indicating a writing style of a description of a product that is listed on platform #1 by a user having the attribute "female in 20s" and that has sold within a predetermined period of time since being listed.

[0036] [2-5. Rules for when to list] In the example of Fig. 1, the information processing device 10 may generate a description based on a rule indicating a writing style corresponding to the season in which the product is put up for sale. For example, the information processing device 10 generates a description of the product based on a rule indicating a writing style according to the correspondence between the season in which the product is used and the season in which the product is put up for sale. As a specific example, when the product "electric fan" is put up for sale in the summer, the information processing device 10 generates a description including a sentence such as "Perfect for this season."

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

[0038] [2-7. Prohibition of use of specified character strings] 1, the information processing device 10 may generate a description of the product #1 based on a rule indicating a character string that is not to be included in the description. For example, the information processing device 10 generates a description of the product #1 without including a character string that is contrary to public order and morals, a character string determined by a business operator that manages the platform #1 (for example, a character string indicating another business operator), and the like.

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

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

[0041] [2-9. Generating explanatory text based on the user's writing style] In the example of Fig. 1, the information processing device 10 may generate a description of product #1 based on a description entered by user U1 for a product previously listed on platform #1. For example, the information processing device 10 generates a description of product #1 based on rules indicating the style of descriptions previously entered by user U1. In addition, the information processing device 10 generates a description of product #1 including predetermined information (e.g., delivery method) written in the description previously entered by user U1.

[0042] [2-10. Generating explanatory text based on information for a given service] In the example of Fig. 1, the information processing device 10 may generate a description of the product #1 based on a rule indicating inclusion of information related to the preferences of the user U1. For example, the information processing device 10 estimates the preferences (in other words, interests and concerns) of the user U1 based on the usage history of the user U1 of various services, such as a search query input by the user U1 in a search service or the like, or content viewed by the user U1 in a news service or the like, and generates a description of the product #1 including information indicating the estimated preferences of the user U1.

[0043] In the example of FIG. 1, the information processing device 10 may generate a description of the product #1 based on a rule indicating inclusion of information on the rarity of the product #1. For example, the information processing device 10 estimates the rarity of the product #1 based on information on products related to the product #1, which are products sold on the platform #1 or other electronic commerce services, and generates a description of the product #1 including information on the estimated rarity. As a specific example, when a product related to the product #1 is being sold at a price higher than the list price on the platform #1, the information processing device 10 generates a description of the product #1 including information indicating that the product #1 is highly rare. Furthermore, when a product related to the product #1 is out of stock on other electronic commerce services, the information processing device 10 generates a description of the product #1 including information indicating that the product #1 is highly rare.

[0044] The information processing device 10 may collect information other than the above from various services and include it in the product description. For example, when the product put up for sale by the user is a product with little information, such as a handmade product or a product with a high hobby-like nature, the information processing device 10 collects information to supplement the information about the product from various services and generates a description of the product including the collected information.

[0045] [2-11. Generating product descriptions according to the category to which the product belongs] In the example of Fig. 1, the information processing device 10 may generate a description of the product #1 based on rules indicating a writing style corresponding to the sales history of the category to which the product #1 belongs on the platform #1. For example, the information processing device 10 generates a description of the product #1 based on rules based on statistical information indicating a tendency of products that are likely to sell well in the category to which the product #1 belongs (for example, products that sell well within a predetermined period after being put up for sale). As a specific example, the information processing device 10 generates a description of the product #1 based on rules indicating a writing style of the description of a product that sells well in the category to which the product #1 belongs.

[0046] [2-12. About generating descriptions according to products related to products] In the example of FIG. 1, the information processing device 10 may generate a description of the product #1 based on a writing style corresponding to the viewers of the products related to the product #1. For example, the information processing device 10 generates a description of the product #1 based on a rule indicating a writing style corresponding to the most common attribute among the attributes of users who viewed the products related to the product #1. To give a specific example, if the proportion of users with the attribute "women in their twenties" is the highest among the users who viewed the products related to the product #1, the information processing device 10 generates a description of the product #1 in the writing style of a product that is likely to sell to users with the attribute "women in their twenties" on the platform #1 (for example, a description of a product that sold within a predetermined period of time).

[0047] [2-13. Creating descriptions that correspond to the context of the product you are selling] In the example of Fig. 1, the information processing device 10 may generate a description of the product #1 based on a rule indicating inclusion of information based on the context when the user U1 purchased the product #1. For example, the information processing device 10 generates a description of the product #1 including information based on the context when the user U1 purchased the product #1 on the platform #1 or another electronic commerce service. As a specific example, the information processing device 10 generates a description of the product #1 including information indicating when, where, and for how much the user U1 purchased the product #1.

[0048] [2-14. Generating explanatory text in response to the purchase of a product with a specified relevance] In the example of FIG. 1, the information processing device 10 may generate a description of product #1 based on a rule indicating inclusion of information regarding the purchase of a product that has a predetermined relationship with product #1 and that was purchased by user U1. For example, if user U1 purchases product #1 after purchasing product #2, which is an outdated product related to product #1, on platform #1 or other electronic commerce services, the information processing device 10 generates a description of product #1 including a character 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 product related to product #1, on platform #1 or other electronic commerce services, the information processing device 10 generates a description of product #1 including a character string such as "This is a replacement for product #3."

[0049] [2-15. Extracting information from images] 1, the information processing device 10 may accept information extracted from an image of product #1 as product information, instead of accepting product information input by user U1. For example, the information processing device 10 accepts product information indicating the product title, category, brand, specification information, condition, etc. of product #1 extracted from an image of product #1 from the user terminal 100. Note that the information processing device 10 may accept an image of product #1 from the user terminal 100 and extract product information from the image.

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

[0051] (Regarding communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC) etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100 etc.

[0052] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 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 related to users. An example of the information stored in the user information database 31 will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the user information database 31. In the example of Fig. 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 for identifying a user. "Attribute information" indicates the user's attributes (e.g., demographic attributes and psychographic attributes). "Usage history" indicates the user's usage history for various services. "Purchase information" indicates information about products purchased by the user on platform #1 or other e-commerce services, and stores information such as the product name, category, price, and purchase date and time. "Listed product information" indicates information about products listed by the user on platform #1, and includes items such as "product ID," "product information," "description," and "sales status."

[0055] "Product ID" indicates identification information for identifying a product. "Product information" indicates information related to the product. "Description" indicates a description of the product. "Sales status" indicates the status related to the sales status of the product, and stores information such as the date and time when the product was sold and the price at the time of sale.

[0056] That is, Figure 3 shows an example in which the attribute information of a user identified by a 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 the user is identified by a product ID "SID#1", the product information is "product information #1", the description is "description #1", and the sales status is "sales status #1".

[0057] (About Rule Database 32) The rule database 32 stores information about rules used when generating product descriptions. An example of information stored in the rule database 32 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the rule database 32. In the example of Fig. 4, the rule database 32 has items such as "rule ID", "rule information", and "application conditions".

[0058] "Rule ID" indicates identification information for identifying a rule. "Rule information" indicates information related to the rule, and stores information such as the style of the description and information to be included in the description. "Application conditions" indicates conditions for applying the rule indicated by the rule information, and stores information such as product information of the product to which the rule is applied and attribute information of the user who puts up the product.

[0059] That is, FIG. 4 shows an example in which the rule information of the rule identified by the rule ID "RID#1" is "rule information #1" and the application condition is "application condition #1".

[0060] (About model database 33) The model database 33 stores a model that has been trained to output a description of the product indicated by the input product information, when the product information is input, based on the input product information and a rule corresponding to the input product information.

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

[0062] (Regarding Reception Section 41) The reception unit 41 receives, from a user, product information on a product that the user puts up for sale on a platform where other users can purchase the product that the user puts up for sale. For example, in the example of FIG. 1, the reception unit 41 receives, from the user terminal 100, product information on a product #1 that a user U1 puts up for sale on the platform #1, and stores the product information in the user information database 31.

[0063] In addition, the reception unit 41 may receive, as product information, a user's response to a question about a product that the user is selling. For example, in the example of Fig. 1, the reception unit 41 provides a screen C4 via the platform #1, displays a message about the provision of product information, and receives the user's response to the message as product information.

[0064] The reception unit 41 may also receive product information extracted from an image of a product put up for sale by a user. For example, in the example of Fig. 1, the reception unit 41 receives product information indicating the product title, category, brand, specification information, condition, etc. of product #1 extracted from an image of product #1 from the user terminal.

[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 a rule corresponding to the input product information. For example, in the example of Fig. 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] The generation unit 42 may generate the description based on a rule specified by the user. For example, in the example of Fig. 1, the generation unit 42 receives a rule specification from the user U1 and generates a description of the product #1 based on the specified rule.

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

[0068] The generating unit 42 may generate the description based on a rule indicating the style of the description of a product whose context when sold on the platform satisfies a predetermined condition. For example, in the example of FIG. 1, when a request such as "I want to sell product #1 within a predetermined period" is received from user U1, the generating unit 42 generates the description of product #1 based on a rule indicating the style of the description of a product related to product #1 that has been put up for sale on platform #1 within a predetermined period. Also, when a request such as "I want to sell product #1 for a predetermined price or more" is received from user U1, the generating unit 42 generates the description of product #1 based on a rule indicating the style of the description of a product related to product #1 that has been sold on platform #1 for a predetermined price or more.

[0069] The generation unit 42 may generate the description based on rules indicating the style of description of a product purchased on the platform by a purchaser who satisfies a predetermined condition. For example, in the example of Fig. 1, when a request is received from user U1 to sell to a user with the attribute "woman in her 20s", the generation unit 42 generates a description of product #1 based on rules indicating the style of description of a product purchased on platform #1 by the attribute "woman in her 20s" among products related to product #1.

[0070] The generation unit 42 may generate a description based on a rule indicating a writing style corresponding to a user having a predetermined attribute. For example, in the example of Fig. 1, when a rule such as "a writing style likely to be written by a woman" is specified by the user U1, the generation unit 42 generates a description for the product #1 based on a rule indicating a writing style of a description input by a user having the attribute "woman" on the platform #1.

[0071] The generation unit 42 may generate the description based on a rule indicating a writing style corresponding to the attribute of the user. For example, in the example of Fig. 1, when the attribute of the user U1 is "female in 20s", the generation unit 42 generates the description of the product #1 based on a rule indicating a writing style of the description entered by the user having the attribute "female in 20s" for the product put up for sale on the platform #1.

[0072] The generation unit 42 may generate the description based on a rule indicating a style of description of a product whose sales situation on the platform satisfies a predetermined condition and corresponds to the attribute of the user. For example, in the example of Fig. 1, when the attribute of the user U1 is "female in 20s", the generation unit 42 generates the description of the product #1 based on a rule indicating a style of description of a product that is listed on the platform #1 by a user having the attribute "female in 20s" and that is sold within a predetermined period after being listed.

[0073] Furthermore, the generation unit 42 may generate a description based on a rule indicating a writing style corresponding to a category to which the product put up by the user belongs. For example, in the example of Fig. 1, the generation unit 42 generates a description #1 for the product #1 based on a rule that specifies that the description for the product #1 is to be generated in a writing style corresponding to the category of the product #1.

[0074] Furthermore, the generation unit 42 may generate a description based on a rule indicating a style of description of a product in a category that corresponds to the product put up for sale by the user and whose sales status on the platform satisfies a predetermined condition. For example, in the example of Fig. 1, the generation unit 42 generates description #1 for product #1 based on a rule indicating a style of description of a product in the category "games" to which product #1 belongs that has been sold within a predetermined period since being put up for sale on platform #1.

[0075] The generation unit 42 may generate a description based on a rule indicating a writing style corresponding to the season in which the user puts the product up for sale. For example, in the example of Fig. 1, the generation unit 42 generates a description of the product based on a rule indicating a writing style according to the correspondence between the season in which the product is used and the season in which the product is put up for sale.

[0076] The generating unit 42 may generate the description based on a rule indicating the number of characters of the description. For example, in the example of Fig. 1, the generating unit 42 generates the description of the product #1 within a character range defined by the platform #1, within a character range specified by the user U1, or within a character range of the description of the product whose sales situation on the platform #1 satisfies a predetermined condition.

[0077] The generating unit 42 may generate the description based on a rule indicating a character string that is not to be included in the description. For example, in the example of Fig. 1, the generating unit 42 generates the description of the product #1 without including a character string that is offensive to public order and morals, a character string determined by the business operator managing the platform #1, and the like.

[0078] Furthermore, the generation unit 42 may generate a description based on a rule indicating information not to be included in the description from among the information indicated by the product information accepted by the acceptance unit 41. For example, in the example of Fig. 1, when generating a description of product #1 based on a rule indicating that the list price of the product is not to be included in the description, if the list price of product #1 is included in the product information of product #1, the generation unit 42 generates a description of product #1 without including the list price of product #1.

[0079] Furthermore, the generation unit 42 may generate a description based on a rule indicating information to be included in the description from among the information indicated by the product information accepted by the acceptance unit 41. For example, in the example of Fig. 1, when generating a description for product #1 based on a rule indicating that the description should include the product's condition, the generation unit 42 generates a description for product #1 including the condition of product #1 being "unused."

[0080] The generation unit 42 may generate a description based on a rule indicating the style of a description input by a user for a product that the user has previously put up for sale. For example, in the example of FIG. 1, the generation unit 42 generates a description for product #1 based on a rule indicating the style of a description input by user U1 in the past.

[0081] The generating unit 42 may generate the description based on a rule indicating inclusion of information on the user's preferences. For example, in the example of Fig. 1, the generating unit 42 estimates the preferences of the user U1 based on the usage history of the user U1 of various services, such as a search query input by the user U1 in a search service or the like, and contents viewed by the user U1 in a news service or the like, and generates the description of the product #1 including information indicating the estimated preferences of the user U1.

[0082] The generating unit 42 may generate the description based on a rule indicating inclusion of information regarding the rarity of the product. For example, in the example of Fig. 1, the generating unit 42 estimates the rarity of the product #1 based on information regarding products related to the product #1 that are sold on the platform #1 or other electronic commerce services, and generates the description of the product #1 including information regarding the estimated rarity.

[0083] The generation unit 42 may generate the description based on a rule 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 of Fig. 1, the generation unit 42 generates the description of the product #1 based on a rule based on statistical information indicating the tendency of products that are likely to sell in the category to which the product #1 belongs.

[0084] The generation unit 42 may generate the description based on a rule indicating a writing style corresponding to viewers of products related to the product on the platform. For example, in the example of Fig. 1, the generation unit 42 generates the description of the product #1 based on a rule indicating a writing style corresponding to the most common attribute among the attributes of users who viewed the products related to the product #1.

[0085] The generation unit 42 may generate the description based on a rule indicating inclusion of information based on the context when the user purchased the product. For example, in the example of Fig. 1, the generation unit 42 generates the description of the product #1 including information based on the context when the user U1 purchased the product #1 on the platform #1 or another electronic commerce service.

[0086] The generating unit 42 may generate the explanatory text based on a rule indicating inclusion of information regarding the purchase of a product having a predetermined relationship with the user's product. For example, in the example of FIG. 1, if the user U1 purchases the product #1 after purchasing the product #2, which is an outdated product related to the product #1, on the platform #1 or another electronic commerce service, the generating unit 42 generates an explanatory text for the product #1 including a character string such as "This is a replacement for the product #2." If the user U1 purchases the product #1 after purchasing the product #3, which is a newer product related to the product #1, on the platform #1 or another electronic commerce service, the generating unit 42 generates an explanatory text for the product #1 including a character string such as "This is a replacement for the product #3."

[0087] Furthermore, the generation unit 42 may generate an explanatory text by inputting the product information received by the reception unit 41, a text indicating a rule corresponding to the product information, and an instruction text instructing to output an explanatory text of the product indicated by the product information in accordance with the rule, into a model. For example, in the example of Fig. 1, the generation unit 42 generates an explanatory text by inputting the product information displayed in the area AR21, a rule corresponding to the product information, and an instruction text instructing to output an explanatory text of the product #1 indicated by the product information in accordance with the rule, into the model #1.

[0088] (Regarding output unit 43) The output unit 43 outputs to the user the explanatory text generated by the generation unit 42. For example, in the example of FIG.

[0089] [4. Information processing flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0090] 5, the information processing device 10 determines whether or not product information on a product put up for sale by a user has been received from the user on a platform where other users can purchase the product put up for sale by the user (step S101). If the product information has not been received (step S101; No), the information processing device 10 waits until the product information is received.

[0091] On the other hand, when product information is received (step S101; Yes), the information processing device 10 generates a description by inputting the received product information to a model 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). Next, the information processing device 10 outputs the generated description to the user (step S103) and ends the process.

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

[0093] [5-1. Processing mode] Among 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 a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above text and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0094] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0095] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0096] 6. Effects As described above, the information processing device 10 according to the embodiment includes a receiving unit 41, a generating unit 42, and an output unit 43. The receiving unit 41 receives product information on a product put up by a user from the user on a platform where other users purchase the product put up by the user. The generating 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 a rule corresponding to the input product information when the product information is input. The generating unit 42 also generates a description by inputting the product information received by the receiving unit 41, a sentence indicating a rule corresponding to the product information, and an instruction sentence instructing to output a description of the product indicated by the product information according to the rule to the model. The output unit 43 outputs the description generated by the generating unit 42 to the user.

[0097] As a result, the information processing device 10 according to the embodiment can output a description of the product indicated by the product information based on the product information received from the user, thereby assisting the user in creating a description of the product to be listed.

[0098] In the information processing device 10 according to the embodiment, for example, the reception unit 41 receives, as product information, a user's answer to a question about a product that the user puts up for sale. In addition, the reception unit 41 receives product information extracted from an image of the product that the user puts up for sale.

[0099] As a result, the information processing device 10 according to the embodiment can receive product information from the user 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 a rule specified by the user.

[0101] As a result, the information processing device 10 according to the embodiment can generate a description of a product based on rules arbitrarily specified by a user, and can generate a description that meets the needs of the user.

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

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

[0104] In addition, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules indicating the style of the description of a product whose context when sold on the platform satisfies a predetermined condition.

[0105] As a result, the information processing device 10 according to the embodiment can generate a description that meets the user's needs, such as wanting to sell the product quickly or wanting to sell it for a high price, and can generate a description that is suitable for the user listing the product.

[0106] In addition, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules indicating the style of the description of a product purchased on a platform by a purchaser who satisfies a predetermined condition.

[0107] As a result, the information processing device 10 according to the embodiment can generate a description that meets the user's desires, such as the type of user to whom the user wishes to sell the product, and can generate a description that is suitable for the user listing the product.

[0108] In the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules indicating a writing style corresponding to a user having a predetermined attribute. The generation unit 42 generates a description based on rules indicating a writing style corresponding to the user's attribute. The generation unit 42 generates a description based on rules indicating a writing style of a description of a product whose sales situation on the platform satisfies a predetermined condition and corresponds to the user's attribute.

[0109] As a result, the information processing device 10 according to the embodiment can generate an explanation according to the attributes of the user, thereby improving convenience.

[0110] 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 a category to which an item listed by a user belongs. In addition, the generation unit 42 generates a description based on a rule indicating a writing style of a description of an item in a category to which an item listed by a user belongs, the sales status of which on the platform satisfies a predetermined condition.

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

[0112] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates a description based on rules indicating a writing style corresponding to the time when a user puts up an item for sale.

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

[0114] Also, 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. Also, the generation unit 42 generates a description based on a rule indicating character strings not to be included in the description. Also, the generation unit 42 generates a description based on a rule indicating information not to be included in the description among information indicated by the product information accepted by the acceptance unit 41. Also, the generation unit 42 generates a description based on a rule indicating information to be included in the description among information indicated by the product information accepted by the acceptance 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 in accordance with the request 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 indicating the style of descriptions entered by users for products that they have put up for sale in the past.

[0117] As a result, the information processing device 10 according to the embodiment can generate a new explanatory text based on the explanatory text input by the user, and can generate an explanatory text that does not seem strange to the user.

[0118] In the information processing device 10 according to the embodiment, for example, the generation unit 42 generates an explanatory text based on a rule indicating that information related to the user's preferences should be included. The generation unit 42 generates an explanatory text based on a rule indicating that information related to the rarity of the product should be included. The generation unit 42 generates an explanatory text based on a rule indicating that information based on the context when the user purchased the product should be included. The generation unit 42 generates an explanatory text based on a rule indicating that information related to the purchase of a product having a predetermined relevance to the user's product should be included.

[0119] As a result, the information processing device 10 according to the 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 description 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 the embodiment can generate an explanation based on statistics in a product category, and can generate an appropriate explanation for the product.

[0122] 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 viewers of products related to the product on the platform.

[0123] As a result, the information processing device 10 according to the embodiment can generate a description that is tailored to viewers who are viewing products related to the product being listed, thereby generating a description that is highly appealing.

[0124] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates an explanation based on a rule indicating that information based on the context at the time when the user purchased the product is to be included.

[0125] [7. Hardware Configuration] Moreover, the information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 6. The information processing device 10 will be described below as an example. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0126] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0127] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data 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 a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs data generated via the input / output interface 1600 to the output devices.

[0129] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), 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 the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 40. In addition, the HDD 1400 stores each piece of data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from another device via a predetermined communication network.

[0131] [8. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0132] Further, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing to realize some functions.

[0133] Furthermore, the term "unit" in the claims may be read as "means" or "circuit," etc. For example, a reception unit may be read as a reception means or a reception circuit. [Explanation of symbols]

[0134] 10. Information processing device 20 Communications Department 30 Storage section 31 User information database 32 Rules Database 33 Model Database 40 Control section 41 Reception 42 Generation part 43 Output section 100 User terminals

Claims

1. a receiving unit that receives product information related to a product that a user puts up for sale from the user in a platform where other users can purchase the product that the user puts up for sale; a generation unit that generates an explanatory text by inputting the product information received by the reception unit to a model that has been trained to output an explanatory text of a product indicated by the input product information based on the input product information and a rule corresponding to the input product information when the product information is input; an output unit that outputs the explanatory text generated by the generation unit to the user; 13. An information processing device comprising:

2. The generation unit is Generate an explanatory text based on rules specified by the user 2. The information processing apparatus according to claim 1,

3. The generation unit is Generate explanatory text based on predefined stylistic rules 2. The information processing apparatus according to claim 1,

4. The generation unit is Generate a description based on rules indicating a style of description of a product whose context when sold on the platform satisfies a predetermined condition 2. The information processing apparatus according to claim 1,

5. The generation unit is A description is generated based on rules indicating a style of description of a product purchased on the platform by a purchaser who satisfies a predetermined condition.

2. The information processing apparatus according to claim 1,

6. The generation unit is Generates explanatory text based on rules that indicate a writing style that corresponds to users with certain attributes 2. The information processing apparatus according to claim 1,

7. The generation unit is Generate an explanatory text based on rules indicating a writing style corresponding to the attributes of the user.

2. The information processing apparatus according to claim 1,

8. The generation unit is A description is generated based on rules indicating a style of description for a product whose sales situation on the platform satisfies a predetermined condition and corresponds to an attribute of the user.

2. The information processing apparatus according to claim 1,

9. The generation unit is Generate a description based on rules indicating a writing style corresponding to the category to which the product listed by the user belongs.

2. The information processing apparatus according to claim 1,

10. The generation unit is A description is generated based on a rule indicating a style of description for a product in a category to which the product put up for sale by the user belongs, the style being a style corresponding to the category, and the sales situation on the platform satisfies a predetermined condition.

2. The information processing apparatus according to claim 1,

11. The generation unit is Generate a description based on rules indicating a writing style corresponding to the time when the user puts the product up for sale.

2. The information processing apparatus according to claim 1,

12. The generation unit is Generate a description based on rules that indicate the length of the description 2. The information processing apparatus according to claim 1,

13. The generation unit is Generate a description based on rules that indicate what not to include in the description 2. The information processing apparatus according to claim 1,

14. The generation unit is A description is generated based on a rule indicating information that is not to be included in the description, among information indicated by the product information received by the receiving unit.

2. The information processing apparatus according to claim 1,

15. The generation unit is generating an explanatory text based on a rule indicating information to be included in the explanatory text among information indicated by the product information received by the receiving unit; 2. The information processing apparatus according to claim 1,

16. The generation unit is A description is generated based on rules indicating a style of description entered by the user for an item previously listed.

2. The information processing apparatus according to claim 1,

17. The generation unit is Generate a description based on rules indicating inclusion of information regarding the user's preferences.

2. The information processing apparatus according to claim 1,

18. The generation unit is Generate a description based on a rule indicating inclusion of information regarding the rarity of the product.

2. The information processing apparatus according to claim 1,

19. The generation unit is 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.

2. The information processing apparatus according to claim 1,

20. The generation unit is Generate a description based on rules indicating a writing style corresponding to viewers of the product and related products on the platform.

2. The information processing apparatus according to claim 1,

21. The generation unit is Generate a description based on rules indicating inclusion of information based on the context in which the user purchased the product.

2. The information processing apparatus according to claim 1,

22. The generation unit is Generate a description based on a rule indicating that the description should include information about the user's purchase of a product having a predetermined relationship with the product.

2. The information processing apparatus according to claim 1,

23. The generation unit is The user's response to a question regarding the product he or she is selling is accepted as product information.

2. The information processing apparatus according to claim 1,

24. The reception unit is Receive product information extracted from images of the products listed by the users 2. The information processing apparatus according to claim 1,

25. The generation unit is The product information accepted by the accepting unit, a sentence indicating a rule corresponding to the product information, and an instruction sentence instructing to output an explanation of the product indicated by the product information in accordance with the rule are input to the model, thereby generating an explanation.

25. An information processing apparatus according to claim 1, wherein the information processing apparatus comprises:

26. 1. A computer-implemented information processing method, comprising: A receiving step of receiving product information related to the product put up for sale by the user from the user on a platform where other users can purchase the product put up for sale by the user; a generation step of generating an explanatory text by inputting the product information received in the receiving step into a model trained to output an explanatory text of a product indicated by the input product information based on the input product information and a rule corresponding to the input product information when the product information is input; an output step of outputting the explanatory text generated by the generation step to the user; 13. An information processing method comprising:

27. A receiving step of receiving product information from a user regarding a product that the user has put up for sale on a platform where other users can purchase the product that the user has put up for sale; a generation step of generating an explanatory text by inputting the product information received in the reception step into a model trained to output an explanatory text of a product indicated by the input product information based on the input product information and a rule corresponding to the input product information when the product information is input; an output step of outputting the explanatory text generated by the generation step to the user; An information processing program for causing a computer to execute the above.

Images