Information processing system, information processing method, and information processing program

Abstract

This invention provides an information processing system, an information processing method, and an information processing program that can generate characters related to a target product. [Solution] The information processing system according to the present invention comprises: information acquisition means for acquiring information on a target product; generation processing means for inputting the information on the target product into a trained character generation model and acquiring information on a character related to the target product (hereinafter referred to as "target product character") from the trained character generation model; and information transmission means for transmitting the information on the target product character, wherein the trained character generation model acquires information on the target product, Includes advantages or superior points compared to other learning materials. It is characterized by being trained to generate information about the target product character based on information about each of the target product and information about each of the target character.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and an information processing program capable of generating a character related to a target product using AI.

Background Art

[0002] Conventionally, a method for generating a virtual character related to a user has been proposed (see, for example, Patent Document 1). In the method described in this document, a virtual character is generated by inputting a video clip received from a terminal used by the user into a machine learning model.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the method described in Patent Document 1 above, a virtual character can be generated based on the information of the video clip, but the generation of a character related to the target product is not considered.

[0005] In view of such circumstances, the present invention aims to provide an information processing system, an information processing method, and an information processing program capable of generating a character related to a target product.

Means for Solving the Problems

[0006] The information processing system according to the present invention comprises: information acquisition means for acquiring information on a target product; generation processing means for inputting the information on the target product into a trained character generation model and acquiring information on a character related to the target product (hereinafter referred to as "target product character") from the trained character generation model; and information transmission means for transmitting information on the target product character. The trained character generation model acquires information on multiple products different from the target product (hereinafter referred to as "learning target products") and information on multiple characters different from the target product character (hereinafter referred to as "learning target characters"), respectively. Includes advantages or superior points compared to other learning materials. This information processing system is characterized by having learned information about each of the aforementioned target products and information about each of the aforementioned target characters, and being trained to generate information about the target product characters based on the information about the target products, the information about each of the aforementioned target products, and the information about each of the aforementioned target characters.

[0007] The information processing method according to the present invention acquires information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the character related to the target product (hereinafter referred to as "target product character") (hereinafter referred to as "learning target character"), respectively. Includes advantages or superior points compared to other learning materials. Using a trained character generation model that has learned information about each of the aforementioned target products and information about each of the aforementioned target characters, and is trained to generate information about the target product characters based on the information about the target products, the information about each of the aforementioned target products and information about each of the aforementioned target characters ComputerAn information processing method to be executed, comprising: an information acquisition step of acquiring information about the target product; a generation processing step of inputting the information about the target product into the trained character generation model and acquiring information about the target product character from the trained character generation model; and an information transmission step of transmitting the information about the target product character.

[0008] The information processing program according to the present invention is a program for an information processing system, which causes a computer to acquire information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the character related to the said target product (hereinafter referred to as "target product character") (hereinafter referred to as "learning target character"), respectively. Includes advantages or superior points compared to other learning materials. This information processing program is characterized by comprising: a trained character generation model that learns information about each of the aforementioned target products and information about each of the aforementioned target characters, and is trained to generate information about the target product characters based on the information about the target products, the information about each of the aforementioned target products, and the information about each of the aforementioned target characters; an information acquisition means for acquiring information about the target products; a generation processing means for inputting the information about the target products into the trained character generation model and acquiring information about the target product characters from the trained character generation model; and an information transmission means for transmitting information about the target product characters. [Effects of the Invention]

[0009] The information processing system, information processing method, and information processing program according to the present invention can achieve the excellent effect of generating characters related to the target product. [Brief explanation of the drawing]

[0010] [Figure 1]This is a schematic diagram showing an overview of the information processing system 10 according to this embodiment. [Figure 2] This is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment. [Figure 3] This figure shows a point in time in the video of the generated product character. [Figure 4] This figure shows a point in time in the video of the generated product character. [Figure 5] This figure shows a point in time in the newly generated video of the target product character. [Modes for carrying out the invention]

[0011] The following describes an information processing system 10 according to an embodiment of the present invention with reference to the drawings.

[0012] <Overview of the Information Processing System> First, an overview of the information processing system 10 according to this embodiment will be described using Figure 1. Figure 1 is a schematic diagram showing an overview of the information processing system 10 according to this embodiment.

[0013] The information processing system 10 is a system configured with a system terminal 12 equipped with a trained character generation model 12c. The trained character generation model 12c acquires information about multiple products B2, B3, etc. (hereinafter referred to as "learning target products B2, B3, etc.") that are different from the target product B1, and information about multiple characters C2, C3, etc. (hereinafter referred to as "learning target characters C2, C3, etc.") that are different from the character C1 related to the target product B1 (hereinafter referred to as "target product character C1"), and learns information about each of the learning target products B2, B3, etc. and learning target characters C2, C3, etc. Furthermore, the trained character generation model 12c is trained to generate the target product character C1 based on the information about the target product B1, the information about each of the learning target products B2, B3, etc. and the information about the learning target characters C2, C3, etc. Furthermore, the information processing system 10 includes an information acquisition means 12a for acquiring information about the target product B1, a generation processing means 12b for inputting the information about the target product B1 into a trained character generation model 12c and acquiring information about the target product character C1 from the trained character generation model 12c, and an information transmission means 12d for transmitting information about the target product character C1.

[0014] According to the information processing system 10, it is possible to generate characters related to the target product.

[0015] <Example of system configuration> Next, an example of the configuration of the information processing system 10 according to this embodiment will be described using Figure 2. Figure 2 is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment.

[0016] The information processing system 10 can be configured, for example, to include a system terminal 12 that controls the entire system, and external terminals 16 that are connected to the system terminal 12 via a network NW so that they can communicate with each other.

[0017] The system terminal 12 is a terminal that controls the entire information processing system 10 and is composed of a conventionally known server, personal computer, or the like. In this example, the system terminal 12 is composed of one server, but it may also be composed of multiple servers, personal computers, or the like. The hardware configuration of the system terminal 12 and the programs executed by the system terminal 12 will be described later.

[0018] The external terminal 16 is a terminal used by the user of the information processing system 10 (for example, a seller who sells goods (including buyers of goods)) and is composed of a personal computer, tablet, smartphone, or the like. The type of the external terminal 16 is not particularly limited, but for example, smartphones, personal computers, tablets, etc. used by individuals are applicable.

[0019] The network NW is a line through which the system terminal 12 and the external terminal 16 can communicate with each other and is typically composed of a WAN (Wide Area Network), that is, the so-called Internet. Note that the network NW may be a LAN (Local Area Network) regardless of whether it is wired or wireless, or may be a dedicated line such as a VPN (Virtual Private Network), or may be a combination of these lines.

[0020] <System Terminal / Hardware Configuration Example> Next, an example of the hardware configuration of the system terminal 12 will be described.

[0021] As shown in FIG. 2, the system terminal 12 is configured to include, for example, a CPU 21, a ROM 22, a RAM 23, an external storage drive 25, a storage device 26, an input device 27, a display device 28, a communication unit 29, etc. that are connected to the CPU 21 via a bus.

[0022] The CPU 21 is a control means that controls the entire system terminal 12, and performs processes such as executing application programs and operating systems (OS) stored in ROM 22 and storage devices 26, and storing data and files necessary for program execution in RAM 23 and storage devices 26.

[0023] ROM22 is a storage means for storing basic I / O programs and various data, and is composed of, for example, PROM, flash memory, etc. RAM23 is a storage means for temporarily storing data, and is composed of, for example, SDRAM, DRAM, etc. External storage drive25 is a control means that can read and write data to recording media 24 such as magnetic tape, DVD, etc., and is composed of, for example, magnetic tape storage, DVD drive, etc.

[0024] The storage device 26 is a storage means for storing application programs, the OS, control programs, related programs, various information, etc., and is composed of, for example, a hard disk drive (HDD), a solid-state drive (SDD), etc. The input device 27 is for inputting commands (instructions), etc., to the system terminal 12, and is composed of, for example, a keyboard, a pointing device (mouse, etc.), a touch panel, etc.

[0025] The display device 28 displays commands input by the input device 27, the response output of the system terminal 12 to those commands, and various other displays, and is composed of, for example, a liquid crystal display, plasma display, organic EL, etc. The communication unit 29 is a control means that controls communication with external terminals 16, etc. via the network NW, and is composed of, for example, a communication card, etc.

[0026] <System Terminal / Function>

[0027] Next, we will explain the functions of the system terminal 12.

[0028] The storage device 26 of the system terminal 12 stores a program (information processing program) that causes the system terminal 12 to function as an information acquisition means 12a, a generation processing means 12b, a trained character generation model 12c, and an information transmission means 12d.

[0029] <System terminal / Function / Information acquisition method> Next, the information acquisition means 12a will be described.

[0030] The information acquisition means 12a is a means capable of acquiring at least the input information INI entered by the user, and is a means for acquiring information on the target product. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0031] The information acquisition means 12a acquires information entered by a user of the information processing system 10 using an external terminal 16 as input information INI, associates the acquired input information INI with the user's ID, and stores it in the storage device 26.

[0032] Here, "Input Information INI" refers to information (data) entered by a user of the information processing system 10 using an input means (keyboard, pointing device (mouse, etc.), touch panel, microphone, etc.) of an external terminal 16. The data format of "Input Information INI" is not particularly limited and may be any of the following: text data, audio data, still image data, video data, file, etc.

[0033] Examples of "Input Information INI" include the user's ID and password, text data and audio data such as information about the target product and questions about the target product to the information processing system 10, and files, still image data, or video data uploaded by the user.

[0034] Here, "information on the target product" refers to information on the product that is to be processed by the information processing system 10. Examples of "information on the target product" include product name, product ID, product category (e.g., skincare, supplements, etc.), JAN code, product brand, product manufacturer, product price range, target gender, target age, active ingredients (e.g., vitamin C, niacinamide, etc.), product efficacy, pharmaceutical classification (e.g., quasi-drug, cosmetic, etc.), information on product commercials, information on in-store POP displays, information on the product's official website, product design, product packaging design, and product description.

[0035] Furthermore, "information regarding questions about the target product" refers to information regarding questions about the product that is the subject of processing by the information processing system 10. Examples of such information include "How do I use it?", "What are the advantages compared to other products?", "What are the disadvantages compared to other products?", "Please explain its features," "What are its appealing points?", and "Please explain any contraindications."

[0036] For example, consider a case where a user of the information processing system 10 (in this case, staff at a store selling the product or a buyer in charge of that store) inputs text data as "information about the product," specifically "product name 'AAA,' product pharmaceutical classification 'cosmetics,' and a description of cosmetics related to product name 'AAA'." The case where a user of the information processing system 10 (in this case, a customer of the store selling the product) inputs "information regarding questions about the product" will be explained later.

[0037] In this case, the information acquisition means 12a stores the acquired information about the target product (in this example, text data relating to "product name "AAA", product pharmaceutical classification "cosmetics", and description of cosmetics related to product name "AAA") as input information INI in the storage device 26, associating it with the user's ID.

[0038] The input information INI may also be entered as a prompt by the user. For example, if the user enters the prompt "Create a character for the cosmetic product related to product name AAA. This cosmetic product is...", the information acquisition means 12a may be configured to analyze the prompt and extract and acquire the following information about the target product from it: text data of the product name (in this example, "AAA"), text data of the product's pharmaceutical classification (in this example, "cosmetics"), and text data of the product description (in this example, "This cosmetic product is...").

[0039] <System terminal / Function / Generation processing means> Next, the generation processing means 12b will be described.

[0040] The generation processing means 12b is a means for acquiring information about the target product in the input information INI stored in the storage device 26 by the information acquisition means 12a, inputting it into the trained character generation model 12c, and acquiring information about the target product character from the trained character generation model 12c. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0041] First, the generation processing means 12b retrieves the "information on the target product" stored in the storage device 26 by the information acquisition means 12a and inputs it into the trained character generation model 12c.

[0042] Next, the generation processing means 12b obtains information about the target product character from the trained character generation model 12c, associates the obtained information about the target product character with the user's ID, and stores it in the storage device 26.

[0043] For example, consider the case where the generation processing means 12b acquires information about the target product stored in the storage device 26 by the information acquisition means 12a (in this example, text data relating to "product name "AAA", product pharmaceutical classification "cosmetics", and description of cosmetics related to product name "AAA").

[0044] In this case, the generation processing means 12b reads text data related to the user's ID, name "AAA", product classification "cosmetics", and description of cosmetics related to name "AAA", from the storage device 26 and inputs it into the trained character generation model 12c.

[0045] Next, the generation processing means 12b obtains information about the target product character for the cosmetic product "AAA" that was generated by inputting the above text data into the trained character generation model 12c from the trained character generation model 12c. Next, the generation processing means 12b associates the information about the target product character obtained from the trained character generation model 12c with the user's ID and stores it in the storage device 26.

[0046] <System terminal / function / trained product information generation model> Next, we will describe the pre-trained character generation model 12c.

[0047] As shown in Figures 1 and 2, the trained character generation model 12c acquires information about the target products B2, B3, etc. and information about the target characters C2, C3, etc., respectively, and learns information about each of the target products B2, B3, etc. and target characters C2, C3, etc.

[0048] For example, the trained character generation model 12c acquires information about the target product B2 from external sources via a network, such as information from websites where the target product B2 is listed and purchase information. It learns the product name, product ID, product category (e.g., skincare, supplements, etc.), JAN code, product brand, product manufacturer, product price range, target gender, target age, active ingredients (e.g., vitamin C, niacinamide, etc.), product efficacy, pharmaceutical classification (e.g., quasi-drug, cosmetics, etc.), information about product commercials, information about in-store POP displays, information from the product's official website, product design, product packaging design, and product description. The trained character generation model 12c also periodically crawls external websites via a network, learning differentiating factors and advantages of the target product B2 compared to other target products, for example, by comparing it with target products from other manufacturers.

[0049] Furthermore, the trained character generation model 12c acquires information about the target product B3 from external sources via the network, such as information from websites where the target product B3 is listed and purchase information. It learns the product name, product ID, product category (e.g., skincare, supplements, etc.), JAN code, product brand, product manufacturer, product price range, target gender, target age, active ingredients (e.g., vitamin C, niacinamide, etc.), product efficacy, pharmaceutical classification (e.g., quasi-drug, cosmetics, etc.), information on product commercials, information on in-store POP displays, information on the product's official website, product design, product packaging design, and product description. The trained character generation model 12c also periodically crawls external websites via the network, learning differentiating factors and advantages of the target product B3 compared to other target products, for example, by comparing it with target products from other manufacturers.

[0050] Furthermore, the information sources from which the trained character generation model 12c collects information on the target product may include the website of the company that manufactures the target product, the websites of competitors of the company that manufactures the target product, or, for example, reviews and ratings of the target product posted on social media or blogs, or advertisements for the target product distributed on the internet (electronic flyers (web flyers), TV commercials, etc.).

[0051] Furthermore, the trained character generation model 12c learns information about the target character C2, including the character's name (e.g., official name or nickname), catchphrase or tagline about the character, when it first appeared, its purpose of use (e.g., advertising, sales promotion, social media, and packaging), the intended target audience (e.g., age group, gender, customer base), the product name associated with the character (e.g., product name, brand name, product category, relationship to brand concept), the character's role (e.g., guide, symbol, storyteller), usage scenarios (e.g., in-store, website, commercial, event), physical characteristics (e.g., shape, color, clothing, animal, human, etc.), personality and impression (e.g., friendly, trustworthy, etc.), tone of voice and speaking style, movements, values ​​and beliefs, likes and dislikes, etc.

[0052] Furthermore, the trained character generation model 12c learns information about the target character C3, including the character's name (e.g., official name or nickname), catchphrase or tagline about the character, when it first appeared, its purpose of use (e.g., advertising, sales promotion, social media, and packaging), the intended target audience (e.g., age group, gender, customer base), the product name associated with the character (e.g., product name, brand name, product category, relationship to brand concept), the character's role (e.g., guide, symbol, storyteller), usage scenarios (e.g., in-store, website, commercial, event), physical characteristics (e.g., shape, color, clothing, animal, human, etc.), personality and impression (e.g., friendly, trustworthy, etc.), voice tone, manner of speaking, movements, values ​​and beliefs, likes and dislikes, etc.

[0053] Furthermore, the information sources from which the trained character generation model 12c collects information on the target character may include the website of the company that manufactures the target product related to the target character, or advertisements for the target product distributed on the internet (electronic flyers (web flyers), TV commercials), etc. Also, the target character that the trained character generation model 12c learns is not limited to characters related to the target product. In other words, the target character that the trained character generation model 12c learns may include characters from manga, animation, etc., that are not related to the target product. In this case, the information sources from which the trained character generation model 12c collects information on characters not related to the target product may include ebooks, animated videos, etc.

[0054] Furthermore, the trained character generation model 12c generates the target product character C1 based on the input information about the target product B1, the information about each of the target products B2, B3, etc., and the information about each of the target characters C2, C3, etc. Here, the information about the target product B1 input to the trained character generation model 12c is, as mentioned above, information such as the product name of the target product B1, but other information may also be included.

[0055] The trained character generation model 12c extracts training target products (e.g., training target products B2, B3, etc.) that belong to the same pharmaceutical classification as target product B1, and extracts differentiating elements and advantages of target product B1 by comparing it with these training target products. The trained character generation model 12c also extracts training target characters (e.g., training target characters C2, C3, etc.) that give an impression of the differentiating elements and advantages of target product B1, and uses the information of these training target characters as a reference to generate information about a new character, target product character C1.

[0056] For example, consider the case where the trained character generation model 12c receives text data from the generation processing means 12b regarding "product name "AAA", product pharmaceutical classification "cosmetics", and description of cosmetics related to product name "AAA"" associated with the user's ID.

[0057] In this case, the trained character generation model 12c extracts cosmetics with the same use as the cosmetic product named "AAA" (for example, lotions named "BBB", "CCC", "DDD", and "EEE"), and extracts differentiating elements and advantages of the cosmetic product named "AAA" by comparing these cosmetics with the cosmetic product named "AAA". For example, the trained character generation model 12c extracts "a price range that is affordable even for people who have just started working" as a differentiating element of the cosmetic product named "AAA", and extracts "high concentration of hyaluronic acid and long-lasting moisturizing effect" as an advantage of the cosmetic product named "AAA". Furthermore, for example, the trained character generation model 12c extracts training target characters that represent a cosmetics advisor in their 20s (for example, characters named "Ms. B," "Ms. C," "Ms. D," and "Ms. E"), and uses the information of these training target characters as a reference to generate information about a new character, the target product character (for example, a cosmetics advisor character named "Ms. A"). For example, as shown in Figure 3, the trained character generation model 12c may generate an animated video in which "Ms. A," the cosmetics advisor, introduces the appeal and usage of cosmetics related to the product name "AAA."

[0058] <System terminal / Function / Information transmission method> Next, the information transmission means 12d will be described.

[0059] The information transmission means 12d is a means capable of outputting information to users of the information processing system 10, and in this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0060] The information transmission means 12d obtains information about the target product character stored in the storage device 26 by the generation processing means 12b and transmits it to the external terminal 16 used by the user of the information processing system 10.

[0061] The external terminal 16 receives information about the target product character from the information transmission means 12d.

[0062] For example, consider a case where the information transmission means 12d outputs an animated video to the user of the information processing system 10, in which a cosmetics advisor named "Ms. A" introduces the appeal and usage of cosmetics related to the product name "AAA" as information about the target product character.

[0063] In this case, the information transmission means 12d retrieves the data of the animation video associated with the user's ID from the storage device 26 and transmits it to the external terminal 16 used by the user of the information processing system 10.

[0064] The external terminal 16 receives the data of the animation video. This allows, for example, the animation video to be played on the external terminal 16. Furthermore, a retailer selling cosmetics related to the product name "AAA" can use the external terminal 16 to play the animation video and promote the sale of cosmetics related to the product name "AAA".

[0065] Furthermore, in the information processing system 10 of this embodiment, customers of a retail store selling cosmetics under the product name "AAA" can use an external terminal 16 to submit questions and receive answers to those questions. The process of submitting and answering questions from customers will be described below.

[0066] For example, consider a case where a user of the information processing system 10 (in this case, a customer of a retailer selling the target product) inputs voice data into an external terminal 16 as "information regarding questions about the target product," specifically asking "What are the advantages of this product compared to others?"

[0067] In this case, the information acquisition means 12a stores information regarding a question about the target product (in this example, voice data saying "Tell me the advantages of this product over others") obtained from the external terminal 16 via the network NW, as input information INI, associated with the user's ID, in the storage device 26.

[0068] Next, the generation processing means 12b reads information about a question regarding the target product associated with the user's ID (in this example, voice data saying "Tell me the advantages of this product over others") from the storage device 26 and inputs it into the trained character generation model 12c.

[0069] Next, the generation processing means 12b inputs the above audio data into the trained character generation model 12c and obtains information about the target product character generated from the trained character generation model 12c.

[0070] Next, when the trained character generation model 12c receives information about a question regarding the target product, it generates information about the target product character, specifically information about the manner in which the target product character responds to the question.

[0071] For example, consider the case where the trained character generation model 12c receives voice data from the generation processing means 12b that says "Tell me the advantages of other products" and is associated with the user's ID.

[0072] In this case, the trained character generation model 12c extracts cosmetics with the same use as the cosmetic product named "AAA" (for example, lotions named "BBB", "CCC", "DDD", and "EEE"), and extracts the advantages of the cosmetic product named "AAA" over other cosmetics by comparing these cosmetics with the cosmetic product named "AAA". For example, the trained character generation model 12c extracts the advantages of the cosmetic product named "AAA" over other cosmetics as "high moisturizing power" and "high effectiveness in balancing sebum". Furthermore, for example, the trained character generation model 12c generates an animated video in which a cosmetics advisor named "Ms. A" answers questions about the above advantages. Specifically, as shown in Figure 4, the trained character generation model 12c generates an animated video in which a cosmetics advisor named "Ms. A" answers questions about the two advantages: "high moisturizing power" and "high effectiveness in balancing sebum".

[0073] Next, the generation processing means 12b associates the information of the target product character obtained from the trained character generation model 12c (in this example, an animated video that answers the two benefits mentioned above) with the user's ID and stores it in the storage device 26.

[0074] Next, the information transmission means 12d retrieves animation video data from the storage device 26 that answers the two benefits associated with the user's ID, and transmits it to the external terminal 16 used by the user of the information processing system 10.

[0075] The external terminal 16 receives the data for the animation video and plays the animation video. In this way, the information processing system 10 of this embodiment can answer questions received from customers by playing an animation video of the cosmetics advisor "Ms. A". In this manner, the information processing system 10 of this embodiment can have a question-and-answer session between the customer and the target product character (the character of the cosmetics advisor "Ms. A").

[0076] Furthermore, the trained character generation model 12c of this embodiment generates a new character related to the target product (hereinafter referred to as the "new target product character") based on the history of "information related to questions about the target product" and "information on how the target product character answers the questions," and replaces the original target product character with it.

[0077] Specifically, the trained character generation model 12c of this embodiment, based on the history of "information regarding questions about the target product" and "information regarding the manner in which the target product character answers the questions" (the history of question-and-answer sessions between the customer and the cosmetics advisor "Ms. A"), determines, for example, that the customer's interest in the target product (in this example, cosmetics related to product name "AAA") has not increased, and generates a new character related to cosmetics related to product name "AAA" (hereinafter referred to as the "new target product character") and replaces the original target product character (the character of cosmetics advisor "Ms. A"). For example, as shown in Figure 5, the trained character generation model 12c generates a character of cosmetics advisor "Ms. Y" as the new target product character and replaces the original character of cosmetics advisor "Ms. A". In this way, the customer can repeatedly engage in question-and-answer sessions with "Ms. Y" instead of cosmetics advisor "Ms. A".

[0078] The trained character generation model 12c is trained to determine whether a customer's interest in the target product is increasing (for example, whether or not they will purchase it) based on a history of "information about questions about the target product" and "information about how the target product character responds to those questions." For example, the trained character generation model 12c learns the correspondence between input (training data showing question-and-answer sessions between customers and store staff) and the correct answer (whether or not the product was purchased) using a dataset that includes training data (e.g., video data) showing question-and-answer sessions between customers and store staff and correct labels (data about whether or not the product was purchased). As a result, the trained character generation model 12c is able to determine whether or not a customer's interest in the target product is increasing based on a history of "information about questions about the target product" and "information about how the target product character responds to those questions."

[0079] <Information Processing Systems / Summary> As described above, the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 1 and 2) includes an information acquisition means (for example, the information acquisition means 12a shown in Figures 1 and 2) for acquiring information about a target product, a generation processing means (for example, the generation processing means 12b shown in Figures 1 and 2) for inputting the information about the target product into a trained character generation model (for example, the trained character generation model 12c shown in Figures 1 and 2) and acquiring information about a character related to the target product (hereinafter referred to as "target product character") from the trained character generation model, and an information transmission means (for example, the information transmission means shown in Figures 1 and 2) for transmitting information about the target product character. The information processing system is characterized in that it has a stage 12d), and the trained character generation model acquires information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the target product character (hereinafter referred to as "learning target characters"), learns the information about each of the learning target products and each of the learning target characters, and is trained to generate information about the target product character based on the information about the target product, the information about each of the learning target products and each of the learning target characters.

[0080] The information processing method according to this embodiment acquires information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the character related to the target product (hereinafter referred to as "target product character") (hereinafter referred to as "learning target character"), learns the information about each of the learning target products and each of the learning target character, and trains a character generation model to generate information about the target product character based on the information about the target product, the information about each of the learning target products and each of the learning target character. An information processing method that is performed using a trained character generation model 12c (for example, shown in Figures 1 and 2), comprising: an information acquisition step (for example, a process performed by the information acquisition means 12a shown in Figures 1 and 2) for acquiring information about the target product; a generation processing step (for example, a process performed by the generation processing means 12b shown in Figures 1 and 2) for inputting the information about the target product into the trained character generation model and acquiring information about the target product character from the trained character generation model; and an information transmission step (for example, a process performed by the information transmission means 12d shown in Figures 1 and 2) for transmitting information about the target product character.

[0081] The information processing program according to this embodiment acquires information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the character related to the target product (hereinafter referred to as "target product character") (hereinafter referred to as "learning target character"), and learns the information about each of the learning target products and each of the learning target character. Furthermore, it is a trained character that is trained to generate information about the target product character based on the information about the target product, the information about each of the learning target products and each of the learning target character. This is a program for an information processing system configured to have a generative model (for example, a trained character generative model 12c shown in Figures 1 and 2), characterized in that it causes a computer to function as an information acquisition means (for example, an information acquisition means 12a shown in Figures 1 and 2) for acquiring information about the target product, a generation processing means (for example, a generation processing means 12b shown in Figures 1 and 2) for inputting the information about the target product into the trained character generative model and acquiring information about the target product character from the trained character generative model, and an information transmission means (for example, an information transmission means 12d shown in Figures 1 and 2) for transmitting information about the target product character.

[0082] According to the information processing system, information processing method, and information processing program of this embodiment, it is possible to generate a character related to the target product.

[0083] Furthermore, the trained character generation model of this embodiment (for example, the trained character generation model 12c shown in Figures 1 and 2) may generate information about the target product character in a manner that the target product character transmits information about the target product.

[0084] With this configuration, users of the information processing system according to this embodiment can, for example, use information in which the target product character transmits information about the target product to promote sales of the target product.

[0085] Furthermore, the trained character generation model of this embodiment (for example, the trained character generation model 12c shown in Figures 1 and 2) may be configured to generate a video in which the target product character introduces the target product.

[0086] With this configuration, users of the information processing system according to this embodiment can, for example, promote the sale of the target product by using a video in which the target product's character introduces the target product.

[0087] Furthermore, the information acquisition means (for example, the information acquisition means 12a shown in Figures 1 and 2) of this embodiment may acquire information related to questions about the target product, the generation processing means (for example, the generation processing means 12b shown in Figures 1 and 2) may input the information related to questions about the target product into the trained character generation model (for example, the trained character generation model 12c shown in Figures 1 and 2), and the trained character generation model may generate information about the target product character, specifically information on how the target product character responds to the questions.

[0088] With this configuration, it is possible to have a question-and-answer session between the user of the information processing system according to this embodiment and the target product character.

[0089] Furthermore, the trained character generation model of this embodiment (for example, the trained character generation model 12c shown in Figures 1 and 2) may generate a new character relating to the target product and replace the original target product character based on a history of information regarding the question and information regarding the manner in which the answer to the question is given.

[0090] With this configuration, users of the information processing system according to this embodiment can engage in question-and-answer sessions with a new character related to the target product, instead of the original target product character.

[0091] It should be noted that the information processing system, information processing method, and information processing program according to the present invention are not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0092] Therefore, for example, the information of the target product character generated by the trained character generation model 12c may be a single piece of information, such as only the character's name or only the character's appearance, or it may be information that combines the character's name, physical characteristics, voice, tone of voice, manner of speaking, movements, etc. [Industrial applicability]

[0093] The information processing system, information processing method, and information processing program according to the present invention can be widely applied to fields such as manufacturing, service industries, and retail industries. [Explanation of Symbols]

[0094] 10 Information Processing Systems 12 System Terminals 12a Information acquisition means 12b Generation processing means 12c Pre-trained Character Generation Model 12d Information transmission means 16 External terminals 21 CPU 22 ROM 23 RAM 24 Recording media 25 External storage drives 26 Storage device 27 Input devices 28 Display device 29 Communications Department

Claims

1. Information acquisition means for obtaining information on the target product, A generation processing means that inputs information about the target product into a trained character generation model and obtains information about a character related to the target product (hereinafter referred to as "target product character") from the trained character generation model, Information transmission means for transmitting information about the aforementioned target product character, It has, The trained character generation model acquires information about multiple products different from the target product (hereinafter referred to as "training target products") and information about multiple characters different from the target product character (hereinafter referred to as "training target characters"), and learns information about each of the training target products, including their advantages or advantages over other training target products, and information about each of the training target characters. It is also trained to generate information about the target product character based on the information about the target product, the information about each of the training target products, and the information about each of the training target characters. An information processing system characterized by the following:

2. In the information processing system described in claim 1, The trained character generation model generates information about the target product character in a manner that the target product character transmits information about the target product. An information processing system characterized by the following:

3. In the information processing system described in claim 2, The aforementioned trained character generation model generates a video in which the target product character introduces the target product. An information processing system characterized by the following:

4. In the information processing system described in claim 1, The information acquisition means acquires information regarding questions about the target product, The generation processing means inputs information regarding the questions about the target product into the trained character generation model. The trained character generation model generates information about the target product character, including information on how the target product character responds to the question. An information processing system characterized by the following:

5. In the information processing system described in claim 4, The trained character generation model generates a new character for the target product and replaces the original target product character based on the history of information regarding the question and the manner in which the question is answered. An information processing system characterized by the following:

6. In the information processing system described in Claim 1, The aforementioned trained character generation model learns information about each of the aforementioned target products, including differentiating factors from other target products. An information processing system characterized by the following:

7. An information processing method performed by a computer using a trained character generation model which acquires information about multiple products different from the target product (hereinafter referred to as "learning target products") and information about multiple characters different from the character related to the target product (hereinafter referred to as "target product character") (hereinafter referred to as "learning target character"), learns information about each of the learning target products and each of the learning target character, including their advantages or advantages over other learning target products, and is trained to generate information about the target product character based on the information about the target product, the information about each of the learning target products and each of the learning target character, An information acquisition step to acquire information on the aforementioned target product, A generation process step in which information about the target product is input into the trained character generation model, and information about the target product character is obtained from the trained character generation model, An information transmission step that transmits information about the target product character, Having, An information processing method characterized by the following:

8. A program for an information processing system, Computers, A trained character generation model acquires information about multiple products different from the target product (hereinafter referred to as "training target products") and information about multiple characters different from the character related to the target product (hereinafter referred to as "target product character") (hereinafter referred to as "training target character"), and learns information about each of the training target products and each of the training target character, including their advantages or advantages over other training target products, and is trained to generate information about the target product character based on the information about the target product, the information about each of the training target products and each of the training target character, Information acquisition means for acquiring information on the aforementioned target product, A generation processing means that inputs information about the target product into a trained character generation model and obtains information about the target product character from the trained character generation model, To function as an information transmission means for transmitting information about the aforementioned target product character, An information processing program characterized by the following features.

Images