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

Abstract

To solve the problem in which it is not easy to assign an appropriate heading when contents are classified into groups.SOLUTION: An information processing device comprises: an acquisition unit 131 which acquires a plurality of presentation targets selected on the basis of attributes of a user; a classification unit 132 which classifies each presentation target into any of a plurality of groups on the basis of the similarity among the plurality of presentation targets acquired by the acquisition unit 131; a generation unit 133 which generates a name of the group using a generation model trained to output answers to input questions from the information of presentation targets classified into the plurality of groups; and an output unit 134 which outputs a content including the name generated by the generation unit 133 to a terminal of 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 is a technology that selects representative news articles from among multiple news articles with similar content distributed via the Internet and provides them to users. In addition, there is a technology that classifies news articles into UI (User Interface) groups according to the user's interest and knowledge level in the content, and manually checks and assigns the contents of the news articles in the classified groups. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-204507 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional technology, it is not easy to give appropriate names to groups. For example, when news articles are classified into groups using a UI, a human being has to check the contents of the news articles in the classified groups and manually assign names to them, which makes it time-consuming to assign appropriate names. [Means for solving the problem]

[0005] The information processing device according to the present application comprises an acquisition unit that acquires a plurality of presentation objects selected based on the attributes of a user; a classification unit that classifies each of the presentation objects into one of a plurality of groups based on similarities between the plurality of presentation objects acquired by the acquisition unit; a generation unit that generates a name of the group from information about the presentation objects classified into the plurality of groups using a generation model that has been trained to output answers to input questions; and an output unit that outputs content including the name generated by the generation unit to a user's terminal. Effect of the Invention

[0006] According to one aspect of the embodiment, an effect is achieved in that it is possible to easily assign an appropriate name. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing an overview of an information processing method according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of information stored in a user information storage unit of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a screen for inputting instruction sentences to a generative model according to an embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating an example 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 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application (hereinafter, referred to as "embodiments") 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 these embodiments. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each embodiment below are given the same reference numerals, and duplicated explanations will be omitted.

[0009] [1. Overview of Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of an information processing method according to the embodiment, which is realized by an information processing device 100. In the example of Fig. 1, an overall system 1 includes a user terminal 10, a provider terminal 20, and the information processing device 100. In addition, the user terminal 10, the provider terminal 20, and the information processing device 100 are each connected to be able to communicate with each other via a network N by wire or wirelessly. Note that Fig. 1 is an example, and the number of user terminals 10 and provider terminals 20 is not limited to the number shown in Fig. 1.

[0010] First, the information processing device 100 acquires information on the presentation target from the user terminal 10 (step S1). For example, the information processing device 100 acquires information on news articles and products that the user has viewed using a dedicated application program (hereinafter referred to as a "dedicated app") as the presentation target. At this time, the information processing device 100 may preferentially acquire news articles that are likely to be viewed by the user. Furthermore, the information processing device 100 may estimate the user's attributes from attribute information such as demographic data and psychographic data obtained when the user uses the dedicated app, purchase history, browsing history, search history, and the like. As a result, the information processing device 100 acquires information on the user's interests and knowledge level based on the estimated user's attributes.

[0011] Next, the information processing device 100 classifies the acquired information on the presentation target into groups (step S2). For example, the information processing device 100 classifies the acquired presentation target into a plurality of groups based on similarity. Also, for example, the information processing device 100 may classify the acquired presentation target into groups with a granularity according to the user's interests and knowledge level acquired from the user terminal 10.

[0012] Next, the information processing device 100 receives an instruction sentence for generating a name of the group into which the presentation target is classified from the provider terminal 20 (step S3). For example, the information processing device 100 receives an instruction sentence such as a command to specify the number of characters in the name, or to generate the name taking into account a knowledge level estimated from the user's attributes.

[0013] Next, the information processing device 100 generates a name of the group using the generative model (step S4). For example, the information processing device 100 generates a name of the group based on the instruction sentence received in step S3. A name for each group is generated using a generative model. Specifically, the information processing device 100 generates the name by inputting, for example, the text of the news article, the title of the news article, and the instruction sentence received in step S3 into the generative model. The generative model here is a sentence generation model that has learned data published on the Web, and is, for example, a GPT (Generative Pre-trained Transformer) model that generates answers to questions.

[0014] Finally, the information processing device 100 outputs the content including the generated name to the user terminal 10 (step S5). For example, when a group is selected by the user in the dedicated app, the information processing device 100 outputs presentation objects belonging to the selected group together with the generated name.

[0015] Conventionally, when classifying news articles into groups, it is possible to give appropriate names to the groups in advance, for example by classifying the groups according to a predetermined classification. However, when the classification method is determined in advance, it cannot be expected that the classification granularity is appropriate for each user's interests and knowledge level. On the other hand, when the classification method is dynamically changed according to each user and the situation of the article, it is possible to classify the articles more appropriately for the user, but there is a problem with the interpretability of the group classification because names cannot be given in advance.

[0016] However, the information processing device 100 can generate a name suited to each user by collecting information about the user and using the estimated interests and knowledge level in a generation model that generates a name.

[0017] 2. Configuration of Information Processing Device Next, the configuration of the information processing device 100 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 2, the information processing device 100 according to the embodiment has a network N, a communication unit 110, a storage unit 120, and a control unit 130.

[0018] The information processing device 100 may be, for example, an information processing device such as a PC (Personal Computer), a WS (Work Station), a computer having a server function, etc. The information processing device 100 performs processing based on information transmitted from a user terminal 10 via a network N, for example.

[0019] The user terminal 10 or the provider terminal 20 is an information processing device used by a user or a provider. For example, the information processing device may be a smartphone, a tablet terminal, a desktop PC, a notebook PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in FIG. 1, the user terminal 10 or the provider terminal 20 is a smartphone.

[0020] The network N connects the information processing device 100, the user terminal 10, and the provider terminal 20 in a wired or wireless manner so that they can communicate with each other. If the network N is wired, it may be realized by Ethernet (registered trademark) defined by IEEE802.3. If the network N is wireless, it may be realized by a wireless LAN (Local Area Network) defined by IEEE802.11.

[0021] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the user terminal 10 and the provider terminal 20 etc.

[0022] (Regarding the storage unit 120) The storage unit 120 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 120 has a presentation target storage unit 121, a user information storage unit 122, and a generation result storage unit 123. The configuration of these units will be described below in order.

[0023] (Regarding the presentation object storage unit 121) The presentation target storage unit 121 stores information about the presentation target being viewed by the user. For example, the presentation target 121 stores information about news articles and products viewed by the user using a dedicated app. At this time, the presentation target storage unit 121 can store, for example, information about news articles and products that are likely to be viewed by the user with priority.

[0024] (Regarding the user information storage unit 122) The user information storage unit 122 stores various information related to the user. For example, the user information storage unit 122 can store the user's browsing history of news articles or product purchase history. Furthermore, the user information storage unit 122 may estimate and store the user's attributes from attribute information such as demographic data and psychographic data obtained when the user uses a dedicated app, purchase history, browsing history, search history, etc. This allows the user information storage unit 122 to store information on the user's interests and knowledge level. The user information storage unit 122 stores information on presentation targets and groups viewed by the user in the past. For this reason, when the information processing device 100 outputs new presentation targets and groups to the user terminal 10, it can output content different from the presentation targets and groups output in the past based on the information stored in the user information storage unit 122.

[0025] Here, an example of items stored in the user information storage unit 122 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of items stored in the user information storage unit 122 of the information processing device 100 according to an embodiment. Fig. 3 illustrates items acquired from the user terminal 10. In the example of Fig. 3, information on items such as "contents", "purchase history", and "attributes" is stored.

[0026] "Content" is data related to content identified by a corresponding content ID. For example, the content includes news articles and product information. Furthermore, the content may include, for example, the number of user views, the number of user ratings, comments by experts and users, and the like, which are given to the news articles and product information.

[0027] "Purchase history" is a history of products purchased by a user. For example, the purchase history stores information on news articles and the date and time of product purchases in chronological order. "Attributes" are classifications of a user's interests and knowledge level. For example, the attributes of a user may be estimated from attribute information such as demographic data and psychographic data obtained when the user uses a dedicated app, purchase history, browsing history, search history, etc.

[0028] (Regarding the generation result storage unit 123) Returning to the description of Fig. 2, the generation result storage unit 123 will be described. The generation result storage unit 123 stores the names of the groups generated by the generative model. For example, the generation result storage unit 123 may store the results of classifying groups and generating names each time a user accesses a dedicated app.

[0029] (Regarding the control unit 130) Next, the control unit 130 in Fig. 2 will be described. The control unit 130 is a controller that controls the information processing device 100, and is stored in the storage unit 120 of the information processing device 100 by, for example, a CPU (Central Processing Unit) or the like. Also, it is realized by reading out various programs and executing them using a RAM as a working area. Also, the control unit 130 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0030] 2, the control unit 130 has an acquisition unit 131, a classification unit 132, a generation unit 133, and an output unit 134. The control unit 130 realizes these functions by reading out a program from the storage unit 120 and executing it using the RAM as a working area, thereby realizing or executing the functions and actions of the information processing described below. These processes will be described in order below.

[0031] (Regarding the acquisition unit 131) The acquisition unit 131 acquires a plurality of presentation targets selected based on the attributes of the user. For example, the acquisition unit 131 acquires a news article to be output to the user's terminal as the presentation target. Also, for example, the acquisition unit 131 acquires information on a product to be output to the user's terminal among products exhibited in the online shopping mall as the presentation target. At this time, the acquisition unit 131 may preferentially acquire information on news articles and products that are likely to be viewed by the user. Furthermore, the acquisition unit 131 may estimate the attributes of the user from attribute information such as demographic data and psychographic data acquired when the user uses a dedicated app, purchase history, browsing history, search history, and the like. As a result, the acquisition unit 131 acquires information on the user's interests and knowledge level based on the estimated attributes of the user. The acquisition unit 131 stores the acquired presentation targets and user information in the presentation target storage unit 121 and the user information storage unit 122, respectively.

[0032] (Regarding the classification unit 132) The classification unit 132 classifies each presentation target into one of a plurality of groups based on the similarity of the plurality of presentation targets acquired by the acquisition unit 131. For example, the classification unit 132 can classify into a plurality of groups using the similarity of news articles and the information of user attributes acquired by the acquisition unit 131. Furthermore, for example, the classification unit 132 may classify into groups with a granularity according to the user's interests and knowledge level acquired from the user terminal 10.

[0033] As a specific classification method, for example, the classification unit 132 can create and classify a model that converts the information of news articles acquired from the user terminal 10 into similar vectors as the information becomes more similar. Furthermore, the classification unit 132 can express each news article as a vector using, for example, a vector conversion model, and classify the news articles based on the similarity of the vectors.

[0034] (Regarding the generation unit 133) The generating unit 133 generates names of the groups from information of the presentation targets classified into a plurality of groups, using a generation model trained to output answers to input questions. For example, the generating unit 133 inputs information of the presentation targets and an instruction sentence instructing to generate names of the groups into which the presentation targets are classified into the generation model, and generates names of the groups. Also, for example, the generating unit 133 generates names in the groups according to the degree of knowledge of the users based on the information of the users. The generating unit 133 stores the generated generation results in the generation result storage unit 123.

[0035] For example, the generation unit 133 generates a prompt including various information related to news, such as the title and text of each news, as a prompt to be input to the GPT. Note that such various information related to news may include the news source, distribution time, evaluation content such as likes, comments on the news, and summaries of the comments. Furthermore, the generation unit 133 generates a prompt including identification information (e.g., group number) of the group into which each news is classified. Furthermore, the generation unit 133 generates a prompt including various user information related to the user (e.g., content viewed by the user in the past, purchase history, various attributes, comment history, evaluation history, etc.).

[0036] Then, the generating unit 133 generates a prompt including an instruction sentence for generating a name of a group into which each news is classified. More specifically, the generating unit 133 generates a prompt including an instruction sentence for generating a name of a group based on the degree of knowledge of the user on the subject (e.g., a person or an event that is the subject of the news commentary) related to the news classified into each group, which is the knowledge of the user estimated from the user information. For example, the generating unit 133 generates a prompt including an instruction sentence for generating a name indicating a more detailed content as the degree of knowledge is higher. As a specific example, the generating unit 133 generates a prompt such as "Please generate a name of each group number into which these news are classified from the information of each news input. When generating the name of the group, please generate it taking into consideration the degree of knowledge of the user on the subject that the news classified into this group deals with, which is the degree of knowledge estimated from the user information. More specifically, please generate a name indicating a more detailed content as the degree of knowledge is higher." Then, the generating unit 133 inputs such a prompt to the GPT, thereby causing the GPT to generate the name of each group.

[0037] The generating unit 133 may generate an instruction sentence that makes the character strings of the names of the groups common to a certain extent. For example, the generating unit 133 may generate an instruction sentence that includes a sentence such as "Please generate the names so that the number of characters is within the range of 10 to 15 characters" as the instruction sentence. The generating unit 133 may also generate an instruction sentence that causes each group to be given a name that indicates the difference between the groups, so that the user can easily recognize the distinction between the groups. For example, the generating unit 133 may generate a prompt that includes a sentence such as "Please generate the names of each group so that they can be distinguished" to cause the group of game news and the group of game results to be given names that can be clearly distinguished from each other.

[0038] Here, an example of a screen generated by the generation unit 133 will be described with reference to Fig. 4. Fig. 4 is an example of a screen for generating a group name by the generation unit 133 of the information processing device 100 according to the embodiment. Fig. 4 illustrates a screen generated on the vendor terminal 20. In the example of Fig. 4, the screen of the vendor terminal 20 has items such as an instruction text input field 501 and a name display field 502.

[0039] The instruction text input field 501 is a place where an instruction text for giving an instruction to a generation model is input. For example, the instruction text input field 501 accepts an instruction such as a specification of the number of characters of a name, generation taking into consideration a knowledge level estimated from a user's attributes, etc. Specifically, the instruction text input field 501 can accept an instruction to generate a name according to a user's interests and knowledge level using user attributes acquired by the acquisition unit 131 for a plurality of groups into which news articles are classified.

[0040] The name display field 502 is a place where the name generated by the generative model is output. For example, the name display field 502 displays a name according to the instruction document input in the instruction document input field 501. This allows the generation unit 133 to assign different names to the same content in accordance with the user's interests and knowledge level.

[0041] (Regarding the output unit 134) The output unit 134 outputs the content including the name generated by the generation unit 133 to the user's terminal 10. For example, when the user selects one of the groups in the dedicated app, the output unit 134 outputs the presentation targets belonging to the group together with the generated name. Specifically, when the user accesses the dedicated app, the output unit 134 can classify the new presentation targets into groups in accordance with the past history based on the user's past browsing history of presentation targets and groups read from the user information storage unit 122, for example, and generate and output a name.

[0042] The information processing device 100 collects information about the user and uses the estimated interests and knowledge level in a generation model that generates names, making it possible to generate names that correspond to each user, and making it easy to assign appropriate names to groups into which the presented objects are classified. Furthermore, by using the generation model, the information processing device 100 can dynamically change the classification method according to the situation of the user and the presented objects, and generate appropriate names, making the interpretation of the group classification clear.

[0043] [3. Information processing flow] Next, the procedure of information processing according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of information processing according to the embodiment. Below, the procedure of information processing according to the embodiment will be described with reference to the flowchart shown in Fig. 5.

[0044] 5, a process procedure for the generative model to generate a name and output it to the user terminal 10 will be described. First, the acquisition unit 131 of the information processing device 100 acquires presentation objects from the user terminal 10 (step S101). At this time, if the acquisition unit 131 of the information processing device 100 acquires presentation objects from the user terminal 10 (step S101, Yes), the classification unit 132 of the information processing device 100 classifies each presentation object into a plurality of groups (step S102). On the other hand, if the acquisition unit 131 of the information processing device 100 has not acquired any presentation objects from the user terminal 10 (step S101, No), the process waits until all presentation objects are acquired.

[0045] Next, the groups classified by the classification unit 132 of the information processing device 100, the presentation target, and the instruction sentence are input to a generation model, and the generation unit 133 of the information processing device 100 generates names of the groups using the generation model (step S103). Finally, the output unit 134 of the information processing device 100 outputs content including the names to the user terminal 10.

[0046] Conventionally, when classifying news articles into groups, it is possible to give appropriate names to the groups in advance, for example by classifying the groups according to a predetermined classification. However, when the classification method is determined in advance, it cannot be expected that the classification granularity is appropriate for each user's interests and knowledge level. On the other hand, when the classification method is dynamically changed according to each user and the situation of the article, it is possible to classify the articles more appropriately for the user, but there is a problem with the interpretability of the group classification because names cannot be given in advance.

[0047] However, the information processing device 100 has become able to generate names suited to each user by collecting information about the user and using the estimated interests and knowledge level in a generation model that generates a name.

[0048] [4. Hardware Configuration] Moreover, the information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0049] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device that stores data used by the arithmetic device 1030 for various calculations and various databases, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, or the like.

[0050] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by, for example, a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, scanner, etc., and is realized by, for example, a USB, etc.

[0051] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disk), a DVD (Digital Versatile Disk), or a PD (Phase change rewriteable Disk), a magneto-optical recording medium such as an MO (Magnet-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0052] The network IF 1080 receives data from other devices via the network N and sends the data to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0053] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0054] For example, when the computer 1000 functions as the information processing device 100, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 130 of the information processing device 100 by executing a program loaded onto the primary storage device 1040.

[0055] 5. Composition and Effects The information processing device 100 according to the present disclosure includes an acquisition unit 131 that acquires multiple presentation targets selected based on user attributes, a classification unit 132 that classifies each of the presentation targets into one of multiple groups based on similarities between the multiple presentation targets acquired by the acquisition unit 131, a generation unit 133 that generates a name of the group from information about the presentation targets classified into the multiple groups using a generation model that has been trained to output answers to input questions, and an output unit 134 that outputs content including the name generated by the generation unit 133 to the user's terminal 10.

[0056] According to this configuration, the information processing device 100 can generate a name that suits each user by collecting information about the user and using the estimated interests and knowledge level in a generation model that generates a name.

[0057] The acquisition unit 131 of the information processing device 100 according to the present disclosure acquires, as a presentation target, a news article to be output to the user's terminal 10. For example, the acquisition unit 131 of the information processing device 100 according to the present disclosure acquires, as a presentation target, information on a product to be output to the user's terminal 10 among products offered in an online shopping mall.

[0058] According to this configuration, the acquisition unit 131 of the information processing device 100 collects information about the user, and uses the estimated interest and knowledge level in a generation model that generates a name, thereby making it possible to generate a name according to the user, and it becomes easy to give an appropriate name to a group into which the presented object is classified. In addition, for example, the acquisition unit 131 collects information about the user, so that it is possible to give each user a name that more clearly distinguishes the difference even among groups in the same category.

[0059] The generation unit 133 of the information processing device 100 according to the present disclosure inputs information of the presentation target and an instruction sentence instructing generation of a name of a group into which the presentation target is classified into a generation model, and generates a name of the group. In addition, for example, the generation unit 133 of the information processing device 100 generates a name according to a knowledge level based on the user's information for the presentation target classified into a plurality of groups.

[0060] According to this configuration, the generation unit 133 of the information processing device 100 can dynamically change the classification method according to the situation of the user or the presented object by using a generative model, and can generate appropriate names, thereby making the interpretability of group classification clear.

[0061] In the above example, the information processing device 100 generates a name to be assigned to each news group, but the embodiment is not limited to this. For example, the information processing device 100 may generate a name for each group when dividing products exhibited in an online shopping mall into groups and presenting them to a user. Also, the information processing device 100 may generate a name for each group when dividing various contents, such as electronic books and music provided by a music distribution service, into groups and presenting them to a user. In other words, the information processing device 100 may process any presentation target as long as it is a presentation target to be divided into groups and presented to a user.

[0062] The above describes the embodiment of the present application in detail based on the drawings, but this is merely an example, and the present invention can be embodied in other forms that include various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the disclosure section of the invention.

[0063] Furthermore, the above-mentioned “section, module, unit” can be read as “means” or “circuit.” For example, the acquisition unit 131 can be read as acquisition means or acquisition circuit. [Explanation of symbols]

[0064] 1. Overall System 10 User terminal 20. Vendor terminal 100 Information processing device 110 Communications Department 120 Storage section 121 Presentation target memory unit 122 User information storage unit 123 Generation result storage unit 130 Control section 131 Acquisition Department 132 Classification Department 133 Generation part 134 Output section N Network

Claims

1. An acquisition unit that acquires a plurality of presentation targets selected based on a user attribute; a classification unit that classifies each of the presentation objects into one of a plurality of groups based on the similarity of the presentation objects acquired by the acquisition unit; a generation unit that generates names of the groups from the information of the presentation targets classified into the plurality of groups by using a generation model that has been trained to output answers to input questions; an output unit that outputs the content including the name generated by the generation unit to a terminal of the user; An information processing device comprising:

2. The information processing apparatus according to claim 1 , wherein the acquisition unit acquires, as the presentation target, a news article outputted to a terminal of the user.

3. The information processing device according to claim 1 , wherein the acquisition unit acquires, as the presentation target, information on a product that is displayed on a terminal of the user among products offered in an online shopping mall.

4. The information processing device according to claim 1, characterized in that the generation unit inputs information about the presentation object and an instruction sentence instructing the generation of a name of a group into which the presentation object is classified into the generation model, and generates the name of the group.

5. The information processing apparatus according to claim 1 , wherein the generating unit generates names for the presentation objects classified into the plurality of groups according to a level of knowledge based on information of the user.

6. An information processing method executed by an information processing device, An acquisition step of acquiring a plurality of presentation objects selected based on a user attribute; a classification step of classifying each of the presentation objects into one of a plurality of groups based on the similarity of the presentation objects acquired by the acquisition step; a generation step of generating names of the groups from the information of the presentation objects classified into the plurality of groups, using a generation model that has been trained to output answers to input questions; an output step of outputting the content including the name generated by the generation step to a terminal of the user; 13. An information processing method comprising:

7. An acquisition step of acquiring a plurality of presentation targets selected based on a user attribute; a classification step of classifying each of the presentation objects into one of a plurality of groups based on the similarity of the presentation objects acquired by the acquisition step; a generation step of generating names of the groups from the information of the presentation targets classified into the plurality of groups, using a generation model that has been trained to output answers to input questions; an output step of outputting the content including the name generated by the generating step to a terminal of the user; An information processing device comprising: An information processing program for causing a computer to execute the above.

Images