Information processing device, information processing method and information processing program

Abstract

To set rewards appropriate to content creators.SOLUTION: An information processing device according to the present invention comprises: a generation unit for generating aggregate content from a plurality of pieces of content using a generation model for generating answers to prompts; a provision unit for providing the aggregate content generated by the generation unit to users; an estimation unit for estimating details of the aggregate content provided by the provision unit and relevance to the content; and a setting unit for setting a reward to the content that is referenced by the aggregate content, in accordance with the relevance estimated by the estimation unit.SELECTED DRAWING: Figure 1

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] 2. Description of the Related Art Conventionally, a technique has been proposed in which a contributor such as a user is paid a reward according to the number of views of content posted by the contributor (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-177525 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, the generation of content by a generative model that generates answers to questions as sentences has not been taken into consideration. Therefore, when providing content generated by a generative model to a user, it is necessary to design an appropriate reward for the creator of the content that is the reference source.

[0005] The present invention has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that are capable of setting appropriate remuneration for content creators. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the information processing device of the present invention includes a generation unit that generates collective content from a plurality of contents using a generation model that generates answers to prompts, a provision unit that provides the collective content generated by the generation unit to a user, an estimation unit that estimates the content of the collective content provided by the provision unit and a relevance between the content, and a setting unit that sets a reward for the content that is a reference source of the collective content in accordance with the relevance estimated by the estimation unit. Effect of the Invention

[0007] According to the present invention, it is possible to set appropriate remuneration for content creators. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a reward system of a news site according to an embodiment. [Diagram 3] FIG. 3 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in a content storage unit according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of information stored in a user information storage unit according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a news screen according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a word cloud according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of advertisement placement according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of advertisement placement according to the embodiment. [Figure 10] FIG. 10 is a flowchart illustrating an example of a processing procedure of the setting process according to the embodiment. [Figure 11] FIG. 11 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

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. 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 information processing according to the embodiment. Note that the information processing according to the embodiment is realized by an information processing device 1 shown in Fig. 1.

[0011] 1 is an information processing device that distributes various contents. The information processing device 1 provides news contents to each user through a news site, for example.

[0012] The user terminal 100 shown in Fig. 1 is a terminal device owned by a user U. For example, the user U can operate the user terminal 100 and view news content distributed from the information processing device 1 through a news site. Note that, although Fig. 1 illustrates an example in which the user terminal 100 is a smartphone, the user terminal 100 may be other devices such as a PC (Personal Computer).

[0013] 1 is a terminal owned by a creator of news content (news article). A creator may be an individual or belong to a variety of media such as a newspaper company or television, and creates news articles.

[0014] Generally, news sites pay remuneration to creators of news articles according to the number of views of the articles, etc. Meanwhile, generative models (generative AI) that generate text have become widespread in recent years, and it is expected that news sites will also distribute news articles generated by generative models.

[0015] In such cases, the generative model is expected to refer to news articles produced by each creator and generate new news articles, but it is also necessary to establish compensation settings for the creators of the source news articles.

[0016] Therefore, in this embodiment, a remuneration is set for each creator according to the relevance between the content of the news article generated by the generative model and the news article created by each creator.

[0017] 1, the information processing device 1 first acquires content (news articles) produced by a producer from the producer terminal 200 (step S1). Next, the information processing device 1 generates aggregate content from multiple contents using a generation model that generates answers to prompts (step S2).

[0018] For example, the information processing device 1 accepts a question from a user U through the user terminal 100, selects a news article corresponding to the question, and generates the answer as collective content using a generative model. In the example shown in Fig. 1, the question from the user U is "Please tell me more about XX", and the information processing device 1 generates the answer using the generative model.

[0019] For example, as shown in Fig. 1, the aggregate content serving as an answer is content generated by referring to multiple articles (contents) corresponding to the question. In other words, the aggregate content can be said to be content that summarizes multiple news articles in response to a question by a user U.

[0020] The information processing device 1 provides the generated aggregate content to the user U (step S3), and then sets a reward for each article (content) according to the relevance between the aggregate content and each article (step S4). For example, as shown in Fig. 1, the information processing device 1 sets a reward according to the number of times each article in the aggregate content is referenced.

[0021] More specifically, the information processing device 1 generates aggregated content consisting of multiple sections (P1 to P3 in FIG. 1). The information processing device 1 then counts the total number of times each section has been referenced as the number of references, with each article being referenced as "1" for each section. The information processing device 1 then sets the number of references x unit price (here, 100 yen per unit price) as the reward for each article. Note that the information processing device 1 may divide the aggregated content into sections for each topic.

[0022] Furthermore, when a predetermined condition is met, such as when there is only one article that is the reference source as in section P3 in FIG. 1, the unit price is increased and the reward is set. For example, in such a case, the information processing device 1 varies the unit price according to the importance of each article when generating the collective content. This makes it possible to set the reward appropriately according to the importance of each article. Note that the predetermined condition is not limited to the importance, and any condition may be set.

[0023] In this way, when generating aggregate content using a generative model, the information processing device 1 according to the embodiment sets a reward for each article according to the relevance between the aggregate content and each article. Therefore, the information processing device 1 according to the embodiment can set an appropriate reward.

[0024] Next, a business model of a news site utilizing a generative model will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of a remuneration system for a news site according to an embodiment. As shown in Fig. 2, a media company (producer) creates an article and then transmits the article to a platform provider of the news site (step S11).

[0025] The platform provider provides the advertisers with advertising space for news articles (step S12). That is, the platform provider sells the advertisers the right to place advertisements in each news article.

[0026] Next, the advertiser transmits an advertisement to be placed in the news article to the platform provider (step S13). Note that steps S12 and S13 may be automatically processed by the platform provider.

[0027] Thereafter, the platformer publishes the article (step S14) and provides the aggregated content to the user in response to the user's access, etc. (step S15). When the user browses the aggregated content (step S16), the platformer pays a fee to the media company in response to the relevance of the aggregated content to the article (step S17).

[0028] In this manner, in the system according to the embodiment, by selling advertising space or advertising publishing rights to advertisers, it is possible to pay compensation to media companies using advertising fees as a source of funds.

[0029] [2. Information Processing Device] Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 3, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0030] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) by wire or wirelessly, and transmits and receives information to and from each of the user terminal 100, the creator terminal 200, etc. via the communication network.

[0031] The storage unit 3 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. The storage unit 3 has a content storage unit 31, a user information storage unit 32, and a model storage unit 33.

[0032] The content storage unit 31 stores various information related to the content. The content is a news article distributed on a news site. Fig. 4 is a diagram showing an example of information stored in the content storage unit 31 according to the embodiment.

[0033] 4, the content storage unit 31 stores information items such as "content ID," "creator," and "content" in association with each other. The "content ID" is an identifier for identifying each piece of content (news article).

[0034] "Producer" is the creator of the content identified by the corresponding content ID. Note that the producer may be an individual or a company to which the producer belongs (such as a newspaper company).

[0035] "Content" is data related to the content identified by the corresponding content ID. For example, the content may include a title, a thumbnail image, and a content body (news article). The content may also include the number of views, the number of likes, and comments on the content by experts and users.

[0036] Returning to the description of Fig. 3, the user information storage unit 32 will be described. The user information storage unit 32 stores various pieces of information related to users. Fig. 5 is a diagram showing an example of information stored in the user information storage unit 32 according to the embodiment.

[0037] 5, the user information storage unit 32 stores information items such as "user ID," "registration information," and "browsing history" in association with each other. The "user ID" is an identifier for identifying each user.

[0038] The "registration information" is information registered on a news site by a user identified by a corresponding user ID. For example, the registration information includes information on demographic attributes such as name, age, address, and occupation, and information on psychographic attributes such as hobbies.

[0039] The "browsing history" is the browsing history of a user identified by the corresponding user ID on a news site. The browsing history stores information on the news articles viewed and the viewing dates and times in chronological order.

[0040] Returning to the explanation of FIG. 3, the model storage unit 33 will be explained. The model storage unit 33 stores a generative model. The generative model generates collective content that summarizes the contents of news articles posted on a news site. For example, the generative model is a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers).

[0041] Next, the control unit 4 will be described. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0042] As shown in Fig. 3, the control unit 4 includes an acquisition unit 41, a generation unit 42, a provision unit 43, an estimation unit 44, and a setting unit 45, and realizes or executes the functions and actions of information processing described below. The internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 3, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units in the control unit 4 is not limited to the connection relationship shown in Fig. 3, and may be other connection relationships.

[0043] The acquisition unit 41 acquires contents (news articles) from the creator through the creator terminal 200. The acquisition unit 41 registers the acquired contents in the content storage unit 31. The acquisition unit 41 also acquires, for example, information related to advertisements from advertisers and stores it in the storage unit 3.

[0044] The generation unit 42 generates aggregate content from a plurality of contents using a generation model that generates answers to prompts. When a user accesses a news site, the generation unit 42 generates aggregate content based on each news article at the time when the user accesses the news site.

[0045] For example, the generation unit 42 picks up themes that correspond to the interests of each user and news articles that are attracting attention from the content storage unit 31, and inputs them into the generation model to generate aggregate content and titles of the aggregate content. For example, the aggregate content is content that summarizes multiple news articles that correspond to each theme. At this time, the generation unit 42 inputs information about the user in addition to the news articles into the generation model.

[0046] The information about the user includes demographic attributes and psychographic attributes. That is, the generator 42 inputs the demographic attributes and psychographic attributes as prompts to the generative model to generate aggregate content summarizing each news article according to the user's interests, etc.

[0047] Furthermore, the generation unit 42 receives a question from the user and inputs the question as a prompt into the generation model, thereby generating an answer to the question as aggregate content. Furthermore, after completing generation of the aggregate content, the generation unit 42 generates an expected question of the user regarding the aggregate content.

[0048] For example, the generation unit 42 inputs user information to the generation model that has finished generating the aggregate content, and instructs the generation model to generate questions anticipated by the user. Note that the anticipated questions may be generated using a learning model that has learned the relationship between questions from other users and the aggregate content.

[0049] The providing unit 43 provides the user with the collective content generated by the generating unit 42. For example, the generating unit 42 generates information about a news screen including the collective content, and provides the information to the user terminal 100.

[0050] 6 is a diagram illustrating an example of a news screen according to an embodiment. For example, when a user accesses a news site, a news screen is displayed. As shown in FIG. 6, the news screen includes a news section A1, a question tab section A2, and a question input section A3.

[0051] The news column A1 displays the title and summary of each news article. By selecting a news item of interest, the user can view the corresponding news article. The question tab column A2 displays tabs for questions anticipated in advance regarding the news item displayed in the news column A1.

[0052] For example, the news screen can accept questions from users through a question tab. Also, the question input field A3 is a field where users input questions in text. When users input questions in text or by voice into the question input field A3, the news screen can accept questions from users.

[0053] The generation unit 42 further generates aggregate content using the question received from the user through the news screen as a prompt. For example, in this case, the provision unit 43 provides aggregate content in a chat format in response to the question from the user, and further displays expected questions in the question tab field A2.

[0054] In other words, by displaying anticipated questions, the user can be encouraged to ask questions, and the display can function as a facilitator for the user to gain a deeper understanding of the content.

[0055] In addition, the news screen provided by the providing unit 43 is not limited to the example in Fig. 6, and may be a screen in which titles of news articles are displayed as a word cloud. Fig. 7 is a diagram showing an example of the word cloud according to the embodiment.

[0056] As shown in Figure 7, the word cloud displays the title of each news article in a table format. In addition, the name of the publisher of the corresponding news article is displayed in the upper right corner of the title.

[0057] For example, in this case, the providing unit 43 picks out news articles to be provided to the user according to the user's interests and the attention of each news article (for example, the number of page views, etc.), and provides the titles of the articles to the user as a word cloud.

[0058] For example, in this case, the news site can receive publication fees for news articles from media companies by selling the display format of the word cloud to the media companies, as described below. Specifically, the publication fee varies depending on the size, color, and position of the title on the word cloud. For example, the larger the title on the word cloud and the more prominent the color, the higher the publication fee.

[0059] In this way, a news site can collect publication fees for news articles, and thereby operate soundly with the publication fees as a source of revenue. Although the case where the titles of news articles are displayed on a word cloud has been described here, the titles of collective content may also be displayed on a word cloud. For example, the titles of collective content displayed in the news section A1 of FIG. 6 may be displayed in a word cloud.

[0060] Furthermore, the providing unit 43 provides the aggregate content generated by the generating unit 42 to the user. The providing unit 43 selects an advertisement when providing the aggregate content.

[0061] For example, the providing unit 43 selects an advertisement corresponding to a query included in a user's question or a query included in the aggregate content as an advertisement to be provided together with the aggregate content.

[0062] At this time, the providing unit 43 selects the advertisement in consideration of the attributes of the user to whom the advertisement is to be provided, in addition to the query. The attributes of the user include demographic attributes and psychographic attributes.

[0063] In addition, when selecting an advertisement, the providing unit 43 executes exclusive control based on the original article of the collective content. More specifically, for example, when the original article is about a traffic accident, the providing unit 43 selects an advertisement by excluding advertisements related to cars and advertisements related to alcoholic beverages from the selection targets.

[0064] For example, the providing unit 43 selects one advertisement for each section of the collective content. In this case, the providing unit 43 selects an advertisement according to the content of each section.

[0065] For example, in collective content related to a certain athlete, advertisements related to sports goods and protein may be selected in a section related to the sport, and advertisements related to food such as protein may be provided in a section related to food, etc.

[0066] Here, an example of advertisement placement in collective content will be described with reference to Fig. 8 and Fig. 9. Fig. 8 and Fig. 9 are diagrams showing an example of advertisement placement according to an embodiment. As shown in Fig. 8, it is assumed that advertisements AD1 to AD3 corresponding to sections P1 to P3 of collective content, respectively, are selected.

[0067] In this case, the advertisements displayed in the advertisement frame Ac are switched according to the scrolling of the screen while the display position of the advertisement frame Ac is fixed. That is, when the user is reading section P1, advertisement AD1 according to the contents of section P1 is displayed, and when the user is reading section P2, advertisement AD2 according to the contents of section P2 is displayed.

[0068] That is, in this case, the advertisements displayed in the advertisement frame Ac are dynamically switched according to the contents of each section, so that the appeal of each advertisement can be increased. For example, in FIG. 8, assume that the user is interested in the advertisement AD2 displayed in the advertisement frame Ac. In this case, the providing unit 43 may also provide a function of pinning (fixing display) the advertisement AD2 in the advertisement frame Ac based on the user's operation, a function of holding the advertisement AD2 on the screen by a drag or flick operation, or a function of stocking the advertisement AD2 in a storage area so that the user can look back on the advertisement AD2 later.

[0069] 9, an advertisement space Ac may be provided in an arbitrary section of the aggregate content. For example, in this case, the providing unit 43 may request the generating unit 42 to generate aggregate content including the selected advertisement. For example, in this case, the generating unit 42 inputs a prompt including the aggregate content and the advertising target to a generation model, and generates aggregate content including the advertising target.

[0070] For example, as shown in Fig. 9, sections P1 and P2 are collective contents, and the area following section P2 is advertisement space Ac, in which articles (text) related to advertisement targets are posted. Note that the advertisement posted in advertisement space Ac in Fig. 9 is not limited to text, and may be an advertisement image.

[0071] In this way, the providing unit 43 provides collective content including advertisements corresponding to the collective content, so that the operator of the news site can collect advertising fees from the advertiser. Note that the providing unit 43 may provide collective content that leads to a search site, for example.

[0072] In this case, the providing unit 43 provides collective content displaying a query included in the collective content. For example, in this case, when a user selects a query, a site corresponding to the query is displayed through a search site. In this case, for example, the search site can earn revenue by displaying so-called listing advertisements or the like.

[0073] Furthermore, the providing unit 43 may provide collective content including hyperlinks to each reference source, and, for example, when the reference source is a paid article, may guide the user to the paid article. For example, in this case, a portion of the sales of the paid article may be paid to the news site.

[0074] The estimation unit 44 estimates the details of the aggregate content provided by the providing unit 43 and the relevance of the content. The estimation unit 44 estimates the relevance of the details of the aggregate content and each of the news articles that are reference sources.

[0075] Specifically, the estimation unit 44 divides the aggregate content into sections and estimates related news articles for each section. For example, the relatedness here refers to whether or not a news article was a reference source.

[0076] At this time, the estimation unit 44 may estimate the importance of each news article. For example, the importance here is an index regarding whether or not each news article could be substituted when generating aggregate content.

[0077] For example, if the news article can be substituted by another news article, i.e., if there are many news articles with similar content, the estimation unit 44 estimates that the importance is low, and if there are few news articles with similar content, it determines that the importance is high.

[0078] The setting unit 45 sets a reward for the content that is the reference source of the aggregate content according to the relevance estimated by the estimation unit 44. Specifically, in the aggregate content, a fee is set in advance for each section, and the fee is allocated to the content that is the reference source of each section.

[0079] That is, in this case, the fewer the referral sources in one section, the higher the reward is set by the setting unit 45. Note that the fee may be dynamically changed according to the attributes of the user, etc.

[0080] Furthermore, the setting unit 45 sets a reward according to the number of references to the aggregate content of each news article. That is, the setting unit 45 sets a higher reward for a news article that contributes to more answers to the user's question. In this case, the setting unit 45 sets a higher reward for a news article that has been referenced more frequently to the aggregate content. Note that the user's question may be an expected question or may be a question input by the user.

[0081] Once the setting unit 45 sets the remuneration, the operator of the news site pays the remuneration to each media company.

[0082] The setting unit 45 also sets a publishing fee for each news article on the news site. For example, the setting unit 45 sets the publishing fee according to the size, color, and arrangement of characters in the word cloud shown in Fig. 7. For example, the setting unit 45 sets a higher publishing fee for larger characters and more conspicuous colors in the word cloud.

[0083] In this case, the compensation for each news article is offset against the publication fee, and the net compensation is paid by the news site operator to each media company.

[0084] [3. Processing flow] Next, a process procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of the process procedure of the setting process according to the embodiment.

[0085] 10, the information processing device 1 acquires content (news articles) from a media company (producer) (step S101). Next, the information processing device 1 generates aggregate content (step S102). Note that the information processing device 1 may generate aggregate content when a user accesses a news site, or may generate aggregate content after receiving a question from a user.

[0086] Next, the information processing device 1 provides the generated aggregate content to the user (step S103). Next, the information processing device 1 estimates the relevance between the aggregate content and each piece of content (step S104).

[0087] Then, the information processing device 1 sets a reward according to the estimated relevance (step S105) and ends the process.

[0088] 4. Modifications In the above embodiment, the content is a news article, but the present invention is not limited to this. The content may include video and audio. In the above embodiment, the content is distributed on a news site, but the present invention is not limited to this. The content may be distributed through various SNSs, video sites, etc.

[0089] 5. Effects The information processing device 1 according to the embodiment includes a generation unit 42 that generates collective content from a plurality of contents using a generation model that generates answers to prompts, a provision unit 43 that provides the collective content generated by the generation unit 42 to a user, an estimation unit 44 that estimates the content of the collective content provided by the provision unit 43 and the relevance between the content, and a setting unit 45 that sets a reward for the content that serves as a reference for the collective content in accordance with the relevance estimated by the estimation unit 44.

[0090] The estimation unit 44 estimates the importance of the content that is the reference source in the aggregate content, and the setting unit 45 sets a reward according to the importance. The setting unit 45 also sets a reward according to the number of times the content is referenced.

[0091] The providing unit 43 provides aggregate content generated from content according to the user. The generating unit 42 generates aggregate content generated from content corresponding to a question received from the user.

[0092] The providing unit 43 provides collective content consisting of multiple sections, and the setting unit 45 sets a reward for each section. The providing unit 43 provides advertisements according to the content of each section. The generating unit 42 generates multiple collective contents, and the providing unit 43 provides the titles of the collective contents as a word cloud.

[0093] By performing any one or a combination of the above-described processes, the information processing device according to the present application can set an appropriate remuneration for the creator of the content.

[0094] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 11. Fig. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0095] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0096] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0097] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 11, the output devices and the input devices are collectively referred to as "input / output devices") via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0098] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0099] For example, when the computer 1000 functions as an information processing device according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0100] [7. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0101] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0102] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0103] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0104] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0105] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0106] 1. Information processing device 2. Communications Department 3 Storage section 4. Control Unit 31 Content storage unit 32 User information storage unit 33 Model Memory Section 41 Acquisition Department 42 Generation part 43 Providing Department 44 Estimation part 45 Setting section 100 user terminals 200 Creator Terminal U User

Claims

1. A generation unit that generates aggregate content from a plurality of contents using a generative model that generates answers to prompts; a providing unit that provides the collective content generated by the generating unit to a user; an estimation unit that estimates the details of the collective content provided by the provision unit and a relevance to the content; a setting unit that sets a reward for the content that is a reference source of the collective content in accordance with the relevance estimated by the estimation unit; An information processing device comprising:

2. The estimation unit is Estimating the importance of the content that is the reference source in the collective content; The setting unit is Setting the reward according to the importance 2. The information processing apparatus according to claim 1,

3. The setting unit is Setting the reward according to the number of views of the content 2. The information processing apparatus according to claim 1,

4. The providing unit is To provide the collective content generated from the content according to the user.

2. The information processing apparatus according to claim 1,

5. The generation unit is generating the collective content from the content corresponding to the question received from the user; 5. The information processing apparatus according to claim 4,

6. The providing unit is providing said collective content consisting of a plurality of sections; The setting unit is Set the above rewards for each section 2. The information processing apparatus according to claim 1,

7. The providing unit is To provide content-specific advertisements for each of the above sections The information processing device according to claim 6 .

8. The generation unit is generating a plurality of said collective contents; The providing unit is providing titles of said collective content as a word cloud; 2. The information processing apparatus according to claim 1,

9. 1. A computer-implemented information processing method, comprising: A generation step of generating aggregate content from a plurality of contents using a generative model that generates answers to prompts; a providing step of providing the collective content generated by the generating step to a user; an estimation step of estimating the details of the collective content provided by the providing step and a relevance of the collective content to the content; a setting step of setting a reward for the content that is a reference source of the collective content in accordance with the relevance estimated by the estimation step; 13. An information processing method comprising:

10. A generation step of generating aggregate content from a plurality of contents using a generative model that generates answers to prompts; a providing step of providing the collective content generated by the generating step to a user; an estimation step of estimating the details of the collective content provided by the provision step and a relevance of the collective content to the content; a setting step of setting a reward for the content that is a reference source of the collective content in accordance with the relevance estimated by the estimation step; An information processing program characterized by causing a computer to execute the above.

Images