Information processor, method for processing information, and information processing program

Abstract

To provide a proper content to a user.SOLUTION: The information processor according to the present invention includes: a collection unit for collecting the distribution manner of each content in a distribution domain for distributing a content; a generation unit for generating a summary content from each content according to the distribution manner collected by the collection unit; and a provision unit for providing a summary content generated by the generation 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, there is a technique for selecting a representative article from among a plurality of news articles having similar contents and providing the selected representative article to a user with regard to news articles distributed via the Internet (see, for example, Patent Document 1). [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 conventional technology, only representative articles are selected and provided, and there is room for improvement in providing appropriate content to users.

[0005] The present invention has been made in view 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 providing appropriate content to a user. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the information processing device of the present invention includes a collection unit that collects distribution modes of each content in a distribution domain where the content is distributed, a generation unit that generates summary content from each of the contents in accordance with the distribution modes collected by the collection unit, and a provision unit that provides the summary content generated by the generation unit. Effect of the Invention

[0007] According to the present invention, appropriate content can be provided to a user. [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 block 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 content storage unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in a user information storage unit according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a news screen according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a word cloud according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of a processing procedure of the providing process according to the embodiment. [Figure 8] FIG. 8 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. For example, the information processing device 1 provides news articles (corresponding to an example of contents) to each user through a news site. The news site corresponds to an example of a distribution domain according to the embodiment.

[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 news article creator. The creator may belong to a variety of media, such as a newspaper company or a television station, and creates news articles.

[0014] Incidentally, in recent years, generative models (generative AI) that generate text have become increasingly popular, and it is expected that news sites will also start distributing news articles generated by generative models.

[0015] In such cases, it is expected that the generative model will refer to the news articles created by each creator and generate new news articles. However, in such cases, there is room for improvement in providing appropriate content to users.

[0016] For example, when generating content using a generative model, different content will be generated depending on the evaluation index used. Therefore, it is necessary to design appropriate evaluation indexes.

[0017] Therefore, the information processing device 1 according to the embodiment generates contents using a generative model with the delivery mode of each content as an evaluation index, and provides the contents to the user.

[0018] 1, first, contents (news articles) created by a creator are acquired from the creator terminal 200 (step S1). Next, the information processing device 1 distributes each content (news article) to the user terminal 100 through a news site (step S2).

[0019] Next, the information processing device 1 collects the delivery mode of each content (step S3). Here, the delivery mode includes attributes of the user to whom the content is delivered, reactions by the user, the number of page views, comments by experts, etc. Furthermore, the reactions include the number of likes for the content, comments, whether or not the content was shared on SNS, etc. Furthermore, the delivery mode may include highlighting of text by users, completion rate, etc.

[0020] Then, for example, when the information processing device 1 receives a question from a user (step S5), it generates an answer to the question as summary content (step S5). For example, as shown in Fig. 1, the information processing device 1 inputs "Please answer the user's question after understanding the content and distribution mode of the content" as a system side prompt P into the generation model, and also inputs the content posted on the news site and the distribution mode of each piece of content into the generation model. The content includes the title of each article on the news site, the date and time of occurrence of the event introduced in each news, and the creator (or media company) of the news article.

[0021] Next, the information processing device 1 inputs a prompt q, which is a question from the user, to the generation model. In the example shown in Fig. 1, the prompt q from the user is "Please tell me the main news today," and the generation model generates summary content corresponding to the user's question after understanding the content and delivery mode of each content.

[0022] That is, the information processing device 1 according to the embodiment generates summary content using a generation model with the delivery mode of each news article as an evaluation axis. In this way, the information processing device 1 according to the embodiment can provide summary content that takes into account how each news article is viewed on a news site, and therefore can provide appropriate content to the user.

[0023] [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. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 2, 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.

[0024] 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.

[0025] 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.

[0026] The content storage unit 31 stores various information related to the content. The content is a news article distributed on a news site. Fig. 3 is a diagram showing an example of information stored in the content storage unit 31 according to the embodiment.

[0027] 3, 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).

[0028] "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).

[0029] "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.

[0030] Returning to the description of Fig. 2, the user information storage unit 32 will be described. The user information storage unit 32 stores various pieces of information related to users. Fig. 4 is a diagram showing an example of information stored in the user information storage unit 32 according to the embodiment.

[0031] 4, 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.

[0032] 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.

[0033] 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.

[0034] 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 summary 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).

[0035] 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).

[0036] As shown in Fig. 2, the control unit 4 includes an acquisition unit 41, a distribution unit 42, a collection unit 43, a generation unit 44, and a provision 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. 2, 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. 2, and may be other connection relationships.

[0037] The acquisition unit 41 acquires contents (news articles) from the creator via the creator terminal 200. The acquisition unit 41 registers the acquired contents in the content storage unit 31.

[0038] The distribution unit 42 distributes each content to each user terminal 100 through the news site. For example, the distribution unit 42 picks up content from the content storage unit 31 in response to access to the news site from the user terminal 100. For example, the distribution unit 42 picks up content from the content storage unit 31 in response to user attributes, etc.

[0039] The delivery unit 42 picks up content from the content storage unit 31 according to the user's interests, the number of page views, the number of actions, etc. Then, the delivery unit 42 delivers information including the picked up content to the user terminal 100 that is the access source.

[0040] The collection unit 43 collects the delivery mode of each piece of content delivered by the delivery unit 42. For example, the collection unit 43 collects various actions for each piece of content. The collection unit 43 collects, as the delivery mode, the number of page views, comments from experts or users to the comment section for the news article, actions to buttons such as "Like," "Learned," "Easy to understand," and "New perspective," highlights added to the news article by users, the completion rate of each news article, and the like.

[0041] At this time, the collection unit 43 may determine whether the comment on the news article corresponds to a positive comment, a negative comment, or a neutral comment, for example. Note that such a determination can be made, for example, by a natural language processing model.

[0042] The generation unit 44 generates summary content from each piece of content in accordance with the delivery mode collected by the collection unit 43. The generation unit 44 receives a question from a user, for example, via a news screen of a news site, and generates an answer corresponding to the user's question using a generative model.

[0043] 5 is a diagram illustrating an example of a news screen according to an embodiment. For example, when a user accesses a news site, the news screen is displayed. As shown in FIG. 5, the news screen includes a news section A1, a question tab section A2, and a question input section A3.

[0044] 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.

[0045] For example, a news site can accept questions from users through a question tab. Also, the question input field A3 is a field where the user inputs a question in text. The news site can accept questions from users by inputting a question in text or by voice into the question input field A3.

[0046] Prior to inputting a prompt regarding a user's question, the generation unit 44 inputs, for example, information regarding each news article and the distribution mode of each news article into the distribution model, and further inputs a prompt on the system side.

[0047] The system side prompt is, for example, "Please answer the user's questions after understanding the content and the delivery mode of the content." In this case, a condition such as "Please answer the user's questions while placing emphasis on the content whose delivery mode satisfies a certain condition" may be specified as the system side prompt. In this case, the generation model instructs the generation model to generate summary content by placing emphasis on the content with a large number of pageviews, number of actions, etc.

[0048] The generating unit 44 may generate summary content by selecting content to be input as a prompt in response to a user's question. In this case, the generating unit 44 selects content including, for example, a keyword included in the user's question.

[0049] The generation unit 44 then inputs the question received from the user as a prompt to the generation model, thereby generating summary content using the generation model. The generation unit 44 may also input information about the user who is the questioner as a prompt to the generation model. The information about the user is, for example, information about the user's age, sex, and interests. The user's interests can be estimated, for example, from the user's browsing history of each news article.

[0050] That is, by inputting information about the user into the generation model, summary content according to the user's interests, etc. can be generated. For example, in this case, the generation unit 44 may generate summary content according to the user's attributes, etc., based on a concept according to the similarity extension of each user. That is, the generation unit 44 may generate summary content by regarding content that is of high interest to users who have similar attribute information, etc., to the target user as content that is of high interest to the target user as well.

[0051] In this way, the generation unit 44 generates summary content using information about the delivery mode as a prompt. This allows the generation unit 44 to generate summary content that takes into consideration, for example, the number of pageviews of each news article, actions and comments of each user for each news article, and the like.

[0052] The generation unit 44 may generate expected questions for the user regarding the summary content by using the generation model. For example, the expected questions are questions for the user to understand the summary content more deeply. That is, the generation unit 44 functions as a facilitator by generating expected questions.

[0053] In the above example, the case where summary content is generated in response to a question from a user has been described, but the present invention is not limited to this. That is, summary content may be generated without receiving a question from a user. In this case, the generating unit 44 may generate summary content and its title corresponding to the user's interests in advance based on each news article and the distribution mode.

[0054] For example, in this case, the generating unit 44 generates the news in advance based on each news article and the distribution mode at the timing when the user accesses the news site.

[0055] Returning to the explanation of FIG. 2, the providing unit 45 will be explained. The providing unit 45 provides the summary content generated by the generating unit 44 to the user. When the generating unit 44 generates summary content for a question accepted from the user, the providing unit 45 provides the summary content to the user in a chat format. In this case, the providing unit 45 also provides anticipated questions. Furthermore, the providing unit 45 accepts further questions from the user regarding the provided summary content, and the generating unit 44 generates summary content for the question by the user.

[0056] Furthermore, when the generating unit 44 generates summary content without accepting a question from the user, the providing unit 45 provides the titles of each summary content as a word cloud. Fig. 6 is a diagram showing an example of the word cloud according to the embodiment.

[0057] As shown in Fig. 6, the title of each summary content is displayed in a different display mode in the word cloud. In the word cloud, the title of a summary content that is close to the user's interests or that is related to a topic that is currently attracting attention is displayed larger and in a more prominent color.

[0058] Then, when the user selects each title, the providing unit 45 provides the user with summary content corresponding to the title. That is, in such a case, it is possible to provide the user with summary content of the title that has caught his / her interest.

[0059] [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. 7. Fig. 7 is a flowchart showing an example of the process procedure of the providing process according to the embodiment.

[0060] 7, the information processing device 1 distributes each content to a user through a news site (step S101). Next, the information processing device 1 collects the distribution mode of each content (step S102).

[0061] Next, the information processing device 1 accepts a question from the user (step S103), and generates summary content corresponding to the user's question based on each piece of content and the delivery mode of each piece of content (step S104).

[0062] Then, the information processing device 1 provides the summary content to the user who is the questioner (step S105), and ends the process.

[0063] 4. Modifications In the above embodiment, the content is a news article, but the present invention is not limited thereto. The content may include video and audio. In the above embodiment, the information processing device 1 collects the distribution mode of a news site, but the present invention is not limited thereto. For example, the information processing device 1 may collect the distribution mode of each content in various SNSs and video sites where the content is distributed.

[0064] 5. Effects The information processing device 1 according to the embodiment includes a collection unit 43 that collects the distribution mode of each content in a distribution domain to which the content is distributed, a generation unit 44 that generates summary content from each content according to the distribution mode collected by the collection unit 43, and a provision unit 45 that provides the summary content generated by the generation unit 44.

[0065] Furthermore, the generation unit 44 generates summary content by inputting the content details, the delivery mode, and a prompt to a generation model that generates answer sentences to questions.

[0066] The generating unit 44 generates answer sentences to questions from users as summary content. The collecting unit 43 collects information on the title, posting date and time, creator, and number of views of the content distributed in the distribution domain as the distribution mode, and the generating unit 44 generates summary content according to the title, posting date and time, creator, and number of views of the content.

[0067] Furthermore, the collection unit 43 collects information on user reactions to each piece of content as a distribution mode, and the generation unit 44 generates summary content in accordance with the reactions.

[0068] The collection unit 43 also collects comments from experts on the content as a distribution form, and the generation unit 44 generates summary content in response to the comments from the experts. The generation unit 44 also generates anticipated questions for the summary content, and the provision unit 45 provides the anticipated questions together with the summary content.

[0069] By performing any one or a combination of the above-described processes, the information processing device according to the present application can provide appropriate content to the user.

[0070] [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. 8. Fig. 8 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.

[0071] 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.

[0072] 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.

[0073] 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. 8, 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.

[0074] 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.

[0075] 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.

[0076] [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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0081] 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]

[0082] 1. Information processing device 2. Communications Department 3 Storage section 4. Control section 31 Content storage unit 32 User information storage unit 33 Model Memory Section 41 Acquisition Department 42 Distribution Department 43 Collection Department 44 Generation part 45 Providing Department 100 user terminals 200 Creator Terminal U User

Claims

1. A collection unit that collects distribution modes of each content in a distribution domain that distributes the content; a generation unit that generates summary content from the respective contents in accordance with the delivery modes collected by the collection unit; a providing unit that provides the summary content generated by the generating unit; An information processing device comprising:

2. The generation unit is generating the summary content by inputting the content details and the delivery mode as prompts to a generation model that generates answer sentences to questions; 2. The information processing apparatus according to claim 1,

3. The generation unit is Generating answer sentences to questions posed by users as the summary content.

3. The information processing apparatus according to claim 2,

4. The collecting unit includes: Collect the distribution status including the title, creator, number of views, and date and time of the news content distributed in the distribution domain; The generation unit is Generating the summary content according to the title, creator, number of views, and date and time of occurrence of the event introduced in the news.

2. The information processing apparatus according to claim 1,

5. The collecting unit includes: Collecting information regarding user reactions to each of the contents as the delivery mode; The generation unit is generating the summary content in response to the reaction; 2. The information processing apparatus according to claim 1,

6. The collecting unit includes: Collecting expert comments on the content as the distribution form; The generation unit is generating said summary content in response to comments from said experts; 2. The information processing apparatus according to claim 1,

7. The generation unit is generating hypothetical questions for the summary content; The providing unit is Providing said anticipated questions along with said summary content 2. The information processing apparatus according to claim 1,

8. 1. A computer-implemented information processing method, comprising: A collection step of collecting information on the distribution mode of each content in a distribution domain to which the content is distributed; a generating step of generating summary content from each of the contents collected in the collecting step in accordance with the delivery manner; a providing step of providing the summary content generated by the generating step; 13. An information processing method comprising:

9. A collection step of collecting information on the distribution mode of each content in a distribution domain that distributes the content; a generation step of generating summary content from each of the contents collected by the collection step in accordance with the delivery manner; a providing step of providing the summary content generated by the generating step; An information processing program characterized by causing a computer to execute the above.

Images