JP7801288B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Technologies related to information distribution via the Internet have been known for some time. One example of such technology is a technology that accepts article submissions from multiple users via a network, edits the articles into an electronic newspaper format, and publishes them.

Japanese Patent Application Laid-Open No. 2008-052426

However, the above-mentioned technology does not necessarily enable users to understand whether the reliability of the content is guaranteed.

For example, the technology described above merely publishes articles posted by users, and does not allow users to determine whether the reliability of the content is guaranteed.

This application was made in light of the above, and aims to enable users to understand whether the reliability of content is guaranteed.

The information processing device according to the present application is characterized by having an acquisition unit that acquires event information related to a predetermined event; a generation unit that generates content related to the event by inputting the event information acquired by the acquisition unit and an instruction sentence that instructs a model trained to generate answers to input questions to output content related to the event indicated by the event information; and a provision unit that provides the content generated by the generation unit to a user together with guarantee information indicating whether the content has been guaranteed by a guarantor who guarantees the reliability of the content.

One aspect of this embodiment has the effect of allowing users to understand whether the reliability of content is guaranteed.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating an example of the configuration of the information processing device 10 according to the embodiment. FIG. 3 is a diagram showing an example of the guarantor information database 31. As shown in FIG. FIG. 4 is a diagram showing an example of the content information database 32. As shown in FIG. FIG. 5 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10.

Below, detailed explanations are given of the information processing device, information processing method, and information processing program (hereinafter referred to as "embodiments") according to the present application, with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to these embodiments. Furthermore, identical components in the following embodiments are designated by the same reference numerals, and duplicate explanations will be omitted.

1. Embodiment
Information processing implemented by an information processing device or the like according to the present 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 in Fig. 1, the information processing according to the embodiment is implemented by an information processing device 10, which is an example of the information processing device according to the present application.

As shown in FIG. 1, the information processing system 1 according to the embodiment includes an information processing device 10, a user terminal 100, a guarantor terminal 200, and an external server 300. The information processing device 10, the user terminal 100, the guarantor terminal 200, and the external server 300 are connected to each other via a network N (see, for example, FIG. 2) via a wired or wireless connection so that they can communicate with each other. The network N is, for example, a wide area network (WAN) such as the Internet. Note that the information processing system 1 shown in FIG. 1 may include multiple information processing devices 10, multiple user terminals 100, multiple guarantor terminals 200, and multiple external servers 300.

The information processing device 10 shown in FIG. 1 is an information processing device that realizes information processing according to the embodiment, and is realized, for example, by a server device or a cloud system. In the example of FIG. 1, the information processing device 10 is an information processing device that provides a news service that provides content showing news articles collected from various mass media such as newspapers, publishers, and broadcasting stations (television stations, radio stations), for example.

The information processing device 10 may also function as a web server that provides a website related to a news service. The information processing device 10 may also be a device that distributes information to the user terminal 100 or the guarantor terminal 200 to be displayed on an application related to a news service (hereinafter, sometimes referred to as a "news app") installed on the user terminal 100 or the guarantor terminal 200. The information processing device 10 may also be a server that distributes the news app data itself. The information processing device 10 may also function as a distribution device that distributes control information to the user terminal 100 or the guarantor terminal 200. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). The news app itself distributed from the information processing device 10 may also be considered to be control information.

The user terminal 100 shown in Figure 1 is an information processing device used by a user. The user terminal 100 may be realized, for example, by a smartphone, tablet terminal, notebook PC (Personal Computer), desktop PC, mobile phone, or PDA (Personal Digital Assistant). In the example shown in Figure 1, the user terminal 100 is a smartphone used by a user.

The guarantor terminal 200 shown in Figure 1 is an information processing device used by a guarantor (e.g., a journalist from various mass media) who guarantees the reliability of content. The guarantor terminal 200 may be realized, for example, as a smartphone, tablet terminal, laptop PC, desktop PC, mobile phone, or PDA. In the example shown in Figure 1, the guarantor terminal 200 is shown as a smartphone used by the guarantor.

In addition, the user terminal 100 and the guarantor terminal 200 display the information provided by the information processing device 10 using a web browser or application. When the user terminal 100 and the guarantor terminal 200 receive control information from the information processing device 10 or the like to realize the display processing of information, they realize the display processing in accordance with the control information.

The external server 300 shown in FIG. 1 is a server device that provides various services to the user terminal 100 and the guarantor terminal 200. For example, the external server 300 manages information used to generate content provided in the news service provided by the information processing device 10. To give a specific example, the external server 300 manages primary information about an event, such as the category of the event that occurred, the date and time the event occurred, the location where the event occurred, people and organizations related to the event that occurred, and the details of the event that occurred.

The information processing performed by the information processing device 10 will be described below using FIG. 1. In the following description, the user terminals 100 will be referred to as user terminals 100-1 to 100-N (N is any natural number) depending on the user using the user terminal 100. For example, user terminal 100-1 is the user terminal 100 used by a user (user U1) identified by user ID "UID#1." In the following description, user terminals 100-1 to 100-N will be referred to as user terminal 100 when there is no particular distinction between them. In the following description, user terminal 100 may be considered the same as the user. In other words, in the following description, user can also be read as user terminal 100.

In the following explanation, the guarantor terminals 200 will be referred to as guarantor terminals 200-1 to 200-N (where N is any natural number) depending on the guarantor using the guarantor terminal 200. For example, guarantor terminal 200-1 is the guarantor terminal 200 used by the guarantor (guarantor D1) identified by the guarantor ID "DID#1". In the following explanation, guarantor terminals 200-1 to 200-N will be referred to as guarantor terminals 200 when no particular distinction is made. In the following explanation, guarantor terminal 200 may be considered the same as the guarantor. In other words, guarantor may be read as guarantor terminal 200 below.

In addition, in the following explanation, it is assumed that a news app is installed on the user terminal 100 and the guarantor terminal 200.

First, the information processing device 10 acquires event information (primary information) related to an event that has occurred from the external server 300 (step S1). For example, the information processing device 10 acquires event information related to an event that has occurred for which no mass media has provided a corresponding news article to the news app. In other words, the information processing device 10 acquires event information related to an event that has occurred for which no mass media has created a corresponding news article (e.g., a long-tail event). In the example of Figure 1, it is assumed that the information processing device 10 has acquired event information #1 related to event #1 and event information #2 related to event #2.

Next, based on the event information acquired in step S1, the information processing device 10 generates content showing a news article about the event indicated by the event information (step S2). For example, the information processing device 10 generates content #1 showing a news article about event #1 using event information #1 and model #1 that has been trained to generate answers to input questions. To give a specific example, the information processing device 10 generates content #1 showing a news article about event #1 by inputting event information #1 and an instruction sentence that instructs model #1 to output content showing a news article about event #1.

Similarly, the information processing device 10 generates content #2 showing a news article about event #2.

Model #1 is a model trained to output an answer corresponding to an input question, and is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Model #1 is located within information processing device 10 and was created independently by the business operator that manages information processing device 10. It is desirable to keep input information, such as personal information, confidential by training it in a way that prevents it from being used as a new answer.

The information processing device 10 then provides the generated content to the guarantor terminal 200 (step S3). For example, the information processing device 10 provides the generated content along with event information related to the event indicated by the content to the guarantor terminal 200 used by the guarantor corresponding to the category of the content. To give a specific example, if the category of the event is "sports," the information processing device 10 provides the event information related to the event along with the content generated related to the event to the guarantor terminal 200 used by the guarantor who is a sports reporter in the mass media.

Next, the information processing device 10 receives information regarding the guarantee of the reliability of the generated content from the guarantor terminal 200 (step S4). For example, the guarantor determines whether there is any discrepancy between the content generated using model #1 and the facts indicated by the event information (in other words, whether the generated content contains fabricated information). Then, the information processing device 10 receives information indicating the results of the guarantor's assessment of the content as information regarding the guarantee of the reliability of the content.

The information processing device 10 then provides the generated content to the user terminal 100 via the news app, along with security information indicating whether the reliability of the content has been guaranteed (step S5). Here, in step S4, guarantor D1 determines that content #1 has been generated based on the facts indicated by event information #1, and this determination result is accepted from guarantor terminal 200-1. In such a case, the information processing device 10 provides content #1 along with security information indicating that the reliability of content #1 has been guaranteed (in other words, information indicating that there is no difference between content #1 and the facts indicated by event information #1). To give a specific example, the information processing device 10 assigns an icon image to content #1 indicating that the reliability of content #1 has been guaranteed, and displays it on the user terminal 100.

On the other hand, it is assumed that the guarantor has not yet made a judgment on content #2. In such a case, the information processing device 10 provides content #2 along with guarantee information indicating that the reliability of content #2 is not guaranteed (in other words, information indicating that content #2 may differ from the facts indicated by event information #2). As a specific example, the information processing device 10 assigns an icon image to content #2 indicating that the reliability of content #2 is not guaranteed, and displays it on the user terminal 100.

Note that steps S3 and S4 may be performed after step S5. For example, after content #1 is generated, the information processing device 10 assigns an icon image to content #1 indicating that the reliability of content #1 is not guaranteed, and displays this icon image on the user terminal 100. If the information processing device 10 subsequently receives from the guarantor terminal 200-1 a determination result that content #1 was generated based on the facts indicated by event information #1, the information processing device 10 assigns an icon image to content #1 indicating that the reliability of content #1 is guaranteed, and displays this icon image on the user terminal 100.

Furthermore, if the information processing device 10 receives from the guarantor terminal 200-1 a determination result that there is a discrepancy between content #1 and the facts indicated by event information #1 (in other words, that content #1 contains fabricated information), the information processing device 10 may not provide content #1 to the user terminal 100. In such a case, the information processing device 10 may provide modified content #1, which is content #1 modified by the guarantor D1 who made the determination on content #1, to the user terminal 100 instead of content #1.

In addition, the information processing device 10 may set a higher priority for content #1, whose reliability is guaranteed, than for content #2, whose reliability is not guaranteed, and provide it to the user terminal 100.

Next, the information processing device 10 receives ratings for the generated content from the user terminal 100 (step S6). For example, the information processing device 10 receives comments on the generated content and user reactions (for example, whether or not a like button associated with the content was pressed).

Next, the information processing device 10 sets a profit for the guarantor (step S7). For example, the information processing device 10 sets a profit for the guarantor based on users' reactions to the content whose reliability has been guaranteed by the guarantor. To give a specific example, the more times the content whose reliability has been guaranteed by the guarantor is viewed, the higher the profit set by the information processing device 10. Furthermore, the higher the user's evaluation of the content whose reliability has been guaranteed by the guarantor (for example, the more favorable comments, the more times the like button has been pressed), the higher the profit set by the information processing device 10. Furthermore, the more content whose reliability has been guaranteed by the guarantor, the higher the profit set by the information processing device 10.

Next, the information processing device 10 outputs the ranking of the guarantors to the user terminal 100 (step S8). For example, the information processing device 10 outputs a ranking based on the number of pieces of content for which the guarantor has guaranteed the reliability, the user's evaluation of the content for which the guarantor has guaranteed the reliability, etc.

In addition, the information processing device 10 may output link information to the guarantor (for example, a link to a website operated by the guarantor or a link to the guarantor's social media account) along with the ranking.

As described above, the information processing device 10 according to the embodiment provides the user with content related to news articles generated by a model (text generation AI (Artificial Intelligence)), along with information indicating whether the reliability of the content is guaranteed. In this way, the information processing device 10 according to the embodiment allows the user to understand whether the reliability of the content is guaranteed.

In addition, the information processing device 10 according to the embodiment can provide users with news articles about long-tail events for which the mass media lack the manpower to write news articles. For example, in the first round of regional high school baseball qualifying matches, the results of games played by lesser-known schools may not be reported in the news. However, users whose alma mater is such a school have a need to view news articles that include information about the results and details of the game. By providing such users with content showing news articles about the wins and losses of their alma mater, comments on the news articles can be shared within the content with fellow alumni of the same school, providing a new user experience in the distribution of news articles.

In addition, the information processing device 10 according to the embodiment can make the content generated by the model a fait accompli by receiving a guarantee of reliability from a guarantor, such as a reporter, for the content related to a news article generated by the model, and can also set a profit as a reward for making the content a fait accompli for the guarantor who is a party to the content generated by the model.

Furthermore, if content related to a news article generated by a model receives a strong response (reaction) from users, the information processing device 10 according to the embodiment can motivate reporters and others to conduct more detailed coverage of the events indicated by the content and create content such as follow-up reports, thereby further enhancing the content distributed in the news app.

[2. Other processing examples]
The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are listed below.

[2-1. Provision of content]
1 , the information processing device 10 may provide the collateral information and the content together with information indicating that the content was generated by model #1 (text generation AI) to the user terminal 100. For example, the information processing device 10 may assign an icon image to content #1 indicating that it was generated by the text generation AI, and display the icon image on the user terminal 100.

[2-2. Images to be included in the content]
1, the information processing device 10 may generate content including images (moving images, still images) showing an event that has occurred. For example, the information processing device 10 acquires event information including images showing the event that has occurred. Then, the information processing device 10 generates content including the images showing the event.

In addition, the information processing device 10 may generate content that includes an image generated based on event information as an image showing an event that has occurred. For example, the information processing device 10 generates an image showing an event by inputting the text information indicated by the event information into model #2, which has been trained to generate images from text information.

Here, model #2 is trained to output an image when, for example, text information describing the event represented by the training image is input. Any known technology can be applied to training model #2, and a learning method appropriately selected depending on the information used as training data may be used. For example, model #2 may be trained using various conventional machine learning technologies (e.g., supervised machine learning technologies such as SVM (Support Vector Machine)). Model #2 may also be trained using deep learning technologies. For example, model #2 may be trained using various deep learning technologies such as RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network).

[2-3. Regarding the posting of related content by the guarantor]
1 , the information processing device 10 may accept a post of related content related to the generated content from a guarantor who has guaranteed the reliability of the content, and provide the post to the user terminal 100 via a news app. For example, the information processing device 10 accepts a post of related content that is a follow-up report on event #1 from guarantor D1 who has guaranteed the reliability of content #1, and provides the post to the user terminal 100.

[2-4. Creating content including tags]
1 , the information processing device 10 may generate content including tag information. For example, the information processing device 10 generates content by inputting event information, rules specifying that tags corresponding to events indicated by the event information should be included in the content, and instruction sentences instructing the content to be output in accordance with the rules into model #1. Then, the information processing device 10 provides the content to users who follow tags included in the generated content in a news app.

[2-5. Content related to events occurring in each area]
In the example of Figure 1, the information processing device 10 may acquire event information regarding an event that has occurred in each area (e.g., a crime or a disaster), generate content related to the event, and provide the generated content to users located in the corresponding area.

For example, the information processing device 10 acquires event information about a crime that occurred in area #1, and generates content #3 that shows information about the crime that occurred in area #1 by inputting the event information and an instruction sentence instructing model #1 to output content showing information about the crime (e.g., crime prevention information, suspicious person information, etc.). The information processing device 10 then provides content #3 to users located in area #1 via a news app. Note that the information processing device 10 may also display an icon image corresponding to content #3 on the map of area #1 in a crime prevention map on the user terminal 100, and provide content #3 in response to the user's selection operation on the icon image.

In addition, the information processing device 10 acquires event information related to a disaster that occurred in area #1, and generates content #4 indicating information related to the disaster that occurred in area #1 by inputting the event information and an instruction sentence instructing model #1 to output content indicating information related to the disaster (for example, the scale of the disaster, the need for evacuation, etc.). The information processing device 10 then provides content #4 to users located in area #1 via a news app. Note that the information processing device 10 may also display an icon image corresponding to content #4 on the map of area #1 in the disaster map on the user terminal 100, and provide content #4 in response to the user's selection operation on the icon image.

In addition, the information processing device 10 may provide content #3 or content #4 together with security information indicating whether the reliability of content #3 or content #4 has been guaranteed by a guarantor corresponding to the category of content #3 or content #4.

In addition, the information processing device 10 may provide content #3 and content #4 along with security information indicating whether the reliability of content #3 and content #4 has been guaranteed by a guarantor located in area #1. For example, the information processing device 10 provides content #3 along with security information indicating whether the reliability of content #3 has been guaranteed by a guarantor who was affected by the disaster indicated by content #3. In addition, the information processing device 10 provides content #4 along with security information indicating whether the reliability of content #4 has been guaranteed by a guarantor who is a victim of the disaster indicated by content #4.

In addition, areas may be set to any size as appropriate. For example, areas may be divided into meshes of similar size based on latitude and longitude. In other words, areas may be areas separated by regional meshes. In this case, the area ID may use a regional mesh code. Note that the above is just one example, and areas may be set based on various information other than regional meshes. For example, areas may be set based on administrative divisions such as "town," "ward," "city," or "prefecture."

[2-6. Content related to events indicated by user posted information]
In the example of FIG. 1 , the information processing device 10 may acquire event information about an event (i.e., a buzzworthy (trending) event) indicated by information posted by users on a predetermined service (e.g., an SNS) that exceeds a predetermined threshold from an external server 300 that provides the service, and generate content related to the event. For example, the information processing device 10 identifies an event indicated by information posted by users on a service provided by the device or an external server within a predetermined period (e.g., one day or three days) that exceeds a predetermined threshold. The information processing device 10 then acquires event information (e.g., posted information) about the identified event, and generates content #5 indicating the event by inputting the event information and an instruction sentence instructing the model #1 to output content indicating the event (e.g., a summary of the posted information) into the model #1. The information processing device 10 then provides the content #5 to the user terminal 100 via a news app, along with security information indicating whether the reliability of the content #5 has been guaranteed by a security party (e.g., an influencer) who is a user of the SNS.

Note that ensuring the reliability of content #5 may mean, for example, ensuring that the event represented by content #5 is popular, or ensuring that the event represented by content #5 is interesting.

In addition, the information processing device 10 may generate content #5 by inputting into model #1 event information, rules specifying that link information to corresponding images (e.g., popular images) indicated by the event information should be included in the content, and instruction sentences instructing the content to be output in accordance with the rules.

The information processing device 10 may also output to the user terminal 100 the rankings of the guarantors of content related to a popular event, along with link information to the guarantors. The information processing device 10 may also output to the user terminal 100 the rankings of content generated related to a popular event, based on user reactions to the content.

In this way, the information processing device 10 can provide content related to popular events and their rankings, allowing users to understand what events are popular.

In addition, users (e.g., influencers) can refer to the news app provided by the information processing device 10 to understand what content will be popular and distribute that content themselves on social media, etc., which can attract influencers to the news app and make it a source of trends.

In addition, by providing link information to the guarantors along with rankings of guarantors of content related to popular events, the information processing device 10 can guide users to the guarantors' own social media accounts and the content they distribute, thereby motivating the guarantors to guarantee the reliability of the content.

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

(Regarding the communication unit 20)
The communication unit 20 is realized by, for example, a network interface card (NIC), etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information between the user terminal 100, the guarantor terminal 200, the external server 300, etc.

(Regarding the storage unit 30)
The storage unit 30 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 30 has a guarantor information database 31, a content information database 32, and a model database 33.

(Regarding the guarantor information database 31)
The guarantor information database 31 stores various information related to guarantors. An example of the information stored in the guarantor information database 31 will now be described with reference to FIG. 3. FIG. 3 is a diagram showing an example of the guarantor information database 31. In the example of FIG. 3, the guarantor information database 31 has items such as "guarantor ID,""guarantor link information,""guarantorcategory," and "guarantor content information."

"Guarantor ID" indicates identification information for identifying the guarantor. "Guarantor link information" indicates link information to the guarantor. "Guarantor category" indicates information about the category to which the guarantor belongs, and stores, for example, information indicating that the guarantor is a sports reporter in the mass media or information indicating that the guarantor is an influencer on social media. "Guarantor content information" indicates information about the content for which the guarantor has guaranteed its reliability, and stores, for example, identification information for identifying the content.

In other words, Figure 3 shows an example in which the guarantor link information of the guarantor identified by the guarantor ID "DID#1" is "guarantor link information #1," the guarantor category is "guarantor category #1," and the collateral content information is "collateral content information #1."

(Regarding the content information database 32)
The content information database 32 stores various types of information related to content. An example of the information stored in the content information database 32 will now be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the content information database 32. In the example of FIG. 4, the content information database 32 has items such as "content ID,""eventinformation,""securityinformation,""contentinformation,""number of views,""ratinginformation," and "link information."

"Content ID" indicates identification information for identifying the content. "Event information" indicates event information related to the event indicated by the content. "Guarantee information" indicates whether the reliability of the content has been guaranteed by the guarantor. "Content information" indicates information related to the content, and stores information such as text information and images contained in the content. "Number of views" indicates the number of views of the content. "Rating information" indicates information related to users' ratings of the content, and stores information such as comments users made about the content and information indicating users' reactions to the content (for example, the number of times the like button was pressed). "Link information" indicates link information to images related to the event indicated by the content.

In other words, Figure 4 shows an example in which the security information for content identified by content ID "CID#1" is "Security Information #1", the event information is "Event Information #1", the content information is "Content Information #1", the number of views is "Number of Views #1", the rating information is "Rating Information #1", and the link information is "Link Information #1".

(Regarding the model database 33)
The model database 33 stores models that have been trained to generate answers to input questions, and also stores models that have been trained to output training images when text information that is an explanation of an event represented by the training images is input.

(Regarding the control unit 40)
The control unit 40 is a controller, and is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 40 is also a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 2 , the control unit 40 according to the embodiment has an acquisition unit 41, a generation unit 42, an image generation unit 43, a reception unit 44, a provision unit 45, a setting unit 46, and an output unit 47, and realizes or executes the functions and actions of information processing described below.

(Regarding the acquisition unit 41)
The acquisition unit 41 acquires event information relating to a predetermined event. For example, in the example of FIG. 1 , the acquisition unit 41 acquires event information relating to an event that has occurred from the external server 300.

The acquisition unit 41 may also acquire event information regarding events for which corresponding content is not distributed in a specified information distribution service. For example, in the example of FIG. 1, the acquisition unit 41 acquires event information regarding events that have occurred for which no corresponding news article is provided by any mass media outlet to the news app.

The acquisition unit 41 may also acquire event information related to an event indicated by posted information equal to or greater than a predetermined threshold from among the posted information posted by users. For example, in the example of FIG. 1, the acquisition unit 41 acquires event information related to an event indicated by posted information equal to or greater than a predetermined threshold from among the posted information posted by users on a predetermined service, from an external server 300 that provides the service.

The acquisition unit 41 may also acquire event information regarding events that have occurred in a specified area. For example, in the example of FIG. 1, the acquisition unit 41 acquires event information regarding events that have occurred in each area.

(Regarding the generation unit 42)
The generation unit 42 generates content related to the event by inputting the event information acquired by the acquisition unit 41 and an instruction sentence instructing a model that has been trained to generate an answer to an input question to output content related to the event indicated by the event information. For example, in the example of Figure 1, the generation unit 42 references the model database 33 and uses event information #1 and model #1 that has been trained to generate an answer to an input question to generate content #1 indicating a news article about event #1, and stores it in the content information database 32.

The generation unit 42 may also generate content that includes an image of an event included in the event information. For example, in the example of FIG. 1, the generation unit 42 generates content that includes an image showing an event included in the event information.

The generation unit 42 may also generate content by inputting into the model rules that stipulate that tags corresponding to events should be included in the content. For example, in the example of FIG. 1, the generation unit 42 generates content by inputting into model #1 event information, rules that stipulate that tags corresponding to events indicated by the event information should be included in the content, and instruction sentences that instruct the content to be output in accordance with the rules.

The generation unit 42 may also generate content by inputting into the model a rule that specifies that link information to an image corresponding to an event should be included in the content. For example, in the example of FIG. 1, the generation unit 42 generates content #5 by inputting into model #1 event information, a rule that specifies that link information to the corresponding image indicated by the event information should be included in the content, and an instruction sentence that instructs the model to output the content in accordance with the rule.

(Regarding the image generation unit 43)
The image generation unit 43 generates an image corresponding to an event by inputting the text information indicated by the event information to an image generation model that has been trained to generate an image from text information. For example, in the example of Figure 1, the image generation unit 43 references the model database 33 and inputs the text information indicated by the event information to model #2 that has been trained to generate an image from text information, thereby generating an image indicating an event.

(Regarding the reception unit 44)
The reception unit 44 receives a post of related content related to the content from a guarantor who has guaranteed the reliability of the content. For example, in the example of FIG. 1 , the reception unit 44 receives a post of related content that is a follow-up report on Event #1 from a guarantor D1 who has guaranteed the reliability of Content #1.

(Regarding the providing unit 45)
The providing unit 45 provides the content generated by the generating unit 42 to the user together with security information indicating whether the content has been guaranteed by a guarantor who guarantees the reliability of the content. For example, in the example of Fig. 1, the providing unit 45 refers to the content information database 32 and provides the generated content to the user terminal 100 via a news app together with security information indicating whether the reliability of the content has been guaranteed.

Furthermore, if the reliability of the content is guaranteed, the providing unit 45 may set a higher priority for providing the content than if the reliability is not guaranteed, and provide the content. For example, in the example of Figure 1, the providing unit 45 sets a higher priority for content #1, whose reliability is guaranteed, than for content #2, whose reliability is not guaranteed, and provides the content to the user terminal 100.

The providing unit 45 may also provide the collateral information and content together with information indicating that the content was generated by a model. For example, in the example of FIG. 1, the providing unit 45 provides the collateral information and content to the user terminal 100 together with information indicating that the content was generated by model #1.

The providing unit 45 may also provide content including images generated by the image generating unit 43. For example, in the example of FIG. 1, the providing unit 45 provides content including images generated using model #2.

The providing unit 45 may also provide the user with the related content accepted by the accepting unit 44. For example, in the example of FIG. 1, the providing unit 45 provides the user terminal 100 with the related content accepted from guarantor D1, who has guaranteed the reliability of content #1.

The providing unit 45 may also provide the content together with security information indicating whether the reliability of the content has been guaranteed by a guarantor corresponding to the category to which the event belongs. For example, in the example of FIG. 1, the providing unit 45 provides the content generated for an event in the "sports" category together with security information indicating whether the reliability of the content has been guaranteed by a guarantor who is a sports reporter in the mass media.

The providing unit 45 may also provide content related to the event together with security information in an information distribution service. For example, in the example of FIG. 1, the providing unit 45 provides the content to the user terminal 100 via a news app, together with security information indicating whether the reliability of the content has been guaranteed.

The providing unit 45 may also provide the content, along with the collateral information, to users who are following the tag. For example, in the example of FIG. 1, the providing unit 45 provides the content to users who are following the tag included in the content in a news app.

The providing unit 45 may also provide the content via a predetermined information distribution service together with security information indicating whether or not the content related to the event has been secured by a guarantor who is a user of a predetermined SNS. For example, in the example of FIG. 1, the providing unit 45 provides content #5 to the user terminal 100 via a news app together with security information indicating whether or not the reliability of content #5 has been secured by a guarantor who is a user of the SNS.

The providing unit 45 may also provide content to users located in an area along with security information indicating whether or not content related to an event has been secured. For example, in the example of FIG. 1, the providing unit 45 provides content #3 indicating information about a crime that occurred in area #1 and content #4 indicating information about a disaster that occurred in area #1, along with security information, to the user terminal 100 via a news app for a user located in area #1.

(Regarding the setting unit 46)
The setting unit 46 sets a predetermined profit for a guarantor who has guaranteed the reliability of content. For example, in the example of Fig. 1, the setting unit 46 references the guarantor information database 31 and the content information database 32 and sets a profit for a guarantor who has guaranteed the reliability of content. To give a specific example, the setting unit 46 sets a higher profit for a larger number of contents for which a guarantor has guaranteed the reliability.

The setting unit 46 may also set a profit for the guarantor based on the user's evaluation of the content. For example, in the example of FIG. 1, the setting unit 46 sets a higher profit the more times the content whose reliability has been guaranteed by the guarantor is viewed. The setting unit 46 also sets a higher profit the more highly the user's evaluation of the content whose reliability has been guaranteed by the guarantor.

(Regarding the output unit 47)
The output unit 47 outputs to the user information indicating the ranking of the guarantors based on at least one of the number of contents for which the guarantors have guaranteed the reliability and the user's evaluation of the content for which the guarantors have guaranteed the reliability. For example, in the example of Figure 1, the output unit 47 refers to the guarantor information database 31 and the content information database 32, and the information processing device 10 outputs a ranking based on the number of contents for which the guarantors have guaranteed the reliability and the user's evaluation of the content for which the guarantors have guaranteed the reliability.

The output unit 47 may also output link information indicating a link corresponding to the guarantor to the user, along with information indicating the ranking of the guarantor. For example, in the example of Figure 1, the output unit 47 outputs link information to the guarantor along with the ranking.

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

As shown in FIG. 5, the information processing device 10 determines whether event information related to a predetermined event has been acquired (step S101). If event information has not been acquired (step S101; No), the information processing device 10 waits until event information is acquired.

On the other hand, if event information has been acquired (Step S101; Yes), the information processing device 10 generates content related to the event by inputting the event information and an instruction sentence that instructs the model, which has been trained to generate an answer to the input question, to output content related to the event indicated by the event information (Step S102). Next, the information processing device 10 provides the content to the user along with guarantee information indicating whether the content has been guaranteed by a guarantor who guarantees the reliability of the content (Step S103), and ends the processing.

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

5-1. Processing Mode
Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above text and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above-mentioned embodiments can be combined as appropriate to the extent that the processing content is not contradictory.

6. Effects
As described above, the information processing device 10 according to the embodiment includes an acquisition unit 41, a generation unit 42, an image generation unit 43, a reception unit 44, a provision unit 45, a setting unit 46, and an output unit 47. The acquisition unit 41 acquires event information related to a predetermined event. The generation unit 42 generates content related to the event by inputting the event information acquired by the acquisition unit 41 and an instruction sentence instructing a model trained to generate an answer to an input question to output content related to the event indicated by the event information. The generation unit 42 also generates content that includes an image of the event included in the event information. The image generation unit 43 generates an image corresponding to the event by inputting text information indicated by the event information to an image generation model trained to generate an image from text information. The reception unit 44 accepts submissions of related content related to the content from a guarantor who has guaranteed the reliability of the content. The provision unit 45 provides the content generated by the generation unit 42 to a user along with security information indicating whether the content has been guaranteed by a guarantor who guarantees the reliability of the content. The providing unit 45 also provides content including the image generated by the image generating unit 43. The providing unit 45 also provides the related content received by the receiving unit 44 to the user. The setting unit 46 sets a predetermined profit for the guarantor who has guaranteed the reliability of the content. The setting unit 46 also sets a profit for the guarantor according to the user's evaluation of the content. The output unit 47 outputs information indicating the ranking of the guarantor to the user based on at least one of the number of contents for which the guarantor has guaranteed the reliability and the user's evaluation of the content for which the guarantor has guaranteed the reliability. The output unit 47 also outputs link information indicating a link corresponding to the guarantor to the user, along with the information indicating the ranking of the guarantor.

As a result, the information processing device 10 according to the embodiment can provide users with content related to news articles generated by the model, along with information indicating whether the reliability of the content is guaranteed, allowing users to understand whether the reliability of the content is guaranteed.

Furthermore, in the information processing device 10 according to the embodiment, for example, the acquisition unit 41 acquires event information relating to an event for which corresponding content is not being distributed in a predetermined information distribution service. Then, the provision unit 45 provides content relating to the event together with security information in the information distribution service.

As a result, the information processing device 10 according to the embodiment can provide users with news articles about long-tail events for which the mass media lacks the manpower to write news articles.

Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates content by inputting into the model a rule specifying that a tag corresponding to the event should be included in the content. Then, the provision unit 45 provides the content, along with the collateral information, to users who follow the tag.

As a result, the information processing device 10 according to the embodiment can provide the generated content to users who follow the tag indicated by the content, thereby improving convenience.

In the information processing device 10 according to the embodiment, for example, the acquisition unit 41 acquires, from among the posted information posted by users, event information related to an event indicated by posted information equal to or greater than a predetermined threshold. The provision unit 45 then provides the content on a predetermined information distribution service together with security information indicating whether the content related to the event has been secured by a guarantor who is a user of a predetermined SNS. The generation unit 42 also generates content by inputting into the model a rule specifying that the content should include link information to an image corresponding to the event.

As a result, the information processing device 10 according to the embodiment can provide content related to popular events, allowing users to understand what events are popular.

Furthermore, in the information processing device 10 according to the embodiment, for example, the acquisition unit 41 acquires event information related to an event that has occurred in a specified area. Then, the provision unit 45 provides content to users located in the area along with security information indicating whether or not the content related to the event has been secured.

As a result, the information processing device 10 according to the embodiment can provide content related to events occurring in the area where the user is located, thereby providing content with high appeal.

Furthermore, in the information processing device 10 according to the embodiment, for example, when the reliability of the content is guaranteed, the providing unit 45 sets a higher priority for providing the content than when the reliability is not guaranteed, and provides the content.

As a result, the information processing device 10 according to the embodiment can provide content with guaranteed reliability on a priority basis, thereby providing highly reliable content to users.

Furthermore, in the information processing device 10 according to the embodiment, for example, the providing unit 45 provides the collateral information and content together with information indicating that the content has been generated by the model.

As a result, the information processing device 10 according to the embodiment can provide information indicating that content was generated using a model, thereby reducing the possibility of users misunderstanding the facts.

Furthermore, in the information processing device 10 according to the embodiment, for example, the providing unit 45 provides content together with guarantee information indicating whether the reliability of the content has been guaranteed by a guarantor corresponding to the category to which the event belongs.

As a result, the information processing device 10 according to the embodiment can receive assurance of the reliability of the content from a guarantor who is familiar with the category to which the event belongs, thereby improving the accuracy of the content.

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

The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400, and controls each component. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 receives data from other devices via communication network 500 (corresponding to network N in the embodiment) and sends it to CPU 1100, and also transmits data generated by CPU 1100 to other devices via communication network 500.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input/output interface 1600. The CPU 1100 acquires data from input devices via the input/output interface 1600. The CPU 1100 also outputs data generated via the input/output interface 1600 to output devices.

Media interface 1700 reads programs or data stored on recording medium 1800 and provides them to CPU 1100 via RAM 1300. CPU 1100 loads the programs from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded programs. 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.

For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1300 to realize the functions of the control unit 40. In addition, the HDD 1400 stores various data within the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from another device via a specified communications network.

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

Furthermore, the configuration of the information processing device 10 described above can be flexibly changed, such as by calling external platforms using APIs (Application Programming Interfaces) or network computing, depending on the function.

Furthermore, the term "unit" in the claims can be read as "means" or "circuit." For example, an acquisition unit can be read as acquisition means or acquisition circuit.

REFERENCE SIGNS LIST 10 Information processing device 20 Communication unit 30 Storage unit 31 Guarantor information database 32 Content information database 33 Model database 40 Control unit 41 Acquisition unit 42 Generation unit 43 Image generation unit 44 Reception unit 45 Provision unit 46 Setting unit 47 Output unit 100 User terminal 200 Guarantor terminal 300 External server

Claims (18)

an acquisition unit that acquires event information related to a predetermined event;
a generation unit that generates content related to the event by inputting the event information acquired by the acquisition unit and an instruction sentence that instructs a model that has been trained to generate an answer to an input question to output content related to the event indicated by the event information;
and a providing unit that provides the content generated by the generating unit to a user together with security information indicating whether the content has been secured by a guarantor who secures the reliability of the content. 2. The information processing device according to claim 1, further comprising: a setting unit for setting a predetermined profit for a person who has guaranteed the reliability of the content. The setting unit
The information processing device according to claim 2 , wherein a profit is set for the guarantor according to the user's evaluation of the content. The information processing device according to claim 1, further comprising an output unit that outputs to a user information indicating the ranking of the guarantor based on at least one of the number of contents for which the guarantor has guaranteed the reliability and the user's evaluation of the content for which the guarantor has guaranteed the reliability. The output unit
5. The information processing device according to claim 4, wherein link information indicating a link corresponding to the guarantor is output to the user together with information indicating the ranking of the guarantor. The providing unit
2. The information processing device according to claim 1, wherein, when the reliability of the content is guaranteed, a higher priority is set for providing the content than when the reliability is not guaranteed, and the content is provided. The providing unit
The information processing apparatus according to claim 1 , further comprising: providing the security information and the content together with information indicating that the content has been generated by the model. The generation unit
The information processing apparatus according to claim 1 , further comprising: generating the content by including an image of the event included in the event information in the content. an image generation unit that generates an image corresponding to the event by inputting text information indicated by the event information into an image generation model that has been trained to generate an image from text information;
The providing unit
The information processing device according to claim 1 , wherein the content provided includes an image generated by the image generating unit. a receiving unit that receives posts of related content related to the content from a guarantor who has guaranteed the reliability of the content,
The providing unit
The information processing device according to claim 1 , wherein the related content accepted by the accepting unit is provided to the user. The providing unit
The information processing device according to claim 1 , further comprising: providing the content together with guarantee information indicating whether or not the reliability of the content has been guaranteed by a guarantor corresponding to a category to which the event belongs. The acquisition unit
Acquire event information regarding an event for which corresponding content is not being distributed in a predetermined information distribution service;
The providing unit
The information processing device according to claim 1 , wherein the content relating to the event is provided together with the security information in the information distribution service. The generation unit
generating the content by further inputting a rule to the model that specifies that a tag corresponding to the event is to be included in the content;
The providing unit
The information processing device according to claim 1 , wherein the content is provided together with the security information to a user who follows the tag. The acquisition unit
Acquire event information relating to an event indicated by posted information equal to or greater than a predetermined threshold from among posted information posted by users;
The providing unit
The information processing device according to claim 1, characterized in that the content related to the event is provided in a predetermined information distribution service together with security information indicating whether the content has been secured by a guarantor who is a user of a predetermined SNS (Social Networking Service). The generation unit
The information processing apparatus according to claim 14, wherein the content is generated by inputting a rule to the model that specifies that the content should include link information to an image corresponding to the event. The acquisition unit
Obtaining event information about events occurring in a specified area;
The providing unit
The information processing device according to claim 1 , further comprising: providing the content to a user located in the area together with security information indicating whether the content related to the event has been secured. 1. A computer-implemented information processing method, comprising:
an acquisition step of acquiring event information relating to a predetermined event;
a generation step of generating content related to the event by inputting the event information acquired in the acquisition step and an instruction sentence instructing a model that has been trained to generate an answer to an input question to output content related to the event indicated by the event information;
and a providing step of providing the content generated by the generating step to a user together with security information indicating whether the content has been secured by a security party that secures the reliability of the content. an acquisition step for acquiring event information relating to a predetermined event;
a generation step of generating content related to the event by inputting the event information acquired by the acquisition step and an instruction sentence instructing a model that has been trained to generate an answer to an input question to output content related to the event indicated by the event information;
and a provision procedure for providing the content generated by the generation procedure to a user together with security information indicating whether the content has been secured by a guarantor who secures the reliability of the content.