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

Abstract

Improve comments posted on streamed content. [Solution] The information processing device according to the present invention is characterized by comprising: an acquisition unit that acquires comments posted to distributed content; an extraction unit that extracts comments that satisfy predetermined conditions from the acquired comments; a generation unit that generates improved comments by improving the extracted comments according to the field to which the distributed content belongs; and a provision unit that provides the improved comments.

Description

[Technical Field]

[0001] The present application relates to an information processing apparatus, an information processing method, and an information processing program. [Background Art]

[0002] Conventionally, technologies relating to information distribution via the Internet have been known. As one example of such technologies, a technology for providing comments posted by users on news articles to viewers who have browsed the news articles is known (see Patent Document 1). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent No. 7012599 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, with conventional technologies, it cannot be said that comments posted on distributed content can be improved. Therefore, there is a demand for improving comments posted on distributed content.

[0005] The present application has been made in view of the above, and an object thereof is to improve comments posted on distributed content. [Means for Solving the Problem]

[0006] An information processing apparatus according to the present application comprises: an acquisition unit that acquires comments posted on distributed content; an extraction unit that extracts comments satisfying a predetermined condition from the acquired comments; a generation unit that generates improved comments by improving the extracted comments in accordance with the field to which the distributed content belongs; and a providing unit that provides the improved comments. [Effect of the Invention]

[0007] According to one embodiment of the invention, comments posted to distributed content can be improved. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the system configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of comment information stored in the comment information storage unit according to this embodiment. [Figure 5] Figure 5 shows an example of improvement comment information stored in the improvement comment information storage unit according to the embodiment. [Figure 6] Figure 6 is a flowchart showing an example of the processing procedure for information processing performed by the information processing device according to the present invention. [Figure 7] Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing apparatus, information processing method, and information processing program according to the present application. Furthermore, each embodiment can be appropriately combined as long as the processing content is not inconsistent. Also, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] [Embodiment] [1. An example of information processing] Hereinafter, an example of information processing according to the embodiment will be described with reference to the drawings. Figure 1 is a diagram showing an example of information processing according to the embodiment, in which the information processing method is executed by the information processing device.

[0011] The information processing according to this embodiment is realized by an information processing system SYS (see, for example, Figure 3) which includes a terminal device 10 and an information processing device 100, as shown in Figure 1. The terminal device 10 and the information processing device 100 are connected to a network N (see, for example, Figure 3) by wired or wireless means, respectively. The terminal device 10 and the information processing device 100 can communicate with other devices through the network N.

[0012] Terminal device 10 is an information processing device used by users who view distributed content via the Internet. For example, the user is viewing distributed content delivered through a designated web service. The user is also viewing (or attempting to view) comments (posted comments) from viewers of articles posted about the distributed content. In Figure 1, terminal device 10 is used by user U. In this embodiment, the distributed content is described as a news article, but it may be other distributed content such as a video.

[0013] The information processing device 100 can obtain user U's usage history information (log information) and attribute information from the terminal device 10 used by user U. Here, the usage history information is, for example, user U's activity history. The attribute information is information about user U.

[0014] Furthermore, User U includes both contributors who post comments on the distributed content and viewers who view the distributed content. When contributors and viewers are not distinguished, they are collectively referred to as User U.

[0015] It is assumed that the information processing apparatus 100 has previously obtained consent to perform the following processing from a creator of distributed content, a poster of a comment, an expert in the field to which the distributed content belongs, or the like. The field to which the distributed content belongs may be a category such as sports, economy, entertainment, or society, or may be a specific topic within a category such as a sports match or a change in economic conditions. In the present embodiment, a baseball game will be described. However, the above is merely an example, and the present invention is not actually limited to the above example.

[0016] Further, the number of each apparatus included in the information processing system SYS shown in FIG. 1 is not limited to that illustrated. For example, in FIG. 1, only one terminal apparatus 10 is shown for simplification of illustration, but this is merely an example and is not limited, and two or more terminal apparatuses may be provided.

[0017] The information processing apparatus 100 acquires a comment posted by a poster with respect to the distributed content (step S1).

[0018] The information processing apparatus 100 extracts comments that satisfy a predetermined condition (step S2). The information processing apparatus 100 extracts comments that satisfy the predetermined condition from the acquired comments.

[0019] The predetermined condition is a condition for improving the quality of the acquired comments. Examples of the predetermined condition include the number of views of the posted comment (hereinafter referred to as the number of views). For the predetermined condition, for example, a threshold for the number of views is provided, and examples thereof include that the number of views is not less than a second threshold and less than a first threshold, and that the number of views is less than the second threshold. The first threshold is larger than the second threshold. In the following description, the first threshold is 1000 and the second threshold is 100, but the first threshold and the second threshold may be arbitrarily set.

[0020] For example, the information processing device 100 extracts comments according to predetermined conditions. The information processing device 100 extracts the acquired comments according to the number of views. The information processing device 100 extracts the acquired comments according to thresholds. For example, the information processing device 100 classifies and extracts comments with a number of views between the second threshold and the first threshold, and comments with a number of views below the second threshold. The information processing device 100 may also classify the acquired comments according to predetermined conditions after extraction.

[0021] The information processing device 100 generates an improved comment that improves upon the extracted comment (step S3). The information processing device 100 generates an improved comment that improves upon the extracted comment according to the field to which the distributed content belongs. The information processing device 100 generates an improved comment that improves upon the extracted comment according to the field to which the distributed content belongs, by comparing it with other comments whose view count is above a threshold. The improved comment is a comment that has been improved so that its view count is higher than that of the extracted comment.

[0022] For example, for comments with fewer than 100 views, the information processing device 100 generates improved comments so that the number of views reaches or exceeds the second threshold, depending on the field to which the distributed content belongs, compared with comments with more than or equal to the second threshold. For comments with more than or equal to the second threshold but less than the first threshold, the information processing device 100 generates improved comments so that the number of views reaches or exceeds the first threshold, depending on the field to which the distributed content belongs, compared with other comments with more than or equal to the first threshold. At this time, the information processing device 100 analyzes the content of the extracted comments. For example, the information processing device 100 analyzes whether the extracted comment is a one-word comment or a mixed comment containing both facts and opinions. For each analysis result, the information processing device 100 generates improved comments by comparing them with other comments. If the comment is a one-word comment, the information processing device 100 generates an improved comment that is longer than the one-word comment. In this case, the information processing device 100 may generate an improved comment by lengthening a single sentence, or it may generate new sentences to generate an improved comment of two or more sentences. If the information processing device 100 is a mixed comment, it generates an improvement comment that separates facts from opinions. In this case, the information processing device 100 first summarizes the facts and then generates an improvement comment that summarizes the opinions.

[0023] Furthermore, the information processing device 100 may generate improvement comments so that the number of views approaches the first threshold. For example, if the number of views is less than half of the first threshold (less than 500 views), the information processing device 100 may compare it with comments for views between half and 900 (700 or 900 views, etc.) so that the number of views is between half and 900. However, the information processing device 100 does not have to perform the process of generating improvement comments so that the number of views approaches the first threshold.

[0024] The information processing device 100 uses artificial intelligence (AI) to generate improvement comments. The information processing device 100 has the artificial intelligence analyze the content of the extracted comments and generate improvement comments according to the field to which the distributed content belongs. The information processing device 100 has the artificial intelligence analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs. The artificial intelligence can be implemented, for example, by a language model that can generate text using natural language processing technology, such as GPT (Generative Pre-trained Transformer). The information processing device 100 can use a text generation AI as the artificial intelligence.

[0025] The information processing device 100 inputs instruction information to the generating AI, which includes instructions to analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs. The information processing device 100 inputs the extracted comments and the instruction information instructing the generating AI to analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs, and causes the generating AI to generate improvement comments.

[0026] An example of instruction information to be input to the generation AI is: "Analyze the content of the extracted comments, compare them with other comments, and generate improved comments that enhance the extracted comments according to the field to which the distributed content belongs. For example, analyze whether the extracted comments are one-word comments or mixed comments that contain a mix of facts and opinions. For example, if the number of views of the extracted comments is below the second threshold, compare them with other comments that are above the second threshold. For example, if the number of views of the extracted comments is between the second threshold and the first threshold, compare them with other comments that are above the first threshold. Then, generate improved comments so that the number of views increases compared to the number of views of the extracted comments. Below are the extracted comments." The content of the instruction information is merely an example and is not limited to the above example.

[0027] Furthermore, the information processing device 100 changes the instruction information for generating improvement comments for the generating AI according to the field to which the distributed content belongs. The process of changing the instruction information for generating improvement comments for the generating AI according to the field to which the distributed content belongs will be described later.

[0028] In this way, the information processing device 100 can improve comments whose view count is below the first threshold. In other words, the information processing device 100 can suppress the improvement of comments whose view count is above the first threshold. That is, the information processing device 100 can suppress the improvement of all comments.

[0029] The information processing device 100 provides improvement comments (step S4). The information processing device 100 provides improvement comments to the poster who posted a comment that meets the predetermined conditions. The information processing device 100 provides improvement comments to the poster and obtains their consent. The information processing device 100 provides improvement comments to viewers who view the distributed content. The information processing device 100 provides improvement comments to viewers by displaying them in the comment display section of the distributed content that displays comments. The information processing device 100 may rearrange the comments so that improvement comments are displayed. At this time, the information processing device 100 may provide information indicating improvement comments in association with the improvement comments. For example, the information processing device 100 may provide information indicating improvement comments by displaying it at the beginning or end of the improvement comments. The information processing device 100 provides information indicating improvement comments to the poster and viewers along with the improvement comments.

[0030] Here, we will explain how the information processing device 100 changes the instruction information for generating improvement comments to input to the generating AI according to the field to which the distributed content belongs. For example, the information processing device 100 causes the generating AI to generate improvement comments that include reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs. The information processing device 100 causes the generating AI to quote reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs, and generate improvement comments that include the reference information. For example, the information processing device 100 causes the generating AI to search for and quote reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs, and generate improvement comments that include the reference information. For example, the information processing device 100 searches for expert opinions, statistical data, case studies, etc., in the field to which the distributed content belongs as reference information. Note that the reference information may also include anecdotes, depending on the field. Furthermore, the reference information is not limited to these.

[0031] The information processing device 100 modifies the instruction information for generating improvement comments for the generating AI according to the field to which the distributed content belongs, and inputs it to the generating AI. For example, the information processing device 100 inputs instruction information to the generating AI that references reference information related to the field to which the distributed content belongs, and generates improvement comments that include the reference information, so that the AI ​​generates improvement comments that include the reference information.

[0032] For example, if the distributed content belongs to the field of politics, the information processing device 100 inputs instruction information to the generating AI to generate an improvement comment that includes at least one piece of political data and statistics. The information processing device 100 inputs instruction information to the generating AI to search for and quote at least one piece of political data and statistics, and to generate an improvement comment that includes the quoted information. The information processing device 100 causes the generating AI to generate an improvement comment that includes the searched data. For example, the information processing device 100 causes the generating AI to quote and add the searched data to the content of the improvement comment, or to add it as a link.

[0033] An example of instructions for content distributed in the political field might be: "Search for specific data and statistics, and then compile the user's claims with the data and statistics you found to support them (including the data and statistics you found in the user's claims)."

[0034] For example, if the distributed content belongs to the field of economics, the information processing device 100 inputs instruction information to the generating AI to generate an improvement comment that includes at least one of market trends and expert opinions. The information processing device 100 inputs instruction information to the generating AI to search for and quote at least one of market trends and expert opinions, and to generate an improvement comment that includes the quoted information. The information processing device 100 causes the generating AI to generate an improvement comment that includes relevant expert opinions and market data. For example, the information processing device 100 causes the generating AI to quote and add expert opinions and market data to the content of the improvement comment, or to add them as links.

[0035] An example of instruction information when the distributed content belongs to the economic field is, "Please make it persuasive by citing market trends and expert opinions."

[0036] For example, if the distributed content belongs to the field of technology, the information processing device 100 inputs instruction information to the generating AI to generate an improvement comment that includes at least one piece of information and an example related to technology. The information processing device 100 inputs instruction information to the generating AI to search for and quote at least one piece of information and an example related to technology, and to generate an improvement comment that includes the quoted information. The information processing device 100 causes the generating AI to generate an improvement comment that includes at least one piece of information and an example related to technology. For example, the information processing device 100 causes the generating AI to add at least one piece of information and an example related to technology to the content of the improvement comment, or to add it as a link.

[0037] An example of instruction information when the distributed content belongs to the field of technology is the instruction, "Please add technical details and specific examples to enhance the reader's understanding." Here, the technology is preferably the latest technology. The information processing device 100 may input instruction information such as "latest technology."

[0038] For example, if the distributed content belongs to the entertainment field, the information processing device 100 inputs instruction information to the generating AI to generate an improvement comment that includes at least one relevant episode and comment. The information processing device 100 may, for example, have the poster input at least one episode and comment. The information processing device 100 then has the generating AI generate an improvement comment that includes at least one episode and comment. For example, the information processing device 100 has the generating AI add at least one episode and comment to the content of the improvement comment. In this case, the information processing device 100 may also provide the poster with a template that can be used as a reference for popular episodes and comments.

[0039] One example of instructions for content distributed in the entertainment field is, "Please include emotionally resonant episodes and personal reflections to gain empathy."

[0040] For example, if the distributed content belongs to the field of sports, the information processing device 100 inputs instruction information to the generating AI to generate improvement comments that include at least one of the following: information about the players and a detailed analysis of the match. The information processing device 100 causes the generating AI to generate improvement comments that include at least one of the following: the analysis information of the match and information about the players. For example, the information processing device 100 causes the generating AI to add match data and player statistics to the content of the improvement comments, or to add them as links.

[0041] An example of instructions for content distributed in the sports field might be: "Please include detailed analysis of players and matches to attract the interest of fans."

[0042] For example, if the distributed content belongs to the field of society, the information processing device 100 inputs instruction information to the generating AI to generate improvement comments that include information about events that have had an impact on society. The information processing device 100 inputs instruction information to search for and quote information about events that have had an impact on society and to generate improvement comments that include the quoted information. The information processing device 100 generates improvement comments that include an analysis of the social impact. For example, the information processing device 100 may instruct the generating AI to add information about events that have had an impact on society to the content of the improvement comments or to add them as links.

[0043] An example of instructions for content distributed in the social sphere is, "Please add information about social impact and a long-term perspective to encourage in-depth discussion."

[0044] The information processing device 100 may add instruction information corresponding to each field to the instruction information shown in step S3, before the extracted comments, and have the generating AI generate improvement comments.

[0045] As an example of the instructions in this case, if the distributed content belongs to the field of politics, the instructions might be: "Analyze the content of the extracted comments, compare them with other comments, and generate improved comments that improve upon the extracted comments according to the field to which the distributed content belongs. For example, analyze whether the extracted comments are one-word comments or mixed comments that contain a mixture of facts and opinions. For example, if the number of views of the extracted comments is below the second threshold, compare them with other comments that are above the second threshold. For example, if the number of views of the extracted comments is between the second threshold and the first threshold, compare them with other comments that are above the first threshold. Then, generate improved comments so that the number of views increases compared to the number of views of the extracted comments. At this time, search for specific data and statistics and summarize the user's claims with the searched data and statistics to support them (including the searched data and statistics in the user's claims). Below are the extracted comments."

[0046] However, the above is merely one example, and in reality, it is not limited to the above example.

[0047] The information processing device 100 may not generate improvement comments, but instead generate suggestions for improving comments that meet predetermined conditions and provide them to the poster. The information processing device 100 may generate guidelines for improving comments and provide them to the poster who has posted a comment that meets predetermined conditions. The information processing device 100 may have a generation AI generate guidelines and provide the generated guidelines to the poster. The guidelines are generated based on comments with a number of views above a threshold or on the evaluation of comments (such as "likes"). For example, the information processing device 100 may generate guidelines for improving one-word comments and provide them to the poster. The information processing device 100 may generate guidelines to include the poster's perspective (such as impressions) on the distributed content in the comments and provide them to the poster. For example, the information processing device 100 may generate guidelines for one-word comments such as "Tell us how you feel. Add specific emotions or thoughts to convey your perspective to the readers" and provide them to the poster. The information processing device 100 may, for example, generate guidelines for improving comments that mix facts and impressions and provide them to the poster. The information processing device 100 generates guidelines to separate facts from opinions and provides them to the poster. For example, for a comment that mixes facts and opinions / feedback, the information processing device 100 generates the following guideline and provides it to the poster: "Let's clearly separate the facts from your opinion. First, explain the events, and then state your opinion or feelings to make it easier for readers to understand." However, the above suggestion (guideline) is merely an example and is not limited to the above example in practice.

[0048] As described above, the information processing device 100 acquires comments posted to the distributed content, extracts comments that meet predetermined conditions, and generates improved comments. This allows the information processing device 100 to improve comments posted to the distributed content. Specifically, the information processing device 100 sets a threshold for the number of views and generates improved comments for each threshold. For example, by setting a first threshold, the information processing device 100 can suppress the improvement of comments with a view count above the first threshold while generating improved comments for comments below the first threshold. This allows the information processing device 100 to increase the number of views of comments that meet predetermined conditions (comments with a view count below the first threshold). The information processing device 100 changes the instruction information of the generation AI according to the field to which the distributed content belongs. This allows the information processing device 100 to generate improved comments more appropriately. Furthermore, the information processing device 100 can generate improved comments more appropriately by analyzing the content of the extracted comments.

[0049] Furthermore, the information processing device 100 may generate improvement comments by further subdividing the number of views, such as by setting three or more thresholds.

[0050] [2. System Configuration] The configuration of the information processing system SYS according to the embodiment will be described in detail below with reference to Figure 2. Figure 2 is a diagram showing an example of the system configuration of the information processing system SYS according to the embodiment.

[0051] As shown in Figure 2, the information processing system SYS according to this embodiment includes a terminal device 10 and an information processing device 100.

[0052] The terminal device 10 and the information processing device 100 are connected to the network N by wire or wireless connection. Each of the terminal device 10 and the information processing device 100 can communicate with other devices through the network N.

[0053] Network N includes, for example, WANs (Wide Area Networks) such as the Internet, and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: 5th Generation Mobile Communication System).

[0054] The terminal device 10 connects to the network N via a mobile communication network or short-range wireless communication such as Bluetooth® or Wi-Fi (Local Area Network), and can communicate with other devices such as the information processing device 100 through the network N.

[0055] Furthermore, terminal device 10 is used by user U, who is a user of the news site. Terminal device 10 may be, for example, a notebook PC (personal computer), a desktop PC, a smartphone, or a tablet PC.

[0056] Furthermore, the terminal device 10 can display, for example, the content distributed by the information processing device 100 using a dedicated application or web browser. When the terminal device 10 receives control information from the information processing device 100 to perform the information display process, it performs the display process according to the control information.

[0057] Control information is described using, for example, scripting languages ​​such as JavaScript (registered trademark), stylesheet languages ​​such as CSS (Cascading Style Sheets), programming languages ​​such as Java (registered trademark), or markup languages ​​such as HTML (HyperText Markup Language). Alternatively, a predetermined application distributed from the information processing device 100 may be considered as control information.

[0058] The information processing device 100 is operated and managed by a service provider that operates a site for distributing content. The information processing device 100 performs various processes related to the embodiment regarding the provision of content such as news articles. The information processing device 100 is typically a server device, but may be implemented as a mainframe or workstation. Furthermore, if the information processing device 100 is implemented as a server device, it may be implemented as a single server device, or as a cloud system in which multiple server devices and multiple storage devices work together.

[0059] [3. Equipment configuration] Hereinafter, an example of the functional configuration of the information processing device 100 in the information processing system SYS according to the embodiment will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 3, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0060] (Communications Department 110) The communication unit 110 is implemented, for example, by a communication module or a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection. The information processing device 100 transmits and receives information with other devices, such as the terminal device 10, through the network N.

[0061] For example, the communication unit 110 can receive information about articles and comments posted by user U from the terminal device 10. The communication unit 110 stores the received articles and comments in the storage unit 120, which will be described later.

[0062] (Storage unit 120) The storage unit 120 stores, for example, programs and data used for control and calculations by the control unit 130. For example, the storage unit 120 can be implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or storage devices such as hard disks or optical discs. For example, the storage unit 120 has a comment information storage unit 121 and an improvement comment information storage unit 122. Note that the storage unit 120 is not particularly limited to the example shown in Figure 3, and can appropriately store data necessary for executing the information processing according to the embodiment.

[0063] (Comment information storage unit 121) The comment information storage unit 121 stores information about the acquired comments. For example, the comment information storage unit 121 stores information about the comment content and posting date and time. Here, Figure 4 shows an example of the comment information storage unit 121 according to the embodiment. Figure 4 is a diagram showing an example of comment information stored in the comment information storage unit according to the embodiment. As shown in Figure 4, the comment information storage unit 121 has items such as "comment ID", "comment content", and "posting date and time".

[0064] The "Comment ID" indicates identification information used to identify a comment. The "Comment Content" indicates the content of the comment. In the example shown in Figure 4, conceptual information such as "Comment Content #1" and "Comment Content #2" is stored in "Comment Content," but in reality, the text of the article is stored there. The "Posting Date and Time" indicates the posting date and time the comment was posted. In the example shown in Figure 4, conceptual information such as "Posting Date and Time #1" and "Posting Date and Time #2" is stored there, but in reality, the posting date and time of the comment is stored there.

[0065] (Improvement comment information storage unit 122) The improvement comment information storage unit 122 stores information about the improved improvement comments. Figure 5 shows an example of improvement comment information stored in the improvement comment information storage unit 122 according to this embodiment.

[0066] As shown in Figure 5, the improvement comment information stored in the improvement comment information storage unit 122 has items such as "improvement comment ID", "extracted comment ID", and "improvement comment content".

[0067] The "Improvement Comment ID" indicates identification information for identifying the improvement comment. The "Extracted Comment ID" indicates identification information for identifying the extracted (meeting predetermined conditions) comment from among the comments stored in the comment information storage unit 121. The "Improvement Comment Content" indicates the content of the improved improvement comment. In the example shown in Figure 5, conceptual information such as "Improvement Comment Content #1" and "Improvement Comment Content #2" is shown as being stored in "Improvement Comment Content," but in reality, the content of the improvement comment and other similar information are stored there.

[0068] The improvement comment information storage unit 122 may have an item such as "Reference Information." "Reference Information" may store information such as expert opinions, articles, and various copyrighted works.

[0069] (Control unit 130) The control unit 130 is a controller, and is realized by the execution of various programs (an example of an "information processing program") stored in the memory device inside the information processing device 100 by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), using RAM as the working area.

[0070] Furthermore, the control unit 130 may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0071] As shown in Figure 3, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a generation unit 133, and a provision unit 134, and each of these units realizes or executes the information processing functions and operations described below.

[0072] The control unit 130 may have multiple internally divided components that realize or execute the functions and operations of the information processing described below. Furthermore, the control unit 130 is not limited to the configuration shown in Figure 3, and may have other configurations as long as they perform the information processing described later, and may have other functional units other than those shown in Figure 3.

[0073] (Acquisition part 131) The acquisition unit 131 acquires user information and history information of user U. The acquisition unit 131 acquires comments posted by the poster on the distributed content. The acquisition unit 131 acquires reference information.

[0074] (Extraction part 132) The extraction unit 132 extracts comments that meet predetermined conditions from the acquired comments.

[0075] The extraction unit 132 extracts comments according to predetermined conditions. The extraction unit 132 extracts the acquired comments according to the number of views. The extraction unit 132 extracts the acquired comments according to thresholds. For example, the extraction unit 132 classifies and extracts comments with a number of views between the second threshold and the first threshold, and comments with a number of views less than the second threshold. The extraction unit 132 may also classify the acquired comments according to predetermined conditions after extraction.

[0076] (Generation unit 133) The generation unit 133 generates improved comments by improving the extracted comments. The generation unit 133 generates improved comments by improving the extracted comments according to the field to which the distributed content belongs. The generation unit 133 generates improved comments by improving the extracted comments according to the field to which the distributed content belongs, by comparing them with other comments whose view count is above a threshold.

[0077] For example, for comments with fewer than two views, the generation unit 133 generates improved comments so that the number of views reaches the second threshold or higher, depending on the field to which the distributed content belongs, compared with comments with more than two views. For comments with more than two views but less than one view, the generation unit 133 generates improved comments so that the number of views reaches the first threshold or higher, depending on the field to which the distributed content belongs, compared with other comments with more than one view. At this time, the generation unit 133 analyzes the content of the extracted comments. For example, the generation unit 133 analyzes whether the extracted comment is a one-word comment or a mixed comment containing both facts and opinions. For each analysis result, the generation unit 133 generates improved comments by comparing them with other comments. If the comment is a one-word comment, the generation unit 133 generates an improved comment that is longer than the one-word comment. In this case, the generation unit 133 may generate an improved comment by lengthening a single sentence, or it may generate new sentences to create an improved comment with two or more sentences. If the comment is a mix of facts and opinions, the generation unit 133 generates an improvement comment that separates facts from opinions. In this case, the generation unit 133 first summarizes the facts and then generates an improvement comment that summarizes the opinions.

[0078] Furthermore, the generation unit 133 may generate improvement comments so that the number of views approaches the first threshold. For example, if the number of views is less than half of the first threshold, the generation unit 133 may compare the improvement comments with comments where the number of views is between half and less than half of the first threshold, so that the number of views is between half and less than half of the first threshold. Note that the generation unit 133 does not have to perform the process of generating improvement comments so that they approach the first threshold.

[0079] The generation unit 133 uses a generation AI to have the generation AI generate improvement comments. The generation unit 133 has the generation AI analyze the content of the extracted comments and generate improvement comments according to the field to which the distributed content belongs. The generation unit 133 has the generation AI analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs. The generation unit 133 can use a text generation AI as the generation AI.

[0080] The generation unit 133 inputs instruction information to the generation AI, which includes instructions to analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs. The generation unit 133 inputs the extracted comments and the instruction information instructing the generation AI to analyze the content of the extracted comments, compare them with other comments, and generate improvement comments according to the field to which the distributed content belongs, and causes the generation AI to generate improvement comments.

[0081] The generation unit 133 changes the instruction information for generating improvement comments to input to the generation AI according to the field to which the distributed content belongs. For example, the generation unit 133 causes the generation AI to generate improvement comments that include reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs. The generation unit 133 causes the generation AI to quote reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs, and generate improvement comments that include the reference information. For example, the generation unit 133 causes the generation AI to search for and quote reference information related to the field to which the distributed content belongs, according to the field to which the distributed content belongs, and generate improvement comments that include the reference information. For example, the generation unit 133 searches for expert opinions, statistical data, case studies, etc., in the field to which the distributed content belongs as reference information.

[0082] The generation unit 133 modifies the instruction information for generating improvement comments for the generation AI according to the field to which the distributed content belongs, and inputs it to the generation AI. For example, the generation unit 133 inputs instruction information to the generation AI that references reference information related to the field to which the distributed content belongs, and generates improvement comments that include the reference information, so that the generation unit 133 generates improvement comments that include the reference information.

[0083] For example, if the distributed content belongs to the field of politics, the generation unit 133 inputs instruction information to the generation AI to generate an improvement comment that includes at least one piece of political data and statistics. The generation unit 133 inputs instruction information to the generation AI to search for and quote at least one piece of political data and statistics, and generate an improvement comment that includes the quoted information. The generation unit 133 causes the generation AI to generate an improvement comment that includes the searched data. For example, the generation unit 133 causes the generation AI to quote and add the searched data to the content of the improvement comment, or to add it as a link.

[0084] For example, if the distributed content belongs to the field of economics, the generation unit 133 inputs instruction information to the generation AI to generate an improvement comment that includes at least one of market trends and expert opinions. The generation unit 133 inputs instruction information to the generation AI to search for and quote at least one of market trends and expert opinions, and generate an improvement comment that includes the quoted information. The generation unit 133 causes the generation AI to generate an improvement comment that includes relevant expert opinions and market data. For example, the generation unit 133 causes the generation AI to quote and add expert opinions and market data to the content of the improvement comment, or to add them as links.

[0085] For example, if the distributed content belongs to the field of technology, the generation unit 133 inputs instruction information to the generation AI to generate an improvement comment that includes at least one piece of information and an example related to technology. The generation unit 133 inputs instruction information to the generation AI to search for and quote at least one piece of information and an example related to technology, and to generate an improvement comment that includes the quoted information. The generation unit 133 causes the generation AI to generate an improvement comment that includes at least one piece of information and an example related to technology. For example, the generation unit 133 causes the generation AI to add at least one piece of information and an example related to technology to the content of the improvement comment, or to add it as a link.

[0086] For example, if the distributed content belongs to the entertainment field, the generation unit 133 inputs instruction information to the generation AI to generate an improvement comment that includes at least one relevant episode and comment. The generation unit 133 may, for example, have the poster input at least one episode and comment. The generation unit 133 causes the generation AI to generate an improvement comment that includes at least one episode and comment. For example, the generation unit 133 causes the generation AI to add at least one episode and comment to the content of the improvement comment.

[0087] For example, if the distributed content belongs to the field of sports, the generation unit 133 inputs instruction information to the generation AI to generate improvement comments that include at least one of the following: information about the players and a detailed analysis of the match. The generation unit 133 causes the generation AI to generate improvement comments that include at least one of the following: the analysis of the match and information about the players. For example, the generation unit 133 causes the generation AI to add match data and player statistics to the content of the improvement comments, or to add them as links.

[0088] For example, if the distributed content belongs to the field of society, the generation unit 133 inputs instruction information to the generation AI to generate improvement comments that include information about events that have had an impact on society. The generation unit 133 inputs instruction information to search for and quote information about events that have had an impact on society and to generate improvement comments that include the quoted information. The generation unit 133 generates improvement comments that include an analysis of the social impact. For example, the generation unit 133 may instruct the generation AI to add information about events that have had an impact on society to the content of the improvement comments or to add it as a link.

[0089] The generation unit 133 may analyze the extracted comments, compare them with other comments, and add instruction information corresponding to each field before the extracted comments to the instruction information that includes a message to generate improved comments, thereby causing the generation AI to generate improved comments.

[0090] The generation unit 133 does not generate improvement comments, but generates suggestions for improving comments that meet predetermined conditions. The generation unit 133 generates guidelines for improving comments. The generation unit 133 causes the generation AI to generate the guidelines. For example, the generation unit 133 generates guidelines for improving a one-word comment and provides them to the poster. The generation unit 133 generates guidelines to include the poster's perspective (such as impressions or thoughts) on the distributed content in the comments. For example, the generation unit 133 generates guidelines to improve comments that mix facts and impressions. The generation unit 133 generates guidelines to separate facts and impressions.

[0091] Furthermore, the generation unit 133 may generate improvement comments by further subdividing the number of views, such as by setting three or more thresholds.

[0092] (Provider 134) The provisioning unit 134 provides improvement comments. For example, the provisioning unit 134 provides improvement comments to user U through the communication unit 110. The provisioning unit 134 provides improvement comments to user U by transmitting them to the terminal device 10 used by user U through the communication unit 110. The provisioning unit 134 provides improvement comments to the poster who posted a comment that meets predetermined conditions. The provisioning unit 134 provides improvement comments to the poster and obtains the poster's consent. The provisioning unit 134 provides improvement comments to viewers who view the distributed content. The provisioning unit 134 provides improvement comments to viewers by displaying them in the comment display section of the distributed content. The provisioning unit 134 may rearrange the comments so that improvement comments are displayed. In this case, the provisioning unit 134 may provide information indicating improvement comments in association with the improvement comments. For example, the provisioning unit 134 may provide information indicating improvement comments by displaying it at the beginning or end of the improvement comments. The provision unit 134 provides information indicating improvement comments, along with the improvement comments themselves, to the terminal device 10 used by user U via the communication unit 110.

[0093] Furthermore, if the distributed content belongs to the entertainment field, the provision section 134 may provide the contributor with templates that can be used as a reference for popular episodes and reviews.

[0094] Furthermore, if the generation unit 133 generates guidelines, the provision unit 134 provides the generated guidelines to the poster. The provision unit 134 provides the generated guidelines to the poster by transmitting them to the poster's terminal device 10, which has posted a comment that meets the predetermined conditions, via the communication unit 110.

[0095] [4. Processing procedure according to the embodiment] The following describes the information processing procedure performed by the information processing device 100 according to this embodiment, using Figure 6 as a reference. Figure 6 is a flowchart showing an example of the information processing procedure performed by the information processing device according to this embodiment. The procedure shown in Figure 6 is performed by the control unit 130 of the information processing device 100. The procedure shown in Figure 6 is repeatedly performed while the information processing device 100 is running.

[0096] As shown in Figure 6, the acquisition unit 131 acquires comments posted to the distributed content (step S101).

[0097] Furthermore, the extraction unit 132 extracts comments that meet predetermined conditions from the acquired comments (step S102).

[0098] Furthermore, the generation unit 133 generates improved comments by improving the extracted comments according to the field to which the content belongs (step S103).

[0099] The providing unit 134 provides the improvement comments generated in step S103 (step S104), and the processing procedure shown in Figure 6 is completed.

[0100] [5. Variant] The information processing device 100 may generate and provide information indicating the viewing status of comments. For example, the information processing device 100 may generate and provide information indicating the viewing status of comments in real time. For example, the information processing device 100 may generate a heatmap in real time and provide it to the viewer. The information processing device 100 may color the expressions that are attracting attention and their surroundings in real time using colors corresponding to the number of views in the comments and the viewer's perspective. The information processing device 100 is not limited to generating a heatmap; it may also change the display manner of expressions that are attracting attention in real time, or display information (such as an icon) indicating that they are attracting attention. Examples of changing the display manner include changing the font weight, adding underlines or markers.

[0101] [6. Hardware Configuration] Furthermore, the information processing device 100 according to the above embodiment can be implemented by a computer 1000 having a configuration such as that shown in Figure 7. Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 100 according to the embodiment.

[0102] Computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0103] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented using ROM (Read Only Memory), HDD, flash memory, etc.

[0104] The output IF1060 is an interface for transmitting information to be output to output devices 1010, such as monitors and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners, and is implemented using, for example, USB.

[0105] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording media, or semiconductor memory. Furthermore, the input device 1020 may be an external storage medium such as a USB memory stick.

[0106] Network IF1080 receives data from other devices via network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 to other devices via network N.

[0107] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0108] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the arithmetic unit 1030 of the computer 1000 realizes the same functions as the control unit 130 by executing a program (for example, an information processing program) loaded on the primary storage device 1040. That is, the arithmetic unit 1030 realizes the processing by the information processing device 100 according to the embodiment in cooperation with the program (for example, an information processing program) loaded on the primary storage device 1040.

[0109] [7. Others] Of 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 known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be changed at will unless otherwise specified.

[0110] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0111] Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

[0112] Although embodiments of the present application have been described in detail above with reference to several drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0113] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, a control unit can be replaced with a control means or a control circuit.

[0114] [8. Effects] The information processing device 100 according to this embodiment includes an acquisition unit 131, an extraction unit 132, a generation unit 133, and a provision unit 134. The acquisition unit 131 acquires comments posted by posters on distributed content. The extraction unit 132 extracts comments that meet predetermined conditions from the acquired comments. The generation unit 133 generates improved comments that improve upon the extracted comments. The provision unit 134 provides the improved comments.

[0115] Furthermore, the extraction unit 132 extracts the acquired comments according to the number of views. The generation unit 133 generates improvement comments using a generation AI.

[0116] The generation unit 133 causes the generation AI to analyze the content of the extracted comments.

[0117] The generation unit 133 changes the instruction information to be input to the generation AI for generating improvement comments, depending on the field to which the distributed content belongs.

[0118] Furthermore, the generation unit 133 causes the generation AI to generate improvement comments that include reference information related to the field to which the distributed content belongs.

[0119] Furthermore, the provision unit 134 provides improvement comments to the poster who submitted a comment that meets the specified conditions.

[0120] Furthermore, the provisioning unit 134 displays improvement comments in the comment section of the distributed content.

[0121] By any or a combination of the above-described processes, the information processing device 100 according to the present invention can improve comments posted to distributed content.

[0122] Furthermore, the effects described above can also be achieved by any combination of the processes performed by each of the parts described above, or by any combination of the processes performed by each of the parts. [Explanation of Symbols]

[0123] SYS Information Processing System N Network 10 Terminal devices 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Comment Information Storage Unit 122 Improvement Comment Information Storage Unit 130 Control Unit 131 Acquisition Department 132 Extraction Section 133 Generation Department 134 Supply Department

Claims

1. A unit for retrieving comments posted on the distributed content, An extraction unit that extracts comments that satisfy predetermined conditions from the acquired comments, A generation unit generates improved comments by improving the extracted comments according to the field to which the distributed content belongs, The provisioning department that provides the aforementioned improvement comments An information processing device characterized by comprising:

2. The extraction unit extracts the acquired comments according to the number of views, The generation unit generates the improvement comments using the generation AI. The information processing apparatus according to feature 1.

3. The generation unit causes the generation AI to analyze the content of the extracted comments. The information processing apparatus according to feature 2.

4. The generation unit changes the instruction information used to generate the improvement comments to be input to the generation AI, according to the field to which the distributed content belongs. The information processing apparatus according to claim 3.

5. The generation unit causes the generation AI to generate improvement comments that include reference information related to the field to which the distributed content belongs. The information processing apparatus according to feature 4.

6. The provisioning unit provides the improvement comments to the poster who submitted the comments that meet the predetermined conditions. The information processing apparatus according to claim 1 or 2.

7. The aforementioned provisioning unit displays the improvement comments in the comment display field of the distributed content where comments are displayed. The information processing apparatus according to claim 1 or 2.

8. A method of information processing performed by a computer, The process of obtaining comments posted on the distributed content, An extraction step of extracting comments that satisfy predetermined conditions from the acquired comments, A generation process that generates improved comments by improving the extracted comments according to the field to which the distributed content belongs, The process of providing the aforementioned improvement comments An information processing method characterized by including

9. On the computer, Procedure for retrieving comments posted on streamed content, An extraction procedure for extracting comments that satisfy predetermined conditions from the acquired comments, A generation procedure for generating improved comments that improve upon the extracted comments, depending on the field to which the distributed content belongs, The procedure for providing the aforementioned improvement comments An information processing program characterized by causing the execution of [a specific action].

Images