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

Abstract

This invention provides an information processing device, an information processing method, and an information processing program that suppress the provision of similar articles. [Solution] In an information processing system in which a terminal device and an information processing device are connected to each other via a network by wired or wireless means so that they can communicate with each other, the control unit 130 of the information processing device 100 includes an acquisition unit 131 that acquires user comments on an event, a first generation unit 132 that generates a first article from the acquired comments, a second generation unit 133 that generates a second article from the acquired comments, a determination unit 135 that determines the similarity between the second article and the first article, and a provision unit 137 that provides the second article if the determination unit determines that the similarity is low.

Description

Technical Field

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

Background Art

[0002] Conventionally, there are online services that provide various types of content such as news articles, columns, and product reviews to service users. In relation to such services, for example, technologies for collectively providing news articles that users should read have also been proposed (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, there is a possibility of providing similar articles. Therefore, there is room for improvement in suppressing the provision of similar articles.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of suppressing the provision of similar articles.

Means for Solving the Problems

[0006] The information processing device according to the present application is characterized by comprising: an acquisition unit that acquires user comments on an event; a first generation unit that generates a first article from the acquired comments; a second generation unit that generates a second article from the acquired comments; a determination unit that determines the similarity between the second article and the first article; and a provision unit that provides the second article if the determination unit determines that the similarity between the second article and the first article is low. [Effects of the Invention]

[0007] According to one embodiment, the effect is to suppress the provision of similar articles. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is an explanatory diagram showing an overview of the information processing system according to the embodiment. [Figure 2] Figure 2 shows an example of information processing according to the present invention. [Figure 3] Figure 3 shows an example of the configuration of a terminal device according to this embodiment. [Figure 4] Figure 4 shows an example of the configuration of an information processing device according to the present invention. [Figure 5] Figure 5 shows an example of a comment information storage unit according to the embodiment. [Figure 6] Figure 6 shows an example of a generated article information storage unit according to the embodiment. [Figure 7] Figure 7 shows an example of a management information storage unit according to the embodiment. [Figure 8] Figure 8 is a flowchart showing the information processing procedure by the information processing system according to the embodiment. [Figure 9] Figure 9 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, 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 device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] (Embodiment) [1. Configuration of the Information Processing System] First, with reference to Figure 1, an overview of the information processing system according to the embodiment will be described. Figure 1 is an explanatory diagram showing an overview of the information processing system according to the embodiment. As shown in Figure 1, the information processing system 1 according to the embodiment includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a network N, either by wire or wireless, enabling communication. This allows the terminal device 10 to cooperate with the information processing device 100. The network N is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet.

[0011] Terminal device 10 is an information processing device used by users who view articles via the internet. Users view articles (e.g., news articles) distributed through a designated web service, for example. Users also view (or attempt to view) comments posted by other readers of an article. Terminal device 10 can be any device as long as it can implement the processing described in the embodiment. Terminal device 10 may also be a smartphone, tablet, notebook PC, desktop PC, mobile phone, PDA, or other device. Figure 2 shows the case where terminal device 10 is a smartphone.

[0012] Terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 4G-5G (Generation) or LTE (Long Term Evolution). Terminal device 10 also has a screen, such as an LCD display, which has touch panel functionality and may accept various operations on displayed data such as content from the user, such as tapping, sliding, and scrolling, using a finger or stylus. In Figure 2, terminal device 10 is used by user U1.

[0013] The information processing device 100 is an information processing device that aims to suppress the provision of similar articles, and can be any device as long as it can realize the processing in the embodiment. The information processing device 100 can be realized by, for example, a server device or cloud system that provides a predetermined article that a user is viewing, or a server device or cloud system that provides a predetermined web service to which such predetermined article is distributed.

[0014] The information processing device 100 obtains user comments on an event, generates a first article, and generates management information related to the first article. The information processing device 100 then generates a second article from the obtained comments. The information processing device 100 then determines the similarity between the second article and the first article, and if it determines that the similarity is low, it provides the second article. The information processing device 100 also determines the similarity between the second article and the first article, and if it determines that the similarity is high, it regenerates the second article to lower the similarity and provides the regenerated second article. The information processing device 100 also updates the management information when it generates a second article or when it regenerates a second article.

[0015] In addition, the information processing device 100 has a model. The model is, for example, a text generation model obtained by training data such as data published on the Internet. For example, the model may be implemented by an AI (Artificial Intelligence) such as GPT (Generative Pre-trained Transformer). GPT is a text generation AI and a language model capable of generating text using natural language processing.

[0016] In FIG. 1, the case where the terminal device 10 and the information processing device 100 are separate devices is shown, but the terminal device 10 and the information processing device 100 may be integrated.

[0017] [2. An Example of Information Processing] FIG. 2 is a diagram showing an example of information processing of the information processing system 1 according to the embodiment.

[0018] First, the information processing device 100 acquires a user comment C on an event (step S1). The information processing device 100 acquires the user comment C on an article (not shown) of the event. In the embodiment, an article related to the economy is shown, but it may be an article of any genre such as sports, entertainment, politics, etc.

[0019] Subsequently, the information processing device 100 generates a first article A1 (step S2). The information processing device 100 generates the first article A1 from the acquired comment C. The information processing device 100 provides the first article A1 to the terminal device 10.

[0020] Next, the information processing device 100 generates and stores management information M (step S3). The information processing device 100 generates and stores management information M related to the first article A1. The information processing device 100 extracts keywords K from comments C and the first article A1. The information processing device 100 generates management information M as a set of keywords K related to the first article A1, the acquired comments C, and the content of the first article A1. For example, the information processing device 100 generates management information M by using the GPT model. The information processing device 100 generates management information M and stores it for a predetermined period. For example, the information processing device 100 stores management information M for one week. Note that the predetermined period is not limited to one week. The predetermined period may be longer or shorter than one week depending on the content of the event or article, the content of the comments, etc. For example, the information processing device 100 may store management information M for the duration of an event (e.g., the Olympics), for one season (e.g., only summer), or for several days (e.g., from the formation to the dissipation of a typhoon).

[0021] Next, the information processing device 100 generates a new second article A2 from the acquired comment C (step S3). For example, the information processing device 100 generates the second article A2 using the GPT model. The information processing device 100 generates the second article A2, for example, within a predetermined period. The information processing device 100 generates the second article A2 at regular intervals (for example, every hour).

[0022] Furthermore, once the second article A2 is generated, the information processing device 100 updates the management information M. The information processing device 100 then links the updated management information M1 to the management information M. For example, the management information is numbered and linked to the management information M and the updated management information M1.

[0023] Furthermore, the information processing device 100 deletes the stored management information M after a predetermined period of time has elapsed.

[0024] Here, we will describe the GPT model according to the embodiment. The GPT model according to the embodiment generates a first article when, for example, the acquired comment and instruction information to generate a first article are input as prompts. Also, for example, the GPT model according to the embodiment generates management information M when, for example, the keyword K related to the first article A1, the acquired comment C, and instruction information to generate the first article A1 and management information M are input as prompts. Also, for example, the GPT model according to the embodiment generates a second article A2 when, for example, the acquired comment and instruction information to generate a second article A2 are input as prompts.

[0025] An example of a prompt for generating the first article A1 is, "Generate an article (first article) from the retrieved comments. The retrieved comments are listed below." For example, the GPT model determines that the more frequently a keyword is included in the retrieved comments, the more important that keyword is and generates an article. For example, the GPT model determines that the keyword is important if the same keyword is included multiple times in the retrieved comments and generates an article.

[0026] An example of a prompt for generating management information M is, "Generate information about the first article as management information. Specifically, generate a summary of the article by combining keywords related to the first article, the retrieved comments, and the first article itself." For example, the GPT model will determine that the more keywords a keyword contains in the retrieved comments and the first article A1, the more important that keyword is and generate an article. For example, the GPT model will determine that the keyword is important if the same keyword is included multiple times in the retrieved comments and generate an article.

[0027] Furthermore, an example of a prompt to generate a second article (A2) from comments is: "Please generate a new article (second article) from the retrieved comments. Please generate the second article so that it is not similar in content to the first article. The retrieved comments are listed below."

[0028] Furthermore, an example of a prompt to update management information M is: "When a second article is newly generated, please update the management information to reflect the second article. Specifically, generate a summary of the second article from the keywords related to the second article, the comments on the second article, and the content of the second article. Also, number and link the updated management information with the management information generated when the first article was generated."

[0029] Next, the information processing device 100 determines the similarity between the second article A2 and the first article A1 (step S4). The information processing device 100 determines the similarity between the second article A2 and the first article A1 based on the management information M. For example, the information processing device 100 compares the management information M with the second article A2 to determine whether the similarity between the second article A2 and the first article A1 exceeds the first threshold. The information processing device 100 compares the summary text of the management information M with the similarity between the second article A2 and the first article A1 to determine whether the similarity exceeds the first threshold. If the information processing device 100 determines that the similarity between the second article A2 and the first article A1 exceeds the first threshold, it compares the second article A2 with the detailed information of the management information M to determine whether the similarity exceeds the second threshold. Specifically, if the information processing device 100 determines that the similarity between the second article A2 and the first article A1 exceeds a first threshold, it compares the second article A2 with the keyword K, the acquired comment C, and the content of the first article A1 to determine whether the similarity exceeds a second threshold. The information processing device 100 may, for example, vectorize the first article A1 and the second article A2, and calculate the cosine similarity of each vector as the similarity between the second article A2 and the first article A1.

[0030] Next, if the information processing device 100 determines that the similarity between the second article A2 and the first article A1 is low, it provides the second article A2 to the terminal device 10 (step S5). For example, if the information processing device 100 determines that the similarity between the second article A2 and the first article A1 is below the second threshold, it provides the second article.

[0031] Figure 2 shows an example of information processing according to the embodiment. Figure 2 shows the case where the second article A2 is a similar article A2a. A similar article A2a is an article whose similarity threshold exceeds the second threshold.

[0032] For example, if the information processing device 100 determines that the similarity between the second article A2 and the first article A1 exceeds the second threshold, that is, if it generates a similar article A2a, it regenerates the second article A2 (similar article A2a) so that the similarity is below the second threshold. In the example shown in Figure 2, the information processing device 100 regenerates similar article A2a into a second article A2b, whose similarity is below the second threshold.

[0033] For example, the information processing device 100 changes the prompt that generated the second article A2. The information processing device 100 changes the prompt to regenerate a similar article A2a as the second article A2b (A2) from a different perspective.

[0034] An example of a prompt to regenerate a similar article A2a into a second article A2b (A2) is: "The newly generated article is similar to other articles in that it explains the trends in inflation rates and their impact on the stock market. Therefore, please regenerate the article from a different perspective. For example, please analyze, with specific examples, how rising inflation rates affect the cost of living for ordinary consumers. In this case as well, please regenerate the article from the acquired comments. The acquired comments are listed below." It should be noted that some of the prompts for generating the second article are not limited to "Please analyze, with specific examples, how rising inflation rates affect the cost of living for ordinary consumers," but may also include "Compare successful and unsuccessful examples of inflation control measures in different countries and consider their impact on the stock market," or "Explain in detail, with expert opinions, the unique impacts that inflation has on specific regions and industries," or all of these may be included.

[0035] Furthermore, when a similar article A2a is generated, the information processing device 100 also updates the management information M. In Figure 2, when the information processing device 100 generates a similar article A2a, it updates the management information M to management information M1. When the information processing device 100 regenerates the similar article A2a into a second article A2, it updates the management information M1 to management information M2.

[0036] [3. Configuration of the terminal device] Next, the configuration of the terminal device 10 according to the embodiment will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Figure 3, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0037] (Communications Section 11) The communication unit 11 is implemented, for example, by a NIC (Network Interface Card). The communication unit 11 is connected to a predetermined network N by wire or wireless connection and sends and receives information to and from the information processing device 100 via the predetermined network N.

[0038] (Input section 12) The input unit 12 receives various operations from the user. In Figure 2, it receives various operations from user U1. For example, the input unit 12 may receive various operations from the user via the display surface using a touch panel function. Alternatively, the input unit 12 may receive various operations from buttons provided on the terminal device 10, or from a keyboard or mouse connected to the terminal device 10.

[0039] (Output section 13) The output unit 13 is a display screen for a tablet terminal, for example, which is implemented using a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various types of information. For example, the output unit 13 displays content based on information transmitted from the information processing device 100.

[0040] (Control Unit 14) The control unit 14 is, for example, a controller, and is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the internal memory of the terminal device 10 using RAM (Random Access Memory) as the working area. For example, these various programs include application programs installed on the terminal device 10. For example, these various programs include application programs that display content based on information transmitted from the information processing device 100. The control unit 14 is also implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0041] As shown in Figure 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0042] (Receiver 141) The receiving unit 141 receives information transmitted from, for example, the information processing device 100. For example, the receiving unit 141 receives information such as a predetermined article or voting content that the user is viewing as feedback on the user's operation.

[0043] (Transmitter 142) The transmission unit 142 transmits, for example, user operation information to the terminal device 10. For example, the transmission unit 142 transmits operation information performed by the user on the UI screen of a comment posted on a predetermined article that the user is viewing. For example, the transmission unit 142 transmits operation information such as posting a comment on an article or voting information from voting content.

[0044] [4. Configuration of the Information Processing Device] Next, the configuration of the information processing device 100 according to the embodiment will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also have an input unit (for example, a keyboard or mouse) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display) for displaying various information.

[0045] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC. The communication unit 110 is connected to the network N by wire or wireless connection and sends and receives information to and from terminal devices 10, etc., via the network N.

[0046] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 4, the storage unit 120 includes a comment information storage unit 121, a generated article information storage unit 122, and a management information storage unit 123.

[0047] 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 5 shows an example of the comment information storage unit 121 according to the embodiment. Figure 5 is a diagram showing an example of the comment information storage unit according to the embodiment. As shown in Figure 5, the comment information storage unit 121 has items such as "comment ID", "comment content", "posting date and time", and "keywords".

[0048] "Comment ID" indicates identification information used to identify a comment. "Comment Content" indicates the content of the comment. In the example shown in Figure 5, conceptual information such as "Comment Content #1" and "Comment Content #2" is shown as being stored in "Comment Content," but in reality, the text of the article, etc., is stored. "Posting Date and Time" indicates the posting date and time when the comment was posted. In the example shown in Figure 5, conceptual information such as "Posting Date and Time #1" and "Posting Date and Time #2" is shown as being stored in "Posting Date and Time," but in reality, the date and time when the comment was posted, etc., is stored. "Keywords" indicates keywords in the comment content. In the example shown in Figure 5, conceptual information such as "Keyword #1" and "Keyword #2" is shown as being stored in "Keywords," but in reality, keywords of the comment, etc., are stored.

[0049] The generated article information storage unit 122 stores information about the generated article. For example, the generated article information storage unit 122 stores information such as the article's content, title, category, and delivery date and time. Here, Figure 6 shows an example of the generated article information storage unit 122 according to the embodiment. Figure 6 is a diagram showing an example of the generated article information storage unit according to the embodiment. As shown in Figure 6, the generated article information storage unit 122 has items such as "generated article ID", "content", "title", "category", "delivery date and time", and "keywords".

[0050] "Generated Article ID" indicates identification information for identifying the generated article. "Content" indicates the content of the generated article. In the example shown in Figure 6, conceptual information such as "Content #1" and "Content #2" is shown as being stored in "Content," but in reality, the text of the generated article is stored there. "Title" indicates the title of the generated article. In the example shown in Figure 6, conceptual information such as "Title #1" and "Title #2" is shown as being stored in "Title," but in reality, the text of the title is stored there. "Category" indicates the category of the article (e.g., economy, entertainment, sports, incidents and accidents, etc.). The category may also be, for example, controversial, royal family, politics, international, domestic, LGBT, lifestyle, etc. "Delivery Date and Time" indicates the delivery date and time of the article. "Keywords" indicates the keywords of the generated article. In the example shown in Figure 6, conceptual information such as "Keyword #1" and "Keyword #2" is shown as being stored in "Keywords," but in reality, the keywords of the generated article are stored there.

[0051] The management information storage unit 123 stores management information. For example, the management information storage unit 123 stores an overview of an article. Here, Figure 7 shows an example of the management information storage unit 123 according to the embodiment. Figure 7 is a diagram showing an example of the management information storage unit according to the embodiment. As shown in Figure 7, the management information storage unit 123 has items such as "management information ID" and "overview text".

[0052] The "Management Information ID" indicates identification information used to identify the management information. The "Summary" indicates the content of the management information. In the example shown in Figure 7, conceptual information such as "Summary #1" and "Summary #2" is stored in the "Summary," but in reality, a summary of the article and other similar information would be stored there.

[0053] (Control unit 130) The control unit 130 is a controller, and is implemented, for example, by a CPU or MPU executing various programs stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 130 can be implemented by an integrated circuit such as an ASIC or FPGA.

[0054] As shown in Figure 4, the control unit 130 includes an acquisition unit 131, a first generation unit 132, a second generation unit 133, a third generation unit 134, a determination unit 135, a regeneration unit 136, and a provision unit 137, and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 4, and other configurations are also acceptable as long as they perform the information processing described later.

[0055] (Acquisition part 131) The acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 also stores the acquired information in the storage unit 120.

[0056] The acquisition unit 131 acquires various information from external information processing devices. The acquisition unit 131 also acquires various information from other information processing devices such as the terminal device 10.

[0057] The acquisition unit 131 acquires user information about the user. The acquisition unit 131 acquires articles about the event. The acquisition unit 131 acquires user comments C regarding the event.

[0058] (first generation unit 132) The first generation unit 132 generates the first article A1. The first generation unit 132 generates the first article A1 from the acquired comment C.

[0059] (Second generation unit 133) The second generation unit 133 generates a new second article A2 from the acquired comment C. The second generation unit 133 generates the second article A2 using the GPT model. The second generation unit 133 generates the second article A2, for example, over a predetermined period of time. The second generation unit 133 generates the second article A2 at regular intervals.

[0060] Furthermore, the second generation unit 133 regenerates the second article A2. For example, if the determination unit 135 determines that the similarity between the second article A2 and the first article A1 exceeds the second threshold, the second generation unit 133 regenerates the second article A2. If the generated second article A2 is a similar article A2a, the second generation unit 133 regenerates the similar article A2a into a second article A2b (A2) whose similarity is less than or equal to the second threshold.

[0061] (Third generation unit 134) The third generation unit 134 generates and stores management information M related to the first article A1. The third generation unit 134 extracts keywords K related to the first article A1 from the article content and the content of comment C. The third generation unit 134 generates management information M as a set of keywords related to the first article, the acquired comment C, and the content of the first article A1, and stores the management information M for a predetermined period. For example, the second generation unit 133 stores the management information M for one week. The third generation unit 134 may also store the management information M for the duration of an event or for one season. The third generation unit 134 generates the management information M using the GPT model. The third generation unit 134 updates the management information M when the second generation unit 133 generates the second article A2. The third generation unit 134 links the updated management information M1 to the management information M. For example, the third generation unit 134 links the management information M with the updated management information M1 by numbering the management information.

[0062] Furthermore, the third generation unit 134 deletes the stored management information M after a predetermined period of time has elapsed.

[0063] (Judgment unit 135) The determination unit 135 determines the similarity between the second article A2 and the first article A1. The determination unit 135 determines the similarity between the second article and the first article based on the management information. For example, the determination unit 135 compares the management information M with the second article A2 to determine whether the similarity between the second article A2 and the first article A1 exceeds the first threshold. The determination unit 135 compares the summary text of the management information M to determine whether the similarity between the second article A2 and the first article A1 exceeds the first threshold. For example, the determination unit 135 compares the summary text of the management information M to determine whether the similarity between the second article A2 and the first article A1 exceeds the first threshold. If the determination unit 135 determines that the similarity between the second article A2 and the first article A1 exceeds the first threshold, it compares the second article A2 with the detailed information of the management information M to determine whether the similarity exceeds the second threshold. Specifically, if the determination unit 135 determines that the similarity between the second article A2 and the first article A1 exceeds the first threshold, it compares the second article A2 with the keyword K, the acquired comment C, and the content of the first article A1 to determine whether the similarity exceeds the second threshold. The determination unit 135 may, for example, vectorize the first article A1 and the second article A2, and calculate the cosine similarity of each vector as the similarity between the second article A2 and the first article A1.

[0064] (Regeneration unit 136) If the determination unit 135 determines that the similarity between the second article A2 and the first article A1 exceeds the second threshold, the regeneration unit 136 instructs the second generation unit 133 to regenerate the second article A2.

[0065] For example, if the third generation unit 134 generates a similar article A2a in which the similarity between the second article A2 and the first article A1 exceeds the second threshold, the regeneration unit 136 causes the third generation unit 134 to regenerate similar article A2a so that the similarity is below the second threshold. The regeneration unit 136 causes the third generation unit 134 to regenerate similar article A2a into second article A2, in which the similarity is below the second threshold. For example, the regeneration unit 136 changes the prompt that generated second article A2. The regeneration unit 136 changes the prompt to regenerate similar article A2a into second article A2 from a different perspective.

[0066] Furthermore, when the regeneration unit 136 generates a similar article A2a, it updates the management information M to management information M1. When the information processing device 100 regenerates the similar article A2a into a second article A2, it updates the management information M1 to management information M2.

[0067] (Providing Department 137) The provisioning unit 137 provides articles to the terminal device 10. The provisioning unit 137 provides the first article A1 to the terminal device 10. The provisioning unit 137 provides the second article A2 to the terminal device 10. If the determination unit 135 determines that the similarity between the second article A2 and the first article A1 is low, the provisioning unit 137 provides the second article to the terminal device 10. For example, if the determination unit 135 determines that the similarity between the second article A2 and the first article A1 is below the second threshold, the provisioning unit 137 provides the second article to the terminal device 10. In addition, if the third generation unit 134 regenerates the second article A2, the provisioning unit 137 provides the regenerated second article A2. If the second article A2 generated by the third generation unit 134 is a similar article A2a, the providing unit 137 regenerates the similar article A2a into a second article A2 whose similarity is less than or equal to the second threshold, and provides the regenerated second article A2.

[0068] [5. Information Processing Flow] Next, the information processing procedure by the information processing system 1 according to the embodiment will be explained using Figure 8. Figure 8 is a flowchart showing the information processing procedure by the information processing system 1 according to the embodiment.

[0069] As shown in Figure 8, the information processing device 100 obtains user comments on the event (step S101).

[0070] The information processing device 100 generates the first article A1 from the comments (step S102).

[0071] The information processing device 100 generates management information M about the first article A1, using the keyword K related to the first article A1, the acquired comment C, and the first article as a set (step S103).

[0072] The information processing device 100 generates a new second article from the acquired comment C (step S104).

[0073] The information processing device 100 determines whether the second article is similar to the first article (step S105). The information processing device 100 determines whether the similarity between the second article and the first article is below a threshold.

[0074] If the information processing device 100 determines that the similarity of the second article A2 to the first article A1 is below a threshold (low similarity) (step S105; No), it provides the second article A2 (step S107).

[0075] If the information processing device 100 determines that the similarity of the second article A2 to the first article A1 exceeds a threshold (i.e., they are similar) (step S105; Yes), it regenerates the second article A2 (step S106) and provides the regenerated second article A2 (step S107). If the generated second article A2 is a similar article A2a, the information processing device 100 regenerates the similar article A2a into a second article A2b whose similarity is less than or equal to the second threshold, and provides the regenerated second article A2b.

[0076] [6. Effects] As described above, the information processing device 100 according to the embodiment is characterized by comprising: an acquisition unit 131 that acquires user comments on an event; a first generation unit 132 that generates a first article from the acquired comments; a second generation unit 133 that generates a second article from the acquired comments; a determination unit 135 that determines the similarity between the second article and the first article based on management information; and a provision unit 137 that provides the second article if the determination unit 135 determines that the similarity of the second article is low.

[0077] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0078] Furthermore, the information processing device according to this embodiment further includes a third generation unit 134 that generates and stores management information relating to the first article.

[0079] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0080] Furthermore, the second generation unit 133 updates the management information once the third generation unit 134 has generated the second article.

[0081] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0082] Furthermore, the second generation unit 133 generates management information as a set of keywords related to the first article, acquired comments, and the content of the first article, and stores the management information for a predetermined period.

[0083] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0084] Furthermore, the determination unit 135 compares the management information with the second article to determine whether the similarity exceeds the first threshold.

[0085] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0086] Furthermore, if the determination unit 135 determines that the similarity exceeds the first threshold, it compares the keywords related to the second article and the first article, the acquired comments, and the content of the first article to determine whether the similarity exceeds the second threshold.

[0087] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0088] Furthermore, the information processing device 100 includes a regeneration unit 136 that causes the second generation unit 133 to regenerate the second article if the determination unit 135 determines that the similarity exceeds the second threshold.

[0089] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0090] The provisioning unit 137 provides a second article if the determination unit 135 determines that the similarity is below the second threshold.

[0091] As a result, the information processing device 100 according to this embodiment can suppress the provision of similar articles.

[0092] [7. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having the configuration shown in Figure 9. Figure 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0093] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls various parts. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0094] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 acquires data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0095] 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 the generated data to output devices via the input / output interface 1600.

[0096] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 can be, for example, an optical recording medium such as a 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 medium, or semiconductor memory.

[0097] For example, when the computer 1000 functions as an information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the RAM 1200. 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 other devices via a predetermined communication network.

[0098] [8. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0099] 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.

[0100] Furthermore, the embodiments described above can be combined as appropriate, as long as the processing content is not contradictory.

[0101] Although some embodiments of the present invention have been described in detail above with reference to the 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.

[0102] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0103] 1. Information Processing System 10 Terminal devices 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Comment Information Storage Unit 122 Generated Article Information Storage Unit 123 Management information storage unit 130 Control Unit 131 Acquisition Department 132 1st generation part 133 Second generation part 134 Third generation part 135 Judgment section 136 Regeneration part 137 Provision Department 141 Receiving Unit 142 Transmitter N Network

Claims

1. A unit for obtaining user comments on an event, A first generation unit generates a first article from the aforementioned acquired comments, A second generation unit generates a new second article from the aforementioned acquired comments, A determination unit for determining the similarity between the second article and the first article, If the determination unit determines that the similarity is low, the provision unit provides the second article, An information processing device characterized by having the following features.

2. It further comprises a third generation unit that generates and stores management information relating to the first article. The information processing apparatus according to feature 1.

3. The second generation unit updates the management information once the third generation unit has generated the second article. The information processing apparatus according to feature 2.

4. The third generation unit generates the management information as a set of keywords related to the first article, the acquired comments, and the content of the first article, and stores the management information for a predetermined period. The information processing apparatus according to feature 2.

5. The determination unit compares the management information with the second article and determines whether the similarity exceeds the first threshold. The information processing apparatus according to feature 2.

6. If the determination unit determines that the similarity exceeds the first threshold, it compares the keywords related to the second article and the first article, the acquired comments, and the content of the first article to determine whether the similarity exceeds the second threshold. The information processing apparatus according to feature 5.

7. If the determination unit determines that the similarity exceeds the second threshold, the regeneration unit further comprises a regeneration unit that causes the second generation unit to regenerate the second article. The information processing apparatus according to feature 6.

8. The providing unit provides the second article if the determination unit determines that the similarity is less than or equal to the second threshold. The information processing apparatus according to feature 7.

9. A method of information processing performed by a computer, The process of obtaining user comments on an event, The first generation step involves generating the first article from the acquired comments, A second generation step involves generating a new second article from the aforementioned comments obtained, A determination step for determining the similarity between the second article and the first article, If the determination step determines that the similarity is low, the provision step of providing the second article is performed. An information processing method characterized by including

10. Procedure for obtaining user comments on an event, The first generation procedure involves generating the first article from the aforementioned comments obtained, The second generation procedure involves generating a new second article from the aforementioned comments obtained, A procedure for determining the similarity between the second article and the first article, If the determination procedure determines that the similarity is low, the procedure for providing the second article is performed, An information processing program characterized by causing a computer to execute it.

Images