Information processing apparatus, information processing method, and information processing program

Abstract

To provide content related to event information of a predetermined target.SOLUTION: An information processing apparatus according to the present application includes an extracting unit configured to extract, from a target content item associated with a predetermined target, event information related to the target, a specifying unit configured to specify a relationship between the event information extracted by the extracting unit and a collected content item collected on a web, a generating unit configured to generate a corresponding content item corresponding to the target based on the collected content item whose relationship with the event information satisfies a predetermined condition, and a providing unit configured to provide the corresponding content item generated by the generating unit.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for providing various information to users via the Internet. One example of such a technique is a technique for selecting representative articles by issue from news articles distributed via the Internet. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-204507 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques cannot be said to be capable of providing content related to event information of a predetermined target.

[0005] For example, the above-mentioned technology merely selects and provides representative articles for each issue, and cannot be said to be able to provide content related to event information of a predetermined target.

[0006] The present application has been made in view of the above, and aims to provide content relating to event information of a predetermined target. [Means for solving the problem]

[0007] The information processing device according to the present application is characterized by having an extraction unit that extracts event information related to a specified target from target content linked to the target; an identification unit that identifies the relevance between the event information extracted by the extraction unit and collected content collected on the web; a generation unit that generates corresponding content corresponding to the target based on the collected content whose relevance with the event information satisfies specified conditions; and a provision unit that provides the corresponding content generated by the generation unit. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to provide content relating to event information of a predetermined target. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the target content database 31. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing an example of the collected content database 32. As shown in FIG. [Figure 5] FIG. 5 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] 1. Embodiment Information processing implemented by an information processing device or the like according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that in Fig. 1, it is assumed that the information processing according to the embodiment is implemented by an information processing device 10, which is an example of the information processing device according to the present application.

[0012] As shown in Fig. 1, an information processing system 1 according to an embodiment includes an information processing device 10, a user terminal 100, and a server device 200. The information processing device 10, the user terminal 100, and the server device 200 are connected to each other via a network N (see Fig. 2, for example) so as to be able to communicate with each other via wired or wireless means. The network N is, for example, a wide area network (WAN) such as the Internet. Note that the information processing system 1 shown in Fig. 1 may include a plurality of information processing devices 10, a plurality of user terminals 100, and a plurality of server devices 200.

[0013] 1 is an information processing device that realizes information processing according to the embodiment, and is realized by, for example, a server device, a cloud system, etc. In the example of FIG. 1, the information processing device 10 is an information processing device that operates a search service that acquires content (e.g., a web page) corresponding to a search query entered by a user from content published on the Internet and provides the acquired content.

[0014] The information processing device 10 may have a function as a web server that provides a website related to a search service. The information processing device 10 may also be a device that distributes information to the user terminal 100 to be displayed in an application related to a search service installed in the user terminal 100. The information processing device 10 may also be a server that distributes the application data itself. The information processing device 10 may also function as a distribution device that distributes control information to the user terminal 100. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). The application itself distributed from the information processing device 10 may also be considered as control information.

[0015] The user terminal 100 shown in Fig. 1 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Fig. 1, the user terminal 100 is a smartphone used by a user.

[0016] Furthermore, the user terminal 100 displays information provided by the information processing device 10 using a web browser or an application. When the user terminal 100 receives control information for realizing information display processing from the information processing device 10 or the like, the user terminal 100 realizes the display processing in accordance with the control information.

[0017] 1 is a web server that manages content provided to users via a search service. Here, the content managed by the server device 200 refers to, for example, news articles, information distributed on websites related to a specific subject (e.g., official websites, fan club sites, etc.), information posted by users, still images, moving images, etc.

[0018] The information processing performed by the information processing device 10 will be described below with reference to FIG. 1. In the following description, it is assumed that the user terminal 100 is used by a user (user U1) identified by the user ID "UID#1." In the following description, the user terminal 100 may be considered to be the same as the user U1. In other words, in the following description, the user U1 may also be read as the user terminal 100.

[0019] In the following description, an example will be given in which the information processing system 1 includes a plurality of server devices 200-1 to 200-N (N is any natural number), but when there is no need to distinguish between the server devices 200-1 to 200-N, they will be referred to as server device 200.

[0020] First, the information processing device 10 crawls the network N and collects content managed by the server device 200 (step S1). For example, the information processing device 10 collects information such as text information indicated by the content managed by the server device 200 and images (still images and moving images) included in the content.

[0021] In the following description, the content collected in step S1 may be referred to as "collected content."

[0022] Next, the information processing device 10 extracts event information related to an event that occurred regarding a specific target #1 from target content #1 linked to the target #1 (step S2). Here, in the example of FIG. 1, it is assumed that target #1 is a specific person (individual) whose occupation (attribute) is actor. In such a case, the information processing device 10 extracts event information related to an event that occurred regarding target #1 from target content #1, which is a webpage indicating an Internet encyclopedia related to target #1 (for example, Wikipedia (registered trademark)) or an official page of target #1 (for example, a webpage operated by a production company to which target #1 belongs).

[0023] To cite a specific example, information processing device 10 extracts event information for target #1 using target content #1 and model #1 that has been trained to generate answers to input questions. To cite a more specific example, information processing device 10 extracts event information for target #1 by inputting target content #1 and an instruction sentence instructing model #1 to extract multiple pieces of event information from target content #1 (e.g., extracting event information corresponding to each of 10 events), including text information indicating the details of events that occurred related to target #1, key terms in the text information, and information about the era in which the events occurred. Here, in the example of FIG. 1, event information #1 related to event #1, event information #2 related to event #2, etc. are assumed to be extracted.

[0024] In the example of Fig. 1, events that occurred regarding subject #1 refer to, for example, subject #1's upbringing, debut, appearance in a work, etc. (in other words, subject #1's career). Also, in the example of Fig. 1, characteristic words refer to, for example, a character string that indicates an event (for example, the title of a work) or subject #1's position in the event (for example, the role played).

[0025] Model #1 is a model trained to output an answer corresponding to an input question, and is a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) or Transformer. Model #1 is stored in information processing device 10 and was created independently by the business operator that manages information processing device 10. It is desirable to keep input information, such as personal information, confidential by training it so that it will not be used as a new answer.

[0026] Furthermore, the target content #1 may be content collected by the information processing device 10 by crawling the network N in step S1, or may be content collected by the information processing device 10 from a web page showing an Internet encyclopedia about the target #1, the official page of the target #1, etc.

[0027] Next, the information processing device 10 identifies the association between the collected content and the event information of the target #1 (step S3). For example, the information processing device 10 identifies the association between the collected content and the event information #1, the association between the collected content and the event information #2, and so on.

[0028] For example, the more frequently the characteristic word #1 indicated by the event information #1 appears in a collected content, the more the information processing device 10 identifies (determines) the higher the relevance between the collected content and the event information #1. Furthermore, the information processing device 10 determines that the relevance between the collected content that includes the characteristic word #1 in the title and the event information #1 is higher than that between the collected content and the other collected content.

[0029] In addition, the information processing device 10 uses a technique such as Word2Vec to convert characteristic word #1 and a character string contained in the collected content (e.g., a characteristic word in the collected content) into a vector, and determines that the higher the similarity (e.g., cosine similarity) between the vector of the character string and the vector of characteristic word #1, the higher the correlation between the collected content and event information #1.

[0030] Any method may be used to convert the feature words and character strings included in the collected content into vectors, and any method may be used to extract feature words from the collected content.

[0031] Next, the information processing device 10 generates corresponding content C1 corresponding to the target #1 based on collected content whose relevance to the event information satisfies a predetermined condition (step S4). For example, the information processing device 10 generates corresponding content C1 based on collected content whose relevance to the event information is equal to or greater than a predetermined threshold.

[0032] As a specific example, the information processing device 10 generates corresponding content C1 including an area AR1 showing a profile of target #1 (e.g., information included in target content #1) and areas (e.g., areas AR2 and AR3) showing information on events #1, #2, ... that occurred regarding target #1 in chronological order of each event (e.g., chronological order based on the era included in each event information). As an example, the information processing device 10 generates information showing event #1 (e.g., a summary of collected content #11, #12, #13, ...; hereinafter, sometimes referred to as "summary #1") based on collected content #11, #12, #13, ... that has a relationship with event information #1 above a predetermined threshold, and generates corresponding content C1 showing the generated summary #1 and an image corresponding to event #1 in area AR2. In addition, the information processing device 10 generates information indicating event #2 (for example, a summary of collected content #21, #22, #23, .... hereinafter, may be referred to as "summary #2") based on collected content #21, #22, #23, ... that is greater than or equal to a predetermined threshold value with respect to event information #2, and generates corresponding content C1 that shows the generated summary #2 and an image corresponding to event #2 in area AR3.

[0033] That is, the information processing device 10 generates corresponding content C1 showing a brief biography of subject #1.

[0034] The information processing device 10 may generate a summary of each event using collected content and model #2 that has been trained to generate answers to input questions. For example, the information processing device 10 generates summary #1 by inputting collected content #11, #12, #13, and so on and an instruction sentence instructing model #2 to output summaries of collected content #11, #12, #13, and so on.

[0035] Furthermore, the information processing device 10 may select an image corresponding to each event by any method. For example, the information processing device 10 may select an image corresponding to event #1 from images included in any of collected content #11, #12, #13, ..., or may select an image from images included in target content #1.

[0036] Next, the information processing device 10 receives the search query entered by the user U1 in the search service from the user terminal 100 (step S5). Next, the information processing device 10 provides the user terminal 100 with corresponding content corresponding to the search query entered by the user U1 via the search service (step S6). For example, if the user U1 enters a search query including a character string indicating target #1, the information processing device 10 provides corresponding content C1 on a screen showing search results corresponding to the search query.

[0037] As described above, the information processing device 10 according to the embodiment generates content corresponding to a predetermined target based on collected content whose relevance to event information about the target satisfies predetermined conditions, and provides the content to the user. This allows the information processing device 10 according to the embodiment to provide content related to event information about the target.

[0038] In addition, conventionally, when generating content related to a person's biography, the information used for generation may have to be collected manually. In such cases, the collection process takes time, and furthermore, the number of web pages, etc. from which information can be collected is limited, which may make it difficult to guarantee the quality of the collected information.

[0039] Therefore, the information processing device 10 according to the embodiment extracts event information of a target from reliable content, such as an Internet encyclopedia or an official page related to the target, and generates corresponding content related to the target's biography based on content highly relevant to the extracted event information among the content collected by crawling. This allows the information processing device 10 according to the embodiment to save the effort of collecting information and ensure the quality of the information used to generate the corresponding content. Furthermore, by using the content collected by crawling, the information processing device 10 according to the embodiment can suppress hallucination caused by a model (generative AI (Artificial Intelligence)) when generating the corresponding content.

[0040] [2. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are listed below.

[0041] [2-1. About the target] 1, the target is not limited to an individual, but may be a group consisting of multiple people (for example, a band, a musical unit, a comedy duo, etc.). In such a case, the information processing device 10 extracts event information related to an event that occurred regarding the group from the target content linked to the group, and generates associated content corresponding to the group based on collected content whose relevance to the extracted event information satisfies a predetermined condition.

[0042] In addition, if the target is an individual belonging to a group, the information processing device 10 may extract event information regarding events that occurred regarding the target and the group to which the target belongs from the target content linked to the target and the target content linked to the group to which the target belongs, and generate corresponding content corresponding to the group based on collected content whose relevance to the extracted event information meets specified conditions.

[0043] Furthermore, the target is not limited to a person, but may be an animal, an inanimate object, or content (for example, music, a movie, an animation, a game, a manga, etc.). Furthermore, the target may be a character in the content.

[0044] [2-2. About collected content] There may be a desire to exclude negative content related to a target (e.g., incidents, misconduct, scandals, etc. that have occurred regarding the target) from the corresponding content, and include only other content (in other words, positive content) in the corresponding content. Therefore, in the example of FIG. 1, when crawling the network N and collecting collected content, the information processing device 10 may collect only collected content that indicates positive content, and generate corresponding content that indicates positive content by identifying the association between event information and collected content that indicates positive content. For example, the information processing device 10 collects collected content that does not include strings that indicate negative content.

[0045] Furthermore, the information processing device 10 may crawl the network N and collect collected content indicating positive content and collected content indicating negative content. Then, the information processing device 10 may generate corresponding content indicating positive content based on collected content whose relevance to event information satisfies a predetermined condition and indicates positive content (for example, collected content that does not include a string indicating negative content).

[0046] [2-3. Regarding the order of each event] In the example of FIG. 1, the corresponding content generated by the information processing device 10 is not limited to the content showing the information on each event in chronological order of the events, and the corresponding content may be generated by arranging the events according to any criteria.

[0047] For example, if each event is related to target #1's appearance in a work such as a drama, information processing device 10 generates corresponding content that shows information about each event in order of the audience ratings of the drama corresponding to each event (e.g., in order of highest audience ratings). As an example, information processing device 10 extracts event information including the audience ratings of the drama corresponding to each event, and generates corresponding content that shows information about each event in order of the audience ratings of the drama corresponding to each event. Note that information processing device 10 may also extract the audience ratings of the drama corresponding to the event from the collected content.

[0048] Furthermore, if each event is related to target #1's appearance in a film or other work, the information processing device 10 generates corresponding content that displays information about each event in order of the box office revenue of the film or other work corresponding to each event (e.g., in descending order of box office revenue). As an example, the information processing device 10 extracts event information including the box office revenue of the film or other work corresponding to each event, and generates corresponding content that displays information about each event in order of the box office revenue of the film or other work corresponding to each event. Note that the information processing device 10 may also extract the box office revenue of the film or other work corresponding to each event from the collected content.

[0049] That is, the information processing device 10 may generate corresponding content that shows information about appearances in each work in the order of the most representative works in which the subject #1 has appeared.

[0050] Furthermore, for example, if the target is a writer and each event is related to the publication of a book that the writer has written, the information processing device 10 generates corresponding content that shows information about each event in order of the number of copies of the book corresponding to each event (for example, in order of the largest number of copies published). As an example, the information processing device 10 extracts event information including the number of copies of the book corresponding to each event, and generates corresponding content that shows information about each event in order of the number of copies of the book corresponding to each event. Note that the information processing device 10 may also extract the number of copies of the book corresponding to each event from the collected content.

[0051] In addition, if the event information and collected content do not include information such as the audience ratings of dramas in which the subject has appeared, the box office revenue of movies in which the subject has appeared, or the number of copies of books published by the subject, the information processing device 10 may generate corresponding content that shows information about each event in a predetermined order using LLMs (Large Language Models) such as GPT or Transformer. For example, the information processing device 10 inputs into a model each piece of event information, collected content whose relevance to each piece of event information satisfies a predetermined condition, and an instruction sentence that instructs the device to output each event in the order of the audience ratings of the corresponding drama. The information processing device 10 then generates corresponding content that shows information about each event in the order of the identified audience ratings.

[0052] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. As shown in Fig. 2, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0053] (Regarding the communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC), etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100, the server device 200, etc.

[0054] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 30 has a target content database 31, a collected content database 32, and a model database 33.

[0055] (Regarding target content database 31) The target content database 31 stores various types of information related to target content. An example of the information stored in the target content database 31 will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the target content database 31. In the example of Fig. 3, the target content database 31 has items such as "target content ID," "target," "text information," and "image information."

[0056] "Target content ID" indicates identification information for identifying the target content. "Target" indicates the target linked to the target content. "Text information" indicates the text information included in the target content. "Image information" indicates the images (moving images, still images) included in the target content.

[0057] That is, Figure 3 shows an example in which the target linked to the target content identified by the target content ID "TID#1" is "target #1", the text information included in the target content is "text information #1", and the image information is "image information #1".

[0058] (About Collected Content Database 32) The collected content database 32 stores various information related to collected content collected by the information processing device 10. An example of the information stored in the collected content database 32 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the collected content database 32. In the example of Fig. 4, the collected content database 32 has items such as "collected content ID," "text information," and "image information."

[0059] "Collected content ID" indicates identification information for identifying collected content. "Text information" indicates text information included in collected content. "Image information" indicates images included in collected content.

[0060] That is, FIG. 4 shows an example in which the text information included in the collected content identified by the collected content ID "SID#11" is "text information #11" and the image information is "image information #11".

[0061] (About Model Database 33) The model database 33 stores models that have been trained to generate answers to input questions.

[0062] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 40 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 2 , the control unit 40 according to the embodiment has an extraction unit 41, an identification unit 42, a generation unit 43, and a provision unit 44, and realizes or executes the functions and actions of information processing described below.

[0063] (Regarding the extraction unit 41) The extraction unit 41 extracts event information related to a predetermined target from target content associated with the target. For example, in the example of Fig. 1, the extraction unit 41 refers to the storage unit 30 (e.g., the target content database 31, the model database 33, etc.) and extracts event information related to an event that occurred in relation to a predetermined target #1 from target content #1 associated with the target #1.

[0064] The extraction unit 41 may also extract event information indicating characteristic words of events related to the target. For example, in the example of Fig. 1, the extraction unit 41 extracts event information including characteristic words in text information indicating the content of an event that occurred related to target #1.

[0065] The extraction unit 41 may also extract multiple pieces of event information corresponding to multiple events related to the target. For example, in the example of Fig. 1, the extraction unit 41 extracts event information #1 related to event #1, event information #2 related to event #2, etc.

[0066] Furthermore, the extraction unit 41 may further identify a time series of multiple events related to the target. For example, in the example of Fig. 1, the extraction unit 41 extracts event information #1 indicating the era in which event #1 occurred, event information #2 indicating the era in which event #2 occurred, ..., and identifies the time series in which events #1, #2, ... occurred based on the eras indicated by the extracted event information.

[0067] Furthermore, the extraction unit 41 may extract event information by inputting target content and an instruction sentence instructing a model trained to generate answers to input questions to extract event information from the target content. For example, in the example of Fig. 1, the extraction unit 41 extracts event information of target #1 using target content #1 and model #1 trained to generate answers to input questions.

[0068] (Regarding the identification unit 42) The identification unit 42 identifies the association between the event information extracted by the extraction unit 41 and collected content collected on the web. For example, in the example of Fig. 1, the identification unit 42 refers to the storage unit 30 (e.g., collected content database 32) and identifies the association between the collected content and the event information of target #1.

[0069] The identification unit 42 may also identify the association between the event information and collected content that indicates positive content. For example, in the example of FIG. 1, the identification unit 42 identifies the association between the event information and collected content that indicates positive content.

[0070] The identification unit 42 may also identify the relevance between a characteristic word indicated by the event information and the collected content. For example, in the example of FIG. 1 , the more frequently characteristic word #1 indicated by event information #1 appears in a collected content, the more highly the identification unit 42 determines that the collected content is highly highly related to event information #1. The identification unit 42 also determines that collected content that includes characteristic word #1 in its title is more highly related to event information #1 than other collected content. The identification unit 42 also converts characteristic word #1 and a character string included in the collected content into a vector, and the higher the similarity between the vector of the character string and the vector of characteristic word #1, the more highly the identification unit 42 determines that the collected content is highly related to event information #1.

[0071] Furthermore, the identification unit 42 may identify the relevance of each of the plurality of pieces of event information to the collected content. For example, in the example of Fig. 1, the identification unit 42 identifies the relevance between the collected content and event information #1, the relevance between the collected content and event information #2, and so on.

[0072] (Regarding the generation unit 43) The generation unit 43 generates corresponding content corresponding to the target based on collected content whose relevance to event information satisfies a predetermined condition. For example, in the example of Fig. 1, the generation unit 43 refers to the storage unit 30 (e.g., collected content database 32) and generates corresponding content C1 corresponding to target #1 based on collected content whose relevance to event information satisfies a predetermined condition.

[0073] Furthermore, the generation unit 43 may generate corresponding content based on collected content whose relevance to event information satisfies a predetermined condition and whose content indicates positive content. For example, in the example of Fig. 1, the generation unit 43 generates corresponding content whose relevance to event information satisfies a predetermined condition and whose content indicates positive content based on collected content whose relevance to event information satisfies a predetermined condition and whose content indicates positive content.

[0074] The generation unit 43 may also generate information indicating an event based on collected content whose relevance to event information corresponding to an event related to a target satisfies a predetermined condition, and generate corresponding content indicating information on each of multiple events related to the target. For example, in the example of FIG. 1, the generation unit 43 generates summary #1 based on collected content #11, #12, #13, ..., whose relationship with event information #1 is equal to or greater than a predetermined threshold, and generates corresponding content C1 that displays the generated summary #1 and an image corresponding to event #1 in area AR2. The generation unit 43 also generates summary #2 based on collected content #21, #22, #23, ..., whose relationship with event information #2 is equal to or greater than a predetermined threshold, and generates corresponding content C1 that displays the generated summary #2 and an image corresponding to event #2 in area AR3.

[0075] Furthermore, the generation unit 43 may generate corresponding content in which information on multiple events related to the target is arranged in chronological order. For example, in the example of Fig. 1, the generation unit 43 generates corresponding content C1 including an area showing information on events #1, #2, ... that occurred regarding the target #1 in chronological order of the events.

[0076] (About the provider 44) The providing unit 44 provides the corresponding content generated by the generating unit 43. For example, in the example of Fig. 1, the providing unit 44 provides the corresponding content C1 to the user terminal 100 via a search service.

[0077] Furthermore, the providing unit 44 may provide corresponding content to a user who inputs a search query related to a target. For example, in the example of Fig. 1, when a user U1 inputs a search query including a character string indicating target #1, the providing unit 44 provides corresponding content C1 on a screen showing search results corresponding to the search query.

[0078] [4. Information processing flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0079] As shown in FIG. 5, the information processing device 10 extracts event information related to a predetermined target from target content associated with the target (step S101). Next, the information processing device 10 identifies the relevance between the extracted event information and collected content collected on the web (step S102). Next, the information processing device 10 generates corresponding content related to the target based on the collected content whose relevance to the event information satisfies a predetermined condition (step S103). Next, the information processing device 10 determines whether a search query related to the predetermined target has been received from the user (step S104). If a search query has not been received (step S104; No), the information processing device 10 waits until a search query is received.

[0080] On the other hand, if a search query has been accepted (step S104; Yes), the information processing device 10 provides the corresponding content (step S105) and ends the process.

[0081] [5. Modifications] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0082] [5-1. Processing mode] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above text and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0083] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0084] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0085] [6. Effects] As described above, the information processing device 10 according to the embodiment includes an extraction unit 41, an identification unit 42, a generation unit 43, and a provision unit 44. The extraction unit 41 extracts event information related to a specific target from target content associated with the target. The extraction unit 41 extracts the event information by inputting the target content and an instruction sentence instructing a model trained to generate an answer to an input question to extract the event information from the target content. The identification unit 42 identifies the relevance between the event information extracted by the extraction unit 41 and collected content collected on the web. The generation unit 43 generates corresponding content corresponding to the target based on collected content whose relevance to the event information satisfies a predetermined condition. The provision unit 44 provides the corresponding content generated by the generation unit 43. The provision unit 44 also provides the corresponding content to a user who inputs a search query related to the target.

[0086] As a result, the information processing device 10 according to the embodiment can generate corresponding content for a specified target based on collected content whose relevance to event information related to the specified target satisfies specified conditions, and provide the content to the user, thereby providing content related to event information for the specified target.

[0087] In the information processing device 10 according to the embodiment, for example, the identification unit 42 identifies the association between the event information and the collected content indicating positive content, and the generation unit 43 generates corresponding content based on the collected content indicating positive content whose association with the event information satisfies a predetermined condition.

[0088] As a result, the information processing device 10 according to the embodiment can generate corresponding content that shows positive content, and can therefore meet the demand for providing content that shows only positive content.

[0089] In the information processing device 10 according to the embodiment, for example, the extracting unit 41 extracts event information indicating characteristic words of an event related to a target. Then, the identifying unit 42 identifies the relevance between the characteristic words indicated by the event information and the collected content.

[0090] As a result, the information processing device 10 according to the embodiment can identify the relevance to the collected content based on the characteristic words of the event, thereby improving the accuracy of the identified relevance.

[0091] Furthermore, in the information processing device 10 according to the embodiment, for example, the extraction unit 41 extracts a plurality of pieces of event information corresponding to a plurality of events related to the target. Then, the identification unit 42 identifies the relevance of each of the plurality of pieces of event information with the collected content. Then, the generation unit 43 generates information indicating the event related to the target based on the collected content whose relevance with the event information corresponding to the event satisfies a predetermined condition, and generates corresponding content indicating information for each of the plurality of events related to the target. Furthermore, the extraction unit 41 further identifies the chronological order of the plurality of events related to the target. Then, the generation unit 43 generates corresponding content in which information for each of the plurality of events related to the target is arranged in chronological order.

[0092] As a result, the information processing device 10 according to the embodiment can generate corresponding content indicating information on each of a plurality of events related to the target, and can therefore provide specific information on each event.

[0093] [7. Hardware Configuration] The information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 6. The information processing device 10 will be described below as an example. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0094] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0095] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0096] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0097] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0098] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1300 to realize the functions of the control unit 40. The HDD 1400 also stores various data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0099] [8. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0100] Furthermore, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing, depending on the function.

[0101] Furthermore, the term "unit" in the claims can be read as "means" or "circuit," etc. For example, a reception unit can be read as a reception means or a reception circuit. [Explanation of symbols]

[0102] 10. Information processing equipment 20 Communications Department 30 Storage section 31 Target Content Database 32 Collected Content Database 33 Model Database 40 Control Unit 41 Extraction part 42 Specific part 43 Generation part 44 Providing Department 100 user terminals 200 Server device

Claims

1. an extraction unit that extracts event information related to a predetermined target from target content associated with the target; an identification unit that identifies a relationship between the event information extracted by the extraction unit and collected content collected on the web; a generation unit that generates corresponding content corresponding to the target based on the collected content whose relevance to the event information satisfies a predetermined condition; a providing unit that provides the corresponding content generated by the generating unit; An information processing device comprising:

2. The identification unit Identifying associations between the event information and the collected content that indicates positive content 2. The information processing apparatus according to claim 1, wherein:

3. The generation unit The corresponding content is generated based on the collected content whose relevance to the event information satisfies a predetermined condition and indicates positive content.

2. The information processing apparatus according to claim 1, wherein:

4. The extraction unit extracting the event information indicating characteristic words of the event related to the target; The identification unit Identifying the relevance between the characteristic words indicated by the event information and the collected content 2. The information processing apparatus according to claim 1, wherein:

5. The extraction unit extracting a plurality of pieces of event information corresponding to a plurality of events relating to the target, The identification unit Identifying a relevance of each of the plurality of pieces of event information to the collected content; The generation unit generating information indicating the event based on the collected content whose relevance to the event information corresponding to the event related to the target satisfies a predetermined condition, and generating the corresponding content indicating information for each of a plurality of events related to the target; 2. The information processing apparatus according to claim 1, wherein:

6. The extraction unit further identifying a time series of a plurality of events relating to the subject; The generation unit Generate the corresponding content in which information on each of a plurality of events related to the target is arranged in chronological order.

6. The information processing apparatus according to claim 5,

7. The extraction unit The event information is extracted by inputting the target content and an instruction sentence instructing the model, which has been trained to generate an answer to an input question, to extract the event information from the target content.

2. The information processing apparatus according to claim 1, wherein:

8. The providing unit Providing the corresponding content to users who input search queries related to the subject 2. The information processing apparatus according to claim 1, wherein:

9. 1. A computer-implemented information processing method, comprising: an extraction step of extracting event information related to a predetermined target from target content associated with the target; an identifying step of identifying a relationship between the event information extracted by the extracting step and collected content collected on the web; a generating step of generating corresponding content corresponding to the target based on the collected content whose relevance to the event information satisfies a predetermined condition; a providing step of providing the corresponding content generated by the generating step; An information processing method comprising:

10. An extraction step of extracting event information related to a predetermined target from target content associated with the target; an identifying step of identifying a relationship between the event information extracted by the extracting step and collected content collected on the web; a generating step of generating corresponding content corresponding to the target based on the collected content whose relevance to the event information satisfies a predetermined condition; a providing step of providing the corresponding content generated by the generating step; An information processing program characterized by causing a computer to execute the above.

Images