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

Abstract

To grasp attributes of a user who has provided information.SOLUTION: An information processing apparatus includes: an acquisition unit which acquires comment information indicating a comment posted by a user for the content; an estimation unit which estimates attributes of the user for the content by inputting the comment information, content information regarding the content, and an instruction sentence instructing to output the attributes of the user for the content based on the comment information and the content information, to a model trained to output an answer to an input question; and a provision unit which provides the comment information together with attribute information indicating the attributes estimated by the estimation unit.SELECTED DRAWING: Figure 3

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, techniques related to information distribution via the Internet are known. As an example of such a technique, there is known a technique of receiving submissions of articles from a plurality of users via a network, editing the articles in the form of an electronic newspaper, and publishing them.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, with the above-described technique, it cannot be said that it is possible to grasp what attributes the user who provided the information has.

[0005] For example, with the above-described technique, it only publishes the articles submitted by the user, and it cannot be said that it is possible to grasp what attributes the user who provided the information has.

[0006] The present application has been made in view of the above, and an object thereof is to grasp what attributes the user who provided the information has.

Means for Solving the Problems

[0007] The information processing apparatus according to the present application includes: an acquisition unit that acquires comment information indicating comments posted by a user on content; for a model trained to output an answer to an input question, the comment information, content information regarding the content, and an instruction sentence that instructs to output the attributes of the user with respect to the content based on the comment information and the content information are input, and an estimation unit that estimates the attributes of the user with respect to the content; and a provision unit that provides the comment information together with attribute information indicating the attributes estimated by the estimation unit.

Advantages of the Invention

[0008] According to one aspect of the embodiment, there is an effect that it is possible to grasp what attributes the user who provided the information has.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0010] Hereinafter, embodiments for implementing an information processing apparatus, 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 apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and redundant explanations are omitted.

[0011] 〔1. Embodiment〕 Using FIG. 1, the information processing realized by the information processing apparatus and the like of this embodiment will be described. FIG. 1 is a diagram showing an example of information processing according to the embodiment. In FIG. 1, it is assumed that the information processing according to the embodiment is realized by an information processing apparatus 10, which is an example of the information processing apparatus according to the present application.

[0012] As shown in FIG. 1, the information processing system 1 according to the embodiment includes an information processing apparatus 10 and a user terminal 100. The information processing apparatus 10 and the user terminal 100 are connected to each other so as to be communicable by wire or wirelessly via a network N (for example, see FIG. 3). The network N is, for example, a WAN (Wide Area Network) such as the Internet. Note that the information processing system 1 shown in FIG. 1 may include a plurality of information processing apparatuses 10 and a plurality of user terminals 100.

[0013] The information processing apparatus 10 shown in FIG. 1 is an information processing apparatus that realizes the information processing according to the embodiment, and is realized, for example, by a server apparatus, a cloud system, or the like. In the example of FIG. 1, the information processing apparatus 10 is, for example, an information processing apparatus that provides a news service that provides content related to news articles to users.

[0014] Note that the information processing apparatus 10 may have a function as a web server that provides a website related to a news service. Further, the information processing apparatus 10 may be a device that distributes information to be displayed on an application related to the news service (hereinafter sometimes referred to as a "news app") installed on the user terminal 100. Further, the information processing apparatus 10 may be a server that distributes the news app data itself. Further, the information processing apparatus 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is described by, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the news app itself distributed from the information processing apparatus 10 may be regarded as control information.

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

[0016] Further, the user terminal 100 displays the information provided by the information processing apparatus 10 by means of a web browser or an application. Note that when the user terminal 100 receives control information for realizing information display processing from the information processing apparatus 10 or the like, the user terminal 100 realizes the display processing according to the control information.

[0017] Hereinafter, the information processing performed by the information processing apparatus 10 will be described with reference to FIG. 1. In the following description, the user terminals 100-1 to 100-N (N is an arbitrary natural number) will be described according to the users who use the user terminal 100. For example, the user terminal 100-1 is the user terminal 100 used by a user (user U1) identified by the user ID "UID#1". Also, hereinafter, when the user terminals 100-1 to 100-N are described without particular distinction, they will be referred to as the user terminal 100. Also, in the following description, the user terminal 100 may be regarded as the same as the user. That is, hereinafter, the user can also be read as the user terminal 100.

[0018] Also, in the following description, it is assumed that a news application is installed in the user terminal 100.

[0019] First, the information processing apparatus 10 acquires, from the user terminal 100, comment information indicating comments posted by the user on the content provided via the news application (step S1). For example, the information processing apparatus 10 acquires, from the user terminal 100-1, comment information #1 indicating a comment posted by the user U1 on the content #1 related to a news article indicating event #1 (for example, an incident, an accident, a disaster, etc.).

[0020] Subsequently, the information processing apparatus 10 estimates the attributes of user U1 with respect to content #1 based on comment information #1 and content information #1 regarding content #1 (for example, text information indicating a news article) (step S2). For example, the information processing apparatus 10 estimates the attributes of user U1 with respect to content #1 using comment information #1, content information #1, and model #1 that has been trained to generate answers to input questions. To give a specific example, the information processing apparatus 10 inputs comment information #1, content information #1, and an instruction sentence that instructs to output the attributes (text information) of user U1 with respect to content #1 based on comment information #1 and content information #1 into model #1, thereby estimating the attributes of user U1 with respect to content #1.

[0021] To give a more specific example, the information processing apparatus 10 inputs into model #1, together with comment information #1 and content information #1, a rule that defines whether to output whether user U1 is a "person involved" in event #1 (for example, a person belonging to the group that caused event #1 or a person affected (such as suffering damage) by event #1), a rule that defines including information indicating the position as a "person involved" (for example, positions such as clerical work, sales, driver, etc. in the group that caused event #1) when the output result that user U1 is a "person involved" is obtained, and an instruction sentence that instructs to output attributes according to these rules, thereby estimating the attributes of user U1 with respect to content #1 (in other words, whether user U1 is a "person involved").

[0022] Further, the information processing apparatus 10 inputs a rule that defines whether the user U1 is a "person involved" in Event #1 (for example, a person who used to belong to the organization that caused Event #1 (in other words, a former party) or a person belonging to the industry corresponding to Event #1, etc.) based on the comment information #1 and the content information #1, and an instruction sentence that instructs to output an attribute according to the rule, together with the comment information #1 and the content information #1, into the model #1, thereby estimating the attribute of the user U1 with respect to the content #1 (in other words, whether the user is a "person involved").

[0023] Also, the information processing apparatus 10 inputs a rule that defines whether the user U1 has "knowledge" about Event #1 (for example, a person having knowledge about Event #1) based on the comment information #1 and the content information #1, and an instruction sentence that instructs to output an attribute according to the rule, together with the comment information #1 and the content information #1, into the model #1, thereby estimating the attribute of the user U1 with respect to the content #1 (in other words, whether the user has "knowledge").

[0024] That is, the information processing apparatus 10 estimates whether the user U1 corresponds to any of the attributes such as "party", "person involved", and "having knowledge". Further, when the user U1 corresponds to a "party", the information processing apparatus 10 further estimates the position of the user U1 as a "party".

[0025] Note that the model #1 is a model trained to output a response sentence corresponding to the input question sentence, and is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). The model #1 is within the information processing apparatus 10 and is created independently by the operator who manages the information processing apparatus 10. It is desirable that the input information be learned so as not to be used as a new response, thereby concealing information such as the input personal information.

[0026] Here, in step S2, it is assumed that the information processing apparatus 10 determines that the user U1 corresponds to the "party" of event #1 and estimates the position of the user U1 as the "driver". Also, it is assumed that the information processing apparatus 10 estimates that the user U1 is a "person concerned" of event #1. In such a case, the information processing apparatus 10 presents, to the user U1 via the user terminal 100-1, information indicating "person skilled in the art: driver" and "person concerned" as candidate attributes of the user U1 with respect to content #1 (step S3). For example, the information processing apparatus 10 presents option #1 for the user U1 to select "person skilled in the art: driver" as his / her own attribute, option #2 for the user U1 to select "person concerned" as his / her own attribute, and option #3 for answering that "person skilled in the art: driver" and "person concerned" are not appropriate attributes.

[0027] Subsequently, the information processing apparatus 10 accepts, from the user terminal 100-1, the selection of the attribute of the user U1 with respect to content #1 (step S4). For example, the information processing apparatus 10 accepts a selection of any one of options #1 to #3.

[0028] Here, it is assumed that the selection of option #1 is accepted in step S4. In such a case, the information processing apparatus 10 provides, to the user terminal 100 used by each user via the news application, the comment information #1 together with the attribute information indicating "person skilled in the art: driver" (step S5). For example, the information processing apparatus 10 causes the attribute information indicating "person skilled in the art: driver" and the comment information #1 to be displayed in the comment column in content #1.

[0029] Here, with reference to FIG. 2, the attribute information provided by the information processing apparatus 10 to the user terminal 100 via the news application will be described. FIG. 2 is a diagram showing an example of the screen of the user terminal 100 according to the embodiment.

[0030] In the example shown in FIG. 2, as shown in screen C1, on the user terminal 100, in the comment field of content #1, together with comment #1, the attribute of user U1 for content #1, "person skilled in the art: driver", is displayed directly below the account name of user U1 in the news app.

[0031] Note that, as shown in screen C2, the user terminal 100 superimposes and displays the attribute of user U1 for content #1, "person skilled in the art: driver", on the icon image of user U1 in the news app.

[0032] Returning to FIG. 1 and continuing the explanation. In step S4, when option #3 is selected, the information processing apparatus 10 uses comment information #1, content information #1, "person skilled in the art: driver", and "interested party" as negative example data to train model #1.

[0033] As described above, the information processing apparatus 10 according to the embodiment estimates the attribute of the user for the content based on the comment information indicating the comment posted by the user for the content and the content information regarding the content, and provides the comment in the news app together with the information indicating the estimated attribute. Thereby, the information processing apparatus 10 according to the embodiment can grasp what attributes the user who provided the information has.

[0034] Also, conventionally, for content related to news articles, there are cases where comments with expertise, such as "explanation" and "supplementary note", are posted by authors who add explanations or supplements to the news articles. Here, among the comments posted by general users, there are also comments with expertise posted by parties involved in the events shown in the news articles, and there is a need from users for such comments.

[0035] Therefore, the information processing apparatus 10 according to the embodiment estimates what kind of attributes (specialties) the user who posted the comment has with respect to the content, and provides information indicating the estimated attributes together with the comment. Thereby, the information processing apparatus 10 according to the embodiment can attach a label to a comment with specialty posted by a general user, so that the visibility of comments with high needs from users can be enhanced.

[0036] 〔2. Other processing examples〕 Note that the above-described processing is merely an example, and the information processing apparatus 10 may perform various processes using various information. Regarding this point, the following examples are listed.

[0037] 〔2-1. Regarding the determination of comment reliability〕 In the example of FIG. 1, the information processing apparatus 10 may determine the reliability of the comment indicated by the comment information #1 based on the comment information #1. For example, the information processing apparatus 10 determines that the higher the number of characters of the comment (in other words, the amount of information regarding event #1), the higher the reliability (in other words, it is determined that the user U1 has deeper insights into event #1). Also, the information processing apparatus 10 determines that the higher the degree of coincidence between the comment and the content #1, the higher the reliability. Then, when the reliability of the comment indicated by the comment information #1 is equal to or higher than a predetermined threshold, the information processing apparatus 10 provides the comment information #1 together with the attribute information selected by the user U1 to the user terminal 100 via the news application.

[0038] Note that the information processing apparatus 10 may determine the reliability of the comment indicated by the comment information #1 based on the comment information regarding the comments posted by the user U1 in the past and the comment information #1. For example, the information processing apparatus 10 determines that the higher the number of characters of the comments posted by the user U1 in the past, the higher the reliability. Also, the information processing apparatus 10 determines that the higher the degree of coincidence between the comments posted by the user U1 in the past and the content #1, the higher the reliability.

[0039] 〔3. Configuration of the information processing apparatus〕 Next, the configuration of the information processing apparatus 10 will be described with reference to FIG. 3. FIG. 3 is a diagram showing a configuration example of the information processing apparatus 10 according to the embodiment. As shown in FIG. 3, the information processing apparatus 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

[0040] (Regarding the communication unit 20) The communication unit 20 is realized by, for example, a NIC (Network Interface Card) or the like. Then, 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 or the like.

[0041] (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. 3, the storage unit 30 includes a user information database 31, a content information database 32, and a model database 33.

[0042] (Regarding the user information database 31) The user information database 31 stores various types of information about the user. Here, an example of the information stored in the user information database 31 will be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the user information database 31. In the example of FIG. 4, the user information database 31 has items such as "user ID" and "comment information".

[0043] "User ID" indicates identification information for identifying a user. "Comment information" indicates information regarding comments posted by a user on content, and has items such as "Comment ID", "Content ID", "Comment", etc. "Comment ID" indicates identification information for identifying a comment posted by a user. "Content ID" indicates identification information for identifying the content on which a user posted a comment. "Comment" indicates the content of the comment posted by a user, and for example, text information indicating the comment is stored.

[0044] That is, in FIG. 4, an example is shown where a comment posted by a user identified by user ID "UID#1" is identified by comment ID "CID#1", the content on which the comment was posted is identified by content ID "NID#1", and the content of the comment is "Comment#1".

[0045] (Regarding Content Information Database 32) Content Information Database 32 stores various types of information regarding content. Here, using FIG. 5, an example of the information stored in Content Information Database 32 will be described. FIG. 5 is a diagram showing an example of Content Information Database 32. In the example of FIG. 5, Content Information Database 32 has items such as "Content ID", "Text Information", "Image Information", "Posted Comment", etc.

[0046] "Content ID" indicates identification information for identifying content. "Text Information" indicates text information showing the content of the content. "Image Information" indicates an image included in the content. "Posted Comment" indicates a comment posted by a user on the content, and for example, identification information for identifying the comment is stored.

[0047] That is, in FIG. 5, an example is shown where the text information of the content identified by content ID "NID#1" is "Text Information#1", the image information is "Image Information#1", and the posted comment is "Posted Comment#1".

[0048] (Regarding the model database 33) The model database 33 stores a model that has been trained to generate answers to the input questions.

[0049] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by various programs stored in the storage device inside the information processing apparatus 10 being executed with the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Further, the control unit 40 is 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. 3, the control unit 40 according to the embodiment includes an acquisition unit 41, an estimation unit 42, a presentation unit 43, a learning unit 44, a determination unit 45, and a provision unit 46, and realizes or executes the functions and operations of information processing described below.

[0050] (Regarding the acquisition unit 41) The acquisition unit 41 acquires comment information indicating comments posted by the user for the content. For example, in the example of FIG. 1, the acquisition unit 41 acquires, from the user terminal 100, comment information indicating comments posted by the user for the content provided via the news application, and stores it in the user information database 31.

[0051] (Regarding the estimation unit 42) The estimation unit 42 estimates the attributes of the user with respect to the content by inputting, to the model trained to output an answer to the input question, the comment information, the content information regarding the content, and an instruction sentence instructing to output the attributes of the user with respect to the content based on the comment information and the content information. For example, in the example of FIG. 1, the estimation unit 42 refers to the user information database 3, the content information database 32, and the model database 33, and uses the comment information #1, the content information #1, and the model #1 trained to generate an answer to the input question to estimate the attributes of the user U1 with respect to the content #1.

[0052] Further, the estimation unit 42 may estimate whether the user is a party to the event indicated by the content. For example, in the example of FIG. 1, the estimation unit 42 inputs, to the model #1, together with the comment information #1 and the content information #1, a rule that defines whether to output whether the user U1 is a "party" to the event #1, and an instruction sentence instructing to output the attributes according to the rule, to estimate the attributes of the user U1 with respect to the content #1.

[0053] Further, the estimation unit 42 may estimate the attributes of the user by inputting, to the model, a rule that defines including information indicating the position of the user as a party when the user is a party to the event. For example, in the example of FIG. 1, the estimation unit 42 inputs, to the model #1, together with the comment information #1 and the content information #1, a rule that defines whether to output whether the user U1 is a "party" to the event #1, a rule that defines including information indicating the position as a "party" when the output result that the user U1 is a "party" is obtained, and an instruction sentence instructing to output the attributes according to these rules, to estimate the attributes of the user U1 with respect to the content #1.

[0054] Further, the estimation unit 42 may estimate whether the user has a predetermined relationship with the event indicated by the content. For example, in the example of FIG. 1, the estimation unit 42 inputs a rule that defines outputting whether the user U1 is a "person involved" in event #1 based on the comment information #1 and the content information #1, and an instruction sentence that instructs to output an attribute according to the rule, together with the comment information #1 and the content information #1 into the model #1, to estimate the attribute of the user U1 with respect to the content #1.

[0055] Further, the estimation unit 42 may estimate whether the user has knowledge about the event indicated by the content. For example, in the example of FIG. 1, the estimation unit 42 inputs a rule that defines outputting whether the user U1 has "knowledge" about event #1 based on the comment information #1 and the content information #1, and an instruction sentence that instructs to output an attribute according to the rule, together with the comment information #1 and the content information #1 into the model #1, to estimate the attribute of the user U1 with respect to the content #1.

[0056] (Regarding the presentation unit 43) The presentation unit 43 presents the attribute estimated by the estimation unit 42 to the user as a candidate for the attribute of the user with respect to the content. For example, in the example of FIG. 1, the presentation unit 43 presents information indicating "person skilled in the art: driver" and "person involved" to the user U1 via the user terminal 100-1 as candidates for the attribute of the user U1 with respect to the content #1.

[0057] Further, the presentation unit 43 may present, together with the attribute candidates, an option indicating that the attribute candidates are not appropriate. For example, in the example of FIG. 1, the presentation unit 43 presents option #1 for the user U1 to select "person skilled in the art: driver" as his / her own attribute, option #2 for the user U1 to select "person involved" as his / her own attribute, and option #3 for the user U1 to answer that "person skilled in the art: driver" and "person involved" are not appropriate attributes.

[0058] (Regarding the learning unit 44) The learning unit 44 performs model learning according to the selection of options. For example, in the example of FIG. 1, when option #3 is selected, the learning unit 44 uses comment information #1, content information #1, "person skilled in the art: driver" and "interested party" as negative example data to perform learning of model #1.

[0059] (Regarding the determination unit 45) The determination unit 45 determines the reliability of the comment based on the comment information. For example, in the example of FIG. 1, the determination unit 45 determines that the higher the number of characters in the comment, the higher the reliability. Also, the determination unit 45 determines that the higher the degree of match between the comment and content #1, the higher the reliability.

[0060] Further, the determination unit 45 may determine the reliability of the comment based on information regarding comments previously posted by the user and the comment information. For example, in the example of FIG. 1, the determination unit 45 determines that the higher the number of characters in the comments previously posted by user U1, the higher the reliability. Also, the determination unit 45 determines that the higher the degree of match between the comments previously posted by user U1 and content #1, the higher the reliability.

[0061] (Regarding the provision unit 46) The provision unit 46 provides the comment information together with the attribute information indicating the attribute estimated by the estimation unit 42. For example, in the example of FIG. 1, the provision unit 46 refers to the user information database 31 and the content information database 32, and provides comment information #1 together with the attribute information indicating "person skilled in the art: driver" to the user terminal 100 via the news application.

[0062] Also, the provision unit 46 may provide the comment information together with the attribute information when the reliability is equal to or higher than a predetermined threshold. For example, in the example of FIG. 1, when the reliability of the comment indicated by comment information #1 is equal to or higher than a predetermined threshold, the provision unit 46 provides comment information #1 together with the attribute information of user U1 to the user terminal 100 via the news application.

[0063] Further, the providing unit 46 may provide comment information together with attribute information indicating an attribute selected by the user among the attribute candidates. For example, in the example of FIG. 1, the providing unit 46 provides the comment information #1 to the user terminal 100 via the news application together with the attribute information selected by the user U1.

[0064] [4. Information Processing Flow] The information processing procedure of the information processing apparatus 10 according to the embodiment will be described with reference to FIG. 6. FIG. 6 is a flowchart showing an example of the information processing procedure according to the embodiment.

[0065] As shown in FIG. 6, the information processing apparatus 10 determines whether or not it has acquired comment information indicating a comment posted by the user on the content (step S101). If it has not acquired the comment information (step S101; No), the information processing apparatus 10 waits until the comment information is acquired.

[0066] On the other hand, if the comment information has been acquired (step S101; Yes), the information processing apparatus 10 inputs the comment information, the content information regarding the content, and an instruction sentence for instructing to output the user's attribute for the content based on the comment information and the content information to a model learned to output an answer to the input question, thereby estimating the user's attribute for the content (step S102). Subsequently, the information processing apparatus 10 provides the comment information together with the attribute information indicating the attribute (step S103), and ends the process.

[0067] [5. Modification Examples] The above-described embodiment is merely an example, and various changes and applications are possible.

[0068] [5-1. Regarding the Processing Mode] Among the respective processes described in the above-described embodiments, all or part of the processes described as being automatically performed can also be manually performed, and conversely, all or part of the processes described as being manually performed can also be automatically performed by known methods. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above text and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0069] In addition, each component of each illustrated device is a functional concept and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of the distribution and integration of each device is not limited to that shown in the figure, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc.

[0070] In addition, the above-described embodiments can be appropriately combined within a range that does not conflict with the processing content.

[0071] 〔6. Effects〕 As described above, the information processing apparatus 10 according to the embodiment includes an acquisition unit 41, an estimation unit 42, a presentation unit 43, a learning unit 44, a determination unit 45, and a provision unit 46. The acquisition unit 41 acquires comment information indicating comments posted by a user with respect to content. The estimation unit 42 inputs, to a model learned to output an answer to an input question, the comment information, content information regarding the content, and an instruction sentence instructing to output, based on the comment information and the content information, the attributes of the user with respect to the content, and estimates the attributes of the user with respect to the content. The presentation unit 43 presents the attributes estimated by the estimation unit 42 to the user as candidates for the attributes of the user with respect to the content. Further, the presentation unit 43 presents, together with the attribute candidates, options indicating that the attribute candidates are not appropriate. The learning unit 44 performs learning of the model according to the selection of the options. The determination unit 45 determines the reliability of a comment based on the comment information. Further, the determination unit 45 determines the reliability of a comment based on information regarding comments posted by the user in the past and the comment information. The provision unit 46 provides the comment information together with attribute information indicating the attributes estimated by the estimation unit 42. Further, the provision unit 46 provides the comment information together with the attribute information when the reliability is equal to or higher than a predetermined threshold. Further, the provision unit 46 provides the comment information together with attribute information indicating the attributes selected by the user among the attribute candidates.

[0072] Accordingly, the information processing apparatus 10 according to the embodiment can estimate the attributes of the user with respect to the content based on the comment information indicating the comments posted by the user with respect to the content and the content information regarding the content, and provide the comment in the news application together with the information indicating the estimated attributes, so that it is possible to grasp what attributes the user who provided the information has.

[0073] Also, in the information processing apparatus 10 according to the embodiment, for example, the estimation unit 42 estimates whether the user is a party to the event indicated by the content. Further, the estimation unit 42 inputs, to the model, a rule that further specifies including information indicating the user's position as a party when the user is a party to the event, thereby estimating the user's attributes. Also, the estimation unit 42 estimates whether the user has a predetermined relationship with the event indicated by the content. Also, the estimation unit 42 estimates whether the user has knowledge of the event indicated by the content.

[0074] Thereby, the information processing apparatus 10 according to the embodiment can estimate what attributes the user has with respect to the content, and thus can grasp in detail what attributes the user who provided the information has.

[0075] 〔7. Hardware Configuration〕 Also, the information processing apparatus 10 according to each of the above-described embodiments is realized by, for example, a computer 1000 having a configuration as shown in FIG. 7. Hereinafter, the information processing apparatus 10 will be described as an example. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 10. The computer 1000 includes 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.

[0076] The CPU 1100 operates based on a program stored in the ROM 1200 or the HDD 1400 and controls each part. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

[0077] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N in the embodiment) and sends it to the CPU 1100, and also sends data generated by the CPU 1100 via the communication network 500 to other devices.

[0078] 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 the input devices via the input / output interface 1600. Further, the CPU 1100 outputs data generated via the input / output interface 1600 to the output devices.

[0079] 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 1300. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1300 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory or the like.

[0080] For example, when the computer 1000 functions as the information processing apparatus 10, the CPU 1100 of the computer 1000 realizes the functions of the control unit 40 by executing the program loaded on the RAM 1300. Further, each data in the storage device of the information processing apparatus 10 is stored in the HDD 1400. 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 acquired from other devices via a predetermined communication network.

[0081] [8. Others] As described above, some embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0082] In addition, the above-described information processing apparatus 10 can have its configuration flexibly changed, such as by calling an external platform or the like through an API (Application Programming Interface) or network computing depending on its functions.

[0083] Also, the "part" described in the claims can be read as "means", "circuit", etc. For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

Explanation of Reference Numerals

[0084] 10 Information processing apparatus 20 Communication unit 30 Storage unit 31 User information database 32 Content information database 33 Model database 40 Control unit 41 Acquisition unit 42 Estimation unit 43 Presentation unit 44 Learning unit 45 Judgment unit 46 Provision unit 100 User terminal

Claims

1. An acquisition unit that acquires comment information indicating comments posted by a user for content; For a model trained to output an answer to an input question, the comment information, content information regarding the content, and an instruction sentence for instructing to output the attributes of the user for the content based on the comment information and the content information are input, and an estimation unit that estimates the attributes of the user for the content; A providing unit that provides the comment information together with attribute information indicating the attributes estimated by the estimation unit An information processing apparatus characterized by comprising:

2. The estimation unit Estimates whether the user is a party to the event indicated by the content The information processing apparatus according to claim 1, characterized in that:

3. The estimation unit Estimates the attributes of the user by inputting a rule for further including information indicating the position of the user as a party when the user is a party to the event to the model The information processing apparatus according to claim 2, characterized in that:

4. The estimation unit Estimates whether the user has a predetermined relationship with the event indicated by the content The information processing apparatus according to claim 1, characterized in that:

5. The estimation unit Estimates whether the user has knowledge of the event indicated by the content The information processing apparatus according to claim 1, characterized in that:

6. A determination unit that determines the reliability of the comment based on the comment information Further comprising: The providing unit Provides the comment information together with the attribute information when the reliability is equal to or greater than a predetermined threshold The information processing apparatus according to claim 1, characterized in that:

7. The determination unit Determines the reliability of the comment based on information regarding comments previously posted by the user and the comment information The information processing apparatus according to claim 6, characterized in that:

8. A presentation unit that presents the attributes estimated by the estimation unit to the user as candidates for the attributes of the user for the content Further comprising: The providing unit Provides the comment information together with attribute information indicating the attributes selected by the user among the candidates for the attributes The information processing apparatus according to claim 1, characterized in that:

9. Present an option indicating that the candidate for the attribute is inappropriate, together with the candidate for the attribute. A learning unit that performs learning of the model according to the selection of the option The information processing apparatus according to claim 8, further comprising the learning unit.

10. An information processing method executed by a computer, comprising: An acquisition step of acquiring comment information indicating a comment posted by a user on content; An estimation step of estimating an attribute of the user with respect to the content by inputting the comment information, content information regarding the content, and an instruction sentence for instructing to output the attribute of the user with respect to the content based on the comment information and the content information to a model learned to output an answer to an input question; A provision step of providing the comment information together with attribute information indicating the attribute estimated in the estimation step The information processing method characterized by including the above steps.

11. An acquisition procedure for acquiring comment information indicating a comment posted by a user on content; An estimation procedure for estimating an attribute of the user with respect to the content by inputting the comment information, content information regarding the content, and an instruction sentence for instructing to output the attribute of the user with respect to the content based on the comment information and the content information to a model learned to output an answer to an input question; A provision procedure for providing the comment information together with attribute information indicating the attribute estimated in the estimation procedure An information processing program for causing a computer to execute the above procedures.

Images