Information processing device, 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, technologies related to information distribution via the Internet are known. As an example of such a technology, there is known a technology that receives submissions of articles from a plurality of users via a network, edits the articles in the form of an electronic newspaper, and publishes 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 technology, it cannot be said that it is possible to grasp what attributes the users who provided the information have.

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

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

Means for Solving the Problems

[0007] The information processing device according to the present invention is characterized by comprising: an acquisition unit that acquires comment information indicating comments posted by a user on content; an estimation unit that estimates the user's attributes on content by inputting the comment information, content information relating to the content, and an instruction sentence that instructs a model trained to output answers to input questions to output the user's attributes on the content based on the comment information and the content information; and a provision unit that provides the comment information along with attribute information indicating the attributes estimated by the estimation unit. [Effects of the Invention]

[0008] According to one embodiment of the system, it has the effect of being able to understand what attributes the user who provided the information possesses. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the screen of the user terminal 100 according to this embodiment. [Figure 3] Figure 3 shows an example of the configuration of the information processing device 10 according to the embodiment. [Figure 4] Figure 4 shows an example of a user information database 31. [Figure 5] Figure 5 shows an example of a content information database 32. [Figure 6] Figure 6 is a flowchart showing an example of the information processing procedure according to the embodiment. [Figure 7] Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10. [Modes for carrying out the invention]

[0010] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0011] [1. Embodiments] The information processing realized by the information processing device of this embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. In Figure 1, the information processing according to the embodiment is realized by the information processing device 10, which is an example of the information processing device according to the present application.

[0012] As shown in Figure 1, the information processing system 1 according to this embodiment includes an information processing device 10 and a user terminal 100. The information processing device 10 and the user terminal 100 are connected to each other via a network N (see, for example, Figure 3) by wire or wireless means so that they can communicate with each other. The network N is, for example, a WAN (Wide Area Network) such as the Internet. Note that the information processing system 1 shown in Figure 1 may include multiple information processing devices 10 and multiple user terminals 100.

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

[0014] The information processing device 10 may also function as a web server providing a website related to the news service. Furthermore, the information processing device 10 may be a device that distributes information to the user terminal 100 for display on an application related to the news service (hereinafter sometimes referred to as "news app") installed on the user terminal 100. The information processing device 10 may also be a server that distributes the news app data itself. Additionally, the information processing device 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is described, for example, using a scripting language such as JavaScript (registered trademark) or a stylesheet language such as CSS (Cascading Style Sheets). The news app itself distributed from the information processing device 10 may also be considered as control information.

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

[0016] Furthermore, the user terminal 100 displays the information provided by the information processing device 10 using a web browser or application. When the user terminal 100 receives control information from the information processing device 10 or the like to implement the information display process, it implements the display process 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, for the sake of explanation, 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 the 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 app is installed on the user terminal 100.

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

[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 to estimate 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 "party" (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 "party" (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 "party" is obtained, and an instruction sentence that instructs to output attributes according to these rules, to estimate the attributes of user U1 with respect to content #1 (in other words, whether user U1 is a "party").

[0022] Furthermore, the information processing device 10 inputs a rule that specifies whether user U1 is a "stakeholder" of event #1 (for example, someone who previously belonged to the organization that caused event #1 (in other words, a former party) or someone who belongs to the industry corresponding to event #1)) and an instruction sentence that instructs the model #1 to output attributes according to the said rule, along with comment information #1 and content information #1, thereby estimating user U1's attributes with respect to content #1 (in other words, whether or not they are a "stakeholder").

[0023] Furthermore, the information processing device 10 inputs a rule that specifies whether user U1 has "knowledge" about event #1 (for example, whether they have knowledge about event #1) based on comment information #1 and content information #1, along with an instruction sentence that instructs the model #1 to output attributes according to the rule, thereby estimating user U1's attributes with respect to content #1 (in other words, whether or not they "have knowledge" about it).

[0024] In other words, the information processing device 10 estimates whether user U1 has any attributes such as "party," "related party," and "has knowledge." Furthermore, if user U1 is a "party," the information processing device 10 estimates user U1's position as a "party."

[0025] Model #1 is a model trained to output a response corresponding to an input question, and is a natural language processing language model such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Model #1 resides within the information processing device 10 and was created independently by the business operator managing the information processing device 10. It is desirable that the input information be kept confidential by training the model so that it is not used as a new answer, thereby protecting personal information and other sensitive data.

[0026] Here, in step S2, the information processing device 10 assumes that user U1 is a "party" to event #1 and that user U1's position is that of a "driver". It also assumes that the information processing device 10 assumes that user U1 is a "person involved" in event #1. In such a case, the information processing device 10 presents user U1 with information indicating "Person skilled in the art: Driver" and "Person involved" as candidate attributes for user U1 in relation to content #1 via user terminal 100-1 (step S3). For example, the information processing device 10 presents option #1 for user U1 to select "Person skilled in the art: Driver" as their attribute, option #2 for user U1 to select "Person involved" as their attribute, and option #3 for user U1 to respond that neither "Person skilled in the art: Driver" nor "Person involved" is an appropriate attribute.

[0027] Next, the information processing device 10 receives a selection of user U1's attributes for content #1 from the user terminal 100-1 (step S4). For example, the information processing device 10 accepts a selection from one of options #1 to #3.

[0028] Here, in step S4, we assume that the selection of option #1 has been accepted. In this case, the information processing device 10 provides comment information #1, along with attribute information indicating "Person skilled in the art: Driver," to the user terminal 100 used by each user via the news app (step S5). For example, the information processing device 10 displays comment information #1, along with attribute information indicating "Person skilled in the art: Driver," in the comment section of content #1.

[0029] Here, using Figure 2, we will explain the attribute information that the information processing device 10 provides to the user terminal 100 via the news application. Figure 2 is a diagram showing an example of the screen of the user terminal 100 according to this embodiment.

[0030] In the example shown in Figure 2, as shown on screen C1, the user terminal 100 displays the user U1 attribute "A person skilled in the art: Driver" for content #1 in the comment section of content #1, along with comment #1, directly below the account name of user U1 in the news app.

[0031] Furthermore, as shown in screen C2, the user terminal 100 displays the attribute of user U1 for content #1, "Person skilled in the art: Driver," superimposed on the icon image of user U1 in the news app.

[0032] Returning to Figure 1, let's continue the explanation. If option #3 is selected in step S4, the information processing device 10 uses comment information #1, content information #1, and "A person skilled in the art: driver" and "Parties involved" as negative example data to train model #1.

[0033] As described above, the information processing device 10 according to the embodiment estimates the user's attributes to the content based on comment information indicating comments posted by the user to the content and content information related to the content, and provides the comment along with information indicating the estimated attributes in the news app. This allows the information processing device 10 according to the embodiment to understand what attributes the user who provided the information has.

[0034] Furthermore, in the past, content related to news articles sometimes includes expert comments labeled as "explanation" or "supplement" by authors who add commentary or supplementary information to the news articles. However, among the comments posted by general users, there are also expert comments posted by those directly involved in the events described in the news articles, and there is a user demand for such comments.

[0035] Therefore, the information processing device 10 according to the embodiment estimates what attributes (expertise) the user who posted the comment has with respect to the content, and provides information indicating the estimated attributes along with the comment. As a result, the information processing device 10 according to the embodiment can assign labels to expert comments posted by general users, thereby improving the visibility of comments that are of high interest to users.

[0036] [2. Other processing examples] The process described above is merely one example, and the information processing device 10 may perform various processes using various types of information. Examples of this are listed below.

[0037] [2-1. Regarding the determination of the reliability of comments] In the example shown in Figure 1, the information processing device 10 may determine the reliability of the comment indicated by comment information #1 based on the comment information #1. For example, the more characters in the comment (in other words, the more information about event #1) the greater the reliability (in other words, the deeper the user U1's knowledge of event #1). Also, the more the comment matches content #1, the greater the reliability. If the reliability of the comment indicated by comment information #1 is above a predetermined threshold, the information processing device 10 provides comment information #1, along with the attribute information selected by user U1, to the user terminal 100 via the news application.

[0038] The information processing device 10 may also determine the reliability of the comment indicated by comment information #1 based on comment information related to comments previously posted by user U1 and comment information #1. For example, the information processing device 10 will determine a higher reliability the longer the number of characters in the comments previously posted by user U1. Also, the information processing device 10 will determine a higher reliability the higher the degree of agreement between the comments previously posted by user U1 and content #1.

[0039] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device 10 will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. As shown in Figure 3, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0040] (Regarding Communications Section 20) The communication unit 20 is implemented, for example, by a NIC (Network Interface Card). The communication unit 20 is connected to the network N by wire or wireless connection and transmits and receives information with the user terminal 100, etc.

[0041] (Regarding memory unit 30) The storage unit 30 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. As shown in Figure 3, the storage unit 30 has a user information database 31, a content information database 32, and a model database 33.

[0042] (Regarding User Information Database 31) The user information database 31 stores various types of information about users. Here, an example of the information stored in the user information database 31 is explained using Figure 4. Figure 4 is a diagram showing an example of the user information database 31. In the example in Figure 4, the user information database 31 has items such as "User ID" and "Comment Information".

[0043] "User ID" indicates identification information used to identify a user. "Comment Information" indicates information about comments posted by a user on content and includes items such as "Comment ID," "Content ID," and "Comment." "Comment ID" indicates identification information used to identify a comment posted by a user. "Content ID" indicates identification information used to identify the content on which a comment was posted by a user. "Comment" indicates the content of the comment posted by the user, and for example, text information representing the comment is stored there.

[0044] In other words, Figure 4 shows an example 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) The content information database 32 stores various types of information related to the content. Here, an example of the information stored in the content information database 32 will be explained using Figure 5. Figure 5 is a diagram showing an example of the content information database 32. In the example in Figure 5, the content information database 32 has items such as "Content ID," "Text Information," "Image Information," and "Posted Comments."

[0046] "Content ID" indicates identification information used to identify the content. "Text Information" indicates text information describing the content. "Image Information" indicates images included in the content. "Posted Comments" indicates comments posted by users about the content, and for example, identification information for identifying the comments is stored.

[0047] In other words, Figure 5 shows an example where the text information of the content identified by the 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 Model Database 33) The model database 33 stores models that have been trained to generate answers to input questions.

[0049] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the memory device inside the information processing device 10 using RAM as a working area. Alternatively, 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 FPGA (Field Programmable Gate Array). As shown in Figure 3, the control unit 40 according to this embodiment has 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 information processing functions and operations described below.

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

[0051] (Regarding the estimation section 42) The estimation unit 42 estimates the user's attributes for content by inputting comment information, content information about the content, and instruction sentences that instruct a model trained to output answers to input questions to output user attributes for the content based on the comment information and said content information. For example, in the example in Figure 1, the estimation unit 42 refers to the user information database 3, the content information database 32 and the model database 33, and estimates the user U1's attributes for content #1 using comment information #1, content information #1 and model #1 which has been trained to generate answers to input questions.

[0052] Furthermore, the estimation unit 42 may estimate whether or not the user is a party to the event indicated by the content. For example, in the example in Figure 1, the estimation unit 42 estimates the user U1's attributes to content #1 by inputting a rule that specifies whether or not user U1 is a "party" to event #1, and an instruction sentence that instructs the model to output attributes according to the rule, along with comment information #1 and content information #1.

[0053] Furthermore, the estimation unit 42 may estimate the user's attributes by inputting a rule to the model that specifies that if the user is a party to the event, information indicating the user's position as a party should be included. For example, in the example in Figure 1, the estimation unit 42 estimates the user's attributes for content #1 by inputting a rule that specifies whether or not user U1 is a "party" to event #1, a rule that specifies that if the output result is that user U1 is a "party", information indicating the user's position as a "party" should be included, and an instruction sentence that instructs the model to output attributes according to these rules, along with comment information #1 and content information #1.

[0054] Furthermore, the estimation unit 42 may estimate whether the user has a predetermined relationship with the event represented by the content. For example, in the example in Figure 1, the estimation unit 42 estimates the user U1's attributes to content #1 by inputting a rule that specifies whether user U1 is a "person involved" in event #1 based on comment information #1 and content information #1, and an instruction sentence that instructs the model to output attributes according to the rule, along with comment information #1 and content information #1.

[0055] Furthermore, the estimation unit 42 may estimate whether the user has knowledge of the events represented by the content. For example, in the example in Figure 1, the estimation unit 42 estimates the user U1's attributes to content #1 by inputting a rule that specifies whether user U1 has "knowledge" of event #1 based on comment information #1 and content information #1, and an instruction sentence that instructs the model to output attributes according to the rule, along with comment information #1 and content information #1.

[0056] (Regarding the presentation section 43) The presentation unit 43 presents the attributes estimated by the estimation unit 42 to the user as candidate attributes of the user for the content. For example, in the example in Figure 1, the presentation unit 43 presents information indicating "Person skilled in the art: Driver" and "Related party" to user U1 via user terminal 100-1 as candidate attributes of user U1 for content #1.

[0057] Furthermore, the presentation unit 43 may present options indicating that the attribute candidates are inappropriate, along with the attribute candidates. For example, in the example in Figure 1, the presentation unit 43 presents user U1 with option #1 for user U1 to select "Person skilled in the art: Driver" as their attribute, option #2 for user U1 to select "Party Member" as their attribute, and option #3 for user U1 to indicate that "Person skilled in the art: Driver" and "Party Member" are not appropriate attributes.

[0058] (Regarding Learning Section 44) The learning unit 44 trains the model according to the selection of an option. For example, in the example in Figure 1, if option #3 is selected, the learning unit 44 trains model #1 using comment information #1, content information #1, and "persons skilled in the art: drivers" and "persons involved" as negative example data.

[0059] (Regarding the determination unit 45) The determination unit 45 determines the reliability of a comment based on the comment information. For example, in the example in Figure 1, the determination unit 45 determines that the more characters a comment has, the higher its reliability. Also, the determination unit 45 determines that the more the comment matches content #1, the higher its reliability.

[0060] Furthermore, the determination unit 45 may determine the reliability of a comment based on information about comments previously posted by the user and the comment information. For example, in the example in Figure 1, the determination unit 45 determines that the more characters a comment previously posted by user U1 has, the higher the reliability. Also, the determination unit 45 determines that the more similar a comment previously posted by user U1 is to content #1, the higher the reliability.

[0061] (Regarding Section 46) The provisioning unit 46 provides comment information along with attribute information indicating the attribute estimated by the estimation unit 42. For example, in the example in Figure 1, the provisioning unit 46 refers to the user information database 31 and the content information database 32 and provides comment information #1 along with attribute information indicating "Person skilled in the art: Driver" to the user terminal 100 via the news application.

[0062] Furthermore, the provisioning unit 46 may provide comment information along with attribute information if the reliability is above a predetermined threshold. For example, in the example in Figure 1, the provisioning unit 46 provides comment information #1 along with user U1's attribute information to the user terminal 100 via the news application if the reliability of the comment indicated by comment information #1 is above a predetermined threshold.

[0063] Furthermore, the provisioning unit 46 may provide comment information along with attribute information indicating the attribute selected by the user from among the candidate attributes. For example, in the example in Figure 1, the provisioning unit 46 provides comment information #1 along with the attribute information selected by user U1 to the user terminal 100 via the news application.

[0064] [4. Information Processing Flow] The information processing procedure of the information processing device 10 according to the embodiment will be explained using Figure 6. Figure 6 is a flowchart of an example of the information processing procedure according to the embodiment.

[0065] As shown in Figure 6, the information processing device 10 determines whether or not it has obtained comment information indicating comments posted by users on the content (step S101). If it has not obtained comment information (step S101; No), the information processing device 10 waits until it obtains comment information.

[0066] On the other hand, if comment information is obtained (step S101; Yes), the information processing device 10 estimates the user's attributes for the content by inputting the comment information, content information about the content, and an instruction sentence instructing the model, which has been trained to output an answer to the input question, to output the user's attributes for the content based on the comment information and the content information (step S102). Subsequently, the information processing device 10 provides the comment information along with attribute information indicating the attributes (step S103), and terminates the process.

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

[0068] [5-1. Regarding the processing method] 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 by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above text and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0069] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0070] Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

[0071] [6. Effects] As described above, the information processing device 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 users on content. The estimation unit 42 estimates the user's attributes on content by inputting comment information, content information about the content, and an instruction sentence instructing a model trained to output answers to input questions to output the user's attributes on content based on the comment information and the content information. The presentation unit 43 presents the attributes estimated by the estimation unit 42 to the user as candidates for the user's attributes on content. The presentation unit 43 also presents options indicating that the attribute candidates are inappropriate. The learning unit 44 trains the model according to the selection of the options. The determination unit 45 determines the reliability of the comment based on the comment information. The determination unit 45 also determines the reliability of the comment based on information about comments previously posted by the user and the comment information. The provisioning unit 46 provides comment information along with attribute information indicating the attribute estimated by the estimation unit 42. The provisioning unit 46 also provides comment information along with attribute information if the reliability is above a predetermined threshold. The provisioning unit 46 also provides comment information along with attribute information indicating the attribute selected by the user from among the attribute candidates.

[0072] As a result, the information processing device 10 according to the embodiment can estimate the user's attributes to the content based on comment information indicating comments posted by the user to the content and content information related to the content, and provide the comment along with information indicating the estimated attributes in the news app, thereby making it possible to understand what kind of attributes the user who provided the information has.

[0073] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether the user is a party to the event shown by the content. The estimation unit 42 also estimates the user's attributes by inputting a rule to the model that specifies that if the user is a party to the event, information indicating the user's position as a party should be included. The estimation unit 42 also estimates whether the user has a predetermined relationship with the event shown by the content. The estimation unit 42 also estimates whether the user has knowledge about the event shown by the content.

[0074] As a result, the information processing device 10 according to this embodiment can estimate what attributes a user has to the content, and can therefore understand in detail what attributes the user who provided the information has.

[0075] [7. Hardware Configuration] Furthermore, the information processing device 10 according to each embodiment described above can be implemented by a computer 1000 having a configuration such as that shown in Figure 7. The following explanation will use the information processing device 10 as an example. Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10. The computer 1000 has a CPU 1100, ROM 1200, RAM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0076] The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400, and controls various parts. The ROM 1200 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

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

[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 input devices via the input / output interface 1600. The CPU 1100 also outputs the data it generates to output devices via the input / output interface 1600.

[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 the 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) or 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.

[0080] For example, when computer 1000 functions as information processing device 10, the CPU 1100 of computer 1000 realizes the functions of control unit 40 by executing programs loaded on RAM 1300. The HDD 1400 stores the data in the storage device of information processing device 10. The CPU 1100 of computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0081] [8. Other] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0082] Furthermore, the configuration of the aforementioned information processing device 10 can be flexibly changed, for example, by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, depending on the function.

[0083] Furthermore, the term "part" in the claims can be replaced with "means," "circuit," etc. For example, "acquisition part" can be replaced with "acquisition means" or "acquisition circuit." [Explanation of Symbols]

[0084] 10 Information Processing Devices 20 Communications Department 30 Storage section 31. User Information Database 32 Content Information Database 33 Model Databases 40 Control Unit 41 Acquisition Department 42 Estimation part 43 Presentation part 44. Learning Department 45 Judgment section 46 Providing Department 100 User Terminals

Claims

1. A unit that retrieves comment information indicating comments posted by users on content, An estimation unit estimates the user's attributes for a content by inputting the comment information, content information about the content, and an instruction sentence that instructs the model, which has been trained to output answers to input questions, to output the user's attributes for the content based on the comment information and the content information. A providing unit that provides attribute information indicating the attribute estimated by the estimation unit, along with the comment information. An information processing device characterized by having the following features.

2. The estimation unit, As an attribute of the user, it is estimated whether or not the user is a party to the events shown in the content. The information processing apparatus according to feature 1.

3. The estimation unit, By inputting a rule to the aforementioned model that further specifies that if the user is a party to the event, information indicating the user's position as a party should be output as an attribute of the user, the user's position as a party can be estimated as an attribute of the user. The information processing apparatus according to feature 2.

4. The estimation unit, As an attribute of the user, it is estimated whether the user has a predetermined relationship with the events shown in the content. The information processing apparatus according to feature 1.

5. The estimation unit, As an attribute of the user, it is estimated whether or not the user has knowledge of the events shown in the content. The information processing apparatus according to feature 1.

6. A determination unit determines the reliability of the comment based on the comment information. It further possesses, The aforementioned supply unit is, If the reliability is above a predetermined threshold, the comment information is provided along with the attribute information. The information processing apparatus according to feature 1.

7. The determination unit, Based on information about comments previously posted by the user and the comment information, the reliability of the comment is determined. The information processing apparatus according to feature 6.

8. Presentation unit presents the attributes estimated by the estimation unit to the user as candidate attributes of the user for the content. It further possesses, The aforementioned supply unit is, The comment information is provided along with attribute information indicating the attribute selected by the user from among the candidate attributes. The information processing apparatus according to feature 1.

9. Along with the candidate attribute, an option is presented indicating that the candidate attribute is inappropriate. The learning unit performs the model training according to the selection of the above options. The information processing apparatus according to claim 8, further comprising

10. A method of information processing performed by a computer, The process involves obtaining comment information that shows comments posted by users on the content, An estimation step in which the user's attributes to the content are estimated by inputting the comment information, content information about the content, and instruction text that instructs the model, which has been trained to output answers to input questions, to output the user's attributes to the content based on the comment information and the content information, A provision step provides attribute information indicating the attributes estimated by the estimation step, along with the comment information. An information processing method characterized by including

11. Procedure for obtaining comment information that shows comments posted by users on content, An estimation procedure for estimating the user's attributes for a content by inputting the comment information, content information about the content, and an instruction sentence instructing the model, which has been trained to output answers to input questions, to output the user's attributes for the content based on the comment information and the content information; A provision procedure for providing comment information along with attribute information indicating the attribute estimated by the estimation procedure described above. An information processing program that causes a computer to execute something.

Images