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

Abstract

To present a suitable choice about a content evaluation to users and to evaluate the content.SOLUTION: An information processing device according to the present application has: an acquisition part to acquire the content information representing the substance of the content and comment information representing the comment posted by users on the content; a generating part; and an output part to output the choice generated by the generating part in a user-selectable format via the content. The generating part generates the choice to evaluate the content by inputting the content information, the comment information, and the instruction sentence which instructs to output the choice for evaluating the content and corresponding to the emotion of the user who viewed the content based on the content information and the comment information, for the model learned so as to output the answer to the input question.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] 2. Description of the Related Art Conventionally, there are known techniques related to information distribution via the Internet. One example of such techniques is a technique for rating news articles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-081394 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques cannot be said to be capable of presenting a user with appropriate options for rating content and allowing the user to rate the content.

[0005] For example, the above-mentioned technology merely calculates an evaluation value for a news article by adding up pre-set individual scores for each target word extracted from the news article, and it cannot be said that it is capable of presenting appropriate options for evaluating content to a user and enabling the user to evaluate the content.

[0006] The present application has been made in consideration of the above, and has an object to present a user with appropriate options for rating content and to enable the user to rate the content. [Means for solving the problem]

[0007] The information processing device of the present application is characterized by having an acquisition unit that acquires content information indicating the details of content and comment information indicating comments posted by users on the content, a generation unit that generates options for evaluating the content by inputting the content information, the comment information, and an instruction sentence that instructs a model trained to output answers to input questions to output options for evaluating the content, the options corresponding to the emotions of a user who viewed the content, based on the content information and the comment information, and an output unit that outputs the options generated by the generation unit in a manner selectable by the user via the content. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to provide a user with appropriate options for rating content, thereby enabling the user to rate the content. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of the provider information database 31. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing an example of the content database 32. As shown in FIG. [Diagram 5] FIG. 5 is a flowchart illustrating an example of a procedure of 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. As shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application 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 the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0011] 1. Embodiment Information processing implemented by the information processing device of the present embodiment will be described with reference to Fig. 1. 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 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 provider terminal 200. The information processing device 10, the user terminal 100, and the provider terminal 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 by wire or wirelessly. 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 provider terminals 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, for example, an information processing device that provides a news service that provides content related to news articles to a user.

[0014] The information processing device 10 may have a function as a web server that provides a website related to a news service. The information processing device 10 may also be a device that distributes information to be displayed on an application (hereinafter, may be referred to as a "news app") related to a news service installed in the user terminal 100 to the user terminal 100. The information processing device 10 may also be a server that distributes the data of the news app 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 described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). The news app itself distributed from the information processing device 10 may be regarded 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 implementing information display processing from the information processing device 10 or the like, the user terminal 100 implements the display processing in accordance with the control information.

[0017] The provider terminal 200 shown in FIG. 1 is an information processing device used by providers of content provided in a news service (for example, journalists in various mass media such as newspapers, publishers, and broadcasting stations (television stations, radio stations)). The provider terminal 200 is realized, for example, by a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In the example shown in FIG. 1, the provider terminal 200 is a notebook PC used by the provider.

[0018] The information processing performed by the information processing device 10 will be described below with reference to FIG. 1. In the following description, the user terminal 100 will be referred to as user terminals 100-1 to 100-N (N is any natural number) according to the user who uses the user terminal 100. For example, the user terminal 100-1 is the user terminal 100 used by a user (user U1) identified by a user ID "UID#1". In the following description, the user terminals 100-1 to 100-N will be referred to as user terminal 100 when there is no particular distinction between them. In the following description, the user terminal 100 may be regarded as the same as the user. That is, in the following description, the user may be read as the user terminal 100.

[0019] In the following description, it is assumed that a news application is installed on the user terminal 100.

[0020] In the following description, the provider terminal 200 is assumed to be used by a provider P1. In the following description, the provider terminal 200 may be regarded as the same as the provider P1. In other words, in the following description, the provider P1 may also be read as the provider terminal 200.

[0021] First, the information processing device 10 acquires content information indicating the details of content provided in the news application from the provider terminal 200 (step S1). For example, the information processing device 10 acquires information such as text information indicating the details of a news article and an image related to the news article as content information #1 related to the content #1 provided to the information processing device 10 by the provider P1.

[0022] Next, the information processing device 10 provides the content #1 to the user terminal 100 (step S2). For example, the information processing device 10 provides the content #1 via a news application.

[0023] Next, the information processing device 10 acquires comment information #1 indicating each comment posted by a user on the content #1 from the user terminal 100 (step S3). For example, the information processing device 10 acquires text information indicating the content of each comment posted on the content #1 as the comment information #1.

[0024] Next, the information processing device 10 generates options for the user to evaluate the content #1 based on the content information #1 and the comment information #1 (step S4). For example, the information processing device 10 generates options for the user to evaluate the content #1 using the content information #1, the comment information #1, and the model #1 that has been trained to generate answers to input questions. As a specific example, the information processing device 10 generates options for the user to evaluate the content #1 by inputting the content information #1, the comment information #1, and an instruction sentence that instructs the model #1 to output options (text information) for evaluating the content #1 that correspond to the feelings of the user who viewed the content #1 based on the content information #1 and the comment information #1.

[0025] To give a more specific example, the information processing device 10 generates options for the user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the number of options to be output should be equal to or less than a predetermined threshold (e.g., 3 or less) and an instruction sentence instructing the options to be output in accordance with the rule into model #1.

[0026] 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) and BERT (Bidirectional Encoder Representations from Transformers). Model #1 is in the information processing device 10, and was created independently by the business entity that manages the information processing device 10. It is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information, such as personal information.

[0027] Here, it is assumed that options #1 to #3 were generated in step S4. In this case, the information processing device 10 outputs the options #1 to #3 in a news application in a manner that allows the user to select them via the content #1 (step S5). For example, the information processing device 10 displays buttons corresponding to the options #1 to #3 on the screen of the user terminal 100 displaying the content #1. In addition, the information processing device 10 displays a button corresponding to option #4, which indicates that options #1 to #3 are not appropriate as options for evaluating the content #1, together with the options #1 to #3, on the screen of the user terminal 100 displaying the content #1.

[0028] Subsequently, the information processing apparatus 10 receives a selection for any one of options #1 to #4 (in other words, a press on any one of the buttons corresponding to options #1 to #4) from the user terminal 100 (step S6). Subsequently, the information processing apparatus 10 sets a profit (remuneration) for the provider P1 according to the number of times options #1 to #3 are selected (step S7). For example, the information processing apparatus 10 sets a higher profit for the provider P1 as the number of times options #1 to #3 are selected is larger (in other words, as the number of times the content #1 is evaluated is larger).

[0029] In addition, when the number of times option #4 is selected is equal to or greater than a predetermined threshold (for example, 100 times or more, 1000 times or more), the information processing apparatus 10 may perform learning of the model #1 using the content information #1, the comment information #1, and options #1 to #3 as negative example data.

[0030] As described above, the information processing apparatus 10 according to the embodiment generates and outputs options for evaluating the content along the content of the content based on the content information indicating the content of the content and the comment information indicating the comments posted by the user for the content. Thereby, the information processing apparatus 10 according to the embodiment can present appropriate options regarding the evaluation of the content to the user and evaluate the content.

[0031] Also, in the content related to conventional news articles, fixed options may be displayed regardless of the content of the news article. However, in such a case, since options along the content of the news article are not displayed, only safe options among the displayed options may be selected, and it may not be possible to specifically grasp how the user evaluates the content.

[0032] In addition, because the options are fixed, options that correspond to the user's feelings toward the content are not displayed, and the user does not select any option (in other words, no reaction is obtained from the user), so the quality of the content cannot be evaluated appropriately. In such cases, it cannot be said that the profits can be set appropriately for the content providers.

[0033] In contrast, the information processing device 10 according to the embodiment can generate options according to the contents of each content and display them as options for evaluating the content, so that it is possible to specifically grasp how users have evaluated the content. Furthermore, the information processing device 10 according to the embodiment can display options according to comments on the content (in other words, information indicating the feelings of users who viewed the content), so that it is possible to increase the possibility that users will select one of the options, appropriately evaluate the quality of the content, and set an appropriate profit for the content provider.

[0034] [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 given below.

[0035] [2-1. About the options to be generated] 1, the information processing device 10 may generate options so that the contents of the options are not similar. For example, the information processing device 10 generates options for a user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the similarity between the options is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule to model #1.

[0036] Furthermore, the information processing device 10 may generate options so that the number of characters in each option is equal to or less than a predetermined threshold (for example, 10 characters or less). For example, the information processing device 10 generates options for a user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the number of characters indicating an option is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the option according to the rule, into model #1.

[0037] [2-2. Providing content according to selected options] 1, the information processing device 10 may provide the content #1 to the user terminal 100 via a news application together with information indicating which option among the options #1 to #3 was most frequently selected by users. For example, if option #1 was most frequently selected by users and option #1 has a content such as "moving," the information processing device 10 provides the content #1 together with a character string such as "moving news article."

[0038] 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.

[0039] (Regarding 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 between the user terminal 100, the provider terminal 200, etc.

[0040] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) 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 provider information database 31, a content database 32, and a model database 33.

[0041] (About Provider Information Database 31) The provider information database 31 stores various types of information related to providers. An example of information stored in the provider information database 31 will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the provider information database 31. In the example of Fig. 3, the provider information database 31 has items such as "provider ID", "content ID", and "profit information".

[0042] "Provider ID" indicates identification information for identifying a provider. "Content ID" indicates identification information for identifying content provided by a provider. "Profit information" indicates information regarding the profit set for the provider in relation to the profit provided by the provider.

[0043] That is, Figure 3 shows an example in which content provided by a provider identified by a provider ID "PID#1" is identified by a content ID "CID#1", and information regarding the benefits set for the content is "Benefit Information #1".

[0044] (About Content Database 32) The content database 32 stores various information related to content. An example of the information stored in the content database 32 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the content database 32. In the example of Fig. 4, the content database 32 has items such as "content ID", "content information", "comment information", "option information", "rating information", and "number of views".

[0045] "Content ID" indicates identification information for identifying content. "Content information" indicates information related to the content, and stores, for example, information such as text information and images contained in the content. "Comment information" indicates comments posted by users on the content. "Option information" indicates options generated for users to rate the content. "Evaluation information" indicates information related to users' evaluations of the content, and stores, for example, information such as the number of times each option indicated in "option information" was selected. "Number of views" indicates the number of views of the content.

[0046] That is, Figure 4 shows an example in which the content information of the content identified by the content ID "CID#1" is "content information #1", the comment information is "comment information #1", the selected ancestor information is "selected ancestor information #1", the rating information is "rating information #1", and the number of views is "number of views #1".

[0047] (About model database 33) The model database 33 stores models that have been trained to generate answers to input questions.

[0048] (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 a RAM as a working 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 acquisition unit 41, a generation unit 42, an output unit 43, a learning unit 44, a provision unit 45, and a setting unit 46, and realizes or executes the functions and actions of information processing described below.

[0049] (Regarding the acquisition unit 41) The acquisition unit 41 acquires content information indicating the content of the content and comment information indicating comments posted by the user for the content. For example, in the example of FIG. 1, the acquisition unit 41 acquires content information indicating the content of the content provided in the news application from the provider terminal 200 and stores it in the content database 32. Further, the acquisition unit 41 acquires comment information #1 indicating each comment posted by the user for content #1 from the user terminal 100 and stores it in the content database 32.

[0050] Note that the acquisition unit 41 may refer to the content database 32 and acquire the content information pre-stored in the content database 32.

[0051] (Regarding the generation unit 42) The generation unit 42 inputs, to a model trained to output an answer to an input question, the content information, the comment information, and an instruction sentence for instructing to output, based on the content information and the comment information, options for evaluating the content, the options corresponding to the feelings of the user who has viewed the content, thereby generating options for evaluating the content. For example, in the example of FIG. 1, the generation unit 42 refers to the content database 32 and the model database 33, inputs the content information #1, the comment information #1, and an instruction sentence for instructing to output, based on the content information #1 and the comment information #1, options for evaluating content #1, the options corresponding to the feelings of the user who has viewed content #1, to the model #1, thereby generating options for the user to evaluate content #1 and storing them in the content database 32.

[0052] Furthermore, the generation unit 42 may generate options for evaluating content by inputting content information, comment information, a rule indicating that the number of options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule into a model. For example, in the example of Fig. 1, the generation unit 42 generates options for the user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the number of options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule into model #1.

[0053] The generation unit 42 may generate options for evaluating content by inputting content information, comment information, a rule indicating that the similarity between options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule, into a model. For example, in the example of Fig. 1, the generation unit 42 generates options for the user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the similarity between options is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule, into model #1.

[0054] The generation unit 42 may generate options for evaluating content by inputting content information, comment information, a rule indicating that the number of characters indicating an option to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the option according to the rule, into a model. For example, in the example of Fig. 1, the generation unit 42 generates options for the user to evaluate content #1 by inputting content information #1, comment information #1, a rule indicating that the number of characters indicating an option is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the option according to the rule, into a model #1.

[0055] (Regarding output unit 43) The output unit 43 outputs the options generated by the generation unit 42 in a manner that allows the user to select them via the content. For example, in the example of FIG. 1, the output unit 43 refers to the content database 32 and displays buttons corresponding to each of the options #1 to #3 on the screen of the user terminal 100 that displays the content #1.

[0056] Alternatively, the output unit 43 may output either the option generated by the generation unit 42 or an inappropriate option indicating that the option is not appropriate for the content in a manner that allows the user to select it via the content. For example, in the example of FIG. 1, the output unit 43 displays a button corresponding to the option #4 indicating that the options #1 to #3 are not appropriate as options for evaluating the content #1 on the screen of the user terminal 100 that displays the content #1, together with the options #1 to #3.

[0057] (Regarding the learning unit 44) The learning unit 44 performs learning of the model according to the number of times the inappropriate option is selected by the user. For example, in the example of FIG. 1, when the number of times the option #4 is selected is equal to or greater than a predetermined threshold, the learning unit 44 uses the content information #1, the comment information #1, and the options #1 to #3 as negative example data to perform learning of the model #1.

[0058] (Regarding the providing unit 45) The providing unit 45 provides the content to the user together with information indicating the option that was most frequently selected by the user among the options generated by the generation unit 42. For example, in the example of FIG. 1, if the option #1 was most frequently selected by the user and the option #1 has content such as "moved", the providing unit 45 provides the content #1 together with a character string such as "news article that moves people".

[0059] (Regarding the setting unit 46) The setting unit 46 sets a predetermined profit to the content provider according to the number of times the option generated by the generation unit 42 is selected by users. For example, in the example of Fig. 1, the setting unit 46 sets a higher profit for the provider P1 as the number of times options #1 to #3 are selected increases.

[0060] [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.

[0061] 5, the information processing device 10 determines whether or not it has acquired content information indicating the details of the content and comment information indicating comments posted by users on the content (step S101). If it has not acquired the content information and the comment information (step S101; No), the information processing device 10 waits until it acquires the content information and the comment information.

[0062] On the other hand, when content information and comment information are acquired (step S101; Yes), the information processing device 10 generates options for evaluating the content by inputting the content information, comment information, and an instruction sentence that instructs the model trained to output an answer to the input question to output options for evaluating the content, which options correspond to the emotions of the user who viewed the content, based on the content information and comment information (step S102). Next, the information processing device 10 outputs the generated options in a form selectable by the user via the content (step S103), and ends the process.

[0063] 5. Modifications The above-described embodiment is merely an example, and various modifications and applications are possible.

[0064] [5-1. Processing mode] Among 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 a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above text and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0065] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.

[0066] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0067] 6. Effects As described above, the information processing device 10 according to the embodiment includes an acquisition unit 41, a generation unit 42, an output unit 43, a learning unit 44, a provision unit 45, and a setting unit 46. The acquisition unit 41 acquires content information indicating the details of the content and comment information indicating comments posted by users on the content. The generation unit 42 generates options for evaluating the content by inputting content information, comment information, and an instruction sentence instructing a model trained to output an answer to an input question to output options corresponding to the emotions of a user who has viewed the content based on the content information and the comment information. The output unit 43 outputs the options generated by the generation unit 42 in a manner selectable by the user via the content. In addition, the output unit 43 outputs either the option generated by the generation unit 42 or an inappropriate option indicating that the option is not appropriate for the content in a manner selectable by the user via the content. The learning unit 44 learns the model according to the number of times the inappropriate option is selected by the user. The providing unit 45 provides the content to the user together with information indicating the option most frequently selected by users among the options generated by the generating unit 42. The setting unit 46 sets a predetermined profit to the content provider according to the number of times the option generated by the generating unit 42 is selected by users.

[0068] As a result, the information processing device 10 according to the embodiment can generate and output options for rating the content in accordance with the content of the content based on content information indicating the content and comment information indicating comments posted by users on the content, thereby presenting appropriate options for rating the content to the user and enabling the user to evaluate the content.

[0069] In addition, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates options for evaluating content by inputting content information, comment information, a rule indicating that the number of options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule, into the model. In addition, the generation unit 42 generates options for evaluating content by inputting content information, comment information, a rule indicating that the similarity between options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule, into the model. In addition, the generation unit 42 generates options for evaluating content by inputting content information, comment information, a rule indicating that the number of characters indicating the options to be output is equal to or less than a predetermined threshold, and an instruction sentence instructing to output the options according to the rule, into the model.

[0070] As a result, the information processing device 10 according to the embodiment can generate an arbitrary number of options, dissimilar options, and options with an arbitrary number of characters, thereby improving convenience.

[0071] [7. Hardware Configuration] Moreover, 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, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0072] The CPU 1100 operates and controls each unit based on a program 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 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0073] 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.

[0074] 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 data generated via the input / output interface 1600 to the output devices.

[0075] 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 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.

[0076] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 40. In addition, the HDD 1400 stores each piece of 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, these programs may be obtained from another device via a predetermined communication network.

[0077] [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 embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0078] Further, 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 to realize some functions.

[0079] Furthermore, the term "unit" in the claims may be read as "means" or "circuit," etc. For example, an acquisition unit may be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0080] 10. Information processing device 20 Communications Department 30 Storage section 31 Provider Information Database 32 Content Database 33 Model Database 40 Control section 41 Acquisition Department 42 Generation part 43 Output section 44 Learning Department 45 Providing Department 46 Setting section 100 User terminals 200 Provider terminal

Claims

1. an acquisition unit that acquires content information indicating details of the content and comment information indicating comments posted by users on the content; a generation unit that generates options for evaluating the content by inputting the content information, the comment information, and an instruction sentence that instructs a model trained to output an answer to an input question to output options for evaluating the content, the options corresponding to the feelings of a user who viewed the content, based on the content information and the comment information; and an output unit that outputs the options generated by the generation unit in a manner that allows a user to select the options via the content; 13. An information processing device comprising:

2. The generation unit is The content information, the comment information, a rule indicating that the number of options to be output is to be equal to or less than a predetermined threshold, and the instruction sentence instructing to output the options in accordance with the rule are input to the model, thereby generating options for evaluating the content.

2. The information processing apparatus according to claim 1,

3. The generation unit is The content information, the comment information, a rule indicating that the similarity between options to be output is equal to or less than a predetermined threshold, and the instruction sentence instructing to output options according to the rule are input to the model, thereby generating options for evaluating the content.

2. The information processing apparatus according to claim 1,

4. The generation unit is The content information, the comment information, a rule indicating that the number of characters indicating the options to be output is equal to or less than a predetermined threshold, and the instruction sentence instructing to output the options in accordance with the rule are input to the model, thereby generating options for evaluating the content.

2. The information processing apparatus according to claim 1,

5. The output unit is outputting, via the content, one of the options generated by the generation unit and an inappropriate option indicating that the option is not appropriate for the content, in a manner that allows a user to select the option; A learning unit that learns the model according to the number of times the inappropriate option is selected by the user.

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

6. a provision section for providing the content to the user together with information indicating the option most frequently selected by users among the options generated by the generation section; 2. The information processing apparatus according to claim 1, further comprising:

7. a setting unit that sets a predetermined profit to the provider of the content according to the number of times the option generated by the generating unit is selected by users; 2. The information processing apparatus according to claim 1, further comprising:

8. 1. A computer-implemented information processing method, comprising: an acquiring step of acquiring content information indicating details of the content and comment information indicating comments posted by users on the content; a generation step of generating options for evaluating the content by inputting the content information, the comment information, and an instruction sentence for instructing a model trained to output answers to input questions, the option being for evaluating the content, the option corresponding to the emotion of a user who viewed the content, based on the content information and the comment information; an output step of outputting the options generated by the generating step in a form selectable by a user via the content; 13. An information processing method comprising:

9. An acquisition step of acquiring content information indicating details of the content and comment information indicating comments posted by users on the content; a generation step of generating options for evaluating the content by inputting the content information, the comment information, and an instruction sentence for instructing a model trained to output an answer to an input question to output options for evaluating the content, the options corresponding to the feelings of a user who viewed the content, based on the content information and the comment information; an output step of outputting the options generated by the generation step in a manner selectable by a user via the content; An information processing program for causing a computer to execute the above.

Images