Proposal device, proposal method, and proposal program

Abstract

To solve the problem that a service provider side such as a news site requests input of more comments with respect to various users who have viewed content, nevertheless the comments are not inputted unexpectedly, and, depending on the details of the content, the inputted comments are overbearing, are defamatory, and are not healthy comments to be requested originally.SOLUTION: A proposal device comprises: a request unit which requests an impression of content, to a user who is viewing the content; an estimation unit which estimates the user's emotion, on the basis of the inputted impression; and a proposal unit which proposes contribution of comments with respect to the content, generated on the basis of the impression, to the user, if the estimated emotion satisfies a predetermined condition. Thereby, healthy comments can be increased more, with respect to the content disclosed on the Internet.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a suggestion device, a suggestion method, and a suggestion program that generate and propose user comments in a conversational format via AI chat. [Background technology]

[0002] Users can view a variety of content, such as news and articles published on the Internet, posts and comments by other users, etc. Depending on the content, users who view the content can also enter comments on the content. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-80641 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, for example, service providers such as news sites, who request many comments from various users, are unable to input as many comments as they would like because a certain level of writing ability is required to input such comments. Also, for example, depending on the content, the comments entered may be intimidating, slanderous, or otherwise undesirable, which is what is actually desired.

[0005] The present application has been made in consideration of the above, and aims to further increase healthy comments on content published on the Internet. [Means for solving the problem]

[0006] The proposal device according to the present application is characterized by having a request unit that requests an opinion on the content from a user viewing the content, an estimation unit that estimates the user's emotions based on the inputted impressions, and a proposal unit that suggests to the user that a comment on the content be posted, which is generated based on the impressions, if the estimated emotions satisfy a predetermined condition. Effect of the Invention

[0007] According to one aspect of the present embodiment, it is possible to advantageously increase the number of healthy comments on content published on the Internet. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing system 1 according to the present embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the proposed device 100 according to this embodiment. [Diagram 3] FIG. 3 is a flowchart illustrating an example of a procedure of the proposal process according to the present embodiment. [Figure 4] FIG. 4 is a flowchart showing an example of a procedure of the correction process according to the present embodiment. [Diagram 5] FIG. 5 is a flowchart showing another example of the procedure of the correction process according to the present embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the proposed device 100. As shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, a detailed description will be given of a proposed device, a proposed method, and a proposed program according to the present application (hereinafter, referred to as an "embodiment") with reference to the drawings. Note that the proposed device, the proposed method, and the proposed program according to the present application are not limited to the embodiment. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0010] [1. Configuration of information processing system] With reference to FIG. 1, information processing realized by the proposed device 100 of the present embodiment and the like will be described. FIG. 1 is a diagram showing a configuration example of an information processing system 1 according to the present embodiment. In the example shown in FIG. 1, the information processing system 1 has a user terminal 10 and a proposed device 100. As shown in FIG. 1, the user terminal 10 and the proposed device 100 are connected to each other via a network N, for example, in a wired or wireless manner so as to be able to communicate with each other. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (such as a mobile phone network or a landline telephone network), a regional IP (Internet Protocol) network, or the Internet. The network N may include a wired network or a wireless network. The information processing system 1 shown in FIG. 1 may include a plurality of user terminals 10 and a plurality of proposed devices 100.

[0011] The user terminal 10 shown in Fig. 1 is, for example, an information processing terminal used by a user to view content on the Internet. The user terminal 10 is, for example, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Fig. 1, the user terminal 10 is a smart device such as a smartphone or tablet used by a user.

[0012] The user terminal 10 shown in FIG. 1 receives content such as news provided by the proposal device 100, and displays it on a display unit or a display communicably connected to the user terminal 10. Then, for example, a user can view the displayed content through the user terminal 10. Also, the user inputs, for example, an impression of the content through a soft keyboard (screen keyboard) of the user terminal 10 or a keyboard communicably connected to the user terminal 10. Note that the impression of the content may be, for example, a comment on a comment made by another user. Note that the content is not limited to, for example, news, and includes various information such as text, images, and videos published on the Internet, so-called Web content.

[0013] 1 is, for example, an information processing device such as a server computer managed by a service provider that provides various contents via the Internet. Alternatively, the proposed device 100 may be, for example, a cloud computer device managed by a cloud service provider that provides cloud computing services.

[0014] Furthermore, the proposal device 100, for example, requests a user viewing content to give an impression of the content, and estimates the user's emotion based on the input impression. Then, for example, when the estimated emotion satisfies a predetermined condition, the proposal device 100 suggests the user to post a comment on the content.

[0015] 2. Configuration of the proposed device Next, the configuration of the proposal device 100 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the proposal device 100 according to the present embodiment. As shown in Fig. 2, the proposal device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0016] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from other devices such as the user terminal 10.

[0017] (Regarding the storage unit 120) The storage unit 120 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 120 has a content data storage unit 121, an impression data storage unit 122, a comment data storage unit 123, and a model data storage unit 124.

[0018] (Regarding the content data storage unit 121) The content data storage unit 121 stores, for example, information related to content that is provided to a user and can be viewed by the user. More specifically, the information may be, for example, information such as text, images, and videos published as content on the Internet. Note that, for example, when the content is provided by an information processing device other than the proposal device 100, the proposal device 100 does not need to have the content data storage unit 121.

[0019] (Regarding the impression data storage unit 122) The impression data storage unit 122 stores information about impressions of the content input by the user, for example. More specifically, the information may be information such as a sentence for each user indicating the impression of the content. The impression may be input from a dedicated input form on the Web provided by the suggestion device 100, for example.

[0020] (Regarding the comment data storage unit 123) The comment data storage unit 123 stores, for example, information related to comments posted on content. More specifically, the information may be, for example, information such as a sentence for each user indicating a comment on the content. Note that the comment may be generated by the suggestion device 100 based on, for example, an input impression.

[0021] (Regarding the model data storage unit 124) The model data storage unit 124 stores, for example, information on a machine learning model for estimating the emotion of a user based on the impression input by the user, and model parameters for constructing the machine learning model. The machine learning model is generated by machine learning using, for example, the impression of the content input by the user as a feature amount and the degree of each of the user's emotions (hereinafter, sometimes referred to as "emotion score") as a correct answer label. The emotion score may be, for example, a numerical value from 1 to 5 that indicates the degree of each of the emotions on a 5-point scale (for example, 1 being the weakest emotion level and 5 being the strongest emotion level). Alternatively, the emotion score may be, for example, the probability (which may be a probability, likelihood, etc.) that the user's emotion is any of the emotions of joy, anger, sadness, and happiness.

[0022] The model data storage unit 124 also stores information about a machine learning model for estimating and generating comments based on, for example, impressions input by a user, and model parameters for constructing the machine learning model. The machine learning model is generated by machine learning using, for example, impressions on content input by a user as features and comments on the content as correct answer labels. Note that the comments may be, for example, summaries of impressions on the content.

[0023] The model data storage unit 124 also stores, for example, information about a machine learning model for estimating the discrepancy between an impression input by a user and the content of the content, and model parameters for constructing the machine learning model. The machine learning model is generated by machine learning using, for example, the impression input by a user on the content and the content of the content as feature quantities, and the degree of semantic discrepancy between the impression and the content as a correct answer label.

[0024] The model data storage unit 124 also stores, for example, information about a machine learning model for estimating and generating a corrected impression based on an impression input by a user, and model parameters for constructing the machine learning model. The machine learning model is generated by machine learning, for example, with the impression on the content input by the user as a feature and the corrected impression after correcting the impression as a corrected label. The corrected impression is, for example, an impression corrected to fall within a predetermined standard when it is determined that the content of the impression before correction and the content are semantically different by more than a predetermined standard. Alternatively, the corrected impression may be, for example, an impression corrected to alleviate the content when the impression before correction includes inappropriate content such as an intimidating expression or slander.

[0025] The various machine learning models whose information is stored in the model data storage unit 124 may be existing machine learning models such as a Generative Pretrained Transformer (GPT).

[0026] (Regarding the control unit 130) The control unit 130 is a controller, and is realized, for example, by a central processing unit (CPU) or a micro processing unit (MPU) executing various programs stored in a storage device inside the proposal device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU). As shown in FIG. 2, the control unit 130 according to this embodiment has a request unit 131, an estimation unit 132, and a proposal unit 133, and realizes or executes the functions and actions of information processing described below.

[0027] (Regarding the request unit 131) The request unit 131, for example, requests the user viewing the content to give their thoughts on the content. For example, if the content is an article, the request may be an inquiry about the content, such as displaying a message such as "What did you think of this article?" via the user terminal 10. The request unit 131 may also display, for example, a text box for inputting thoughts via the user terminal 10 and accept input of thoughts from the user. Note that such a request for thoughts or acceptance of input by the request unit 131 may be made in the form of a chat between the AI ​​(Artificial Intelligence) chat by the proposal device 100 and the user via the user terminal 10.

[0028] (Regarding the estimation unit 132) The estimation unit 132 estimates the emotion of the user based on, for example, the impression input by the user. The process of estimating the emotion may include, for example, a process of estimating the degree of each of the emotions (emotion score) of the user from the content of the impression input by the user. In addition, such estimation of the user emotion by the estimation unit 132 may be performed using, for example, a machine learning model whose information is stored in the model data storage unit 124. Alternatively, for example, the estimation of the user emotion may be a rule-based estimation of the user emotion based on keywords included in the impression input by the user. Note that, for example, when using GPT, the GPT may be made to estimate the user emotion by inputting a message such as "Based on the content of the conversation, please rate each of the emotions of joy, anger, sadness, and happiness on a five-point scale. 1 is the weakest and 5 is the strongest." In addition, the estimation of the user emotion by the estimation unit 132 may be performed based on the content of the conversation up to that point, for example, as the chat-style conversation between the AI ​​chat by the proposal device 100 and the user via the user terminal 10 progresses. That is, the estimation unit 132 may estimate the user's emotion that changes as the conversation progresses, for example.

[0029] Furthermore, the estimation unit 132 estimates whether or not the impression is semantically dissociated from the contents of the content, based on the content and the impression on the content input by the user, for example. Note that such estimation of the semantic dissociation of the impression by the estimation unit 132 may be performed using, for example, a machine learning model whose information is stored in the model data storage unit 124.

[0030] (About Proposal Section 133) For example, when the emotion estimated by the estimation unit 132 satisfies a predetermined condition, the suggestion unit 133 suggests the user to post a comment on the content. The process of suggesting the user to post a comment may include, for example, a process of suggesting the user to post a comment when any of the estimated degrees of joy, anger, sadness, and happiness is equal to or higher than a predetermined threshold. More specifically, for example, when the emotion score expresses the degree of each of joy, anger, sadness, and happiness on a five-level scale from 1 to 5 (1 being the weakest and 5 being the strongest), the suggestion unit 133 suggests the user to post a comment on the content when any of the degrees of joy, anger, sadness, and happiness is 4 or higher. In addition, when the GPT is used, for example, a message such as "When the score of joy, anger, sadness, and happiness is 4 or higher, say 'Would you like to comment?'" may be input as a prompt to cause the GPT to suggest the user to post a comment.

[0031] Furthermore, for example, when the suggestion unit 133 obtains consent for posting a comment from the user, the suggestion unit 133 generates the comment based on the impressions input by the user. The comment may be, for example, a summary of impressions on the content, and the comment may be generated using a machine learning model whose information is stored in the model data storage unit 124.

[0032] Furthermore, the suggestion unit 133, for example, presents the generated comment to the user to check the content of the comment, and posts the comment if the content of the comment is approved by the user. More specifically, regarding the posting of the comment, the suggestion unit 133 posts the comment on the Internet to make it public, for example, as a comment on content published on the Internet.

[0033] Furthermore, for example, when the impression input by the user is semantically deviated from the contents of the content (as estimated by the estimation unit 132), the suggestion unit 133 corrects the impression and presents the corrected impression to the user to confirm whether the corrected impression is correct or not. Note that such correction of the impression by the suggestion unit 133 may be performed using, for example, a machine learning model whose information is stored in the model data storage unit 124.

[0034] Furthermore, for example, when the emotion estimated by the estimation unit 132 satisfies a predetermined condition (for example, when the degree of any of joy, anger, sadness, and happiness is 4 or more) and the user responds that the corrected impression is correct, the suggestion unit 133 suggests to the user that he or she post a comment on the content. Note that, for example, when the user agrees to post a comment, the suggestion unit 133 will generate a comment, and the comment in this case may be generated based on the corrected impression.

[0035] Furthermore, for example, when the degree of anger of the joy, anger, sadness, and happiness estimated by the estimation unit 132 is equal to or greater than a predetermined threshold, the suggestion unit 133 corrects the impression input by the user, presents the corrected impression to the user, and confirms whether the corrected impression is correct. For example, when the degree of anger of the user's emotion indicates a high value such as a threshold value 4 or more, the impression input by the user is likely to include inappropriate content as an impression, such as intimidating expressions or slander, and therefore, the correction of the impression is a process of correcting the content of the impression to be less harsh. Note that such correction of the impression by the suggestion unit 133 may also be performed using, for example, a machine learning model whose information is stored in the model data storage unit 124.

[0036] [3. Proposal processing flow] A procedure for a process of suggesting a comment for content being viewed by a user according to this embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an example of the procedure for the suggestion process according to this embodiment. The delivery process shown in Fig. 3 may be triggered by the passage of a certain period of time after the user displays the content provided by the suggestion device 100 via the user terminal 10.

[0037] First, as shown in Fig. 3, the proposal device 100 determines whether the assist mode of the user associated with the user terminal 10 that displayed the content is ON or OFF (step S101). The assist mode is, for example, a preset setting for whether the user will use AI chat or not, and is controlled so that AI chat is used when the assist mode is ON and not used when the assist mode is OFF. Therefore, when the assist mode is OFF (step S101: No), the proposal process shown in Fig. 3 ends.

[0038] When the assist mode is ON (step S101: Yes), the proposal device 100, for example, requests the user viewing the content to provide their thoughts on the content via the user terminal 10 (step S102). Then, for example, in response to the request for thoughts in step S102, when the user inputs thoughts via the user terminal 10, the proposal device 100 receives and accepts the thoughts from the user terminal 10. Note that the request for thoughts from the user and the acceptance of the thoughts may be made, for example, during a chat-style conversation between the user and the proposal device 100 via AI chat.

[0039] Next, the suggestion device 100 estimates the emotion of the user based on, for example, the impression input by the user (step S103). The estimation of the emotion may be, for example, a rule-based estimation based on keywords included in the impression, or may be estimation using a machine learning model such as GPT. The estimation of the emotion may be, for example, an estimation of an emotion score that indicates the degree of each of joy, anger, sadness, and happiness on a five-point scale. The estimation of the emotion may be performed, for example, in a chat-style conversation with the user through AI chat, and the emotion of the user may be estimated every time a conversation is input from the user in the conversation.

[0040] Next, the proposal device 100 determines whether the degree of any of joy, anger, sadness, and happiness in the emotion score estimated in step S103 is equal to or greater than a predetermined threshold (for example, equal to or greater than 4 out of 5) (step S104). If the degree of any of joy, anger, sadness, and happiness is less than the predetermined threshold (step S104: No), the proposal process shown in Fig. 3 ends. However, for example, if a chat-style conversation with the user through AI chat is continuing, the process may return to step S103, and the user's emotion may be estimated for the new conversation.

[0041] On the other hand, if the degree of any of joy, anger, sadness, and happiness is equal to or greater than a predetermined threshold (step S104: Yes), the suggestion device 100, for example, via the user terminal 10, suggests the user to post a comment on the content (step S105). If the user does not agree to post a comment (step S106: No), the suggestion process shown in FIG. 3 ends.

[0042] On the other hand, if the user agrees to post a comment (step S106: Yes), the proposal device 100 generates a comment based on, for example, the impression input by the user (step S107).

[0043] Next, the proposing device 100 presents the comment generated in step S107 to the user via, for example, the user terminal 10, and checks the content of the comment (step S108). If the user's approval is not obtained for the content of the comment (step S109: No), the process returns to step S107, and the proposing device 100 generates a comment again. Such regeneration of the comment may be performed while checking, for example, which part of the content of the comment did not obtain approval through a chat-style conversation between the user and an AI chat. Note that, for example, the initial generation of the comment (step S107) may also be performed through a chat-style conversation between the user and an AI chat.

[0044] On the other hand, if the user's approval is obtained for the content of the comment generated in step S107 (step S109: Yes), the proposing device 100 posts the comment generated in step S107, for example (step S109). Note that the posting of the comment may be, for example, posting and making public the comment on the Internet as a comment on the content published on the Internet. After the execution of step S109, the proposing process shown in FIG. 3 ends.

[0045] [4. Flow of correction process] Using FIG. 4, the procedure for the correction process of the impressions input by the user according to this embodiment will be described. FIG. 4 is a flowchart showing an example of the procedure for the correction process according to this embodiment. The correction process shown in FIG. 4 may be executed, for example, between step S102 and step S103 in the proposing process shown in FIG. 3.

[0046] First, as shown in FIG. 4, the proposing device 100 is, for example, in the proposing process shown in FIG. 3 It is estimated whether the impression input by the user in response to the impression request in step S102 is semantically different from the content of the content (step S201). If it is estimated that the impression is not semantically different from the content of the content (step S202: No), the correction process shown in Fig. 4 ends and returns to the suggestion process shown in Fig. 3, and then step S103 is executed.

[0047] On the other hand, if it is estimated that the impression is semantically deviated from the contents of the content (step S202: Yes), the suggestion device 100, for example, corrects the impression (step S203).

[0048] Next, the suggestion device 100 presents the impression corrected in step S203 to the user via the user terminal 10, for example, and confirms whether the corrected impression is correct (step S204). If the user replies that the corrected impression is incorrect (step S205: No), the process returns to step S203, and the suggestion device 100 corrects the impression again. Note that such re-correction of the impression may be performed, for example, by a chat-style conversation with the user via AI chat, while confirming which parts of the impression are incorrect.

[0049] On the other hand, if the user replies that the impression corrected in step S203 is correct (step S205: Yes), the correction process shown in Fig. 4 ends and the process returns to the suggestion process shown in Fig. 3, and then step S103 is executed. Note that, for example, in this case, the impression corrected in step S203 is used in the processes after step S103.

[0050] [5. Correction Processing Flow] A procedure for correcting an impression input by a user according to this embodiment will be described with reference to FIG. 5. FIG. 5 is a flowchart showing another example of the procedure for the correction process according to this embodiment. For example, the correction process for an impression shown in FIG. 4 is a correction of a semantic deviation of an impression on a content, whereas the correction process for an impression shown in FIG. 5 is a correction for mitigating an inappropriate impression such as an intimidating expression or a slanderous remark. The correction process shown in FIG. 5 may be executed, for example, between step S103 and step S104 in the suggestion process shown in FIG. 3.

[0051] First, as shown in Fig. 4, the proposal device 100 determines whether the degree of anger of the emotion score estimated in step S103 in the proposal process shown in Fig. 3 is equal to or greater than a predetermined threshold (e.g., equal to or greater than 4 out of 5) (step S301). If the degree of anger is less than the predetermined threshold (step S301: No), the correction process shown in Fig. 5 ends and the process returns to the proposal process shown in Fig. 3, and then step S104 is executed.

[0052] On the other hand, if the degree of anger is equal to or greater than the predetermined threshold (step S301: Yes), the proposal device 100 corrects, for example, the impression input by the user (step S302). In step S302, for example, the impression input by the user is corrected to reduce inappropriate content such as intimidating expressions or slander.

[0053] Next, the proposal device 100 presents the impression corrected in step S302 to the user via the user terminal 10, for example, and confirms whether the corrected impression is correct (step S303). If the user replies that the corrected impression is incorrect (step S304: No), the process returns to step S302, and the proposal device 100 corrects the impression again. Note that such re-correction of the impression may be performed, for example, by a chat-style conversation with the user via AI chat, while confirming which parts of the impression are incorrect.

[0054] On the other hand, if the user replies that the impression corrected in step S302 is correct (step S304: Yes), the correction process shown in Fig. 5 ends and the process returns to the suggestion process shown in Fig. 3, and then step S104 is executed. Note that, for example, in this case, the impression corrected in step S302 is used in the processes after step S103.

[0055] 6. Effects The proposal device 100 according to this embodiment includes a request unit 131 that requests an opinion on the content from a user viewing the content, an estimation unit 132 that estimates the user's emotion based on the inputted emotion, and a proposal unit 133 that suggests to the user that he or she post a comment on the content if the estimated emotion satisfies a predetermined condition.

[0056] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0057] Furthermore, the process of estimating emotions, which is executed by the proposal device 100 according to the present embodiment, includes a process of estimating the degree of each of the user's emotions, joy, anger, sadness, and happiness, from the contents of the impressions.

[0058] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0059] In addition, the process of suggesting posting a comment executed by the suggestion device 100 according to this embodiment includes a process of suggesting to the user to post a comment if any of the estimated degrees of joy, anger, sadness, and happiness is equal to or greater than a predetermined threshold.

[0060] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0061] Furthermore, when consent is obtained from the user for posting a comment, the suggestion unit 133 included in the suggestion device 100 according to this embodiment generates a comment based on the user's impression.

[0062] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0063] Moreover, the proposing unit 133 included in the proposing device 100 according to this embodiment presents the comment to the user, checks the content of the comment, and posts the comment if the content of the comment is approved by the user.

[0064] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0065] In addition, the estimation unit 132 included in the proposal device 100 according to this embodiment estimates whether or not the impression is semantically different from the content of the content based on the content and the impression, and if the impression is semantically different from the content of the content, the proposal unit 133 corrects the impression and presents the corrected impression to the user to confirm whether the corrected impression is correct or not.

[0066] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0067] In addition, the process of suggesting posting of a comment, which is executed by the suggestion device 100 according to this embodiment, includes a process of suggesting to the user that the user post a comment on the content, when the estimated emotion satisfies a predetermined condition and the user responds that the corrected impression is correct.

[0068] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0069] In addition, when the degree of anger among the joy, anger, sadness, and happiness estimated is equal to or greater than a predetermined threshold, the suggestion unit 133 of the suggestion device 100 according to this embodiment corrects the impression, presents the corrected impression to the user, and confirms whether the corrected impression is correct or not.

[0070] As a result, the proposal device 100 according to the present embodiment can further increase healthy comments on content published on the Internet.

[0071] [7. Hardware Configuration] The proposed device 100 and the user terminal 10 according to this embodiment are realized, for example, by a computer 1000 configured as shown in Fig. 6. The proposed device 100 will be described below as an example with reference to Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the proposed device 100. 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] HDD 1400 stores programs executed by CPU 1100, data used by such programs, etc. Communication interface 1500 receives data from other devices via communication network 500 (e.g., corresponding to network N shown in FIG. 1) and sends the data to CPU 1100, and also transmits data generated by CPU 1100 to other devices via 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 proposed device 100, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 130. In addition, the HDD 1400 stores each piece of data in the storage device of the proposed device 100. 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 present embodiments 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] Furthermore, the proposed device 100 can be flexibly configured such that some functions can be implemented by calling an external platform using an API (Application Programming Interface) or network computing.

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

[0080] 10 User terminal 100 Proposed device 110 Communications Department 120 Storage section 121 Content data storage unit 122 Impression data storage unit 123 Comment data storage unit 124 Model data storage unit 130 Control section 131 Request part 132 Estimation Department 133 Proposal Department 1000 Computers 1100 CPU 1200 ROM 1300 RAM 1400 HDD 1500 Communication Interface 1600 Input / Output Interface 1700 Media Interface 1800 Recording media

Claims

1. a request unit for requesting an opinion on a content from a user viewing the content; an estimation unit that estimates a feeling of the user based on the input impression; a suggestion unit that suggests to the user to post a comment on the content when the estimated emotion satisfies a predetermined condition; The proposed device is characterized by having:

2. The emotion estimation process includes: The degree of each of the user's emotions, such as joy, anger, sadness, and happiness, is estimated from the content of the impression. The suggestion device according to claim 1, further comprising a process.

3. The process of suggesting posting of a comment includes: If any of the estimated levels of joy, anger, sadness, and happiness is equal to or greater than a predetermined threshold, the user is suggested to post the comment.

3. The suggestion device according to claim 2, further comprising a process.

4. The suggestion unit, If the user agrees to post the comment, the comment is generated based on the user's impression.

2. The proposal device according to claim 1 .

5. The suggestion unit, presenting the comment to the user to confirm the content of the comment; If the content of the comment is approved by the user, the comment is posted.

5. The proposal device according to claim 4.

6. The estimation unit estimates whether or not the impression is semantically deviated from a content of the content, based on the content and the impression; When the impression is semantically deviated from the content of the content, the suggestion unit corrects the impression, presents the corrected impression to the user, and confirms whether the corrected impression is correct.

6. A proposal device according to claim 1, wherein the proposal device is a device for proposing a proposal to a user.

7. The process of suggesting posting of a comment includes: If the estimated emotion satisfies a predetermined condition and the user responds that the corrected impression is correct, the user is suggested to post a comment on the content. The suggestion device according to claim 6, further comprising a process.

8. When the estimated degree of anger among the joy, anger, sadness, and happiness is equal to or greater than a predetermined threshold, the suggestion unit corrects the impression, presents the corrected impression to the user, and confirms whether the corrected impression is correct.

3. The proposal device according to claim 2.

9. A proposal method executed by a proposal device, a request step of requesting an opinion on the content from a user viewing the content; an estimation step of estimating the user's emotion based on the input impression; a suggestion step of suggesting to the user to post a comment on the content if the estimated emotion satisfies a predetermined condition; The proposed method comprises:

10. a request step of requesting a user viewing a content to provide feedback on the content; an estimation step of estimating the user's emotion based on the input impression; a suggestion step of suggesting to the user to post a comment on the content if the estimated emotion satisfies a predetermined condition; A proposal program that causes a proposal device to execute the above.

Images