Information processing system, information processing method, and program

Abstract

The present invention proposes an action with respect to data input by a user. This information processing system comprises: a first generation request acquisition unit that acquires, from a user device, first generation request information for generating prescribed content; a second generation request generation unit that generates second generation request information which is evaluated to be higher in quality than the first generation request information, on the basis of a generation request generation rule, a generation request evaluation rule, and the first generation request information; a content acquisition unit that acquires first content generated on the basis of the first generation request information, and second content generated on the basis of the second generation request information; a content evaluation unit that evaluates the first content and the second content on the basis of the content evaluation rule; an action proposal generation unit that, on the basis of the evaluation results, generates action proposal information relating to a proposal to a user of an action related to the first generation request information; and an action proposal output unit that outputs the action proposal information.

Description

Information processing system, information processing method, and program CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on Japanese Patent Application No. 2023-147580 filed on September 12, 2023 and Japanese Patent Application No. 2023-188794 filed on November 2, 2023, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to an information processing system, an information processing method, and a program.

[0003] In recent years, the use of artificial intelligence (AI) has progressed, and techniques for proposing appropriate utilization methods of AI to users have become known. For example, the AI ​​service usage support system described in Patent Literature 1 supports the use of AI service systems. The AI ​​service usage support system has an accuracy evaluation processing unit that receives response data by sending inquiry data to an AI service system to be evaluated, and calculates accuracy information of the AI ​​service system using correct answer data corresponding to the inquiry data and the response data.

[0004] Japanese Patent Application Laid-Open No. 2019-3267

[0005] However, in the AI ​​service usage support system described in Patent Literature 1, the accuracy of an AI service system is evaluated by evaluating the output results of the AI ​​service system. Therefore, if a user inputs data into a first AI service system and is unable to obtain desired content, the AI ​​service usage support system does not take into consideration proposing actions (e.g., proposing corrections) for the data input by the user, and the user must use the AI ​​service usage support system to search for a second AI service system with higher accuracy.

[0006] Therefore, an object of the present disclosure is to suggest actions for data input by a user.

[0007] An information processing system according to one aspect of the present disclosure includes a first generation request acquisition unit that acquires first generation request information for generating specified content from a user device, a second generation request generation unit that generates second generation request information that is evaluated to be of higher quality than the first generation request information based on generation request generation rules for generating the generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and the first generation request information, a content acquisition unit that acquires first content generated based on the first generation request information and second content generated based on the second generation request information, a content evaluation unit that evaluates each of the first content and the second content based on content evaluation rules for evaluating the content, an action proposal generation unit that generates action proposal information regarding action proposals related to the first generation request information to a user using the user device based on the results of the evaluation, and an action proposal output unit that outputs the action proposal information.

[0008] According to the present disclosure, it is possible to suggest actions for data input by a user.

[0009] FIG. 7 is a diagram illustrating an overview of processing in an information processing system 100 according to an embodiment of the present disclosure. FIG. 8 is a diagram illustrating a configuration of an information processing system 100 according to an embodiment of the present disclosure. FIG. 9 is a diagram illustrating an example of evaluation result information stored in a storage unit 110. FIG. 10 is a flowchart illustrating an example of processing in the information processing system 100. FIG. 11 is a flowchart illustrating an example of processing in the information processing system 100. FIG. 12 is a diagram illustrating an example of a hardware configuration of a computer 700.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present disclosure will be described with reference to the accompanying drawings. Fig. 1 is a diagram showing an overview of processing in an information processing system 100 according to an embodiment of the present disclosure.

[0011] The information processing system 100 is an information processing system that acquires first generation request information from a user device, generates second generation request information based on the first generation request information, evaluates the first content generated based on the first generation request information and the second content generated based on the second generation request information, and generates and outputs action suggestion information regarding action suggestions related to the first generation request information.

[0012] In recent years, users have been obtaining desired content by providing generation request information (e.g., a prompt) to a predetermined information processing system (e.g., a content generator 300) described below. If the desired content cannot be obtained, the user may modify the generation request information and provide the modified generation request information to the predetermined information processing system again. In other words, to obtain the desired content, the user must invest resources (e.g., time and effort) in repeatedly creating, modifying, and providing the generation request information. However, it may be difficult for the user to fully understand the content generation algorithm in the content generator 300. As a result, even with the modified generation request information, the desired content may not be generated. Furthermore, lower-quality content may be generated based on the modified generation request information. In such cases, the resources invested by the user are wasted.

[0013] Thus, acquiring content through generation request information does not necessarily improve the quality of the acquired content in proportion to the resources invested. Therefore, users provide generation request information to the content generator 300 in the faint hope that increasing their investment will result in higher-quality content, while at the same time bearing the risk that increasing their investment will not improve the quality of the content. If content acquisition through generation request information is considered an investment, in which content is acquired as a return on the investment of resources in generating, modifying, and providing the generation request information, then users are currently forced to gamble with their own time and effort. This can be seen as a situation in which the user's investment efficiency is low or they are unable to make rational decisions due to a lack of information to make investment decisions.

[0014] Therefore, the information processing system 100 generates second generation request information of higher quality than the first generation request information created by the user based on the generation request generation rules and the generation request evaluation rules, and evaluates the quality of content generated based on each of the first and second generation request information to determine whether it is desirable for the user to modify the generation request information or not, and proposes an action to the user regarding the generation request information. That is, for example, if the information processing system 100 determines that the return obtained in response to the resource investment of modifying the generation request information is small, the information processing system 100 may generate action suggestion information that suggests proceeding with the processing without modifying the generation request information, or if it determines that the return obtained in response to the resource investment of modifying the generation request information is large, the information processing system 100 may generate action suggestion information that suggests modifying the generation request information and processing, or that suggests proceeding with the processing based on the second generation request information generated in the information processing system 100.

[0015] Specifically, first, the information processing system 100 acquires first generation request information 101 from the user device 200. The information processing system 100 generates second generation request information 102 based on the first generation request information.

[0016] Next, the information processing system 100 acquires the first content 103 generated based on the first generation request information and the second content 104 generated based on the second generation request information. Then, the information processing system 100 evaluates the first content 103 and the second content 104, generates action suggestion information 105 related to action suggestions related to the first generation request information, and outputs the action suggestion information 105 to the user device 200.

[0017] This allows the information processing system 100 to control the user's expectations regarding the return obtained in response to the investment of resources. In other words, the user can grasp the user's expectations regarding the improvement in the quality of the content that can be generated by the investment of resources, i.e., by modifying the generation request information, before modifying the generation request information, thereby controlling the user's expectations. Furthermore, if it is determined that the quality of the content that can be generated will not improve, the user can avoid wasting resources, i.e., modifying the generation request information. Furthermore, rather than repeatedly modifying the generation request information as if gambling, the user can make rational investment decisions based on the processing results of the information processing system 100, thereby increasing the user's sense of self-efficacy. Furthermore, by avoiding the user from carelessly inputting generation request information into the content generator 300, the power consumption of the content generator 300 is reduced and the processing speed of the content generator 300 is expected to improve.

[0018] 2 is a diagram showing a configuration of an information processing system 100 according to an embodiment of the present disclosure. The information processing system 100 is communicably connected to a user device 200 and a content generator device 300 via a network such as the Internet. Details of the information processing system 100 will be described later.

[0019] The user device 200 is an information processing device used by a user of the information processing system 100, and is a computer, a smartphone, a tablet terminal, a personal computer, or the like.

[0020] The user accesses the information processing system 100 using the user device 200 and provides first generation request information to the information processing system 100. The user also accesses the information processing system 100 using the user device 200 and obtains action suggestion information from the information processing system 100.

[0021] The content generator 300 is an information processing device that generates content based on generation request information, and includes, for example, a server device that provides so-called generative artificial intelligence (AI).

[0022] The content generator 300 may be an information processing device that receives generation request information as an input and outputs content based on, for example, natural language processing technology and machine learning technology. The content generator 300 may also receive generation request information as an input and output content based on, for example, a large-scale language model.

[0023] The generation request information (e.g., first generation request information, second generation request information, and third generation request information described below) may be, for example, a command statement (e.g., a prompt) for the content generator 300 to generate content in the content generator 300. The generation request information may include, for example, text data, image data, video data, or audio data.

[0024] The content generated by the content generator 300 is not particularly limited, but may include, for example, text data, image data, video data, or audio data.

[0025] Although one user device 200 and one content generator 300 are shown in FIG. 2, there may be a plurality of user devices 200 and a plurality of content generators 300.

[0026] Next, details of the information processing system 100 will be described. The information processing system 100 includes a storage unit 110, a first generation request acquisition unit 120, a user information acquisition unit 130, a second generation request generation unit 140, a content acquisition unit 150, a content evaluation unit 160, a user score calculation unit 170, an action proposal generation unit 180, and an action proposal output unit 190. Each unit shown in Fig. 2 can be realized, for example, by using a storage area or by a processor executing a program stored in the storage area.

[0027] The storage unit 110 stores information to be processed in the information processing system 100. The storage unit 110 can store, for example, user information, first generation request information, second generation request information, first content, second content, evaluation result information, user score, and action suggestion information, which will be described later.

[0028] The first generation request acquisition unit 120 acquires first generation request information for generating a predetermined content (first content) from the user device 200 and stores the acquired first generation request information in the storage unit 110.

[0029] The first content may be, for example, a “flyer proposal to encourage people to undergo cancer screening.” In this case, the first generation request information may be, for example, “Generate 10 types of flier proposals to encourage people to undergo cancer screening.”

[0030] The user information acquisition unit 130 acquires user information relating to the user and stores the acquired user information in the storage unit 110 .

[0031] The user information may include, for example, attribute information about the user's attributes, such as age, occupation, affiliation (for example, company name or department name), or job title.

[0032] The user information also includes, for example, behavior information about the user's behavior based on the behavior suggestion information, which will be described later.

[0033] The second generation request generation unit 140 generates second generation request information that is evaluated to be of higher quality than the first generation request information based on generation request generation rules for generating generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and the first generation request information, and stores the generated second generation request information in the memory unit 110.

[0034] The generation request information that enables appropriate content to be generated includes, for example, a plurality of predetermined elements. The plurality of elements include, for example, "assigning a job title to the content generator 300," "communicating information that the user does not want to be included in the generated content," "setting the size of the content (e.g., the number of characters, the amount of data)," "showing an example to the content generator 300," and "clarifying the intent and background of the question." The generation request generation rule is, for example, a rule that corresponds to the plurality of elements.

[0035] The generation request evaluation rule may be, for example, a rule that evaluates the quality of the generation request information as high if the data amount (e.g., number of characters) of the generation request information is within an appropriate data amount range, or a rule that evaluates the quality of the generation request information as high if it contains specified elements depending on whether or not multiple elements corresponding to the generation request generation rule are present.

[0036] The generation request generation rule and the generation request evaluation rule may be different rules, for example, depending on the purpose of the generation request information, or more specifically, depending on the content to be generated based on the generation request information (specifically, for example, the nature of the content). For example, if the content to be generated based on the generation request information is text data, the generation request generation rule and the generation request evaluation rule may be rules that can generate and evaluate generation request information that can generate text data containing more specific content. Also, if the content to be generated based on the generation request information includes visual content (for example, in the case of a flyer), the generation request generation rule and the generation request evaluation rule may be rules that can generate and evaluate generation request information that can generate content that is more visually appealing to the viewer or content that takes universal design into consideration.

[0037] For example, the second generation request generator 140 first evaluates the presence or absence of multiple elements in the first generation request information that correspond to the generation request generation rules based on the generation request generation rules and the first generation request information, and identifies elements that are not included in the first generation request information.The second generation request generator 140 then generates second generation request information that supplements the missing elements and is evaluated to be of higher quality than the first generation request information based on the generation request evaluation rules.This allows the second generation request generator 140 to generate second generation request information that can generate more appropriate content.

[0038] Specifically, for example, if the first generation request information is "Generate 10 types of flyer designs to encourage people to undergo cancer screening," the second generation request generator 140 first identifies, for example, an element "setting the content size (e.g., number of characters, amount of data)" as an element not included in the first generation request information. Then, the second generation request generator 140 generates, for example, second generation request information "Generate 10 types of flyer designs to encourage people to undergo cancer screening, A4-sized posters with a text ratio of 20% to 40%," supplemented with the element "setting the content size (e.g., number of characters, amount of data)."

[0039] At this time, the second generation request generation unit 140 may, for example, refer to generation request information that the user has used in the past and generate second generation request information that supplements elements not included in the first request information.

[0040] The second generation request generator 140 may also generate multiple pieces of second generation request information based on one piece of first generation request information, which allows the information processing system 100 to generate action suggestion information (described later) based on the variation in the generated pieces of second generation request information (e.g., the variation in the content of each piece of second generation request information).

[0041] The second generation request generator 140 can also generate second generation request information based on the user information. In this case, the second generation request generator 140 generates second generation request information that supplements, for example, elements not included in the first generation request information based on the user information. More specifically, for example, if the user information indicates that the user belongs to the legal department, the user is likely to desire content of a quality comparable to that created by a legal expert (e.g., a veteran legal professional or lawyer). Therefore, the second generation request generator 140 can generate second generation request information that assigns the content generator 300 the role of a "legal expert," for example.

[0042] The second generation request generator 140 can also generate second generation request information based on predetermined behavioral factors. In this case, the second generation request generator 140 generates second generation request information by, for example, supplementing elements not included in the first generation request information based on the predetermined behavioral factors. Hereinafter, factors defined by the Integrated Behavioral Model (IBM) (also referred to as "IBM factors") will be exemplified as the behavioral factors. However, the behavioral factors may be any factors related to human behavioral intentions, such as factors defined by behavioral models other than IBM. Examples of behavioral factors include experiential attitude, instrumental attitude, injunctive norm, descriptive norm, perceived control, self-efficacy, knowledge, skills, salience of the behavior, environmental constraints, and habit. If the first generation request information does not include any element related to any of the above-mentioned behavioral factors, the second generation request generator 140 can generate second generation request information for stimulating a predetermined behavioral factor (e.g., "importance of behavior"). This allows the user to obtain content that is highly effective in encouraging people to take action.

[0043] If the first generation request information includes an element related to any of the aforementioned behavioral factors, the second generation request generation unit 140 can generate second generation request information to assign to the content generation device 300 the role of stimulating a behavioral factor (e.g., “environmental constraints”) different from the behavioral factor (e.g., “importance of behavior”) included in the first generation request information.

[0044] The second generation request generator 140 can generate second generation request information related to each of a plurality of behavioral factors based on one piece of first generation request information. For example, the second generation request generator 140 can generate multiple pieces of second generation request information to assign to the content generator 300 the role of stimulating each of the behavioral factors, namely, "self-efficacy," "knowledge," "importance of behavior," and "environmental constraints."

[0045] The content acquisition unit 150 acquires the first content generated based on the first generation request information and the second content generated based on the second generation request information, and stores the acquired first content and second content in the memory unit 110.

[0046] For example, the information processing system 100 outputs first generation request information and second generation request information to the content generator 300. The content generator 300 generates a first content based on the first generation request information and generates a second content based on the second generation request information. The content generator 300 then outputs the first content and the second content to the information processing system 100, and the content acquisition unit 150 acquires the first content and the second content.

[0047] The content evaluation unit 160 evaluates each of the first content and the second content based on content evaluation rules for evaluating content, generates evaluation result information relating to the results of the evaluation, and stores the evaluation result information in the storage unit 110 .

[0048] For example, based on content evaluation rules, the content evaluation unit 160 may evaluate content (e.g., text) as low quality if the content is general, and may evaluate content (e.g., text) as high quality if the content is distinctive. Here, whether or not the content is distinctive may be evaluated based on, for example, the proportion of proper nouns contained in the content. In other words, the higher the proportion of proper nouns contained in the content, the more distinctive the content may be evaluated to be.

[0049] For example, content may be evaluated as being of high quality if it is composed of multiple sentences and the similarity of the meaning of each sentence is low and the density of information is high, if the proportion of kanji and hiragana used is appropriate and the sentences are highly readable, if the content is appropriate for the context even when translated into another language, or if the content includes fonts, sizes, shapes, or colors that take universal design into consideration.

[0050] The content evaluation rule may be, for example, correspondence information indicating the correspondence between a plurality of elements for evaluating content and the weight of each element, which are set in advance. Alternatively, the content evaluation rule may be, for example, an evaluation model that inputs content and outputs a score indicating the evaluation result of the content.

[0051] The content evaluation unit 160 calculates, for example, scores indicating the evaluation results of each of the first content and the second content based on the content evaluation rules.

[0052] 3 is a diagram showing an example of evaluation result information stored in the storage unit 110. The evaluation result information stored in the storage unit 110 includes, for example, an evaluation ID, a first score, and a second score. The evaluation ID is, for example, information that identifies the evaluation result information stored in the storage unit 110. The first score and the second score are, for example, scores that indicate the evaluation results of the first content and the second content, respectively. The first score and the second score may be, for example, quantitative scores indicated using numerical values, or may be qualitative scores (for example, "very good", "good", etc.).

[0053] The user score calculation unit 170 calculates a user score of the user who uses the user device 200 based on the result of the evaluation by the content evaluation unit 160 .

[0054] The user score calculated by the user score calculation unit 170 is, for example, a score indicating the user's ability to create generation request information for generating appropriate content. That is, the higher the first score calculated by the content evaluation unit 160, the higher the user score calculated by the user score calculation unit 170. Furthermore, based on the first score and the second score, for example, the higher the first score is compared to the second score, the higher the user score calculated by the user score calculation unit 170.

[0055] The user score calculation unit 170 may calculate the user score based on, for example, the evaluation results of a plurality of pieces of content generated based on a plurality of pieces of generation request information created by the user in the past, thereby enabling the information processing system 100 to calculate the user score based on the user's creation results of the generation request information.

[0056] The user score calculation unit 170 may also calculate the user score based on, for example, the track record of evaluations of content generated based on generation request information created by other users. In this case, for example, the user score calculation unit 170 may calculate the user score based on a statistical value (e.g., the degree of deviation from the average value) of evaluations of content generated based on generation request information created by a first user in a distribution of evaluations of multiple content items generated based on generation request information created by multiple users, including a specific first user. This allows the information processing system 100 to evaluate the ability of users in a specific group to create generation request information as a user score.

[0057] The action proposal generation unit 180 generates action proposal information regarding action proposals related to the first generation request information for the user using the user device 200 based on the results of the evaluation by the content evaluation unit 160, and stores the generated action proposal information in the memory unit 110.

[0058] The action suggestion information generated by the action suggestion generation unit 180 may be, for example, at least one of action suggestion information that suggests proceeding with processing based on the first generation request information, action suggestion information that suggests proceeding with processing based on the second generation request information, and action suggestion information that suggests modifying the first generation request information.

[0059] The action suggestion information proposing to proceed with the processing based on the first generation request information may include, for example, display information for displaying a “continue” button that prompts the user to proceed with the processing based on the first generation request information on the user device 200. In this case, when the user presses the “continue” button, the first content generated based on the first generation request information may be displayed on the user device 200.

[0060] The action suggestion information may also include display information for displaying the first score. The action suggestion information may also include display information for displaying information indicating whether the first generation request information can generate content of a predetermined quality (e.g., content whose evaluation result based on content evaluation rules is equal to or exceeds a predetermined threshold). This allows a user referring to the display of the action suggestion information to refer to at least one of the first score and the information indicating whether the first generation request information can generate content of a predetermined quality as information for deciding whether to press the "Continue" button.

[0061] The action suggestion information proposing to proceed with processing based on the second generation request information may include, for example, display information for displaying a "See Revision Suggestion" button on the user device 200, which prompts the user to refer to the second generation request information. In this case, the second generation request information may be displayed on the user device 200 when the user presses the "See Revision Suggestion" button. This allows the user to use the second generation request information that is expected to generate more appropriate content. The action suggestion information may also include display information for displaying a second score. In this case, the information processing system 100 may provide the second generation request information to the user on the condition that the user provides a predetermined value (e.g., money, points, etc.). This allows the administrator of the information processing system 100 to receive benefits based on the provision of the second generation request information.

[0062] The action suggestion information proposing to modify the first generation request information may include, for example, display information for displaying a "Modify" button on the user device 200 to prompt the user to modify the first generation request information. In this case, when the user presses the "Modify" button, a modification field for modifying the first generation request information may be displayed on the user device 200. The action suggestion information proposing to modify the first generation request information may be, for example, information that does not include the content of the second generation request information (e.g., the content of the prompt). This allows the information processing system 100 to prompt the user to voluntarily modify the first generation request information. The action suggestion information may also include display information for displaying a third score indicating an evaluation result of third content that may be generated based on the third generation request information described below. The action suggestion information may also include display information for displaying information indicating elements to be modified or added to the first generation request information based on, for example, a generation request evaluation rule (e.g., "A better generation result will be obtained by inputting additional information about element A").

[0063] Next, a specific example of the process of generating action suggestion information by the action suggestion generator 180 will be described.

[0064] If the first score is higher than the second score, the action suggestion generator 180 can generate action suggestion information that suggests proceeding with the process based on the first generation request information, for example.

[0065] Furthermore, if the second score is higher than the first score, the action suggestion generator 180 can generate action suggestion information that suggests proceeding with the process based on the second generation request information, for example.

[0066] Furthermore, if the second score is higher than the first score, the action suggestion generator 180 can generate action suggestion information that suggests modifying the first generation request information, for example.

[0067] Furthermore, the action suggestion generator 180 may generate action suggestion information further based on the quality of the first generation request information and the quality of the second generation request information, which are based on the generation request evaluation rule.

[0068] Specifically, if the quality of the first generation request information is evaluated to be higher than the quality of the second generation request information based on the generation request evaluation rules, the action proposal generation unit 180 can generate action proposal information that suggests, for example, proceeding with processing based on the first generation request information.

[0069] Furthermore, if the quality of the second generation request information is evaluated to be higher than the quality of the first generation request information based on the generation request evaluation rules, the action proposal generation unit 180 can generate, for example, action proposal information that suggests proceeding with processing based on the second generation request information, or action proposal information that suggests modifying the first generation request information.

[0070] The action suggestion generator 180 may generate action suggestion information based on a likelihood of improvement of the first generation request information, which is evaluated based on the generation request evaluation rule. Here, the likelihood of improvement of the first generation request information is, for example, a degree of improvement in content quality from the first content corresponding to the first generation request information, in a third content corresponding to third generation request information that can be generated by modifying the first generation request information.

[0071] For example, if the quality of the second generation request information is evaluated to be higher than the quality of the first generation request information by a predetermined threshold or more, the information processing system 100 may evaluate the likelihood of improvement of the first generation request information as high; or, for example, if the quality of the second generation request information is higher than the quality of the first generation request information but the difference is smaller than a predetermined threshold (in other words, if the quality of the first generation request information and the quality of the second generation request information are about the same), the information processing system 100 may evaluate the likelihood of improvement of the first generation request information as low.

[0072] Furthermore, when the first generation request information is evaluated as having a high likelihood of improvement based on the generation request evaluation rules, the action proposal generator 180 can generate, for example, action proposal information that suggests proceeding with processing based on the second generation request information or action proposal information that suggests modifying the first generation request information. In this way, when generation request information that can generate content of higher quality than the first content is expected, the information processing system 100 can suggest to the user that the second generation request information be adopted or the first generation request information be modified.

[0073] Furthermore, when the first generation request information is evaluated as having a low likelihood of improvement based on the generation request evaluation rules, the action proposal generator 180 can generate, for example, action proposal information that suggests proceeding with the processing based on the first generation request information. As a result, when the first generation request information and the second generation request information have similar qualities, even if the quality of the first generation request information is lower than the quality of the second generation request information, the information processing system 100 can determine that there is no significant problem with the quality of the first content and generate action proposal information that suggests proceeding with the processing based on the first generation request information.

[0074] Furthermore, the action suggestion generating unit 180 can generate action suggestion information further based on the user score.

[0075] Specifically, for example, if the user score is higher than a predetermined threshold and the second score is higher than the first score, the action suggestion generator 180 can generate action suggestion information that suggests modifying the first generation request information. This allows the information processing system 100 to generate action suggestion information according to the user score, and for example, if the user score is high, that is, if the user has high capabilities to create and modify generation request information, the information processing system 100 can encourage the user to voluntarily modify the first generation request information.

[0076] Furthermore, the action suggestion generator 180 can generate action suggestion information that suggests proceeding with processing based on the first generation request information or the second generation request information, for example, if the user score is lower than a predetermined threshold and the second score is higher than the first score. This allows the information processing system 100 to generate action suggestion information according to the user score. For example, if the user score is low, that is, if the user's ability to create generation request information is low, the information processing system 100 can determine that the user is unlikely to correct the first generation request information and suggest proceeding with processing based on the first generation request information, or can convey to the user second generation request information that can be evaluated as a so-called correction example and suggest proceeding with processing based on the second generation request information.

[0077] Furthermore, the action proposal generator 180 can generate action proposal information further based on the generation request evaluation rules and the user score. In this case, the action proposal generator 180 can generate action proposal information based on, for example, the likelihood of improvement of the first generation request information evaluated based on the generation request evaluation rules and the user score.

[0078] Specifically, when the first generation request information is evaluated as having a low likelihood of improvement based on the generation request evaluation rules and the user score is equal to or greater than a predetermined threshold, the action suggestion generator 180 can generate action suggestion information that suggests correcting the first generation request information. This allows the information processing system 100 to determine that a user with a user score equal to or greater than the predetermined threshold is likely to correct the first generation request information, and to encourage the user to voluntarily correct the first generation request information.

[0079] Furthermore, when the first generation request information is evaluated as having a low likelihood of improvement based on the generation request evaluation rules and the user score is equal to or less than a predetermined threshold, the action proposal generator 180 can generate, for example, action proposal information proposing to proceed with processing based on the first generation request information or action proposal information proposing to proceed with processing based on the second generation request information. As a result, for a user with a user score equal to or less than the predetermined threshold, the information processing system 100 can determine that the user is unlikely to correct the first generation request information, taking into consideration the possibility that correcting the first generation request information may actually deteriorate the quality of the content, and can propose to proceed with processing using the first generation request information as is, or to proceed with processing based on the second generation request information.

[0080] In addition, the action suggestion generation unit 180 can generate action suggestion information based on the degree of improvement expected from the first generation request information, which is evaluated based on the user score and is further based on the degree of improvement expected from the third generation request information that can be generated by the user modifying the first generation request information.

[0081] Specifically, first, the action proposal generator 180 generates third generation request information based on the first generation request information and the user score. At this time, the action proposal generator 180, for example, predicts, so to speak, third generation request information that can be generated by the user modifying the first generation request information based on the user score, and generates the third generation request information.

[0082] Here, the action proposal generator 180 may generate the third generation request information by, for example, transmitting and receiving data with a prompt generation device. The prompt generation device is an information processing device that generates generation request information different from the generation request information based on the generation request information, and includes, for example, a server device that provides so-called generative artificial intelligence (AI). In this case, the action proposal generator 180 may, for example, transmit the first generation request information to the prompt generation device and receive the third generation request information generated in the prompt generation device from the prompt generation device.

[0083] Furthermore, the action suggestion generator 180 may, for example, set in advance a correspondence relationship between the user score and a pattern of corrections to the generation request information, and transmit the correspondence relationship and the first generation request information to the prompt generation device. This allows the third generation request information to be predicted by simulating, so to speak, the corrections made by the user according to the user score.

[0084] Next, the action proposal generator 180 evaluates the likelihood of improvement from the first generation request information based on the first generation request information and the third generation request information. At this time, the action proposal generator 180 may evaluate the quality of the first generation request information and the quality of the third generation request information based on a generation request evaluation rule, for example, to evaluate the likelihood of improvement of the third generation request information from the first generation request information. Specifically, if the quality of the third generation request information is higher than the quality of the first generation request information, the likelihood of improvement of the third generation request information from the first generation request information may be evaluated as high. Then, if the likelihood of improvement is high, the action proposal generator 180 can generate action proposal information that suggests modifying the first generation request information. This allows the information processing system 100 to generate action proposal information by, so to speak, predicting third generation request information that may be generated by a user.

[0085] The action suggestion generator 180 can generate the action suggestion information further based on the cost of modifying the first generation request information to generate the third generation request information, which is evaluated based on the user score. Here, the cost of modification may be, for example, the time required to modify the first generation request information or the amount of data (e.g., the number of characters) to be added, modified, or deleted when generating the third generation request information.

[0086] Specifically, the information processing system 100 may, for example, evaluate the higher the user score, the lower the cost of correction, and may also evaluate the lower the user score, the higher the cost of correction. The action suggestion generator 180 may generate action suggestion information that suggests correcting the first generation request information, for example, the higher the user score, and may suggest proceeding with processing based on the first generation request information or the second generation request information, for example, the lower the user score.

[0087] Furthermore, the action suggestion generator 180 can generate action suggestion information based on the variation in the plurality of pieces of second generation request information generated by the second generation request generator 140 .

[0088] Here, the variation in the plurality of pieces of second generation request information may be, for example, the variation in the content of each piece of second generation request information. The variation in the content of each piece of second generation request information may be, for example, the presence or absence of multiple elements corresponding to the generation request generation rule, or the amount of content of each of the multiple elements (e.g., the amount of characters). The variation in the content of each piece of second generation request information may be calculated based on existing technology (e.g., natural language processing technology).

[0089] When the variation in the plurality of pieces of second generation request information is large, the action proposal generator 180 can generate, for example, action proposal information that suggests modifying the first generation request information. As a result, when the variation in the plurality of pieces of second generation request information is large, the information processing system 100 can determine that the likelihood of modifying the first generation request information is high and encourage the user to voluntarily modify the first generation request information. Furthermore, when the variation in the plurality of pieces of second generation request information is small, the action proposal generator 180 can generate, for example, action proposal information that suggests proceeding with processing based on the first generation request information or action proposal information that suggests proceeding with processing based on the second generation request information. As a result, when the variation in the plurality of pieces of second generation request information is small, the information processing system 100 can determine that the likelihood of modifying the first generation request information is low and propose proceeding with processing based on the first generation request information or the second generation request information.

[0090] Furthermore, the action suggestion generator 180 can generate action suggestion information further based on the action information.

[0091] Specifically, the information processing system 100 first generates action suggestion information for the user. Next, the user refers to the action suggestion information and takes an action based on the action suggestion information (e.g., whether or not to correct the generation request information), and the information processing system 100 acquires action information related to the user's action based on the action suggestion information. The action suggestion generator 180 then generates the action suggestion information based on the action information. In other words, the action suggestion generator 180 can generate action suggestion information based on the user's track record of actions based on action suggestion information provided to the user in the past.

[0092] More specifically, for example, based on the action suggestion information, the action suggestion generation unit 180 may generate action suggestion information that suggests modifying the first generation request information for a user who has a strong track record of taking actions in accordance with the action suggestion information.

[0093] Here, the behavioral information may be, for example, information regarding the time spent referring to the behavioral suggestion information, eye movements, cursor movements, whether or not operations such as clicking were performed when referring to the behavioral suggestion information, and evaluation of the behavioral suggestion information (for example, whether or not the "Like" button was clicked).

[0094] Furthermore, the action suggestion generator 180 can generate action suggestion information based on the action information of other users, thereby enabling the information processing system 100 to generate action suggestion information taking into account the track record of the actions of other users.

[0095] Specifically, the action suggestion generation unit 180 may generate, as action suggestion information, behavioral information of other users with similar user scores (e.g., the percentage of times the first generation request information was revised), information regarding the quality of the content acquired by the other users (e.g., the percentage of times the content improved as a result of the revision of the first generation request information, or the percentage of times the content acquired as a result of the revision of the first generation request information was positively evaluated, for example, as a "like").

[0096] In this way, if the acquisition of content through generation request information is considered to be an investment, in which content is acquired as a return obtained in response to the investment of resources in generating, modifying, and providing the generation request information, then the action suggestion generation unit 180 can be considered to be generating action suggestion information as information for making investment decisions.

[0097] That is, the action proposal generator 180 can generate, for example, action proposal information suggesting that processing be carried out based on the first generation request information, as information for the user to make an investment decision that the user's investment in modifying the first generation request information or creating new generation request information is not commensurate with the return obtained in response to the resource investment. The action proposal generator 180 can also generate action proposal information suggesting that processing be carried out based on the second generation request information, as information for the user to determine that investing resources in utilizing the second generation request information is a more reasonable investment decision than investing resources in modifying the first generation request information. The action proposal generator 180 can also generate action proposal information suggesting that the user modify the first generation request information, as information for the user to determine that investing resources in modifying the first generation request information is a more reasonable investment decision. In other words, the action proposal generator 180 can generate action proposal information by functioning as an ROI predictor that predicts the degree of return on investment (ROI) corresponding to the user's resource investment.

[0098] The action suggestion output unit 190 outputs action suggestion information.

[0099] The action suggestion output unit 190 can output the action suggestion information to, for example, the user device 200 .

[0100] Furthermore, the action suggestion output unit 190 may output, for example, action suggestion information including display information for displaying buttons on the screen of the user device 200. The user device 200 acquires the display information and displays, for example, buttons such as "Continue," "See proposed revision," or "Edit" on the screen of the user device 200.

[0101] FIG. 4 is a flowchart showing an example of processing in the information processing system 100.

[0102] First, the first generation request acquisition unit 120 acquires first generation request information (S401). The second generation request generation unit 140 generates second generation request information (S402). The content acquisition unit 150 acquires the first content and the second content (S403). The content evaluation unit 160 evaluates the first content and the second content (S404). The action proposal generation unit 180 generates action proposal information, and the action proposal output unit 190 outputs the action proposal information (S405).

[0103] Fig. 5 is a flowchart showing an example of processing in the information processing system 100. The flowchart shown in Fig. 5 shows an example of processing for generating second generation request information based on user information.

[0104] First, the user information acquisition unit 130 acquires user information (S501), and the second generation request generation unit 140 generates second generation request information further based on the user information (S502).

[0105] Fig. 6 is a flowchart showing an example of processing in the information processing system 100. The flowchart shown in Fig. 6 shows an example of processing for generating action suggestion information based on a user score.

[0106] First, the user score calculation unit 170 calculates a user score based on the result of the evaluation by the content evaluation unit 160 (S601). The action proposal generation unit 180 generates action proposal information based on the user score, and the action proposal output unit 190 outputs the action proposal information (S602).

[0107] Next, an example of a hardware configuration in which the information processing system 100 is realized by a computer 700 will be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of the hardware configuration of the computer 700.

[0108] As shown in FIG. 7, a computer 700 includes, for example, a processor 701, a memory 702, a storage device 703, an input I / F unit 704, a data I / F unit 705, a communication I / F unit 706, and a display device 707.

[0109] Computer 700 may be, for example, a server computer, a personal computer (e.g., desktop, laptop, tablet, etc.), a media computing platform (e.g., cable, satellite set-top box, digital video recorder, etc.), a handheld computing device (e.g., PDA, email client, etc.), or some other type of computing or communications platform.

[0110] The processor 701 is a control unit that controls various processes in the computer 700 by executing programs stored in the memory 702 .

[0111] The memory 702 is a storage medium such as a RAM (Random Access Memory), etc. The memory 702 temporarily stores the program code of the program executed by the processor 701 and data required when the program is executed.

[0112] The storage device 703 is a non-volatile storage medium such as a hard disk drive (HDD), flash memory, etc. The storage device 703 stores an operating system and various programs for realizing the above-mentioned components.

[0113] The input I / F unit 704 is a device for receiving input from a user. The input I / F unit 704 is, for example, a keyboard, a mouse, a touch panel, various sensors, a wearable device, etc. The input I / F unit 704 may be connected to the computer 700 via an interface such as a USB (Universal Serial Bus).

[0114] The data I / F unit 705 is a device for inputting data from outside the computer 700. The data I / F unit 705 is, for example, a drive device for reading data stored in various storage media. The data I / F unit 705 may be provided outside the computer 700. When the data I / F unit 705 is provided outside the computer 700, the data I / F unit 705 is connected to the computer 700 via an interface such as a USB.

[0115] The communication I / F unit 706 is a device for performing data communication via a network such as the Internet, either wired or wirelessly, with devices external to the computer 700. The communication I / F unit 706 may be provided outside the computer 700. When the communication I / F unit 706 is provided outside the computer 700, the communication I / F unit 706 is connected to the computer 700 via an interface such as a USB.

[0116] The display device 707 is a device for displaying various types of information. The display device 707 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, a display of a wearable device, or the like. The display device 707 may be provided outside the computer 700. When the display device 707 is provided outside the computer 700, the display device 707 is connected to the computer 700 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F unit 704, the display device 707 may be configured as an integral part of the input I / F unit 704.

[0117] The above describes one embodiment of the present disclosure. The information processing system 100 can acquire first generation request information from the user device 200, generate second generation request information based on the generation request generation rules, the generation request evaluation rules, and the first generation request information, acquire first content and second content, evaluate each of them, and generate and output action suggestion information based on the evaluation results. This allows the information processing system 100 to suggest actions for data input by the user.

[0118] Furthermore, the information processing system 100 can generate action suggestion information based on the quality of the first generation request information and the quality of the second generation request information, which are based on the generation request evaluation rule. This allows the information processing system 100 to generate action suggestion information based on, for example, the likelihood of improvement of the first generation request information.

[0119] Furthermore, the information processing system 100 can calculate a user score based on the evaluation result and generate action suggestion information based on the user score, thereby allowing the information processing system 100 to suggest an action for the data input by the user, taking into account the user's ability to create first generation request information.

[0120] Furthermore, the information processing system 100 can generate action suggestion information based on the degree of improvement expected from the first generation request information, which is evaluated based on the user score, and further based on the degree of improvement expected from the first generation request information of third generation request information that can be generated by the user modifying the first generation request information. This allows the information processing system 100 to suggest actions for data input by a user, taking into account the user's ability to create the first generation request information and the return to be obtained from the user's resource investment.

[0121] Furthermore, the information processing system 100 can generate action suggestion information based on the cost of modifying the first generation request information to generate the third generation request information, which is evaluated based on the user score. This allows the information processing system 100 to suggest an action for the data input by the user, taking into account the user's ability to create the first generation request information and the cost of modification by the user.

[0122] Furthermore, the information processing system 100 can acquire user information and generate second generation request information further based on the user information, thereby supplementing the first generation request information based on the user information and generating second generation request information that enables the generation of higher quality content.

[0123] Furthermore, the information processing system 100 can acquire behavior information regarding the behavior of at least one first user based on behavior suggestion information proposed to at least one first user, and generate behavior suggestion information further based on the behavior information. This allows the information processing system 100 to learn user behavior based on the behavior suggestion information and generate behavior suggestion information.

[0124] It should be noted that the present embodiment is provided to facilitate understanding of the present disclosure and is not intended to limit the present disclosure. The present disclosure may be modified or improved without departing from the spirit thereof, and equivalents thereof are also included in the present disclosure.

[0125] In addition, in this disclosure, a "unit" does not simply mean a physical means, but also includes cases where the functions of the "unit" are realized by software. Furthermore, the functions of one "unit" or device may be realized by two or more physical means, devices, or software, and the functions of two or more "units" or devices may be realized by one physical means, device, or software.

[0126] REFERENCE SIGNS LIST 100 Information processing system, 110 Storage unit, 120 First generation request acquisition unit, 130 User information acquisition unit, 140 Second generation request generation unit, 150 Content acquisition unit, 160 Content evaluation unit, 170 User score calculation unit, 180 Action proposal generation unit, 190 Action proposal output unit, 200 User device, 300 Content generation device

Claims

1. An information processing system comprising: a first generation request acquisition unit that acquires first generation request information for generating a specified content from a user device; a second generation request generation unit that generates second generation request information that is evaluated to be of higher quality than the first generation request information based on generation request generation rules for generating the generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and the first generation request information; a content acquisition unit that acquires a first content generated based on the first generation request information and a second content generated based on the second generation request information; a content evaluation unit that evaluates each of the first content and the second content based on content evaluation rules for evaluating content; a behavior proposal generation unit that generates behavior proposal information regarding the first generation request information to a user using the user device based on a result of the evaluation; and a behavior proposal output unit that outputs the behavior proposal information.

2. An information processing system as described in claim 1, wherein the action suggestion generation unit generates the action suggestion information further based on the quality of the first generation request information and the quality of the second generation request information based on the generation request evaluation rules.

3. The information processing system of claim 1, further comprising a user score calculation unit that calculates a user score for the user calculated based on the result of the evaluation, and the action suggestion generation unit generates the action suggestion information further based on the user score.

4. The information processing system of claim 3, wherein the action suggestion generation unit generates action suggestion information based further on the degree of expected improvement from the first generation request information, which is evaluated based on the user score, and which is a degree of expected improvement from the first generation request information of third generation request information that can be generated by the user modifying the first generation request information.

5. An information processing system as described in claim 4, wherein the action suggestion generation unit generates the action suggestion information further based on the cost of modifying the first generation request information to generate the third generation request information, which is evaluated based on the user score.

6. An information processing system as described in any one of claims 1 to 5, further comprising a user information acquisition unit that acquires first information regarding the user, wherein the second generation request generation unit generates the second generation request information further based on the first information.

7. An information processing system as described in any one of claims 1 to 5, further comprising a user information acquisition unit that acquires first information regarding the behavior of at least one first user based on the behavior suggestion information to be proposed to at least one first user, wherein the behavior suggestion generation unit generates the behavior suggestion information further based on the first information.

8. An information processing method in which a computer obtains first generation request information for generating a specified content from a user device, generates second generation request information evaluated to be of higher quality than the first generation request information based on generation request generation rules for generating the generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and the first generation request information, obtains a first content generated based on the first generation request information and a second content generated based on the second generation request information, evaluates each of the first content and the second content based on content evaluation rules for evaluating content, generates action suggestion information regarding a suggestion of an action regarding the first generation request information to a user using the user device based on a result of the evaluation, and outputs the action suggestion information.

9. A program for causing a computer to realize the following: a first generation request acquisition unit that acquires first generation request information for generating a specified content from a user device; a second generation request generation unit that generates second generation request information that is evaluated to be of higher quality than the first generation request information based on generation request generation rules for generating generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and the first generation request information; a content acquisition unit that acquires a first content generated based on the first generation request information and a second content generated based on the second generation request information; a content evaluation unit that evaluates each of the first content and the second content based on content evaluation rules for evaluating content; an action proposal generation unit that generates action proposal information regarding a proposal of an action related to the first generation request information to a user using the user device based on a result of the evaluation; and an action proposal output unit that outputs the action proposal information.

Images