Information processing system, information processing method, and program

Abstract

To suggest an action to be input by a user on data.SOLUTION: An information processing system includes: a first generation request acquisition unit which acquires, from a user device, first generation request information for generating predetermined content; a second generation request generation unit which generates second generation request information 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 which 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 which evaluates the first content and the second content on the basis of the content evaluation rule; an action proposal generation unit which generates action proposal information related to proposal for an action on the first generation request information, to a user, based on results of the evaluation; and an action proposal output unit which outputs the action proposal information.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, the use of artificial intelligence (AI) has progressed, and it has become increasingly difficult to provide users with appropriate ways to utilize AI. Techniques for proposing this are known.

[0003] For example, the AI ​​service usage support system described in Patent Document 1 is an AI service The AI ​​service usage support system supports the use of the AI ​​to be evaluated. By sending inquiry data to the service system, the system receives response data and The accuracy of the AI ​​service system is improved by using the correct answer data corresponding to the target data and the response data. and an accuracy evaluation processing unit that calculates the information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-3267 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the AI ​​service usage support system described in Patent Document 1, Evaluate the accuracy of the AI ​​service system by evaluating the output results of the service system. Therefore, the user inputs data into the first AI service system to generate the desired content. If the AI ​​service usage support system cannot obtain the content, it will use the information entered by the user. It is not intended to provide any actionable suggestions for the collected data (e.g., suggestions for corrections) and is not intended to be used by users. The user will use the AI ​​service usage support system to develop a more accurate second AI service system. You need to explore the stem.

[0006] Therefore, the present invention proposes actions for data input by a user. The purpose is. [Means for solving the problem]

[0007] According to one aspect of the present invention, there is provided an information processing system for generating predetermined content from a user device. a first generation request acquisition unit that acquires first generation request information for generating the generation request information; generation rules for generating the generation request information, generation request evaluation rules for evaluating the quality of the generation request information, and and a second generation request information that is evaluated to be of higher quality than the first generation request information based on the first generation request information. a second generation request generating unit that generates request information; and a first generation request generating unit that generates request information based on the first generation request information. A content generating unit that receives the second content generated based on the content and the second generation request information A content acquisition unit and a content evaluation rule for evaluating the first content. a content evaluation unit for evaluating the first content and the second content, and Regarding a proposal of an action regarding the first generation request information to a user who uses a user device, an action proposal generating unit that generates action proposal information to be used for the action proposal; and an action proposal output unit that outputs the action proposal information. And, it is equipped with. Effect of the Invention

[0008] According to the present invention, it is possible to provide action suggestions for data input by a user. Cut. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an overview of processing in an information processing system 100 according to an embodiment of the present invention. [Diagram 2] 1 is a diagram showing a configuration of an information processing system 100 according to an embodiment of the present invention. [Diagram 3] 10 is a diagram showing an example of evaluation result information stored in a storage unit 110. FIG. [Figure 4] 4 is a flowchart showing an example of processing in the information processing system 100. [Diagram 5] 4 is a flowchart showing an example of processing in the information processing system 100. [Figure 6] 4 is a flowchart showing an example of processing in the information processing system 100. [Figure 7] FIG. 7 is a diagram illustrating an example of the hardware configuration of a computer 700. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] A preferred embodiment of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a diagram illustrating an overview of processing in an information processing system 100 according to an embodiment.

[0011] The information processing system 100 acquires first generation request information from the user device and generating second generation request information based on the information; and Evaluating the second content generated based on the content and the second generation request information An information processing system for generating and outputting action proposal information regarding action proposals regarding generation request information It is.

[0012] In recent years, users have been using a predetermined information processing system (for example, a content generating device 30 described later). 0), by providing creation request information (e.g., a prompt) described later, to the If the desired content cannot be acquired, the user modifies the generation request information. and may provide the revised generation request information to a predetermined information processing system again. That is, in order to obtain the desired content, the user must create and modify the generation request information. It requires the investment of resources (e.g., time and effort) in repeatedly correcting and delivering. However, the user may not be able to determine the content generation algorithm of the content generation device 300. It may be difficult to fully understand the system. However, the content desired by the user may not be generated even if the content is modified. In some cases, lower quality content may be generated based on the information requested. The resources invested by the user are wasted.

[0013] In this way, content acquisition through generation request information does not necessarily correspond to the input resources. However, this does not improve the quality of the content that can be acquired. The hope is that more resources will lead to higher quality content. On the other hand, there is a risk that the quality of content will not improve even if the investment resources are increased. The request information is provided to the content generating device 300. Acquiring content through the generation request information as the return obtained in response to the resource input for generating, modifying, and providing the generation request information. If you think of acquiring content as an investment, currently users spend their time It can be said that users are forced to take a gamble with their efforts. The investment efficiency is low, or rational decision-making is difficult due to lack of information to make investment decisions. It is a situation where this is not possible.

[0014] Therefore, the information processing system 100 performs the following operations based on the generation request generation rules and the generation request evaluation rules: Based on the information, second generation request information of higher quality than the first generation request information created by the user is generated; Quality of content generated based on the first generation request information and the second generation request information By evaluating the above, the user can decide whether it is desirable to modify the generation request information or not. The system determines whether it is desirable to make corrections or not, and notifies the user of the generation request information. That is, the information processing system 100 proposes an action to be taken based on, for example, the generation request information. If the return on the resource investment of correction is judged to be small, the generation request information Alternatively, action suggestion information may be generated that suggests proceeding with the process without modifying the If the return on investment in modifying the required information is deemed to be large, Modify and process the request information or the request information generated in the information processing system 100 Action suggestion information that suggests proceeding with the process may be generated based on the second generation request information. .

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

[0016] Next, the information processing system 100 generates a first component based on the first generation request information. The second content 104 generated based on the second generation request information is acquired. The information processing system 100 then stores the first content 103 and the second content 10 4 to generate action suggestion information 105 regarding action suggestions related to the first generation request information. and outputs it to the user device 200.

[0017] In this way, the information processing system 100 can calculate the return on investment. It is possible to control the user's expectations. In other words, the user can modify the generation request information. The expectation of the improvement in the quality of the content that can be generated by the resource investment is expressed as the generation request information. Since the user can know the modification beforehand, the user's expectation can be controlled. In addition, if it is determined that the quality of the content that can be generated will not improve, the user may decide not to waste resources. In other words, the modification of the generation request information can be avoided. Instead of repeatedly modifying the generation request information like a gamble, the information processing system 100 Users can make rational investment decisions based on the processing results, enhancing their self-efficacy In addition, it is possible to prevent the content generation device 300 from easily inputting generation request information. By avoiding this, the power consumption of the content generating device 300 is reduced, and It is expected that the processing speed of the content generation device 300 will improve.

[0018] FIG. 2 is a diagram showing a configuration of an information processing system 100 according to an embodiment of the present invention. The information processing system 100 is a user device 200 and a content generating device 300 connected to the Internet. The information processing system 100 is communicably connected via a network such as a More on this later.

[0019] The user device 200 is an information processing device used by a user of the information processing system 100. , computers, smartphones, tablet devices, personal computers, etc.

[0020] A user accesses the information processing system 100 using the user device 200 and creates a first The user provides the creation request information to the information processing system 100. The action suggestion information is transmitted to the information processing system 100 through the Retrieve from.

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

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

[0023] Generation request information (for example, first generation request information, second generation request information, third generation request information, etc., which will be described later) The requested information may be, for example, information required for generating content in the content generating device 300. Alternatively, the content may be a command (e.g., a prompt) to the content generator 300. The creation request information includes, for example, text data, image data, video data, or audio data. That's fine.

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

[0025] In FIG. 2, the user device 200 and the content generating device 300 are each Although one each is shown, there are a plurality of user devices 200 and content generating devices 300. may be also possible.

[0026] Next, the information processing system 100 will be described in detail. , a storage unit 110, a first generation request acquisition unit 120, a user information acquisition unit 130, a second generation request generation unit generation unit 140, content acquisition unit 150, content evaluation unit 160, user score calculation unit 1 70, an action proposal generating unit 180, and an action proposal output unit 190. For example, the use of a memory area or the execution of a program stored in the memory area by a processor. This can be achieved by:

[0027] The storage unit 110 stores information to be processed in the information processing system 100. 110 stores, for example, user information, first generation request information, second generation request information, and first The content, the second content, the evaluation result information, the user score, and the action suggestion information are stored. It is possible.

[0028] The first generation request acquisition unit 120 receives a predetermined content (first content) from the user device 200. and acquiring first generation request information for generating the content, and storing the acquired first generation request information. The information is stored in 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 flyers to encourage people to take a cancer screening test.” "It may be ".

[0030] The user information acquisition unit 130 acquires user information related to the user, and The information is stored in the storage unit 110.

[0031] The user information includes, for example, attribute information related to the attributes of the user. Information about the user's age, occupation, affiliation (e.g., company name or department name), or job title It may include.

[0032] The user information may be, for example, information about the user's actions based on action suggestion information (to be described later). This includes dynamic information. The behavioral information will be described later.

[0033] The second generation request generating unit 140 generates a generation request generating rule for generating the generation request information. A generation request evaluation rule for evaluating the quality of the generation request information, and and generating second generation request information that is evaluated to be of higher quality than the first generation request information. The second generation request information is stored in the storage unit 110.

[0034] The generation request information that can generate appropriate content includes, for example, a plurality of predetermined elements. The plurality of elements include, for example, "a title is assigned to the content generating device 300" "Information that you do not want to be included in the generated content" "Content "Setting the size (e.g., number of characters, amount of data) of the content," "Content generating device 300 "To provide examples for the question" and "To clarify the intent and background of the question" are included in the request generation rule. The rule is, for example, a rule corresponding to the plurality of elements.

[0035] The generation request evaluation rule may be, for example, based on the amount of data (e.g., the number of characters) of the generation request information. This rule evaluates the quality of the generation request information as high if the amount of data is within an appropriate range. Also, depending on the presence or absence of a plurality of elements corresponding to the generation request generation rule, a predetermined requirement may be generated. Alternatively, the rule may be such that if the generation request information includes an element, the quality of the generation request information is evaluated as high.

[0036] The production request generation rules and the production request evaluation rules may be used to determine, for example, the purpose of the production request information, Specifically, for example, content generated based on generation request information (specifically, , the nature of the content) may be different. For example, When the content to be generated based on the generation request is text data, the generation request generation rule and the generation The generation requirement evaluation rules are generated based on the generation requirement information that can generate text data containing more specific content. The rule may be generated and evaluated based on the generation request information. If the content contains visual content (e.g., flyers), the generation request generation rule The rules and the generation request evaluation rules are designed to create content or Capable of generating and evaluating generation request information that can generate content that takes universal design into consideration It may be a possible rule.

[0037] The second generation request generating unit 140, for example, first generates a generation request generating rule and a first generation request information. Based on the information, the validity of a plurality of elements corresponding to the generation request generation rule in the first generation request information is Evaluate the element not included in the first generation request information to identify the element not included in the second generation request information. The generating unit 140 generates second generation request information by supplementing the missing element, Second generation request information that is evaluated to be of higher quality than the first generation request information based on the evaluation rule. This enables the second generation request generator 140 to generate more appropriate content. It is possible to generate second generation request information that can be generated.

[0038] Specifically, for example, the first generation request information is "Create 10 flyers to encourage people to take cancer screening tests." In the case where the second generation request generating unit 140 receives, for example, the first generation request information The element "Content size (e.g., number of characters, amount of data)" is not included in Then, the second generation request generating unit 140 specifies, for example, the element The second student supplemented with "Setting the size of the content (e.g., number of characters, amount of data)" Request information: "Text ratio 20% to 40%, A4 size poster, cancer screening Generate 10 promotional flyer designs.

[0039] At this time, the second generation request generating unit 140 may generate a generation request information that the user has used in the past. and generating second generation request information by supplementing the elements not included in the first request information with reference to the information. This is also fine.

[0040] In addition, the second generation request generating unit 140 generates a plurality of second generation requests based on one piece of first generation request information. In this way, the information processing system 100 can Variation in the number of pieces of second generation request information (for example, the content of each piece of second generation request information) Based on the variation, action suggestion information described later can be generated.

[0041] The second generation request generating unit 140 also generates second generation request information based on the user information. At this time, the second generation request generating unit 140 can generate, for example, the first generation request. Generate second generated request information by supplementing elements not included in the request information based on the user information. More specifically, for example, if the user information indicates that the user belongs to the legal affairs department, In this case, the user may be required to provide a copy of the Therefore, the second generation request generation unit 140, for example, assigns the content generator 300 the role of “legal expert.” For this purpose, second generation request information can be generated.

[0042] The content acquisition unit 150 acquires the first content and and acquiring a second content to be generated based on the second generation request information, and The first content and the second content are stored in the storage unit 110.

[0043] The information processing system 100, for example, The content generation device 300 outputs the first generation request information to the content generation device 300. and generating a first content based on the second generation request information. The content generating device 300 processes the first content and the second content. The content acquisition unit 150 outputs the first content and the second content to the system 100. Get the .

[0044] The content evaluation unit 160 evaluates the content based on the content evaluation rules. and evaluating each of the first content and the second content, and providing a report on the results of the evaluation. Evaluation result information is generated and stored in the storage unit 110 .

[0045] The content evaluation unit 160 evaluates the content ( For example, if the content of a text is general, the quality of the content is evaluated as low. ,The quality of the content (e.g., text) when its content is ,characteristic. Here, whether the content is distinctive or not can be evaluated as being highly distinctive. For example, the content may be rated based on the percentage of proper nouns contained therein, i.e. The higher the percentage of proper nouns contained in the content, the more distinctive the content is evaluated to be. may be evaluated.

[0046] For example, for content consisting of multiple sentences, the meaning of each sentence is When the similarity is low and the information density is high, the ratio of kanji and hiragana used is appropriate and the text is easy to read. If the text is of high quality, if the content remains relevant in the context even if translated into another language, or The content includes fonts, sizes, shapes, or colors that take universal design into consideration. If the content is more than 100% accurate, the content may be evaluated as being of high quality.

[0047] The content evaluation rules may be, for example, multiple predefined rules for evaluating content. The correspondence information may be information indicating a correspondence relationship between a number of elements and a weight for each element. The content evaluation rule is, for example, inputting a content and evaluating the result of the content. The evaluation model may output a score indicating the above.

[0048] The content evaluation unit 160 evaluates, for example, the first content based on the content evaluation rule. A score indicating the evaluation result of each of the first content and the second content is calculated.

[0049] FIG. 3 is a diagram showing an example of evaluation result information stored in the storage unit 110. The evaluation result information to be stored includes, for example, an evaluation ID, a first score, and a second score. D is, for example, information for identifying the evaluation result information stored in the storage unit 110. The first and second scores are, for example, evaluation results of the first and second contents, respectively. The first score and the second score are, for example, quantitative scores indicated by numerical values. The score may be a qualitative score (e.g., "very good," "good," etc.). This is also fine.

[0050] The user score calculation unit 170 calculates the user score based on the result of the evaluation by the content evaluation unit 160. The user score of the user using the user device 200 is calculated.

[0051] The user score calculated by the user score calculation unit 170 is, for example, a measure of the appropriateness of the user. This score indicates the ability to create generation request information for generating suitable content. That is, the user score calculation unit 170 calculates the first score calculated by the content evaluation unit 160 as being high. The user score calculation unit 170 may calculate a higher user score for a higher number of users. For example, based on the first score and the second score, e.g., if the first score is higher than the second score A higher user score may be calculated.

[0052] The user score calculation unit 170 calculates, for example, a score of a plurality of pieces of generation request information created by a user in the past. The user scores are calculated based on the evaluation results of the multiple contents generated based on each of them. In this way, the information processing system 100 can calculate the core based on the user's generation request information. A user score can be calculated based on the creation history.

[0053] In addition, the user score calculation unit 170 may calculate a score based on, for example, generation request information created by other users. A user score may be calculated according to the evaluation results for the content generated based on the At this time, for example, the user score calculation unit 170 may calculate the score of a plurality of users including a predetermined first user. Distribution of ratings for multiple contents generated based on user-created generation request information Evaluation of content generated based on generation request information created by the first user in the A user score may be calculated based on the statistical value of the score (e.g., the degree of deviation from the average value). In this way, the information processing system 100 can obtain the generated request information of the user in a predetermined group. The user's ability to create information can be evaluated as a user score.

[0054] The action proposal generating unit 180 proposes an action to be taken by the user based on the result of the evaluation by the content evaluating unit 160. A proposal of an action regarding the first generation request information to a user who uses the device 200. Action suggestion information is generated, and the generated action suggestion information is stored in the storage unit.

[0055] The action proposal information generated by the action proposal generating unit 180 is, for example, based on the first generation request information. and proceeding with the processing based on the second generation request information. and action proposal information proposing to modify the first generation request information. The information may be at least one of the proposal information.

[0056] The action suggestion information that suggests proceeding with the process based on the first generation request information may be, for example, The user clicks a “Continue” button to prompt the user to proceed with the process based on the first generation request information. The display information may include information to be displayed on the user device 200. By pressing the "Enter" button, the first content generated based on the first generation request information is , may be displayed on the user device 200.

[0057] The action suggestion information may include display information for displaying the first score. The action suggestion information is generated when the first generation request information is a content of a predetermined quality (e.g., a content evaluation rule Whether or not it is possible to generate content whose evaluation results based on the rule are equal to or greater than a certain threshold The display information may include display information for displaying information indicating whether the action suggestion information is displayed. Users who refer to the display will use the first score, and at least information indicating whether the first generation request information is capable of generating content of a predetermined quality. You can refer to either one.

[0058] The action suggestion information that suggests proceeding with the process based on the second generation request information may be, for example, The user can then press a “Refer to Revision” button on the user device 200 to prompt the user to refer to the second generation request information. In this case, the display information to be displayed on the screen of the user may be included. By pressing the button, the second generation request information may be displayed on the user device 200. The user uses the second generation request information that is expected to generate more appropriate content. The action suggestion information may further include display information for displaying the second score. At this time, the information processing system 100 may receive a predetermined amount of compensation (e.g. The second generation request information may be provided to the user on the condition that the user provides a certain amount of 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. You can receive it.

[0059] The action suggestion information that suggests modifying the first generation request information may, for example, be A "Modify" button is displayed on the user device 200 to prompt the user to modify the first generation request information. In this case, when the user presses the "Edit" button, A correction field for correcting the first generation request information may be displayed on the user device 200. The action suggestion information proposing to modify the generation request information is, for example, in the second generation request information. The information may not include the content of the prompt. The system 100 may prompt the user to voluntarily modify the first generation request information. The action suggestion information may be generated based on third generation request information, which will be described later. The display information may include display information for displaying a third score indicating the evaluation result of the content. The action suggestion information is modified in the first generation request information based on, for example, the generation request evaluation rule. Or information indicating the element to be added (for example, "Add information about element A" will produce better results.") may be included.

[0060] Next, a specific example of the generation process of the action suggestion information by the action suggestion generating unit 180 will be described. do.

[0061] If the first score is higher than the second score, the action suggestion generator 180, for example, Action suggestion information that suggests proceeding with the process based on the request information can be generated.

[0062] Furthermore, if the second score is higher than the first score, the action suggestion generator 180 may, for example, 2. It is possible to generate action suggestion information that suggests proceeding with a process based on the generation request information. Cut.

[0063] Furthermore, if the second score is higher than the first score, the action suggestion generator 180 may, for example, 1 Action suggestion information can be generated that suggests modifying the generation request information.

[0064] In addition, the action proposal generating unit 180 evaluates the quality of the first generation request information based on the generation request evaluation rule. The action suggestion information may be generated further based on the quality of the second generation request information.

[0065] Specifically, the quality of the first generation request information is compared with the quality of the second generation request information based on the generation request evaluation rule. If the quality of the information is evaluated to be higher than the quality of the information, the action proposal generating unit 180 may, for example, Based on the information, action suggestion information that suggests proceeding with the process can be generated.

[0066] In addition, based on the generation request evaluation rule, the quality of the second generation request information is compared with the quality of the first generation request information. If the action proposal is evaluated to be higher than the first action proposal, the action proposal generating unit 180, for example, Action suggestion information that suggests proceeding with the process based on the action suggestion information, or a request to modify the first generation request information It is possible to generate action suggestion information that suggests the user to take action.

[0067] The action proposal generator 180 also generates a first generation request that is evaluated based on the generation request evaluation rule. The action suggestion information may be generated based on the degree of improvement of the request information. The degree of improvement of the generation request information is, for example, In the third content corresponding to the third generation request information, This is the degree of improvement in content quality from the first content.

[0068] For example, the information processing system 100 determines whether the quality of the second generation request information is higher than the quality of the first generation request information. In addition, when the evaluation result is evaluated to be higher than a predetermined threshold, the degree of improvement of the first generation request information is high. For example, the quality of the second generation request information is evaluated to be higher than the quality of the first generation request information. If the difference is smaller than a predetermined threshold (that is, if the first generation request information and the second generation request information are different, (When the quality of the requirement information is the same), the first generated requirement information is evaluated as having a low likelihood of improvement. You may do so.

[0069] In addition, based on the generation request evaluation rule, the first generation request information is likely to be improved. If the action proposal is evaluated, the action proposal generating unit 180 performs processing based on the second generation request information, for example. Action proposal information proposing to proceed or proposing to modify the first generation request information In this way, the information processing system 100 can generate action suggestion information that In other words, generation request information that can generate content of higher quality than the first content is assumed. In this case, the user is offered to adopt the second generation request information or to modify the first generation request information. It is possible to come up with a plan.

[0070] In addition, based on the generation request evaluation rule, the first generation request information is deemed to have a low likelihood of improvement. If the action proposal is evaluated, the action proposal generating unit 180 performs processing based on the first generation request information, for example. This allows the information processing system to generate action suggestion information that suggests the user to proceed. For example, when the quality of the first generation request information and the quality of the second generation request information are about the same, the system 100 In the case where the quality of the first generation request information is lower than the quality of the second generation request information, It is determined that there is no significant problem with the quality of the content, and the process proceeds based on the first generation request information. It is possible to generate action suggestion information that suggests

[0071] In addition, the action suggestion generating unit 180 generates action suggestion information further based on the user score. It is possible.

[0072] Specifically, the action suggestion generating unit 180 detects, for example, that the user score is higher than a predetermined threshold value. And if the second score is higher than the first score, suggest modifying the first generation request information. In this way, the information processing system 100 can generate action suggestion information that can be used to It is possible to generate action suggestion information according to the user score. For example, when the user score is high, In this case, that is, when the user has high ability to create and modify the generation request information, It is possible to encourage the user to voluntarily modify the first generation request information.

[0073] In addition, the action suggestion generating unit 180 may, for example, determine whether the user score is lower than a predetermined threshold and If the second score is higher than the first score, Based on this, action suggestion information can be generated that suggests proceeding with the process. The information processing system 100 can generate action suggestion information according to the user score. For example, when the user score is low, that is, the user's ability to create request information is low. If the first generation request information is low, it is determined that the user is unlikely to modify the first generation request information. 1. Proceed with the process based on the generation request information, or, in other words, a second example that can be evaluated as a correction example. The generation request information is transmitted to the user, and a suggestion is made to proceed with the process based on the second generation request information. It is possible.

[0074] In addition, the action proposal generating unit 180 further generates a request for action based on the action request evaluation rule and the user score. In this case, the action suggestion generating unit 180 can generate action suggestion information by, for example, The degree of improvement of the first generation request information evaluated based on the generation request evaluation rule and the user Based on the user score, action suggestion information can be generated.

[0075] Specifically, based on the generation request evaluation rule, the degree of improvement of the first generation request information is If the user score is rated low, and is above a certain threshold, an action is suggested. The generation unit 180 generates, for example, action suggestion information that suggests modifying the first generation request information. In this way, the information processing system 100 can detect the number of users exceeding a predetermined threshold. For a user having a score, the likelihood of the user correcting the first generation request information is high. and prompts the user to voluntarily correct the first generation request information. .

[0076] In addition, based on the generation request evaluation rule, the first generation request information is deemed to have a low likelihood of improvement. In the case where the user score is evaluated, if the user score is equal to or less than a predetermined threshold, the action suggestion generating unit 180 is, for example, action suggestion information that suggests proceeding with the process based on the first generation request information. Generate action suggestion information that suggests proceeding with the process based on the second generation request information, or the second generation request information. In this way, the information processing system 100 can detect a user speed that is equal to or lower than a predetermined threshold. For users with a core, the content may be generated more quickly by modifying the first generation request information. Considering the possibility of quality degradation, the possibility that the user will modify the first generation request information is low. or to proceed with the process based on the second generation request information. It may be possible to suggest that processing should proceed based on the

[0077] The action proposal generating unit 180 also calculates the degree of improvement likelihood based on the user score. of third generation request information that can be generated by a user's modification of the first generation request information, and generating action suggestion information based on the degree of improvement expected from the first generation request information. It is possible.

[0078] Specifically, first, the action proposal generating unit 180 generates an action proposal based on the first generation request information and the user score. At this time, the action proposal generating unit 180 generates the third generation request information based on the user's Based on the user score, the user may modify the first generation request information to generate a third generation request. The request information is, so to speak, predicted, and the third generation request information is generated.

[0079] Here, the action suggestion generating unit 180 may, for example, transmit and receive data to and from the prompt generating device. The prompt generation device may generate third generation request information based on the generation request information. and an information processing device that generates generation request information different from the generation request information. This includes a server device that provides so-called generative artificial intelligence (AI). In this case, the action suggestion generating unit 180 generates the first generation request information as a prompt, for example. and transmitting third generation request information generated by the prompt generating device to the prompt generating device. The information may be received from a message generating device.

[0080] In addition, the action suggestion generating unit 180 may, for example, A correspondence relationship between the first and second generation requests is set in advance, and the correspondence relationship and the first generation request information are input to a prompt generation device. This allows the user to make corrections based on the user score to be sent to the system. By simulating, the third generation request information can be predicted.

[0081] Next, the action proposal generation unit 180 generates an action proposal based on the first generation request information and the third generation request information. The action proposal generating unit 18 evaluates the degree of improvement expected from the first generation request information. 0, for example, based on the generation request evaluation rule, the quality of the first generation request information and the third generation request Evaluate the quality of the information and evaluate the degree 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, In this case, even if the third generation request information is evaluated as having a high likelihood of improvement from the first generation request information, If the degree of improvement is high, the action proposal generator 180 generates the first generation Action suggestion information that suggests modifying the request information can be generated. The information processing system 100 predicts, so to speak, third generation request information that may be generated by a user. Then, action suggestion information can be generated.

[0082] The action suggestion generating unit 180 also generates third generated request information, which is evaluated based on the user score. generating action suggestion information based on a cost of modifying the first generating request information; Here, the cost of modification can be, for example, The time required to generate the third generation request information, or the amount of data added, modified, or deleted when generating the third generation request information Alternatively, it may be the amount of data (for example, the number of characters) to be recorded.

[0083] Specifically, the information processing system 100, for example, determines whether the correction is required as the user score increases. The lower the user score, the higher the cost of fixing the problem. The action suggestion generating unit 180 may, for example, select the first generation as the user score is higher. Action suggestion information can be generated that suggests modifying the user score. The lower the value, the more likely it is that the process will proceed based on the first generation request information or the second generation request information. It can be suggested.

[0084] The action proposal generating unit 180 also generates a plurality of The action suggestion information can be generated based on the variance in the second generation request information.

[0085] Here, the variation in the plurality of pieces of second generation request information may be, for example, The content of each of the plurality of second generation request information may vary. The variation may be, for example, the presence or absence of multiple elements corresponding to the generation request generation rule, or the presence or absence of the multiple elements. The amount of content of each element (for example, the amount of characters) may be used. The variance of each content is calculated based on existing technology (e.g., natural language processing technology). This may be done.

[0086] When the variation in the plurality of pieces of second generation request information is large, for example, the action proposal generation unit 180 Action suggestion information that suggests modifying the first generation request information can be generated. In this way, when the plurality of pieces of second generation request information vary widely, the information processing system 100 , and judges that there is a high possibility that the first generation request information will be corrected, and requests the user to voluntarily, The action proposal generating unit 180 can prompt the user to correct the first generation request information. When the variation in the generation request information is small, for example, the process is carried out based on the first generation request information. or to proceed with the process based on the second generation request information. The information processing system 100 can generate action suggestion information to be proposed. , when the variation of the plurality of second generation request information is small, the likelihood of correcting the first generation request information The second generation request information is determined to be smaller than the first generation request information and the process is continued. The system can suggest further action based on the information.

[0087] The action suggestion generating unit 180 generates action suggestion information further based on the action information. It is possible.

[0088] 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. , modifying or not modifying the generation request information), and the information processing system 100 Then, behavior information regarding the user's behavior based on the behavior suggestion information is acquired. The plan generating unit 180 generates action suggestion information based on the action information. The suggestion generating unit 180 generates, so to speak, a user's action suggestion based on action suggestion information provided to the user in the past. Action suggestion information can be generated based on the track record of the action.

[0089] More specifically, for example, based on the action suggestion information, the user is asked to take an action in accordance with the action suggestion information. For users who have a large number of actions, the action suggestion generating unit 180 modifies the first action generation request information. The controller 12 may generate action suggestion information that suggests the user to take action.

[0090] Here, the behavior information may include, for example, the time spent to refer to the behavior suggestion information, the behavior suggestion When referring to information, eye movements, cursor movements, clicks, and other operations, and action suggestions Even if the information is related to the evaluation of the information (for example, whether or not the "Like" button was clicked), good.

[0091] In addition, the action suggestion generating unit 180 generates action suggestion information based on the action information of other users. In this way, the information processing system 100 can generate information on the behavior of other users. The action suggestion information can be generated taking into account the track record of the user.

[0092] Specifically, the action suggestion generating unit 180 compares the actions of other users who have the same user score. dynamic information (e.g., the percentage of the first generation request information that has been modified), Information about the quality of the content (e.g., the percentage of content that has improved as a result of modifying the first generation request information) In this case, or a positive evaluation is given to the content obtained by correcting the first generation request information. For example, the percentage of users who gave "like" ratings may be generated as action suggestion information.

[0093] In this way, content acquisition through the generation request information is performed by generating, modifying, and The content is obtained as a return in response to the investment of resources in providing the service. When the investment decision is made, the action proposal generating unit 180 considers the investment decision as information for making the investment decision. This can be considered as generating suggested information.

[0094] That is, the action suggestion generating unit 180 receives a correction or new action suggestion from the user in the first action suggestion generating request information. The investment of resources in creating new generation request information is commensurate with the return obtained from such investment of resources. For example, based on the first generation request information, It is possible to generate action suggestion information that suggests proceeding with the process based on the action suggestion. The plan generating unit 180 is configured to generate the second generation request information rather than inputting resources into the modification of the first generation request information by the user. Users decide that investing resources in utilizing the requirements information is a rational investment decision. As information for the purpose of the present invention, action proposal information that proposes to proceed with the process based on the second generation request information is provided. In addition, the action proposal generating unit 180 can generate the action proposal information in response to the first generation request by the user. To allow users to determine whether investing resources in correcting the information is a rational investment decision generating action suggestion information that suggests modifying the first generation request information as information of the In other words, the action proposal generator 180 can, so to speak, provide a user with a resource input. Predict the degree of return according to the investment. Predict ROI (Return On Investment) By functioning as a container, it is possible to generate action suggestion information.

[0095] The action suggestion output unit 190 outputs action suggestion information.

[0096] The action suggestion output unit 190 is capable of outputting the action suggestion information to, for example, the user device 200. can.

[0097] In addition, the action suggestion output unit 190 displays a button on the screen of the user device 200, for example. The user device 200 may output the action suggestion information including the display information for the action suggestion information. The information is acquired, and a message such as "Continue," "See proposed revisions," or the like is displayed on the screen of the user device 200. displays a "Fix" button.

[0098] FIG. 4 is a flowchart showing an example of processing in the information processing system 100.

[0099] First, the first generation request acquisition unit 120 acquires the first generation request information (S401). The generation request generating unit 140 generates the second generation request information (S402). The content evaluation unit 150 acquires the first content and the second content (S403). The unit 160 evaluates the first content and the second content (S404). The unit 180 generates the action suggestion information, and the action suggestion output unit 190 outputs the action suggestion information. (S405).

[0100] FIG. 5 is a flowchart showing an example of processing in the information processing system 100. The flowchart shown in FIG. 1 illustrates an example of a process for generating second generation request information based on user information.

[0101] First, the user information acquisition unit 130 acquires user information (S501). The generation request generating unit 140 generates second generation request information further based on the user information ( S502).

[0102] FIG. 6 is a flowchart showing an example of processing in the information processing system 100. The flowchart shown in FIG. 1 illustrates an example of a process for generating action suggestion information based on a user score.

[0103] First, the user score calculation unit 170 calculates the score based on the result of the evaluation by the content evaluation unit 160. The action suggestion generating unit 180 calculates a user score based on the user score (S601). Based on the result, the action proposal output unit 190 generates action proposal information and outputs the action proposal information. (S602).

[0104] Next, referring to FIG. 7, the information processing system 100 is realized by a computer 700. An example of the hardware configuration in this case will be described. FIG. 7 shows the hardware configuration of a computer 700. FIG. 1 illustrates an example of a hardware configuration.

[0105] As shown in FIG. 7, a computer 700 includes, for example, a processor 701, a memory 702, and , storage device 703, input I / F unit 704, data I / F unit 705, communication I / F unit 706, and a display device 707.

[0106] The computer 700 may be, for example, a server computer, a personal computer (e.g., (e.g. desktop, laptop, tablet, etc.), media computing platform systems (e.g., cable, satellite set-top boxes, digital video recorders, etc.), hardware handheld computing devices (e.g., PDAs, email clients, etc.); Or it may be any other type of computer or communications platform.

[0107] The processor 701 executes a program stored in the memory 702. This is a control unit that controls various processes in the computer 700.

[0108] The memory 702 is a storage medium such as a RAM (Random Access Memory). 702 is a program code of a program executed by the processor 701, The memory area temporarily stores data required for program execution.

[0109] The storage device 703 is, for example, a hard disk drive (HDD) or a flash memory. The storage device 703 is a non-volatile storage medium. It stores various programs to realize the configuration.

[0110] The input I / F unit 704 is a device for receiving input from a user. The / F unit 704 includes, for example, a keyboard, a mouse, a touch panel, various sensors, and wearables. The input I / F unit 704 is, for example, a USB (Universal Serial Bus) The computer 700 may be connected via an interface such as the above.

[0111] 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 device for transferring data stored in various storage media. The data I / F unit 705 is a drive device for reading data from the computer 700. The data I / F unit 705 may be provided outside the computer 700. In this case, the data I / F unit 705 is connected to a computer via an interface such as a USB. The computer 700 is connected to the

[0112] The communication I / F unit 706 is a device that can communicate with an external device of the computer 700 via wire or wirelessly. A device for data communication via a network such as the Internet. 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 may be, for example, a USB or the like. It is connected to a computer 700 via an interface.

[0113] The display device 707 is a device for displaying various information. For example, LCD displays, organic EL (Electro-Luminescence) displays, wearables, The display device 707 is an external device of the computer 700. When the display device 707 is provided external to the computer 700, The display device 707 is connected to the computer 700 via, for example, a display cable or the like. In addition, when a touch panel is used as the input I / F unit 704, the display device 7 07 may be configured integrally with the input I / F unit 704.

[0114] The information processing system 100 includes a user device, 200, obtains first generation request information, and generates a generation request generation rule, a generation request evaluation rule, and A second generation request information is generated based on the first generation request information, and the first content and the second content are generated. The system acquires the content, evaluates each of them, and generates and outputs action proposal information based on the results of the evaluation. In this way, the information processing system 100 can They can make suggestions for action on the data.

[0115] The information processing system 100 also performs a generation of the first generation request information based on the generation request evaluation rule. The action suggestion information can be generated further based on the quality and the quality of the second generation request information. As a result, the information processing system 100 can, for example, Based on this, action suggestion information can be generated.

[0116] The information processing system 100 also calculates a user score based on the evaluation result. Based on the user score, action suggestion information can be generated. The management system 100 determines whether the user has the ability to create the first generation request information. Suggestions for actions can be made based on the data entered.

[0117] The information processing system 100 also calculates the degree of improvement likelihood based on the user score. Third generation request information that can be generated by a user modifying the first generation request information. Based on the degree of improvement expected from the first generation request information, action suggestion information is generated. In this way, the information processing system 100 can Taking into account the user's production capabilities, the user is given the return on their investment of resources. It can provide actionable suggestions for the data entered by

[0118] The information processing system 100 also generates a third generation request that is evaluated based on the user score. and generating action recommendation information based further on a cost of modifying the first generating request information for generating the information. This allows the user to generate the first generation request information in consideration of the user's ability to generate the first generation request information. , taking into account the cost of correction by the user, the row for the data entered by the user is They can make suggestions for action.

[0119] The information processing system 100 also acquires user information and, based on the user information, In this way, the information processing system 100 can generate the second generation request information. The first generation request information is supplemented based on the user information, and a higher quality content can be generated. 2. Generation request information can be generated.

[0120] The information processing system 100 also provides at least one action proposal to be proposed to the first user. Obtaining behavioral information regarding at least one behavior of the first user based on the suggestion information, and Furthermore, based on the above, action suggestion information can be generated. 100 learns user behavior based on the behavior suggestion information and generates behavior suggestion information. can be done.

[0121] It should be noted that the present embodiment is provided to facilitate understanding of the present invention and does not limit the present invention. The present invention is not intended to be interpreted as being limited to the above-mentioned embodiments, and may be modified or improved without departing from the spirit and scope of the present invention. and equivalents thereof are also included in the present invention.

[0122] In addition, in the present invention, the term "part" does not simply mean a physical means, but rather the " This also includes cases where the functions of a "part" or "unit" are realized by software. Even if the functions of a device are realized by two or more physical means, devices, or software, , two or more "parts" or functions of a device are performed by one physical means, device, or software. It may be realized. [Explanation of symbols]

[0123] 100 Information processing system, 110 Storage unit, 120 First generation request acquisition unit, 130 User User information acquisition unit, 140 second generation request generation unit, 150 content acquisition unit, 160 content 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. A first generation request information for generating a predetermined content is acquired from a user device. A generation request acquisition unit; A generation request generation rule for generating generation request information, and a method for evaluating the quality of the generation request information Based on the generation request evaluation rule and the first generation request information, a second generation request generator that generates second generation request information that is evaluated to be of higher quality than the first generation request information; A first content generated based on the first generation request information and the second generation request information a content acquisition unit that acquires a second content generated based on the The first content and the second content based on a content evaluation rule for evaluating the content. a content evaluation unit that evaluates each of the first content and the second content; The first generation is performed for a user who uses the user device based on a result of the evaluation. an action proposal generating unit that generates action proposal information regarding a proposal of an action related to the request information; an action suggestion output unit that outputs the action suggestion information; An information processing system comprising:

2. The action proposal generation unit evaluates the quality of the first generation request information based on the generation request evaluation rule. and generating the action suggestion information further based on the quality of the second generation request information.

2. An information processing system according to claim 1.

3. A user score of the user is calculated based on the result of the evaluation. a user score calculation unit, The action suggestion generating unit generates the action suggestion information further based on the user score. do, The information processing system according to claim 1 .

4. The action suggestion generation unit is configured to generate a degree of improvement likelihood evaluated based on the user score. Thus, third generation request information that can be generated by the user modifying the first generation request information is Based on the degree of improvement expected from the first generation request information, the action suggestion information is generated. The information processing system according to claim 3 .

5. The action suggestion generating unit generates the third generation request information, which is evaluated based on the user score. the action recommendation is further based on a cost of modifying the first generation request information to generate the action recommendation. The information processing system according to claim 4 , further comprising: a processor configured to generate proposal information.

6. A user information acquisition unit that acquires first information regarding the user, The second generation request generating unit generates the second generation request information based on the first information. Generate, The information processing system according to any one of claims 1 to 5.

7. The at least one action suggestion information is based on the action suggestion information to be suggested to at least one first user. a user information acquisition unit that acquires first information regarding a behavior of the first user; The action suggestion generating unit generates the action suggestion information further based on the first information. 、 The information processing system according to any one of claims 1 to 5.

8. The computer obtaining first generation request information for generating a predetermined content from a user device; A generation request generation rule for generating generation request information, and a method for evaluating the quality of the generation request information Based on the generation request evaluation rule and the first generation request information, generating second generation request information that is evaluated to be of higher quality than the first generation request information; A first content generated based on the first generation request information and the second generation request information and acquiring a second content generated based on the The first content and the second content based on a content evaluation rule for evaluating the content. and evaluating each of the first and second contents; The first generation is performed for a user who uses the user device based on a result of the evaluation. generating action suggestion information relating to action suggestions relating to the requirements information; outputting the action suggestion information; Information processing methods.

9. On the computer, A first generation request information for generating a predetermined content is acquired from a user device. A generation request acquisition unit; A generation request generation rule for generating generation request information, and a method for evaluating the quality of the generation request information Based on the generation request evaluation rule and the first generation request information, a second generation request generator that generates second generation request information that is evaluated to be of higher quality than the first generation request information; A first content generated based on the first generation request information and the second generation request information a content acquisition unit that acquires a second content generated based on the The first content and the second content based on a content evaluation rule for evaluating the content. a content evaluation unit that evaluates each of the first content and the second content; The first generation is performed for a user who uses the user device based on a result of the evaluation. an action proposal generating unit that generates action proposal information regarding a proposal of an action related to the request information; an action suggestion output unit that outputs the action suggestion information; A program to achieve this.

Images