Information processor, information processing method, and program

Abstract

To provide information that helps a user improve his / her prompt creation technique.SOLUTION: An information processor 1 has: a reception part 131 that receives a reception prompt that is a prompt for instructing a generative model as a machine learning model for outputting information based on an instruction described in natural language by taking the instruction as an input, and is a prompt created by a user; a prompt generation part 132 that generates an evaluation request prompt that is a prompt for requesting an evaluation to the reception prompt, and inputs the generated evaluation request prompt to the generation model; an acquisition part 133 that acquires evaluation information indicating an evaluation to the reception prompt generated by the generation model; and a transmission part 134 that transmits information based on the evaluation information to an information terminal of the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] In recent years, large-scale language models (LLMs) have been increasingly used by individuals and companies. It is known that when generating information using a large-scale language model, the quality of the prompt specified by the user has a significant impact on the accuracy of the information output by the large-scale language model. As a method for ensuring the quality of the prompt, a technique for generating sentences to be input as prompts to a large-scale language model is known (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7416390 Summary of the Invention [Problem to be solved by the invention]

[0004] In the prior art, prompts are generated based on templates, but there is a problem that appropriate prompts cannot be generated for applications for which templates are not available. In order to enable large-scale language models to generate appropriate information, it is important to improve the user's prompt creation skills.

[0005] One way to improve users' skills is to provide tutorials and know-how collections, but many users do not refer to these, making it difficult for them to improve their prompt creation skills.

[0006] SUMMARY OF THE INVENTION The present invention has been made in light of these points, and aims to provide information that will enable users to improve their prompt creation skills. [Means for solving the problem]

[0007] An information processing device of a first aspect of the present invention includes a reception unit that receives a reception prompt, which is a prompt created by a user, to instruct a generation model, which is a machine learning model that takes instructions written in natural language as input and outputs information based on the instructions; a prompt generation unit that generates an evaluation request prompt, which is a prompt that requests an evaluation of the reception prompt, and inputs the generated evaluation request prompt to the generation model; an acquisition unit that acquires evaluation information indicating an evaluation of the reception prompt generated by the generation model; and a transmission unit that transmits information based on the evaluation information to the user's information terminal.

[0008] The system may further include an evaluation unit that evaluates the user's skill for creating prompts based on the evaluation information, and the transmission unit may transmit information determined based on the user's skill evaluated by the evaluation unit to the user's information terminal.

[0009] The transmission unit may transmit, to the information terminal of the user, improvement point information indicating an improvement point of the reception prompt generated based on the skill of the user evaluated by the evaluation unit.

[0010] The prompt generation unit may generate an improvement request prompt, which is a prompt for requesting the generation of information indicating improvements to the reception prompt, based on the user's skills evaluated by the evaluation unit and the reception prompt, and input the improvement request prompt into the generation model.The acquisition unit may acquire improvement information, which is information generated by the generation model based on the improvement request prompt, and the transmission unit may transmit the improvement information acquired by the acquisition unit to the user's information terminal.

[0011] The system may further include a determination unit that determines the conditions for providing information to the user based on the user's skills evaluated by the evaluation unit, and the transmission unit may transmit the improvement information to the user's information terminal when the conditions determined by the determination unit are met.

[0012] The reception unit inputs the reception prompt into the generation model, the acquisition unit further acquires answer information which is information generated by the generation model based on the reception prompt, and the transmission unit transmits information for displaying the answer information on the user's information terminal, and may also transmit information to the user's information terminal to instruct the display of the improvement information when the conditions determined by the determination unit are met.

[0013] The evaluation unit may evaluate the user's skill in creating prompts based on a plurality of pieces of evaluation information generated based on a plurality of reception prompts received from the user.

[0014] The evaluation information may indicate the degree to which information required for the generative model to generate answer information is presented in the reception prompt.

[0015] The system further includes a storage unit that stores a condition table that associates improvement point information indicating improvements to the reception prompt with conditions for providing the improvement point information, When the evaluation information satisfies a condition in the condition table for providing improvement information, the transmission unit may transmit improvement information corresponding to the condition to the information terminal of the user.

[0016] An information processing method of a second aspect of the present invention includes the steps of: accepting a reception prompt, which is a prompt created by a user and is executed by a computer to instruct a generation model, which is a machine learning model that takes instructions written in natural language as input and outputs information based on the instructions; generating an evaluation request prompt, which is a prompt requesting an evaluation of the reception prompt, and inputting the generated evaluation request prompt into the generation model; obtaining evaluation information indicating an evaluation of the reception prompt generated by the generation model; and transmitting information based on the evaluation information to the user's information terminal.

[0017] In a third aspect of the program of the present invention, a computer is caused to execute the steps of: accepting a reception prompt, which is a prompt created by a user and is used to instruct a generation model, which is a machine learning model that takes instructions written in natural language as input and outputs information based on the instructions; generating an evaluation request prompt, which is a prompt that requests an evaluation of the reception prompt, and inputting the generated evaluation request prompt into the generation model; obtaining evaluation information indicating an evaluation of the reception prompt generated by the generation model; and transmitting information based on the evaluation information to the user's information terminal. [Effects of the Invention]

[0018] Advantageous Effects of Invention The present invention provides an advantage in that it is possible to provide information that allows users to improve their prompt creation skills. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a diagram for explaining an overview of an information processing system S according to an embodiment. [Figure 2] 1 is a block diagram showing a configuration of an information processing device 1. FIG. [Figure 3] FIG. 10 is a diagram showing an example of a dialogue screen displayed by a reception unit 131. [Figure 4]10 is a diagram showing an example of evaluation information acquired by an acquisition unit 133. FIG. [Figure 5] FIG. 3 is a diagram showing an example of a condition table stored in a storage unit 12. [Figure 6] 10 is a diagram showing an example of a skill determination table stored in the storage unit 12. FIG. [Figure 7] FIG. 3 is a diagram showing an example of a condition table stored in a storage unit 12. [Figure 8] 10 is a diagram showing an example of a timing determination table stored in the storage unit 12. FIG. [Figure 9] FIG. 10 is a diagram showing an example of a dialogue screen displayed by a reception unit 131. [Figure 10] 3 is a flowchart showing the flow of processing in the information processing device 1. DETAILED DESCRIPTION OF THE INVENTION

[0020] [Outline of Information Processing System S] 1 is a diagram illustrating an overview of an information processing system S. The information processing system S is a system for providing an interactive generative AI (Artificial Intelligence) service. The information processing system S includes an information processing device 1, an information terminal 2, and a generative model 3.

[0021] The information processing device 1 is a device for providing a user interface for a user to use the generative model 3. The information processing device 1 receives a prompt from the information terminal 2, inputs the received prompt to the generative model 3, and transmits an answer output by the generative model 3 to the information terminal 2. The information processing device 1 also transmits information for the user to improve the prompt to the information terminal 2.

[0022] The information terminal 2 is a terminal used by a user of the information processing system S. The information terminal 2 is, for example, a smartphone, a tablet, or a personal computer. The information terminal 2 receives a prompt input from the user, transmits the received prompt to the information processing device 1, and displays information acquired from the information processing device 1 on a display unit (not shown).

[0023] The generative model 3 is a machine learning model trained to receive a prompt as input, generate information based on the instruction, and output the information. The prompt is information indicating an instruction to the generative model 3 written in natural language. The generative model 3 is also called a large-scale language model (LLM), and is a neural network used in the field of natural language processing, and is a natural language processing model constructed using a large amount of data set and deep learning technology. In FIG. 1, the generative model 3 operates in a device configured separately from the information processing device 1, but the generative model 3 may also be configured as a part of the information processing device 1.

[0024] The information processing device 1 receives a reception prompt ((1) in FIG. 1). The reception prompt is a prompt created by the user. The information processing device 1 inputs the reception prompt to the generation model 3 ((2) in FIG. 1). The information processing device 1 generates an evaluation request prompt and inputs the generated evaluation request prompt to the generation model 3 ((3) in FIG. 1). The evaluation request prompt is a prompt that requests an evaluation of the reception prompt.

[0025] The information processing device 1 acquires an answer to the reception prompt generated by the generative model 3 ((4) in FIG. 1). The information processing device 1 acquires evaluation information generated by the generative model 3 ((5) in FIG. 1). The evaluation information is an answer generated by the generative model 3 in response to an evaluation request prompt, and indicates the degree to which the information required for the generative model 3 to generate answer information is presented in the reception prompt.

[0026] The information processing device 1 determines the information to be provided to the user based on the acquired evaluation information ((6) in FIG. 1). The information processing device 1 transmits an answer to the reception prompt acquired from the generative model 3 to the information terminal 2 ((7) in FIG. 1). The information processing device 1 transmits the determined information to the information terminal 2 ((8) in FIG. 1). One example of the information transmitted to the information terminal 2 is improvement point information. The improvement point information is information indicating improvements to the reception prompt.

[0027] By configuring the information processing system S in this way, it is possible to provide information that allows users to improve their prompt creation skills.

[0028] In the above example, the explanation is based on the assumption that the reception prompt and the evaluation request prompt are processed by the same generation model 3, but this is not limited to this. The reception prompt and the evaluation request prompt may be configured to be processed by different generation models 3. In this case, the generation model 3 that requests the evaluation request prompt is fine-tuned so that it inputs the prompt based on training data that associates the prompt with the evaluation corresponding to the prompt, and outputs evaluation information about the input prompt.

[0029] [Configuration of information processing device 1] 2 is a block diagram showing the configuration of information processing device 1. Information processing device 1 has a communication unit 11, a storage unit 12, and a control unit 13. Control unit 13 has a reception unit 131, a prompt generation unit 132, an acquisition unit 133, a transmission unit 134, an evaluation unit 135, and a determination unit 136.

[0030] The communication unit 11 is a communication interface for transmitting and receiving data to and from other devices via a network. The storage unit 12 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid State Drive), a hard disk drive, etc. The storage unit 12 stores in advance a program to be executed by the control unit 13.

[0031] The control unit 13 is a processor such as a CPU (Central Processing Unit), and functions as a reception unit 131, a prompt generation unit 132, an acquisition unit 133, a transmission unit 134, an evaluation unit 135, and a determination unit 136 by executing a program stored in the storage unit 12.

[0032] The reception unit 131 receives a reception prompt. As an example, the reception unit 131 displays the interactive screen shown in FIG. 3 on the information terminal 2. The interactive screen is a screen for receiving an input of a reception prompt and displaying information generated based on the reception prompt. The interactive screen displays a text field O1 for inputting the reception prompt, an object O2 for transmitting the reception prompt to the information processing device 1, and an area O3 for displaying a history of the dialogue. When the user inputs the reception prompt in the text field O1 and presses the object O2, the information terminal 2 transmits the input reception prompt to the information processing device 1, and the reception unit 131 accepts it. In the area O3, the received reception prompt and the answer generated by the generation model 3 are displayed in chronological order. When the reception prompt is received, the reception unit 131 inputs the reception prompt to the generation model 3.

[0033] The prompt generation unit 132 generates an evaluation request prompt. As an example, the prompt generation unit 132 generates an evaluation request prompt by combining a sentence for requesting an evaluation of the prompt with the reception prompt received by the reception unit 131. For example, if the reception prompt received by the reception unit 131 is "Tell me about ABC," the prompt generation unit 132 combines the sentence "Please rate the prompt below on a scale of 100 points for each evaluation item" as a sentence requesting an evaluation of the prompt, to generate an evaluation request prompt such as "Please rate the prompt below on a scale of 100 points. Prompt: Tell me about ABC." The prompt generation unit 132 inputs the generated evaluation request prompt into the generation model 3.

[0034] The acquisition unit 133 acquires answer information, which is information generated by the generative model 3 based on the reception prompt. The acquisition unit 133 also acquires evaluation information, which is information generated by the generative model 3 based on the evaluation request prompt. As an example, the evaluation information includes information indicating the degree to which the evaluation criteria for each evaluation item for evaluating the prompt are met. Examples of items for evaluating the prompt include, but are not limited to, "specificity," "clarity of question," "provision of context," and "clarity of purpose."

[0035] "Specificity" indicates whether the prompt specifically provides the content of the question. "Clarity of the question" indicates whether the prompt provided can be clearly determined to be a question. "Provision of context" indicates whether the received prompt and any prompts provided before it provide information for answering the question. "Clarity of purpose" indicates whether the background and purpose of the question are provided. The acquisition unit 133 may store the acquired evaluation information in the memory unit 12 in association with the user ID, and accumulate a history of the evaluation information.

[0036] Fig. 4 is a diagram showing an example of evaluation information. The evaluation information shown in Fig. 4 includes a score for each evaluation item. Instead of a score for each evaluation item, the evaluation information may include information indicating a graded level such as "A," "B," "C," or "D" for each evaluation item.

[0037] The transmitting unit 134 transmits the answer information to the information terminal 2. The transmitting unit 134 controls the display of the answer information on the interactive screen. The transmitting unit 134 transmits information based on the evaluation information to the user's information terminal 2. As an example, the storage unit 12 stores a condition table in which conditions for providing information to the user are associated with improvement point information that is sent when the conditions are met. FIG. 5 is a diagram showing an example of the condition table. In the condition table shown in FIG. 5, the conditions for providing information to the user are determined based on the score of each item in the evaluation items. In the condition table shown in FIG. 5, it is assumed that the score of each item is given from 0 to 100 points, and it is set that improvement point information is provided when the score of each item falls below a threshold. In the condition table, a different threshold may be set for each item.

[0038] When the acquired evaluation information satisfies the conditions indicated in the condition table, the transmission unit 134 transmits improvement point information corresponding to the satisfied conditions to the information terminal 2. In addition, the transmission unit 134 may transmit the acquired evaluation information to the information terminal 2.

[0039] By configuring information processing device 1 in this way, it is possible to provide information that allows users to improve their prompt creation skills.

[0040] The information processing device 1 may be configured to evaluate the skill level of the user based on the evaluation information, and to determine information to be displayed on the information terminal 2 of the user based on the evaluated skill level.

[0041] The evaluation unit 135 evaluates the user's skill for creating prompts based on the evaluation information. As an example, the evaluation unit 135 determines to which of a plurality of stages indicating the level of the user's skill the user belongs based on the evaluation information. As an example, the user's skill level is expressed in four stages: "A," "B," "C," and "D." Here, "A" indicates high skill and "D" indicates low skill. The evaluation unit 135 determines to which stage the user's skill belongs based on the evaluation information.

[0042] As an example, the storage unit 12 stores a skill determination table for determining a user's skill based on the evaluation information. FIG. 6 is a diagram showing an example of the skill determination table stored in the storage unit 12. The evaluation unit 135 refers to the skill determination table and identifies the user's skill level corresponding to the score for each item indicated by the evaluation information. The evaluation unit 135 may store the identified skill level in the storage unit 12 in association with the user ID.

[0043] The transmitting unit 134 transmits information determined based on the user's skill evaluated by the evaluating unit 135 to the user's information terminal 2. In this case, the storage unit 12 stores a condition table that associates the user's skill level, scores for the evaluation items, and improvement information to be provided to the user. FIG. 7 is a diagram showing an example of the condition table in this case. The transmitting unit 134 refers to the condition table shown in FIG. 7 and determines the improvement information to be provided to the user based on the user's skill level and the score indicated by the evaluation information. The transmitting unit 134 transmits the determined improvement information to the information terminal 2.

[0044] The information processing device 1 is configured to evaluate a user's skill when evaluation information has been accumulated a predetermined number of times or more, thereby enabling a more accurate evaluation of the user's skill. The evaluation unit 135 may evaluate the user's skill in creating prompts based on multiple pieces of evaluation information generated based on multiple reception prompts received from the user. In this case, the acquisition unit 133 associates the acquired evaluation information with a user ID for identifying the user to be evaluated and stores it in the storage unit 12. The evaluation unit 135 evaluates the user's skill based on the evaluation information acquired by the acquisition unit 133 and the evaluation information stored in the storage unit 12 in association with the user ID of the user to be evaluated.

[0045] For example, the evaluation unit 135 may refer to a skill determination table based on the average value of the plurality of pieces of evaluation information to identify the skill level of the user. Alternatively, the evaluation unit 135 may evaluate the skill of the user based on the number of times that the degree of each evaluation item included in each piece of evaluation information satisfies a predetermined standard and the number of times that it falls below the predetermined standard.

[0046] The improvement information may be generated by the generative model 3. In this case, the condition table includes conditions for providing the information. The sending unit 134 determines whether to send the improvement information based on the user's skills evaluated by the evaluation unit 135. If the sending unit 134 determines to send the improvement information, the prompt generating unit 132 generates an improvement request prompt based on the user's skills evaluated by the evaluation unit 135 and the reception prompt. The improvement request prompt is a prompt for requesting the generation of information indicating improvements to the reception prompt.

[0047] As an example, the prompt generation unit 132 generates an improvement request prompt by combining a sentence for requesting an improvement, a reception prompt, and the user's skill level. If the reception prompt is "Tell me about ABC" and the user's skill level is C, the prompt generation unit 132 generates an improvement request prompt saying, "Please generate improvements for the following prompt for a user with skill level C. Prompt: Tell me about ABC."

[0048] The prompt generation unit 132 inputs the generated improvement request prompt to the generation model 3. The acquisition unit 133 acquires the improvement information generated by the generation model 3 based on the improvement request prompt. The transmission unit 134 transmits the improvement information acquired by the acquisition unit 133 to the user's information terminal 2. The transmission unit 134 may perform control so that the improvement information is displayed on the interactive screen.

[0049] By configuring information processing device 1 in this way, it is possible to provide information that allows users to improve their prompt creation skills.

[0050] The information processing device 1 may be configured to determine the timing for transmitting improvement point information depending on the skill of the user.

[0051] The determination unit 136 determines conditions for providing information to a user based on the user's skill evaluated by the evaluation unit 135. As an example, the storage unit 12 stores a timing determination table that associates the timing for providing information to a user with each skill level. FIG. 8 is a diagram illustrating an example of the timing determination table stored in the storage unit 12. In the timing determination table, the timing for providing information to a user is set so that the lower the user's skill evaluation, the more likely the user is to receive information. As an example, the timing determination table may be set so that information is not provided to a user with the highest skill level. This configuration allows information to be provided to users who need to be provided with improvements, and prevents users who already have a high skill level from feeling annoyed. The determination unit 136 refers to the timing determination table and determines the timing corresponding to the user's skill level as the timing for providing information to the user. The determination unit 136 associates the determined timing with a user ID for identifying the user and stores them in the storage unit 12.

[0052] When the timing determined by the determination unit 136 is met, the transmission unit 134 transmits the improvement information to the user's information terminal 2. As an example, the transmission unit 134 refers to the history of evaluation information stored in the storage unit 12 and determines whether the timing determined by the determination unit 136 is met. When the evaluation information included in the history of evaluation information meets the timing determined by the determination unit 136, the transmission unit 134 transmits the improvement information to the information terminal 2.

[0053] The information processing device 1 may be configured to allow the user to select whether or not to view the improvement point information. In this case, when the improvement point information is acquired, the information processing device 1 may be configured to present a user interface on an interactive screen for selecting whether or not to view the improvement point information.

[0054] The transmission unit 134 transmits information for displaying the answer information on the user's information terminal 2, and also transmits information for instructing the display of improvement information to the user's information terminal 2 when the condition determined by the determination unit 136 is satisfied. Fig. 9 is a diagram showing an example of an interactive screen displayed on the information terminal 2 in this case. The interactive screen shown in Fig. 9 displays an object O31 for displaying the improvement information transmitted by the transmission unit 134. When the object O31 is pressed, the improvement information is displayed on the interactive screen shown in Fig. 9.

[0055] By configuring the information processing device 1 in this way, an effect is achieved in that the user can refer to the improvement point information at a convenient time.

[0056] The reception screen may be configured to allow the user to select feedback for the improvement information. The feedback is given by the user selecting the number of stars, for example. The storage unit 12 may store the received feedback in association with the improvement information.

[0057] [Processing flow in information processing device 1] 10 is a flowchart showing the flow of processing in the information processing device 1. The flowchart shown in FIG.

[0058] The reception unit 131 displays an interactive screen on the information terminal 2 (S01). The reception unit 131 receives a reception prompt from the information terminal 2 (S02). The reception unit 131 inputs the reception prompt into the generative model 3 (S03).

[0059] The prompt generation unit 132 generates an evaluation request prompt based on the reception prompt (S04), and inputs the generated evaluation request prompt into the generation model 3 (S05).

[0060] The acquisition unit 133 acquires the answer generated by the generative model 3 based on the reception prompt (S06). The acquisition unit 133 acquires the evaluation information generated by the generative model 3 based on the evaluation request prompt (S07). The transmission unit 134 determines information to be provided to the user based on the evaluation information (S08). The transmission unit 134 transmits the determined information to the information terminal 2 (S09).

[0061] The information processing device 1 determines whether or not a termination condition is met (S10). The termination condition is, for example, when the user performs an operation to terminate. If the termination condition is not met (NO in S10), the process returns to S02 and is repeated. If the termination condition is met (YES in S10), the information processing device 1 terminates the process.

[0062] <Modification> In the above description, the information processing device 1 is an example of a server, but the information processing device 1 may be configured as a terminal used by a user. In this case, the reception unit 131 displays an interactive screen on the display unit of the terminal and receives a reception prompt from the input unit of the terminal. The transmission unit 134 is configured to control the display unit of the terminal to display information.

[0063] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which is "Build resilient infrastructure, promote inclusive and sustainable industrialization, and promote innovation and resilience."

[0064] The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by functionally or physically distributing or integrating any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination also have the effects of the original embodiments. [Explanation of symbols]

[0065] 1. Information processing equipment 2. Information terminal 11 Communications Department 12 Storage section 13 Control Unit 131 Reception 132 Prompt Generation Unit 133 Acquisition Department 134 Transmitter 135 Evaluation Department 136 Decision Section

Claims

1. a reception unit that receives a reception prompt, which is a prompt created by a user, to instruct a generative model that is a machine learning model that receives an instruction written in a natural language as input and outputs information based on the instruction; a prompt generation unit that generates an evaluation request prompt, which is a prompt that requests an evaluation of the reception prompt, and inputs the generated evaluation request prompt into the generation model; an acquisition unit that acquires evaluation information indicating an evaluation of the reception prompt generated by the generative model; a transmitting unit that transmits information based on the evaluation information to the information terminal of the user; An information processing device having the above.

2. an evaluation unit that evaluates the user's skill for creating prompts based on the evaluation information; the transmitting unit transmits information determined based on the skill of the user evaluated by the evaluating unit to the information terminal of the user. The information processing device according to claim 1 .

3. the transmitting unit transmits improvement point information indicating an improvement point of the reception prompt generated based on the skill of the user evaluated by the evaluating unit to the information terminal of the user. The information processing device according to claim 2 .

4. the prompt generation unit generates an improvement request prompt, which is a prompt for requesting generation of information indicating improvements to the reception prompt, based on the skill of the user evaluated by the evaluation unit and the reception prompt, and inputs the improvement request prompt into the generation model; the acquisition unit acquires improvement information that is information generated by the generative model based on the improvement request prompt; the transmitting unit transmits the improvement information acquired by the acquiring unit to the information terminal of the user; The information processing device according to claim 3 .

5. a determination unit that determines conditions for providing information to the user based on the skill of the user evaluated by the evaluation unit; the transmitting unit transmits the improvement information to the information terminal of the user when the condition determined by the determining unit is satisfied. The information processing device according to claim 3 .

6. the reception unit inputs the reception prompt into the generative model; the acquisition unit further acquires answer information that is information generated by the generative model based on the reception prompt; the transmitting unit transmits information for displaying the response information on the information terminal of the user, and, when the condition determined by the determining unit is satisfied, transmits information for instructing the display of the improvement information to the information terminal of the user. The information processing device according to claim 5 .

7. the evaluation unit evaluates the prompt creation skill of the user based on a plurality of pieces of evaluation information generated based on each of a plurality of reception prompts received from the user. The information processing device according to claim 2 .

8. the evaluation information indicates a degree to which information necessary for the generative model to generate answer information is presented in the reception prompt; The information processing device according to claim 1 .

9. The system further includes a storage unit that stores a condition table that associates improvement point information indicating improvements to the reception prompt with conditions for providing the improvement point information, the transmitting unit, when the evaluation information satisfies a condition in the condition table for providing improvement information, transmits the improvement information corresponding to the condition to the information terminal of the user; The information processing device according to claim 1 .

10. The computer executes a step of receiving a reception prompt, which is a prompt created by a user and is used to instruct a generative model that is a machine learning model that receives an instruction written in a natural language as input and outputs information based on the instruction; generating an evaluation request prompt, which is a prompt requesting an evaluation of the reception prompt, and inputting the generated evaluation request prompt into the generation model; acquiring evaluation information indicating an evaluation of the reception prompt generated by the generative model; transmitting information based on the evaluation information to an information terminal of the user; An information processing method comprising:

11. On the computer, a step of receiving a reception prompt, which is a prompt created by a user and is used to instruct a generative model that is a machine learning model that receives an instruction written in a natural language as input and outputs information based on the instruction; generating an evaluation request prompt, which is a prompt requesting an evaluation of the reception prompt, and inputting the generated evaluation request prompt into the generation model; acquiring evaluation information indicating an evaluation of the reception prompt generated by the generative model; transmitting information based on the evaluation information to an information terminal of the user; A program that executes the following.

Images