Information processing device, information processing method, and program

Abstract

Help users build their opinions. [Solution] The information processing device 2 includes a sentence acquisition unit 100 that acquires a first sentence related to a user's opinion, an evaluation information acquisition unit 102 that acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and an output unit 104 that outputs information that prompts the user to input a second sentence related to their opinion based on the first evaluation information.

Description

[Technical Field]

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

[0002] Conventionally, there is known a technique for evaluating the logic of user opinions (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-219989 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional techniques have not been able to adequately support users in forming their opinions.

[0005] The present disclosure provides an information processing device, an information processing method, and a program that can support a user in forming an opinion. [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present disclosure includes a sentence acquisition unit that acquires a first sentence related to a user's opinion, an evaluation information acquisition unit that acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and an output unit that outputs information that prompts the user to input a second sentence related to the user's opinion based on the first evaluation information.

[0007] An information processing method according to another aspect of the present disclosure includes a computer acquiring a first sentence related to a user's opinion, acquiring first evaluation information related to an evaluation of the persuasiveness of the first sentence, and outputting information prompting the user to input a second sentence related to the user's opinion based on the first evaluation information.

[0008] A program according to another aspect of the present disclosure causes a computer to acquire a first sentence related to a user's opinion, acquire first evaluation information related to an evaluation of the persuasiveness of the first sentence, and output information prompting the user to input a second sentence related to the user's opinion based on the first evaluation information. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to support users in forming opinions. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram for explaining an overview of a system 1 according to the present embodiment. [Figure 2] 1 is a diagram illustrating an example of a functional configuration of a system 1 according to an embodiment of the present invention. [Figure 3] FIG. 2 is a diagram for explaining an example of the operation of the system 1 according to the present embodiment. [Figure 4] 3 is a diagram for explaining an example of a display screen of the terminal device 3 according to the present embodiment. FIG. [Figure 5] 3 is a diagram for explaining an example of a display screen of the terminal device 3 according to the present embodiment. FIG. [Figure 6] 3 is a diagram for explaining an example of a display screen of the terminal device 3 according to the present embodiment. FIG. [Figure 7] 3 is a diagram for explaining an example of a display screen of the terminal device 3 according to the present embodiment. FIG. [Figure 8] 3 is a diagram for explaining an example of a display screen of the terminal device 3 according to the present embodiment. FIG. [Figure 9] 1 is a diagram illustrating an example of a hardware configuration of a system 1 according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] 1. Overview One of the exemplary purposes of the system 1 according to this embodiment (hereinafter simply referred to as "system 1") is to support the user in formulating opinions. Note that in this embodiment, supporting the user in formulating opinions includes the user learning and / or training a method for formulating opinions.

[0012] In one example, an opinion may be composed of claims, reasons, and specific examples. In this embodiment, the claims, reasons, and specific examples included in an opinion may be collectively referred to as the "contents of the opinion."

[0013] An assertion is the core of an opinion and can also be called a conclusion. A reason can be a logical explanation or evidence supporting an assertion. A concrete example can be an actual example or situation supporting an assertion or reason. For example, an example of an opinion on the topic "Should you eat breakfast every day?" is "You should eat breakfast every day. This is because regular meals promote metabolism and help maintain a healthy weight. Specifically, research has shown that people who habitually eat breakfast have a lower risk of obesity than those who do not." In this example, the part "You should eat breakfast every day" is an example of an assertion. The part "This is because regular meals promote metabolism and help maintain a healthy weight" in the above example is an example of a reason. And the part "Research has shown that people who habitually eat breakfast have a lower risk of obesity than those who do not" in the above example is an example of a concrete example. In this embodiment, "constructing an opinion" can mean creating an opinion on a certain topic that includes such assertions, reasons, and concrete examples.

[0014] It is not always easy to construct a substantial opinion. For example, there may be situations where a person constructing an opinion on a certain topic can intuitively come up with an argument, but cannot quickly come up with reasons and / or specific examples. This situation is likely to arise particularly when the person constructing the opinion must construct the opinion in a language other than their first language (for example, when the person's first language is Japanese and they must construct the opinion in English).

[0015] Debate is one form of training for formulating opinions. However, traditionally, training in formulating opinions through debate has not always been easy, as it requires the person formulating the opinion to have an opponent to debate with, and / or a teacher to evaluate and provide feedback on the content of the debate. Furthermore, because debate involves countering the opponent's opinion, formulating an opinion can be more difficult than simply stating one's own opinion.

[0016] The system 1 can solve the above-described exemplary problem. That is, exemplary effects of the system 1 can be at least one of (1) supporting a user in formulating an opinion including claims, reasons, and specific examples, (2) supporting a user in formulating an opinion in a language different from the user's first language, and (3) supporting a user in formulating an opinion in anticipation of a debate.

[0017] An overview of the operation of the system 1 will be described with reference to Fig. 1. The system 1 includes a terminal device 3 used by a user, an information processing device 2 that executes at least a part of a process for supporting the user in constructing opinions, and a large language model (LLM) server device 4 that hosts an LLM.

[0018] First, the terminal device 3 receives an input of a first text relating to the user's opinion from the user, and transmits the first text to the information processing device 2 (S1). Note that the first text is an example of a first sentence.

[0019] Next, the information processing device 2 generates an instruction to evaluate the persuasiveness of the first text and transmits this instruction to the LLM server device 4 (S2). The LLM server device 4 evaluates the persuasiveness of the first text in accordance with the instruction based on the LLM it hosts, and transmits a response including the result to the information processing device 2 (S3).

[0020] The response includes evaluation information regarding an evaluation of the persuasiveness of the first text. The evaluation information may include information regarding the logic, clarity, and richness of specific examples of the first text. When the logic, clarity, and richness of specific examples of the first text are evaluated as high, it may be said that the first text includes arguments, reasons, and specific examples.

[0021] Next, the information processing device 2 generates information prompting the user to input second text regarding his / her opinion based on the evaluation information, and transmits the information to the terminal device 3 (S4). The second text is an example of a second sentence. In response to this, the terminal device 3 can accept input of the second text from the user.

[0022] The information prompting the user to input the second text is generated based on evaluation information regarding the evaluation of the persuasiveness of the first text. Therefore, the user can reinforce the persuasiveness of the opinion expressed in the first text by referring to the information prompting the user to input the second text. This allows the system 1 to support the user in formulating an opinion that includes assertions, reasons, and specific examples (see (1) of the exemplary effect above).

[0023] In one embodiment, the terminal device 3 accepts input of the first text and the second text in a language other than the user's first language, which allows the system 1 to support the user in formulating opinions in a language other than the first language (see the above-mentioned exemplary effect (2)).

[0024] In one embodiment, the information prompting the user to input the second text may include an opposing opinion to the first text. This configuration allows the system 1 to support the user in formulating an opinion in anticipation of a debate (see the above exemplary effect (3)).

[0025] Although details will be described later, the system 1 can repeatedly execute the same processes as steps S1 to S4 executed for the first text for the nth text (where n=a natural number from 1 to N-1). With this configuration, the user is prompted to input the (n+1)th text based on the evaluation of the persuasiveness of the nth text, so that the persuasiveness of the user's opinion can be repeatedly reinforced.

[0026] In one embodiment, the logic of an opinion may be evaluated based on whether the assertion is sufficiently supported by reasons, whether the assertion and reasons are sufficiently supported by specific examples, etc. In one embodiment, the clarity of an opinion may be evaluated based on whether the assertion, reasons, and specific examples are consistent, whether the content is concise and has little redundant expression, etc.

[0027] In this embodiment, when there is no particular distinction between "first" to "Nth" of the words prefixed with any of "first" to "Nth," or when they are referred to collectively, the prefix may not be added. For example, when there is no particular distinction between the first sentence and the second sentence, or when they are referred to collectively, they may be simply referred to as "sentence."

[0028] 2. Functional Configuration The functional configuration of system 1 of this embodiment will be described with reference to Fig. 2. System 1 includes an information processing device 2, a terminal device 3, an LLM server device 4, and a communication network 5. The information processing device 2, the terminal device 3, and the LLM server device 4 are configured to be able to communicate with each other via the communication network 5.

[0029] 2.1 Information processing device 2 The information processing device 2 executes at least a part of the process of supporting the user in constructing opinions. In one embodiment, the information processing device 2 is a server device in the case where the terminal device 3 is a client device. In one embodiment, the information processing device 2 is a cloud server device. Note that the information processing device 2 may be, for example, a device including one or more virtual or physical web server devices and one or more virtual or physical database server devices.

[0030] The information processing device 2 includes a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16.

[0031] 2.1.1 Control unit 10 The control unit 10 executes various programs stored in the storage unit 12, which will be described later, to function as a sentence acquisition unit 100, an evaluation information acquisition unit 102, an output unit 104, a generation unit 106, a determination unit 108, and an identification unit 110. Each configuration that can be realized by the information processing device 2 based on these functions will be described below.

[0032] The sentence acquisition unit 100 acquires a first sentence related to a user's opinion. The evaluation information acquisition unit 102 acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence. The output unit 104 outputs information prompting the user to input a second sentence related to the user's opinion based on the first evaluation information. The information prompting the user to input the second sentence may include at least a portion of the first evaluation information.

[0033] In this embodiment, a "sentence" may be a group of one or more words that has a complete meaning (which may also be called a "sentence" in the narrow sense), but is not limited to this. In this embodiment, a "sentence" may be, for example, any of a word, a group of words, a sentence in the narrow sense, a paragraph, a passage, etc.

[0034] In one embodiment, the sentence may be text, audio, or the like. In one example, the sentence acquisition unit 100 acquires text input by a user to the terminal device 3 as a sentence. In another example, the sentence acquisition unit 100 acquires audio input by a user via a microphone or the like of the terminal device 3 as a sentence. Note that in this embodiment, acquiring a sentence by the sentence acquisition unit 100 may include acquiring data corresponding to the sentence (for example, text data, audio data, or the like).

[0035] In one embodiment, statements regarding a user's opinion may include, for example, what a user may argue in a debate, what an user may write in an email, and what a user may say in an interview when job hunting.

[0036] In one embodiment, the evaluation information acquisition unit 102 may acquire evaluation information based on a natural language processing technique that may be appropriately selected by a person skilled in the art.

[0037] In one example, the evaluation information acquisition unit 102 may acquire evaluation information based on a machine learning model (hereinafter referred to as a "persuasiveness evaluation model") configured by inputting learning data in which values obtained by vectorizing a sentence using doc2vec and / or word2vec, etc. are labeled (annotated) with an index indicating the persuasiveness of the sentence. The evaluation information acquisition unit 102 can acquire an index indicating the persuasiveness of the sentence (an example of evaluation information) by inputting values obtained by vectorizing a sentence to be evaluated into the persuasiveness evaluation model.

[0038] In another example, the evaluation information acquisition unit 102 may acquire evaluation information based on a machine learning model (hereinafter, this machine learning model will be referred to as a "multiple evaluation criteria model," and together with the above-mentioned "persuasiveness evaluation model," will be referred to as an "evaluation model") configured by inputting learning data in which values obtained by vectorizing a sentence using, for example, doc2vec and / or word2vec are labeled (annotated) with an index indicating the logicality of the sentence, an index indicating the clarity of the sentence, and an index indicating the degree of completeness of specific examples of the sentence. The evaluation information acquisition unit 102 can acquire an index indicating the logicality of the sentence, an index indicating the clarity of the sentence, and an index indicating the degree of completeness of specific examples of the sentence (these three indexes are examples of evaluation information) by inputting values obtained by vectorizing a sentence to be evaluated into the multi-evaluation criteria model (an example of evaluating a sentence using one or more evaluation criteria).

[0039] In one embodiment, the evaluation information acquisition unit 102 acquires evaluation information by inputting an instruction (hereinafter referred to as an "evaluation instruction") to the LLM to evaluate the persuasiveness of a sentence. Inputting the evaluation instruction to the LLM includes transmitting a request (for example, an HTTP request) including the evaluation instruction to the LLM server device 4. Furthermore, acquiring the evaluation information includes receiving a response (for example, an HTTP response) corresponding to the request from the LLM server device 4.

[0040] In one embodiment, the evaluation instructions may include instructions to evaluate at least one of the logic, clarity, and completeness of specific examples of the sentence, and may include instructions to select an evaluation criterion that is relatively lower in evaluation than the other evaluation criteria from among the logic, clarity, and completeness of specific examples of the sentence.

[0041] In one embodiment, the output unit 104 outputting information prompting the input of a second sentence based on the evaluation information includes inputting an instruction to the LLM to generate information prompting the input of a second sentence based on the evaluation information (hereinafter referred to as a "comment generation instruction"), and outputting the response obtained thereby.

[0042] In one embodiment, the first evaluation information is determined by evaluating the first sentence based on one or more evaluation criteria, and the information prompting the user to enter the second sentence includes information prompting the user to enter a criterion among the one or more evaluation criteria that has a lower evaluation than the other evaluation criteria. In one embodiment, the one or more evaluation criteria include at least one of logic, clarity, and completeness of specific examples.

[0043] Among the one or more evaluation criteria, an evaluation criterion that has a lower rating compared to other evaluation criteria may be a bottleneck for improving the persuasiveness of an opinion. Therefore, prompting input regarding the evaluation criterion with a lower rating can more efficiently support the user in formulating an opinion.

[0044] In one embodiment, among one or more evaluation criteria, an evaluation criterion that is rated lower than other evaluation criteria can be identified based on a multiple evaluation criteria model. For example, by inputting vectorized values of a sentence to be evaluated into a multiple evaluation criteria model and comparing the magnitude relationships of an index indicating the logicality of the sentence, an index indicating the clarity of the sentence, and an index indicating the degree of completeness of specific examples of the sentence, which are obtained by inputting the vectorized values of the sentence to be evaluated into the multiple evaluation criteria model, an evaluation criterion that is rated lower than other evaluation criteria can be identified among the logicality, clarity, and degree of completeness of specific examples (examples of one or more evaluation criteria). For example, if the magnitude of the index corresponds to the level of evaluation, and when vectorized values of the sentence to be evaluated are input into the multiple evaluation criteria model, the index indicating the clarity of the sentence is "100," the index indicating the logicality of the sentence is "50," and the index indicating the degree of completeness of specific examples of the sentence is "30," the evaluation criterion with a relatively low evaluation can be identified as the degree of completeness of specific examples with a relatively small index.

[0045] In one example, in the first sentence, among logic, clarity, and the degree of completeness of specific examples (examples of one or more evaluation criteria), if the degree of completeness of specific examples is rated low compared to logic and clarity (examples of other evaluation criteria), the information prompting the input of the second sentence may include information prompting the input of specific examples. In this case, the degree of completeness of specific examples corresponds to an example of "an evaluation criterion, out of one or more evaluation criteria, that is rated low compared to other evaluation criteria."

[0046] In another example, in the first sentence, among logic, clarity, and the degree of specific examples (an example of one or more evaluation criteria), if the degree of specificity of logic is evaluated low compared to clarity and the degree of specific examples (an example of another evaluation criteria), the information prompting the input of the second sentence may include information pointing out a logical leap in the content of the opinion in the first sentence. In this case, logic corresponds to an example of "an evaluation criterion, out of one or more evaluation criteria, that is evaluated low compared to other evaluation criteria."

[0047] In one embodiment, the sentence acquisition unit 100 further acquires a second sentence, and the evaluation information acquisition unit 102 further acquires second evaluation information regarding an evaluation of the persuasiveness of the second sentence. In one embodiment, the output unit 104 further outputs information prompting the user to input a third sentence regarding his or her opinion based on the second evaluation information.

[0048] In one embodiment, the sentence acquisition unit 100 further acquires a second sentence, and the output unit 104 further outputs information prompting the input of a general sentence that generalizes the first sentence and the second sentence.

[0049] Prompting the user to input a summary sentence can train the user to construct a persuasive opinion. For example, if the first sentence is sufficiently rich in specific examples but relatively insufficient in logic, and the logic is subsequently reinforced by the second sentence, prompting the user to input a summary sentence for the first and second sentences can train the user to construct an opinion that is sufficiently rich in logic and specific examples.

[0050] In one embodiment, the sentence acquisition unit 100 further acquires a summary sentence, the information processing device 2 further includes a generation unit 106 that generates a revised sentence that reflects corrections and / or additions to the summary sentence, and the output unit 104 further outputs the revised sentence. With this configuration, the user can specifically grasp points that need further improvement in the summary sentence.

[0051] In one embodiment, the generator 106 generates the corrected sentence based on a natural language processing algorithm that can be selected by one skilled in the art.

[0052] In one embodiment, the generator 106 generates the revised sentence by inputting an instruction to the LLM to correct and / or add to the general sentence (hereinafter referred to as a "correction instruction"). The generator 106 generating the revised sentence by inputting the correction instruction to the LLM includes sending a request including the correction instruction to the LLM server device 4 and receiving a response thereto from the LLM server device 4.

[0053] In one embodiment, the correction instructions may include instructions regarding the relationship between the general sentence and the revised sentence. The instructions regarding the relationship between the general sentence and the revised sentence may be, for example, instructions not to revise the general sentence too much, instructions not to use words not used in the general sentence in the revised sentence, instructions to estimate the proficiency and / or experience of the user who input the general sentence and generate a revised sentence according to that proficiency and / or experience, instructions to generate a revised sentence that maintains the logical development of the general sentence as much as possible, etc. If the revised sentence is too different from the general sentence, it may be difficult for the user to use the revised sentence as a reference.

[0054] In one embodiment, the information prompting the user to input the second sentence includes an opposing opinion to the first sentence. With this configuration, the user inputs the second sentence based on the opposing opinion to the first sentence. This can help the user to formulate an opinion based on more multifaceted thinking.

[0055] In one embodiment, the sentence acquisition unit 100 further acquires a fourth sentence input by the user, and the information processing device 2 further includes a determination unit 108 that determines whether the fourth sentence satisfies a predetermined condition regarding a request for a hint, and if the fourth sentence satisfies the predetermined condition, the output unit 104 further outputs a hint for creating a persuasive sentence based on the fourth sentence and / or the first sentence, and if the fourth sentence does not satisfy the predetermined condition, the evaluation information acquisition unit 102 further acquires other evaluation information regarding an evaluation of the persuasiveness of the fourth sentence.

[0056] In one example, if a sentence (an example of a fourth sentence) input by the user in response to information prompting input of a second sentence includes the text "I don't understand," the determination unit 108 may determine that the sentence satisfies a predetermined condition regarding a hint request. In this case, the output unit 104 may output a hint for creating a persuasive sentence based on the sentence (an example of a fourth sentence) and / or sentences previously input by the user (an example of a first sentence).

[0057] In another example, if a sentence (an example of a fourth sentence) input by the user in response to information prompting input of a second sentence includes text indicating the reason for the opinion, the determination unit 108 may determine that the sentence does not satisfy a predetermined condition regarding a request for a hint. In this case, the evaluation information acquisition unit 102 may acquire evaluation information (an example of other evaluation information) corresponding to the sentence.

[0058] In one embodiment, determining whether the sentence satisfies a predetermined condition for a hint request by the determination unit 108 includes determining whether at least a portion of the sentence is consistent with one or more words for a hint request (e.g., "I don't know" and "hint"). In another embodiment, determining whether the sentence satisfies a predetermined condition for a hint request by the determination unit 108 includes determining whether at least a portion of the sentence has predetermined characteristics for whether a hint is needed (e.g., whether there are errors in vocabulary and / or grammar, etc.).

[0059] In one embodiment, the determination unit 108 determines whether a sentence satisfies a predetermined condition related to a hint request by inputting an instruction (hereinafter referred to as a "determination instruction") to the LLM to determine whether the sentence satisfies the predetermined condition, and obtaining a response thereto.

[0060] In one embodiment, the output unit 104 outputting a hint for creating a persuasive sentence includes outputting a formula hint corresponding to the fourth sentence and / or the first sentence. Note that the correspondence between the fourth sentence and / or the first sentence and the formula hint may be stored in advance in the storage unit 12 as, for example, setting information. In another embodiment, the output unit 104 outputting a hint for creating a persuasive sentence includes outputting a hint corresponding to a predetermined characteristic regarding whether a hint is necessary. For example, if the sentence contains an error in vocabulary and / or grammar, the output unit 104 may output a hint such as, "So that's what you wanted to say."

[0061] In one embodiment, the output unit 104 outputs hints for creating persuasive sentences by inputting instructions to the LLM to generate hints based on the fourth sentence and / or the first sentence (hereinafter referred to as "hint generation instructions"), and outputting the response obtained thereby.

[0062] In one embodiment, the information processing device 2 further includes an identification unit 110 that identifies evaluation criteria for increasing the persuasiveness of a sentence from one or more evaluation criteria related to the evaluation of the sentence, and the hints for creating persuasive sentences output by the output unit 104 are determined based on the evaluation criteria identified by the identification unit 110.

[0063] In one example, when the identification unit 110 identifies a sentence as being relatively insufficient in terms of logic, clarity, and the degree of specific examples (one or more examples of evaluation criteria) compared to other evaluation criteria, the output unit 104 may output hints to reinforce the logic.

[0064] In one embodiment, the identification unit 110 identifies an evaluation criterion for increasing the persuasiveness of a sentence from one or more evaluation criteria based on a multiple evaluation criteria model. For example, the identification unit 110 inputs vectorized values of the sentence to be evaluated into the multiple evaluation criteria model, and can identify an evaluation criterion for increasing the persuasiveness of the sentence based on the magnitude relationship between the index of logic, the index of clarity, and the index of the completeness of specific examples obtained thereby.

[0065] In one embodiment, the identification unit 110 can identify an evaluation criterion for increasing the persuasiveness of a sentence by inputting an instruction (hereinafter referred to as a "specific instruction") to the LLM to identify the evaluation criterion from one or more evaluation criteria.

[0066] 2.1.2 Storage section 12 The storage unit 12 stores various types of information required for the operation of the information processing device 2. In one embodiment, the storage unit 12 stores a program executed by the control unit .

[0067] 2.1.3 Network interface unit 14 The network interface unit 14 realizes communication with other devices via the communication network 5 .

[0068] 2.2 Terminal Device 3 The terminal device 3 is a communication device used by a user. The terminal device 3 is, for example, a smartphone, a personal computer, a tablet terminal, a wearable terminal, etc. The terminal device 3 includes an input interface, an output interface, and a communication interface.

[0069] The input interface is an interface for receiving input from a user by the terminal device 3. The input interface may be a touch panel, a microphone, a camera, a keyboard, a mouse, or the like.

[0070] The output interface is an interface for transmitting information to the user by means of images, sounds, etc. The output interface is a display (which may also serve as a touch panel), a speaker, etc.

[0071] The communication interface is an interface for realizing communication with other devices via the communication network 5. The communication interface may be a wireless communication interface or a wired communication interface.

[0072] The terminal device 3 may be able to access the services provided by the information processing device 2 via, for example, a web browser, or may be able to access the services by installing dedicated software.

[0073] The terminal device 3 may accept the specification of the language of the sentence to be input by the user. At this time, the user may specify a language different from his / her own primary language.

[0074] 2.3 LLM Server Device 4 The LLM server device 4 is a server device that hosts the LLM on its own device. The LLM server device 4, for example, accepts requests such as HTTP requests via an API (Application Programming Interface), executes processing according to the requests, and returns responses such as HTTP responses. The LLM may be, for example, a deep learning model having hundreds of millions of parameters and having learned hundreds of gigabytes of training data related to natural languages. An example of an LLM is gpt-4o.

[0075] 2.4 Communication Networks5 The communication network 5 realizes communication between the devices included in the system 1. The communication network 5 realizes communication between the devices based on, for example, the TCP / IP protocol.

[0076] 3 operations An example of the operation of the system 1 will be described with reference to Figures 3 to 8. In the following example, the sentence will be described as a text.

[0077] 3.1 Sequence FIG. 3 is a sequence diagram showing an example of the operation of the system 1.

[0078] First, the information processing device 2 transmits information about the theme on which the user will construct an opinion to the terminal device 3 (S100). The information about the theme may be, for example, information stored in advance in the storage unit 12, or may be information received in advance by the information processing device 2 from the LLM server device 4.

[0079] Next, the system 1 repeatedly executes the processes described in the following steps S102 to S114 for each of the natural numbers n=1 to N-1.

[0080] First, the terminal device 3 accepts input of the nth text from the user (S102). Next, the terminal device 3 transmits the nth text to the information processing device 2 (S104). Receiving the nth text is an example of obtaining a sentence related to the user's opinion.

[0081] The information processing device 2 generates an nth instruction, which is an instruction corresponding to the nth text, based on the received nth text (S106). The nth instruction may include, for example, the following (1) to (11). The nth response is a response obtained by inputting the nth instruction to the LLM server device. (1) nth text (2) Text 1 to Text n-1 (3) 1st instruction ~ n-1st instruction (4) 1st response to n-1th response (5) Information prompting input of the second text to information prompting input of the nth text (6) General instructions Example: "The nth text, the subject of which persuasiveness is to be evaluated, as well as the 1st to n-1st texts, the 1st to n-1st instructions, the 1st to n-1st responses, and the information prompting you to enter the 2nd to nth texts regarding past interactions with the user, are as follows. Please take this into consideration and follow the instructions below to proceed." (7) Judgment instructions Example: "Determine whether the nth text requires a hint." (8) Hint generation instructions Example: "If it is determined that the nth text requires a hint, please generate a hint based on the contents of the 1st text through the n-1th text to improve the logic, clarity, or completeness of the specific examples of the user's opinion. If it is determined that the nth text does not require a hint, please proceed according to the instructions below." (9) Evaluation Instructions Example: "Please rate the logic, clarity, and the extent to which specific examples are provided for the nth text on a scale of 1 to 10. Then, throughout the entirety of the first through nth texts, please rate the logic, clarity, and the extent to which specific examples are provided for each text on a scale of 1 to 10." (10)Specific instructions Example: "Please identify the evaluation criterion with the smallest index among the logic, clarity, and the degree of specific examples for texts 1 through n." (11) Comment generation instructions Example: "Generate and output comments to improve the evaluation criterion with the smallest index among the first through nth texts."

[0082] Note that sending an instruction including the evaluation instruction to the LLM server device 4 is an example of determining evaluation information by evaluating a sentence with one or more evaluation criteria.

[0083] The information processing device 2 transmits the generated nth instruction to the LLM server device 4 (S108). Next, the information processing device 2 receives the nth response generated by the LLM server device 4 based on the nth instruction (S110). Receiving the nth response is an example of obtaining evaluation information related to an evaluation of the persuasiveness of a sentence.

[0084] Next, the information processing device 2 generates information prompting the input of the (n+1)th text based on the received nth response (S112). The information prompting the input of the (n+1)th text may include a comment generated based on the nth instruction to generate a comment.

[0085] Next, the information processing device 2 transmits information prompting the input of the (n+1)th text to the terminal device 3 (S114). Generating and transmitting information prompting the input of the (n+1)th text based on the nth response is an example of outputting information prompting the input of a sentence related to the user's opinion based on evaluation information.

[0086] By the system 1 repeatedly executing steps S102 to S114 for each of n=1 to N-1, the user will input the first text to the N-1th text into the terminal device 3, and the information processing device 2 will send information prompting the input of the second text to the Nth text to the terminal device 3.

[0087] Thereafter, the terminal device 3 accepts input of the Nth text from the user (S116). Next, the terminal device 3 transmits the Nth text to the information processing device 2 (S118).

[0088] In response to this, the information processing device 2 generates information prompting the input of summary text summarizing the first text to the Nth text (S120). The information processing device 2 transmits information prompting the input of summary text to the terminal device 3 (S122).

[0089] In response to this, the terminal device 3 accepts input of the summary text (S124). Next, the terminal device 3 transmits the summary text to the information processing device 2 (S126).

[0090] The information processing device 2 generates instructions corresponding to the summary text based on the received summary text (S128). The instructions corresponding to the summary text may include, for example, the following (1) to (9). (1) Summary text (2) Text 1 to Text N (3) 1st instruction ~ N-1st instruction (4) 1st Response to N-1st Response (5) Information prompting input of the second text to information prompting input of the Nth text (6) General instructions Example: "The summary text, the subject of which persuasiveness is to be evaluated, as well as the 1st through Nth texts, 1st through N-1st instructions, 1st through N-1st responses, and the information prompting you to enter the 2nd through Nth texts regarding past interactions with the user, are as follows. Please take this into consideration and follow the instructions below to proceed." (7) Evaluation Instructions Example: "Please rate the logic, clarity, and completeness of the summary text on a scale of 1 to 10." (8) Correction instructions Example: "Generate a revised summary that strengthens the persuasiveness of the summary text. Please be careful not to over-revise the summary, as we want the generated revision to be easy for users to refer to." (9) Comment generation instructions Example: "Generate and output comments to reinforce the persuasiveness of the general comment and / or comments regarding the intent of the revised text. If there is any content included in the general comment that is not included in Text 1 through Text N, please point out that content."

[0091] The information processing device 2 transmits an instruction corresponding to the generated summary text to the LLM server device 4 (S130). Next, the information processing device 2 receives a response generated by the LLM server device 4 based on the instruction corresponding to the summary text (S132). The information processing device 2 transmits overall evaluation information including the response to the terminal device 3 (S134).

[0092] 3.2 Display screen example 4 to 8, examples of display screens on the terminal device 3 will be described. Note that, in the following, the language in which the terminal device 3 accepts input and / or displays may be a language designated by the user on at least some of the display screens. The language designated by the user may be a language different from the user's primary language (for example, English when the user's primary language is Japanese).

[0093] In the following, an example will be described in which N in FIG. 3 is "6" (that is, an example in which the user is prompted to input the first to sixth texts and their summary sentences).

[0094] 4 displays texts t100 to t108, an input field d100, and a voice input button d102. The input field d100 is a display element that allows the user to input text via, for example, a keyboard (including a virtual keyboard displayed on the screen) provided in the terminal device 3. The voice input button d102 is a display element that allows the user to input voice via, for example, a microphone provided in the terminal device 3, and input the transcribed text into the input field d100.

[0095] Text t100 indicates information about the topic and may be displayed on the terminal device 3 immediately after step S100 in Fig. 3. The text t100 reads, "Do you think two days off a week is enough? Let us know your opinion."

[0096] The text t102 may be the text initially input by the user. The text t102 may be displayed on the terminal device 3 immediately after step S104 where n=1 in FIG. 3. The text t102 displays "No, I don't think so." This may correspond to the assertion among the assertions, reasons, and specific examples of the user's opinion.

[0097] The text t104 may be displayed based on the response corresponding to the text t102. The text t104 may be displayed on the terminal device 3 immediately after step S114 where n=1 in FIG. 3. The text t104 displays, "That's an interesting opinion! Can you tell me why you think two days off a week is not enough?" This is an example of information that prompts the user to enter the next text.

[0098] Text t106 may be text that the user inputs following text t102. Text t106 may be displayed on the terminal device 3 immediately after step S104 where n=2 in FIG. 3. Text t106 displays, "Because I think it is necessary to improve the balance between school time and free time." This may correspond to the reason among the assertion, reasons, and specific examples of the user's opinion.

[0099] Text t108 may be displayed based on the response corresponding to text t106. Text t106 may be displayed on the terminal device 3 immediately after step S114 where n=2 in FIG. 3. Text t108 displays, "That's a compelling reason. Do you have any specific examples that explain the need to improve the balance between school time and free time?" This is an example of information that prompts for input of the next text.

[0100] The display screen example in Fig. 5 shows an example of a continuation of the display screen example in Fig. 4. In the display screen example in Fig. 5, in addition to the input field d100 and voice input button d102 described above, texts t200 to t206 are displayed.

[0101] Text t200 may be text that the user inputs following text t106 in FIG. 4. Text t200 may be displayed on the terminal device 3 immediately after step S104 where n=3 in FIG. 3. Text t200 displays, "If I have free time, I can use it for my hobbies, so my study efficiency improves." This may correspond to a specific example among the assertion, reason, and specific example of the user's opinion. Note that text t200 may also have an aspect of the reason for the user's opinion.

[0102] Text t202 may be displayed based on a response corresponding to text t200. Text t202 may be displayed on the terminal device 3 immediately after step S114 where n=3 in FIG. 3. Text t202 displays, "Can you tell me the relationship between having time to spend on hobbies and improving study efficiency?" This is an example of information that prompts input of the next text, and also an example of information that prompts input of an evaluation criterion (in this example, logic) that is rated lower than the other evaluation criteria out of one or more evaluation criteria.

[0103] Text t204 may be text that the user inputs following text t200. Text t204 may be displayed on the terminal device 3 immediately after step S104 where n=4 in FIG. 3. The text t204 displays "Please give me a hint." This is an example of a sentence that satisfies the predetermined condition for requesting a hint.

[0104] Text t206 may be displayed based on the response corresponding to text t204. Text t206 may be displayed on the terminal device 3 immediately after step S114 where n=4 in FIG. 3. Text t204 reads, "Of course. Think about how relaxing can help you concentrate on your studies. Think about how taking time for a hobby can recharge you and motivate you to study." This is an example of a hint for creating a persuasive sentence that is output based on a sentence already input by the user.

[0105] The display screen example in Fig. 6 shows an example of a continuation of the display screen example in Fig. 5. In the display screen example in Fig. 6, in addition to the input field d100 and voice input button d102 described above, texts t300 to t306 are displayed.

[0106] Text t300 may be text entered by the user following text t204 in FIG. 5. Text t300 may be displayed on the terminal device 3 immediately after step S104 where n=5 in FIG. 3. Text t300 displays, "Being able to spend my free time on my hobbies helps me relax, which in turn allows me to concentrate on my studies." This may correspond to a specific example among the assertion, reason, and specific example of the user's opinion. Note that text t300 may also have an aspect of the reason for the user's opinion.

[0107] Text t302 may be displayed based on the response corresponding to text t300. Text t302 may be displayed on the terminal device 3 immediately after step S114 where n=5 in FIG. 3. Text t302 displays, "That's great reasoning! I have a slightly different opinion. I think a two-day weekend would make it easier to maintain a routine. What do you think?" This is an example of information prompting the user to enter the next text, and also an example of an opposing opinion to the statement.

[0108] Text t304 may be text that the user inputs following text t300. Text t304 may be displayed on the terminal device 3 immediately after step S116 in FIG. 3. Text t304 displays, "For example, for hobbies that require a large amount of time, such as camping or traveling, two days off a week is not enough." This may correspond to a specific example among the assertions, reasons, and specific examples of the user's opinion.

[0109] Text t306 displays "Please summarize your opinions up to this point." Text t306 can be displayed on the terminal device 3 immediately after step S122 in Fig. 3. This is an example of information that prompts the user to input a summary sentence that summarizes multiple sentences that the user has already input.

[0110] The display screen example in Fig. 7 shows an example of a continuation of the display screen example in Fig. 6. In the display screen example in Fig. 7, in addition to the input field d100 and voice input button d102 described above, text t400 is displayed.

[0111] Text t400 reads, "I don't think two days off a week is enough because I think we need to improve the balance between school time and free time. In particular, people who have hobbies that require a lot of time, such as camping or traveling, are unable to achieve this balance. If you increase your free time, you will be able to spend more time on your hobbies and relax. And relaxation will improve your study efficiency." Text t400 may be displayed on the terminal device 3 immediately after step S126 in FIG. 3. This is an example of a summary sentence.

[0112] The display screen example in Fig. 8 shows an example of a continuation of the display screen example in Fig. 7. In the display screen example in Fig. 7, texts t500 to t506 are displayed.

[0113] The text t500 reads, "That's a great idea! Your reasons and examples strongly support your opinion. Below are some examples that will make your opinion even more persuasive. Please use them as a reference." This is an example of evaluation information that corresponds to a summary statement.

[0114] Text t502 reads, "I don't think two days off a week is enough. This is because we need to improve the balance between school time and free time. In particular, people who have hobbies that require a large amount of time, such as camping or traveling, cannot secure enough time for these activities on weekends alone. For example, if you go camping, the actual time you can spend on these activities is limited when you include the preparation and cleanup. With more free time, you can spend more time on these hobbies, which has a significant relaxing effect. As a result, you can study in a refreshed state, which I believe will lead to improved learning efficiency." This is an example of a revised sentence.

[0115] Text t504 reads, "An example of not having enough free time when going camping has been added." Text t506 reads, "The causal relationship between relaxation and improved study efficiency has been clarified." These are examples of information about the differences between the summary sentence and the revised sentence.

[0116] Although not shown in the drawings, the terminal device 3 may further display examples of expressions that are not used in the revised sentence. With this configuration, it is possible to efficiently support the user in formulating an opinion, for example, even if the gist of the revised sentence differs from what the user intended, or if the revised sentence does not contain expressions that the user can use and / or wants to use.

[0117] 4. Hardware Configuration 9, an example of a hardware configuration in which the devices included in the above-described system 1 are realized by a computer 70 will be described. Note that the functions of each device can also be realized by dividing them into multiple devices.

[0118] As shown in FIG. 9, a computer 70 includes a processor 700 , a storage device 702 , an input I / F 704 , a data I / F 706 , a communication I / F 708 , and a display device 710 .

[0119] The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit included in the control unit 10 of the information processing device 2 can be realized by the processor 700 executing the programs stored in the storage device 702.

[0120] The storage device 702 is a storage medium such as a RAM (Random Access Memory), etc. The RAM temporarily stores the program code of the program executed by the processor 700 and data required when the program is executed.

[0121] The storage device 702 may also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores an operating system and various programs for implementing the above-described configurations. The storage medium storing the various programs may be a non-transitory computer-readable medium. The storage device 702 may also store tables that register various types of information and a DB that manages the tables. Such programs and data are loaded into the storage device 702 as needed and referenced by the processor 700.

[0122] The input I / F 704 is a device for receiving input from a user. Specific examples of the input I / F 704 include a camera, a button, a microphone, a keyboard, a mouse, a touch panel, various sensors, and a wearable device. The input I / F 704 may be connected to the computer 70 via an interface such as a USB (Universal Serial Bus).

[0123] The data I / F 706 is a device for inputting data from outside the computer 70. A specific example of the data I / F 706 is a drive device for reading data stored in various storage media. The data I / F 706 may be provided outside the computer 70. In this case, the data I / F 706 is connected to the computer 70 via an interface such as a USB.

[0124] The communication I / F 708 is a device for performing wired or wireless data communication with devices external to the computer 70 via the communication network 5. The communication I / F 708 may be provided external to the computer 70. In this case, the communication I / F 708 is connected to the computer 70 via an interface such as a USB.

[0125] The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a display of a wearable device. The display device 710 may be provided outside the computer 70. In this case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F 704, the display device 710 can be configured as an integral part of the input I / F 704.

[0126] Furthermore, the components of the devices included in the system 1 described in the above embodiment are assumed to realize predetermined processing in cooperation with other hardware by the processor 700 executing a program stored in the storage device 702. In other words, these components are envisioned as both software or firmware and the corresponding hardware, and in both of these concepts, they are also referred to as "functions," "means," "parts," "processing circuits," "units," or "modules," and can be interpreted as such.

[0127] 5. Variations The above-described embodiments are intended to facilitate understanding of the present disclosure and are not intended to limit the present disclosure. The configurations that the embodiments may have are not limited to those exemplified and may be modified as appropriate. Furthermore, configurations shown in different embodiments may be partially substituted or combined with each other.

[0128] 5.1 First Modification In "3.2 Display Screen Examples" of the above embodiment, an example in which N in Fig. 3 is "6" (i.e., an example in which the user is prompted to input the first to sixth texts and a summary sentence for them) has been described. In relation to this, the information processing device 2 can control the processing according to the above embodiment so that the user inputs a sentence other than the summary sentence a predetermined number of times.

[0129] In one embodiment, after acquiring a sentence from the terminal device 3, the information processing device 2 determines the number of times the user has input sentences up to that point, including the sentence in question, and if it determines that the number of times has reached a predetermined number, outputs information prompting the user to input a summary sentence (see S116 to S122 in Figure 3), and if it determines that the number of times has not reached the predetermined number, acquires evaluation information corresponding to the most recently acquired sentence and outputs information prompting the user to input the next sentence based on the evaluation information (see S102 to S114 in Figure 3).

[0130] In this case, the information processing device 2 may output information prompting the user to input a summary sentence if the number of times the user has input a sentence has reached a predetermined number, regardless of the content of the sentence already input by the user (for example, whether it is logical, clear, etc.).

[0131] 5.2 Second variant In one embodiment, the evaluation information acquisition unit 102 may acquire the second evaluation information based on at least a part of the first sentence, the first evaluation information, and information prompting the input of the second sentence, in addition to the second sentence. That is, the evaluation information acquisition unit 102 may acquire the second evaluation information based on the process leading up to the acquisition of the second sentence. In the above embodiment, an example of such a configuration is that the nth instruction transmitted to the LLM server device 4 may include the first text to the (n-1)th text and the first response to the (n-1)th response.

[0132] 5.3 Third Modification In the above embodiment, an example has been described in which the information processing device 2 inputs instructions to the LLM server device 4, but the LLM may be hosted by the information processing device 2. That is, the information processing device 2 may execute the processing according to the above embodiment using a local LLM. Note that the LLM may be replaced by a large-scale deep learning model such as Transformer that has been tuned to suit the above embodiment.

[0133] 5.4 Fourth Variant In the above embodiment, FIG. 3 and other figures illustrate an example in which an nth instruction including a general instruction, a judgment instruction, a hint generation instruction, an evaluation instruction, a specific instruction, and a comment generation instruction is sent to the LLM server device 4 to execute a series of processes, but this is not limiting. In this case, at least a part of the processes executed by the LLM server device 4 may be executed by the information processing device 2 instead. In one example, the information processing device 2 may determine whether the nth text contains a predetermined word or the like related to a hint request, and if it determines that it does not contain the nth instruction, it may send the nth instruction including a general instruction, an evaluation instruction, a specific instruction, and a comment generation instruction to the LLM server device 4, or if it determines that it does contain the nth instruction, it may send the nth instruction including a general instruction and a hint generation instruction to the LLM server device 4. In other words, an instruction corresponding to the judgment instruction may be executed by the information processing device 2 instead of the LLM server device 4.

[0134] 5.5 Fifth Variant With respect to the display screen examples described with reference to FIGS. 4 to 8 in the above embodiment, at least a portion of the information displayed by the terminal device 3 may be displayed in a predetermined language, and at least another portion of the information displayed by the terminal device 3 may be displayed in another language different from the predetermined language. In this case, the predetermined language may be the user's first language, and the other language may be a language other than the user's first language. The terminal device 3 may accept designation of the predetermined language and / or another language from the user. The terminal device 3 may estimate or determine the predetermined language and / or another language based on, for example, its own location information, etc.

[0135] In one example, if a user specifies Japanese, which is the first language, as the predetermined language and English as another language, on the terminal device 3, the sentence entered by the user (e.g., text t102 and text t106 in Figure 4) and information prompting the user to enter the next sentence (e.g., text t104 and text t108 in Figure 4) may be displayed in English, and feedback on the summary sentence (e.g., text t500, t504 and t506 in Figure 8) may be displayed in Japanese.

[0136] 5.6 Sixth Variant In the above embodiment, an example in which a user inputs a summary sentence separately from the first text to the Nth text has been described, but this is not limiting. The information processing device 2 may treat the first text to the Nth text input by the user as a summary sentence. The information processing device 2 may generate a summary sentence based on the first text to the Nth text (for example, by combining these texts) and control the terminal device 3 to display a revised sentence based on the generated summary sentence. The information processing device 2 may prompt the user to input a summary sentence separately from the first text to the Nth text if a predetermined condition regarding the progress of opinion construction is met, and may treat the first text to the Nth text as a summary sentence if the predetermined condition is not met. The predetermined condition may be that the user's opinion is not constructed within a predetermined number of sentence inputs (for example, if at least one of the user's opinion claims, reasons, and specific examples is significantly missing, or if the user requests hints multiple times).

[0137] 5.7 Seventh Variant In the above embodiment, an example has been described in which the output unit 104 outputs information that prompts the user to input a second sentence related to his or her opinion based on the first evaluation information. However, the information output by the output unit 104 is not limited to this. In one embodiment, the output unit 104 outputs a second sentence that reflects corrections and / or additions to the first sentence to increase its persuasiveness, based on the first sentence and the first evaluation information. That is, while the information processing device 2 in the above embodiment has mainly been described as prompting the user to input a second sentence that is more persuasive than the first sentence, an information processing device 2 according to another embodiment may present the second sentence, which is more persuasive than the first sentence, to the user as, for example, a sample answer corresponding to the first sentence. This configuration allows the user to identify a more persuasive sentence based on the first sentence that the user input. This can more efficiently support the user in formulating an opinion.

[0138] The information processing device 2 may send to the LLM server device 4 an instruction to generate a sentence that reflects corrections and / or additions to the first sentence that increase the persuasiveness of the first sentence, and may present the sentence to the user based on the response. Furthermore, the various configurations described in the above embodiments may be applied to determine the second sentence that the information processing device 2 presents to the user.

[0139] The information processing device 2 may further output a sentence in which corrections and / or additions that increase the persuasiveness of the first sentence are reflected in the first sentence, along with information prompting input of the second sentence according to the above embodiment.

[0140] 6 Supplementary Information The wording in this embodiment can be understood as follows to the extent that no contradiction occurs.

[0141] In this embodiment, "executing a predetermined process based on predetermined information" may mean executing the predetermined process based on at least a part of the predetermined information, executing the predetermined process based on at least the predetermined information, or executing the predetermined process probabilistically based on the predetermined information. In other words, "executing a predetermined process based on predetermined information" is not limited to executing the predetermined process based only on the predetermined information.

[0142] In this embodiment, "executing another process based on a predetermined process" may mean executing the other process after the predetermined process has been executed, executing the predetermined process and the other process consecutively, executing the other process based on information determined by the predetermined process, executing the other process on the condition that the predetermined process has been executed, or executing the other process by means of the predetermined process. Note that "executing another process by a predetermined process" may also be understood as the same as "executing another process based on a predetermined process."

[0143] In this embodiment, "the specified information includes other information" may mean either that at least a part of the specified information is the other information, or that the other information can be obtained based on the specified information.

[0144] In this embodiment, "a specified process includes another process" may mean either that at least a part of the specified process is the other process (i.e., that the other process is performed in the process of obtaining the result of the specified process), or that one aspect of the specified process is the other process.

[0145] In this embodiment, "a predetermined object corresponds to another object" may mean any of the following: the predetermined object and the other object are in a one-to-one relationship; the other object is included in a predetermined set identified based on the predetermined object; or the other object can be identified based on the predetermined object. Note that "a predetermined object corresponds to another object" is not limited to being managed, for example, in a database. Furthermore, "a predetermined object is associated with another object" may be understood in the same way as "a predetermined object corresponds to another object."

[0146] In this embodiment, "obtaining information" includes making the information processable in the control unit 10. "Obtaining information" may mean, for example, receiving the information from another device, obtaining the information through predetermined processing, reading the information from the storage unit 12, etc.

[0147] In this embodiment, "generating information" may mean either making the information obtained by a specified process processable in the control unit 10, or storing the information obtained by a specified process in the memory unit 12.

[0148] In this embodiment, "determining information" may mean either selecting at least one piece of information from one or more pieces of information, or newly generating that information.

[0149] In this embodiment, "outputting information" may mean either transmitting the information to another device or outputting the information as sound or video.

[0150] 7 Configuration example The present disclosure includes the following techniques:

[0151] [Appendix 1] An information processing device 2 includes a sentence acquisition unit 100 that acquires a first sentence related to a user's opinion, an evaluation information acquisition unit 102 that acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and an output unit 104 that outputs information that prompts the user to input a second sentence related to the user's opinion based on the first evaluation information.

[0152] [Appendix 2] An information processing device 2 as described in Appendix 1, wherein the first evaluation information is determined by evaluating the first sentence using one or more evaluation criteria, and the information prompting the input of the second sentence includes information prompting the input of an evaluation criterion among the one or more evaluation criteria that has a lower rating compared to other evaluation criteria.

[0153] [Appendix 3] The information processing device 2 according to Appendix 2, wherein the one or more evaluation criteria include at least one of logic, clarity, and completeness of specific examples.

[0154] [Appendix 4] An information processing device 2 described in any one of Appendices 1 to 3, wherein the sentence acquisition unit 100 further acquires a second sentence, and the evaluation information acquisition unit 102 further acquires second evaluation information regarding an evaluation of the persuasiveness of the second sentence.

[0155] [Appendix 5] The information processing device 2 according to claim 4, wherein the output unit 104 further outputs information prompting input of a third sentence regarding the user's opinion, based on the second evaluation information.

[0156] [Appendix 6] An information processing device 2 described in any one of Appendices 1 to 5, wherein the sentence acquisition unit 100 further acquires a second sentence, and the output unit 104 further outputs information prompting input of a summary sentence that summarizes the first sentence and the second sentence.

[0157] [Appendix 7] The information processing device 2 described in Appendix 6, wherein the sentence acquisition unit 100 further acquires a summary sentence and further includes a generation unit 106 that generates a revised sentence that reflects corrections and / or additions to the summary sentence, and the output unit 104 further outputs the revised sentence.

[0158] [Appendix 8] The information processing device 2 according to any one of appendices 1 to 7, wherein the information prompting the input of the second sentence includes an opposing opinion to the first sentence.

[0159] [Appendix 9] The information processing device 2 according to any one of appendices 1 to 8, wherein the evaluation information acquisition unit 102 acquires the first evaluation information by inputting an instruction to make a large-scale language model evaluate the persuasiveness of the first sentence.

[0160] [Appendix 10] The sentence acquisition unit 100 further acquires a fourth sentence input by the user and further includes a judgment unit 108 that determines whether the fourth sentence satisfies a predetermined condition regarding a request for a hint, and if the fourth sentence satisfies the predetermined condition, the output unit 104 further outputs a hint for creating a persuasive sentence based on the fourth sentence and / or the first sentence, and if the fourth sentence does not satisfy the predetermined condition, the evaluation information acquisition unit 102 further acquires other evaluation information regarding an evaluation of the persuasiveness of the fourth sentence. An information processing device 2 described in any one of Appendices 1 to 9.

[0161] [Appendix 11] An information processing device 2 as described in Appendix 10, further comprising an identification unit 110 that identifies evaluation criteria for increasing the persuasiveness of the first sentence from one or more evaluation criteria related to the evaluation of the first sentence, and hints for creating a persuasive sentence are determined based on the evaluation criteria identified by the identification unit 110.

[0162] [Appendix 12] An information processing device 2 includes a sentence acquisition unit 100 that acquires a first sentence related to a user's opinion, an evaluation information acquisition unit 102 that acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and an output unit 104 that outputs a second sentence that reflects corrections and / or additions to the first sentence that increase the persuasiveness of the first sentence based on the first sentence and the first evaluation information.

[0163] [Appendix 13] An information processing method in which a computer 70 acquires a first sentence related to a user's opinion, acquires first evaluation information related to an evaluation of the persuasiveness of the first sentence, and outputs information prompting the user to input a second sentence related to the user's opinion based on the first evaluation information.

[0164] [Appendix 14] A program that causes a computer 70 to acquire a first sentence related to a user's opinion, acquire first evaluation information related to an evaluation of the persuasiveness of the first sentence, and output information that prompts the user to input a second sentence related to the user's opinion based on the first evaluation information. [Explanation of symbols]

[0165] 1...system, 2...information processing device, 3...terminal device, 4...LLM server device, 10...control unit, 70...computer, 100...sentence acquisition unit, 102...evaluation information acquisition unit, 104...output unit, 106...generation unit, 108...determination unit, 110...identification unit

Claims

1. a sentence acquisition unit that acquires a first sentence related to a user's opinion; an evaluation information acquisition unit that acquires first evaluation information regarding an evaluation of persuasiveness of the first sentence; an output unit that outputs information prompting the user to input a second sentence regarding the user's opinion based on the first evaluation information; Equipped with the first evaluation information is determined by evaluating the first sentence based on a plurality of evaluation criteria including at least one of logic, clarity, and a degree of completeness of specific examples; the information prompting the input of the second sentence includes information prompting the input of an evaluation criterion that has a lower evaluation than other evaluation criteria among the plurality of evaluation criteria; Information processing device.

2. the sentence acquisition unit further acquires the second sentence; The information processing device according to claim 1 , wherein the evaluation information acquisition unit further acquires second evaluation information regarding an evaluation of persuasiveness of the second sentence, the evaluation information being determined by evaluating the second sentence using the plurality of evaluation criteria.

3. the output unit further outputs information prompting the user to input a third sentence regarding the user's opinion based on the second evaluation information; the information prompting the input of the third sentence includes information prompting the input of an evaluation criterion that has a lower evaluation than other evaluation criteria among the plurality of evaluation criteria; The information processing device according to claim 2 .

4. the sentence acquisition unit further acquires the second sentence; The information processing device according to claim 1 , wherein the output unit further outputs information prompting input of a general sentence that generalizes the first sentence and the second sentence.

5. The sentence acquisition unit further acquires the general sentence, a generation unit that generates a modified sentence that reflects the modification and / or addition to the general sentence by inputting a request including the general sentence and an instruction to modify and / or add to the general sentence into a large-scale language model, The information processing device according to claim 4 , wherein the output unit further outputs the corrected sentence.

6. The information processing device according to claim 1 , wherein the information prompting the user to input the second sentence further includes an opposing opinion to the first sentence.

7. The information processing device according to claim 1 , wherein the evaluation information acquisition unit acquires the first evaluation information by inputting an instruction to a large-scale language model to evaluate the persuasiveness of the first sentence.

8. the sentence acquisition unit further acquires a fourth sentence input by the user; a determination unit that determines whether the fourth sentence satisfies a predetermined condition regarding a request for a hint, If the fourth sentence satisfies the predetermined condition, the output unit further outputs a hint for creating a persuasive sentence based on the fourth sentence and / or the first sentence; 2. The information processing device of claim 1, wherein if the fourth sentence does not satisfy the specified condition, the evaluation information acquisition unit further acquires other evaluation information regarding an evaluation of the persuasiveness of the fourth sentence, which is determined by evaluating the fourth sentence using the multiple evaluation criteria.

9. Further comprising: an identification unit that identifies an evaluation criterion for increasing the persuasiveness of the first sentence from the plurality of evaluation criteria; The information processing device according to claim 8 , wherein the hint for creating a persuasive sentence is determined based on an evaluation criterion specified by the specifying unit.

10. The computer Obtaining a first sentence regarding a user's opinion; obtaining first evaluation information regarding an evaluation of the persuasiveness of the first sentence; outputting information prompting the user to input a second sentence regarding his / her opinion based on the first evaluation information; An information processing method for performing the first evaluation information is determined by evaluating the first sentence based on a plurality of evaluation criteria including at least one of logic, clarity, and a degree of completeness of specific examples; the information prompting the input of the second sentence includes information prompting the input of an evaluation criterion that has a lower evaluation than other evaluation criteria among the plurality of evaluation criteria; Information processing methods.

11. On the computer, Obtaining a first sentence regarding a user's opinion; obtaining first evaluation information regarding an evaluation of the persuasiveness of the first sentence; outputting information prompting the user to input a second sentence regarding his / her opinion based on the first evaluation information; A program for executing the first evaluation information is determined by evaluating the first sentence based on a plurality of evaluation criteria including at least one of logic, clarity, and a degree of completeness of specific examples; the information prompting the input of the second sentence includes information prompting the input of an evaluation criterion that has a lower evaluation than other evaluation criteria among the plurality of evaluation criteria; program.

Images