Information processing device, information processing system, information processing method, and program

Abstract

An information processing device, an information management system, an information management method, and a program are provided that can improve the accuracy of processing an original text. [Solution] The information processing device includes an original text acquisition unit that acquires an original text input by an administrator, a guideline information acquisition unit that acquires guideline information regarding the processing of the original text acquired by the original text acquisition unit from a memory unit, a processed sentence acquisition unit that acquires a processed sentence obtained by processing the original text acquired by the original text acquisition unit by sending the original text acquired by the original text acquisition unit and the guideline information acquired by the guideline information acquisition unit to a processing model, and an evaluation unit that evaluates the processed sentence acquired by the processed sentence acquisition unit by sending the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, and the processed sentence acquired by the processed sentence acquisition unit to an evaluation model.

Description

[Technical field]

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

[0002] Conventionally, there has been known an information processing system that acquires a summary as a processed text by inputting a product description as an original text into a learning model on a product sales page of an electronic commerce site, as shown in, for example, Patent Document 1. In such an electronic commerce site, the product description is input by the manager of the product to be traded. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-128805 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in such an information processing system, depending on the original text input by the administrator, there are cases where the original text is not processed as desired in the operation of the information processing system. For this reason, it is desired to improve the accuracy of processing from the original text. [Means for solving the problem]

[0005] An information processing device that solves the above problem includes an original text acquisition unit that acquires an original text input by an administrator, a guideline information acquisition unit that acquires guideline information regarding processing of the original text acquired by the original text acquisition unit from a memory unit, a processed sentence acquisition unit that acquires a processed sentence obtained by processing the original text acquired by the original text acquisition unit by transmitting the original text acquired by the original text acquisition unit and the guideline information acquired by the guideline information acquisition unit to a processing model, and an evaluation unit that evaluates the processed sentence acquired by the processed sentence acquisition unit by transmitting the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, and the processed sentence acquired by the processed sentence acquisition unit to an evaluation model.

[0006] An information management system that solves the above problem includes an original text acquisition unit that acquires an original text input by an administrator, a guideline information acquisition unit that acquires guideline information regarding processing of the original text acquired by the original text acquisition unit from a memory unit, a processed sentence acquisition unit that acquires a processed sentence obtained by processing the original text acquired by the original text acquisition unit by transmitting the original text acquired by the original text acquisition unit and the guideline information acquired by the guideline information acquisition unit to a processing model, and an evaluation unit that evaluates the processed sentence acquired by the processed sentence acquisition unit by transmitting the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, and the processed sentence acquired by the processed sentence acquisition unit to an evaluation model.

[0007] An information management method that solves the above-mentioned problems includes one or more computers acquiring an original text input by an administrator, acquiring guideline information regarding processing of the original text from a memory unit, transmitting the original text and the guideline information to a processing model to obtain a processed sentence obtained by processing the original text, and transmitting the original text, the guideline information, and the processed sentence to an evaluation model to evaluate the processed sentence.

[0008] A program for solving the above problem causes one or more computers to acquire an original text input by an administrator, acquire guideline information regarding processing of the original text from a memory unit, obtain a processed sentence by processing the original text by sending the original text and the guideline information to a processing model, and evaluate the processed sentence by sending the original text, the guideline information, and the processed sentence to an evaluation model. Effect of the Invention

[0009] According to the present invention, the accuracy of processing the original text can be improved. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing the overall configuration of an information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an electrical configuration of the terminal device of the first embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an electrical configuration of the information processing apparatus according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing the control content of the information processing system of the first embodiment. [Diagram 5] FIG. 5 is a diagram showing guideline information according to the first embodiment. [Figure 6] FIG. 6 is a diagram showing an explanatory text, a summary text, and a translation text according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing evaluation result information according to the first embodiment. [Figure 8] FIG. 8 is a flowchart showing the summary control process according to the first embodiment. [Figure 9] FIG. 9 is a flowchart showing the evaluation control process of the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] [First embodiment] An embodiment of an information processing device, an information processing system, an information processing method, and a program will be described.

[0012] <Configuration of Information Processing System 10> 1, the information processing system 10 is a system that processes information. The information processing system 10 is a system that provides information to a user who uses the information processing system 10. The information processing system 10 is a system that controls services provided to the user.

[0013] The information processing system 10 includes an information processing device 11. The information processing device 11 is a device that processes information. The information processing device 11 performs control related to information provided to a user. The information processing device 11 performs control related to services provided to a user. The information processing device 11 is managed by an administrator of the information processing device 11. The information processing device 11 is managed by an operator of the information processing system 10.

[0014] The information processing system 10 may include a travel management server 12. The information processing system 10 may include multiple travel management servers 12. The travel management server 12 is a server that provides travel services to users. The travel management server 12 is a server that manages information related to travel. The travel management server 12 manages information entered by an administrator of the transaction object. The administrator of the transaction object is a person who provides travel services. As a specific example, the transaction object includes a hotel, a restaurant, and a passport, and the transaction includes reservation, purchase, sale, loan, and use.

[0015] The multiple travel management servers 12 may include a first travel management server 12A. The first travel management server 12A is a server that manages information related to travel to at least a first country. The first travel management server 12A is a server that manages information related to travel in a first language. For example, the first country may be Japan and the first language may be Japanese.

[0016] The multiple travel management servers 12 may include a second travel management server 12B. The second travel management server 12B may be a server that manages information related to travel to a second country. The second travel management server 12B may be a server that manages information related to travel to a first country. The second travel management server 12B is a server that manages information related to travel in a second language. For example, the second country may be the United States of America and the second language may be English.

[0017] The information processing system 10 may include a large language model (LLM) server 17. Hereinafter, the large language model server 17 will be referred to as an LLM server 17. The information processing system 10 may include a plurality of LLM servers 17. The plurality of LLM servers 17 may include a first LLM server 17A and a second LLM server 17B.

[0018] The LLM server 17 is a server equipped with a large-scale language model. A large-scale language model is a language model constructed using a large amount of data and deep learning technology. The LLM server 17 has a function of controlling various sentences using generative artificial intelligence. The LLM server 17 is equipped with various learning models of the generative artificial intelligence.

[0019] As a specific example, the LLM server 17 has a function of summarizing input text. The LLM server 17 is equipped with a summarization model that uses generative artificial intelligence. The summarization model is a learning model related to summarizing text. The summarization model corresponds to an example of a processing model. The processing model is a learning model related to processing original text.

[0020] The LLM server 17 has a function of translating an input text into a predetermined language. The LLM server 17 has a translation model using generative artificial intelligence. The translation model is a learning model for translating text.

[0021] The LLM server 17 has a function of evaluating the input sentence by comparing it with other input sentences. The LLM server 17 has an evaluation model using generative artificial intelligence. The evaluation model is a learning model that evaluates the input sentence by comparing it with other input sentences.

[0022] The information processing system 10 may include one or more terminal devices 18. As a specific example, the information processing system 10 may include a user terminal device. The user terminal device is a terminal device used by a user. The user terminal device may be a portable terminal device that can be carried by the user. The user is also a person who plans to transact with the transaction target.

[0023] The information processing device 11, one or more travel management servers 12, one or more LLM servers 17, and one or more terminal devices 18 are communicatively connected via a network 19. At least any combination of the information processing device 11, one or more travel management servers 12, one or more LLM servers 17, and one or more terminal devices 18 may be communicatively connected directly without via the network 19. Hereinafter, a description of communication between each device via the network 19 will be omitted.

[0024] <Configuration of terminal device 18> 2, the terminal device 18 is composed of one or more computers. The terminal device 18 includes a terminal control unit 20, a terminal storage unit 21, a terminal communication unit 22, a terminal input unit 23, and a terminal display unit 24.

[0025] The terminal control unit 20 is configured to control the terminal device 18. The terminal control unit 20 includes an arithmetic unit and a main storage medium. The arithmetic unit loads an OS (Operating System) and a program from the terminal storage unit 21 to the main storage medium, and executes the command retrieved from the main storage medium. The arithmetic unit is one or more circuits. The circuit may be a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), or an NPU (Neural network Processing Unit). The terminal storage unit 21 may be a secondary storage medium and may store a program. The program may be a dedicated application for using the information processing system 10.

[0026] The terminal communication unit 22 is implemented as hardware, software, or a combination thereof. The terminal communication unit 22 transmits and receives data to and from the information processing device 11. The terminal input unit 23 is configured to input information in response to a user's operation. The terminal input unit 23 may be a touch panel integrated with the terminal display unit 24. The terminal input unit 23 may be a pointing device of operation buttons. The terminal display unit 24 displays information in response to an output instruction from the terminal control unit 20.

[0027] <Configuration of information processing device 11> As shown in Fig. 3, the information processing device 11 is composed of one or more computers. The information processing device 11 includes a control unit 30, a storage unit 31, and a communication unit 32. The control unit 30 is configured to control the information processing device 11. The control unit 30 includes a calculation device and a main storage medium. The control unit 30 has a similar configuration to the terminal control unit 20, and the description of the calculation device and the main storage medium will be omitted. The storage unit 31 is a secondary storage medium, and stores information for managing the information processing device 11.

[0028] The communication unit 32 is implemented as hardware, software, or a combination of these. The communication unit 32 transmits and receives data between one or more travel management servers 12 and one or more LLM servers 17. The information processing device 11 may include an operation unit that allows an information provider to perform an input operation, and may include a display unit that displays information.

[0029] The travel management server 12 and the LLM server 17 are configured in the same manner as the information processing device 11. In other words, the travel management server 12 and the LLM server 17 have configurations similar to the control unit 30, the memory unit 31, and the communication unit 32 in the information processing device 11. Explanation of the configurations of the travel management server 12 and the LLM server 17 will be omitted.

[0030] <Processing circuit of information processing device 11> In the information processing device 11, the control unit 30 executes a program to configure a processing circuit. The control unit 30 includes, as the processing circuit, an explanatory text acquisition unit 30A, a guideline information acquisition unit 30B, an information transmission unit 30C, and an information reception unit 30D. The control unit 30 includes, as the processing circuit, a summary text acquisition unit 30E, a translation text acquisition unit 30F, an evaluation unit 30G, an information provision unit 30H, and a guideline correction unit 30I.

[0031] The explanation acquisition unit 30A acquires the explanation of the transaction object. Hereinafter, the explanation of the transaction object will be simply referred to as the explanation. The explanation is input by the manager of the transaction object. The explanation is an example of the original text before processing. In other words, the explanation acquisition unit 30A acquires the original text. The explanation acquisition unit 30A corresponds to an example of an original text acquisition unit.

[0032] The description acquisition unit 30A may acquire a description of the travel service entered by the manager of the transaction target from the first travel management server 12A. In other words, the description acquisition unit 30A may acquire a description of the travel service related to a trip to a first country and in a first language.

[0033] The guideline information acquisition unit 30B acquires the guideline information from the storage unit 31. The guideline information is information indicating a guideline regarding summarization of the explanatory text. In other words, the guideline information is information indicating a guideline regarding processing of the original text. The guideline information does not include the information itself requesting the summarization of the explanatory text, but includes information indicating a guideline regarding the summary content of the explanatory text. In other words, the guideline information does not include the information itself requesting the processing of the original text, but includes information indicating a guideline regarding the processing content of the original text. The guideline information includes information regarding the selection of explanatory text. The guideline information includes information regarding the arrangement order of the explanatory text. The guideline information includes information regarding the sentence expression of the explanatory text.

[0034] The guideline information is information set by an administrator of the information processing system 10, unlike the administrator of the transaction object who inputted the explanatory text. The guideline information is information set by an administrator of the information processing device 11.

[0035] The information transmitting unit 30C is configured to transmit information. The information transmitting unit 30C is configured to transmit information to the LLM server 17. As a specific example, the information transmitting unit 30C transmits an explanatory text and guideline information to the LLM server 17. As a result, the information transmitting unit 30C transmits the explanatory text and guideline information to the summary model of the generating artificial intelligence. The information transmitting unit 30C may be configured to transmit information via an API (application programming interface).

[0036] The information receiving unit 30D is configured to receive information. When the information transmitting unit 30C transmits information to the LLM server 17, the information receiving unit 30D is configured to receive information from the LLM server 17. As a specific example, when the information transmitting unit 30C transmits an explanatory text and guideline information to the LLM server 17, the information receiving unit 30D receives a summary text that summarizes the explanatory text from the LLM server 17. The information receiving unit 30D may be configured to receive information via an API (application programming interface).

[0037] The summary acquisition unit 30E acquires a summary of a transaction object that is a summary of an explanatory text. Hereinafter, the summary of a transaction object is simply referred to as a summary. The summary is an example of a processed text after processing. In other words, the summary acquisition unit 30E acquires a processed text that has been processed from an original text. The summary acquisition unit 30E corresponds to an example of a processed text acquisition unit.

[0038] In particular, the summary acquisition unit 30E acquires a summary that summarizes the explanatory text by transmitting the explanatory text and the guideline information to the summary model of the generating artificial intelligence. The summary acquisition unit 30E may acquire the summary text in stages. As a specific example, when the summary acquisition unit 30E acquires a first summary that summarizes the explanatory text, the summary acquisition unit 30E may acquire a second summary that summarizes the explanatory text by transmitting the first summary text and the guideline information to the summary model of the generating artificial intelligence.

[0039] The translation acquisition unit 30F acquires a translation of the transaction object obtained by translating the summary. That is, the translation acquisition unit 30F acquires a translation obtained by translating the processed text. In particular, the translation acquisition unit 30F acquires a translation of the transaction object obtained by translating the summary by sending the summary to the translation model of the generation artificial intelligence.

[0040] As a specific example, the translation acquisition unit 30F acquires a translation of travel services relating to travel to the first country and in a second language by sending a summary of travel services relating to travel to the first country and in a first language to the translation model of the generation artificial intelligence.

[0041] The evaluation unit 30G evaluates the summary sentence obtained based on the guideline information. The evaluation unit 30G evaluates the summary sentence obtained based on the guideline information by transmitting the explanatory text, guideline information, and summary sentence to the evaluation model of the generating artificial intelligence. In other words, the evaluation unit 30G evaluates the processed sentence obtained based on the guideline information by transmitting the original text, guideline information, and processed sentence to the evaluation model of the generating artificial intelligence.

[0042] The evaluation unit 30G may evaluate the first summary sentence obtained based on the guideline information by transmitting the explanatory text, the guideline information, and the first summary sentence to an evaluation model of the generating artificial intelligence. The evaluation unit 30G may evaluate the second summary sentence obtained based on the guideline information by transmitting the explanatory text, the guideline information, and the second summary sentence to an evaluation model of the generating artificial intelligence. The evaluation unit 30G may evaluate the second summary sentence obtained based on the guideline information by transmitting the first summary sentence, the guideline information, and the second summary sentence to an evaluation model of the generating artificial intelligence. The evaluation unit 30G may evaluate the second summary sentence obtained based on the guideline information by transmitting the explanatory text, the first summary sentence, the guideline information, and the second summary sentence to an evaluation model of the generating artificial intelligence.

[0043] The information providing unit 30H provides the summary so that it can be viewed by the prospective user. In other words, the information providing unit 30H provides the processed text so that it can be viewed. The information providing unit 30H provides the summary for each specified item so that it can be viewed by the prospective user of the transaction target. The specified items may be items corresponding to the guideline items described later that are included in the guideline information.

[0044] In particular, the information providing unit 30H may transmit the summary to the second travel management server 12B so that it can be viewed by a prospective user of the transaction object. That is, the information providing unit 30H may provide a translation of the transaction object in a second language obtained by translating the summary in the first language so that it can be viewed. In this way, when the explanation acquisition unit 30A acquires an explanation in the first language from the first travel management server 12A, the information providing unit 30H can transmit a translation of the transaction object in the second language to the second travel management server 12B. That is, the information providing unit 30H may provide a translation of the transaction object in a different language so that it can be viewed by a prospective user of the transaction object.

[0045] The guideline correction unit 30I corrects the guideline information. In particular, the guideline correction unit 30I corrects the guideline information related to the summary of the explanatory text based on the result of the evaluation by the evaluation unit 30G. In other words, the guideline correction unit 30I corrects the guideline information related to the processing of the original text based on the result of the evaluation by the evaluation unit 30G.

[0046] <Information processing of information processing system 10> Here, the information processing of the information processing system 10 will be described with reference to FIG. As shown in Fig. 4, in the information processing system 10, the first travel management server 12A manages descriptions related to a first country. In particular, the first travel management server 12A manages descriptions of travel services for the first country in a first language so that the descriptions can be viewed. In response to a request from a terminal device 18 held by the prospective transaction party, the first travel management server 12A provides the descriptions of travel services for the first country in the first language to the prospective transaction party.

[0047] The second travel management server 12B manages explanatory texts related to the second country. In particular, the second travel management server 12B manages explanatory texts of travel services for the second country in a second language so that the explanatory texts can be viewed. In response to a request from a terminal device 18 possessed by the prospective transaction party, the second travel management server 12B provides the explanatory texts of travel services for the second country in the second language to the prospective transaction party.

[0048] The information processing device 11 manages guideline information. The information processing device 11 acquires explanatory text from the first travel management server 12A through communication with the first travel management server 12A. The information processing device 11 transmits a summary request for requesting summarization, the explanatory text, and the guideline information to the LLM server 17.

[0049] The LLM server 17 manages the summary model. When the LLM server 17 receives a summary request from the information processing device 11, it inputs the summary request, the explanatory text, and the guideline information to the summary model of the generating artificial intelligence. As a result, the explanatory text and the guideline information are input to the summary model of the generating artificial intelligence. The LLM server 17 transmits the summary result output from the summary model to the information processing device 11. The summary result includes the summary text in the first language.

[0050] The information processing device 11 receives the summary result from the LLM server 17. The information processing device 11 receives the summary sentence in the first language included in the summary result from the LLM server 17. As a result, the information processing device 11 acquires the summary sentence by transmitting the explanatory sentence and the guideline information to the summary model of the generation artificial intelligence.

[0051] The information processing device 11 may transmit the summary request, the guideline information, and the first summary sentence acquired from the LLM server 17 to the LLM server 17. In this case, the information processing device 11 acquires the second summary sentence by transmitting the first summary sentence and the guideline information to the summary model of the generation artificial intelligence in the same way as in the case of acquiring the first summary sentence.

[0052] The information processing device 11 transmits to the LLM server 17 a translation request requesting a translation, the summary obtained from the LLM server 17, and information indicating the language into which the translation will be performed. In this case, the information processing device 11 transmits to the LLM server 17 the translation request, the summary in the first language obtained from the LLM server 17, and information indicating the second language as the language into which the translation will be performed.

[0053] The LLM server 17 manages the translation model. When the LLM server 17 receives a translation request from the information processing device 11, it inputs the translation request, the summary, and the translated language into the translation model of the generating artificial intelligence. As a result, the summary is input into the translation model of the generating artificial intelligence. The LLM server 17 transmits the translation result output from the translation model to the information processing device 11. The translation result includes a translation of the transaction object in the second language.

[0054] The information processing device 11 receives the translation result including the translated text from the LLM server 17. The information processing device 11 receives the translation result including the translated text of the transaction object in the second language from the LLM server 17. The information processing device 11 then obtains the translated text by sending the summary text to the translation model of the generating artificial intelligence. The information processing device 11 transmits the obtained translated text of the transaction object to the second travel management server 12B.

[0055] The second travel management server 12B receives a translation of the transaction object from the information processing device 11. The second travel management server 12B manages a viewable translation of the first country travel service in the second language in addition to a description of the second country travel service in the second language. The translation of the first country travel service in the second language is a summary of the first country travel service translated into the second language. In other words, the second travel management server 12B manages a viewable summary of the first country travel service translated into the second language. The second travel management server 12B provides the prospective transactor with the summary of the first country travel service in the second language in response to a request from a terminal device 18 held by the prospective transactor.

[0056] The information processing device 11 transmits an evaluation request requesting an evaluation, an explanatory text, guideline information, and a summary to the LLM server 17. The information processing device 11 may transmit the evaluation request, the explanatory text, guideline information, and a first summary to the LLM server 17. The information processing device 11 may transmit the evaluation request, the explanatory text, guideline information, and a second summary to the LLM server 17. The information processing device 11 may transmit the evaluation request, the first summary, guideline information, and the second summary to the LLM server 17. The information processing device 11 may transmit the evaluation request, the explanatory text, guideline information, and the second summary to the LLM server 17.

[0057] The LLM server 17 manages the evaluation model. When the LLM server 17 receives an evaluation request from the information processing device 11, it inputs the evaluation request, the explanatory text, the guideline information, and the summary text to the evaluation model of the generating artificial intelligence. As a result, the explanatory text, the guideline information, and the summary text are input to the evaluation model of the generating artificial intelligence. The LLM server 17 transmits the evaluation result output from the evaluation model to the information processing device 11.

[0058] The information processing device 11 receives the evaluation result from the LLM server 17. The information processing device 11 then transmits the explanatory text, the guideline information, and the summary text to the evaluation model of the generating artificial intelligence, thereby acquiring an evaluation result for the summary text that is summarized from the explanatory text based on the guideline information. The information processing device 11 may modify the guideline information based on the evaluation result.

[0059] <Guideline information> Next, an example of the guideline information will be described in detail with reference to FIG. As shown in Fig. 5, the guideline information is stored in the storage unit 31. The guideline information includes a plurality of pieces of information indicating guidelines related to summarization. The guideline information is associated with a guideline type and a guideline item. The guideline type is information indicating a type of a guideline related to summarization. The guideline item is information indicating an item of a guideline related to summarization.

[0060] The guideline information includes first guideline information 31A and second guideline information 31B. The first guideline information 31A includes guideline information regarding selection of explanatory text. The first guideline information 31A includes guideline information regarding the arrangement of explanatory text. The first guideline information 31A includes guideline information regarding specified items for summarizing the summary text. The second guideline information 31B includes guideline information regarding the sentence expression of the explanatory text.

[0061] As a specific example, the first guideline information 31A includes guideline types "maintain" and "delete." "Maintain" is a guideline type indicating that a statement for a guideline item is to be left. Guideline items associated with "maintain" may include meal contents, benefits, and services. "Delete" is a guideline type indicating that a statement for a guideline item is not to be left. Guideline items associated with "delete" may include all facilities, customer comments, and the entire facility.

[0062] In the first guideline information 31A, the sorting order is included as a guideline type. In the sorting order, the sorting order of guideline items is determined. The sorting order may be, for example, meal contents, benefits, and services. In the sorting order, it is determined that guideline items are grouped together as prescribed items.

[0063] In the second guideline information 31B, a sentence expression is included as a guideline type. A sentence expression is a guideline type indicating that a sentence expression is to be corrected. The guideline items associated with the sentence expression may include subject completion, metaphorical expressions, and region-specific expressions. Region-specific expressions are expressions that take into account the cultural background of a region.

[0064] <Specific examples of explanatory text, summary text and translation text> Next, a specific example of an explanatory text, a summary text, and a translation text will be described with reference to FIG. 6, a specific example of the explanatory text is a first text 40. The first text 40 is a text entered by an administrator of a transaction subject that provides travel services. The first text 40 includes texts 41 to 48.

[0065] The first text 40 includes texts 41-43 about benefits. The first text 40 includes text 44 about the inn's overall facilities. The first text 40 includes texts 45-47 about the meals. The first text 40 includes text 48 about customer opinions.

[0066] A specific example of the summary sentence is the second sentence 50. The second sentence 50 is a sentence that is summarized from the first sentence 40 based on the guideline information. The second sentence 50 includes sentences 51, 52, and 55 to 57.

[0067] The second text 50 includes texts 55 to 57 about the meal contents. The second text 50 includes texts 51 and 52 about the benefits. In this way, the explanatory text whose guideline type is "keep" is left in the summary text based on the guideline information.

[0068] The second text 50 does not include the text about the inn's overall facilities 44. The second text 50 does not include the text about customer feedback 48. In this way, explanatory text with a guideline type of "delete" is not left in the summary text based on the guideline information.

[0069] The second text 50 is a summary of the texts 55 to 57 about the meal contents as the prescribed items. The second text 50 is a summary of the texts 51 and 52 about the benefits as the prescribed items. In this way, the summary text is adjusted for each prescribed item based on the guideline information.

[0070] The second sentence 50 is a sentence that has been adjusted in order to include sentences 55-57 about the meal details and sentences 51 and 52 about the benefits. In more detail, sentences 55-57 about the meal details have been adjusted in order to precede sentences 51 and 52 about the benefits. In this way, the summary sentence is adjusted in accordance with the order defined as the guideline type based on the guideline information.

[0071] The second sentence 50 is a sentence with the subject complemented from the first sentence 40. The second sentence 50 is a sentence with the abbreviation complemented from the first sentence 40. In detail, the sentence 52 is a sentence adjusted from the expression "Special benefits exclusive to consecutive stays" in the explanatory sentence 42 to the expression "Special benefits exclusive to consecutive stays" by complementing the abbreviation and using "consecutive stayers" complemented as the subject.

[0072] The second sentence 50 is a sentence in which the metaphorical expression has been adjusted from the first sentence 40. In detail, the sentence 51 is a sentence in which the expression "with special benefits for women" in the explanatory sentence 41 has been adjusted to the expression "with special benefits only for women."

[0073] The second sentence 50 is a sentence in which the region-specific expression has been adjusted from the first sentence 40. More specifically, the sentence 56 is a sentence in which the expression "Wagyu" in the explanatory sentence 46 has been adjusted to the expression "Wagyu". In this way, when a direct translation into a foreign language would sound unnatural, it is possible to translate into Roman letters by adding the Roman alphabet instead of translating directly.

[0074] Sentence 57 is a sentence that adds a subject, such as "we." Sentence 57 is an adjustment to sentence 47, which is explanatory and uses the expression "elementary school students and under" to "12 years old and under." In this way, because the ages for schools and grades differ from country to country, converting them into a common age for each country allows foreigners to understand appropriately.

[0075] The second sentence 50 is the sentence 43 as an explanatory sentence with the expression "Prefectural resident discount applicable" deleted. Sentence 43 is a sentence about benefits, but it was deleted because it is a region-specific expression.

[0076] A specific example of a translation is a third sentence 60. The third sentence 60 is a sentence obtained by translating the second sentence 50, which is in Japanese, into English. The third sentence 60 includes sentences 61, 62, and 65-67.

[0077] In the third text 60, sentences 65 to 67 about meal contents are summarized as stipulated items, similar to the second text 50. In the third text 60, sentences 61 and 62 about benefits are summarized as stipulated items, similar to the second text 50.

[0078] <Evaluation Result Information 31C> Next, an example of the evaluation result information 31C indicating the evaluation result will be described in detail with reference to FIG.

[0079] 7, evaluation result information 31C is stored in the storage unit 31. The evaluation result information 31C is managed in the information processing device 11. The evaluation result information 31C is information including the evaluation result acquired from the LLM server 17. The evaluation result information 31C may be information generated every time a summary is acquired from a description.

[0080] The evaluation result information 31C includes a result based on the explanatory text, the guideline information, and the summary. The evaluation result information 31C may include a result based on the explanatory text, the guideline information, and the second summary. The evaluation result information 31C may include both a result based on the explanatory text, the guideline information, and the first summary, and a result based on the first summary, the guideline information, and the second summary.

[0081] In the evaluation result information 31C, a guideline type, a guideline item, an evaluation coefficient, an evaluation result and an evaluation value from the first LLM server 17A, and an evaluation result and an evaluation value from the second LLM server 17B are associated with each other.

[0082] The evaluation coefficient is a coefficient for weighting the evaluation results. The evaluation coefficient can be set by the administrator of the information processing system 10. A coefficient larger than that for evaluation results for which it is desired to give more importance is set.

[0083] The evaluation result is a result output from the LLM server 17. The evaluation result includes an appropriate evaluation result and an inappropriate evaluation result. The appropriate evaluation result is information indicating a result evaluated as being appropriately summarized. The inappropriate evaluation result is information indicating a result evaluated as being inappropriately summarized.

[0084] The evaluation result includes invalid information. The invalid information is information indicating that the item is not to be evaluated. The invalid information is information indicating that the explanatory text does not include a statement corresponding to the guideline type and guideline item. In particular, when a guideline item associated with "maintain" as the guideline type does not include a statement corresponding to the guideline item, invalid information is associated as the evaluation result. When a guideline item associated with "delete" as the guideline type does not include a statement corresponding to the guideline item, invalid information is associated as the evaluation result.

[0085] The evaluation value is information indicating the multiplication result of the evaluation coefficient and the evaluation result. The evaluation result and evaluation value from the first LLM server 17A and the evaluation result and evaluation value from the second LLM server 17B are associated with a comprehensive evaluation result and a comprehensive evaluation value.

[0086] As a specific example, in the evaluation result, "1" is associated with an appropriate evaluation result, "-1" with an inappropriate evaluation result, and "0" with invalid information. The evaluation value is associated with the multiplication result of the evaluation result and the evaluation coefficient. The overall evaluation result is associated with the average of all the evaluation results that were evaluated, but may also be associated with the sum of all the evaluation results that were evaluated. The overall evaluation value is associated with the average of all the evaluation values ​​that were evaluated, but may also be associated with the sum of all the evaluation values ​​that were evaluated.

[0087] In this way, the evaluation result of the summary sentence that has been summarized from the explanatory sentence based on the guideline information can be recognized based on the evaluation value and the overall evaluation value. The evaluation result of the second summary sentence that has been summarized from the first summary sentence based on the guideline information can be recognized based on the evaluation value and the overall evaluation value.

[0088] <Summary control processing> Next, the summarization control process will be described with reference to Fig. 8. The summarization control process is a process executed by the control unit 30 when a summarization condition is satisfied. The summarization condition may be satisfied by an instruction from the administrator of the information processing system 10.

[0089] As shown in Fig. 8, in step S10, the control unit 30 executes an explanatory text acquisition process. In the explanatory text acquisition process, the control unit 30 acquires an explanatory text from the first travel management server 12A by communicating with the first travel management server 12A. In this case, the control unit 30 acquires an explanatory text in a first language related to a travel service in a first country from the first travel management server 12A. The explanatory text is input in the first travel management server 12A by an administrator who provides the travel services.

[0090] In this way, the control unit 30 acquires the explanatory text entered by the administrator of the transaction target. That is, the control unit 30 acquires the original text entered by the administrator who is the source of the information. In step S11, the control unit 30 executes a first guideline information acquisition process. In the first guideline information acquisition process, the control unit 30 reads out the first guideline information 31A from the storage unit 31 to acquire the first guideline information 31A.

[0091] In this manner, the control unit 30 acquires the guideline information regarding the summary of the explanatory text from the storage unit 31. In other words, the control unit 30 acquires the guideline information regarding the processing of the original text from the storage unit 31. In step S12, the control unit 30 executes a first summary request transmission process. In the first summary request transmission process, the control unit 30 transmits a first summary request to the LLM server 17. The control unit 30 may transmit the first summary request to either the first LLM server 17A or the second LLM server 17B.

[0092] The control unit 30 transmits the explanatory text and first guideline information 31A together with the first summary request to the LLM server 17. The first guideline information 31A includes guideline information for generating a summary text by selecting and discarding words from the explanatory text. The first guideline information 31A includes guideline information for generating a summary text by adjusting the order of the explanatory text. The first guideline information 31A includes guideline information for generating a summary text adjusted for each specified item.

[0093] In this way, the control unit 30 generates a prompt including the first summary request, the explanatory text, and the first guideline information 31A, and instructs to summarize the selection of the explanatory text and the arrangement order of the explanatory text, and transmits the generated prompt to the LLM server 17.

[0094] On the other hand, when the LLM server 17 receives the first summary request, it inputs the explanatory sentences and the first guideline information 31A into the summary model. As a result, in response to receiving the first summary request, the LLM server 17 selects from the explanatory sentences based on the first guideline information 31A and generates a summary sentence by adjusting the order of the explanatory sentences for each specified item. This summary sentence corresponds to an example of a first summary sentence. The LLM server 17 transmits the summary result including the summary sentence to the information processing device 11.

[0095] In step S13, the control unit 30 executes a first summary acquisition process. In the first summary acquisition process, the control unit 30 acquires a summary by receiving a summary result from the LLM server 17. In this manner, the control unit 30 acquires a summary based on the first guideline information 31A. In this case, the control unit 30 acquires a summary that is summarized from an explanation in the first language related to a travel service in the first country based on the first guideline information 31A. The control unit 30 stores the acquired summary in the memory unit 31.

[0096] In this way, the control unit 30 obtains a summary that summarizes the explanatory text by transmitting the explanatory text and the guideline information to the summary model of the generating AI. In other words, the control unit 30 obtains a processed text that processes the original text by transmitting the original text and the guideline information to the processing model of the generating AI.

[0097] The control unit 30 executes the processes of steps S11 to S13 as a first stage process. In the first stage process, the control unit 30 acquires a summary sentence in which the explanatory sentences are selected and the order of the explanatory sentences is adjusted for each specified item based on the first guideline information 31A.

[0098] In step S14, the control unit 30 executes a second guideline information acquisition process. In the second guideline information acquisition process, the control unit 30 reads the second guideline information 31B from the storage unit 31 to acquire the second guideline information 31B.

[0099] In this manner, the control unit 30 acquires the guideline information regarding the summary of the explanatory text from the storage unit 31. In other words, the control unit 30 acquires the guideline information regarding the processing of the original text from the storage unit 31. In step S15, the control unit 30 executes a second summary request transmission process. In the second summary request transmission process, the control unit 30 transmits a second summary request to the LLM server 17. The control unit 30 may transmit the second summary request to either the first LLM server 17A or the second LLM server 17B.

[0100] The control unit 30 transmits the first summary and the second guideline information 31B together with the second summary request to the LLM server 17. The second guideline information 31B includes guideline information for generating a summary in which the sentence expression of the explanatory text is adjusted.

[0101] In this way, the control unit 30 generates a prompt that includes the second summary request, the first summary sentence, and the second guideline information 31B and instructs to summarize the sentence expression of the explanatory sentence, and transmits the generated prompt to the LLM server 17.

[0102] On the other hand, when the LLM server 17 receives the second summary request, it inputs the first summary sentence and the second guideline information 31B into the summary model. As a result, in response to receiving the second summary request, the LLM server 17 generates a summary sentence in which the sentence expression of the explanatory text is adjusted based on the second guideline information 31B. This summary sentence corresponds to an example of a second summary sentence. The LLM server 17 transmits the summary result including the summary sentence to the information processing device 11.

[0103] In step S16, the control unit 30 executes a second summary acquisition process. In the second summary acquisition process, the control unit 30 acquires a summary by receiving a summary result from the LLM server 17. In this manner, the control unit 30 acquires a second summary based on the second guideline information 31B. In this case, the control unit 30 acquires a summary that is summarized from an explanation in the first language regarding a travel service in the first country based on the second guideline information 31B. The control unit 30 stores the acquired summary in the memory unit 31.

[0104] In this way, the control unit 30 obtains a summary that summarizes the explanatory text by transmitting the explanatory text and the guideline information to the summary model of the generating AI. In other words, the control unit 30 obtains a processed text that processes the original text by transmitting the original text and the guideline information to the processing model of the generating AI.

[0105] The control unit 30 executes the processes of steps S14 to S16 as a second stage process. In the second stage process, the control unit 30 acquires a summary text in which the sentence expression of the explanatory text is adjusted based on the second guideline information 31B.

[0106] In step S17, the control unit 30 executes a translation request transmission process. In the translation request transmission process, the control unit 30 transmits a translation request to the LLM server 17. The control unit 30 may transmit the translation request to either the first LLM server 17A or the second LLM server 17B.

[0107] In addition to the translation request, the control unit 30 transmits the summary and information indicating the language into which the summary will be translated to the LLM server 17. In this way, the control unit 30 generates a prompt that includes the translation request, the summary, and information indicating the language into which the summary will be translated, and transmits it to the LLM server 17.

[0108] On the other hand, when the LLM server 17 receives a translation request, it inputs the summary and the translation language into the translation model. In response to the translation request, the LLM server 17 generates a translation by translating the summary into the specified language. The LLM server 17 transmits the translation result including the translation to the information processing device 11.

[0109] In step S18, the control unit 30 executes a translation acquisition process. In the translation acquisition process, the control unit 30 acquires the translation by receiving the translation result from the LLM server 17. In this case, the control unit 30 acquires a translation obtained by translating a summary in a first language about travel services in a first country into a second language. In other words, the control unit 30 acquires the summary in a second language about travel services in the first country as a translation. The control unit 30 stores the acquired translation in the memory unit 31.

[0110] In this way, the control unit 30 executes the processes of steps S17 and S18 as a third stage process. In the third stage process, the control unit 30 obtains a translation of the summary into a different language.

[0111] In step S19, the control unit 30 executes information provision processing. In the information provision processing, the control unit 30 transmits the acquired translation to the second travel management server 12B. As a result, the second travel management server 12B controls the received translation so that it can be viewed. In particular, the second travel management server 12B controls the received translation so that it can be viewed for each specified item. In other words, the control unit 30 provides the prospective user of the transaction subject with a summary for each specified item. In particular, the control unit 30 provides the summary translated into a different language as the translation to the prospective user of the transaction subject.

[0112] <Evaluation control process> Next, the evaluation control process will be described with reference to Fig. 9. The evaluation control process is a process executed by the control unit 30 when an evaluation condition is satisfied. The evaluation condition may be satisfied by an instruction from the administrator of the information processing system 10. The evaluation condition may be satisfied when a summary of the description is obtained.

[0113] In step S20, the control unit 30 executes an evaluation information acquisition process. In the evaluation information acquisition process, the control unit 30 reads an explanatory sentence, guideline information, and a summary for evaluation as evaluation information from the storage unit 31. In this way, the control unit 30 acquires the explanatory sentence, guideline information, and summary for evaluation.

[0114] In step S21, the control unit 30 executes a first evaluation request transmission process. In the first evaluation request transmission process, the control unit 30 transmits a first evaluation request to the first LLM server 17A. The first evaluation request is an evaluation request to be transmitted to the first LLM server 17A.

[0115] The control unit 30 transmits the explanatory text, guideline information, and summary text acquired as the evaluation information to the first LLM server 17A in addition to the first evaluation request. In particular, the control unit 30 transmits information to the first LLM server 17A to evaluate whether the explanatory text and summary text are an appropriate evaluation result, an inappropriate evaluation result, or invalid information for each guideline item of the guideline information.

[0116] In this way, the control unit 30 generates a prompt that includes a first evaluation request, an explanatory text, guideline information, and a summary text, and instructs the user to evaluate the summary text that has been summarized from the explanatory text based on the guideline information, and transmits the prompt to the first LLM server 17A.

[0117] On the other hand, when the first LLM server 17A receives the first evaluation request, it inputs the explanatory text, the guideline information, and the summary text into the evaluation model. As a result, in response to receiving the first evaluation request, the first LLM server 17A generates an evaluation result for the summary text that is summarized from the explanatory text based on the guideline information. In particular, in response to receiving the first evaluation request, the first LLM server 17A generates an evaluation result for each guideline item for the summary text that is summarized from the explanatory text based on the guideline information. The first LLM server 17A transmits the evaluation result to the information processing device 11.

[0118] In step S22, the control unit 30 executes a first evaluation result acquisition process. In the first evaluation result acquisition process, the control unit 30 acquires the first evaluation result by receiving the evaluation result from the first LLM server 17A. In this manner, the control unit 30 acquires the evaluation result for the summary sentence that is summarized from the explanatory sentence based on the guideline information.

[0119] The control unit 30 stores the acquired evaluation result as evaluation result information 31C in the storage unit 31. In particular, the control unit 30 calculates an evaluation value by multiplying the evaluation result by an evaluation coefficient. The control unit 30 stores the calculated evaluation value in the storage unit 31 as evaluation result information 31C.

[0120] In step S23, the control unit 30 executes a second evaluation request transmission process. In the second evaluation request transmission process, the control unit 30 transmits a second evaluation request to the second LLM server 17B. The second evaluation request is an evaluation request to be transmitted to the second LLM server 17B.

[0121] The control unit 30 transmits the explanatory text, guideline information, and summary text acquired as evaluation information to the second LLM server 17B in addition to the second evaluation request. In particular, the control unit 30 transmits to the second LLM server 17B information evaluating whether the explanatory text and summary text are an appropriate evaluation result, an inappropriate evaluation result, or invalid information for each guideline item of the guideline information. The information transmitted to the first LLM server 17A and the information transmitted to the second LLM server 17B are the same information.

[0122] In this way, the control unit 30 generates a prompt that includes the second evaluation request, an explanatory text, guideline information, and a summary text, and instructs the user to evaluate the summary text that has been summarized from the explanatory text based on the guideline information, and transmits the prompt to the second LLM server 17B.

[0123] On the other hand, when the second LLM server 17B receives the second evaluation request, it inputs the explanatory text, the guideline information, and the summary text into the evaluation model. As a result, in response to receiving the second evaluation request, the second LLM server 17B generates an evaluation result for the summary text summarized from the explanatory text based on the guideline information. In particular, in response to receiving the second evaluation request, the second LLM server 17B generates an evaluation result for each guideline item for the summary text summarized from the explanatory text based on the guideline information. The second LLM server 17B transmits the evaluation result to the information processing device 11.

[0124] In step S24, the control unit 30 executes a second evaluation result acquisition process. In the second evaluation result acquisition process, the control unit 30 acquires the second evaluation result by receiving the evaluation result from the second LLM server 17B. In this manner, the control unit 30 acquires the evaluation result for the summary sentence that is summarized from the explanatory sentence based on the guideline information.

[0125] The control unit 30 stores the acquired evaluation result as evaluation result information 31C in the storage unit 31. In particular, the control unit 30 calculates an evaluation value by multiplying the evaluation result by an evaluation coefficient. The control unit 30 stores the calculated evaluation value in the storage unit 31 as evaluation result information 31C.

[0126] In step S25, the control unit 30 executes an evaluation process. In the evaluation process, the control unit 30 performs an evaluation based on the evaluation result information 31C stored in the storage unit 31. The control unit 30 evaluates the evaluation result information 31C stored in the storage unit 31 for each guideline item. In particular, the control unit 30 transmits the explanatory text, the guideline information, and the summary text to the evaluation model, thereby performing an evaluation of the summary text acquired based on the guideline information.

[0127] As a specific example, the control unit 30 evaluates whether to include or exclude a summary sentence based on the evaluation results of guideline items associated with "maintain" as the guideline type. In particular, the control unit 30 evaluates whether information should be left as a summary sentence in the explanatory text based on the evaluation results of guideline items associated with "maintain" as the guideline type. The control unit 30 evaluates whether information should not be left as a summary sentence in the explanatory text based on the evaluation results of guideline items associated with "delete" as the guideline type.

[0128] When an appropriate evaluation result and an inappropriate evaluation result are associated as the evaluation result of a guideline item associated with "maintenance" as the guideline type, the control unit 30 evaluates whether the information should be left as a summary in the explanatory text. When invalid information is associated as the evaluation result of a guideline item associated with "maintenance" as the guideline type, the control unit 30 determines that the explanatory text does not contain information to be left as a summary. In this case, the control unit 30 does not evaluate whether the information should be left as a summary in the explanatory text.

[0129] When an appropriate evaluation result and an inappropriate evaluation result are associated as the evaluation result of a guideline item associated with deletion as the guideline type, the control unit 30 evaluates whether the information is to be left as a summary in the explanatory text. When invalid information is associated as the evaluation result of a guideline item associated with deletion as the guideline type, the control unit 30 determines that the explanatory text does not contain information that is to be left as a summary. In this case, the control unit 30 does not evaluate whether the information is to be left as a summary in the explanatory text.

[0130] The control unit 30 evaluates the order of the summary sentence based on the evaluation results of the guideline items to which the order is associated as the guideline type. The control unit 30 evaluates the sentence expression of the summary sentence based on the evaluation results of the guideline items to which the sentence expression is associated as the guideline type.

[0131] The control unit 30 also performs a first evaluation of the summary by transmitting the explanatory text, guideline information, and summary to a first evaluation model of the first LLM server 17A. The control unit 30 performs a second evaluation of the summary by transmitting the explanatory text, guideline information, and summary to a second evaluation model of the second LLM server 17B. The control unit 30 then performs an evaluation of the summary by comparing the first evaluation result with the second evaluation result.

[0132] In step S26, the control unit 30 determines whether or not the needle correction condition is met. The needle correction condition is met based on the evaluation result. More specifically, the needle correction condition is met based on the evaluation value.

[0133] The guideline revision condition may be established based on the first evaluation result and the second evaluation result. The guideline revision condition may be established when there is a guideline item for which both the evaluation value corresponding to the first evaluation result and the evaluation value corresponding to the second evaluation result are equal to or less than a specified value. The guideline revision condition may be established when there is a guideline item for which at least one of the evaluation value corresponding to the first evaluation result and the evaluation value corresponding to the second evaluation result is equal to or less than a specified value. The guideline revision condition may be established when both the overall evaluation value corresponding to the first evaluation result and the overall evaluation value corresponding to the second evaluation result are equal to or less than a specified value. The guideline revision condition may be established when at least one of the overall evaluation value corresponding to the first evaluation result and the overall evaluation value corresponding to the second evaluation result is equal to or less than a specified value.

[0134] If the control unit 30 determines that the needle correction condition is not met, the process proceeds to step S29. If the control unit 30 determines that the needle correction condition is met, the process proceeds to step S27.

[0135] In step S27, the control unit 30 executes a correction guideline information generation process. In the correction guideline information generation process, the control unit 30 generates correction guideline information for correcting the guideline information. In particular, the control unit 30 may generate, as the correction guideline information, information indicating a guideline item for which both the evaluation value corresponding to the first evaluation result and the evaluation value corresponding to the second evaluation result are equal to or less than a specified value.

[0136] In step S28, the control unit 30 executes a correction guideline information notification process. In the correction guideline information notification process, the control unit 30 notifies the generated correction guideline information. To give a specific example, the control unit 30 may notify the correction guideline information to the operation terminal device managed by the operator of the information processing system 10.

[0137] In step S29, the control unit 30 determines whether there is a correction instruction. The correction instruction may be input by the operator of the information processing system 10. The correction instruction may include a correction target and correction content for correcting the guideline information. When the control unit 30 determines that there is no correction instruction, it ends the evaluation control process. When the control unit 30 determines that there is a correction instruction, it transfers the process to step S30.

[0138] In step S30, the control unit 30 executes a guideline information correction process. In the guideline information correction process, the control unit 30 corrects the guideline information based on the correction instruction. The control unit 30 updates the guideline information according to the correction instruction by storing the corrected guideline information in the storage unit 31. In this way, the control unit 30 corrects the guideline information regarding the summary of the explanatory text based on the evaluated result.

[0139] <Actions and Effects of the First Embodiment> The actions and effects of the first embodiment will be described. (1-1) The control unit 30 acquires the explanatory text input by the administrator of the transaction target. The control unit 30 acquires the guideline information regarding the summary of the explanatory text from the storage unit 31. The control unit 30 obtains a summary text obtained by summarizing the explanatory text by transmitting the explanatory text and the guideline information to the summary model of the generation artificial intelligence. Therefore, by transmitting the guideline information to the summary model of the generation artificial intelligence in addition to the explanatory text input by the administrator, the possibility of obtaining an appropriate summary text along with the operation of the information processing system 10 can be increased. Therefore, the accuracy of summarizing from the explanatory text input by the administrator can be improved.

[0140] (1-2) The guideline information includes information regarding the selection of explanatory texts. Therefore, by transmitting the guideline information to the summary model of the generating artificial intelligence in addition to the explanatory texts input by the administrator, it is possible to increase the possibility of acquiring an appropriate summary regarding the selection of explanatory texts as the information processing system 10 is operated. Therefore, it is possible to improve the accuracy of summarization from the explanatory texts input by the administrator.

[0141] (1-3) The guideline information includes information regarding the order of explanatory text. Therefore, by transmitting the guideline information to the summary model of the generating AI in addition to the explanatory text input by the administrator, it is possible to increase the possibility that an appropriate summary text can be obtained for the order of explanatory text as the information processing system 10 is operated. Therefore, it is possible to improve the accuracy of summarization from the explanatory text input by the administrator.

[0142] (1-4) The guideline information includes information regarding the sentence expression of the explanatory text. Therefore, by transmitting the guideline information to the summary model of the generating artificial intelligence in addition to the explanatory text input by the administrator, it is possible to increase the possibility that an appropriate summary text can be obtained for the sentence expression of the explanatory text as the information processing system 10 is operated. Therefore, it is possible to improve the accuracy of summarization from the explanatory text input by the administrator.

[0143] (1-5) The control unit 30 provides the summary for each specified item so that it can be viewed by the prospective user of the transaction target. Therefore, it is possible to provide the prospective user of the transaction target with a summary with improved accuracy based on the explanation entered by the administrator.

[0144] (1-6) The control unit 30 translates the abstract into a different language and provides the translation so that it can be viewed by the prospective user of the transaction target. This improves the accuracy of summarizing the explanatory text entered by the administrator, and makes it possible to provide the prospective user of the transaction target with the abstract translated into a desired language.

[0145] (1-7) Furthermore, in the past, it has been desired to appropriately evaluate whether a desired summary sentence has been acquired during the operation of the information processing system 10. Therefore, the control unit 30 transmits the explanatory sentence, the guideline information, and the summary sentence to an evaluation model of the generating artificial intelligence, thereby evaluating the summary sentence based on the guideline information. Therefore, by transmitting the explanatory sentence, the guideline information, and the summary sentence to the evaluation model of the generating artificial intelligence, it is possible to evaluate whether an appropriate summary sentence has been acquired during the operation of the information processing system 10. This makes it possible to determine, based on the evaluation result, whether an appropriate summary sentence has been acquired during the operation of the information processing system 10. Then, it is possible to increase the possibility that an appropriate summary sentence can be acquired during the operation of the information processing system 10. Therefore, it is possible to improve the accuracy of summarizing from the explanatory sentence input by the administrator.

[0146] (1-8) The control unit 30 evaluates the selection of the summary sentences. Therefore, by transmitting the explanatory sentence, guideline information, and the summary sentence to the evaluation model of the generation artificial intelligence, it is possible to evaluate whether an appropriate summary sentence has been acquired in terms of the selection of the summary sentences as the information processing system 10 is operated. This makes it possible to determine, based on the evaluation results, whether an appropriate summary sentence has been acquired in terms of the selection of the summary sentences as the information processing system 10 is operated. This makes it possible to improve the accuracy of summarizing from the explanatory sentences entered by the administrator.

[0147] (1-9) When the description does not contain information to be kept as a summary, the control unit 30 does not evaluate whether the description contains information to be kept as a summary. Therefore, by selecting evaluation targets without using unnecessary information as evaluation targets, it is possible to improve the accuracy of evaluation as to whether an appropriate summary has been obtained in the operation of the information processing system 10. Therefore, it is possible to improve the accuracy of summarization from the description input by the administrator.

[0148] (1-10) When the description does not contain information that should not be retained as a summary, the control unit 30 does not evaluate the description as to whether it is information that should not be retained as a summary. Therefore, by selecting evaluation targets without using unnecessary information as evaluation targets, it is possible to improve the accuracy of evaluation as to whether an appropriate summary has been obtained in the operation of the information processing system 10. Therefore, it is possible to improve the accuracy of summarization from the description input by the administrator.

[0149] (1-11) The control unit 30 evaluates the order of the summary sentences. Therefore, by transmitting the explanatory sentence, guideline information, and summary sentence to the evaluation model of the generation artificial intelligence, it is possible to evaluate whether appropriate summary sentences have been acquired in terms of the order of the summary sentences as the information processing system 10 is operated. This makes it possible to determine, based on the evaluation result, whether appropriate summary sentences have been acquired in terms of the order of the summary sentences as the information processing system 10 is operated. This makes it possible to improve the accuracy of summarizing from the explanatory sentences input by the administrator.

[0150] (1-12) The control unit 30 evaluates the sentence expression of the summary sentence. Therefore, by transmitting the explanatory sentence, guideline information, and summary sentence to the evaluation model of the generation artificial intelligence, it is possible to evaluate whether an appropriate summary sentence has been acquired with respect to the sentence expression of the summary sentence as the information processing system 10 is operated. This makes it possible to determine, based on the evaluation result, whether an appropriate summary sentence has been acquired with respect to the sentence expression of the summary sentence as the information processing system 10 is operated. Therefore, it is possible to improve the accuracy of summarizing from the explanatory sentence input by the administrator.

[0151] (1-13) The control unit 30 evaluates the summary based on the evaluation value calculated by combining the evaluation result from the evaluation model and the evaluation coefficient. This allows weighting of the evaluation result by the evaluation coefficient. This improves the accuracy of summarizing the explanatory text entered by the administrator.

[0152] (1-14) The control unit 30 performs a first evaluation of the summary by transmitting the explanatory text, guideline information, and summary to a first evaluation model of the generating artificial intelligence. The control unit 30 performs a second evaluation of the summary by transmitting the explanatory text, guideline information, and summary to a second evaluation model of the generating artificial intelligence. The control unit 30 evaluates the summary by comparing the first evaluation with the second evaluation. Therefore, it is possible to determine whether an appropriate summary has been obtained in conjunction with the operation of the information processing system 10 based on both the evaluation result by the first evaluation model and the evaluation result by the second evaluation model. Therefore, it is possible to improve the accuracy of summarizing the explanatory text input by the administrator.

[0153] (1-15) The control unit 30 corrects the guideline information based on the evaluation result. Therefore, the guideline information itself can be corrected based on the evaluation result as to whether an appropriate summary sentence is obtained along with the operation of the information processing system 10. Therefore, the accuracy of summarizing from the explanation sentence input by the administrator can be improved.

[0154] [Second embodiment] Next, a second embodiment will be described. In the following description, the same components as those in the already described embodiment are denoted by the same reference numerals, and duplicated descriptions thereof will be omitted or simplified.

[0155] In the second embodiment, the control unit 30 executes the summary control process for the first LLM server 17A. That is, the control unit 30 acquires a summary by outputting the explanatory text and the guideline information to the first processed model. In this manner, the summary acquired from the first processed model corresponds to an example of the first processed text.

[0156] The control unit 30 also executes a summary control process for the second LLM server 17B. That is, the control unit 30 acquires a summary by outputting the explanatory text and the guideline information to the second processed model. In this manner, the summary acquired from the second processed model corresponds to an example of the second processed text.

[0157] Then, the control unit 30 executes the evaluation control process for the first LLM server 17A. In this case, the control unit 30 outputs the summary sentence, the original sentence, and the guideline information acquired from the first processed model in step S21 to the first LLM server 17A, and acquires the evaluation result in step S22.

[0158] In step S23, the control unit 30 outputs the summary text, the original text, and the guideline information acquired from the second processed model to the first LLM server 17A, thereby acquiring an evaluation result in step S24.

[0159] In this way, the control unit 30 transmits the explanatory text, the guideline information, the summary obtained from the first processed model, and the summary obtained from the second processed model to the evaluation model. As a result, the control unit 30 evaluates the summary obtained from the first processed model and the summary obtained from the second processed model.

[0160] In particular, in step S25, the control unit 30 compares the evaluation value for the summary obtained from the first processing model with the evaluation value for the summary obtained from the second processing model. In this way, the control unit 30 can evaluate which of the summary obtained from the first processing model or the summary obtained from the second processing model is more appropriate based on the comparison result.

[0161] <Actions and Effects of the Second Embodiment> The operation and effects of the second embodiment will be described. (2-1) The control unit 30 transmits the explanatory text, the guideline information, the summary text acquired from the first processing model, and the summary text acquired from the second processing model to the evaluation model, thereby evaluating the summary text from each processing model. Therefore, by comparing the evaluation values ​​for the summary texts acquired from the multiple processing models, it is possible to evaluate the summary texts acquired from the multiple processing models. This makes it possible to evaluate the processing accuracy of the multiple processing models. Therefore, it is possible to improve the accuracy of summarizing the explanatory text entered by the administrator.

[0162] [Example of change] This embodiment can be modified as follows: This embodiment and the following modifications can be combined with each other to the extent that there is no technical contradiction.

[0163] The control unit 30 may obtain a translation from the summary when a translation condition is met. The translation condition may be met at the instruction of an operator of the information processing system 10. The translation condition may be met depending on the type of server providing the summary. The control unit 30 does not have to obtain a translation from the summary.

[0164] The control unit 30 may execute the first stage process and the second stage process as a process of three or more stages. As a specific example, the control unit 30 may acquire a first summary sentence selected from the explanatory text by transmitting the explanatory text and the first guideline information 31A to the LLM server 17. The control unit 30 may acquire a second summary sentence in which the order of the explanatory text is adjusted by transmitting the first summary sentence and the first guideline information 31A to the LLM server 17. The control unit 30 may acquire a third summary sentence in which the sentence expression of the explanatory text is adjusted as a summary sentence by transmitting the second summary sentence and the second guideline information 31B to the LLM server 17. The control unit 30 may execute the stage process of multiple stages in an arbitrary execution order. As the stage process of multiple stages, the control unit 30 may acquire a first summary sentence selected from the explanatory text, and then acquire a second summary sentence in which the order of the first summary sentence is adjusted. In this way, the control unit 30 may execute the stage process of multiple stages in an arbitrary execution order. By inputting various information to the learning model in multiple stages, the accuracy of the information output from the learning model can be improved. In addition, when inputting various information to the learning model in multiple stages, if the amount of information output from the learning model becomes small compared to the amount of information input to the learning model, the amount of information input to the learning model in the next stage can be reduced.

[0165] The control unit 30 may execute the first stage process and the second stage process as a single process. As a specific example, the control unit 30 may transmit the explanatory text, the first guideline information 31A, and the second guideline information 31B to the LLM server 17, and obtain a summary text that is a summary of the explanatory text based on the guideline information. This can reduce the number of times that data is input to the learning model.

[0166] The control unit 30 may obtain an evaluation result by communication with the second LLM server 17B for the summary obtained by communication with the first LLM server 17A. The control unit 30 may obtain an evaluation result by communication with the first LLM server 17A for the summary obtained by communication with the second LLM server 17B. In other words, the control unit 30 may use a different LLM server 17 for obtaining the summary and the LLM server 17 for obtaining the evaluation result.

[0167] The evaluation coefficient may be set based on the behavioral history of the prospective trader with respect to the description and summary. In other words, the evaluation coefficient may be based on the behavioral history of one or more prospective traders. A high evaluation coefficient may be set for a specified item having a high value indicating the behavioral history of one or more prospective traders. The behavioral history may include impressions (IMP). The impressions indicate the number of times a specified item in the description and summary was displayed. The behavioral history may include click-through rates (CTR). The click-through rates indicate the ratio of the number of clicks to the number of times a specified item in the description and summary was displayed. The behavioral history may include conversions (CV). Conversions indicate the number of times a targeted behavior was performed starting from a specified item in the description and summary. Conversions include the establishment of a transaction in a travel service, including the purchase of a product or service related to travel. Conversions include the establishment of a transaction in an e-commerce service, including the purchase of a product or service in e-commerce. As a specific example, a high evaluation coefficient may be set for a prescribed item with a high impression, a high evaluation coefficient may be set for a prescribed item with a high click-through rate, or a high evaluation coefficient may be set for a prescribed item with a high conversion rate.

[0168] Based on the evaluation results, the control unit 30 may select an LLM server 17 with a high evaluation result as a server for acquiring a summary sentence. In other words, the control unit 30 may select a summary model with a high evaluation result based on the evaluation results.

[0169] The control unit 30 may leave as is any text that does not correspond to the guideline types of maintenance and deletion. The control unit 30 may delete any text that does not correspond to the guideline types of maintenance and deletion without leaving it.

[0170] The control unit 30 may evaluate at least one of the selection of explanatory text, the arrangement of explanatory text, and the sentence expression of explanatory text. The control unit 30 may perform either one of the evaluation of whether information is to be left in the explanatory text as a summary sentence or the evaluation of whether information is not to be left in the explanatory text as a summary sentence, and not the other. The control unit 30 may evaluate content other than the selection of explanatory text, the arrangement of explanatory text, and the sentence expression of explanatory text.

[0171] The control unit 30 may execute a process of summarizing at least one of the selection of explanatory sentences, the arrangement of explanatory sentences, and the sentence expressions of explanatory sentences from the explanatory sentences. The control unit 30 may execute either one of the process of leaving the explanatory sentence as a summary sentence or the process of not leaving the explanatory sentence as a summary sentence, and not execute the other. The control unit 30 may execute a process of summarizing from the explanatory sentences about content other than the selection of explanatory sentences, the arrangement of explanatory sentences, and the sentence expressions of explanatory sentences.

[0172] The information processing system 10 may provide a service other than the travel service. As a specific example, the information processing system 10 may provide an electronic commerce service. In this case, the description of the transaction object may be a description of a product traded in the electronic commerce service. The information processing system 10 may provide a video distribution service. In this case, the description of the transaction object may be a description of a video traded in the video distribution service. The information processing system 10 may provide a plurality of services. The information processing system 10 may not provide a travel service. In other words, the information processing system 10 may be a system that provides a service that is a transaction object. The information processing system 10 itself may be a system that does not provide a service that is a transaction object.

[0173] The first travel management server 12A and the second travel management server 12B may be configured as an integrated travel management server 12. The travel management server 12 may include a third travel management server separate from the first travel management server 12A and the second travel management server 12B.

[0174] The first LLM server 17A and the second LLM server 17B may be configured as an integrated LLM server 17. The LLM server 17 may include a third LLM server separate from the first LLM server 17A and the second LLM server 17B.

[0175] The LLM server 17 may manage at least one of the summary model, the translation model, and the evaluation model as an integrated learning model. The LLM server 17 may be provided with another learning model in addition to the summary model, the translation model, and the evaluation model.

[0176] The information processing device 11 may have the configuration of another server. As a specific example, the information processing device 11 may have a part or all of the configuration related to the travel management server 12. The information processing device 11 may have a part or all of the configuration related to the LLM server 17.

[0177] The information processing device 11 may be composed of a plurality of servers. As a specific example, the plurality of servers may include a server for acquiring a summary from an explanatory text based on guideline information. The plurality of servers may include a server for acquiring a translation from the summary. The plurality of servers may include a server for evaluating a summary summarised from an explanatory text based on guideline information. The plurality of servers may be managed by different or the same person.

[0178] The information processing device 11 may acquire something other than an explanatory text, as long as it acquires an original text. The information processing device 11 may acquire something other than a summary text that is summarized from an original text, as long as it acquires a processed text that is processed from the original text. The guideline information may be information other than information regarding the summary of the original text, as long as it is information regarding the processing of the original text. In other words, the information processing device 11 may be configured to acquire a processed text of the original text by inputting the original text and guideline information regarding the processing of the original text into a processing model.

[0179] The information processing device 11 may acquire processing information including a processed image based on original information including an original image and guide information. In this case, the guide information may include information indicating a guide for maintaining an image as processing information of the original information. The guide information may include information indicating a guide for deleting an image as processing information of the original information.

[0180] The term "at least any" as used herein means one or more of the desired options. As an example, the term "at least any" as used herein means only one option or both options if the number of options is two. As another example, the term "at least any" as used herein means only one option or any combination of two or more options if the number of options is three or more.

[0181] [Note] The technical ideas understood from the above-described embodiment and modified examples will be described below. (A) An information processing device includes an original text acquisition unit that acquires an original text input by an administrator, a guideline information acquisition unit that acquires guideline information regarding processing of the original text acquired by the original text acquisition unit from a memory unit, a processed sentence acquisition unit that acquires a processed sentence obtained by processing the original text acquired by the original text acquisition unit by transmitting the original text acquired by the original text acquisition unit and the guideline information acquired by the guideline information acquisition unit to a processing model, and an evaluation unit that evaluates the processed sentence acquired by the processed sentence acquisition unit by transmitting the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, and the processed sentence acquired by the processed sentence acquisition unit to an evaluation model.

[0182] (B) In the information processing device described in (A), the guideline information includes information regarding the selection of original text acquired by the original text acquisition unit, and the evaluation unit evaluates the selection of processed text acquired by the processed text acquisition unit.

[0183] In the information processing device described in (C) and (B), if the original text acquired by the original text acquisition unit does not contain information to be retained as a processed text, the evaluation unit does not evaluate whether the original text acquired by the original text acquisition unit contains information to be retained as a processed text.

[0184] In the information processing device described in (D) (B) or (C), if the original text acquired by the original text acquisition unit does not contain information that should not be retained as a processed text, the evaluation unit does not evaluate whether the original text acquired by the original text acquisition unit contains information that should not be retained as a processed text.

[0185] (E) In an information processing device described in any one of (A) to (D), the guideline information includes information regarding the order of the original text acquired by the original text acquisition unit, and the evaluation unit evaluates the order of the processed text acquired by the processed text acquisition unit.

[0186] (F) In an information processing device described in any one of (A) to (E), the guideline information includes information regarding the sentence expression of the original sentence acquired by the original sentence acquisition unit, and the evaluation unit evaluates the sentence expression of the processed sentence acquired by the processed sentence acquisition unit.

[0187] (G) In an information processing device described in any one of (A) to (F), the evaluation unit evaluates the processed sentence acquired by the processed sentence acquisition unit based on an evaluation value calculated from an evaluation result from an evaluation model and an evaluation coefficient.

[0188] In the information processing device described in (H) and (G), the evaluation unit evaluates the processed sentence acquired by the processed sentence acquisition unit based on an evaluation value calculated from the evaluation result from the evaluation model and an evaluation coefficient based on the behavioral history of the prospective transaction party.

[0189] In the information processing device described in any one of (I)(A) to (H), the evaluation unit transmits the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, the first processed sentence acquired by the processed sentence acquisition unit from a first processed model, and the second processed sentence acquired by the processed sentence acquisition unit from a second processed model to an evaluation model, thereby comparing an evaluation of the first processed sentence acquired by the processed sentence acquisition unit with an evaluation of the second processed sentence acquired by the processed sentence acquisition unit, and performing an evaluation of the first processed sentence and the second processed sentence acquired by the processed sentence acquisition unit.

[0190] (J) An information processing device described in any one of (A) to (I) includes a guideline correction unit that corrects guideline information regarding processing of the original text acquired by the original text acquisition unit based on the result of evaluation by the evaluation unit.

[0191] (K) The information processing system includes an original text acquisition unit that acquires an original text input by an administrator, a guideline information acquisition unit that acquires guideline information regarding processing of the original text acquired by the original text acquisition unit from a memory unit, a processed sentence acquisition unit that acquires a processed sentence obtained by processing the original text acquired by the original text acquisition unit by transmitting the original text acquired by the original text acquisition unit and the guideline information acquired by the guideline information acquisition unit to a processing model, and an evaluation unit that evaluates the processed sentence acquired by the processed sentence acquisition unit by transmitting the original text acquired by the original text acquisition unit, the guideline information acquired by the guideline information acquisition unit, and the processed sentence acquired by the processed sentence acquisition unit to an evaluation model.

[0192] (L) An information processing method in which one or more computers execute the following steps: acquiring an original text input by an administrator; acquiring guideline information regarding processing of the original text from a memory unit; acquiring a processed sentence obtained by processing the original text by transmitting the original text and the guideline information to a processing model; and evaluating the processed sentence by transmitting the original text, the guideline information, and the processed sentence to an evaluation model.

[0193] (M) The program causes one or more computers to execute the following operations: acquiring an original text input by an administrator; acquiring guideline information regarding processing of the original text from a memory unit; acquiring a processed sentence obtained by processing the original text by transmitting the original text and the guideline information to a processing model; and evaluating the processed sentence by transmitting the original text, the guideline information, and the processed sentence to an evaluation model. [Explanation of symbols]

[0194] 10...information processing system, 11...information processing device, 12...travel management server, 12A...first travel management server, 12B...second travel management server, 17...large scale language model server, 17A...first large scale language model server, 17B...second large scale language model server, 18...terminal device, 30...control unit, 30A...explanatory text acquisition unit (original text acquisition unit), 30B...guideline information acquisition unit, 30E...summary text acquisition unit (processed text acquisition unit), 30G...evaluation unit, 30H...information provision unit, 30I...guideline correction unit, 31...memory unit, 31A...first guideline information, 31B...second guideline information, 31C...evaluation result information.

Claims

1. an original text acquisition unit that acquires an original text input by an administrator; a guideline information acquisition unit that acquires, from a storage unit, guideline information regarding processing of the original text acquired by the original text acquisition unit; a processed sentence acquisition unit that generates a processing prompt including an original sentence acquired by the original sentence acquisition unit and guideline information acquired by the guideline information acquisition unit, and instructs the user to process the original sentence acquired by the original sentence acquisition unit based on the guideline information acquired by the guideline information acquisition unit, and transmits the processing prompt to a processing model that is a large-scale language model, thereby acquiring a processed sentence obtained by processing the original sentence acquired by the original sentence acquisition unit; an evaluation unit which generates an evaluation prompt including an original text acquired by the original text acquisition unit, guideline information acquired by the guideline information acquisition unit, and a processed text acquired by the processed text acquisition unit, and which instructs an evaluation of whether the processed text acquired by the processed text acquisition unit has been appropriately processed from the original text acquired by the original text acquisition unit based on the guideline information acquired by the guideline information acquisition unit, and which evaluates the processed text acquired by the processed text acquisition unit by transmitting the evaluation prompt to an evaluation model which is a large-scale language model; An information processing device comprising:

2. 2. The information processing device according to claim 1, the guideline information includes information regarding selection of the original text acquired by the original text acquisition unit, the evaluation unit generates the evaluation prompt instructing, when the original text acquired by the original text acquisition unit contains information to be left as a processed sentence, to evaluate the information to be left as the processed sentence in the original text acquired by the original text acquisition unit as appropriate when the information to be left as the processed sentence in the original text acquired by the original text acquisition unit is included in the processed sentence acquired by the processed sentence acquisition unit, and to evaluate the information to be left as the processed sentence in the original text acquired by the original text acquisition unit as inappropriate when the information to be left as the processed sentence in the original text acquired by the original text acquisition unit is not included in the processed sentence acquired by the processed sentence acquisition unit, and performs an evaluation of the selection of the processed sentence acquired by the processed sentence acquisition unit by transmitting the evaluation prompt to the evaluation model; Information processing device.

3. 3. The information processing device according to claim 2, When the original text acquired by the original text acquisition unit does not include information to be left as a processed text, the evaluation unit does not evaluate whether the original text acquired by the original text acquisition unit includes information to be left as a processed text. Information processing device.

4. 2. The information processing device according to claim 1, the guideline information includes information regarding selection of the original text acquired by the original text acquisition unit, the evaluation unit generates the evaluation prompt instructing, when the original text acquired by the original text acquisition unit contains information that is not to be left as a processed sentence, to evaluate the processed sentence acquired by the processed sentence as appropriate when the information that is not to be left as a processed sentence in the original text acquired by the original text acquisition unit is not included in the processed sentence acquired by the processed sentence acquisition unit, and to evaluate the processed sentence acquired by the processed sentence acquisition unit as inappropriate when the information that is not to be left as a processed sentence in the original text acquired by the original text acquisition unit is included in the processed sentence acquired by the processed sentence acquisition unit, and performs an evaluation of the selection of the processed sentence acquired by the processed sentence acquisition unit by transmitting the evaluation prompt to the evaluation model; Information processing device.

5. 5. The information processing device according to claim 4, When the original text acquired by the original text acquisition unit does not include information that should not be left as a processed text, the evaluation unit does not evaluate whether the original text acquired by the original text acquisition unit includes information that should not be left as a processed text. Information processing device.

6. 2. The information processing device according to claim 1, the guideline information includes prescribed items as information regarding the order of the original text acquired by the original text acquisition unit, The evaluation unit generates the evaluation prompt instructing to evaluate whether the processed sentence acquired by the processed sentence acquisition unit is a processed sentence obtained by adjusting the original sentence acquired by the original sentence acquisition unit to the order of each of the specified items, and transmits the evaluation prompt to the evaluation model, thereby evaluating the order of the processed sentence acquired by the processed sentence acquisition unit. Information processing device.

7. 2. The information processing device according to claim 1, the guideline information includes information regarding a sentence expression of the original text acquired by the original text acquisition unit, the evaluation unit generates the evaluation prompt instructing to evaluate whether the processed sentence acquired by the processed sentence acquisition unit is a processed sentence obtained by modifying a sentence expression of the original sentence acquired by the original sentence acquisition unit, and transmits the evaluation prompt to the evaluation model, thereby evaluating the sentence expression of the processed sentence acquired by the processed sentence acquisition unit. Information processing device.

8. In the information processing device according to any one of claims 1 to 7, The evaluation unit evaluates the processed sentence acquired by the processed sentence acquisition unit based on an evaluation value calculated from the evaluation result from the evaluation model and an evaluation coefficient. Information processing device.

9. 9. The information processing device according to claim 8, The evaluation unit evaluates the processed sentence acquired by the processed sentence acquisition unit based on an evaluation value calculated from an evaluation result from the evaluation model and an evaluation coefficient based on a behavior history of the prospective transactor. Information processing device.

10. In the information processing device according to any one of claims 1 to 7, The evaluation unit includes an original text acquired by the original text acquisition unit, guideline information acquired by the guideline information acquisition unit, a first processed sentence acquired by the processed sentence acquisition unit from a first processed model which is a large-scale language model, and a second processed sentence acquired by the processed sentence acquisition unit from a second processed model which is a large-scale language model, and generates the evaluation prompt that instructs to evaluate whether the first processed sentence and the second processed sentence acquired by the processed sentence acquisition unit have been appropriately processed from the original text acquired by the original text acquisition unit based on the guideline information acquired by the guideline information acquisition unit, and transmits the evaluation prompt to the evaluation model to compare an evaluation of the first processed sentence acquired by the processed sentence acquisition unit with an evaluation of the second processed sentence acquired by the processed sentence acquisition unit, and evaluates the first processed sentence and the second processed sentence acquired by the processed sentence acquisition unit. Information processing device.

11. In the information processing device according to any one of claims 1 to 7, a guideline correction unit that corrects guideline information regarding processing of the original text acquired by the original text acquisition unit based on the result of the evaluation by the evaluation unit; Information processing device.

12. an original text acquisition unit that acquires an original text input by an administrator; a guideline information acquisition unit that acquires, from a storage unit, guideline information regarding processing of the original text acquired by the original text acquisition unit; a processed sentence acquisition unit that generates a processing prompt including an original sentence acquired by the original sentence acquisition unit and guideline information acquired by the guideline information acquisition unit, and instructs the user to process the original sentence acquired by the original sentence acquisition unit based on the guideline information acquired by the guideline information acquisition unit, and transmits the processing prompt to a processing model that is a large-scale language model, thereby acquiring a processed sentence obtained by processing the original sentence acquired by the original sentence acquisition unit; an evaluation unit which generates an evaluation prompt including an original text acquired by the original text acquisition unit, guideline information acquired by the guideline information acquisition unit, and a processed text acquired by the processed text acquisition unit, and which instructs an evaluation of whether the processed text acquired by the processed text acquisition unit has been appropriately processed from the original text acquired by the original text acquisition unit based on the guideline information acquired by the guideline information acquisition unit, and which evaluates the processed text acquired by the processed text acquisition unit by transmitting the evaluation prompt to an evaluation model which is a large-scale language model; An information processing system comprising:

13. One or more computers Obtaining the original text entered by the administrator; Obtaining guideline information regarding processing of the original text from a storage unit; generating a processing prompt including the original text and the guideline information, the processing prompt instructing to process the original text based on the guideline information; Sending the processing prompt to a processing model, which is a large-scale language model, to obtain a processed sentence by processing the original sentence; generating an evaluation prompt including the original text, the guideline information, and the processed text, the evaluation prompt instructing the user to evaluate whether the processed text has been appropriately processed from the original text based on the guideline information; evaluating the processed sentence by sending the evaluation prompt to an evaluation model, the evaluation model being a large-scale language model; An information processing method.

14. On one or more computers, Obtaining the original text entered by the administrator; Obtaining guideline information regarding processing of the original text from a storage unit; generating a processing prompt including the original text and the guideline information, the processing prompt instructing to process the original text based on the guideline information; Sending the processing prompt to a processing model, which is a large-scale language model, to obtain a processed sentence by processing the original sentence; generating an evaluation prompt including the original text, the guideline information, and the processed text, the evaluation prompt instructing the user to evaluate whether the processed text has been appropriately processed from the original text based on the guideline information; evaluating the processed sentence by sending the evaluation prompt to an evaluation model, the evaluation model being a large-scale language model; A program to execute.

Images