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

Abstract

This invention provides an information processing device, an information processing system, an information processing method, and a program that can improve the convenience of evaluating editing accuracy. [Solution] The information processing device comprises at least one memory configured to store a program, and at least one processor configured to execute processing based on the program. The at least one processor performs the following: generates a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications; and inputs the first prompt to a language model to obtain editing errors in association with error classifications.

Description

Technical Field

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

Background Art

[0002] Conventionally, for example, as shown in Patent Document 1, there has been disclosed an information processing system in which, after an evaluator determines whether a translation result translated by a learning model is appropriate, the determination result by the evaluator is input by the evaluator. In such an information processing system, the learning model can be evaluated by evaluating the translation result, which is an example of the editing result.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in such an information processing system, as a result of the evaluator determining whether the editing result is appropriate, the determination result is input by the evaluator. Therefore, it takes time and effort for the evaluator. Thus, it is desired to improve the convenience regarding the evaluation of the editing accuracy.

Means for Solving the Problems

[0005] An information processing device that solves the above problems comprises at least one memory configured to store a program, and at least one processor configured to execute processing based on the program, wherein the at least one processor generates a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputs the first prompt to a language model to obtain the editing errors in association with the error classifications.

[0006] An information processing system for solving the above problems comprises at least one memory configured to store a program, and at least one processor configured to execute processing based on the program, wherein the at least one processor generates a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputs the first prompt to a language model to obtain the editing errors in association with the error classifications.

[0007] An information processing method that solves the above problem involves at least one processor generating a first prompt that includes a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputting the first prompt into a language model to obtain the editing errors in accordance with the error classifications.

[0008] A program that solves the above problem causes at least one processor to generate a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in correspondence with error classifications, and to input the first prompt into a language model to obtain the editing errors in correspondence with the error classifications. [Effects of the Invention]

[0009] According to the present invention, the convenience of evaluating editing accuracy can be improved. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows the overall configuration of the information processing system according to the first embodiment. [Figure 2] Figure 2 shows the error management database of the first embodiment. [Figure 3] Figure 3 shows the coefficient database of the first embodiment. [Figure 4] Figure 4 is a flowchart showing the source text translation process in the first embodiment. [Figure 5] Figure 5 is a flowchart showing the error management process of the first embodiment. [Figure 6] Figure 6 is a flowchart showing the error determination process of the first embodiment. [Figure 7] Figure 7 is a flowchart showing the error classification process of the first embodiment. [Figure 8] Figure 8 is a flowchart showing the severity control process of the first embodiment. [Figure 9] Figure 9 is a flowchart showing the evaluation control process of the first embodiment. [Figure 10] Figure 10 is a flowchart showing the display control process of the first embodiment. [Figure 11] Figure 11 shows the display contents of the display device of the first embodiment. [Modes for carrying out the invention]

[0011] [First Embodiment] One 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> As shown in FIG. 1, the information processing system 10 is a system that analyzes the translation accuracy of a translated text. The translated text is a text obtained by translating the original text in the first language into the second language. The translated text is also an edited text in which the original text has been edited. The translated text is also a processed text in which the original text has been processed. For example, the first language may be Japanese and the second language may be English. For example, the first language may be English and the second language may be Japanese. The information processing system 10 may be a system that obtains a translated text from an original text.

[0013] The original text is at least one sentence and may include multiple sentences. For example, the original text may be an explanatory text in an e-commerce service. For example, the original text may be an explanatory text in a travel service.

[0014] The information processing system 10 includes an information processing device 11. The information processing device 11 obtains a translated text. The information processing device 11 obtains a translation error in the translated text. The information processing device 11 analyzes the translated text. The information processing device 11 evaluates the translated text. The information processing device 11 displays an image related to the translation error.

[0015] The information processing system 10 may include at least one translation server 12. The translation server 12 may be a server for translating an input original text. The information processing system 10 may include a first translation server 13 and a second translation server 14.

[0016] The first translation server 13 may include a first translation language model 13A. The first translation language model 13A is a language model for translating an original text. The first translation language model 13A may be a machine translation model for translating an original text. The first translation language model 13A corresponds to an example of a first machine translation model, and the translated text obtained by translating the original text by the first translation language model 13A corresponds to an example of a first translated text.

[0017] The second translation server 14 may include a second translation language model 14A. The second translation language model 14A is a language model for translating the original text. The second translation language model 14A may be a machine translation model for translating the original text. The second translation language model 14A corresponds to an example of the second machine translation model, and the translated text obtained by translating the original text by the second translation language model 14A corresponds to an example of the second translated text.

[0018] The information processing system 10 may include a large language model (LLM) server 15. Hereinafter, the large language model is referred to as LLM. The LLM server 15 may include an LLM 15A. The LLM 15A is a language model constructed by a large amount of data and deep learning technology. The LLM server 15 has a function of controlling various texts using generative artificial intelligence. The LLM server 15 may have a function of controlling various images using generative artificial intelligence. The LLM server 15 includes various learning models of generative artificial intelligence.

[0019] Taking a specific example, the LLM server 15 has a function of detecting a translation error based on the input original text and translated text. The LLM server 15 has a function of generating an analysis result obtained by analyzing the translation error. The analysis of the translation error may include the error classification of the translation error, the determination of the propriety of the translation error, and the content regarding the severity of the translation error.

[0020] The information processing device 11, the translation server 12, and the LLM server 15 may be able to communicate with each other via the network 19. Hereinafter, the description of communicating via the network 19 for the communication between the information processing device 11, the translation server 12, and the LLM server 15 is omitted.

[0021] <Configuration of the information processing device 11> The information processing device 11 may be implemented by at least one computer. The information processing device 11 includes at least one processor 20 and at least one memory 21. The information processing device 11 includes a communication interface 22. In the figure, the interface is indicated as I / F. The information processing device 11 may also include an input device 23 and a display device 24.

[0022] The processor 20 controls the information processing device 11. The processor 20 is configured to execute processing based on the program 26 stored in the memory 21. The processor 20 may be a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), or an NPU (Neural Network Processing Unit). The processor 20 may include an integrated circuit, such as an application-specific integrated circuit, or it may be an integrated circuit. The processor 20 may be a combination of these.

[0023] Memory 21 is configured to store program 26. Memory 21 is a non-temporary computer-readable medium for storing program 26, but may include temporary computer-readable medium. Program 26 may include dedicated applications for using the information processing system 10. Memory 21 also stores database 27.

[0024] The communication interface 22 is implemented as hardware, software, or a combination thereof. The communication interface 22 sends and receives data to and from the translation server 12 and the LLM server 15.

[0025] The input device 23 inputs data in response to user operations. The input device 23 may be a touch panel integrated with the display device 24. The input device 23 may also be a pointing device for operation buttons. The display device 24 displays information in response to output instructions from the processor 20.

[0026] The translation server 12 is configured in the same way as the information processing device 11. Therefore, the description of the processor, memory, and communication interface of the translation server 12 is omitted. The LLM server 15 is configured in the same way as the information processing device 11. Therefore, the description of the processor, memory, and communication interface of the LLM server 15 is omitted.

[0027] <Data structure of database 27> As shown in Figure 2, the memory 21 of the information processing device 11 stores the error management database 30 as database 27. Database 27 includes the error management database 30. The error management database 30 is a database for managing translation errors.

[0028] The error management database 30 comprises at least one dataset 30A. The dataset 30A associates a source text identifier, a translated text identifier, and an evaluation value. In the diagram, the identifier is shown as ID. In dataset 30A, at least one error identifier is associated with the source text identifier. In dataset 30A, the error identifier, error content, error suitability, primary error classification, error classification, group, and severity are associated. In dataset 30A, at least one error classification is associated with the error identifier.

[0029] The source text identifier is data used to identify the source text. The translated text identifier is data used to identify the translated text. The evaluation value is data that indicates the evaluation result of the translated text. The evaluation value is a value that indicates the degree of translation error. The evaluation value may be higher if there are many translation errors. In other words, the lower the evaluation value, the higher the translation accuracy is considered to be.

[0030] The error identifier is data used to identify translation errors. The error details are data that describe the nature of the translation error. The error suitability is data that shows the result of the reassessment of the suitability of the translation error after it has been determined to be a translation error from the translated text.

[0031] The primary error classification is data that shows the main error classification for translation errors. The error classification is data that shows the error classification for translation errors. The primary error classification is the appropriate error classification from at least one error classification.

[0032] More specifically, the error classification may include a first error classification, a second error classification, and a third error classification. A concrete example of this is that the error classification may include accuracy, fluency, and style.

[0033] Error classification may be divided into multiple levels. Error classification may include both major and minor categories. For example, the major categories of error classification may include accuracy, fluency, and style. The minor category of accuracy may include mistranslation and omission.

[0034] A group is data that indicates a group of translation errors based on their error content. A group is different from an error classification. Multiple translation errors with overlapping error content are grouped together as the same group.

[0035] Severity is data indicating the severity of a translation error. Severity may include severe, moderate, and mild. Specifically, severe errors include translation errors that have a significant impact on the user. Mild errors include translation errors that do not change the meaning but degrade the quality of the written expression.

[0036] In this way, the error management database 30 manages the evaluation value of the translated text and data related to translation errors. More specifically, the error management database 30 manages the results of the translation error analysis and the evaluation result of the translated text based on the result that at least one translation error has been detected in the translated text.

[0037] As shown in Figure 3, the memory 21 of the information processing device 11 stores the coefficient database 31 as database 27. Database 27 includes the coefficient database 31. The coefficient database 31 is a database of coefficients used when calculating the evaluation value of translation errors.

[0038] The coefficient database 31 associates combinations of primary error classifications and severity levels with corresponding coefficients. The evaluation value of the translated text is calculated based on the result of a calculation between the number of translation errors corresponding to the primary error classification and severity level combination and the corresponding coefficient.

[0039] The coefficients may differ for each of the first, second, and third error classifications. The coefficients may be larger for the first error classification than for the second error classification, and larger for the second error classification than for the third error classification. The coefficients may be larger for the first error classification than for the second error classification, and larger for the second error classification than for the third error classification. In this way, the first error classification has a higher priority in evaluating translation errors than the second error classification. The second error classification has a higher priority in evaluating translation errors than the third error classification.

[0040] The coefficients may differ for severe, moderate, and mild errors. The coefficients may be larger for severe errors than for moderate errors, and larger for moderate errors than for mild errors. The coefficients may be such that the evaluation score is higher for severe errors than for moderate errors, and higher for moderate errors than for mild errors. In this way, severe errors have a higher priority in evaluating translation errors than moderate errors. Moderate errors have a higher priority in evaluating translation errors than mild errors.

[0041] <Original text translation processing> Next, the source text translation process will be described with reference to Figure 4. The source text translation process is executed by the processor 20 when a translation instruction for the source text is received. The translation instruction includes a source text identifier, the target language, and the translation server 12 that will be the primary translator. The translation instruction may also include the language of the source text. The translation instruction includes an instruction to have all specified translation servers 12 act as primary translators and translate the source text into the specified language.

[0042] As shown in Figure 4, in step S10, the processor 20 performs a translation server determination process. In this process, the processor 20 determines the translation server 12 that will be the primary translator from among the translation servers 12 included in the translation instruction.

[0043] The translation server 12 that will be the primary translator does not include any translation servers 12 included in the translation instruction that have already become the primary translator. The translation server 12 that will be the primary translator is determined from among the translation servers 12 included in the translation instruction that have not yet become the primary translator.

[0044] For example, if, among the first translation server 13 and the second translation server 14 included in the translation instruction, the processor 20 determines the second translation server 14 to be the translation subject if the first translation server 13 has already become the translation subject and the second translation server 14 has not yet become the translation subject. In this way, the processor 20 sequentially determines the translation servers 12 included in the translation instruction to be the translation subjects.

[0045] In step S11, the processor 20 executes the source text retrieval process. In this process, the processor 20 reads the source text corresponding to the source text identifier included in the translation instruction from memory 21. As a result, the processor 20 retrieves the source text based on the translation instruction.

[0046] In step S12, the processor 20 performs a translation prompt generation process. In this process, the processor 20 generates a translation prompt. The translation prompt includes the source text. The translation prompt may also include the language of the source text. The translation prompt includes the target language. The translation prompt includes instructions to translate the source text into the target language.

[0047] In step S13, the processor 20 performs translation prompt input processing. In this process, the processor 20 sends the translation prompt generated in step S12 to the translation server 12, which is the main translator. The translation prompt is input into the translation language model at the translation server 12, which is the main translator. In this way, the processor 20 inputs the translation prompt into the translation language model of the translation server 12, which is the main translator.

[0048] In step S14, the processor 20 executes the translation acquisition process. In this process, the processor 20 receives the translation from the translation server 12, which is the translation source. As a result, the processor 20 acquires the translation. The processor 20 generates a translation identifier and registers it in the error management database 30 to correspond to the source identifier. The processor 20 stores the translation in memory 21 to correspond to the translation identifier.

[0049] In step S15, the processor 20 determines whether it has obtained all the translated texts from each of the translation servers 12 that are the primary translators. If the processor 20 determines that it has not obtained all the translated texts, it proceeds to step S10. If the processor 20 determines that it has obtained all the translated texts, it terminates the source text translation process. In this way, the processor 20 repeatedly executes steps S10 to S14 until it has obtained all the translated texts from each of the translation servers 12 that are the primary translators.

[0050] In this way, the processor 20 obtains the translated text by inputting the source text into the translation language model. More specifically, the processor 20 obtains the first translated text by inputting the source text into the first translation language model 13A. The processor 20 obtains the second translated text by inputting the source text into the second translation language model 14A.

[0051] <Translation Analysis Processing> Next, the translation analysis process will be described with reference to Figures 5 to 9. Error management processing is performed by the processor 20 when an analysis instruction is received. The analysis instruction includes a source text identifier and at least one translated text identifier.

[0052] In step S20, the processor 20 performs the analysis target determination process. In this process, the processor 20 determines the translation to be analyzed from at least one translation identifier corresponding to the source text identifier.

[0053] The translations to be analyzed do not include translations corresponding to translation identifiers included in the analysis instruction that have already been analyzed. The translations to be analyzed are determined from translations corresponding to translation identifiers included in the analysis instruction that have not yet been analyzed. For example, if, of the first and second translations included in the analysis instruction, the first translation has already been analyzed but the second translation has not, the processor 20 will determine the second translation to be analyzed.

[0054] <Error detection process> In step S21, the processor 20 performs an error determination process. In this process, the processor 20 makes a determination regarding translation errors for the translated text that has been determined to be the target of analysis.

[0055] As shown in Figure 6, in the error determination process, in step S30, the processor 20 executes the source text acquisition process. In this process, the processor 20 acquires the source text corresponding to the source text identifier included in the analysis instruction from memory 21. The processor 20 registers the source text identifier in the error management database 30.

[0056] In step S31, the processor 20 executes the translation acquisition process. In this process, the processor 20 acquires the translated text corresponding to the translation identifier determined to be the target of analysis from memory 21. The processor 20 registers the translated text identifier in the error management database 30 so that it corresponds to the source text identifier.

[0057] In step S32, the processor 20 executes an error determination prompt generation process. In this process, the processor 20 generates an error determination prompt. Specifically, the processor 20 generates an error determination prompt that includes the source text obtained in step S30, the translated text obtained in step S31, and instructions regarding the determination of translation errors.

[0058] Instructions for determining translation errors include extracting at least one translation error from the translated text relative to the source text. Instructions for determining translation errors include determining the error classification of at least one error. Instructions for determining translation errors include returning at least one error corresponding to the error classification.

[0059] Thus, the error detection prompt includes the source text, the translated text obtained from the source text, and instructions for determining translation errors in the translated text by associating them with error classifications. The error detection prompt is an example of the first prompt.

[0060] Instructions for determining translation errors may include error guideline data for determining the error classification. The error guideline data includes data indicating the error classification. The error guideline data may include data indicating the major and minor categories of the error classification. For example, the error guideline data may include accuracy, fluency, and style as major categories of the error classification.

[0061] In step S33, the processor 20 performs an error determination prompt input process. In this process, the processor 20 sends the error determination prompt generated in step S32 to the LLM 15A. The error determination prompt is input to the LLM 15A in the LLM server 15. In this way, the processor 20 inputs the error determination prompt to the LLM 15A of the LLM server 15.

[0062] In step S34, the processor 20 executes the error judgment result acquisition process. In this process, the processor 20 receives the error judgment result from the LLM server 15. As a result, the processor 20 acquires the error judgment result. In other words, the processor 20 acquires the translation error corresponding to the error classification by inputting the error judgment prompt to the LLM 15A.

[0063] In particular, the processor 20 obtains an error determination result that associates the error content of at least one translation error contained in the translated text with an error classification. The processor 20 may also obtain an error determination result that associates multiple duplicate error content contained in the translated text with an error classification.

[0064] In step S35, the processor 20 executes an error determination result registration process. In this process, the processor 20 registers the error determination result obtained in step S34 in the error management database 30 so as to correspond to the source identifier and translation identifier.

[0065] More specifically, the processor 20 generates an error identifier corresponding to at least one translation error contained in the translated text. The processor 20 registers the error details and error classification in the error management database 30 to correspond to the source text identifier, translation identifier, and error identifier.

[0066] In particular, even if multiple error contents overlap, the processor 20 registers the error contents and error classifications in the error management database 30 so that they correspond to the source text identifier, translation identifier, and error identifier, respectively.

[0067] In step S36, the processor 20 performs error grouping. In this process, if multiple error identifiers correspond to the translated text identifier determined to be analyzed, the processor 20 groups the translation errors.

[0068] If the processor 20 finds that multiple error identifiers correspond to multiple overlapping error contents, it updates the error management database 30 to associate the same group with the multiple error identifiers that have overlapping error contents. In this way, when the processor 20 obtains multiple translation errors from the source text, it groups the overlapping translation errors among the multiple translation errors.

[0069] In step S37, the processor 20 executes an error suitability prompt generation process. In this process, the processor 20 generates an error suitability prompt. Specifically, the processor 20 generates an error suitability prompt that includes the source text obtained in step S30, the translated text obtained in step S31, the error judgment result obtained in step S34, and an instruction to determine whether the error judgment is appropriate or not. The error suitability prompt may also include an error identifier corresponding to the error judgment result.

[0070] In particular, for multiple error determination results grouped together as the same group, the processor 20 generates an error suitability prompt that includes one error determination result and excludes the remaining error determination results. In other words, the processor 20 generates an error suitability prompt that includes the grouped error determination results.

[0071] Instructions for determining the appropriateness of an error include re-evaluating whether the error result determined to be included in the translation relative to the source text is appropriate. Instructions for determining the appropriateness of an error include returning a response indicating whether the error result is appropriate as a result of the re-evaluation.

[0072] Thus, the error suitability prompt includes the source text, the translated text, the translation error, and instructions for determining whether the translation error is suitable or not. The error suitability prompt is an example of a second prompt.

[0073] In step S38, the processor 20 performs error suitability prompt input processing. In this process, the processor 20 sends the error suitability prompt generated in step S37 to the LLM 15A. The error suitability prompt is input to the LLM 15A in the LLM server 15. In this way, the processor 20 inputs the error suitability prompt to the LLM 15A of the LLM server 15.

[0074] In step S39, the processor 20 executes the error suitability result acquisition process. In this process, the processor 20 receives the error suitability result from the LLM server 15. As a result, the processor 20 acquires the error suitability result. In other words, the processor 20 acquires the suitability of the translation error by inputting an error suitability prompt to the LLM 15A.

[0075] In step S40, the processor 20 executes the error compliance result registration process. In this process, the processor 20 registers the error compliance results obtained in step S39 in the error management database 30 so as to correspond to the source text identifier, translated text identifier, and error identifier. In particular, the processor 20 registers the same error compliance result in the error management database 30 so as to correspond to multiple error identifiers that are grouped together as the same group.

[0076] <Error Classification Process> As shown in Figure 5, once the error determination process is complete, in step S22, the processor 20 performs error classification. In this process, the processor 20 performs error classification of translation errors.

[0077] As shown in Figure 7, in the error classification process, in step S50, the processor 20 executes the error classification prompt generation process. In this process, the processor 20 generates an error classification prompt.

[0078] More specifically, the processor 20 obtains the error identifier corresponding to the error suitability result for which an error has been properly determined from the error management database 30. The processor 20 generates an error classification prompt that includes the error content and error classification corresponding to the error identifier, and an instruction to select the appropriate primary error classification from the error classifications.

[0079] In this case, the processor 20 may retrieve from the error management database 30 the error identifiers that correspond to multiple error classifications among the error identifiers that correspond to the appropriate error suitability result for error determination. The processor 20 does not need to retrieve from the error management database 30 the error identifiers that correspond to one error classification among the error identifiers that correspond to the appropriate error suitability result for error determination. In other words, the processor 20 may generate an error classification prompt when multiple error classifications are associated with a translation error.

[0080] In particular, for error classifications corresponding to multiple error identifiers grouped together as the same group, the processor 20 generates an error classification prompt that includes multiple error classifications corresponding to the grouped error identifiers. In other words, the processor 20 generates an error classification prompt that includes grouped error classifications.

[0081] Thus, the error classification prompt includes a translation error, multiple error classifications, and instructions to select the appropriate primary error classification from the multiple error classifications. The error classification prompt is an example of a third prompt.

[0082] In step S51, the processor 20 performs error classification prompt input processing. In this process, the processor 20 sends the error classification prompt generated in step S50 to the LLM 15A. The error classification prompt is input to the LLM 15A in the LLM server 15. In this way, the processor 20 inputs the error classification prompt to the LLM 15A of the LLM server 15.

[0083] In step S52, the processor 20 executes the classification selection result acquisition process. In this process, the processor 20 receives the primary error classification from the LLM server 15. As a result, the processor 20 obtains the primary error classification. In other words, the processor 20 obtains the primary error classification corresponding to the translation error by inputting an error classification prompt to the LLM 15A.

[0084] In step S53, the processor 20 executes the classification selection result registration process. In this process, the processor 20 registers the acquired primary error classification in the error management database 30 so that it corresponds to the error identifier. In particular, the processor 20 registers the same primary error classification in the error management database 30 so that it corresponds to multiple error identifiers that are grouped together as the same group.

[0085] <Severity Determination Process> As shown in Figure 5, once the error classification process is complete, in step S23, the processor 20 executes a severity determination process. In this process, the processor 20 determines the severity of the translation error.

[0086] As shown in Figure 8, in the severity determination process, in step S60, the processor 20 executes a severity prompt generation process. In this process, the processor 20 generates a severity prompt.

[0087] More specifically, the processor 20 retrieves the error identifier corresponding to the error suitability result for which an error has been appropriately determined from the error management database 30. The processor 20 generates a severity prompt that includes the error content corresponding to the error identifier, the main error classification, and instructions for determining the severity of the translation error.

[0088] Thus, the severity prompt includes the translation error, the primary error classification, and instructions for determining the severity of the translation error. The translation error may also include the error description. The severity prompt is an example of a fourth prompt.

[0089] Severity prompts may include severity guideline data for determining the severity of a translation error. Severity guideline data is data that indicates guidelines for determining the severity of a translation error. For example, severity guideline data may include guidelines for determining translation errors that have a significant impact on the user as severe. For example, severity guideline data may include guidelines for determining translation errors that do not have a significant impact on the user but have a different meaning as moderate. For example, severity guideline data may include guidelines for determining translation errors that do not have a different meaning but degrade the quality of the written expression as minor.

[0090] In step S61, the processor 20 performs severity prompt input processing. In this process, the processor 20 sends the severity prompt generated in step S60 to the LLM 15A. The severity prompt is input to the LLM 15A at the LLM server 15. In this way, the processor 20 inputs the severity prompt to the LLM 15A of the LLM server 15.

[0091] In step S62, the processor 20 performs a severity acquisition process. In this process, the processor 20 receives the severity from the LLM server 15. As a result, the processor 20 acquires the severity. That is, the processor 20 acquires the severity of the translation error by inputting a severity prompt to the LLM 15A.

[0092] In step S63, the processor 20 performs a severity registration process. In this process, the processor 20 registers the acquired severity in the error management database 30 so that it corresponds to the error identifier. In particular, the processor 20 registers the same severity in the error management database 30 so that it corresponds to multiple error identifiers that are grouped together as the same group.

[0093] <Evaluation control process> As shown in Figure 5, once the severity determination process is complete, in step S24, the processor 20 executes the evaluation control process. In this process, the processor 20 evaluates the translated text. In other words, the processor 20 evaluates the translation server 12. It can also be said that the processor 20 evaluates the translation language model.

[0094] As shown in Figure 9, in the evaluation control process, in step S70, the processor 20 executes a character count acquisition process. In this process, the processor 20 counts the number of characters in the translated text to be analyzed. In this way, the processor 20 obtains the character count of the translated text.

[0095] In step S71, the processor 20 performs an evaluation value calculation process. In this process, the processor 20 calculates the evaluation value of the translated text to be analyzed. The processor 20 may calculate the evaluation value of the translated text to be analyzed using any calculation method.

[0096] More specifically, the processor 20 refers to the error management database 30 and calculates the number of translation errors corresponding to the combination of primary error classification and severity for each error identifier corresponding to the translated text identifier being analyzed.

[0097] The processor 20 refers to the coefficient database 31 and reads the coefficients corresponding to the combination of primary error classification and severity from memory 21. The processor 20 multiplies the number of translation errors by the coefficient for each combination of primary error classification and severity.

[0098] Processor 20 adds up the multiplication results for each combination of primary error classification and severity. Processor 20 calculates an evaluation value by dividing the summation result by the number of characters in the translated text.

[0099] In this way, the processor 20 calculates an evaluation value for the translated text based on the translation error, the primary error classification, and the severity. Specifically, the processor 20 calculates an evaluation value for the first translated text and an evaluation value for the second translated text, respectively.

[0100] More specifically, the processor 20 calculates an evaluation value based on the number of translation errors in the translated text and the coefficients corresponding to the main error classification and severity. The processor 20 also calculates an evaluation value based on the number of characters in the translated text.

[0101] In step S72, the processor 20 executes the evaluation value registration process. In this process, the processor 20 registers the calculated evaluation value in the error management database 30 so that it corresponds to the translated text identifier.

[0102] As shown in Figure 5, once the evaluation control process is complete, in step S25, the processor 20 determines whether or not it has analyzed all the translations to be analyzed. If the processor 20 determines that it has not analyzed all the translations to be analyzed, it proceeds to step S20. If the processor 20 determines that it has analyzed all the translations to be analyzed, it terminates the translation analysis process. In this way, the processor 20 repeatedly executes steps S20 to S24 until it has analyzed all the translations to be analyzed.

[0103] <Display control processing> Next, the display control process will be described with reference to Figure 10. The display control process is executed by the processor 20 at predetermined intervals.

[0104] In step S80, the processor 20 determines whether or not a display instruction was received. If the processor 20 determines that no display instruction was received, it terminates the display control process. If the processor 20 determines that a display instruction was received, it proceeds to step S81.

[0105] A display instruction includes the translated text to be displayed, which will result in the analysis. In other words, a display instruction includes the translation server to be displayed. It can also be said that a display instruction includes the translation language model to be displayed.

[0106] The display instructions include the method of displaying the analysis results. The method of displaying the analysis results is to display an evaluation value for each translated text to be displayed. The method of displaying the analysis results includes a first display method and a second display method.

[0107] The first display mode displays the number of translation errors corresponding to the severity level for each translated text to be displayed. The second display mode displays the number of translation errors corresponding to the main error classification for each translated text to be displayed.

[0108] In step S81, the processor 20 performs analysis result display processing. In this process, the processor 20 displays images related to translation errors on the display device 24 in accordance with the display instructions.

[0109] More specifically, the processor 20 refers to the error management database 30 corresponding to the translated text to be displayed, as included in the display instruction. This allows the processor 20 to obtain data regarding translation errors corresponding to the translated text to be displayed, as included in the display instruction.

[0110] The processor 20 causes the display device 24 to display images related to translation errors in a manner corresponding to the display mode of the analysis results included in the display instruction. When the first display mode is included in the display instruction, the processor 20 displays an image related to the evaluation value and an image related to the number of translation errors corresponding to the severity on the display device 24 for each translation sentence to be displayed. When the second display mode is included in the display instruction, the processor 20 displays an image related to the evaluation value and an image related to the number of translation errors corresponding to the main error classification on the display device 24 for each translation sentence to be displayed.

[0111] As shown in Figure 11, when the first display mode is included in the display instruction, the display device 24 displays the first image 24A. The first image 24A displays an image showing the evaluation value for each translated sentence. For each translated sentence, the first image 24A displays an image showing the number of errors with a minor severity, the number of errors with a moderate severity, and the number of errors with a severe severity.

[0112] When the second display mode is included in the display instruction, the display device 24 displays the second image 24B. The second image 24B displays an image showing the evaluation value for each translated sentence. For each translated sentence, the second image 24B displays an image showing the number of errors whose primary error classification is the first error classification, the number of errors whose primary error classification is the second error classification, and the number of errors whose primary error classification is the third error classification. An example of the first error classification may be accuracy, an example of the second error classification may be fluency, and an example of the third error classification may be style.

[0113] In this way, the processor 20 displays images related to translation errors on the display device 24. In particular, the processor 20 displays images related to evaluation values ​​corresponding to the translated text on the display device 24. The processor 20 displays images related to translation errors associated with the main error classification on the display device 24. The processor 20 displays images related to translation errors associated with the severity on the display device 24.

[0114] <Operation and Effects of the First Embodiment> The operation and effects of the first embodiment will now be described. (1) The processor 20 generates an error determination prompt that includes the source text, the translated text, and instructions for determining translation errors in the translated text in relation to error classifications. The processor 20 inputs the error determination prompt to the LLM15A and obtains translation errors in accordance with the error classifications. With this configuration, translation errors can be obtained from the LLM15A in accordance with the error classifications. This reduces the need for manual judgment regarding whether or not a translation error exists and the error classification of the translation error. Therefore, manual effort can be reduced. Consequently, the convenience of evaluating translation accuracy can be improved.

[0115] In addition, the accuracy of evaluation regarding whether or not a translation error exists, and the classification of translation errors, can be improved compared to human judgment. Therefore, the convenience of evaluating translation accuracy can be improved.

[0116] (2) The processor 20 generates an error suitability prompt that includes a translation error and an instruction to determine whether the translation error is appropriate or not. The processor 20 obtains whether the translation error is appropriate or not by inputting the error suitability prompt to the LLM 15A. With this configuration, after the LLM 15A has determined that there is a translation error, it is possible to have the LLM 15A determine again whether the translation error is appropriate or not. This reduces the opportunities for human judgment regarding whether or not there is a translation error and improves the accuracy of the determination of whether or not there is a translation error. As a result, human effort can be reduced. Consequently, the convenience of evaluating translation accuracy can be improved.

[0117] (3) When the processor 20 obtains multiple translation errors from the source text, it groups together any duplicate translation errors. This configuration reduces the control load for duplicate translation errors by grouping them together. Therefore, it improves the convenience of evaluating translation accuracy.

[0118] (4) When multiple error classifications are associated with a translation error, the processor 20 generates an error classification prompt that includes the translation error, the multiple error classifications, and an instruction to select the appropriate primary error classification from the multiple error classifications. The processor 20 obtains the appropriate primary error classification corresponding to the translation error by inputting the error classification prompt to the LLM15A. With this configuration, even when multiple error classifications are associated with a translation error, the appropriate primary error classification corresponding to the translation error can be obtained from the LLM15A. This reduces the need for manual judgment regarding the appropriate primary error classification corresponding to the translation error. Therefore, manual effort can be reduced. Consequently, the convenience of evaluating translation accuracy can be improved.

[0119] (5) The processor 20 generates a severity prompt that includes the translation error, the primary error classification, and an instruction to determine the severity of the translation error. The processor 20 obtains the severity of the translation error by inputting the severity prompt to the LLM15A. With this configuration, the severity of the translation error can be obtained from the LLM15A. This reduces the need for manual judgment regarding the severity of the translation error. Therefore, manual effort can be reduced. Consequently, the convenience of evaluating translation accuracy can be improved.

[0120] (6) The severity prompt includes a guideline for determining the severity of the translation error. With this configuration, by inputting the guideline for determining the severity of the translation error into LLM15A, the severity of the translation error can be determined as intended by the evaluator. Therefore, the convenience of evaluating translation accuracy can be improved.

[0121] (7) The processor 20 calculates an evaluation value for the translated text based on the translation error, the primary error classification, and the severity. With this configuration, an objective evaluation can be performed using the evaluation value for the translated text. Therefore, the convenience of evaluating translation accuracy can be improved.

[0122] (8) The processor 20 calculates an evaluation value based on the calculation result of the number of translation errors contained in the translated text and coefficients corresponding to the main error classification and severity. With this configuration, an objective evaluation of the translated text can be performed using an evaluation value based on the number of translation errors contained in the translated text. In addition, the evaluation value of the translated text can be weighted using coefficients corresponding to the main error classification and severity. Therefore, the convenience of evaluating translation accuracy can be improved.

[0123] (9) The processor 20 calculates an evaluation value based on the number of characters in the translated text. With this configuration, an evaluation value for the translated text can be calculated taking into account the number of characters in the translated text. Therefore, the convenience of evaluating translation accuracy can be improved.

[0124] (10) The processor 20 obtains a first translation by inputting the source text into the first translation language model 13A. The processor 20 obtains a second translation by inputting the source text into the second translation language model 14A. The processor 20 calculates an evaluation value for the first translation and an evaluation value for the second translation, respectively. With this configuration, the first and second translations can be obtained by inputting the same source text into both the first translation language model 13A and the second translation language model 14A. In addition, the evaluation value of the first translation and the evaluation value of the second translation can be compared and evaluated objectively. Therefore, the convenience of evaluating translation accuracy can be improved.

[0125] (11) The processor 20 causes the display device 24 to display images related to the translation errors associated with the primary error classification. With this configuration, the evaluator can recognize the analysis results for the translation errors associated with the primary error classification. Therefore, the convenience of evaluating translation accuracy can be improved.

[0126] (12) The processor 20 causes the display device 24 to display images related to translation errors associated with severity. With this configuration, the evaluator can be made aware of the analysis results regarding translation errors associated with severity. Therefore, the convenience of evaluating translation accuracy can be improved.

[0127] (13) The processor 20 causes the display device 24 to display an image related to the evaluation value. With this configuration, the evaluator can be made aware of the analysis results regarding the evaluation value of the translated text. Therefore, the convenience of evaluating translation accuracy can be improved.

[0128] [Example of changes] This embodiment can be implemented with the following modifications. This embodiment and the following modifications can be combined with each other to the extent that they do not contradict each other technically.

[0129] The processor 20 may generate a grouping prompt that includes the error details of the translation errors and instructions for grouping the translation errors. The processor 20 may input the grouping prompt to the LLM15A and obtain the grouped translation errors from the LLM15A.

[0130] The processor 20 may analyze each translation error with overlapping error content without grouping the translation errors. The processor 20 may evaluate each translation error with overlapping error content without grouping the translation errors.

[0131] The processor 20 does not need to re-evaluate the appropriateness of a translation error after it has been determined to be a translation error from the translated text. The processor 20 may determine the severity of the translation error based on the result of determining it to be a translation error from the translated text. The processor 20 may calculate an evaluation value based on the result of determining it to be a translation error from the translated text.

[0132] The processor 20 does not need to perform step S22 in Figure 5 if the error identifier corresponds to only one type of error classification. In other words, if the error identifier corresponds to multiple error classifications, the processor 20 only needs to generate an error classification prompt and input the error classification prompt to LLM15A to obtain the primary error classification corresponding to the translation error.

[0133] The processor 20 does not have to perform step S22 in Figure 5 even if multiple error classifications correspond to an error identifier. In this case, the processor 20 may analyze the translated text based on at least one error classification corresponding to the error identifier, rather than the primary error classification. For example, the processor 20 may determine the severity of the translation error based on at least one error classification corresponding to the error identifier, rather than the primary error classification. For example, the processor 20 may calculate an evaluation value for the translation error based on at least one error classification corresponding to the error identifier, rather than the primary error classification. If multiple error classifications correspond to one error identifier, the processor 20 may calculate an evaluation value for the translation error for each of the multiple error classifications and calculate the average of the evaluation values ​​as the evaluation value corresponding to one error identifier. For example, the processor 20 may display the results of the translation error analysis on the display device 24 based on at least one error classification corresponding to the error identifier, rather than the primary error classification.

[0134] Processor 20 may calculate an evaluation value for the translated text regardless of the primary error classification. In this case, processor 20 does not need to obtain the primary error classification. Processor 20 may calculate an evaluation value for the translated text regardless of the severity of the translation errors. In this case, processor 20 does not need to obtain the severity of the translation errors.

[0135] The coefficient database 31 may include primary error classifications that have the same coefficient. The coefficient database 31 may include severity levels that have the same coefficient. The coefficient database 31 may include coefficients based on either primary error classification or severity level. The coefficient database 31 may include other elements besides primary error classification and severity level. For example, the other element may be the number of characters in the translated text.

[0136] The processor 20 may calculate the evaluation value of the translated text regardless of the coefficients. In this case, the coefficient database 31 does not need to be stored in memory 21. The processor 20 may calculate the evaluation value of the translated text based on the number of characters in the source text. The processor 20 may calculate the evaluation value of the translated text regardless of the number of characters in the translated text.

[0137] The processor 20 may compare evaluation values ​​for multiple translations. The processor 20 may display the comparison results of the evaluation values ​​for multiple translations on the display device 24. The processor 20 may also display the number of characters in each translation on the display device 24. The processor 20 may compare evaluation values ​​for multiple translations and upload the translation with the smallest evaluation value to a web server (not shown).

[0138] Processor 20 may obtain the source text from a web server (not shown). Processor 20 does not have to perform source text translation processing to obtain the translated text from the source text. In such cases, processor 20 may obtain the translated text from another server.

[0139] The processor 20 may input one prompt into multiple prompts to the LLM15A. The processor 20 may also input multiple prompts into one prompt to the LLM15A.

[0140] The information processing system 10 does not need to analyze the translated text obtained by translating the original text. The information processing system 10 does not need to analyze the summarized text obtained by summarizing the original text. In other words, the information processing system 10 does not need to analyze the edited text obtained by editing the original text.

[0141] In such a case, the translation server 12 may also be an editing server, the first translation server 13 may also be a first editing server, and the second translation server 14 may also be a second editing server. The first translation language model 13A may be a first editing language model, and the second translation language model 14A may also be a first editing language model.

[0142] The processor 20 may obtain the edited text by inputting a prompt to the editing language model that includes the source text, editing guideline data which is a guideline for editing the source text, and instructions for editing the source text. The processor 20 may also obtain the result of editing error determination by inputting a prompt to the LLM15A that includes the source text, the edited text, editing guideline data, and instructions for determining editing errors. In this case, the processor 20 may also obtain the result of error classification and the corresponding editing error determination by inputting a prompt to the LLM15A that includes instructions for determining the error classification and the corresponding editing error.

[0143] The translation server 12 may be equipped with an LLM 15A. In this case, the destination of prompts other than translation prompts from the information processing device 11 becomes the translation server 12. The processor 20 may input prompts related to the first translated sentence to the LLM 15A of the second translation server 14, and prompts related to the second translated sentence to the LLM 15A of the first translation server 13.

[0144] The information processing device 11 may include an LLM 15A. In this case, the processor 20 in the information processing device 11 may input a prompt to the LLM 15A. In such cases, the information processing system 10 does not need to include an LLM server 15.

[0145] In the information processing system 10, the processor 20 may input prompts to a smaller language model that has less computational complexity, data volume, and number of model parameters compared to LLM15A, rather than to LLM15A. In other words, in the information processing system 10, the processor 20 may input prompts to a language model. The language model may be a learning model using deep learning.

[0146] The information processing device 11 does not necessarily have to include at least one of the input device 23 and the display device 24. The information processing device 11 may be communicatively connected to a terminal device (not shown) via a communication interface 22. The terminal device may include at least one of the input device 23 and the display device 24. In this way, the processor 20 may cause the display device 24 of the terminal device to display various images via the communication interface 22. The processor 20 may receive various instructions from the input device 23 of the terminal device via the communication interface 22.

[0147] The information processing device 11 may include at least one processor 20 and at least one memory 21. The information processing system 10 may include at least one processor 20 and at least one memory 21.

[0148] The information processing device 11 may consist of multiple servers. In this case, the multiple servers are connected in a communicative manner. The multiple servers may each have a divided set of functions provided by the information processing device 11.

[0149] The information processing system 10 may include other servers besides the translation server 12 and the LLM server 15, provided that it includes at least the information processing device 11. The information processing system 10 may not include at least one of the servers, such as the translation server 12 and the LLM server 15, provided that it includes at least the information processing device 11.

[0150] As used herein, the expression "at least one of" means one or more of the desired options. For example, as used herein, if there are two options, the expression "at least one of" means either one option or both of the two options. As another example, as used herein, if there are three or more options, the expression "at least one of" means either one option or any combination of two or more options.

[0151] [Note] The technical concepts that can be gleaned from the embodiments and modifications described above are outlined below. [1] The information processing device comprises at least one memory configured to store a program, and at least one processor configured to perform processing based on the program, wherein the at least one processor generates a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputs the first prompt to a language model to obtain the editing errors in association with the error classifications.

[0152] The information processing apparatus described in [2][1], wherein the at least one processor generates a second prompt including the editing error and an instruction for determining whether the editing error is appropriate, and obtains whether the editing error is appropriate by inputting the second prompt to a language model.

[0153] An information processing apparatus according to [3] [1] or [2], wherein at least one processor performs the action of grouping the duplicate editing errors among the multiple editing errors when multiple editing errors are obtained from the original text.

[0154] An information processing device according to any one of [4] [1] to [3], wherein at least one processor generates a third prompt including the editing error, the plurality of error classifications, and an instruction to select an appropriate error classification from the plurality of error classifications, when a plurality of error classifications are associated with the editing error, and obtains an appropriate error classification corresponding to the editing error by inputting the third prompt to a language model.

[0155] An information processing device according to any one of [5] [1] to [4], wherein at least one processor generates a fourth prompt including the editing error, the error classification, and an instruction for determining the severity of the editing error, and obtains the severity of the editing error by inputting the fourth prompt to a language model.

[0156] The information processing device described in [6][5], wherein the fourth prompt includes a guideline for determining the severity of the editing error. An information processing apparatus according to [7][5] or [6], wherein at least one processor performs the calculation of an evaluation value for the edited statement based on the editing error, the error classification, and the severity.

[0157] The information processing device described in [8][7], wherein calculating the evaluation value includes calculating the evaluation value based on the result of a calculation between the number of editing errors included in the editing text and a coefficient corresponding to the error classification and severity.

[0158] The information processing device described in [9][8], wherein calculating the evaluation value includes calculating the evaluation value based on the number of characters in the edited text. An information processing apparatus according to

[10] , [7] to [9], wherein at least one processor performs the following actions: inputting the source text into a first machine translation model to obtain a first translated text as the edited text; inputting the source text into a second machine translation model to obtain a second translated text as the edited text; and calculating the evaluation value includes calculating an evaluation value for the first translated text and an evaluation value for the second translated text, respectively.

[0159] An information processing device according to

[11] to

[10] , wherein at least one processor performs the function of displaying an image relating to the editing error associated with the error classification on a display device.

[0160] An information processing device according to

[12] , [5] to

[10] , wherein at least one processor performs the function of displaying an image relating to the editing error associated with the severity on a display device.

[0161] An information processing apparatus according to

[13] , [7] to

[10] , wherein at least one processor performs the function of displaying an image relating to the evaluation value on a display device. An information processing device as described in

[14] [1] to

[13] , wherein the edited text is a translated text obtained by translating the original text.

[0162]

[15] The information processing system comprises at least one memory configured to store a program and at least one processor configured to perform processing based on the program, wherein the at least one processor generates a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputs the first prompt to a language model to obtain the editing errors in association with the error classifications.

[0163]

[16] The information processing method includes at least one processor generating a first prompt that includes a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and inputting the first prompt to a language model to obtain the editing errors in association with the error classifications.

[0164]

[17] The program causes at least one processor to generate a first prompt including a source text, an edited text obtained by editing the source text, and instructions for determining editing errors in the edited text in association with error classifications, and to input the first prompt to a language model to obtain the editing errors in association with the error classifications. [Explanation of symbols]

[0165] 10... Information processing system, 11... Information processing device, 12... Translation server, 13... First translation server, 13A... First translation language model, 14... Second translation server, 14A... Second translation language model, 15... Large-scale language model server, 15A... Large-scale language model, 20... Processor, 21... Memory, 24... Display device, 24A... First image, 24B... Second image, 26... Program, 27... Database, 30... Error management database, 31... Coefficient database.

Claims

1. At least one memory configured to store a program, The system comprises at least one processor configured to perform processing based on the program, The aforementioned at least one processor is A first prompt is generated which includes the original text, the edited version of the original text, and instructions for determining editing errors in the edited version by associating them with error classifications. By inputting the first prompt into the language model, the editing error is obtained in accordance with the error classification, Execute Information processing device.

2. An information processing apparatus according to claim 1, The aforementioned at least one processor is A second prompt is generated that includes the aforementioned editing error and an instruction to determine whether the editing error is appropriate or not. By inputting the second prompt into the language model, the appropriateness of the editing error is obtained, Execute Information processing device.

3. An information processing apparatus according to claim 1, The at least one processor, when it obtains multiple editing errors from the source text, performs the action of grouping the duplicate editing errors among the multiple editing errors. Information processing device.

4. An information processing apparatus according to claim 1, The aforementioned at least one processor is When multiple error classifications are associated with the editing error, a third prompt is generated that includes the editing error, the multiple error classifications, and an instruction to select the appropriate error classification from the multiple error classifications. By inputting the third prompt into the language model, an appropriate error classification corresponding to the editing error is obtained, Execute Information processing device.

5. An information processing apparatus according to claim 1, The aforementioned at least one processor is To generate a fourth prompt including the editing error, the error classification, and an instruction to determine the severity of the editing error, By inputting the fourth prompt into the language model, the severity of the editing error is obtained, Execute Information processing device.

6. An information processing device according to claim 5, The fourth prompt includes a guideline for determining the severity of the editing error, Information processing device.

7. An information processing device according to claim 5, The at least one processor performs the calculation of an evaluation value for the edited statement based on the editing error, the error classification, and the severity. Information processing device.

8. An information processing apparatus according to claim 7, Calculating the aforementioned evaluation value includes calculating the evaluation value based on the result of a calculation between the number of editing errors included in the editing text and the coefficients corresponding to the error classification and severity. Information processing device.

9. An information processing apparatus according to claim 8, Calculating the aforementioned evaluation value includes calculating the evaluation value based on the number of characters in the edited text. Information processing device.

10. An information processing apparatus according to claim 7, The aforementioned at least one processor is The first translated text is obtained as the edited text by inputting the original text into the first machine translation model, The original text is input into a second machine translation model to obtain the second translated text as the edited text, Execute, Calculating the aforementioned evaluation values ​​includes calculating the evaluation value for the first translated text and the evaluation value for the second translated text, respectively. Information processing device.

11. An information processing apparatus according to claim 1, The at least one processor performs the action of displaying an image relating to the editing error associated with the error classification on a display device. Information processing device.

12. An information processing device according to any one of claims 5 to 10, The at least one processor performs the action of displaying an image relating to the editing error associated with the severity on a display device. Information processing device.

13. An information processing device according to any one of claims 7 to 10, The at least one processor performs the action of displaying an image relating to the evaluation value on a display device. Information processing device.

14. An information processing device according to any one of claims 1 to 11, The aforementioned edited text is a translation of the aforementioned original text. Information processing device.

15. At least one memory configured to store a program, The system comprises at least one processor configured to perform processing based on the program, The aforementioned at least one processor is A first prompt is generated which includes the original text, the edited version of the original text, and instructions for determining editing errors in the edited version by associating them with error classifications. By inputting the first prompt into the language model, the editing error is obtained in accordance with the error classification, Execute Information processing system.

16. At least one processor, A first prompt is generated which includes the original text, the edited version of the original text, and instructions for determining editing errors in the edited version by associating them with error classifications. By inputting the first prompt into the language model, the editing error is obtained in accordance with the error classification, Execute Information processing methods.

17. At least one processor, A first prompt is generated which includes the original text, the edited version of the original text, and instructions for determining editing errors in the edited version by associating them with error classifications. By inputting the first prompt into the language model, the editing error is obtained in accordance with the error classification, To execute program.

Images