Information processing device, information processing method, and program

The information processing device improves language processing reliability by rewriting and sourcing text from credible documents within the language model, ensuring accurate and transparent results.

WO2024236619A1PCT designated stage expired Publication Date: 2024-11-21NEC CORP

Patent Information

Application Number
PCT/JP2023/017858
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Existing language processing technologies using language models do not verify the correctness of responses from external search engines, leading to potential inaccuracies in question answering.

Method used

An information processing device and method that acquires a target text, extracts related documents, rewrites the text using these documents, generates text using a language model, and adds document-identifying information to improve reliability, ensuring that language processing results are accurate and trustworthy.

Benefits of technology

Enhances the reliability of language processing results by referencing credible documents and providing users with information about the sources used in the processing, thus improving the accuracy and transparency of the output.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023017858_21112024_PF_FP_ABST
    Figure JP2023017858_21112024_PF_FP_ABST
Patent Text Reader

Abstract

To increase the reliability of a result of language processing executed through use of a language model, an information processing device (1) comprises: an acquisition unit (11) that acquires a target text; an extraction unit (12) that extracts a document related to the target text; a rewriting unit (13) that uses the document to rewrite the target text; a generation unit (14) that uses the language model to generate a text corresponding to the rewritten target text; and an output unit (15) that outputs a result obtained by adding information for identifying the document to the generated text.
Need to check novelty before this filing date? Find Prior Art

Description

Information processing device, information processing method, and program

[0001] The present invention relates to an information processing device, an information processing method, and a program for performing language processing on text.

[0002] A technique using a language model that is trained using text data and performs language processing is known.

[0003] Patent Document 1 discloses a question answering device that generates a response to a question based on entities extracted from the question and a perplexity value calculated from the question using a language model that assumes questions in a specific field.

[0004] The question answering device divides a text, which is a question, into morphemes, which are the smallest units that have meaning, and requests an external search engine to perform a keyword search using nouns among the words that are the divided morphemes as keywords.The question answering device also regards the response from the external search engine as an answer to the input question.

[0005] Japanese Patent Application Publication No. 2015-87796

[0006] The question answering device described in Patent Document 1 does not verify whether the response from the external search engine is correct, which poses a problem that the response to the question sentence by the question answering device may be incorrect.

[0007] One aspect of the present invention has been made in consideration of the above-mentioned problems, and one example of its purpose is to provide a technology for improving the reliability of the results of language processing performed using a language model.

[0008] An information processing device according to one aspect of the present invention comprises an acquisition means for acquiring a target text, an extraction means for extracting documents related to the target text, a rewriting means for rewriting the target text using the documents, a generation means for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text, and an output means for outputting the result of adding information identifying the document to the text generated by the generation means.

[0009] An information processing method according to one aspect of the present invention includes acquiring a target text, extracting documents related to the target text, rewriting the target text using the documents, generating text corresponding to the rewritten target text using a language model trained to generate text based on input text, and outputting a result in which information identifying the document is added to the text generated in the generating step.

[0010] A program according to one aspect of the present invention causes a computer to execute an acquisition process for acquiring target text, an extraction process for extracting documents related to the target text, a rewriting process for rewriting the target text using the documents, a generation process for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text, and an output process for outputting the result of adding information identifying the document to the text generated in the generation process.

[0011] According to one aspect of the present invention, it is possible to improve the reliability of the results of language processing performed using a language model.

[0012] FIG. 1 is a block diagram showing the configuration of an information processing device according to exemplary embodiment 1 of the present invention. FIG. 2 is a flow chart showing the flow of an information processing method according to exemplary embodiment 1 of the present invention. FIG. 3 is a block diagram showing the configuration of an information processing device according to exemplary embodiment 2 of the present invention. FIG. 4 is a flowchart showing the flow of an information processing method according to exemplary embodiment 2 of the present invention. FIG. 5 is a diagram showing examples of each process executed by an information processing device according to exemplary embodiment 2 of the present invention. FIG. 6 is a block diagram showing the configuration of an information processing system according to exemplary embodiment 3 of the present invention. FIG. 7 is a diagram showing an example of a document in exemplary embodiment 3 of the present invention. FIG. 8 is a diagram showing example information related to the author of a document in exemplary embodiment 3 of the present invention. FIG. 9 is a flowchart showing the flow of an information processing method according to exemplary embodiment 3 of the present invention. FIG. 10 is a diagram showing an example of an image displayed by an information processing terminal according to exemplary embodiment 3 of the present invention. FIG. 11 is a block diagram showing an example of the hardware configuration of an information processing device according to each exemplary embodiment of the present invention.

[0013] [First Exemplary Embodiment] A first exemplary embodiment of the present invention will be described in detail with reference to the drawings. This exemplary embodiment is a basic form of the exemplary embodiments described below.

[0014] (Configuration of Information Processing Apparatus 1) The configuration of the information processing apparatus 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing apparatus 1 according to this exemplary embodiment.

[0015] 1, the information processing device 1 includes an acquisition unit 11, an extraction unit 12, a rewriting unit 13, a generation unit 14, and an output unit 15. In this exemplary embodiment, the acquisition unit 11, the extraction unit 12, the rewriting unit 13, the generation unit 14, and the output unit 15 respectively function as an acquisition means, an extraction means, a rewriting means, a generation means, and an output means.

[0016] The acquisition unit 11 acquires a target text and supplies the acquired target text to the extraction unit 12 and the rewriting unit 13.

[0017] The extraction unit 12 extracts documents related to the target text supplied from the acquisition unit 11. The extraction unit 12 supplies the extracted documents to the rewriting unit 13.

[0018] The rewriting unit 13 rewrites the target text acquired by the acquisition unit 11 using the document supplied from the extraction unit 12. The rewriting unit 13 supplies the rewritten target text to the generation unit .

[0019] The generation unit 14 uses a language model trained to generate text based on input text to generate text corresponding to the target text rewritten by the rewriting unit 13. The generation unit 14 supplies the generated text to the output unit 15.

[0020] The output unit 15 outputs the result of adding information for identifying the document to the text generated by the generation unit 14.

[0021] As described above, the information processing device 1 according to this exemplary embodiment has a configuration including an acquisition unit 11 that acquires target text, an extraction unit 12 that extracts documents related to the target text supplied from the acquisition unit 11, a rewriting unit 13 that rewrites the target text acquired by the acquisition unit 11 using the documents supplied from the extraction unit 12, a generation unit 14 that generates text corresponding to the target text rewritten by the rewriting unit 13 using a language model trained to generate text based on input text, and an output unit 15 that outputs a result in which information identifying the document is added to the text generated by the generation unit 14. Therefore, the information processing device 1 according to this exemplary embodiment has the effect of improving the reliability of the results of language processing performed using the language model.

[0022] (Flow of Information Processing Method S1) The flow of the information processing method S1 according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow chart showing the flow of the information processing method S1 according to this exemplary embodiment.

[0023] (Step S11) In step S11, the acquisition unit 11 acquires the target text and supplies the acquired target text to the extraction unit 12 and the rewriting unit 13.

[0024] (Step S12) In step S12, the extraction unit 12 extracts documents related to the target text supplied from the acquisition unit 11. The extraction unit 12 supplies the extracted documents to the rewriting unit 13.

[0025] (Step S13) In step S13, the rewriting unit 13 rewrites the target text acquired by the acquisition unit 11 using the document supplied from the extraction unit 12. The rewriting unit 13 supplies the rewritten target text to the generation unit 14.

[0026] (Step S14) In step S14, the generation unit 14 uses a language model trained to generate text based on input text to generate text corresponding to the target text rewritten by the rewriting unit 13. The generation unit 14 supplies the generated text to the output unit 15.

[0027] (Step S15) In step S15, the output unit 15 outputs the result of adding information for identifying the document to the text generated by the generation unit 14.

[0028] As described above, the information processing method S1 according to this exemplary embodiment employs a configuration including the following: the acquisition unit 11 acquires target text; the extraction unit 12 extracts documents related to the target text supplied from the acquisition unit 11; the rewriting unit 13 rewrites the target text acquired by the acquisition unit 11 using the documents supplied from the extraction unit 12; the generation unit 14 generates text corresponding to the target text rewritten by the rewriting unit 13 using a language model trained to generate text based on input text; and the output unit 15 outputs a result in which information identifying the document is added to the text generated by the generation unit 14. Therefore, the information processing method S1 according to this exemplary embodiment can achieve the same effects as the information processing device 1 described above.

[0029]

[0033] A second exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first exemplary embodiment are denoted by the same reference numerals, and their description will be omitted as appropriate.

[0030] (Overview of Information Processing Device 2) The information processing device 2 according to this exemplary embodiment is a device that acquires target text and outputs the results of performing language processing on the target text. The results output by the information processing device 2 also include information that identifies documents related to the acquired target text. Documents will be described later. Note that, hereinafter, "target text" and "text" are also referred to as "character strings."

[0031] The information processing device 2 performs language processing using a language model M trained using text data. The language model M receives a character string (text) as input and outputs the result (text) of performing language processing on the character string. The result output from the language model M may be a character string or an image. The language processing performed by the language model M is not particularly limited, and examples include processing for generating text based on input text, text classification, sentiment analysis, information extraction, sentence summarization, text generation, image generation, and question answering.

[0032] The language model M will now be described in detail. The language model M is a model that learns the relationships between words in sentences (text data) and generates related strings related to a target string from the target string. By using a language model that has learned sentences and paragraphs from various contexts, it is possible to generate related strings with appropriate content related to the target string.

[0033] Examples of the language model M include, but are not limited to, large language models (LLMs) such as BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-trained Transformer), T5 (Text-to-Text Transfer Transformer), RoBERTa (Robustly optimized BERT approach), and ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately), as well as learning models generated by transfer learning or fine-tuning using a pre-trained model (e.g., ChatGPT (Chat Generative Pre-trained Transformer)).

[0034] Furthermore, the character string generated by the language model M is not limited to a natural language. For example, the language model M may output an artificial language (such as a program source code) for a character string input in a natural language. For example, the language model M may receive an input question such as "How do I retrieve data containing a specific character string from a database?" as a target character string. In response to this input, the language model M may output a program source code for performing database processing. Alternatively, the language model M may output a natural language corresponding to a character string input in an artificial language.

[0035] The character string acquired by the information processing device 2 is not particularly limited, and may be, for example, a character string including at least one word and an instruction indicating what kind of language processing to perform. For example, assume that the information processing device 2 acquires the character string "What is the main business field of XX Corporation?" In this case, the character string includes five words, "XX Corporation," "of," "main," "business field," and "is," as well as an instruction to respond to the question "What is the main business field of XX Corporation?"

[0036] (Configuration of Information Processing Device 2) The configuration of the information processing device 2 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 2 according to this exemplary embodiment.

[0037] As shown in FIG. 3, the information processing device 2 includes a control unit 20, an input unit 25, an output unit 26, and a storage unit 27.

[0038] The input unit 25 is an interface that accepts user input. For example, the input unit 25 supplies information indicating the accepted user input to the control unit 20. Examples of the input unit 25 include, but are not limited to, a mouse, a keyboard, a touchpad, and a microphone.

[0039] The output unit 26 outputs data. As an example, the output unit 26 may be an interface that outputs data to another connected device. In this case, for example, the output unit 26 outputs the result output from the control unit 20 to the other connected device. As another example, the output unit 26 may be a display device that displays an image or a speaker that outputs sound. When the output unit 26 is a display device, the output unit 26 displays an image including the result output from the control unit 20.

[0040] The storage unit 27 stores data referenced by the control unit 20. Documents are an example of data stored in the storage unit 27. Examples of the storage unit 27 include, but are not limited to, flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0041] Furthermore, the storage unit 27 stores a language model M. Note that storing the language model M in the storage unit 27 means that parameters defining the language model M are stored in the storage unit 27. Furthermore, the language model may be stored in a storage device other than the storage unit 27 (for example, an external server, etc.).

[0042] The control unit 20 controls each component included in the information processing device 2. As shown in Fig. 3, the control unit 20 includes an acquisition unit 11, an extraction unit 12, a rewriting unit 13, a generation unit 14, an output control unit 23, a calculation unit 21, and a determination unit 22. In this exemplary embodiment, the acquisition unit 11, the extraction unit 12, the rewriting unit 13, the generation unit 14, the output control unit 23, the calculation unit 21, and the determination unit 22 are configured to realize an acquisition means, an extraction means, a rewriting means, a generation means, an output means, a calculation means, and a determination means, respectively.

[0043] The acquisition unit 11 acquires data supplied from the input unit 25. As an example, the acquisition unit 11 acquires a character string. Hereinafter, the character string acquired by the acquisition unit 11 is also referred to as a first character string. The acquisition unit 11 stores the acquired first character string in the storage unit 27.

[0044] The extraction unit 12 extracts documents related to the character string. As one example, the extraction unit 12 may extract documents related to the first character string from documents stored in the storage unit 27. As another example, the extraction unit 12 may extract documents related to the first character string from documents stored in a database connected to the information processing device 2 via a network. The extraction unit 12 stores the extracted documents in the storage unit 27 in association with the first character string.

[0045] The method by which the extraction unit 12 extracts documents related to the character string is not limited. For example, the extraction unit 12 may extract documents that include the character string. Alternatively, the extraction unit 12 may extract documents related to the character string using an existing search engine.

[0046] The rewriting unit 13 rewrites the character string. As an example, the rewriting unit 13 rewrites the first character string using the document extracted by the extraction unit 12. The character string rewritten by the rewriting unit 13 is also referred to as the second character string. The rewriting unit 13 stores the second character string in the storage unit 27 in association with the first character string.

[0047] The method by which the rewriting unit 13 rewrites the character string is not limited. As one example, the rewriting unit 13 may generate the second character string by adding a character string described in the document to the first character string. As another example, the rewriting unit 13 may generate the second character string by adding a character string described in the document and a character string indicating an additional instruction to the first character string. As yet another example, the rewriting unit 13 may generate the second character string by rewriting the first character string with a character string indicating an additional instruction and then adding a character string described in the document.

[0048] The generation unit 14 generates a result of performing language processing on the character string. As an example, the generation unit 14 generates text that is a result of performing language processing on a second character string. As described above, the generation unit 14 may use a language model M that is trained to generate text based on input text. That is, the generation unit 14 may input the second character string into the language model M and generate text output from the language model M as a result of performing language processing on the second character string. The result that is text generated by the generation unit 14 is also referred to as a first result. The generation unit 14 stores the generated first result in the storage unit 27 in association with the second character string.

[0049] The output control unit 23 outputs data to the output unit 26. The output control unit 23 corresponds to the output unit 15 in the above-described exemplary embodiment 1. As an example, the output control unit 23 outputs a result in which information identifying the documents extracted by the extraction unit 12 is added to the first result generated by the generation unit 14. The output control unit 23 may add information identifying some of the documents extracted by the extraction unit 12 to the first result generated by the generation unit 14. Examples of information identifying the documents include the document name, author name, publication date and time, and a uniform resource locator (URL) indicating the location where the document is stored. The result output by the output control unit 23 is also referred to as a second result.

[0050] Furthermore, in addition to the second result, the output control unit 23 may output the reliability calculated by the calculation unit 21, which will be described later. With this configuration, the output control unit 23 can present the reliability of the second result to the user.

[0051] Furthermore, the output control unit 23 may be configured to output the second result as an optimized result when the determination unit 22 (described later) determines that the reliability calculated by the calculation unit 21 exceeds a threshold. With this configuration, the output control unit 23 can output a highly reliable and optimized second result.

[0052] The calculation unit 21 calculates the reliability of the result. As an example, the calculation unit 21 calculates the reliability of the first result (text) generated by the generation unit 14. The calculation unit 21 associates the calculated reliability with the first result and stores it in the storage unit 27. With this configuration, the calculation unit 21 can grasp how reliable the first result is.

[0053] The method by which the calculation unit 21 calculates the reliability of the first result is not limited. The calculation unit 21 may calculate the reliability of the first result using an existing technique such as factuality analysis, which is a technique for analyzing whether an event actually occurred. As an example, the calculation unit 21 may calculate the reliability of the first result using the first result and the document extracted by the extraction unit 12. Examples of the method by which the calculation unit 21 calculates the reliability of the first result using the first result and the document extracted by the extraction unit 12 include (a) a method based on word distance, (b) a method based on document distance, and (c) a method based on a learning model.

[0054] When using the method based on word distance, the calculation unit 21 calculates the reliability of the first result based on the word distance between each word included in the first result and each word included in the document. Specifically, the calculation unit 21 first calculates the word distance for each combination between each word included in the first result and each word included in the document. The calculation unit 21 calculates the reliability of the first result such that the shorter the calculated word distance, the higher the reliability of the first result.

[0055] When the method based on the inter-document distance is used, the calculation unit 21 calculates the reliability of the first result based on the inter-document distance between a sentence included in the first result and a sentence included in the document. Specifically, the calculation unit 21 first calculates the inter-document distance between a sentence included in the first result and a sentence included in the document. The calculation unit 21 calculates the reliability of the first result such that the shorter the calculated inter-document distance, the higher the reliability of the first result.

[0056] When using a method based on a learning model, the calculation unit 21 uses a learning model that has been trained by machine learning to input two sentences and output the similarity between the two sentences. In this case, the calculation unit 21 inputs a sentence included in the first result and a sentence included in the document into the learning model. Then, the calculation unit 21 calculates the reliability of the first result such that the higher the similarity output from the learning model, the higher the reliability of the first result.

[0057] When the extraction unit 12 extracts a plurality of documents, the calculation unit 21 calculates the reliability of the first result for each of the plurality of documents. Then, the calculation unit 21 may calculate the arithmetic mean value of the calculated plurality of reliabilities as the reliability of the first result.

[0058] As another example, the calculation unit 21 may calculate the reliability using the first result, the document extracted by the extraction unit 12, and the character string acquired by the acquisition unit 11. For example, the calculation unit 21 may calculate the reliability by referring to a result in which the first result, the document extracted by the extraction unit 12, and the character string acquired by the acquisition unit 11 are input into a language model M used by the generation unit 14. As an example, the calculation unit 21 acquires, from the language model M, an index indicating how accurate the first result that references the document is as a response to the first character string. The calculation unit 21 calculates the reliability of the first result such that the reliability of the first result increases as the output result becomes more positive (e.g., the larger the value of the index). With this configuration, the calculation unit 21 can preferably calculate the reliability of the first result using the language model M that generated the first result.

[0059] Furthermore, the calculation unit 21 may input the first result, the document extracted by the extraction unit 12, and the character string acquired by the acquisition unit 11 multiple times to the language model M. In this case, the calculation unit 21 may score (likelihood, positive frequency, etc.) the results output from the language model M for each of the multiple inputs, and calculate the reliability of the first result such that the higher the score, the higher the reliability of the first result.

[0060] Furthermore, instead of the character string acquired by the acquisition unit 11, the calculation unit 21 may input to the language model a character string that instructs the user to answer whether or not the first result is correct in consideration of the document identified by the information added by the output control unit 23. In this case as well, the calculation unit 21 calculates the reliability of the first result such that the more positive the output result is, the higher the reliability of the first result becomes.

[0061] The determination unit 22 determines whether the value exceeds a threshold. As an example, the determination unit 22 determines whether the reliability calculated by the calculation unit 21 exceeds a threshold. The determination unit 22 associates the determination result with the reliability and stores it in the storage unit 27.

[0062] (Processing Executed by Information Processing Device 2) The information processing method executed by the information processing device 2 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of an information processing method S2 according to this exemplary embodiment.

[0063] An example of each process executed by the information processing device 2 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of each process executed by the information processing device 2 according to this exemplary embodiment.

[0064] (Step S21) In step S21, the acquiring unit 11 acquires a character string (first character string) and stores the first character string in the storage unit 27.

[0065] For example, as shown in FIG. 5, the acquiring unit 11 acquires a first character string str1 indicating "What are the main business activities of XX Corporation?".

[0066] (Step S22) In step S22, the extraction unit 12 extracts documents related to the first character string stored in the storage unit 27. The extraction unit 12 stores the extracted documents in the storage unit 27 in association with the first character string.

[0067] 5, the extraction unit 12 extracts a document doc related to a first character string str1, "What is the main business of XX Corporation?" The document doc includes multiple documents (such as "related document 1," "related document 2," and "related document 3").

[0068] (Step S23) In step S23, the rewriting unit 13 generates a second character string by rewriting the first character string using the first character string and the document stored in the storage unit 27. The rewriting unit 13 stores the second character string in the storage unit 27 in association with the first character string.

[0069] For example, as shown in FIG. 5, the rewriting unit 13 generates a second character string str2 by adding a document "doc" to a first character string str1.

[0070] Furthermore, the rewriting unit 13 may generate the second string str2 by adding an instruction. For example, the rewriting unit 13 may generate the second string str2 by adding a string instructing that the document referenced to generate the first result be added to the referenced location. As an example, as shown in FIG. 5 , the rewriting unit 13 may include, in the second string str2, a string ins indicating an additional instruction: "Please answer the question taking into consideration the information below. Please include a citation in the notation ${n} in your answer." This instruction instructs the language model M to add the document "${n}" to a string that references the document "${n}" when the result of the language model M includes the string.

[0071] (Step S24) In step S24, the generation unit 14 uses the language model M trained to generate text based on the input text to generate a character string (first result) corresponding to the second character string stored in the storage unit 27. The generation unit 14 stores the first result in the storage unit 27 in association with the second character string.

[0072] For example, as shown in FIG. 5, the generation unit 14 inputs a second character string str2 to a language model M and generates a first result res1 output from the language model M.

[0073] (Step S25) In step S25, the calculation unit 21 calculates the reliability of the first result stored in the storage unit 27. The calculation unit 21 stores the calculated reliability in the storage unit 27 in association with the first result.

[0074] 5 , the calculation unit 21 calculates the reliability using the first result res1, the document doc, and the first character string str1. As an example, the calculation unit 21 inputs the first result res1, the document doc, and the first character string str1 to the language model M. In this case, the calculation unit 21 obtains, from the language model M, an index indicating how accurate the first result res1, which references the document doc, is in response to the first character string str1. The calculation unit 21 calculates the reliability by referring to the index.

[0075] 5 (${1} or ${3}) into the language model M instead of the document doc, and calculates the reliability. Furthermore, the calculation unit 21 may input a character string "In consideration of the information of the document indicated by ${1}, can it be said that the first result res1 is correct?" into the language model M instead of the first character string str1, and calculate the reliability.

[0076] (Step S26) In step S26, the determination unit 22 determines whether the reliability stored in the storage unit 27 exceeds a threshold value.

[0077] (Step S27) If it is determined in step S26 that the reliability exceeds the threshold (step S26: YES), in step S27 the output control unit 23 generates a result (second result) by adding information that identifies the document stored in the storage unit 27 to the first result stored in the storage unit 27. The output control unit 23 outputs the generated second result as the optimization result.

[0078] For example, as shown in FIG. 5, the output control unit 23 generates a second result res2 by adding information i_doc that identifies the document to the first result res1.

[0079] The output control unit 23 may also be configured to add information that identifies only the document (doc) that the language model M referenced when generating the first result (res1) from among the documents (doc) extracted by the extraction unit 12. This configuration can be realized by adding the character string (ins) indicating the additional instruction described above, "Please answer the question taking into consideration the information below. Please include citations in your answer using the notation ${n}," to the second character string (str2).

[0080] For example, assume that the first result res1 includes "${1}" and "${3}" as shown in Fig. 5. In this case, the output control unit 23 adds information i_doc that identifies the documents indicated by "${1}" and "${3}" to the first result res1, and generates the second result res2.

[0081] On the other hand, if it is determined in step S26 that the reliability does not exceed the threshold (step S26: NO), the output control unit 23 does not output the second result, and the information processing device 2 terminates execution of the information processing method S2.

[0082] (Effects of Information Processing Device 2) In this way, the information processing device 2 according to this exemplary embodiment performs language processing on the second character string obtained by rewriting the first character string using a document related to the acquired first character string, using the language model M. Therefore, the information processing device 2 can prevent the language model M from performing language processing by referencing documents whose content is unclear, such as documents with low credibility, documents of unknown authenticity, and documents of unknown origin. Therefore, the information processing device 2 can improve the reliability of the results of language processing performed using the language model M.

[0083] Furthermore, the information processing device 2 outputs a result in which information specifying documents related to the first character string is added to the result of language processing performed by the language model M on the second character string. Therefore, the information processing device 2 can present to the user the result of the language processing and information on the documents referenced in the language processing. Therefore, the information processing device 2 can present to the user the reliability of the language processing performed using the language model.

[0084] Third Exemplary Embodiment A third exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the above exemplary embodiment will be denoted by the same reference numerals, and their description will be omitted as appropriate.

[0085] (Outline and Configuration of Information Processing System 100) The outline and configuration of the information processing system 100 according to this exemplary embodiment will be described with reference to Fig. 6. Fig. 6 is a block diagram showing the configuration of the information processing system 100 according to this exemplary embodiment.

[0086] As shown in Fig. 6, the information processing system 100 includes an information processing device 3 and an information processing terminal 4. The information processing device 3 and the information processing terminal 4 are communicably connected to each other via a network. An example of the information processing device 3 is a desktop computer. Examples of the information processing terminal 4 are a smartphone, a tablet terminal, and a laptop computer.

[0087] In the information processing system 100, the information processing terminal 4 acquires target text, and the information processing device 3 performs language processing on the target text using the language model M. The information processing device 3 also outputs the results of the language processing to the information processing terminal 4. Note that, hereinafter, "target text" and "text" are also referred to as "character string."

[0088] As an example, in the information processing system 100, a user of the information processing terminal 4 creates an account for using the information processing system 100 and registers basic information (such as name, age, sex, and email address). When the user inputs a character string related to a medical consultation into the information processing terminal 4, the information processing device 3 outputs a response to the medical consultation. Examples of user input include symptoms, chronic illnesses, and medication usage. In response to the medical consultation, the information processing device 3 outputs information that serves as the basis for the response in addition to the response.

[0089] (Configuration of Information Processing Device 3) As shown in FIG. 6, the information processing device 3 includes a control unit 20, a storage unit 37, and a communication unit .

[0090] The storage unit 37 has the same configuration and functions as the above-mentioned storage unit 27. The storage unit 37 also stores information about documents and authors of the documents.

[0091] Examples of information about documents and authors stored in the storage unit 37 are shown in Figures 7 and 8. Figure 7 is a diagram showing an example of a document in this exemplary embodiment. Figure 8 is a diagram showing an example of information about the author of a document in this exemplary embodiment.

[0092] 7, the documents stored in the storage unit 37 are medical documents. As shown in FIG. 7, the documents stored in the storage unit 37 may be stored in association with the authors, publication years, and abstracts of the papers.

[0093] 8, information about the author who created the document stored in the storage unit 37 may be stored in the storage unit 37. As shown in FIG. 8, the information about the author who created the document may include the doctor's name, place of employment, career history, and field of specialty stored in the storage unit 37.

[0094] In this way, the documents in the information processing system 100 are medical documents, and the author's background, field of expertise, etc. are clearly defined. Therefore, the medical documents in the information processing system 100 can be said to be highly reliable.

[0095] The communication unit 38 is an interface that transmits and receives data to and from external devices via a network. For example, the communication unit 38 transmits data supplied from the control unit 20 to the information processing terminal 4, and supplies data received from the information processing terminal 4 to the control unit 20. Examples of the communication unit 38 include, but are not limited to, communication chips for various communication standards such as Ethernet (registered trademark), Wi-Fi (registered trademark), and wireless communication standards for mobile data communication networks, and USB-compliant connectors.

[0096] The control unit 20 controls each component included in the information processing device 3. As shown in Fig. 6, the control unit 20 includes an acquisition unit 11, an extraction unit 12, a rewriting unit 13, a generation unit 14, an output control unit 23, a calculation unit 21, and a determination unit 22. In this exemplary embodiment, the acquisition unit 11, the extraction unit 12, the rewriting unit 13, the generation unit 14, the output control unit 23, the calculation unit 21, and the determination unit 22 are configured to realize an acquisition means, an extraction means, a rewriting means, a generation means, an output means, a calculation means, and a determination means, respectively.

[0097] The acquisition unit 11 acquires data supplied from the communication unit 38. As an example, the acquisition unit 11 acquires a first character string. The acquisition unit 11 stores the acquired first character string in the storage unit 37.

[0098] The extraction unit 12 extracts documents related to the character string. The method by which the extraction unit 12 extracts documents is as described above. The extraction unit 12 also obtains information about the authors of the extracted documents from the storage unit 37. The extraction unit 12 associates the extracted documents and information about the authors of the extracted documents with the first character string and stores them in the storage unit 37.

[0099] The rewriting unit 13 rewrites the character string. The method by which the rewriting unit 13 rewrites the first character string to generate the second character string is as described above.

[0100] The generation unit 14 generates a result of performing language processing on the character string. As described above, the generation unit 14 generates a first result by performing language processing on the second character string. The method by which the generation unit 14 generates the first result is as described above. The generation unit 14 associates the generated first result with the second character string and stores it in the storage unit 37.

[0101] The output control unit 23 outputs the data to the communication unit 38. As an example, the output control unit 23 outputs a result in which information identifying the document extracted by the extraction unit 12 is added to the first result generated by the generation unit 14. Furthermore, the output control unit 23 may output a result in which information regarding the author of the document extracted by the extraction unit 12 is added.

[0102] Furthermore, as described above, the output control unit 23 may output the reliability calculated by the calculation unit 21 in addition to the second result.

[0103] Furthermore, the output control unit 23 may be configured to output the second result when the determination unit 22 determines that the reliability calculated by the calculation unit 21 exceeds a threshold value.

[0104] The calculation unit 21 calculates the reliability of the result. As an example, the calculation unit 21 calculates the reliability of the first result generated by the generation unit 14. The method by which the calculation unit 21 calculates the reliability of the first result is as described above. The calculation unit 21 stores the calculated reliability in the storage unit 37 in association with the first result.

[0105] The determination unit 22 determines whether the value exceeds a threshold. As an example, the determination unit 22 determines whether the reliability calculated by the calculation unit 21 exceeds a threshold. The determination unit 22 associates the determination result with the reliability and stores it in the storage unit 37.

[0106] (Configuration of Information Processing Terminal 4) As shown in FIG. 6, the information processing terminal 4 includes a control unit 40, an input unit 45, a display unit 46, and a communication unit 48.

[0107] The control unit 40 controls each component included in the information processing terminal 4. The control unit 40 also includes an acquisition unit 41 and an output control unit 42, as shown in FIG.

[0108] The acquisition unit 41 acquires data supplied from the input unit 45 or the communication unit 48. As one example, the acquisition unit 41 acquires a character string from the input unit 45. As another example, the acquisition unit 41 acquires a second result from the communication unit 48. The acquisition unit 41 supplies the acquired data to the output control unit 42.

[0109] The output control unit 42 outputs data to the display unit 46 or the communication unit 48. As one example, the output control unit 42 outputs the character string acquired by the acquisition unit 41 to the communication unit 48. As another example, the output control unit 42 outputs the second result acquired by the acquisition unit 41 to the display unit 46.

[0110] The input unit 45 is an interface that accepts input of data. Examples of the input unit 45 include a mouse, a keyboard, a touchpad, and a microphone. The input unit 45 supplies the accepted data to the control unit 40.

[0111] The display unit 46 is a device that displays an image. For example, the display unit 46 displays an image based on data supplied from the control unit 40. Examples of the display unit 46 include a liquid crystal display and an organic EL (Electro Luminescence) display.

[0112] The communication unit 48 is an interface that transmits and receives data to and from external devices via a network. For example, the communication unit 48 transmits data supplied from the control unit 40 to the information processing device 3, and supplies data received from the information processing device 3 to the control unit 40. Examples of the communication unit 48 include, but are not limited to, communication chips for various communication standards such as Ethernet, Wi-Fi, and wireless communication standards for mobile data communication networks, and USB-compliant connectors.

[0113] (Processing Executed in Information Processing System 100) An information processing method executed in the information processing system 100 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of an information processing method S100 according to this exemplary embodiment.

[0114] (Step S101) In step S101, the acquisition unit 41 of the information processing terminal 4 acquires a character string (first character string). The acquisition unit 41 supplies the first character string to the output control unit .

[0115] (Step S102 ) In step S102 , the output control unit 42 outputs the first character string supplied from the acquisition unit 41 to the information processing device 3 via the communication unit 48 .

[0116] (Step S103) In step S103, the acquisition unit 11 of the information processing device 3 acquires the first character string output from the information processing terminal 4 via the communication unit 38. The acquisition unit 11 stores the first character string in the storage unit 37.

[0117] (Step S104) In step S104, the extraction unit 12 extracts documents related to the first character string stored in the storage unit 37. The extraction unit 12 also obtains information about the authors of the extracted documents from the storage unit 37. The extraction unit 12 associates the extracted documents and the information about the authors of the documents with the first character string and stores them in the storage unit 37.

[0118] (Step S105) In step S105, the rewriting unit 13 generates a second character string by rewriting the first character string using the first character string and the document stored in the storage unit 37. The rewriting unit 13 stores the second character string in the storage unit 37 in association with the first character string.

[0119] (Step S106) In step S106, the generation unit 14 uses the language model M trained to generate text based on the input text to generate a character string (first result) corresponding to the second character string stored in the storage unit 37. The generation unit 14 stores the first result in the storage unit 37 in association with the second character string.

[0120] (Step S107) In step S107, the calculation unit 21 calculates the reliability of the first result stored in the storage unit 37. The calculation unit 21 stores the calculated reliability in the storage unit 37 in association with the first result.

[0121] (Step S108) In step S108, the determination unit 22 determines whether the reliability stored in the storage unit 37 exceeds a threshold value.

[0122] (Step S109) If it is determined in step S108 that the reliability exceeds the threshold (step S108: YES), in step S109 the output control unit 23 generates, as an optimization result, a result (second result) in which information identifying the document stored in the storage unit 37 is added to the first result stored in the storage unit 37. The output control unit 23 may include, in the second result, a result in which information about the author of the document stored in the storage unit 37 is added. The output control unit 23 outputs the generated second result to the information processing terminal 4 via the communication unit 38.

[0123] (Step S110) In step S110, the acquisition unit 41 of the information processing terminal 4 acquires the second result output from the information processing device 3 via the communication unit 48. The acquisition unit 41 supplies the acquired second result to the output control unit 42.

[0124] (Step S111) In step S111, the output control unit 42 displays the second result supplied from the acquisition unit 41 on the display unit 46.

[0125] On the other hand, if it is determined in step S108 that the reliability does not exceed the threshold (step S108: NO), the output control unit 23 does not output the second result, and the information processing system 100 terminates the execution of the information processing method S100.

[0126] Alternatively, the output control unit 23 may output information indicating that a highly reliable result could not be generated to the information processing terminal 4 via the communication unit 38. In this case, the output control unit 42 of the information processing terminal 4 may display on the display unit 46 that a highly reliable result could not be generated.

[0127] (Example 1 of an image displayed by information processing terminal 4) An example of an image displayed by the information processing terminal 4 will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of an image displayed by the information processing terminal 4 according to this exemplary embodiment.

[0128] As described above, the output control unit 42 of the information processing terminal 4 displays the second result on the display unit 46. As an example, as shown on the left side of Fig. 10 , the output control unit 42 displays the second result res "Have you also noticed either eye sensitivity to light or slurring of your speech?" in response to an input "Moderate" from a user exhibiting a symptom.

[0129] As one example, the output control unit 42 may display the second result res including information identifying the document. As another example, when the acquisition unit 41 acquires information indicating a user's operation to select the second result res (for example, an operation of touching the display position of the second result res on the display unit 46), the output control unit 42 may display the information identifying the document. Furthermore, as described above, when the output control unit 23 of the information processing device 3 outputs the second result to which information about the author of the document has been added, the output control unit 42 may display the information about the author of the document in addition to the information identifying the document.

[0130] (Example 2 of image displayed by information processing terminal 4) In step S109 described above, the output control unit 23 may output, in addition to the second result, information for communicating with a doctor to the information processing terminal 4. As an example, the output control unit 23 may refer to information that identifies a document and information about the author of the document, and output, in addition to the second result, to the information processing terminal 4, contact information for a doctor who has the same specialty as the author.

[0131] For example, in step S109 described above, when the output control unit 23 outputs the doctor's contact information in addition to the second result to the information processing terminal 4, the information processing terminal 4 displays the doctor's contact information in addition to the second result on the display unit 46. In this configuration, when the acquisition unit 41 acquires information indicating an operation by the user to select the doctor's contact information (for example, an operation of touching the display position of the doctor's contact information on the display unit 46), the output control unit 42 contacts the doctor's contact information.

[0132] With this configuration, as shown in the center of FIG. 10, the information processing terminal 4 can allow the user to have a video call with a doctor.

[0133] (Example 3 of image displayed by information processing terminal 4) In step S109 described above, the output control unit 23 may output, in addition to the second result, information about an action suggested to the user to the information processing terminal 4. Examples of actions suggested to the user include going to a hospital and obtaining a prescription drug from a doctor. The following describes a configuration in which the output control unit 23 outputs, to the information processing terminal 4, information indicating a method for obtaining a prescription drug from a doctor.

[0134] If the second result includes information identifying the drug, the output control unit 23 may output the location of the pharmacy that sells the drug to the information processing terminal 4 in addition to the second result.

[0135] Alternatively, as described above, when the user communicates with a doctor, the doctor may output the user's prescription to the information processing terminal 4. When the information processing terminal 4 obtains the prescription, the information processing terminal 4 may output the location of a pharmacy that sells the drug listed in the prescription to the information processing terminal 4 in addition to the second result.

[0136] With this configuration, as shown on the right side of FIG. 10, the information processing terminal 4 can present to the user places where the medicine prescribed by the doctor can be purchased.

[0137] (Effect 1 of Information Processing System 100) As described above, in the information processing system 100 according to this exemplary embodiment, the information processing device 3 uses the language model M to perform language processing on a second character string obtained by rewriting a first character string using a document related to the first character string obtained from the information processing terminal 4. This allows the information processing device 3 to prevent the language model M from performing language processing by referencing documents whose content is unclear, such as documents with low credibility, documents of unknown authenticity, and documents of unknown origin. This allows the information processing device 3 to improve the reliability of the results of language processing performed using the language model M.

[0138] Furthermore, in the information processing system 100 according to this exemplary embodiment, the information processing device 3 outputs a result in which information identifying documents related to the first character string is added to the result of language processing performed by the language model M on the second character string. Therefore, the information processing device 3 can present to the user the result of the language processing and information on the documents referenced in the language processing. Therefore, the information processing device 3 can present to the user the reliability of the language processing performed using the language model.

[0139] (Effect 2 of Information Processing System 100) In the information processing system 100, the information processing terminal 4 accepts a medical consultation, and the information processing device 3 generates a response to the medical consultation. The following describes the effect of the configuration in which the information processing system 100 outputs a response to a medical consultation from a user.

[0140] First, in the information processing system 100, the information processing device 3 generates a response to a medical consultation using a language model M. In this configuration, a user receives medical consultation via an information processing terminal 4, such as a smartphone. Therefore, the information processing system 100 allows the user to easily receive medical consultation. Furthermore, the information processing system 100 allows the user to easily receive medical consultation anytime and anywhere. Furthermore, the information processing system 100 can provide the user with general information and advice regarding symptoms, for example, before the user receives a diagnosis or treatment.

[0141] Furthermore, since the information processing terminal 4 accepts medical consultations and outputs responses, the user can receive medical consultations without going to a hospital. Furthermore, with the information processing system 100, a response to a medical consultation can be obtained more quickly than if the user went to a hospital. Furthermore, with the information processing system 100, a response to a medical consultation is provided without the intervention of a doctor, so a response to a medical consultation can be provided at low cost.

[0142] Furthermore, the language model M used by the information processing device 3 performs language processing with reference to documents. For example, the information processing device 3 causes the language model M to perform language processing with reference to documents written by professional doctors, rather than documents of questionable credibility such as news articles on the Internet. Therefore, the information processing device 3 can present information with a higher degree of reliability than when a conventional language model is used.

[0143] [Example of Software Implementation] Some or all of the functions of the information processing devices 1, 2, and 3 may be implemented by hardware such as an integrated circuit (IC chip), or by software.

[0144] In the latter case, the information processing devices 1, 2, and 3 are realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in FIG. 11. The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for operating the computer C as the information processing devices 1, 2, and 3. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the information processing devices 1, 2, and 3.

[0145] The processor C1 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0146] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0147] The program P can also be recorded on a non-transitory, tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0148] [Additional Note 1] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiments are also included in the technical scope of the present invention.

[0149] [Additional Note 2] Part or all of the above-described embodiment can also be described as follows: However, the present invention is not limited to the following described aspects.

[0150] (Supplementary Note 1) A language processing device comprising: an acquisition means for acquiring a target text; an extraction means for extracting a document related to the target text; a rewriting means for rewriting the target text using the document; a generation means for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text; and an output means for outputting a result of adding information identifying the document to the text generated by the generation means.

[0151] (Supplementary Note 2) The information processing device according to Supplementary Note 1, further comprising: a calculation unit that calculates a reliability of the text generated by the generation unit.

[0152] (Appendix 3) The information processing device described in Appendix 2 further includes a determination means for determining whether the reliability exceeds a threshold, and when the determination means determines that the reliability exceeds the threshold, the output means outputs the result of adding information that identifies the document as an optimization result.

[0153] (Supplementary Note 4) The information processing device according to Supplementary Note 2 or 3, wherein the output means outputs the reliability in addition to a result to which information specifying the document is added.

[0154] (Supplementary Note 5) The information processing device according to Supplementary Note 4, wherein the calculation means calculates the reliability by referring to a result of inputting the text generated by the generation means, the document extracted by the extraction means, and the target text acquired by the acquisition means into the language model.

[0155] (Supplementary Note 6) An information processing method including: at least one processor acquiring target text; extracting documents related to the target text; rewriting the target text using the documents; generating text corresponding to the rewritten target text using a language model trained to generate text based on input text; and outputting a result of adding information identifying the document to the generated text.

[0156] (Supplementary Note 7) A program that causes a computer to execute an acquisition process that acquires a target text, an extraction process that extracts documents related to the target text, a rewriting process that rewrites the target text using the documents, a generation process that generates text corresponding to the rewritten target text using a language model trained to generate text based on input text, and an output process that outputs the result of adding information that identifies the document to the text generated in the generation process.

[0157] [Additional Note 3] Part or all of the above-described embodiment can also be expressed as follows.

[0158] (Supplementary Note 1) An information processing device including at least one processor, the at least one processor executing an acquisition process for acquiring a target text, an extraction process for extracting documents related to the target text, a rewriting process for rewriting the target text using the documents, a generation process for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text, and an output process for outputting a result of adding information identifying the document to the text generated in the generation process.

[0159] (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the at least one processor further executes a calculation process of calculating a reliability of the text generated in the generation process.

[0160] (Appendix 3) An information processing device as described in Appendix 2, further executing a judgment process to judge whether the reliability exceeds a threshold value, and if it is judged in the judgment process that the reliability exceeds the threshold value in the output process, outputting the result of adding information that identifies the document as an optimization result.

[0161] (Supplementary Note 4) The information processing device according to Supplementary Note 2 or 3, wherein the output process outputs the reliability in addition to a result to which information specifying the document is added.

[0162] (Supplementary Note 5) The information processing device according to Supplementary Note 4, wherein in the calculation process, the reliability is calculated by referring to the results of inputting the text generated in the generation process, the document extracted in the extraction process, and the target text acquired in the acquisition process into the language model.

[0163] The information processing device may further include a memory that stores a program for causing the processor to execute the acquisition process, the extraction process, the rewriting process, the generation process, the output process, the calculation process, and the determination process. The program may be recorded on a computer-readable, non-transitory, tangible recording medium.

[0164] 1, 2, 3 Information processing device 11 Acquisition unit 12 Extraction unit 13 Rewriting unit 14 Generation unit 15 Output unit 21 Calculation unit 22 Determination unit 23 Output control unit C1 Processor C2 Memory doc Document res, res2 Second result res1 First result str1 First character string str2 Second character string

Claims

1. A language processing device comprising: an acquisition means for acquiring a target text; an extraction means for extracting documents related to the target text; a rewriting means for rewriting the target text using the documents; a generation means for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text; and an output means for outputting a result of adding information identifying the document to the text generated by the generation means.

2. The information processing device according to claim 1, further comprising a calculation means for calculating a reliability of the text generated by the generation means.

3. The information processing device of claim 2, further comprising a judgment means for judging whether the reliability exceeds a threshold value, and when the judgment means judges that the reliability exceeds the threshold value, the output means outputs the result of adding information that identifies the document as an optimization result.

4. The information processing device according to claim 2 or 3, wherein the output means outputs the reliability in addition to the result to which the information specifying the document is added.

5. The information processing device according to claim 4, wherein the calculation means calculates the reliability by referring to the result of inputting the text generated by the generation means, the document extracted by the extraction means, and the target text acquired by the acquisition means into the language model.

6. An information processing method including: at least one processor: acquiring a target text; extracting documents related to the target text; rewriting the target text using the documents; generating text corresponding to the rewritten target text using a language model trained to generate text based on input text; and outputting a result of adding information identifying the document to the text generated in the generating step.

7. A program that causes a computer to execute the following processes: an acquisition process for acquiring target text; an extraction process for extracting documents related to the target text; a rewriting process for rewriting the target text using the documents; a generation process for generating text corresponding to the rewritten target text using a language model trained to generate text based on input text; and an output process for outputting the result of adding information that identifies the document to the text generated in the generation process.

Citation Information

Patent Citations

  • Method and system for answering question and recording medium with recorded question answering program

    JP2002132811A

  • Automatic identification and extraction of medical condition and fact from electronic medical treatment record

    JP2019049964A

  • Method and apparatus for verifying medical fact, electronic device, computer-readable storage medium, and computer program

    JP2021111411A

  • Virtual Person Interaction Device

    JP3241834U

  • Decision-support application and system for medical differential-diagnosis and treatment using a question-answering system

    US20120078062A1

Cited By

  • A system, method, and program for generating, evaluating, and scoring news releases.

    JP2026167883A

  • A system, method, and program for generating, evaluating, and scoring news releases.

    JP2026167994A

  • System, method, and program for generating and evaluating news releases

    JP7725038B1