Information processing device
The information processing device addresses user uncertainty in large language model answers by displaying relevant text data alongside responses, allowing users to validate the chatbot's output.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2024-12-10
- Publication Date
- 2026-06-22
AI Technical Summary
Users lack confidence in the validity of answers provided by large language models due to the exclusive information sources being undisclosed, leading to uncertainty in chatbot responses.
An information processing device that inputs a question and related text data from a database to a large language model, displays the model's answer alongside relevant text data, enabling users to assess the answer's validity.
Enables users to determine the validity of large language model answers by viewing associated text data, enhancing trust in chatbot responses.
Smart Images

Figure 2026100998000001_ABST
Abstract
Description
Technical Field
[0004] ,
[0006] , , , , , ,
[0005] , , , , ,
[0001] The present invention relates to the technical field of information processing devices.
Background Art
[0002] As an apparatus of this kind, for example, an apparatus that generates a document to be input as a prompt to a large language model (LLM) has been proposed (see Patent Document 1).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] For example, by combining a large language model with the search of a specific information source (hereinafter, appropriately referred to as a "knowledge base"), a chatbot using a mechanism (Retrieval-Augmented Generation: RAG) that gives the large language model an exclusive information source has been proposed. In such a chatbot, the above-mentioned exclusive information source is often not disclosed to the user. Therefore, the user may not be able to have confidence in the answer of the chatbot (in other words, the answer of the large language model). Note that a large language model is a language model constructed using a very large dataset and deep learning technology.
[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide an information processing device that enables a user to determine the validity of an answer of a large language model.
Means for Solving the Problems
[0006] An information processing device according to one aspect of the present invention includes an input means for inputting a prompt to a large-scale language model, which includes a question and text data related to the question extracted from a database by searching the database based on the question; an acquisition means for obtaining an answer to the question generated by the large-scale language model; and a display means for displaying information relating to the answer and the text data. [Brief explanation of the drawing]
[0007] [Figure 1] This is a diagram showing the configuration of an information processing system according to an embodiment. [Figure 2] This block diagram shows an example of the configuration of a computing device according to the embodiment. [Figure 3] This figure shows an example of a displayed image. [Modes for carrying out the invention]
[0008] Embodiments relating to the information processing device will be described with reference to Figures 1 to 3. In Figure 1, the information processing system 1 comprises an information processing device 10, a server 20, and a knowledge base 30. The information processing device 10, the server 20, and the knowledge base 30 are configured to communicate with each other via a network NW.
[0009] Server 20 and Knowledge Base 30 provide a chatbot using RAG. Server 20 is a server for operating a Large-Scale Language Model (LLM). Therefore, Server 20 may be referred to as an LLM server. Server 20 may also be a cloud server.
[0010] Knowledge Base 30 contains multiple text data. For example, the text data included in Knowledge Base 30 (in other words, registered) may be fragmented data generated by splitting a document. Fragmented data may be referred to as "chunks." Methods for splitting a document include, for example, splitting at fixed lengths, splitting at sentence units based on sentence delimiters, or splitting based on structure such as Markdown. Furthermore, each of the multiple fragmented data may be registered in Knowledge Base 30 as a vector. In other words, Knowledge Base 30 may be a vector database / vector store.
[0011] The information processing device 10 comprises an arithmetic unit 11, a storage device 12, a communication device 13, an input device 14, and an output device 15. The arithmetic unit 11, storage device 12, communication device 13, input device 14, and output device 15 are connected via a data bus 16. The information processing device 10 may be a personal computer, a tablet terminal, or a smartphone.
[0012] The arithmetic unit 11 may have a processor. The arithmetic unit 11 may have a single processor or multiple processors. In other words, the arithmetic unit 11 may have one or more processors. Furthermore, the processor may be a multi-core processor. If the arithmetic unit 11 has a single processor that is a multi-core processor, then logically, the arithmetic unit 11 can be said to have multiple processors.
[0013] The processor may be at least one of the following: CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and TPU (Tensor Processing Unit).
[0014] The storage device 12 may be at least one of the following: RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and optical disk array. In other words, the storage device 12 may be implemented by a single device or by multiple devices.
[0015] The communication device 13 may be capable of communicating with an external device (for example, a server 20) of the information processing device 10. The communication device 13 may use either wired or wireless communication.
[0016] The input device 14 is a device capable of receiving information input to the information processing device 10 from an external source. The input device 14 may include an operating device (e.g., a keyboard, mouse, touch panel, etc.) that can be operated by the user of the information processing device 10. The input device 14 may include a recording medium reader capable of reading information recorded on a recording medium that can be attached to and detached from the information processing device 10, such as a USB (Universal Serial Bus) memory. When information is input to the information processing device 10 via the communication device 13 (in other words, when the information processing device 10 acquires information via the communication device 13), the communication device 13 may function as an input device.
[0017] The output device 15 is a device capable of outputting information to the outside of the information processing device 10. The output device 15 has a display device 151 capable of outputting visual information such as characters and images as the above information. The output device 15 may also have a speaker capable of outputting auditory information such as sound as the above information. The output device 15 may also have a vibration motor capable of outputting tactile information such as vibration as the above information. The output device 15 may also have a printer. The output device 15 may be capable of outputting information to a recording medium that can be attached to and detached from the information processing device 10, such as a USB memory stick. When the information processing device 10 outputs information via the communication device 13, the communication device 13 may function as an output device.
[0018] The storage device 12 is capable of storing desired data. The storage device 12 may store the computer program CP that the arithmetic unit 11 will execute. The storage device 12 may temporarily store data that the arithmetic unit 11 will use temporarily when the arithmetic unit 11 is executing the computer program CP.
[0019] Furthermore, the computer program CP may be recorded on a non-temporary recording medium that is readable by a computer. In this case, the computer program CP may be stored in the storage device 12 by reading the recording medium using a recording medium reading device (not shown) provided by the information processing device 10. Furthermore, at least one of the following may be used as the recording medium: an optical disc, a magnetic medium, a magneto-optical disc, a semiconductor memory, and any other medium capable of storing a program. Furthermore, the computer program CP may be obtained from an external device (not shown) of the information processing device 10 via a communication device 13. In other words, the computer program CP may be downloaded from an external device to the storage device 12 of the information processing device 10.
[0020] The arithmetic unit 11 (for example, a processor) may execute the processing that the information processing device 10 should perform together with the memory device 12 in which the computer program CP is stored (in other words, together with the memory device 12 and the computer program CP stored in the memory device 12). For example, by the arithmetic unit 11 executing the computer program CP, a logical functional block for executing the processing that the information processing device 10 should perform may be realized within the arithmetic unit 11 (for example, within the processor).
[0021] The arithmetic unit 11 of the information processing apparatus 10 has a search unit 111, an input unit 112, and an acquisition unit 113 in order to use the chatbots provided by the server 20 and the knowledge base 30 (see FIG. 2). The search unit 111, the input unit 112, and the acquisition unit 113 may be realized as the logical functional blocks described above. Note that at least one of the search unit 111, the input unit 112, and the acquisition unit 113 may be realized as a physical processing circuit. At least one of the search unit 111, the input unit 112, and the acquisition unit 113 may be realized in a form in which logical functional blocks and physical processing circuits are mixed.
[0022] For example, the user U may use a chatbot using the information processing apparatus 10. For example, the user U may input a question sentence to the chatbot using the information processing apparatus 10. In this case, the user U may input the question sentence via the input device 14 of the information processing apparatus 10. Here, the "question sentence" is not limited to an interrogative sentence. For example, the "question sentence" may be a sentence including expressions such as "Tell me about ****" and "Answer ****", such as requests, instructions, commands, etc. Therefore, the "question sentence" is not limited to an interrogative sentence, but is a concept including sentences including expressions such as requests, instructions, commands, etc. That is, the "question sentence" may mean a sentence that requests an answer from the other party.
[0023] The search unit 111 of the information processing apparatus 10 searches the knowledge base 30 based on the question sentence. For example, the search unit 111 may calculate a search score indicating the degree of relevance between the question sentence and the text data included in the knowledge base 30. The search unit 111 may extract text data having a search score equal to or higher than a predetermined value as text data related to the question sentence. Note that the search unit 111 may extract a plurality of pieces of text data related to the question sentence. That is, the search unit 111 may extract one or more pieces of text data related to the question sentence from the knowledge base 30. Note that various existing modes can be applied to the method of calculating the search score. Therefore, a detailed description of the method of calculating the search score is omitted.
[0024] The input unit 112 of the information processing device 10 sends a prompt containing a question and text data related to the question to the server 20 via the communication device 13. As a result, the prompt is input to the large-scale language model. The server 20 sends the answer to the question generated by the large-scale language model to the information processing device 10. The acquisition unit 113 of the information processing device 10 acquires the answer sent by the server 20. The arithmetic unit 11 of the information processing device 10 controls the display device 151 to display the answer. At this time, the arithmetic unit 11 controls the display device 151 to display the text data related to the question together with the answer.
[0025] For example, the display device 151 may display the image 200 shown in Figure 3. The image 200 may include an area 201 where the question entered by user U is displayed, an area 202 where the answer generated by the large-scale language model is displayed, and an area 203 where information about text data related to the question is displayed. Note that the information about text data displayed in area 203 is not limited to the text data itself, but may also include information indicating the location where the text data is stored (e.g., an address).
[0026] Furthermore, the arithmetic unit 11 may control the display device 151 to display the prompt input to the large-scale language model together with the answer. In other words, when a prompt is displayed, information regarding the text data related to the question contained in the prompt may be displayed on the display device 151. Furthermore, the text data related to the question may be displayed in the area 202 where the answer generated by the large-scale language model is displayed. In this case, area 203 does not need to be provided.
[0027] (Technical effects) In this embodiment, along with the answer generated by the large-scale language model, information regarding text data related to the question (i.e., text data input to the large-scale language model along with the question) is displayed. For example, a user (e.g., user U) may determine whether the answer generated by the large-scale language model is valid by checking the information regarding text data related to the question. Therefore, the information processing device according to this embodiment allows the user to determine the validity of the answer from the large-scale language model.
[0028] Various aspects of the invention derived from the embodiments described above are described below.
[0029] An information processing device according to one aspect of the invention includes an input means for inputting a prompt to a large-scale language model, which includes a question and text data related to the question extracted from a database by searching the database based on the question; an acquisition means for acquiring an answer to the question generated by the large-scale language model; and a display means for displaying the answer and the text data. In the above embodiment, the "input unit 112" corresponds to an example of the "input means," the "acquisition unit 113" corresponds to an example of the "acquisition means," and the "display device 151" corresponds to an example of the "display means."
[0030] In the information processing apparatus according to the above embodiment, the display means may display the text data by displaying the prompt.
[0031] The present invention is not limited to the embodiments described above, and can be modified as appropriate without contradicting the gist or idea of the invention as can be read from the claims and specification as a whole. Information processing devices that involve such modifications are also included within the technical scope of the present invention. [Explanation of Symbols]
[0032] 1... Information processing system, 10... Information processing device, 20... Server, 30... Knowledge base, 111... Search unit, 112... Input unit, 113... Acquisition unit
Claims
1. An input means for inputting a prompt into a large-scale language model, which includes a question and text data related to the question extracted from the database by searching the database based on the question; An acquisition means for obtaining the answer to the question sentence generated by the aforementioned large-scale language model, A display means for displaying the aforementioned answer and information relating to the aforementioned text data, An information processing device equipped with the following features.
2. The display means displays information about the text data by displaying the prompt. The information processing apparatus according to claim 1.