Information processing device

Abstract

This chat will reflect the content of past chats. [Solution] The information processing device (10) includes a storage means (12) for storing first chat data relating to a first chat between a user and a large language model, a display means (151) for displaying history information relating to the first chat data when the user and the large language model start a second chat after the first chat, a reception means (14) for receiving user input, and a control means (11) for including at least a portion of the first chat data in a prompt input to the large language model in the second chat when the reception means receives user input indicating the selection of history information.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing apparatuses.

Background Art

[0002] As this type of apparatus, for example, an apparatus has been proposed that generates query data based on a document for a language model and uses a pair of the document and the query data for learning a search model for a chatbot (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] As a chatbot, a chatbot using a large language model (LLM) has been proposed. By the way, there is a limit to the length of a series of chats that a chatbot can record. For this reason, when the length of a series of chats reaches a predetermined limit length, the user must start a new chat. For example, in a new chat, when the user wants to chat on the premise of the content of a past chat, the user must input the content of the past chat. 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 problems, and an object thereof is to provide an information processing apparatus capable of performing a chat in which the content of a past chat is reflected.

Means for Solving the Problems

[0006] An information processing device according to one aspect of the present invention includes: a storage means for storing first chat data relating to a first chat between a user and a large language model; a display means for displaying history information relating to the first chat data when the user and the large language model start a second chat after the first chat; a receiving means for receiving input from the user; and a control means for including at least a portion of the first chat data in a prompt input to the large language model in the second chat when the receiving means receives input from the user indicating that it selects the history information. [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 figure shows an example of a displayed image. [Figure 3] This figure shows other examples of the 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 and a server 20. The information processing device 10 and the server 20 are configured to communicate with each other via a network NW. The server 20 is a server for operating a large-scale language model (LLM). For this reason, the server 20 may be referred to as an LLM server. The server 20 may also be a cloud server.

[0009] In Figure 1, 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.

[0010] 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.

[0011] 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).

[0012] 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.

[0013] 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.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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).

[0019] (Chatbot) Server 20 may provide a chatbot service using a large-scale language model. The computer program CP stored in the storage device 12 includes a computer program related to an application for using the above chatbot service (hereinafter referred to as "chat application" as appropriate). By launching the chat application via the input device 14, the user of the information processing device 10 can use the above chat service.

[0020] For example, the user may input a question sentence into the input field of the chat application via the input device 14. Note that the user is not limited to text input and may also perform voice input. 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 ****", "Answer ****", etc., which are requests, instructions, commands, etc. Therefore, the "question sentence" is not limited to a sentence in the interrogative form, 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.

[0021] The arithmetic unit 11 may transmit the first information indicating the question sentence to the server 20 via the communication device 13. The server 20 that has received the first information may input a prompt including the question sentence indicated by the first information into the large language model. The server 20 may obtain an answer to the question sentence generated by the large language model. The server 20 may transmit the second information indicating the answer to the information processing device 10. The arithmetic unit 11 of the information processing device 10 that has received the second information may control the display device 151 so that the answer indicated by the second information is displayed.

[0022] Note that the above chatbot service may be a chatbot service using a mechanism (Retrieval-Augmented Generation: RAG) that combines a large language model and the search of a specific information source (so-called knowledge base) to give the large language model a unique information source.

[0023] In this case, the arithmetic unit 11 may search the knowledge base based on the question text input by the user. The arithmetic unit 11 may transmit, via the communication device 13, third information indicating the question text and the search result to the server 20. The server 20 that has received the third information may input a prompt including the question text and the search result indicated by the third information into the large language model. The server 20 may acquire an answer to the question text generated by the large language model. The server 20 may transmit fourth information indicating the answer to the information processing device 10. The arithmetic unit 11 of the information processing device 10 that has received the fourth information may control the display device 151 so that the answer indicated by the fourth information is displayed.

[0024] By the way, there is a limit to the length of a series of chats that can be recorded in the chatbot service. Therefore, when the length of a series of chats reaches a predetermined limit length, the user has to start a new chat. Here, the chat application according to the present embodiment has, as a part of its functions, a function of saving chat data (in other words, chat history) related to the chat between the user and the large language model in the chatbot service.

[0025] In the information processing device 10, when the length of a series of chats reaches a predetermined limit length, for example, the chat application (specifically, the arithmetic unit 11) may store the chat data related to the series of chats in the storage device 12 in association with the user. Note that the chat data may be stored in a device different from the storage device 12 (for example, the server 20). Note that the arithmetic unit 11 treats the chat data related to the current chat and the chat data related to a new chat as separate data.

[0026] The computing unit 11 may generate a summary of chat data when chat data is stored (i.e., saved) as chat history. The chat data summary may be a summary of multiple utterances contained in the chat data (i.e., a summary of the entire series of chats including multiple utterances). The chat data summary may be a summary of each of the multiple utterances contained in the chat data. In other words, the chat data summary may be at least one of a summary of multiple utterances contained in the chat data, or a summary of each of the multiple utterances. The computing unit 11 may generate the chat data summary using a large-scale language model, or a language model (i.e., a language model smaller than a large-scale language model). The user may pre-configure whether a summary of the entire series of chats including multiple utterances or a summary of each of the multiple utterances is generated.

[0027] Now, when the length of a series of chats reaches a predetermined limit and the user starts a new chat, the display device 151 may display the image 210 shown in Figure 2. In other words, when the user starts a new chat, the arithmetic unit 11 may control the display device 151 to display the image 210. The image 210 may include an area 211 for displaying the content of the current chat and an area 212 for displaying chat history information related to the user (in other words, history information about stored chat data). Figure 2 shows a state where no information has yet been entered in the input field where the user's question is entered. As shown in Figure 2, when the user starts a new chat, the history information is displayed on the display device 151.

[0028] For example, if a user wants to initiate a new chat based on the content of a previous chat (e.g., the most recent chat), the user may select a history item displayed in area 212 via the input device 14. If the user selects a history item, the arithmetic unit 11 may input at least a portion of the chat data related to that history item into the input field displayed in area 211. In other words, simply by the user selecting a history item, at least a portion of the chat data related to that history item may be automatically entered into the input field. For example, at least a portion of the chat data may be a summary of that chat data. Furthermore, at least a portion of the chat data may be keywords.

[0029] After the user selects a piece of history information, the user may input a question via the input device 14. In this case, the display device 151 may display the image 210a shown in Figure 3. For example, as shown in Figure 3, the user's input field may include a summary of chat data relating to past chats and the user's question. The arithmetic unit 11 may send a prompt (corresponding to the first information described above) to the server 20, which includes the summary of chat data (i.e., at least a portion of the chat data relating to a piece of history information) and the question.

[0030] (Technical effects) In this embodiment, at least a portion of the chat data relating to past chats between the user and the large-scale language model can be included in the prompts input to the large-scale language model. As described above, when the user selects history information relating to chat data, at least a portion of the chat data is automatically input into the prompt. In other words, in this embodiment, if the user wants to have a chat based on the content of past chats, the user does not need to input the content of past chats. Therefore, according to the information processing device 10 of this embodiment, it is possible to have a chat that reflects the content of past chats while reducing the burden on the user.

[0031] The embodiments of the invention derived from the above-described embodiments are described below.

[0032] An information processing device according to one aspect of the invention includes: a storage means for storing first chat data relating to a first chat between a user and a large language model, associated with the user; a display means for displaying history information relating to the first chat data when the user and the large language model start a second chat after the first chat; a receiving means for receiving input from the user; and a control means for including at least a portion of the first chat data in a prompt input to the large language model in the second chat when the receiving means receives input from the user indicating that it selects the history information. In the above embodiment, "storage device 12" corresponds to an example of "storage means," "display device 151" corresponds to an example of "display means," "input device 14" corresponds to an example of "receiving means," and "arithmetic unit 11" corresponds to an example of "control means."

[0033] In the information processing device according to the above embodiment, at least a portion of the first chat data may be a summary of the first chat data. In this case, the summary of the first chat data may be at least one of a summary of the multiple utterances included in the first chat data, and a summary of each of the multiple utterances.

[0034] 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]

[0035] 10... Information processing device, 11... Arithmetic unit, 12... Memory device, 13... Communication device, 14... Input device, 15... Output device, 151... Display device

Claims

1. A storage means for storing first chat data relating to a first chat between a user and a large-scale language model, If, after the first chat, the user and the large-scale language model initiate a second chat, a display means for displaying history information relating to the first chat data is provided. A receiving means for receiving user input, When the receiving means receives input from the user indicating the selection of the history information, the control means includes, in the second chat, a prompt to be input to the large-scale language model, and An information processing device equipped with the following features.

2. At least a portion of the first chat data is a summary of the first chat data. The information processing apparatus according to claim 1.

3. The summary of the first chat data is at least one of the summaries of the multiple utterances contained in the first chat data, and the summaries of each of the multiple utterances. The information processing apparatus according to claim 2.

Images