JP-7856220-B2 - Information processing device, program, and information processing system

JP7856220B2JP 7856220 B2JP7856220 B2JP 7856220B2JP-7856220-B2

Inventors

辰巳大祐
高仁子

Assignees

株式会社レゾナック

Dates

Publication Date: 20260511
Application Date: 20250521
Priority Date: 20240524

Claims (11)

A summary sentence data generation unit performs summarization of the target sentence data multiple times according to processing instruction data and generates multiple summary sentence data for each of the multiple categories that constitute the target sentence data , An extraction unit that extracts key information contained in the plurality of summary sentence data for each category that constitutes the sentence data to be processed, A summary sentence data selection unit selects the summary sentence data to be output from the plurality of summary sentence data using the key information for each category , for each category that constitutes the sentence data to be processed . An information processing device having
The information processing apparatus according to claim 1, wherein the summary sentence data generation unit performs summarization of the processing target sentence data multiple times in accordance with the processing instruction data, generates multiple summary sentence data including summary sentences of the multiple categories constituting the processing target sentence data, and generates the multiple summary sentence data for each of the multiple categories by collecting the summary sentences for each of the multiple categories.
The system further includes an importance calculation unit that calculates the importance of the aforementioned key information, The information processing apparatus according to claim 1 or 2, characterized in that the summary text data selection unit selects the summary text data to be output from the plurality of summary text data using the importance level.
The summary text data selection unit, Using the importance of the aforementioned key information, the importance of each of the multiple summary sentence data is calculated. From the aforementioned plurality of summary data, select the first summary data with the highest importance. Using the importance of the remaining key information after removing the key information contained in the first summary data, the importance of each of the remaining summary data after removing the first summary data is calculated. The information processing apparatus according to claim 3, characterized in that it selects the second summary data with the highest importance from the remaining summary data.
The information processing apparatus according to claim 1 or 2, characterized in that the summary sentence data generation unit generates a plurality of summary sentence data from the same processing target sentence data according to different processing instruction data.
The information processing apparatus according to claim 1 or 2, characterized in that the summary sentence data generation unit generates the plurality of summary sentence data from different processing target sentence data in accordance with the same processing instruction data.
The information processing apparatus according to claim 1 or 2, characterized in that the summary sentence data generation unit generates a plurality of summary sentence data from different processing target sentence data according to different processing instruction data.
The system further includes a detection unit for detecting variations in the notation of the aforementioned key information, The information processing apparatus according to claim 1 or 2, characterized in that the extraction unit treats the detected key information of the notation variation as the same key information.
The information processing apparatus according to claim 3, characterized in that the importance calculation unit calculates the importance of the key information using one or more of the following: the number of occurrences of the key information, TF-IDF (Term Frequency - Inverse Document Frequency), or the co-occurrence relationship between words.
In an information processing device, Summary sentence data generation step: Performs summarization of the target sentence data multiple times according to processing instruction data, and generates multiple summary sentence data for each of the multiple categories that constitute the target sentence data . Extraction step of extracting key information contained in the plurality of summary sentence data for each category that constitutes the sentence data to be processed, A summary sentence data selection step in which, using the key information for each category, a summary sentence data to be output from the plurality of summary sentence data is selected for each category that constitutes the sentence data to be processed . A program that executes the command.
An input receiving unit that receives processing instruction data and data to be processed, A summary sentence data generation unit performs summarization of the target sentence data multiple times according to the processing instruction data and generates multiple summary sentence data for each of the multiple categories that constitute the target sentence data , An extraction unit that extracts key information contained in the plurality of summary sentence data for each category that constitutes the sentence data to be processed, A summary sentence data selection unit selects the summary sentence data to be output from the plurality of summary sentence data using the key information for each category , for each category that constitutes the sentence data to be processed . A display control unit that displays the selected summary data on a display device, An information processing system having

Description

This disclosure relates to information processing equipment, programs, and information processing systems. While large-scale language models (LLMs) can generate high-quality summaries, their content can vary with each generation, potentially missing important information. Furthermore, LLMs tend to generate information not present in the input document, known as hallucination. Conventionally, a step-by-step method (two-stage summarization) has been proposed, which involves first extracting text to be used in the summary from the input document and then synthesizing it to generate a highly explainable summary (see, for example, Non-Patent Document 1). Masafumi Enomoto et al., "Analysis of hallucination in two-stage summarization using a large-scale language model," Proceedings of the 30th Annual Meeting of the Association for Natural Language Processing (March 2024), pp. 2641-2646. This is a diagram illustrating an example of an information processing system according to this embodiment.This is a hardware configuration diagram of an example of a computer according to this embodiment.This is an illustrative diagram of an example of a process that generates summary sentence data from target sentence data according to prompts.This diagram illustrates an example of the process by which the information processing system according to this embodiment generates summary data from data to be processed.This is a functional configuration diagram of an example of an information processing system according to this embodiment.This is an example flowchart illustrating the processing of the information processing system according to this embodiment.This is an example flowchart illustrating the processing of the information processing system according to this embodiment.This is an example flowchart illustrating the process in step S16.This is an example flowchart illustrating the process in step S16.Figure 9 is an explanatory diagram illustrating an example of the process in the flowchart.This is an explanatory diagram illustrating an example of the process in step S12.This is an explanatory diagram illustrating an example of the process in step S12.This is an explanatory diagram illustrating an example of the process in step S12.This is an explanatory diagram illustrating an example of the process in step S12.This is a specific example of the processing performed by the information processing system according to this embodiment. Next, embodiments of the present invention will be described in detail. However, the present invention is not limited to the following embodiments. <System Configuration> Figure 1 is a configuration diagram of an example of an information processing system 1 according to this embodiment. The information processing system 1 in Figure 1 provides a summarization function using a large-scale language model (hereinafter referred to as LLM). The LLM generates summary sentence data from the sentence data to be processed according to a prompt. A prompt is an example of processing instruction data, and is data such as a string that instructs the LLM on the content of the summary sentence data to be generated. The information processing system 1 also selects the summary sentence data to be output from the multiple summary sentence data generated by the LLM, as described later. In this way, the information processing system 1 performs a process of selecting and outputting the summary sentence data selected from the multiple summary sentence data generated by the summarization function of the LLM. The information processing system 1 comprises an information processing device 10 and a user terminal 12, which are connected via a network 18 to enable data communication. The network 18 is, for example, a local area network (LAN) or the internet. The information processing device 10 can be implemented as a workstation or a PC (Personal Computer). The user terminal 12 can be implemented as an information processing terminal operated by the user, such as a PC, tablet, or smartphone. The user can operate the user terminal 12 and utilize the summarization function provided by the information processing device 10. The user operates the user terminal 12 and inputs the sentence data to be processed and prompts to the information processing device 10. The user terminal 12 transmits the input sentence data to be processed and prompts to the information processing device 10, thereby causing the information processing device 10 to output summarized sentence data of the sentence data to be processed, as described later. The user terminal 12 receives the summary text data of the processed sentence data output from the information processing device 10 and displays it on a display device or the like. In this way, the user can confirm the summary text data of the processed sentence data displayed on the display device or the like. Furthermore, the information processing device 10 receives the sentence data to be processed and prompts