Scientific research auxiliary system and method based on large language model

Through a scientific research auxiliary system based on large language model, the metadata layer and experimental simulation layer are used to generate a scientific and authentic paper draft, which solves the problem of lack of innovation and logic in the existing system, and achieves efficient and accurate Scientific research assistance.

CN118940833AActive Publication Date: 2024-11-12BEIJING XINGXU TECHNOLOGY CO LTD

Patent Information

Application Number
CN202410943811.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-12
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

Papers generated by existing scientific research auxiliary systems lack independent views and innovation, have poor logic and coherence, and cannot provide rigorous logical reasoning and theoretical support. The generated papers are single and have serious templates.

Method used

Using a scientific research auxiliary system based on large language models, including metadata layer, basic computing layer, experimental simulation layer and paper generation layer, the experimental data is constructed through user input information and available knowledge bases to generate a scientific and authentic paper draft. And fine-tune the model through iterative feedback mechanism to improve the in-depth discussion and rigorous reasoning of the paper.

Benefits of technology

It has achieved the generation of a scientific and authentic first draft of the paper, and the content is customized according to user needs, avoiding template generation, improving the logic and coherence of the paper, and providing efficient and accurate scientific research assistance for scientific research.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940833A_ABST
    Figure CN118940833A_ABST
Patent Text Reader

Abstract

The invention provides a scientific research auxiliary system and method based on a large language model, the system provides basic data support and available knowledge base support for the system through a metadata layer and a basic calculation layer, and provides customized experimental analysis and paper first draft writing services for user input information through an experimental simulation layer and a paper generation layer; moreover, in the process of generating the first draft of the thesis, the basic calculation layer, the experimental simulation layer and the thesis generation layer carry out iterative feedback on respective output results according to the principle effectiveness measurement index and the effect evaluation index, so as to carry out fine adjustment on models used by the layers according to the output results. Therefore, the system gradually realizes deep discussion and rigorous reasoning on the thesis through the four functional modules from bottom to top according to user requirements and a heuristic strategy based on the powerful information processing capability and tool calling capability of a large language model, and obtains a first draft of the thesis which has scientificity and authenticity and conforms to the specification of the thesis; and efficient and accurate scientific research assistance is provided for the scientific research process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of scientific research assistance systems, and in particular to a scientific research assistance system and method based on a large language model. Background Art

[0002] The scientific research support system is an important tool to assist researchers in completing scientific research. With the development of science and technology, various types of scientific research support systems have emerged, covering multiple scientific research processes from literature retrieval, experimental design, data analysis, to paper writing, knowledge management, etc. A scientific research support system with excellent performance can provide reliable support for scientific research and improve the efficiency of scientific research.

[0003] However, existing research support systems only generate papers based on the titles and fields input by users. These papers lack independent viewpoints and innovation, and are merely summaries and repetitions of existing data. Such papers cannot provide valuable references for scientific research. Moreover, in complex and in-depth scientific research fields, the generated papers lack in-depth discussions at the logical level and rigorous reasoning processes, which makes the logic and coherence of the generated papers poor. Scientific research papers require rigorous logical reasoning and theoretical support, which is difficult for existing research support systems to fully grasp. In addition, the paragraphs of papers generated by existing research support systems have single content, strong paragraph sequence, and serious templates.

[0004] Therefore, there is an urgent need for a scientific research assistance system with excellent performance to generate a draft of a paper that is scientific, authentic, and in line with paper specifications, so as to provide better scientific research assistance for scientific research. Summary of the invention

[0005] In view of the above problems, the embodiments of the present application provide a scientific research assistance system and method based on a large language model to overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect of an embodiment of the present application, a scientific research assistance system based on a large language model is disclosed, comprising:

[0007] The metadata layer, including the corpus and tool library, is used to provide basic data for the basic computing layer and the paper generation layer;

[0008] The basic computing layer is used to regularize and sort the basic data based on the pre-trained language model to obtain a usable knowledge base, where the usable knowledge base represents the callable knowledge meta-services and tool meta-services;

[0009] The experiment simulation layer is used to construct and simulate the generation of experiment data based on the large language model according to the user input information and the available knowledge base to obtain the experiment data;

[0010] A paper generation layer, for generating a first draft of the paper based on a large language model, according to the user input information, the basic data, the experimental data and the available knowledge base;

[0011] In the process of generating the first draft of the paper, the basic computing layer, the experimental simulation layer and the paper generation layer iteratively feedback their respective output results according to the principle validity measurement index and the effect evaluation index, so as to fine-tune the model used by themselves according to the output results.

[0012] Optionally, the available knowledge base includes: specialized knowledge graph construction, embedded representation of scientific data, literature material similarity retriever, callable tool retrieval coding, knowledge linking system, and large model preset logical chain.

[0013] Optionally, the experimental simulation layer includes:

[0014] The investigative experiment module includes a target data acquisition module and a data visualization modeling module, which is used to generate basic experimental data;

[0015] Theoretical experiment module, including inductive bias introduction module and basic theoretical reasoning module, is used to generate theoretical experimental data;

[0016] The simulation experiment module includes virtual environment construction, meta-code module construction and code logic chain combination module, which are used to generate simulation experiment data.

[0017] Optionally, the paper generation layer includes:

[0018] A previous work analysis module, used for analyzing the basic data;

[0019] The paper logic combing module is used to comb out the logical structure of the paper draft according to the user input;

[0020] Thesis formula deduction module, used to derive the formula used in the first draft of the thesis;

[0021] A paper illustration generation module, used to generate illustrations for the first draft of the paper;

[0022] An experimental data regularization module, used for normalizing the experimental data;

[0023] An experimental data analysis module, used for analyzing the experimental data;

[0024] Reference regularization module, used to insert references in the first draft of the paper.

[0025] A second aspect of the embodiment of the present application discloses a scientific research assistance method based on a large language model, which is applied to the scientific research assistance system based on a large language model described in the first aspect of the embodiment of the present application, and the method includes:

[0026] Obtaining user input information, wherein the user input information at least includes a paper title and a paper field;

[0027] The experimental simulation layer constructs and simulates experimental data generation according to the user input information and the available knowledge base provided by the basic computing layer to obtain experimental data;

[0028] The paper generation layer constructs a hierarchical index vector database according to the basic data provided by the metadata layer, and generates a first draft of the paper according to the user input information, the hierarchical index vector database, the available knowledge base and the experimental data.

[0029] Optionally, the paper generation layer constructs a hierarchical index vector database based on the basic data provided by the metadata layer, and generates a first draft of the paper based on the user input information, the hierarchical index vector database, the available knowledge base and the experimental data, including:

[0030] Constructing a specialized document library according to the user input information and the hierarchical index vector database;

[0031] Generate a paper abstract and keywords based on the specialized document library, and generate a paper outline based on the paper abstract and the keywords;

[0032] Sending the paper abstract, the keywords and the paper outline to the user, so that the user can modify the paper abstract, the keywords and the paper outline to obtain a modified paper abstract, modified keywords and a modified paper outline;

[0033] Creating an online reference library based on the modified paper abstract, the modified keywords and the modified paper outline;

[0034] Generate English abstracts based on the online reference library;

[0035] Based on a randomized paper paragraph generation strategy, parallel paper generation is performed according to the English abstract, the available knowledge base and the experimental data to obtain a first draft of the paper.

[0036] Optionally, generating a paper outline according to the paper abstract and the keywords includes:

[0037] According to the paper abstract and the keywords, randomly retrieve multiple learning documents from the specialized document library;

[0038] Sorting out the paper logic of the plurality of learning documents to obtain a plurality of initial paper outlines;

[0039] Imitation learning is performed according to the multiple initial paper outlines and domain-based reference materials to obtain a paper outline, wherein the domain-based reference materials are references provided by the user.

[0040] Optionally, the randomized paper paragraph generation strategy includes:

[0041] When the word count of the first draft of the paper is less than the first word count, the first draft of the paper includes a first-level title, and a first paragraph generation strategy is executed, wherein the first paragraph generation strategy calls a large language model basic unit once for each first-level title to generate multiple paragraphs corresponding to each first-level title;

[0042] When the number of words in the first draft of the paper is greater than or equal to the first number of words and less than or equal to the second number of words, the first draft of the paper includes a first-level title, a second-level title, and a third-level title, and a second paragraph generation strategy is executed, wherein the second paragraph generation strategy calls the large language model basic unit once for each second-level title or each third-level title to generate multiple paragraphs corresponding to each second-level title or each third-level title, and the second number of words is greater than the first number of words;

[0043] In the case that the number of words in the first draft of the paper is greater than the second number of words, the first draft of the paper includes a first-level title, a second-level title and a third-level title, and a third paragraph generation strategy is executed. The third paragraph generation strategy randomly calls the large language model basic unit multiple times in each second-level title or each third-level title to generate multiple paragraphs of content corresponding to each second-level title or each third-level title.

[0044] Optionally, the large language model basic unit is randomly called multiple times in each secondary title or each tertiary title to generate multiple paragraphs of content corresponding to each secondary title or each tertiary title, including:

[0045] The content of each title is segmented and planned to obtain the center of each paragraph, wherein the title includes a secondary title and a tertiary title;

[0046] Calling the large language model basic unit to generate the first paragraph content according to the center of the first paragraph;

[0047] The large language model basic units are called in sequence to generate the next paragraph of content according to the previous paragraph of content and the center of the next paragraph, until all the paragraph contents under the current title are generated.

[0048] Optionally, the large language model basic unit is encapsulated according to the following steps based on the reinforcement learning iterative tuning strategy:

[0049] Receiving the user input information, and retrieving relevant data according to the user input information;

[0050] Constructing prompt information according to the retrieved relevant data;

[0051] Calling a large language model according to the prompt information;

[0052] Based on the large language model, a structured output result is constructed.

[0053] Optionally, the method further comprises:

[0054] Screening papers according to the modified keywords to obtain screened papers;

[0055] A semantic matching library is constructed based on sentences of the contents or abstracts of the screened papers;

[0056] Comparing the sentences in the first draft of the paper with the sentences in the semantic matching library to obtain a similarity comparison result;

[0057] According to the similarity comparison result, the similarity threshold and the dynamic citation probability, literature citations are added to the first draft of the paper.

[0058] Optionally, the dynamic citation probability is determined according to the product of the citation probabilities corresponding to the citation threshold constraint, the citation distribution constraint, the multiple citation constraint and the repeated citation constraint, wherein:

[0059] The reference threshold constraint is that when the similarity comparison result is greater than the similarity threshold, the reference is made according to the full probability, and when the similarity comparison result is not greater than the similarity threshold, the reference is made according to the first probability, and the full probability reference represents that the reference probability is 100%;

[0060] The citation distribution constraint is to cite the content of the first chapter according to the full probability, cite the content of the second chapter according to the second probability, not cite the content of the last chapter, and cite the content of other chapters according to the third probability, wherein the third probability is less than the second probability;

[0061] The multiple citation constraint, when multiple citation documents are retrieved in each citation bracket, the citation documents in the citation bracket are sorted by similarity, and the first N documents with the highest similarity are cited according to full probability, where N is an integer greater than 1;

[0062] The repeated citation constraint is that when the same document is cited multiple times in the same paragraph, it is cited according to the fourth probability and the number of citations of the same document in the same paragraph is recorded. The fourth probability decays exponentially according to the number of citations.

[0063] The embodiments of the present application include the following advantages:

[0064] The scientific research assistance system based on the large language model provided in the embodiment of the present application provides basic data support and available knowledge base support for the system through the metadata layer and the basic computing layer, and provides customized experimental analysis and paper draft writing services for user input information through the experimental simulation layer and the paper generation layer; since the experimental data is generated by constructing and simulating the experimental data according to the user input information and the available knowledge base, that is, the experimental data is obtained by customized analysis and design based on the available knowledge base according to the user needs, thus ensuring the accuracy and authenticity of the experimental data; since the paper draft is generated by the paper model according to the user input information, the basic data, the experimental data and the available knowledge base, that is, the content of the paper draft is written based on the user needs, with the basic data as a reference and real and accurate experimental data as the basis, rather than being generated in a templated manner, thus ensuring the scientific nature of the content of the paper draft; since the paper draft is directly generated based on the user input information rather than a short text description, the system can achieve efficient content generation.

[0065] In the process of generating the first draft of the paper, the basic computing layer processes its own input data based on the pre-trained language model to ensure the running speed of the system; the experimental simulation layer and the paper generation layer process their own input data based on the large language model respectively; and the basic computing layer, the experimental simulation layer and the paper generation layer iteratively feedback their respective output results according to the principle validity measurement index and the effect evaluation index, so as to fine-tune the model used by themselves according to the output results, and further retain the scientific nature of the first draft of the paper. In this way, based on the powerful information processing ability and tool calling ability of the large language model, the system is based on four functional modules from bottom to top, according to user needs and heuristic strategies, starting from the basic data and available knowledge base, and sequentially carries out the scientific research process of experimental construction and simulation experimental data generation, and first draft of the paper writing, gradually realizing the in-depth discussion and rigorous reasoning of the paper, and obtaining a first draft of the paper that is scientific and authentic and meets the paper specifications, providing efficient and accurate scientific research assistance for the scientific research process. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0067] Figure 1 It is a structural diagram of a scientific research assistance system based on a large language model provided in an embodiment of the present application;

[0068] Figure 2 It is a structural diagram of another scientific research auxiliary system based on a large language model provided in an embodiment of the present application;

[0069] Figure 3 It is a flowchart of a scientific research assistance method based on a large language model provided in an embodiment of the present application;

[0070] Figure 4 A schematic diagram of a theoretical model for writing a first draft of a paper provided in an embodiment of the present application;

[0071] Figure 5 It is a flow chart for generating a first draft of a paper adopted by an embodiment of the present application;

[0072] Figure 6 is a flowchart of the steps of a paragraph generation method provided in an embodiment of the present application;

[0073] Figure 7 It is a packaging method of a large language model basic unit provided in an embodiment of the present application;

[0074] Figure 8 It is a flow chart of the steps of a method for adding references provided by the present application. DETAILED DESCRIPTION

[0075] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0076] Reference Figure 1 As shown, Figure 1 Schematic diagram of a scientific research support system based on a large language model provided in an embodiment of the present application. Figure 1 As shown, the scientific research assistance system based on the large language model includes:

[0077] The metadata layer 110 includes a corpus and a tool library, which is used to provide basic data for the basic calculation layer and the paper generation layer;

[0078] The basic computing layer 120 is used to regularize and sort the basic data based on the pre-trained language model to obtain an available knowledge base, where the available knowledge base represents the callable knowledge meta-service and tool meta-service;

[0079] The experiment simulation layer 130 is used to construct and simulate the generation of experiment data based on the large language model according to the user input information and the available knowledge base to obtain the experiment data;

[0080] The paper generation layer 140 is used to generate a first draft of the paper based on the large language model, according to the user input information, the basic data, the experimental data and the available knowledge base;

[0081] In the process of generating the first draft of the paper, the basic computing layer, the experimental simulation layer and the paper generation layer iteratively feedback their respective output results according to the principle validity measurement index and the effect evaluation index, so as to fine-tune the model used by themselves according to the output results.

[0082] In the embodiment of the present application, the tool library in the metadata layer can assist researchers in providing reliable means for reproducing old experiments and designing new experiments. The tool library includes available APIs (Application Programming Interfaces), domain inductive biases, nominal knowledge graphs, and other prior knowledge. In order to ensure the accuracy and stability of the content retrieved by the large language model of the basic computing layer, these heterogeneous and multi-level data in the tool library are also cleaned and vectorized, and ultimately the basic data with unified expression will be provided to the basic computing layer.

[0083] The basic computing layer is a service base based on the metadata layer. It organizes and sorts the basic data provided by the metadata layer to obtain an available knowledge base, which represents the callable knowledge meta-services and tool meta-services. In other words, the available knowledge base is a meta-service that can be better called by the upper-level modules (such as the experimental simulation layer and the paper generation layer) compared to the basic data.

[0084] Specifically, the available knowledge base includes: specialized knowledge graph construction, embedded representation of scientific data, literature material similarity retriever, callable tool retrieval code, knowledge link system, and logical chain preset by large model. These available knowledge bases are the basic units for the upper experimental simulation layer to perform experimental design and the paper generation layer to perform paper writing. In addition, in order to ensure the operating speed of the system, the basic computing layer and embedding-related service implementation are mainly completed by PLM (Pretrained Language Models).

[0085] As the decisive basis for the generation of the first draft paper, the experimental simulation layer mainly implements the design and execution of investigative experiments, theoretical experiments and simulation experiments through a large language model based on the basic experimental information input by the user and the meta-services (i.e., available knowledge base) provided by the basic computing layer. Specifically, the experimental simulation layer includes: an investigative experiment module, including a target data acquisition module and a data visualization modeling module, which are used to generate basic experimental data; a theoretical experiment module, including an inductive bias introduction module and a basic theoretical reasoning module, which are used to generate theoretical experimental data; a simulation experiment module, including a virtual environment construction, a meta-code module construction and a code logic chain combination module, which are used to generate simulation experimental data. In this way, through the various functional modules in the experimental simulation layer, basic experimental data, theoretical experimental data and simulation experimental data can be provided for the writing of the upper paper generation layer; because the experimental data is obtained through customized analysis and design based on user needs using the available knowledge base, the accuracy and authenticity of the experimental data are guaranteed.

[0086] The paper generation layer is the final output of the system for users. It generates a draft of the paper based on user input information, basic data, experimental data and available knowledge base. The draft of the paper can be an experimental result analysis report or an academic paper. Specifically, the paper generation layer includes: a previous work analysis module for analyzing the basic data; a paper logic combing module for combing out the logical structure of the draft of the paper based on the user input; a paper formula deduction module for deriving the formulas used in the draft of the paper; a paper illustration generation module for generating illustrations for the draft of the paper; an experimental data regularization module for normalizing the experimental data; an experimental data analysis module for analyzing the experimental data; and a reference regularization module for inserting references into the draft of the paper. In this way, based on the various functional modules in the paper generation layer, a compliant scientific research paper (i.e., a first draft of the paper) that is innovative, academic, feasible, and credible can be stably written according to the user input information to provide certain reference and support in the subsequent scientific research process. Since the content of the first draft of the paper is written according to user needs, with basic data as a reference and real and accurate experimental data as the basis, the scientific nature of the content of the first draft of the paper is guaranteed.

[0087] In summary, the scientific research assistance system based on the large language model provided in the embodiment of the present application provides basic data support and available knowledge base support for the system through the metadata layer and the basic computing layer, and provides customized experimental analysis and paper draft writing services for user input information through the experimental simulation layer and the paper generation layer; since the experimental data is generated by constructing and simulating the experimental data generation according to the user input information and the available knowledge base, the experimental data is obtained by customized analysis and design based on the user needs using the available knowledge base, thereby ensuring the accuracy of the experimental data; since the paper draft is generated by the paper model based on the user input information, the basic data, the experimental data and the available knowledge base, the content of the paper draft is written based on user needs, with the basic data as a reference and real and accurate experimental data as the basis, rather than being generated in a templated manner, thereby ensuring the scientific nature of the content of the paper draft; since the paper draft is directly generated based on the user input information rather than a short text description, the system can achieve efficient content generation.

[0088] In the process of generating the first draft of the paper, the basic computing layer processes its own input data based on the pre-trained language model to ensure the running speed of the system; the experimental simulation layer and the paper generation layer process their own input data based on the large language model respectively; and the basic computing layer, the experimental simulation layer and the paper generation layer iteratively feedback their respective output results according to the principle validity measurement index and the effect evaluation index, so as to fine-tune the model used by themselves according to the output results, and further retain the scientific nature of the first draft of the paper. In this way, based on the powerful information processing ability and tool calling ability of the large language model, the system is based on four functional modules from bottom to top, according to user needs and heuristic strategies, starting from the basic data and available knowledge base, and sequentially carries out the scientific research process of experimental construction and simulation experimental data generation, and first draft of the paper writing, gradually realizing the in-depth discussion and rigorous reasoning of the paper, and obtaining a first draft of the paper that is scientific and authentic and meets the paper specifications, providing efficient and accurate scientific research assistance for the scientific research process.

[0089] For example, Figure 2 It is a structural diagram of another scientific research assistance system based on a large language model provided in an embodiment of the present application. Specifically, the scientific research assistance system of the large language model includes a metadata layer, a basic computing layer, an experimental simulation layer, and a paper generation layer. Among them, the metadata layer includes a corpus and a tool library. The corpus includes: real-time news information, a public academic paper library, a proprietary academic document library, and other available Internet data; in order to ensure the real-time nature of the corpus, various data are connected to the metadata layer through network probes. The tool library can assist scientific researchers in providing reliable means for reproducing old experiments and designing new experiments. The tool library includes available APIs, domain induction biases, nominal knowledge graphs, and other prior knowledge.

[0090] The basic computing layer provides an available knowledge base based on the service base of the metadata layer. The available knowledge base includes: specialized knowledge graph construction, embedded representation of scientific data, literature material similarity searcher, callable tool retrieval coding, knowledge link system, and large model preset logical chain. The experimental simulation layer includes: investigative experimental module (including target data acquisition module and data visualization modeling module), theoretical experimental module (including inductive bias introduction module and basic theoretical reasoning module), simulation experimental module (including virtual environment construction, metacode module construction and code logic chain combination module); through the various functional modules of the experimental simulation layer, experimental data is provided for paper generation.

[0091] The paper generation layer includes: previous work analysis module, paper logic combing module, paper formula deduction module, paper illustration generation module, experimental data regularization module, experimental data analysis module, and reference regularization module. Through the various functional modules of the paper generation layer, you can write a compliant scientific research paper that is innovative, academic, feasible, and credible.

[0092] Reference Figure 3 As shown, Figure 3 1 is a flow chart of the steps of a scientific research assistance method based on a large language model provided in an embodiment of the present application, and the method is applied to the above-mentioned scientific research assistance system based on a large language model. Figure 3 As shown, the method includes steps S310 to S330:

[0093] Step S310: Obtain user input information, where the user input information at least includes the paper title and paper field.

[0094] Step S320: The experiment simulation layer constructs and simulates the generation of experimental data according to the user input information and the available knowledge base provided by the basic computing layer to obtain experimental data.

[0095] Step S330: The paper generation layer constructs a hierarchical index vector database based on the basic data provided by the metadata layer, and generates a first draft of the paper based on the user input information, the hierarchical index vector database, the available knowledge base and the experimental data.

[0096] In the embodiment of the present application, the metadata layer and basic computing layer in the scientific research auxiliary system based on the large language model are independent of the user output information, and provide basic data support and basic meta-service support for the system. After the system obtains the user input information, it mainly calls the experimental simulation layer and the paper generation layer to perform experimental analysis and generate the first draft of the paper.

[0097] When writing the first draft of the paper, first execute step S310 to obtain user input information, where the user input information can be input into the system by the user through the input text editor; then execute step S320, the experimental simulation layer customizes the experimental data according to the user input information and the available knowledge base provided by the basic computing layer to construct and simulate the experiment that meets the user input information and obtain the experimental results. Then execute step S330, the paper generation layer uses the basic data provided by the metadata layer as a reference to construct a hierarchical index vector database, so as to write the first draft of the paper in combination with the experimental data, user input information and the available knowledge base.

[0098] In some embodiments, the user input information also includes: an abstract (i.e., a regularized abstract) and core references, so as to provide a more scientific reference for the large language model to generate a draft of the paper. For example, Figure 4 A schematic diagram of a theoretical model for writing a first draft of a paper provided in an embodiment of the present application, wherein the paper generation layer writes the first draft of the paper according to the theoretical model for writing a first draft of the paper. Specifically, the paper generation layer uses the basic data provided by the metadata layer as a reference, edits the metadata according to the document editor, and constructs a hierarchical index vector database; wherein the basic data may include HowNet documents, real-time news, and international public document libraries, which are accessed to the metadata layer through HowNet protocols or real-time network probes. Afterwards, an information retriever is used to retrieve domain-specific knowledge from the hierarchical index vector database based on user input information, thereby obtaining a first draft generation prompt based on the academic style prompt design, the user-entered abstract, and the core references. Finally, based on the first draft generation prompt, the large language model is called to write the paper to obtain a first draft of the paper.

[0099] Based on the above embodiment process, since the experimental data is obtained by constructing and simulating the experimental data generation by the experimental simulation layer according to the user input information and the available knowledge base, that is, the experimental data is obtained by customized analysis and design based on the available knowledge base according to the user needs, which ensures the accuracy of the experimental data; since the first draft of the paper is generated by the paper model according to the user input information, the basic data, the experimental data and the available knowledge base, that is, the content of the first draft of the paper is written based on the user needs, with the basic data as a reference and the real and accurate experimental data as the basis, rather than being generated in a templated manner, which ensures the scientific nature of the content of the first draft of the paper; since the first draft of the paper is directly generated according to the user input information, rather than a short text description, the system can achieve efficient content generation. In this way, according to user needs and heuristic strategies, starting from the basic data and the available knowledge base, the scientific research process of experimental construction, simulation of experimental data generation, and first draft of the paper is carried out in sequence, and the in-depth discussion and rigorous reasoning of the paper are gradually realized, and a first draft of the paper that is scientific and authentic and meets the paper specifications is obtained. This method provides an efficient and accurate auxiliary method for literature research, innovation discovery, experimental simulation, data analysis, and first draft writing in the scientific research process.

[0100] In an optional embodiment, the paper generation layer constructs a hierarchical index vector database based on the basic data provided by the metadata layer, and generates a first draft of the paper based on the user input information, the hierarchical index vector database, the available knowledge base and the experimental data, including steps A1 to A6:

[0101] Step A1: constructing a specialized document library according to the user input information and the hierarchical index vector database;

[0102] Step A2: generating a paper abstract and keywords based on the specialized literature library, and generating a paper outline based on the paper abstract and the keywords;

[0103] Step A3: sending the paper abstract, the keywords and the paper outline to the user, so that the user can modify the paper abstract, the keywords and the paper outline to obtain a modified paper abstract, modified keywords and modified paper outline;

[0104] Step A4: creating an online reference library according to the modified paper abstract, the modified keywords and the modified paper outline;

[0105] Step A5: Generate an English abstract based on the online reference library;

[0106] Step A6: Based on the randomized paper paragraph generation strategy, parallel paper generation is performed according to the English abstract, the available knowledge base and the experimental data to obtain a first draft of the paper.

[0107] In the embodiment of the present application, the proprietary document library constructed according to the user input information and the hierarchical index vector database is a coarse-grained reference generation database, and the paper abstract, keywords and paper outline are quickly obtained based on the coarse-grained reference generation database. In order to make the final draft of the paper more scientific, the paper abstract, keywords and paper outline are fed back to the user, and the user modifies the paper abstract, keywords and paper outline to obtain a modified paper abstract, modified keywords and modified paper outline that are more in line with user needs. Afterwards, a fine-grained online reference library (the online reference library is more relevant to the user's research field) is constructed based on the modified paper abstract, modified keywords and modified paper outline to generate an English abstract. Finally, parallel paper generation is performed according to the English abstract, the available knowledge base and the experimental data to obtain a first draft of the paper; wherein, parallel paper generation refers to the ability to generate the contents of multiple chapters at the same time, so as to achieve efficient first draft generation of the paper.

[0108] In some embodiments, before step A1, the local document database is initialized, that is, the basic data provided by the metadata layer is loaded into the paper generation module, and after the local document database is initialized, the large language model is initialized. After step A6, the generated paper draft is written into a local word document, and the log record is updated, and finally the cache in the system is cleared. For example, Figure 5 It is a flow chart for generating a first draft of a paper adopted in an embodiment of the present application.

[0109] In this way, by establishing two reference generation databases of different sizes, coarse-grained and fine-grained, the first draft of the paper is generated in parallel with short delay according to the experimental data and available knowledge base, and the first draft of the paper is generated through the diversification and accuracy of collaborative calls of multiple databases.

[0110] In an optional embodiment, a paper outline is generated according to the paper abstract and the keywords, including: randomly retrieving multiple learning documents from the specialized document library according to the paper abstract and the keywords; combing the paper logic of the multiple learning documents to obtain multiple initial paper outlines; performing imitation learning according to the multiple initial paper outlines and domain-based reference materials to obtain a paper outline, wherein the domain-based reference materials are reference documents provided by users.

[0111] According to the embodiments of the present application, multiple learning documents randomly retrieved from a specialized document library based on paper abstracts and keywords are documents related to user research. Therefore, based on the retrieved multiple learning documents, valuable references can be provided for writing a first draft of the paper, so as to obtain a more scientific paper outline based on the multiple learning documents, so as to provide support for the subsequent writing of the first draft of the paper.

[0112] In an optional embodiment, the randomized paper paragraph generation strategy includes steps B1 to B3:

[0113] Step B1: when the word count of the first draft of the paper is less than the first word count, the first draft of the paper includes a first-level title, and a first paragraph generation strategy is executed, wherein the first paragraph generation strategy calls a large language model basic unit once for each first-level title to generate multiple paragraphs corresponding to each first-level title;

[0114] Step B2: When the number of words in the first draft of the paper is greater than or equal to the first number of words and less than or equal to the second number of words, the first draft of the paper includes a first-level title, a second-level title, and a third-level title, and a second paragraph generation strategy is executed, wherein the second paragraph generation strategy calls the large language model basic unit once for each second-level title or each third-level title to generate multiple paragraphs corresponding to each second-level title or each third-level title, and the second number of words is greater than the first number of words;

[0115] Step B3: When the number of words in the first draft of the paper is greater than the second number of words, the first draft of the paper includes a first-level title, a second-level title and a third-level title, and a third paragraph generation strategy is executed. The third paragraph generation strategy randomly calls the large language model basic unit multiple times in each second-level title or each third-level title to generate multiple paragraphs of content corresponding to each second-level title or each third-level title.

[0116] In the embodiment of the present application, in order to ensure that the contents of different chapters and paragraphs of the first draft of the paper are more diverse, paragraph contents are generated based on a randomized paper paragraph generation strategy. Specifically, a paper whose word count of the first draft is less than the first word count (for example, the first word count is 10,000 words) usually includes multiple first-level headings. At this time, the first paragraph generation strategy is executed to obtain multiple paragraphs corresponding to each first-level heading, and finally the multiple paragraphs corresponding to each first-level heading are spliced ​​to obtain the first draft of the paper.

[0117] A paper whose word count is greater than or equal to the first word count (for example, the first word count is 10,000 words) and less than or equal to the second word count (for example, the second word count is 30,000 words) usually includes a first-level title, a second-level title, and a third-level title. At this time, the second paragraph generation strategy is executed to obtain multiple paragraphs corresponding to each second-level title or each third-level title. Finally, the multiple paragraphs corresponding to each second-level title or each third-level title are spliced ​​to obtain the first-level draft of the paper. In addition, in order to prevent content confusion between multiple levels of titles, when generating the content of each level of title, all the second-level titles and third-level titles contained in the first-level title are input into the basic unit of the large language model. Since multiple titles are loosely coupled individuals, this method can effectively avoid the duplication of the text content between the generated multiple levels of titles.

[0118] The number of words in the first draft of the paper is greater than the second word count (for example, the second word count is 30,000 words) and usually includes a first-level title, a second-level title, and a third-level title. At this time, the third paragraph generation strategy is executed to obtain multiple paragraphs corresponding to each second-level title or each third-level title. Finally, the multiple paragraphs corresponding to each second-level title or each third-level title are spliced ​​to obtain the first draft of the paper. Since the coupling between multiple titles is loose and the coupling between multiple paragraphs is tight, it is ensured that the paragraph content generated by multiple calls to the basic unit of the large language model is closely connected and there is no duplication. When each paragraph is generated, the content of the previous paragraph is also considered for generation.

[0119] In an alternative embodiment, referring to Figure 6 As shown, Figure 6 It is a flowchart of the steps of a paragraph generation method provided in an embodiment of the present application, in which the large language model basic unit is randomly called multiple times in each secondary title or each tertiary title to generate multiple paragraphs of content corresponding to each secondary title or each tertiary title, including steps C1 to C3:

[0120] Step C1: segment the content of each title to obtain the center of each paragraph, wherein the title includes a secondary title and a tertiary title;

[0121] Step C2: calling the large language model basic unit to generate the first paragraph content according to the center of the first paragraph;

[0122] Step C3: calling the large language model basic units in sequence, generating the next paragraph of content according to the previous paragraph of content and the center of the next paragraph, until all the paragraph contents under the current title are generated.

[0123] In the embodiment of the present application, the center of each paragraph is obtained by planning the content of each title in sections, so that different paragraphs are related and the content is not repeated. Afterwards, for the first paragraph of each title, the corresponding paragraph content is obtained directly based on the center of the first paragraph. For each subsequent paragraph of content, not only its own center should be considered, but also the corresponding paragraph content is generated based on the previous paragraph of content, so that the adjacent paragraph contents have a better connection relationship.

[0124] In this way, in the embodiment of the present application, based on the randomized paper paragraph generation strategy, the first draft of the paper obtained by parallel paper generation based on the English abstract, available knowledge base and experimental data can better meet the needs of users, and the paragraph content of the first draft of the paper is richer. It is not generated in a templated manner, thereby ensuring the scientific nature of the content of the first draft of the paper.

[0125] In an alternative embodiment, referring to Figure 7As shown, the large language model basic unit is encapsulated based on the reinforcement learning iterative tuning strategy according to the following steps: receiving the user input information, and retrieving relevant data according to the user input information; constructing prompt information according to the retrieved relevant data; calling the large language model according to the prompt information; and constructing a structured output result according to the large language model. In this way, by encapsulating the large language model into the large language model basic unit, when generating a paragraph, the paragraph content can be generated by directly calling the large language model basic unit.

[0126] In an optional embodiment, a method for adding references is also provided, referring to Figure 8 As shown, Figure 8 This is a flowchart of a method for adding references provided by the present application. The method for adding references includes the following steps D1 to D4:

[0127] Step D1: Screening papers according to the modified keywords to obtain screened papers;

[0128] Step D2: constructing a semantic matching library based on sentences of the contents or abstracts of the screened papers;

[0129] Step D3: performing a similarity comparison between the sentences in the first draft of the paper and the sentences in the semantic matching library to obtain a similarity comparison result;

[0130] Step D4: adding literature citations to the first draft of the paper according to the similarity comparison result, the similarity threshold and the dynamic citation probability.

[0131] In the embodiment of the present application, double screening modeling is performed based on the modified keywords and the dynamic threshold of the semantic similarity of sentences fed back by users, and a semantic matching library is established with sentences in the paper content or abstract as the unit. The greater the similarity comparison result between the sentences in the first draft of the paper and the sentences in the semantic matching library, the more similar the two are, so it can be considered to add the corresponding documents as references, and by setting a similarity threshold to compare with the similarity comparison result, the similarity comparison result can be used as the basis for whether to add the reference.

[0132] Furthermore, considering that the citations of the contents at different positions in the first draft are different, for example, a large number of references may need to be cited for the contents about the background technology in the first chapter, but in the last chapter, it may not be necessary to cite a large number of references about the conclusion of the paper, so the citations of the references at different positions in the paper are different; in addition, the citation of references is also related to the number of citations to the same document. Therefore, the embodiment of the present application proposes to use the dynamic citation probability as the basis for whether to add references. In this way, by introducing the similarity threshold and the dynamic citation probability, the addition of references in the first draft of the paper is comprehensively considered, so that the reference citations of the final first draft of the paper are more scientific, avoiding the problems of irregular citation format, serious inconsistency between the citation content and the article, rigid citation distribution, and inaccurate data citation.

[0133] Specifically, the dynamic citation probability is determined according to the product of the citation probabilities corresponding to the citation threshold constraint, the citation distribution constraint, the multiple citation constraint, and the repeated citation constraint, where:

[0134] Item E1: The reference threshold constraint. If the similarity comparison result is greater than the similarity threshold, the reference is made according to the full probability. If the similarity comparison result is not greater than the similarity threshold, the reference is made according to the first probability. The full probability reference represents that the reference probability is 100%;

[0135] Item E2: The citation distribution constraint is to cite the content of the first chapter according to the full probability, cite the content of the second chapter according to the second probability, not cite the content of the last chapter, and cite the content of other chapters according to the third probability, where the third probability is less than the second probability;

[0136] Item E3: The multiple citation constraint, when multiple citation documents are retrieved in each citation bracket, the citation documents in the citation bracket are sorted by similarity, and the first N documents with the highest similarity are cited according to the full probability, where N is an integer greater than 1;

[0137] Item E4: The repeated citation constraint, when the same document is cited multiple times in the same paragraph, is cited according to the fourth probability, and the number of citations of the same document in the same paragraph is recorded. The fourth probability decays exponentially according to the number of citations.

[0138] In the embodiment of the present application, for each cited reference, four citation probabilities corresponding to the constraints of items E1 to E4 of the reference are determined in turn, so that the dynamic citation probability is obtained according to the product of the four citation probabilities.

[0139] For the E1 multi-reference constraint, if the similarity comparison result is greater than the similarity threshold, the reference probability corresponding to the multi-reference constraint is 1; if the similarity comparison result is not greater than the similarity threshold, the reference probability corresponding to the multi-reference constraint is the first probability. The first probability is a value less than 1 and can be flexibly set according to actual conditions.

[0140] For the E2 citation distribution constraint, different citation probabilities are set according to the different positions of sentences in the paper. For the first chapter, since the first chapter is usually related to the technical background and usually cites a large number of literature for discussion, the citation probability is set to 1; for the second chapter, the citation probability is set to the second probability (where the second probability is a value less than 1 and can be flexibly set according to actual conditions); for the last chapter, since the last chapter is usually the conclusion of the paper, the citation probability is set to 0 (i.e. no citation); for other chapters, sparse citation search is performed according to the third probability, i.e. the citation probability is set to the third probability.

[0141] For the E3 multi-reference constraint, when a sentence is similar to multiple sentences in the semantic matching library, the sentence may need to cite multiple references. Set the maximum number of references (i.e. N), and use the first N with the greatest similarity as the references that need to be cited, that is, set the citation probability corresponding to the first N references to 1; and set the citation probability of other references to 0, that is, no citation is performed.

[0142] For the repeated citation constraint E4, if the same paragraph cites the same reference multiple times, the corresponding citation probability (i.e., the fourth probability) is determined based on the number of citations. For example, if it is the second citation, the value of the fourth probability is smaller than the value of the first citation.

[0143] In this way, the dynamic citation probability of each reference is determined according to multiple constraints, so as to determine whether to add the corresponding reference citation in the first draft of the paper according to the dynamic citation probability, thereby ensuring the rationality and scientificity of the reference citation in the first draft of the paper, which is more in line with the norms of scientific and technological papers, and further ensuring the authenticity and scientificity of the first draft of the paper. Therefore, this method provides an efficient and accurate auxiliary method for literature research, innovation discovery, experimental simulation, data analysis, and first draft writing in the scientific research process.

[0144] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0145] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the systems and methods according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0148] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0149] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0150] The above is a detailed introduction to a scientific research assistance system and method based on a large language model provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A scientific research assistance system based on a large language model, characterized in that: include: The metadata layer, including the corpus and tool library, is used to provide basic data for the basic computing layer and the paper generation layer; The basic computing layer is used to regularize and sort the basic data based on the pre-trained language model to obtain a usable knowledge base, where the usable knowledge base represents the callable knowledge meta-services and tool meta-services; The experiment simulation layer is used to construct and simulate the generation of experiment data based on the large language model according to the user input information and the available knowledge base to obtain the experiment data; A paper generation layer, for generating a first draft of the paper based on a large language model, according to the user input information, the basic data, the experimental data and the available knowledge base; In the process of generating the first draft of the paper, the basic computing layer, the experimental simulation layer and the paper generation layer iteratively feedback their respective output results according to the principle validity measurement index and the effect evaluation index, so as to fine-tune the model used by themselves according to the output results.

2. The scientific research auxiliary system based on a large language model according to claim 1, characterized in that: The available knowledge base includes: specialized knowledge graph construction, embedded representation of scientific data, literature material similarity retriever, callable tool retrieval coding, knowledge linking system, and logical chain preset by large model.

3. The scientific research auxiliary system based on a large language model according to claim 1, characterized in that: The experimental simulation layer includes: The investigative experiment module includes a target data acquisition module and a data visualization modeling module, which is used to generate basic experimental data; Theoretical experiment module, including inductive bias introduction module and basic theoretical reasoning module, is used to generate theoretical experimental data; The simulation experiment module includes virtual environment construction, meta-code module construction and code logic chain combination module, which are used to generate simulation experiment data.

4. The scientific research auxiliary system based on a large language model according to claim 1, characterized in that: The paper generation layer includes: A previous work analysis module, used for analyzing the basic data; The paper logic combing module is used to comb out the logical structure of the paper draft according to the user input; Thesis formula deduction module, used to derive the formula used in the first draft of the thesis; A paper illustration generation module, used to generate illustrations for the first draft of the paper; An experimental data regularization module, used for normalizing the experimental data; An experimental data analysis module, used for analyzing the experimental data; Reference regularization module, used to insert references in the first draft of the paper.

5. A scientific research assistance method based on a large language model, characterized in that: Applied to the scientific research assistance system based on the large language model described in any one of claims 1 to 4, the method comprising: Obtaining user input information, wherein the user input information at least includes a paper title and a paper field; The experimental simulation layer constructs and simulates experimental data generation according to the user input information and the available knowledge base provided by the basic computing layer to obtain experimental data; The paper generation layer constructs a hierarchical index vector database according to the basic data provided by the metadata layer, and generates a first draft of the paper according to the user input information, the hierarchical index vector database, the available knowledge base and the experimental data.

6. The scientific research assistance method based on a large language model according to claim 5, characterized in that: The paper generation layer constructs a hierarchical index vector database based on the basic data provided by the metadata layer, and generates a first draft of the paper based on the user input information, the hierarchical index vector database, the available knowledge base and the experimental data, including: Constructing a specialized document library according to the user input information and the hierarchical index vector database; Generate a paper abstract and keywords based on the specialized document library, and generate a paper outline based on the paper abstract and the keywords; Sending the paper abstract, the keywords and the paper outline to the user, so that the user can modify the paper abstract, the keywords and the paper outline to obtain a modified paper abstract, modified keywords and a modified paper outline; Creating an online reference library based on the modified paper abstract, the modified keywords and the modified paper outline; Generate English abstracts based on the online reference library; Based on a randomized paper paragraph generation strategy, parallel paper generation is performed according to the English abstract, the available knowledge base and the experimental data to obtain a first draft of the paper.

7. The scientific research assistance method based on a large language model according to claim 6, characterized in that: Generate a paper outline according to the paper abstract and the keywords, including: According to the paper abstract and the keywords, randomly retrieve multiple learning documents from the specialized document library; Sorting out the paper logic of the plurality of learning documents to obtain a plurality of initial paper outlines; Imitation learning is performed according to the multiple initial paper outlines and domain-based reference materials to obtain a paper outline, wherein the domain-based reference materials are references provided by the user.

8. The scientific research assistance method based on a large language model according to claim 6, characterized in that: The randomized essay paragraph generation strategy includes: When the word count of the first draft of the paper is less than the first word count, the first draft of the paper includes a first-level title, and a first paragraph generation strategy is executed, wherein the first paragraph generation strategy calls a large language model basic unit once for each first-level title to generate multiple paragraphs corresponding to each first-level title; When the number of words in the first draft of the paper is greater than or equal to the first number of words and less than or equal to the second number of words, the first draft of the paper includes a first-level title, a second-level title, and a third-level title, and a second paragraph generation strategy is executed, wherein the second paragraph generation strategy calls the large language model basic unit once for each second-level title or each third-level title to generate multiple paragraphs corresponding to each second-level title or each third-level title, and the second number of words is greater than the first number of words; In the case that the number of words in the first draft of the paper is greater than the second number of words, the first draft of the paper includes a first-level title, a second-level title and a third-level title, and a third paragraph generation strategy is executed. The third paragraph generation strategy randomly calls the large language model basic unit multiple times in each second-level title or each third-level title to generate multiple paragraphs of content corresponding to each second-level title or each third-level title.

9. The scientific research assistance method based on a large language model according to claim 8, characterized in that: The large language model basic unit is randomly called multiple times in each secondary title or each tertiary title to generate multiple paragraphs of content corresponding to each secondary title or each tertiary title, including: The content of each title is segmented and planned to obtain the center of each paragraph, wherein the title includes a secondary title and a tertiary title; Calling the large language model basic unit to generate the first paragraph content according to the center of the first paragraph; The large language model basic units are called in sequence to generate the next paragraph of content according to the previous paragraph of content and the center of the next paragraph, until all the paragraph contents under the current title are generated.

10. The scientific research assistance method based on a large language model according to claim 8, characterized in that: The basic unit of the large language model is encapsulated based on the reinforcement learning iterative tuning strategy according to the following steps: Receiving the user input information, and retrieving relevant data according to the user input information; Constructing prompt information according to the retrieved relevant data; Calling a large language model according to the prompt information; Based on the large language model, a structured output result is constructed.

11. The scientific research assistance method based on a large language model according to claim 10, characterized in that: The method further comprises: Screening papers according to the modified keywords to obtain screened papers; A semantic matching library is constructed based on sentences of the contents or abstracts of the screened papers; Comparing the sentences in the first draft of the paper with the sentences in the semantic matching library to obtain a similarity comparison result; According to the similarity comparison result, the similarity threshold and the dynamic citation probability, literature citations are added to the first draft of the paper.

12. The scientific research assistance method based on a large language model according to claim 11, characterized in that: The dynamic citation probability is determined by multiplying the citation probabilities corresponding to the citation threshold constraint, the citation distribution constraint, the multiple citation constraint, and the repeated citation constraint, wherein: The reference threshold constraint is that when the similarity comparison result is greater than the similarity threshold, the reference is made according to the full probability, and when the similarity comparison result is not greater than the similarity threshold, the reference is made according to the first probability, and the full probability reference represents that the reference probability is 100%; The citation distribution constraint is to cite the content of the first chapter according to the full probability, cite the content of the second chapter according to the second probability, not cite the content of the last chapter, and cite the content of other chapters according to the third probability, wherein the third probability is less than the second probability; The multiple citation constraint, when multiple citation documents are retrieved in each citation bracket, the citation documents in the citation bracket are sorted by similarity, and the first N documents with the highest similarity are cited according to full probability, where N is an integer greater than 1; The repeated citation constraint is that when the same document is cited multiple times in the same paragraph, it is cited according to the fourth probability and the number of citations of the same document in the same paragraph is recorded. The fourth probability decays exponentially according to the number of citations.

Citation Information

Patent Citations

  • Scientific Research Knowledge Management Method and System

    CN109241278A

  • AI intelligent paper generation method

    CN110598197A

  • Meta analysis generation method based on artificial intelligence

    CN111552776A

  • System for college physics experiment teaching

    CN112614033A

  • Method and system for automatically generating fine-grained labeled document format analysis data set

    CN117634447A

Cited By

  • Scientific research assisting method and device based on generative model and computer equipment

    CN119204199A

  • Medical literature intelligent processing and analysis system, method and terminal based on large model

    CN119807435A

  • Academic viewpoint labeling and analyzing method and system

    CN120068800A

  • A method and system for marking and analyzing academic opinions

    CN120068800B

  • Automatic scientific research method and system

    CN120068803A