Academic institution-oriented paper review auxiliary method and system

By using the large language model BERT and natural language processing technology, combined with the paper review database, the problems of traditional manual review time and subjective factors are solved, efficient and accurate paper review is achieved, and review efficiency and objectivity are improved.

CN119088829AInactive Publication Date: 2024-12-06HUACHEN ZHIYU (BEIJING) TECHNOLOGY CO LTD

Patent Information

Application Number
CN202411133407.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional paper review relies on manual review, which takes time and is susceptible to subjective factors. It is impossible to quickly and effectively process a large number of submissions within the specified time, which affects the timely release of papers and the dissemination of scientific research results.

Method used

The large language model BERT is used for paper review, combined with the paper review database and natural language processing technology, an evaluation report is generated, and the data is displayed in real time through a visual interface to improve the review efficiency and accuracy.

Benefits of technology

It improves the accuracy and scientificity of paper review, reduces the influence of subjective factors, improves the review efficiency and data analysis efficiency, and ensures the objectivity and transparency of the review.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088829A_ABST
    Figure CN119088829A_ABST
Patent Text Reader

Abstract

The invention discloses an academic institution-oriented paper review auxiliary method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting paper review data, and carrying out the preprocessing of the collected paper review data; establishing a paper review database and optimizing the paper review database; performing model training based on a big language model BERT, and performing paper review; generating a paper review report based on the paper review result and review database data; and constructing a visual interface, and displaying paper review data in real time. According to the method, the paper review database is constructed, the paper review data is used for large language model training, the large language model is used for outputting the paper review guide prompt, and a reviewer is assisted in paper review, so that the knowledge depth of paper review content and the accuracy and scientificity of paper review are improved; and moreover, the objectivity of paper review is prevented from being influenced by subjective factors of a manuscript reviewer, and the efficiency of paper review is improved.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a paper review auxiliary method and system for academic institutions. Background Art

[0002] With the increasing frequency of global academic exchanges and the rapid accumulation of scientific research results, the number of academic papers has shown explosive growth, especially in the fields of science, technology, engineering and mathematics (STEM). New research results continue to emerge, driving the academic community's demand for efficient and accurate paper review mechanisms.

[0003] However, the traditional paper review process relies on manual review, where reviewers evaluate papers based on their own professional knowledge and experience. Although this method ensures the quality of academic review to a certain extent, it also has obvious limitations. First, manual review is time-consuming and easily affected by reviewers' subjective factors, such as aesthetic fatigue, personal bias, and knowledge blind spots. In addition, faced with the increasing number of submissions, reviewers have limited energy and may not be able to complete high-quality reviews within the specified time, affecting the timely publication of papers and the dissemination of scientific research results. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing paper review auxiliary methods and systems for academic institutions, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that manual review of papers is time-consuming and easily affected by subjective factors of reviewers, and there are too many papers to review them quickly and effectively within the specified time.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a paper review auxiliary method for academic institutions, which includes collecting paper review data and preprocessing the collected paper review data; establishing a paper review database and optimizing the paper review database; training a model based on the large language model BERT to conduct paper review; generating a paper review report based on the paper review results and the review database data; and constructing a visual interface to display the paper review data in real time.

[0007] As a preferred solution of the paper review auxiliary method for academic institutions of the present invention, the collection of paper review data includes:

[0008] Select Web of Science and PubMed academic databases, obtain API access rights and keys, and configure access parameters including query keywords, date range, and return fields;

[0009] Use Python to connect to the Web of Science and PubMed academic databases through HTTP requests, call APIs, collect academic papers and review data corresponding to academic papers, and generate paper review data sets, which include paper text data and paper review data.

[0010] As a preferred solution of the paper review auxiliary method for academic institutions described in the present invention, the preprocessing of the collected paper review data includes:

[0011] Based on the paper review data set, perform data cleaning, data standardization and paper text data processing;

[0012] The data cleaning refers to identifying and deleting duplicate data and correcting erroneous data using predefined rules;

[0013] The data standardization refers to normalization of numerical data;

[0014] The text processing refers to using natural language processing technology NLP to perform word segmentation and part-of-speech tagging on text data.

[0015] As a preferred solution of the paper review auxiliary method for academic institutions described in the present invention, the establishment of a paper review database and optimization of the paper review database include:

[0016] Construct a paper review database based on the relational database MySQL framework, including paper tables, review tables, vocabulary tables, and inverted index tables;

[0017] Use inverted index technology to search data, assign a unique identifier ID to each word based on the text data after word segmentation;

[0018] Generate a vocabulary based on the word segmentation results, record the position of each word in the document, and generate an inverted index for each word based on the vocabulary;

[0019] Set the review database update frequency, regularly collect newly published papers and review data according to the set review database update frequency, and update them incrementally to the review database.

[0020] As a preferred solution of the paper review auxiliary method for academic institutions described in the present invention, wherein: the model training based on the large language model BERT and the paper review include:

[0021] Collect historical paper review data and preprocess them to generate a historical paper review dataset;

[0022] Based on the large language model BERT, the historical paper review data is input into the large language model BERT as training data, and the Adam optimizer is used to update the parameters;

[0023] The pre-processed paper text data collected in real time is input into the trained large language model BERT, the paper review database is retrieved and the paper review results are obtained, including scores of different dimensions of the paper, paper evaluation prompts and comprehensive scores of the paper.

[0024] As a preferred solution of the paper review auxiliary method for academic institutions of the present invention, wherein: the paper review report generated based on the paper review results and the review database data includes:

[0025] Use RAG technology to retrieve paper review data from the paper review database, including the latest research results in the field of paper-related research, core references, historical review data and academic data in the field of paper-related research;

[0026] Integrate the paper review data retrieved from the paper review database with the paper evaluation guidance prompts output by the large language model to generate a paper review report;

[0027] Send paper review reports to clients and reviewers, and collect feedback from clients and reviewers.

[0028] As a preferred solution of the paper review auxiliary method for academic institutions of the present invention, the construction of a visual interface to display paper review data in real time includes:

[0029] Use Figma and Adobe XD design tools to create prototypes of visual interfaces and define how users interact with the visual interfaces, including clicking, dragging, and zooming;

[0030] Choose React.js and Three.js front-end frameworks to build interactive interfaces, choose D3.js to draw flowcharts, progress bars, and data flow diagrams, and use Python back-end technology to process data requests and responses;

[0031] Use the visualization interface backend API interface to obtain paper review data and transmit the obtained paper review data to the front-end interactive interface for visual display.

[0032] Another object of the present invention is to provide a paper review auxiliary system for academic institutions, which comprises:

[0033] Data collection module, used to collect and preprocess paper review data to generate paper review data set;

[0034] A database establishment module is used to establish a paper review database and store paper review data;

[0035] Data analysis module, used to train the large language model BERT and obtain paper review results;

[0036] The review report generation module is used to generate a paper review report by combining the paper review results and the review database retrieval data;

[0037] The visualization module is used to build a visualization interface for paper review visualization.

[0038] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a paper review auxiliary method for academic institutions when executing the computer program.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a paper review assistance method for academic institutions.

[0040] The beneficial effects of the present invention are as follows: the present invention constructs a paper review database, uses the paper review data to train a large language model, and uses the large language model to output paper evaluation guidance prompts to assist reviewers in paper review, thereby improving the knowledge depth of paper review content and the accuracy and scientificity of paper review, avoiding the influence of reviewers' subjective factors on the objectivity of paper review, and improving the efficiency of paper review. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 The figure is a flowchart of the paper review assistance method for academic institutions.

[0043] Figure 2 Schematic diagram of the paper review process.

[0044] Figure 3 This is a schematic diagram of the structure of the paper review assistance system for academic institutions. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] Example 1

[0049] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides a paper review assistance method for academic institutions. The paper review assistance method for academic institutions includes:

[0050] S1. Collect paper review data and pre-process the collected paper review data;

[0051] Furthermore, the collection of paper review data includes:

[0052] Select Web of Science and PubMed academic databases, obtain API access rights and keys, and configure access parameters including query keywords, date range, and return fields;

[0053] Use Python to connect to the Web of Science and PubMed academic databases through HTTP requests, call APIs, collect academic papers and review data corresponding to academic papers, and generate paper review data sets, which include paper text data and paper review data.

[0054] By collecting paper review data from multiple sources, we achieve richness of paper review data and effectively avoid the problems of data bias and single perspective. This process enables the system to cover a wider range of academic fields and review standards, thereby improving the universality and generalization of the review model. By integrating review data from different fields and under different review standards, we provide the model with more comprehensive training samples, so that the review results can adapt to a variety of academic scenarios. Through a systematic data collection process, we can improve the efficiency and accuracy of data collection, avoid omissions or errors that may occur in manual data collection, and ensure that the model can obtain the latest paper review data at any time, thereby improving the dynamic response capability of the system.

[0055] Furthermore, the collected paper review data is preprocessed including:

[0056] Based on the paper review data set, perform data cleaning, data standardization and paper text data processing;

[0057] The data cleaning refers to identifying and deleting duplicate data and correcting erroneous data using predefined rules;

[0058] The data standardization refers to normalization of numerical data;

[0059] The text processing refers to using natural language processing technology NLP to perform word segmentation and part-of-speech tagging on text data.

[0060] By preprocessing the collected paper review data, we can identify and delete duplicate data, thereby streamlining and eliminating redundancy in the paper review data set, ensuring that model bias will not be caused by duplicate samples during subsequent data analysis and model training. By using natural language technology to segment and tag text data, continuous text can be split into independent vocabulary units, making the structure of the text clearer, providing basic vocabulary-level features for subsequent text analysis and model input, enabling the model to better understand and process text content, thereby improving the accuracy and in-depth analysis capabilities of paper reviews.

[0061] S2. Establish a paper review database and optimize it;

[0062] Furthermore, establishing a paper review database and optimizing the paper review database include:

[0063] Construct a paper review database based on the relational database MySQL framework, including paper tables, review tables, vocabulary tables, and inverted index tables;

[0064] Use inverted index technology to search data, assign a unique identifier ID to each word based on the text data after word segmentation;

[0065] Generate a vocabulary based on the word segmentation results, record the position of each word in the document, and generate an inverted index for each word based on the vocabulary;

[0066] Set the review database update frequency, collect newly published papers and review data regularly according to the set review database update frequency, and update them incrementally to the review database;

[0067] By using the MySQL framework to build a paper review database, a structured, efficient and easy-to-manage data storage system is implemented. MySQL has good scalability and stability, is suitable for storing and processing large-scale academic papers and review data, can support complex query operations and provide good data consistency. In addition, through the inverted index technology for data search, efficient retrieval of text data is achieved, and documents containing specific vocabulary can be quickly located, which greatly improves the query speed and search efficiency of text data. By setting a regular update mechanism for the review database, the timeliness and accuracy of the review data are guaranteed, which can promptly reflect the latest academic research results and review dynamics, ensuring that the data obtained by users is always the latest and relevant, enhancing the real-time and practicality of the system.

[0068] S3. Conduct model training based on the large language model BERT and conduct paper review;

[0069] Furthermore, model training based on the large language model BERT was conducted, and paper review included:

[0070] Collect historical paper review data and preprocess them to generate a historical paper review dataset;

[0071] Based on the large language model BERT, the historical paper review data is input into the large language model BERT as training data, and the Adam optimizer is used to update the parameters;

[0072] Input the pre-processed paper text data collected in real time into the trained large language model BERT, search the paper review database and obtain the paper review results, including the scores of different dimensions of the paper, paper evaluation prompts and the comprehensive score of the paper. The scores of different dimensions of the paper include the score of paper innovation, the score of paper academic value and the score of paper compliance;

[0073] Use the large language model BERT to guide reviewers in paper review and give reviewers average guidance tips for paper review, including:

[0074] 1. Is the topic of the paper cutting-edge and open?

[0075] 2. What is the innovation and value of the paper?

[0076] 3. Basic knowledge and scientific research ability?

[0077] 4. Is the paper standardized?

[0078] The large language model BERT answers questions based on relevant field data in the review database, conducts paper reviews, and provides evaluation prompts and suggestions for each part of the paper.

[0079] By collecting historical paper review data and preprocessing it, a historical paper review data set is generated, and the historical review data is input into the large language model BERT for training. The BERT model can learn complex language patterns and semantic associations from massive data, and improve the model's ability to understand and analyze paper texts. The role of this process is that through the deep learning ability of the large language model BERT, the model can more accurately capture the subtle differences in academic language, so as to make more accurate judgments in the review. By using the trained large language model BERT to analyze papers, retrieve paper review databases, and provide paper evaluation prompts to help reviewers conduct paper reviews, it not only improves the review efficiency, but also provides a more comprehensive paper evaluation through a multi-dimensional evaluation method, so that reviewers can more accurately understand the advantages and disadvantages of the paper, so as to make more scientific and reasonable decisions. In addition, this real-time and intelligent evaluation system can also improve the transparency and fairness of the review work, and provide academic institutions and researchers with a more objective and fair review basis.

[0080] S4. Generate a paper review report based on the paper review results and review database data;

[0081] Furthermore, the paper review report generated based on the paper review results and the review database data includes:

[0082] Use RAG technology to retrieve paper review data from the paper review database, including the latest research results in the field of paper-related research, core references, historical review data and academic data in the field of paper-related research;

[0083] Integrate the paper review data retrieved from the paper review database with the paper evaluation guidance prompts output by the large language model to generate a paper review report;

[0084] Send paper review reports to clients and reviewers, and collect feedback from clients and reviewers.

[0085] By using RAG technology to retrieve paper review data, sufficient and authoritative background information can be provided for the subsequent generation of paper review reports, so that the paper review report is not limited to the output results of the large language model BERT, but also includes the latest research trends and historical data in the field related to the paper, which helps reviewers to more comprehensively understand and evaluate the innovation and contribution of the paper, realizes the integration of multi-source data, effectively improves the comprehensiveness and pertinence of the review report, and makes the paper review report more convincing and valuable for reference. In addition, by collecting feedback information from reviewers and customers, the deficiencies of the paper review report can be identified, and continuous improvements can be made accordingly, thereby improving the adaptability of the system and the accuracy of the review report.

[0086] S5. Build a visual interface to display paper review data in real time;

[0087] Furthermore, a visual interface is constructed to display the paper review data in real time, including:

[0088] Use Figma and Adobe XD design tools to create prototypes of visual interfaces and define how users interact with the visual interfaces, including clicking, dragging, and zooming;

[0089] Choose React.js and Three.js front-end frameworks to build interactive interfaces, choose D3.js to draw flowcharts, progress bars, and data flow diagrams, and use Python back-end technology to process data requests and responses;

[0090] Use the visualization interface backend API interface to obtain paper review data and transmit the obtained paper review data to the front-end interactive interface for visual display.

[0091] By using Figma and Adobe XD design tools to create prototypes and define how users interact with the visual interface, we ensure that users have a smooth experience when using the visual interface, making complex review processes and review data easier to understand and operate, thereby improving the efficiency of data analysis and the accuracy of decision-making. This provides academic institutions with a powerful and intuitive data analysis tool, and customers can understand the paper review process through the visual interface, thereby enhancing their trust in academic institutions and reviewers.

[0092] Example 2

[0093] Reference Figure 3 , which is the second embodiment of the present invention. This embodiment is different from the previous embodiment and provides a paper review auxiliary system for academic institutions, including:

[0094] Data collection module, used to collect and preprocess paper review data to generate paper review data set;

[0095] A database establishment module is used to establish a paper review database and store paper review data;

[0096] Data analysis module, used to train the large language model BERT and obtain paper review results;

[0097] The review report generation module is used to generate a paper review report by combining the paper review results and the review database retrieval data;

[0098] The visualization module is used to build a visualization interface for paper review visualization.

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0101] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A paper review assistance method for academic institutions, Features: include, Collect paper review data and pre-process the collected paper review data; Establish a paper review database and optimize it; Conduct model training based on the large language model BERT and conduct paper review; Generate a paper review report based on the paper review results and review database data; Build a visual interface to display paper review data in real time.

2. The paper review auxiliary method for academic institutions as claimed in claim 1, Features: The collected paper review data includes: Select Web of Science and PubMed academic databases, obtain API access rights and keys, and configure access parameters including query keywords, date range, and return fields; Use Python to connect to the Web of Science and PubMed academic databases through HTTP requests, call APIs, collect academic papers and review data corresponding to academic papers, and generate paper review data sets, which include paper text data and paper review data.

3. The paper review auxiliary method for academic institutions as claimed in claim 2, Features: The preprocessing of the collected paper review data includes: Based on the paper review data set, perform data cleaning, data standardization and paper text data processing; The data cleaning refers to identifying and deleting duplicate data and correcting erroneous data using predefined rules; The data standardization refers to normalization of numerical data; The text processing refers to using natural language processing technology NLP to perform word segmentation and part-of-speech tagging on text data.

4. The paper review auxiliary method for academic institutions as claimed in claim 3, Features: The said establishing and optimizing the paper review database includes: Construct a paper review database based on the relational database MySQL framework, including paper tables, review tables, vocabulary tables, and inverted index tables; Use inverted index technology to search data, assign a unique identifier ID to each word based on the text data after word segmentation; Generate a vocabulary based on the word segmentation results, record the position of each word in the document, and generate an inverted index for each word based on the vocabulary; Set the review database update frequency, regularly collect newly published papers and review data according to the set review database update frequency, and update them incrementally to the review database.

5. The paper review auxiliary method for academic institutions as claimed in claim 4, Features: The model training based on the large language model BERT and the paper review include: Collect historical paper review data and preprocess them to generate a historical paper review dataset; Based on the large language model BERT, the historical paper review data is input into the large language model BERT as training data, and the Adam optimizer is used to update the parameters; The pre-processed paper text data collected in real time is input into the trained large language model BERT, the paper review database is retrieved and the paper review results are obtained, including scores of different dimensions of the paper, paper evaluation prompts and comprehensive scores of the paper.

6. The paper review auxiliary method for academic institutions as claimed in claim 5, Features: The generating of the paper review report based on the paper review results and the review database data includes: Use RAG technology to retrieve paper review data from the paper review database, including the latest research results in the field of paper-related research, core references, historical review data and academic data in the field of paper-related research; Integrate the paper review data retrieved from the paper review database with the paper evaluation guidance prompts output by the large language model to generate a paper review report; Send paper review reports to clients and reviewers, and collect feedback from clients and reviewers.

7. The paper review auxiliary method for academic institutions as claimed in claim 6, Features: The construction of a visual interface to display paper review data in real time includes: Use Figma and Adobe XD design tools to create prototypes of visual interfaces and define how users interact with the visual interfaces, including clicking, dragging, and zooming; Choose React.js and Three.js front-end frameworks to build interactive interfaces, choose D3.js to draw flowcharts, progress bars, and data flow diagrams, and use Python back-end technology to process data requests and responses; Use the visualization interface backend API interface to obtain paper review data and transmit the obtained paper review data to the front-end interactive interface for visual display.

8. A paper review assistance system for academic institutions based on the paper review assistance method for academic institutions as described in any one of claims 1 to 7, Features: include, Data collection module, used to collect and preprocess paper review data to generate paper review data set; A database establishment module is used to establish a paper review database and store paper review data; Data analysis module, used to train the large language model BERT and obtain paper review results; The review report generation module is used to generate a paper review report by combining the paper review results and the review database retrieval data; The visualization module is used to build a visualization interface for paper review visualization.

9. A computer device, include: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the paper review assistance method for academic institutions described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the steps of the paper review assistance method for academic institutions described in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Method and device for providing query suggestions, electronic equipment and storage medium

    CN113239258A

  • Text quality evaluation system and method

    CN113743085A

  • Data name recommendation and auditing auxiliary system of large language model

    CN117151043A

  • Medical AI assistant implementation method and system based on data driving and large model

    CN118098585A

  • Large language model system for clinical test data analysis and interpretation

    CN118116536A

Cited By

  • Method and system for constructing manuscript review agent embedded in gradient evaluation system

    CN120597933A

  • Medical review and publishing quality control system based on deep learning and medical knowledge

    CN121391142A

  • Multi-agent-driven paper intelligent reviewing method and system

    CN121961793A

  • A Multi-Agent Driven Intelligent Paper Review Method and System

    CN121961793B