System and method for automatically generating review based on artificial intelligence

Abstract

The invention relates to the field of data classification, and discloses an automatic review generation system and method based on artificial intelligence, and the system comprises a retrieval type construction module, a literature screening module, a scale evaluation module, a data extraction and information summarization module, an output and application module, and a system maintenance and update module. Wherein the retrieval formula construction module is used for receiving keywords and retrieval conditions input by a user, generating a retrieval formula and retrieving related literatures according to the retrieval formula; the literature screening module is used for carrying out quality evaluation and screening on the retrieved literatures; the scale evaluation module is used for reading and extracting key data in the screened literature and carrying out scale evaluation; the data extraction and information summarization module is used for summarizing the extracted information and generating a report; the output and application module outputs the generated report; and the system maintenance and updating module is used for carrying out system maintenance and updating. According to the method, the AI automatic construction retrieval formula is realized, the standard is proposed, and the retrieval efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of data classification, and in particular to a system and method for automatically generating a review based on artificial intelligence. Background Art

[0002] There are strong barriers between disciplines, and medical students are unfamiliar with or do not understand the professional knowledge of other branches; there is a large number of literatures with great differences in quality, and how to quickly extract and scientifically analyze high-quality information and data has become a puzzle in scientific research; scientific research lags behind clinical needs, and there is also a low conversion rate of scientific research into clinical applications.

[0003] Teaching - Difficulty in student training: The number of medical literature has increased dramatically. According to PubMed statistics, the number of new medical literature is about 40,000 per year in the past year. It is difficult for students to read and organize the literature and integrate knowledge! Scientific research - high difficulty, large volume, high error rate, and long time consumption: traditional splicing of subject terms, free words, and manual truncation of words are time-consuming and have high error rates when searching for literature; a large number of articles are retrieved during literature screening, and manual screening to eliminate redundancy has high error rates; the background methods and conclusions of a large number of documents are read in detail during scale evaluation, and the accuracy of summarization is poor; multiple types of data are used when designing conclusions / data summaries, which is difficult, large in volume, and lacks scientificity.

[0004] Clinical - The conversion of scientific research results lags behind, and precision medicine has a long way to go: There is a lag in the conversion of scientific research results and clinical applications, the diagnosis and treatment plans are updated slowly, it is difficult to be personalized and advanced, scientific research results are difficult to apply to precision medicine, and patient benefits are low. In 2019, the National Institutes of Health invested more than US$100 million in the field of precision medicine, but the conversion rate was only 10%.

[0005] Although there are document management software such as Endnote and Noteexpress, they can only manage documents but are still helpless in classifying and identifying document contents.

[0006] Although people have proposed literature reviews and used them to allow other scholars to quickly understand the latest progress in a certain field, and review generation software has emerged, this is obviously an inefficient method given the ever-changing scope of literature that needs to be summarized and the huge workload.

[0007] Although project collaboration software supports document collaboration and exchange and circulation within the team, and improves efficiency to a certain extent, the degree of improvement is still closely related to manual labor.

[0008] Therefore, there is an urgent need for a product with strong content aggregation capabilities, accurate and comprehensive data extraction, analysis and summary capabilities, which can improve research efficiency and the accuracy of scientific decision-making. Summary of the invention

[0009] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a system for automatically generating a review based on artificial intelligence, comprising: a search formula construction module, a document screening module, a scale evaluation module, a data extraction and information summary module, an output and application module, and a system maintenance and update module; the search formula construction module, the document screening module, the scale evaluation module, the data extraction and information summary module, the output and application module, and the system maintenance and update module are connected in sequence; The search formula building module is used to receive keywords and search conditions input by the user, generate a search formula, and search for relevant documents according to the search formula; The literature screening module is used to evaluate and screen the quality of retrieved literature; The scale evaluation module is used to read and extract key data from the screened literature and conduct scale evaluation; The data extraction and information aggregation module is used to aggregate the extracted information and generate reports; Output and apply module output to generate reports; The system maintenance and update module is used to perform system maintenance and updates based on user feedback and system evaluation results.

[0010] Preferably, the search formula building module is used to receive keywords and search conditions input by a user, generate a search formula, and search for relevant documents according to the search formula, including: The search formula construction module receives keywords and search conditions input by the user, automatically generates a search formula through the MeSH interface of PubMed and the natural language processing model, and searches for corresponding documents in the medical database according to the search formula; The search formula building module includes an optimization unit, which is used to dynamically adjust the natural language processing model parameters according to the user's historical search records and feedback.

[0011] Preferably, the document screening module is used to perform quality assessment and screening on the retrieved documents, including: Through the knowledge base and vector database of Langchain-ChatChat, combined with the fine-tuning of OCR and deep learning models, the retrieved documents are quality evaluated and screened to select the corresponding medical literature.

[0012] Preferably, the scale evaluation module is used to read and extract key data from the screened literature and perform scale evaluation, including: Through table OCR and semantic recognition, based on chatpdf and chatdoc interfaces, read and extract key data from the screened literature; the key data include literature title, abstract, publication time, author, literature research method, research sample size, research population characteristics, research method corresponding dependent variable indicator information, and effect size of research results; The scale evaluation module includes a verification unit for cross-validating the extracted key data.

[0013] Preferably, the data extraction and information aggregation module is used to aggregate the extracted information and generate a report, including: The effect sizes of each research result are extracted, and the groups and specific scopes of application of the effect sizes of the research results are summarized. The summarized information is formatted through regular expressions, and an automated report with charts and multi-style themes is generated through Python's Matplotlib and Python-docx. The data extraction and information aggregation module includes a custom report generation unit, which is used to generate corresponding reports according to the report style, chart type and content layout selected by the user.

[0014] Preferably, the system maintenance and update module further comprises a collaboration platform for multi-user online collaborative editing, annotation and sharing of reports.

[0015] A method for automatically generating a review based on artificial intelligence, using a system for automatically generating a review based on artificial intelligence, comprises the following steps: S1, search formula construction, through the MeSH interface of PubMed and the language output multi-task design mode of the NLP model, AI automatically constructs the search formula and formulates the inclusion and exclusion criteria; S2, literature screening, artificially made data set screening software is fine-tuned on the 7BBaichuan language model to filter literature types by abstract; S3, scale evaluation, using Langchain.Chatchat’s knowledge base and vector database technology, OCR technology, and deep learning to fine-tune the large language model for literature screening; S4, data extraction, using table OCR technology and language recognition technology on the basis of chatpdf and chatdoc interfaces, to condense and extract data from the selected articles; S5, information summary, summarizes the extracted literature data information, uses regular formatting to apply Python's Matplotlib and Python-docxE operation technology, and outputs charts and multi-style theme automated PDF reports.

[0016] The beneficial effects of the present invention are: through the MeSH interface of PubMed and the language output multi-task design mode of the NLP model, AI is used to automatically construct search formulas, formulate inclusion and exclusion criteria, and improve search efficiency and accuracy.

[0017] Improve the efficiency of document screening: Through Langchain-ChatChat's knowledge base and vector database technology, OCR technology, and deep learning, fine-tune the large language model to achieve screening functions and improve the efficiency and accuracy of document screening.

[0018] Improve data extraction efficiency: Through table OCR technology and semantic recognition technology, based on the chatpdf and chatdoc interfaces, AI can read the selected articles and perform data concentration and extraction, thereby improving data extraction efficiency and accuracy.

[0019] Improve report generation efficiency: Through Python's Matplotlib and Python-docx interoperability technology, output charts and automated PDF reports with multiple styles and themes to improve report generation efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the principle of a system for automatically generating reviews based on artificial intelligence; Figure 2 Schematic diagram of the implementation of a system for automatically generating reviews based on artificial intelligence. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0022] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0023] like Figure 1 As shown, a system for automatically generating reviews based on artificial intelligence includes: a search formula construction module, a literature screening module, a scale evaluation module, a data extraction and information summary module, an output and application module, and a system maintenance and update module; The search formula building module is used to receive keywords and search conditions input by the user, generate a search formula, and search for relevant documents according to the search formula; The literature screening module is used to evaluate and screen the quality of retrieved literature; The scale evaluation module is used to read and extract key data from the screened literature and conduct scale evaluation; The data extraction and information aggregation module is used to aggregate the extracted information and generate reports; Output and apply module output to generate reports; The system maintenance and update module is used to perform system maintenance and updates based on user feedback and system evaluation results.

[0024] The search formula building module is used to receive keywords and search conditions input by the user, generate a search formula, and search for relevant documents according to the search formula, including: The search formula construction module receives keywords and search conditions input by the user, automatically generates a search formula through the MeSH interface of PubMed and the natural language processing model, and searches for corresponding documents in the medical database according to the search formula; The search formula construction module includes an optimization unit, which is used to dynamically adjust the parameters of the natural language processing model according to the user's historical search records and feedback. For example, if the search command officially issued by the user in the history contains more free words, the temperature value of the basic model will be increased, otherwise it will be automatically lowered. If the user feedbacks that there are too many free words, the temperature value of the basic model will be automatically lowered, otherwise it will be automatically raised.

[0025] The document screening module is used to evaluate and screen the quality of the retrieved documents, including: Through the knowledge base and vector database of Langchain-ChatChat, combined with the fine-tuning of OCR and deep learning models, the retrieved literature is quality evaluated and screened to select the corresponding medical literature. This includes first excluding online literature under given standards, including these inclusion and exclusion data, and giving the corresponding inclusion criteria and articles to the model for fine-tuning. In the actual environment, the paper is identified by OCR for tables and text information, and this information is given to the fine-tuned model to determine whether it is included or excluded under given standards. The quality assessment is fed back through prompt preset NOS and other scales to give feedback on the score considered by each model and output in JSON format.

[0026] The scale evaluation module is used to read and extract key data from the screened literature and perform scale evaluation, including: Through table OCR and semantic recognition, based on chatpdf and chatdoc interfaces, key data in the screened literature can be automatically read and extracted for scale evaluation; The scale evaluation module includes a verification unit, which is used to cross-validate the extracted key data. This includes: using fine-tuning models based on multiple different benchmark models trained in clinical, basic research, and bioinformatics research to conduct simultaneous scale evaluation, and adopting a majority priority system to obtain results recognized by more models.

[0027] The data extraction and information summary module is used to summarize the extracted information and generate a report, including: Summarize the extracted information, format it using regular expressions, and generate automated reports with charts and multi-style themes using Python's Matplotlib and Python-docx. The data extraction and information aggregation module includes a custom report generation unit, which is used to generate corresponding reports according to the report style, chart type and content layout selected by the user.

[0028] The system maintenance and update module also includes a collaboration platform, which is used for multi-user online collaborative editing, annotation and sharing of reports.

[0029] A method for automatically generating a review based on artificial intelligence, using a system for automatically generating a review based on artificial intelligence, comprises the following steps: S1, search formula construction, through the MeSH interface of PubMed and the language output multi-task design mode of the NLP model, AI automatically constructs the search formula and formulates the inclusion and exclusion criteria; S2, literature screening, artificially made data set screening software is fine-tuned on the 7BBaichuan language model to filter literature types by abstract; S3, scale evaluation, using Langchain.Chatchat’s knowledge base and vector database technology, OCR technology, and deep learning to fine-tune the large language model for literature screening; S4, data extraction, using table OCR technology and language recognition technology on the basis of chatpdf and chatdoc interfaces, to condense and extract data from the selected articles; S5, information summary, summarizes the extracted literature data information, uses regular formatting to apply Python's Matplotlib and Python-docxE operation technology, and outputs charts and multi-style theme automated PDF reports.

[0030] Specifically, the present invention realizes accurate screening and analysis of medical literature through an artificial intelligence-based system. The following is its specific working principle: Search formula construction: The system uses PubMed's MeSH interface and natural language processing (NLP) model to automatically generate search formulas. This process improves the efficiency and accuracy of retrieval through AI's multi-task design mode.

[0031] Literature screening: The system uses Langchain-ChatChat’s knowledge base and vector database technology, combined with OCR technology and deep learning model fine-tuning, to automatically screen out high-quality literature. AI can understand and filter out irrelevant or low-quality literature.

[0032] Scale evaluation: Through table OCR technology and semantic recognition technology, the system can automatically read and extract key data from documents based on chatpdf and chatdoc interfaces.

[0033] Data extraction and information summary: The system summarizes the extracted information, formats it using regular expressions, and generates charts and automated PDF reports with multiple styles and themes through Python's Matplotlib and Python-docx technology.

[0034] Output and application: Ultimately, the reports generated by the system can be used for scientific research, teaching, and clinical applications, helping researchers quickly obtain high-quality information, promoting interdisciplinary cooperation, improving scientific research efficiency, and promoting the clinical transformation of scientific research results.

[0035] Through these principles, the system realizes the automation of the entire process from literature retrieval to data analysis, greatly improving the efficiency and accuracy of literature processing.

[0036] Working process: Step 1: Search query construction The system receives keywords and search conditions entered by the user The system uses PubMed's MeSH interface and NLP model to automatically generate search terms The system searches for relevant literature in databases such as PubMed based on the search formula Step 2: Literature screening The system uses Langchain-ChatChat's knowledge base and vector database technology to screen the retrieved documents The system combines OCR technology and deep learning model fine-tuning to evaluate the quality of documents The system selects high-quality literature based on the evaluation results Step 3: Scale Evaluation The system uses table OCR technology and semantic recognition technology to evaluate the selected documents. The system extracts key data from the literature based on the scale evaluation results Step 4: Data extraction and information aggregation The system summarizes the extracted information The system uses regular expressions for formatting The system generates charts and automated PDF reports with multiple themes using Python's Matplotlib and Python-docx technologies. Step 5: Output and Application System output generated reports The system provides reports in different formats (such as PDF, Word, etc.) according to user needs The system supports users to browse and download reports online Step 6: System maintenance and updates The system regularly updates the literature information in databases such as PubMed The system is maintained and updated based on user feedback and evaluation results Through these steps, the system realizes the automation of the entire process from literature retrieval to data analysis, greatly improving the efficiency and accuracy of literature processing.

[0037] Examples, such as Figure 2 As shown: Step 01: Search formula construction Purpose: To automatically construct search terms based on given topics and formulate inclusion and exclusion criteria.

[0038] Technology: Utilizes PubMed's MeSH interface and natural language processing (NLP) models.

[0039] Operation: AI automatically generates search expressions based on preset tasks and instructions.

[0040] Step 02: Literature screening Objective: To determine whether the literature is included in the study through abstract screening.

[0041] Technology: Dataset screening software based on the 7B Baichuan language model.

[0042] Operation: Conduct preliminary screening of a large amount of literature to determine whether it meets the research requirements.

[0043] Step 03: Scale Evaluation Objective: To evaluate the quality of the literature.

[0044] Technology: Use Langchain-ChatChat’s knowledge base, vector database technology, and OCR technology.

[0045] Operation: Fine-tune the large language model through deep learning to achieve automatic evaluation of document quality.

[0046] Step 04: Data Extraction Purpose: To extract the required data from the selected literature.

[0047] Technology: Combination of table OCR technology and semantic recognition technology.

[0048] Operation: Using chatpdf and chatdoc interfaces, AI understands the content of the article and extracts key data.

[0049] Step 05: Information summary Purpose: To summarize and format the extracted data.

[0050] Technique: Use regular expressions for formatting, combined with Python's Matplotlib and Python-docx libraries.

[0051] Operation: Generate automated PDF summary reports with charts and multiple themes.

[0052] Specific implementation cases Conduct a literature review on “Applications of Artificial Intelligence in Medicine”.

[0053] 1. Construct search formula: Use AI tools to enter keywords such as "artificial intelligence", "oralmedicine", etc., and AI will automatically generate PubMed search terms.

[0054] 2. Literature screening: Run the generated search formula in the database to obtain a large number of documents.

[0055] Use AI screening software to filter out literature related to the topic based on the abstract content.

[0056] 3. Scale evaluation: The quality of the screened literature is evaluated, and the AI ​​tool automatically scores it according to the preset evaluation criteria.

[0057] 4. Data extraction: For literature evaluated as high-quality, AI tools are used to extract key data, such as research methods and results.

[0058] 5. Information summary: The extracted data is sorted, and the AI ​​tool generates charts based on the data characteristics.

[0059] Use the Python-docx library to generate a formatted PDF report that contains the main content and conclusions of the literature review.

Claims

1. A system for automatically generating reviews based on artificial intelligence, characterized in that: include: A search formula construction module, a document screening module, a scale evaluation module, a data extraction and information summary module, an output and application module, and a system maintenance and update module; the search formula construction module, the document screening module, the scale evaluation module, the data extraction and information summary module, the output and application module, and the system maintenance and update module are connected in sequence; The search formula building module is used to receive keywords and search conditions input by the user, generate a search formula, and search for relevant documents according to the search formula; The literature screening module is used to evaluate and screen the quality of retrieved literature; The scale evaluation module is used to read and extract key data from the screened literature and conduct scale evaluation; The data extraction and information aggregation module is used to aggregate the extracted information and generate reports; Output and apply module output to generate reports; The system maintenance and update module is used to perform system maintenance and updates based on user feedback and system evaluation results.

2. The system for automatically generating a review based on artificial intelligence according to claim 1, characterized in that: The search formula building module is used to receive keywords and search conditions input by the user, generate a search formula, and search for relevant documents according to the search formula, including: The search formula construction module receives keywords and search conditions input by the user, automatically generates a search formula through the MeSH interface of PubMed and the natural language processing model, and searches for corresponding documents in the medical database according to the search formula; The search formula building module includes an optimization unit, which is used to dynamically adjust the natural language processing model parameters according to the user's historical search records and feedback.

3. The system for automatically generating a review based on artificial intelligence according to claim 2, characterized in that: The document screening module is used to evaluate and screen the quality of the retrieved documents, including: Through the knowledge base and vector database of Langchain-ChatChat, combined with the fine-tuning of OCR and deep learning models, the retrieved documents are quality evaluated and screened to select the corresponding medical literature.

4. The system for automatically generating a review based on artificial intelligence according to claim 3, characterized in that: The scale evaluation module is used to read and extract key data from the screened literature and perform scale evaluation, including: Through table OCR and semantic recognition, based on chatpdf and chatdoc interfaces, read and extract key data from the screened literature; the key data include literature title, abstract, publication time, author, literature research method, research sample size, research population characteristics, research method corresponding dependent variable indicator information, and effect size of research results; The scale evaluation module includes a verification unit for cross-validating the extracted key data.

5. The system for automatically generating a review based on artificial intelligence according to claim 4, characterized in that: The data extraction and information summary module is used to summarize the extracted information and generate a report, including: The effect sizes of each research result are extracted, and the groups and specific scopes of application of the effect sizes of the research results are summarized. The summarized information is formatted through regular expressions, and an automated report with charts and multi-style themes is generated through Python's Matplotlib and Python-docx. The data extraction and information aggregation module includes a custom report generation unit, which is used to generate corresponding reports according to the report style, chart type and content layout selected by the user.

6. The system for automatically generating a review based on artificial intelligence according to claim 5, characterized in that: The system maintenance and update module also includes a collaboration platform, which is used for multi-user online collaborative editing, annotation and sharing of reports.

7. A method for automatically generating a review based on artificial intelligence, characterized in that: A system for automatically generating a review based on artificial intelligence according to any one of claims 1 to 6 is applied, comprising the following steps: S1, search formula construction, through the MeSH interface of PubMed and the language output multi-task design mode of the NLP model, AI automatically constructs the search formula and formulates the inclusion and exclusion criteria; S2, literature screening, artificially made data set screening software is fine-tuned on the 7BBaichuan language model to filter literature types by abstract; S3, scale evaluation, using Langchain.Chatchat’s knowledge base and vector database technology, OCR technology, and deep learning to fine-tune the large language model for literature screening; S4, data extraction, using table OCR technology and language recognition technology on the basis of chatpdf and chatdoc interfaces, to condense and extract data from the selected articles; S5, information summary, summarizes the extracted literature data information, uses regular formatting to apply Python's Matplotlib and Python-docxE operation technology, and outputs charts and multi-style theme automated PDF reports.

Images