AI-based intelligent duplicate checking method and system for medical wound materials

Abstract

The embodiment of the invention relates to the technical field of information, in particular to an AI-based intelligent duplicate checking method and system for a medical wound material. The method comprises the steps that historical scientific research project materials are read, deconstruction information of the scientific research project materials is generated, and the deconstruction information comprises a plurality of technical target descriptions, technical stack portraits and subject information abstracts; according to the deconstruction information, establishing a rapid detection table of historical scientific research project materials; reading the medical wound material to be subjected to duplicate checking, and extracting a technical target, a technical abstract and subject information of the medical wound material; respectively comparing the technical target, the technical abstract and the subject information of the medical wound material with the fast detection table to obtain all matched rows; according to all matched rows, respectively generating a technical target repetition degree, a technical abstract repetition degree and a subject information repetition degree; and according to the technical target repetition degree, the technical abstract repetition degree and the subject information repetition degree, generating a duplicate checking rate of the medical wound material to be subjected to duplicate checking.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of information technology, and specifically to an AI-based intelligent duplication checking method and system for scientific and technological materials. Background Art

[0002] With the advancement of science and technology and the increasing frequency of scientific research activities, checking for duplicate content in research project materials has become a crucial step in ensuring the integrity of research. Traditional methods for checking for duplicate content rely primarily on text similarity comparisons, which are insensitive to changes in textual expression and struggle to effectively identify rewritten research materials that still contain substantial duplicate content. This is particularly true in the field of scientific and technological innovation, where research projects often involve complex technology stacks, unique technical objectives, and diverse subject matter, further complicating the task of checking for duplicate content.

[0003] Artificial intelligence (AI) technology has made significant progress in natural language processing and pattern recognition, providing new solutions for improving the accuracy and efficiency of checking for plagiarism in scientific research materials. AI-based methods can deeply understand the actual content of scientific research materials. However, research on plagiarism checking technologies for scientific and creative materials is currently lacking. Summary of the Invention

[0004] Multiple embodiments of this specification describe an AI-based intelligent duplication checking method and system for scientific and technological materials.

[0005] In a first aspect, the embodiments of this specification provide an AI-based intelligent duplicate checking method for scientific and technological innovation materials, comprising the following steps:

[0006] Read historical scientific research project materials and generate deconstruction information of the scientific research project materials, wherein the deconstruction information includes several technical goal descriptions, technology stack portraits and main information summaries;

[0007] Establish a quick check list of historical scientific research project materials based on the deconstruction information, where each row of the quick check list records the identification and deconstruction information of a historical scientific research project material;

[0008] Read the scientific and technological innovation materials to be checked for duplicates, and extract the technical objectives, technical summaries and main information of the scientific and technological innovation materials;

[0009] Use the technical objectives, technical summary and main information of the scientific and technological innovation materials to compare with the quick check table respectively to obtain all matching rows;

[0010] Based on all matching rows, generate the technical target duplication, technical summary duplication and main information duplication respectively;

[0011] Based on the duplication of the technical objectives, the duplication of the technical abstracts and the duplication of the main information, the duplication rate of the scientific and technological materials to be checked is generated.

[0012] In a second aspect, the embodiments of this specification provide an AI-based intelligent duplicate checking system for scientific and technological innovation materials, which is characterized by including:

[0013] A reading module reads historical scientific research project materials and generates deconstructed information of the scientific research project materials, wherein the deconstructed information includes several technical goal descriptions, technology stack portraits, and main information summaries;

[0014] A first generation module creates a quick check list of historical scientific research project materials based on the deconstruction information, wherein each row of the quick check list records the deconstruction information of a historical scientific research project material;

[0015] The extraction module reads the scientific and technological innovation materials to be checked for duplicates and extracts the technical objectives, technical abstracts and main information of the scientific and technological innovation materials;

[0016] A comparison module compares the technical objectives, technical summaries, and subject information of the scientific and technological innovation materials with the quick check table to obtain all matching rows;

[0017] The second generation module generates the technical goal duplication, technical summary duplication and main information duplication respectively based on all matching rows;

[0018] The result module generates the duplication rate of the scientific and technological materials to be checked for duplication based on the duplication of the technical objectives, the duplication of the technical abstracts and the duplication of the main information.

[0019] In a third aspect, embodiments of this specification provide an electronic device, including a processor and a memory;

[0020] The processor is connected to the memory;

[0021] The memory is used to store executable program code;

[0022] The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method described in any one of the above aspects.

[0023] In a fourth aspect, an embodiment of this specification provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in any one of the above aspects is implemented.

[0024] In a fifth aspect, embodiments of this specification provide a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0025] The beneficial effects of the technical solutions provided by some embodiments of this specification include at least:

[0026] In multiple embodiments of this specification, the provided AI-based intelligent duplicate checking method and system for scientific and technological materials calculates the duplicate checking rate of scientific and technological materials by deconstructing and comparing the technical goals, technology stack portraits and main information in the scientific research project materials. It can deeply understand the core content of the materials, effectively identify the content that is still substantially repeated even after rewriting, and significantly improve the accuracy of duplicate checking. The AI-based intelligent duplicate checking method for scientific and technological materials not only relies on text similarity, but also needs to consider multi-dimensional information such as technical goals, technical summaries and main information. Through pre-configured matching strategies, it can more effectively evaluate the originality of the scientific and technological materials to be checked for duplicates. By performing weighted calculations on the matching results, the duplicate checking rate of the scientific and technological materials to be checked for duplicates is automatically generated, providing a scientific basis for scientific research management personnel, and helping to make more fair and transparent decisions in scientific research project establishment, review and other links.

[0027] Other features and advantages of the various embodiments of this specification will be further disclosed in the following detailed description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0029] Figure 1 Schematic diagram of intelligent duplicate checking for scientific and technological innovation materials provided in the embodiments of this specification.

[0030] Figure 2 A flow chart of the intelligent duplicate checking method for scientific and technological innovation materials provided in the embodiments of this specification.

[0031] Figure 3 This is a schematic diagram of the search matching degree provided in the embodiments of this specification.

[0032] Figure 4 Schematic diagram of the intelligent duplicate checking system for scientific and technological innovation materials provided in the embodiments of this specification.

[0033] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0034] The following is an explanation and description of the technical solutions of the embodiments of this specification in conjunction with the drawings of the embodiments of this specification. However, the following embodiments are only preferred embodiments of this specification and are not exhaustive. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without making any creative work are all within the scope of protection of this specification.

[0035] Throughout this specification, the claims, and the accompanying drawings, the terms "first," "second," "third," and the like are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may include other steps or elements inherent to the process, method, product, or apparatus.

[0036] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limitations on this specification.

[0037] The data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions.

[0038] Before introducing the technical solution in this specification, the application scenarios and related technologies of the technical solution are introduced.

[0039] The originality of scientific research materials is one of the key criteria for assessing their value. With the advancement of science and technology, the number of research projects has skyrocketed, making it increasingly important to ensure the uniqueness and innovation of each piece of research material. Therefore, checking for plagiarism in research materials has become a crucial component of scientific research. The significance of checking for plagiarism in research materials lies in preventing academic misconduct, such as plagiarism, and protecting intellectual property rights. It also promotes scientific integrity and improves the quality of research materials. Effective plagiarism checking can safeguard the authenticity and uniqueness of research findings, maintaining fairness and transparency within the scientific community. For example, consider an innovative technology company planning to submit its latest environmentally friendly battery technology for an annual science and technology excellence award. To ensure the uniqueness and innovation of this technology, the relevant research materials for this environmentally friendly battery technology must be checked for plagiarism during the review process. The plagiarism check results provide strong data support for the review experts, helping to enhance the fairness and transparency of the review process.

[0040] Many current duplicate checking technologies rely mainly on direct comparison of texts, evaluating similarity by calculating the text repetition rate between documents. Although this method can identify completely or partially copied and pasted content to a certain extent, its limitation is that it only focuses on matching at the text level and fails to conduct in-depth checks at the semantic level. To this end, this manual provides an AI-based intelligent duplicate checking method and system for scientific and technological materials. Please refer to the attached Figure 1 First, the system reads historical research project materials and generates deconstructed information, including a description of technical objectives, a technology stack, and a summary of the main information. A quick check table is then created based on this information. Next, the scientific and technological innovation materials to be checked for duplicate content are parsed, extracting the technical objectives, technical summaries, and main information. These are then compared with the information in the quick check table to calculate the duplication rate, or the duplication rate.

[0041] This manual first provides an AI-based intelligent duplicate checking method for scientific and creative materials. Figure 2 , including the steps of:

[0042] Step S1) reads historical scientific research project materials and generates deconstruction information of the scientific research project materials, wherein the deconstruction information includes several technical target descriptions, technology stack portraits and main information summaries.

[0043] The technical goal description aims to capture the fundamental purpose and desired outcomes of a research project. To generate this description, a large language model is used to extract the focus problem description, the involved technologies, and the desired outcomes from the research project materials. These descriptions are then fitted into a pre-set technical goal description prompt template. The template requires the description to start with the focus problem and ultimately achieve a specific outcome through the involved technologies. This provides a clear description of the research project's technical goals.

[0044] The technology stack profile identifies and records the technical tools used in a research project. The system reads a preset tool set, which contains the technical names and descriptions of various tools. These tools are then compared with the research project materials to determine their compatibility. If a tool's compatibility exceeds a preset threshold, it is incorporated into the project's technology stack and a corresponding usage description is generated. The technology stack profile is formed based on the technical tools included in the technology stack and their usage descriptions.

[0045] The main information summary includes a summary of key information such as the person in charge of the scientific research project, participating personnel, research institutions, etc., which is used to quickly understand the background of the scientific research project.

[0046] The main purpose of step S1) is to extract key information that will be helpful in the subsequent duplication checking process through in-depth analysis of historical scientific research project materials, namely, technical goal description, technology stack portrait and main information summary. This information together constitutes the "fingerprint" of the scientific research project materials, enabling subsequent duplication checking work to be carried out more accurately.

[0047] For example, consider a research project called "Smart City Traffic Management System." Here's an example of deconstructed information from the project's materials:

[0048] Technical Goal Description: Committed to solving urban traffic congestion and its environmental impact, improving traffic management efficiency through advanced data analysis technology and AI algorithms;

[0049] Technology stack profile: Covering a range of technical tools from data collection to model training, such as Python, Apache Kafka, and TensorFlow;

[0050] Main Information Summary: This project is implemented by a team of experts from a university's Intelligent Transportation Research Center.

[0051] The steps of generating the technical goal description of the scientific research project materials include:

[0052] Instruct the pre-connected large language model to extract the focus problem description, related technology description and effect description of the scientific research project materials;

[0053] The focused problem description, the technology description involved and the effect description are put into a preset technical goal description prompt template and submitted to the large language model, and the pursuit description is obtained according to the response of the large language model. The technical goal description prompt template includes a description statement with the focused problem description as the starting point, the technology description involved as the path, and the effect description as the result.

[0054] The process of generating technical goal descriptions for research project materials involves using a pre-connected large language model to analyze and extract the core elements of the research project. Using a specific template, the system generates a technical goal description that is easy to understand and compare. The system instructs the large language model to extract three core elements from the research project materials.

[0055] Focus on the problem statement, that is, what is the main problem or challenge that the research project aims to solve;

[0056] Involving technical description, what technical means or methods are used in the process of trying to solve the problem;

[0057] Effect description: the expected results or impacts achieved through the above technologies and methods.

[0058] The three extracted core elements are placed into a preset technical goal description prompt template. The purpose of the template design is to ensure that the final technical goal description clearly conveys the scientific research project's focus on the problem as the starting point, the technologies involved as the approach, and the effects as the results. After filling in the template, it is submitted to the large language model again to obtain a more fluent, accurate, and logical technical goal description. This step leverages the powerful text processing capabilities of the large language model to ensure that the final output technical goal description not only contains the necessary information but also expresses it in a more natural and professional manner.

[0059] The technical objectives of the research project based on "Intelligent City Traffic Management System" are described as follows:

[0060] Focus on the problem description: Current urban traffic congestion is serious, leading to energy waste and increased environmental pollution;

[0061] Technology Description: Leveraging big data analytics, Internet of Things (IoT) devices, and artificial intelligence algorithms to optimize traffic flow management;

[0062] Effect description: It is expected to reduce traffic congestion time in the city center by 30%, reduce carbon emissions, and improve citizens' travel efficiency.

[0063] The steps of generating the technology stack portrait of the scientific research project materials include:

[0064] Reading a preset technical tool set, wherein the technical tool set records the technical name and technical description of the technical tool;

[0065] Compare the technical names and technical descriptions in the technical tool set with the scientific research project materials to obtain the matching degree between the technical tools and the scientific research project materials;

[0066] Incorporate the technical tools whose matching degree exceeds the preset threshold into the technology stack, and generate a description of the use of the technology stack based on the scientific research project materials;

[0067] Generate a technology stack portrait based on the technical names of the technical tools in the technology stack and their usage descriptions.

[0068] The process of generating a technology stack profile for scientific research project materials is a systematic approach for identifying the key technologies used in scientific research projects and building a detailed technology stack profile based on this information.

[0069] Load a pre-set technical tool set, which contains detailed information about various technical tools, including but not limited to the technology name and description.

[0070] The system compares each technology name and description in the technology tool set with the scientific research project materials, and evaluates the relevance or matching degree between each technology tool and the current scientific research project. The matching degree can be calculated through text similarity algorithms, keyword matching, etc.

[0071] Based on the obtained matching scores, all technical tools are screened and those with matching scores exceeding a preset threshold are included in the project's technology stack. Based on the research project materials, detailed usage descriptions are generated for the technical tools, explaining how the technical tools are used in the project. All technical tools included in the technology stack and their usage descriptions are integrated to form a comprehensive technology stack portrait that reflects the technical architecture that the research project relies on.

[0072] The technology stack of the scientific research project based on the "Smart City Traffic Management System" is shown below.

[0073] Technical toolset loading: Loads a technical toolset that includes various technical tools, such as the Python programming language, the Apache Kafka message queue system, and the TensorFlow machine learning framework.

[0074] Compare and determine the degree of match: By comparing these technology names and descriptions with the materials of the scientific research project, it was found that the project mainly used the following technologies: Python was used to write data analysis scripts, Apache Kafka was used to process real-time data streams from multiple sensors, and TensorFlow was used to train deep learning models to predict traffic flow.

[0075] Incorporate into the technology stack and generate a description: For each technology tool whose match exceeds a preset threshold, it is incorporated into the technology stack and a detailed description of its use is generated based on project requirements. For example, Python is used as the core programming language for data cleaning, transformation, and visualization. Apache Kafka is used to build a distributed messaging system to ensure efficient processing of data streams from thousands of vehicle sensors. TensorFlow is used to build a neural network model to predict future traffic conditions and recommend optimal routes.

[0076] Step S2) A quick check list of historical scientific research project materials is established based on the deconstruction information, where each row of the quick check list records the identification and deconstruction information of a historical scientific research project material.

[0077] Specifically, the method of establishing a quick checklist for historical research project materials includes:

[0078] Create a cache area in the high-speed storage space;

[0079] Creating a KV value pair using identification and deconstruction information of historical scientific research project materials, and storing the KV value pair in the cache area;

[0080] The content stored in the cache area is persisted at a set period.

[0081] A dedicated cache area is created within the system's high-speed storage space. The cache area is used to temporarily store identification and deconstruction information for historical research project materials that are about to be processed. Using the cache area can significantly increase the speed of data reading and writing, thereby speeding up the entire duplicate checking process.

[0082] For each historical research project, the system creates a key-value (KV) pair. The key is typically a unique identifier for the research project, such as a project number or name; the value is the project's deconstructed information. These KV pairs are stored in a previously created cache for quick access and querying. This streamlines each research project into a manageable and easily comparable format.

[0083] To prevent data loss and ensure long-term preservation, the system persists the contents of the cache to more stable storage media, such as a hard disk or database, at set intervals. This ensures that even in the event of a system failure or other unexpected situation, processed data is not lost and can be reloaded into the cache for further processing when needed.

[0084] Through the above steps, the system can effectively build a quick check table containing the material identification and deconstruction information of all historical scientific research projects. The quick check table not only supports fast query and matching operations, but also ensures the security and reliability of data through regular data persistence.

[0085] Step S3) Read the scientific and technological innovation materials to be checked for duplication, and extract the technical objectives, technical abstracts and main information of the scientific and technological innovation materials.

[0086] The system needs to obtain scientific and technological innovation materials to be checked for duplicate content and identify and extract the project's technical objectives from these materials. Technical objectives generally refer to the core problems, goals, or expected effects of a scientific research project. Natural language processing technology is used to analyze the text content, identifying key information such as the focus problem description, the involved technologies, and the effect description. The system then generates the final technical objective description using a preset technical objective description prompt template.

[0087] Extract technical summaries from scientific and technological materials. Technical summaries summarize the technical means, tools, and methods used in scientific research projects, including but not limited to identifying the specific technology names mentioned in the project, technical descriptions, and how they are applied. This process also relies on natural language processing technology to accurately capture technology-related information and form a concise and clear picture of the technology stack.

[0088] Extract the main information from scientific and technological materials. The main information usually includes relevant background information such as the person in charge, participants, and research institutions of the scientific research project. It helps to understand the background and implementation environment of the scientific research project, and is very important for comprehensively evaluating the uniqueness and originality of the scientific research project.

[0089] The system effectively extracts essential information from scientific and creative materials to be checked for duplicate content, including technical objectives, technical summaries, and subject information. This extracted information is then compared against a quick checklist of historical research project materials to calculate the duplication rate and determine the novelty and uniqueness of the scientific and creative materials.

[0090] Step S4) Use the technical objectives, technical summary and main information of the scientific and technological innovation materials to compare with the quick check table respectively to obtain all matching rows.

[0091] For details, please refer to the attached Figure 3 , the steps to get all matching rows include:

[0092] Compare the technical objectives of the scientific and technological innovation materials with the technical objective descriptions in the quick check table to obtain a technical objective matching degree;

[0093] Compare the technical summary of the scientific and technological innovation materials with the technology stack profile of the row in the quick check table to obtain the degree of technical matching;

[0094] Compare the subject information of the scientific and technological innovation materials with the subject information summary of the row in the quick check table to obtain the subject matching degree;

[0095] Generate a first coefficient and a second coefficient with an initial value of 1;

[0096] When the technical target matching degree is higher than a preset first threshold, the value of the first coefficient is updated to be greater than 1; when the technical target matching degree is not higher than the preset first threshold, the value of the first coefficient is updated to be less than 1;

[0097] When the subject matching degree is higher than a preset second threshold, the value of the second coefficient is updated to be less than 1; when the subject matching degree is not higher than the preset second threshold, the value of the second coefficient is updated to be greater than 1;

[0098] Obtaining a search matching degree between the scientific and technological innovation material and the row according to the technical matching degree, the first coefficient, and the second coefficient;

[0099] When the search matching degree is higher than a preset reference threshold, the row is regarded as a matching row.

[0100] Compare the technical objectives of the scientific and technological innovation materials to be checked for duplicates with the "Technical Objective Description" of each historical scientific research project in the quick check table to obtain a technical objective matching degree, which indicates the degree of similarity between the two. Compare the technical summary of the scientific and technological innovation materials to the "Technical Stack Profile" in the corresponding row of the quick check table to assess the similarity in technical application between the two and thus determine the technical matching degree.

[0101] Comparing the subject information of the scientific and technological materials to be checked for duplication with the "subject information summary" of the corresponding row in the quick check table will help identify possible duplicate research work performed by the same or related teams and generate subject matching.

[0102] If the technical target matching degree is higher than the preset first threshold, it is considered that the technical target has a high similarity, and the value of the first coefficient is updated to be greater than 1; conversely, if the technical target matching degree is not high, the value of the first coefficient is reduced to less than 1.

[0103] For the subject matching degree, if it is higher than a preset second threshold, the value of the updated second coefficient is less than 1, which means that the high similarity of the subject information may indicate lower uniqueness; otherwise, the value of the second coefficient is greater than 1.

[0104] Combining the matching degrees of the three dimensions mentioned above with the adjusted first and second coefficients, the system calculates a comprehensive search matching degree. This matching degree reflects the overall similarity between the scientific and creative materials to be checked for duplicates and each historical research project in the quick check list. Finally, if the search matching degree of a historical research project exceeds the preset reference threshold, the entry is considered to have significant duplication or similarity with the scientific and creative materials to be checked for duplicates and is marked as a matching row.

[0105] Assume that the scientific and technological innovation materials to be checked for duplicate content are Project X, and their deconstruction information is as follows:

[0106] Technical Goal: Address insufficient medical resources in remote areas and improve diagnostic accuracy by 20% through telemedicine systems. Technical Summary: Real-time audio and video communication based on WebRTC, mobile application development with React Native, and serverless computing with AWS Lambda. Subject Information: Telemedicine department of a hospital, Dr. Wang Wu's team.

[0107] Step S4) Specific operation example, technical goal match calculation: The technical goal of the referenced material (Project X) is: "Solve the problem of insufficient medical resources in remote areas and improve diagnostic accuracy by 20% through telemedicine systems." The technical goal of the historical project (ProjectID_C) is: "Provide convenient medical services to residents in remote areas and improve diagnostic accuracy by 20%." Match calculation: Using a text similarity algorithm, we found that the focus and effect descriptions of the two are highly consistent, resulting in a technical goal match of 0.9. Technical match calculation: The technical summary of the referenced material (Project X) includes: React Native (mobile), WebRTC (real-time communication), and AWS Lambda (serverless computing).

[0108] The technology stack profile of the historical project (ProjectID_C): React Native, WebRTC, AWS Lambda. Match calculation: The technical tools are completely identical, resulting in a technical match of 1.0. Subject matter match calculation: The subject matter of the material to be checked (Project X): The telemedicine department of a certain hospital, Dr. Wang Wu's team. The subject matter summary of the historical project (ProjectID_C): The telemedicine department of a certain hospital, Dr. Wang Wu, etc.

[0109] Matching Calculation: If the principal information (institution and principal) is completely consistent, the principal matching is 1.0. Coefficient Adjustment: Initial Values: First Coefficient = 1.0, Second Coefficient = 1.0. The following rules apply: If the technical target matching exceeds the first threshold (assuming 0.8), the first coefficient is updated to 1.2. If the principal matching exceeds the second threshold (assuming 0.8), the second coefficient is updated to 0.8. After Adjustment: First Coefficient = 1.2 (Technical Target Match 0.9 > 0.8), Second Coefficient = 0.8 (Principal Match 1.0 > 0.8).

[0110] The specific formula for calculating the search match degree is: Search Match Degree = Technical Match Degree × First Coefficient × Second Coefficient. Substituting the values, we obtain a Search Match Degree of 1.0 × 1.2 × 0.8 = 0.96. To determine whether a match exists, we use a preset reference threshold of 0.9. Result: The search match degree is 0.96 > 0.9, resulting in a matching behavior for ProjectID_C. The historical project is highly similar to the material being searched.

[0111] Key logic explains that technical goal match dominates. If the technical goal match is high (e.g., 0.9), the first coefficient is amplified (1.2), emphasizing the importance of goal similarity. Subject information duplication suppression involves reducing the second coefficient (0.8) if the subject match is high (e.g., 1.0), mitigating overmatch caused by repeated submissions from the same team. Technical match is core, including complete consistency of the technology stack (1.0), which is the key factor in the final match.

[0112] Step S5) Generate the technical goal repetition rate, technical summary repetition rate and main information repetition rate respectively based on all matching rows.

[0113] The specific steps include:

[0114] Obtaining an initial value of the technical target repetition degree based on the maximum value of the technical target matching degree between the scientific and technological innovation material and all matching rows;

[0115] Obtaining an initial value of the duplication of the technical abstract based on the maximum value of the technical matching degree between the scientific and technological innovation material and all matching rows;

[0116] Obtaining the degree of duplication of subject information according to the maximum value of the subject matching degree between the scientific and technological innovation material and all matching rows;

[0117] When the repetition of the main information is higher than the preset reference value, the initial value of the technical target repetition is reduced as the final technical target repetition, and the initial value of the technical abstract repetition is reduced as the final technical target repetition.

[0118] Step S5) further calculates specific duplication indices based on all matching rows obtained in step S4). These duplication indices help quantify the degree of similarity between the scientific and creative materials to be checked for duplication and historical research projects.

[0119] The system examines all rows identified as matches in step S4) and finds the maximum technical target matching score. This maximum value reflects the highest similarity in technical targets between the scientific and creative material to be checked for duplication and its most similar historical research project. This maximum value is used as the initial value for the technical target duplication score.

[0120] The system will find the maximum value of the technical matching degree from all matching rows to indicate the highest similarity in technical implementation between the scientific and technological materials to be checked for duplication and their closest historical scientific research projects. This maximum value will serve as the initial value of the duplication degree of the technical abstract.

[0121] The system will also extract the maximum value of the subject matching degree from all matching rows, which represents the highest similarity between the scientific and technological materials to be checked for duplication and a historical scientific research project in terms of the research team or execution entity. This maximum value directly becomes the duplication degree of the subject information.

[0122] If the duplication of subject information exceeds the preset reference value, this means that the scientific and creative materials to be checked for duplication have a high degree of similarity in research subject matter with certain historical scientific research projects. To reduce the risk of excessive duplication due to identical subject matter, the initial values ​​of the duplication of technical objectives and technical abstracts are adjusted downward to generate the final duplication of technical objectives and technical abstracts.

[0123] Step S6) Generate a duplication rate of the scientific and technological innovation materials to be checked for duplication based on the duplication of the technical objectives, the duplication of the technical abstracts, and the duplication of the main information.

[0124] The specific steps include:

[0125] Obtaining the technical target matching degree and the retrieval matching degree of the row corresponding to the maximum technical matching degree respectively;

[0126] Using the search matching degree as a weight, a weighted average of the technical target duplication degree and the technical abstract duplication degree is obtained;

[0127] Calculate the quotient of a preset constant and the repetition degree of the main information, and multiply the quotient by the weighted average value as the duplication rate of the scientific and creative materials to be checked for duplication.

[0128] The purpose of step S6) is to generate the overall duplication rate of the scientific and technological innovation materials to be checked for duplication based on the previously calculated technical target duplication, technical abstract duplication and main information duplication.

[0129] Determine the rows corresponding to the maximum technical target match and the maximum technical match. Obtain the search match for these rows. The search match reflects the degree of similarity between the scientific and creative materials to be checked for duplicates and the historical research project at a comprehensive level.

[0130] Using the search matching scores obtained above as weights, a weighted average is calculated for the duplications of technical objectives and technical abstracts. If a historical research project is very similar to the scientific and creative materials to be checked for duplication in terms of technical objectives or technical implementation, the duplication of this project will account for a larger proportion of the final weighted average.

[0131] Calculate the quotient of a preset constant and the duplication rate of the main body information. The "preset constant" is a fixed value used to adjust the proportional relationship of the overall calculation. Multiply the quotient by the previously calculated weighted average to obtain the final duplication rate. Further consider the impact of the duplication of the research subject on the overall duplication check results. If the main body information has a high duplication rate, it means there may be a greater risk of duplication, which will affect the final duplication rate.

[0132] On the other hand, in another embodiment, the scheme recorded in this embodiment also calculates text similarity and text similarity based on synonyms, and calculates the final duplication rate based on text similarity, text similarity based on synonyms, technical goal duplication, technical abstract duplication and main information duplication.

[0133] On the other hand, this manual provides an AI-based intelligent duplicate checking system for scientific and technological materials. Figure 4 ,include:

[0134] The reading module 100 reads historical scientific research project materials and generates deconstructed information of the scientific research project materials, wherein the deconstructed information includes several technical goal descriptions, technology stack portraits, and main information summaries;

[0135] The first generating module 200 creates a quick check list of historical scientific research project materials based on the deconstruction information, where each row of the quick check list records the deconstruction information of a historical scientific research project material;

[0136] Extraction module 300, reads the scientific and technological innovation materials to be checked for duplicates, and extracts the technical objectives, technical abstracts, and main body information of the scientific and technological innovation materials;

[0137] The comparison module 400 compares the technical objectives, technical summaries, and subject information of the scientific and technological innovation materials with the quick check table to obtain all matching rows;

[0138] The second generation module 500 generates the technical goal repetition degree, the technical summary repetition degree and the main information repetition degree respectively according to all matching rows;

[0139] The result module 600 generates a duplication rate of the scientific and technological innovation materials to be checked for duplication according to the duplication of the technical objectives, the duplication of the technical abstracts and the duplication of the main information.

[0140] See also Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of this specification is shown.

[0141] like Figure 5 As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. The communication bus 1102 may be used to implement connection and communication between the above-mentioned components. The user interface 1103 may include buttons, and optionally the user interface may also include a standard wired interface or a wireless interface. The network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. The processor 1101 may include one or more processing cores. The processor 1101 uses various interfaces and lines to connect the various components within the entire electronic device 1100, and performs various functions of the routing device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 may be implemented in the form of at least one hardware component selected from the group consisting of a DSP, an FPGA, and a PLA. The processor 1101 may integrate one or a combination of a CPU, a GPU, and a modem. Among them, the CPU mainly processes the operating system, user interface and applications; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display; and the modem is used to handle wireless communications.

[0142] It is understandable that the above-mentioned modem may not be integrated into the processor 1101, but may be implemented by a separate chip.

[0143] Memory 1105 may include either RAM or ROM. Optionally, memory 1105 may include non-transitory computer-readable media. Memory 1105 may be used to store instructions, programs, codes, code sets, or instruction sets. Memory 1105 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, sound playback function, image playback function, etc.), instructions for implementing the aforementioned method embodiments, etc.; the data storage area may store data related to the aforementioned method embodiments, etc. Memory 1105 may optionally be at least one storage device located remotely from the aforementioned processor 1101. Memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program. Processor 1101 may be configured to invoke the application program stored in memory 1105 and execute the methods described in the aforementioned embodiments.

[0144] The embodiments of this specification also provide a computer-readable storage medium having instructions stored therein that, when executed on a computer or processor, cause the computer or processor to perform the steps of the aforementioned embodiments. If the components of the aforementioned electronic device are implemented as software functional units and sold or used as independent products, they may be stored in the computer-readable storage medium.

[0145] The embodiments of this specification also provide a computer program product, including a computer program, which implements multiple steps in the above embodiments when executed by a processor.

[0146] In the absence of conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0147] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product comprises multiple computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that integrates multiple available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0148] When implemented via hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and realize the corresponding function. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit, whose logical function is determined by the user's device programming. Designers can "integrate" a digital system onto a PLD through self-programming, eliminating the need for chip manufacturers to design and fabricate dedicated integrated circuit chips. Moreover, today, instead of manually fabricating integrated circuit chips, this programming is often performed using "logic compiler" software. This is similar to the software compiler used in program development. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There are not just one type of HDL, but many. Those skilled in the art will also understand that simply by programming the method flow in one of the aforementioned hardware description languages ​​and programming it into the integrated circuit, a hardware circuit that implements the logical method flow can be easily obtained.

[0149] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. An AI-based intelligent duplicate checking method for scientific and technological materials, characterized in that: Including steps: Read historical scientific research project materials and generate deconstruction information of the scientific research project materials, wherein the deconstruction information includes several technical goal descriptions, technology stack portraits and main information summaries; Establish a quick check list of historical scientific research project materials based on the deconstruction information, where each row of the quick check list records the identification and deconstruction information of a historical scientific research project material; Read the scientific and technological innovation materials to be checked for duplicates, and extract the technical objectives, technical summaries and main information of the scientific and technological innovation materials; Use the technical objectives, technical summary and main information of the scientific and technological innovation materials to compare with the quick check table respectively to obtain all matching rows; Based on all matching rows, generate the technical target duplication, technical summary duplication and main information duplication respectively; Based on the duplication of the technical objectives, the duplication of the technical abstracts and the duplication of the main information, the duplication rate of the scientific and technological materials to be checked is generated.

2. The AI-based intelligent duplicate checking method for scientific and creative materials according to claim 1 is characterized in that: The steps for generating the technical goal description of the research project materials include: Instruct the pre-connected large language model to extract the focus problem description, related technology description and effect description of the scientific research project materials; The focused problem description, the technology description involved and the effect description are put into a preset technical goal description prompt template and submitted to the large language model, and the pursuit description is obtained according to the response of the large language model. The technical goal description prompt template includes a description statement with the focused problem description as the starting point, the technology description involved as the path, and the effect description as the result.

3. The AI-based intelligent duplicate checking method for scientific and creative materials according to claim 1 is characterized in that: The steps of generating the technology stack portrait of the scientific research project materials include: Reading a preset technical tool set, wherein the technical tool set records the technical name and technical description of the technical tool; Compare the technical names and technical descriptions in the technical tool set with the scientific research project materials to obtain the matching degree between the technical tools and the scientific research project materials; Incorporate the technical tools whose matching degree exceeds the preset threshold into the technology stack, and generate a description of the use of the technology stack based on the scientific research project materials; Generate a technology stack portrait based on the technical names of the technical tools in the technology stack and their usage descriptions.

4. The AI-based intelligent duplicate checking method for scientific and creative materials according to any one of claims 1 to 3, characterized in that: The steps of comparing the technical objectives, technical summary, and main body information of the scientific and technological innovation materials with the quick check table to obtain all matching rows include: Compare the technical objectives of the scientific and technological innovation materials with the technical objective descriptions in the quick check table to obtain a technical objective matching degree; Compare the technical summary of the scientific and technological innovation materials with the technology stack profile of the row in the quick check table to obtain the degree of technical matching; Compare the subject information of the scientific and technological innovation materials with the subject information summary of the row in the quick check table to obtain the subject matching degree; Generate a first coefficient and a second coefficient with an initial value of 1; When the technical target matching degree is higher than a preset first threshold, the value of the first coefficient is updated to be greater than 1; when the technical target matching degree is not higher than the preset first threshold, the value of the first coefficient is updated to be less than 1; When the subject matching degree is higher than a preset second threshold, the value of the second coefficient is updated to be less than 1; when the subject matching degree is not higher than the preset second threshold, the value of the second coefficient is updated to be greater than 1; Obtaining a search matching degree between the scientific and technological innovation material and the row according to the technical matching degree, the first coefficient, and the second coefficient; When the search matching degree is higher than a preset reference threshold, the row is regarded as a matching row.

5. The AI-based intelligent duplicate checking method for scientific and creative materials according to claim 4 is characterized in that: The steps of generating the technical target duplication, technical summary duplication, and main information duplication based on all matching rows include: Obtaining an initial value of the technical target repetition degree based on the maximum value of the technical target matching degree between the scientific and technological innovation material and all matching rows; Obtaining an initial value of the duplication of the technical abstract based on the maximum value of the technical matching degree between the scientific and technological innovation material and all matching rows; Obtaining the degree of duplication of subject information according to the maximum value of the subject matching degree between the scientific and technological innovation material and all matching rows; When the repetition of the main information is higher than the preset reference value, the initial value of the technical target repetition is reduced as the final technical target repetition, and the initial value of the technical abstract repetition is reduced as the final technical target repetition.

6. The AI-based intelligent duplicate checking method for scientific and creative materials according to claim 5 is characterized in that: The steps of generating the duplication rate of the scientific and technological innovation materials to be checked for duplication according to the duplication degree of the technical objectives, the duplication degree of the technical abstracts and the duplication degree of the main information include: Obtaining the technical target matching degree and the retrieval matching degree of the row corresponding to the maximum technical matching degree respectively; Using the search matching degree as a weight, a weighted average of the technical target duplication degree and the technical abstract duplication degree is obtained; Calculate the quotient of a preset constant and the repetition degree of the main information, and multiply the quotient by the weighted average value as the duplication rate of the scientific and creative materials to be checked for duplication.

7. The AI-based intelligent duplicate checking method for scientific and creative materials according to any one of claims 1 to 3, characterized in that: Methods for establishing a quick checklist for historical research project materials include: Create a cache area in the high-speed storage space; Creating a KV value pair using identification and deconstruction information of historical scientific research project materials, and storing the KV value pair in the cache area; The content stored in the cache area is persisted at a set period.

8. An AI-based intelligent duplicate checking system for scientific and creative materials, characterized by: include: A reading module reads historical scientific research project materials and generates deconstructed information of the scientific research project materials, wherein the deconstructed information includes several technical goal descriptions, technology stack portraits, and main information summaries; A first generation module creates a quick check list of historical scientific research project materials based on the deconstruction information, wherein each row of the quick check list records the deconstruction information of a historical scientific research project material; The extraction module reads the scientific and technological innovation materials to be checked for duplicates and extracts the technical objectives, technical abstracts and main information of the scientific and technological innovation materials; A comparison module compares the technical objectives, technical summaries, and subject information of the scientific and technological innovation materials with the quick check table to obtain all matching rows; The second generation module generates the technical goal duplication, technical summary duplication and main information duplication respectively based on all matching rows; The result module generates the duplication rate of the scientific and technological materials to be checked for duplication based on the duplication of the technical objectives, the duplication of the technical abstracts and the duplication of the main information.

9. An electronic device, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images