Whole disease scientific research management platform and control method thereof

Abstract

The invention provides an all-disease scientific research management platform and a control method thereof, and relates to the technical field of data management. Heterogeneous data of multiple preset sources is acquired, format conversion, preprocessing and integration are performed, multi-source integrated data is acquired, data pushing is performed on the multi-source integrated data, category pushing data is acquired, and the category pushing data is sent to a server; according to the constraint conditions of the disease database, carrying out incorporation and exclusion processing on each category of push data to obtain category data of the disease database; performing distributed storage and classified management of a plurality of function categories on the disease category library category data to obtain category management data, and further obtaining management push data of each function category; calculating a data push error coefficient, judging the error data of the push data according to the data push error coefficient, adjusting the preset constraint adjustment data according to the judgment result, and adjusting the push error data. According to the invention, the data integration efficiency can be improved, the disease database management can be optimized, and the data push accuracy can be improved.

Description

Technical Field

[0001] The present invention proposes a full-disease scientific research management platform and a control method thereof, which relate to the technical field of data management, and specifically to the technical field of full-disease scientific research management. Background Art

[0002] Although hospital informatization is advancing, there are still many challenges in clinical research data management. First, data collection and management are difficult and require high technology. Many hospitals still use paper-based office methods, and are unable to establish a mutual recognition mechanism for ethical review results between hospitals and within regions. Paper medical records not only reduce the overall operating efficiency of the hospital, but also easily cause the loss of patients' medical records and clinical research data, and cannot achieve full-chain services in medical ethics, statistics, biological sample libraries, and data management. The existing clinical research data platform also has deficiencies in data research and analysis, multi-center collaboration, and data security sharing, making it difficult to intelligently regulate the inclusion and exclusion data of the disease library; hospitals need a platform that can fully support hospital / department management and doctor research needs. The platform should have the ability to collect, store, process, analyze, and share data securely to solve the current problems in clinical research data management. In the existing medical field, especially in the field of evidence-based medicine, there are very few guidelines, mainly because of the lack of data and platforms to support them. Therefore, it is particularly important to build a full-disease research management platform based on big data. Summary of the invention

[0003] The present invention provides a full-disease scientific research management platform and a control method thereof to solve the above problems:

[0004] The present invention proposes a full-disease scientific research management platform and a control method thereof, wherein the management platform comprises:

[0005] The push constraint module is used to obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the disease library constraint conditions, and obtain disease library category data;

[0006] Function management module, used for distributed storage of disease category data and classification management of multiple functional categories, obtaining category management data, and then obtaining management push data for each functional category;

[0007] The error adjustment module is used to calculate the data push error coefficient, judge the error data of the pushed data according to the data push error coefficient, adjust the preset constraint adjustment data according to the judgment result, and adjust the pushed error data.

[0008] Furthermore, the push constraint module includes:

[0009] A data acquisition module is used to acquire heterogeneous data from multiple preset sources through different data interfaces;

[0010] A format conversion module, used to obtain data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data;

[0011] A preprocessing module, used for preprocessing the conversion data to obtain preprocessed data;

[0012] A data integration module is used to integrate pre-processed data from multiple preset sources to obtain multi-source integrated data;

[0013] A data push module is used to obtain preset disease library category information, push each disease library category to the multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories;

[0014] The data constraint processing module is used to obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain multiple disease library category data after processing.

[0015] Furthermore, the data constraint processing module includes:

[0016] A condition acquisition module is used to acquire preset constraints of the disease library, wherein the preset constraints include inclusion conditions and exclusion conditions;

[0017] An inclusion module is used to obtain category push data of the disease database, extract inclusion data from the category push data according to preset constraints, obtain inclusion extraction data, and include the inclusion extraction data into the corresponding disease database;

[0018] An exclusion module is used to extract exclusion data from the category push data according to the exclusion conditions of the preset constraint conditions, obtain exclusion extraction data, and exclude the exclusion extraction data from the corresponding disease library;

[0019] An exclusion integration module is used to obtain the exclusion extraction data of the disease library, integrate the exclusion extraction data of all disease libraries, and obtain exclusion integration data;

[0020] Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing;

[0021] A new category establishment module is used to obtain exclusion extraction data that has been excluded at least twice, establish a new disease library category, incorporate the exclusion extraction data that has been excluded at least twice into the corresponding new disease library category, and obtain disease library category data.

[0022] Furthermore, the function management module includes:

[0023] A block storage module, used to perform distributed storage of the disease library category data through a blockchain method to obtain distributed storage data;

[0024] A classification management module, used to obtain a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function categories of the preset function module to obtain multiple category management data;

[0025] The authentication push module is used to classify and encrypt each preset function category to obtain category encryption information;

[0026] The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

[0027] Furthermore, the error adjustment module includes:

[0028] An error calculation module is used to obtain category push data and combine it with re-push data to calculate the data push error coefficient;

[0029] An error comparison module, used to compare the data push error coefficient with a preset error threshold to obtain a push error comparison result;

[0030] A push error determination module, used to perform data push determination according to the push error comparison result, and obtain data push determination information;

[0031] The parameter push adjustment module is used to adjust and update the parameters of the preset constraint conditions according to the data push determination information until the data push error coefficient is less than the preset error threshold.

[0032] Furthermore, the control method comprises:

[0033] S1. Obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the constraints of the disease database, and obtain category data of the disease database;

[0034] S2. Distribute and manage the disease database category data by multiple functional categories, obtain category management data, and then obtain management push data for each functional category;

[0035] S3. Calculate the data push error coefficient, determine the error data of the push data according to the data push error coefficient, adjust the preset constraint adjustment data according to the determination result, and adjust the push error data.

[0036] Further, the S1 includes:

[0037] Acquire heterogeneous data from multiple preset sources through different data interfaces;

[0038] Acquire data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data;

[0039] Preprocessing the converted data to obtain preprocessed data;

[0040] Integrate pre-processed data from multiple preset sources to obtain multi-source integrated data;

[0041] Acquire preset disease library category information, push each disease library category to multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories;

[0042] Obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain processed multiple disease library category data.

[0043] Furthermore, the acquisition of the disease library constraint conditions, performing data processing on each category of pushed data according to the disease library constraint conditions, and obtaining processed multiple disease library category data, includes:

[0044] Obtaining preset constraints of the disease database, wherein the preset constraints include inclusion conditions and exclusion conditions;

[0045] Obtain category push data of the disease database, extract the category push data according to preset constraints, obtain extracted data, and incorporate the extracted data into the corresponding disease database;

[0046] Perform exclusion data extraction on the category push data according to the exclusion condition of the preset constraint condition to obtain exclusion extracted data, and exclude the exclusion extracted data from the corresponding disease library;

[0047] Obtaining the exclusion extraction data of the disease database, integrating the exclusion extraction data of all disease databases, and obtaining exclusion integration data;

[0048] Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing;

[0049] Obtain the excluded extracted data that has been excluded at least twice, establish a new disease library category, incorporate the excluded extracted data that has been excluded at least twice into the corresponding new disease library category, and obtain the disease library category data.

[0050] Further, the S2 includes:

[0051] Distributed storage of the disease database category data is performed through a blockchain method to obtain distributed storage data;

[0052] Acquire a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function category of the preset function module to obtain multiple category management data;

[0053] Classify and encrypt each preset functional category to obtain category encryption information;

[0054] The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

[0055] Further, the S3 includes:

[0056] Obtain category push data and combine it with re-push data to calculate the data push error coefficient;

[0057] Compare the data push error coefficient with a preset error threshold to obtain a push error comparison result;

[0058] Performing data push determination according to the push error comparison result to obtain data push determination information;

[0059] The preset constraint conditions are parameter adjusted and updated according to the data push determination information until the data push error coefficient is less than the preset error threshold.

[0060] Beneficial effects of the present invention: The present invention proposes a scientific research management platform for all diseases and a control method thereof. The platform aims to establish an automatic data collection system for clinical research through informatization, integrate diagnosis and treatment, imaging, testing, medical expenses, follow-up and other data, and adopt cutting-edge technologies such as blockchain, big data, and artificial intelligence to achieve full-chain services in ethics, statistics, biological sample libraries, and data management, improve the operating efficiency of research wards, and gradually establish a mutual recognition mechanism for ethical review results between hospitals and within regions. The scientific research management platform for all diseases of the present invention includes multiple modules such as a data access engine unit, a blockchain-based data trusted circulation management unit, a subject management unit, a medical record management unit, a medical record authority management unit, a doctor's order management unit, a bed management unit, a drug management unit, an Internet of Things management unit, and data reports. These modules work together to achieve functions such as integration of hospital test data, generation of structured research electronic medical records, data ownership and trusted storage, improvement of data quality control level, real-time authentication of data access, encryption processing and transmission storage of data, auditing and penetrating supervision of data, and collaboration and sharing of multi-center data. The all-disease scientific research management platform and its control method proposed in the present invention are aimed at solving the problems existing in the current clinical scientific research data management, improving the service level and scientific research ability of hospitals, and promoting scientific and technological innovation and development in the medical field. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a schematic diagram of a control method for a full-disease scientific research management platform;

[0062] Figure 2 This is a partial process diagram of the management platform;

[0063] Figure 3 Schematic diagram of constraint conditions. DETAILED DESCRIPTION

[0064] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] In one embodiment of the present invention, a full-disease research management platform and a control method thereof are provided by the present invention, and the management platform comprises:

[0066] The push constraint module is used to obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the disease library constraint conditions, and obtain disease library category data;

[0067] Function management module, used for distributed storage of disease category data and classification management of multiple functional categories, obtaining category management data, and then obtaining management push data for each functional category;

[0068] The error adjustment module is used to calculate the data push error coefficient, judge the error data of the pushed data according to the data push error coefficient, adjust the preset constraint adjustment data according to the judgment result, and adjust the pushed error data.

[0069] The working principle of the above technical solution is as follows: heterogeneous data is obtained from different preset sources (such as hospital information systems, electronic medical records, clinical research databases, etc.). The data are format converted, preprocessed and integrated to eliminate format differences and data inconsistencies, and finally multi-source integrated data is obtained. The multi-source integrated data is pushed to different category libraries to obtain category push data. According to the constraints of the disease library (such as disease definition, diagnostic criteria, exclusion criteria, etc.), each category push data is included and excluded to screen out the disease library category data that meets the requirements of the disease library. The disease library category data is distributedly stored to improve the efficiency and reliability of data storage. The data is classified and managed according to multiple functional categories to obtain category management data. According to the classified management data, management push data for each functional category is generated. The error coefficient in the data push process is calculated to evaluate the accuracy of the push data. The error data of the push data is judged according to the error coefficient, and the preset constraint adjustment data is adjusted according to the judgment result. By adjusting the preset constraint adjustment data, the push error data is corrected and optimized to improve the accuracy and reliability of data push.

[0070] The technical effects of the above technical solutions are: through a unified format conversion, preprocessing and integration process, integrated data from multiple sources can be obtained quickly and accurately. The inclusion and exclusion of data according to the constraints of the disease library can ensure the accuracy and completeness of the disease library data. Distributed storage and classification management can improve the efficiency of data storage and processing. By calculating the data push error coefficient, the error data in the push process can be discovered and corrected in time, improving the accuracy and reliability of data push. The adjustment of preset constraint adjustment data can further optimize the data push process and reduce the generation of error data. The management push data provided by the platform can provide comprehensive and accurate data support for scientific researchers. Through the data analysis and mining functions of the platform, scientific researchers can deeply explore the potential laws and associations in the data, providing more powerful support for all disease research.

[0071] In one embodiment of the present invention, the push constraint module includes:

[0072] A data acquisition module is used to acquire heterogeneous data from multiple preset sources through different data interfaces;

[0073] A format conversion module, used to obtain data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data;

[0074] A preprocessing module, used for preprocessing the conversion data to obtain preprocessed data;

[0075] A data integration module is used to integrate pre-processed data from multiple preset sources to obtain multi-source integrated data;

[0076] A data push module is used to obtain preset disease library category information, push each disease library category to the multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories;

[0077] The data constraint processing module is used to obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain multiple disease library category data after processing.

[0078] The working principle of the above technical solution is: through different data interfaces, heterogeneous data is obtained from multiple preset data sources. These data sources may include hospital information systems, public health databases, scientific research data platforms, etc. Heterogeneous data refers to data from different systems and different formats. These data may have different data structures, data types and data formats when they are obtained. It is necessary to convert the obtained multiple data formats into a preset unified data format. The conversion process may involve operations such as data parsing, data mapping, and data encoding to ensure that the converted data meets the requirements of subsequent processing. The converted data may contain missing values, outliers, duplicate values, and other problems. These problems will be processed in the data cleaning stage to improve the quality and accuracy of the data. Cleaning operations may include filling missing values, deleting duplicate values, correcting outliers, etc. The data needs to be standardized and normalized. Standardization is to scale the data to a similar range, while normalization is to scale the data to a fixed range. The preprocessed data comes from multiple different data sources, and these data need to be merged into a unified data set. Data merging may involve operations such as database join operations and data table merging. During the data merging process, data consistency check is required to ensure that the merged data is logically consistent. This may include data redundancy detection, data value conflict detection and processing, and other operations. According to business needs, obtain the preset disease library category information. This information may include the name, classification, and coding of the disease. According to the preset disease library category information, push the multi-source integrated data for each disease library category. This means that the relevant data is classified according to the disease library category and pushed to the corresponding disease library for storage and management. Before processing the disease library data, it is necessary to obtain the constraints of the disease library. These constraints may include data integrity constraints, data validity constraints, etc. According to the constraints of the disease library, process the data pushed for each category. The processing operations may include data verification, data conversion, data format adjustment, etc. to ensure that the data meets the requirements of the disease library.

[0079] The technical effect of the above technical solution is: heterogeneous data from multiple preset sources are obtained through different data interfaces, realizing cross-system and cross-platform data integration. The conversion of data formats ensures that data from different sources can be processed uniformly, improving the efficiency and accuracy of data processing. The converted data is preprocessed, such as cleaning, deduplication, format adjustment, etc., which effectively improves the quality and availability of the data. The preprocessing step reduces the noise and uncertainty in subsequent data analysis. The preprocessed data from multiple preset sources are integrated together to form a comprehensive and rich data set. Multi-source integrated data provides more comprehensive and accurate information support for researchers, clinicians and decision makers, allowing them to make more scientific decisions. According to the preset disease library category information, the multi-source integrated data is accurately pushed to ensure that each disease library category can obtain relevant data. The category push data provides strong data support for the update and maintenance of the disease library, which can improve the accuracy and practicality of the disease library. Obtaining the disease library constraints and processing the category push data according to these conditions ensures the accuracy and consistency of the data. The data processing steps follow strict constraints, reduce the possibility of data errors and anomalies, and improve the reliability of data processing. The processed data of multiple disease database categories provide rich data resources for the research of complex diseases. These data can support clinical decision-making, help doctors better understand the characteristics of the disease and the patient's condition, and thus formulate more personalized treatment plans. The data integration and processing process described in this method has significant technical effects in terms of efficient integration of heterogeneous data, improvement of data quality, enhanced decision support of multi-source integrated data, accurate push of disease database category data, ensuring data accuracy, and support for complex disease research and clinical decision-making.

[0080] In one embodiment of the present invention, the data constraint processing module includes:

[0081] A condition acquisition module is used to acquire preset constraints of the disease library, wherein the preset constraints include inclusion conditions and exclusion conditions;

[0082] An inclusion module is used to obtain category push data of the disease database, extract inclusion data from the category push data according to preset constraints, obtain inclusion extraction data, and include the inclusion extraction data into the corresponding disease database;

[0083] An exclusion module is used to extract exclusion data from the category push data according to the exclusion conditions of the preset constraint conditions, obtain exclusion extraction data, and exclude the exclusion extraction data from the corresponding disease library;

[0084] An exclusion integration module is used to obtain the exclusion extraction data of the disease library, integrate the exclusion extraction data of all disease libraries, and obtain exclusion integration data;

[0085] Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing;

[0086] A new category establishment module is used to obtain exclusion extraction data that has been excluded at least twice, establish a new disease library category, incorporate the exclusion extraction data that has been excluded at least twice into the corresponding new disease library category, and obtain disease library category data.

[0087] The working principle of the above technical solution is as follows: the preset constraints of each disease library are obtained. These constraints usually include inclusion conditions and exclusion conditions, which are used to determine which data should be included in the disease library and which data should be excluded. The system obtains the category push data of each disease library. These data are pushed from the multi-source integrated data according to the previous steps and are related to a specific disease library. The system screens the category push data according to the preset inclusion conditions, extracts the data that meets the inclusion conditions (inclusion extraction data), and includes these data in the corresponding disease library. The system also screens the category push data according to the preset exclusion conditions, extracts the data that meets the exclusion conditions (exclusion extraction data), and excludes these data from the corresponding disease library. The system obtains the exclusion extraction data of all disease libraries and integrates these data together to form exclusion integration data. The exclusion integration data may contain some valuable data that does not meet the constraints of the current disease library. In order to make full use of these data, the system re-pushes them, that is, re-evaluates whether these data should be included in other disease libraries according to new conditions or rules. During the re-pushing process, the system identifies the exclusion extraction data that has been excluded at least twice. These data may represent a new or under-recognized disease type. The system creates new disease library categories based on these data and incorporates these excluded extracted data that have been excluded at least twice into the corresponding new disease library categories.

[0088] The platform can integrate heterogeneous data from different medical information systems (such as HIS, LIS, PACS, etc.), and automatically identify and correct errors, duplications or missing items in the data through intelligent cleaning algorithms to ensure the accuracy and completeness of scientific research data.

[0089] Data trusted circulation framework based on blockchain:

[0090] By using blockchain technology, we can achieve distributed storage, non-tamperability, transparency and traceability of scientific research data, and ensure the security and credibility of data during collection, transmission, storage and sharing. At the same time, we can establish a data transaction and authorization mechanism to promote the efficient circulation of data under the premise of legality and compliance.

[0091] Full-chain scientific research management functional modules:

[0092] The platform covers multiple modules including ethical review, statistical analysis, biobank management, and data management, forming a full-chain scientific research management process from project establishment, data collection, analysis and processing to results release, thereby improving scientific research efficiency and project management level.

[0093] Artificial Intelligence Assisted Decision Support:

[0094] By integrating AI technologies such as natural language processing and machine learning, it conducts in-depth mining and analysis of massive scientific research data, provides researchers with intelligent suggestions in areas such as disease prediction, treatment plan optimization, and drug development, and accelerates the transformation and application of scientific research results.

[0095] Multi-center collaborative research platform:

[0096] Support cross-institutional and cross-regional multi-center scientific research cooperation, achieve seamless connection and sharing of data through unified data standards and interfaces, and promote the optimal allocation of scientific research resources and collaborative innovation.

[0097] Highly customized user interface and permission management:

[0098] According to the needs of different user roles (such as scientific researchers, ethics reviewers, data managers, etc.), highly customized operation interfaces and permission settings are provided to ensure secure access to and efficient use of information.

[0099] The information of the disease databases created and participated by users is displayed in the form of cards, including: the name of the disease database, the number of patients, the number of scientific research projects created with the disease database as the data source, the creator, and the creation time. When the mouse moves into the corresponding disease database card, the operation buttons "Rename, Manage Team, Set, Delete" are displayed. Click the card to enter the disease database details page. You can enter the disease database name to search.

[0100] Rename: You can rename the disease database. The name of the disease database must be unique among all users.

[0101] Management team: The pop-up window of the management team displays the account, name, organization, role, mobile phone number and joining time of the team members, arranged in reverse order of joining time. When the disease database is created for the first time, the creator will be added to the team members by default. You can add, delete, and set roles for team members (roles and role permissions can be configured in [Backstage Management System] - [Role Management]). When adding new members, you can search for users by account or name, using an associative search method. A list of all users on the platform is displayed under the search box.

[0102] Settings: Displays the inclusion and exclusion conditions of the disease database, as well as the settings for pushing cases and the method of pushing cases into the database, such as Figure 3 shown.

[0103] Delete: A pop-up window will pop up for secondary confirmation when deleting. If there is a scientific research project created with this disease database as the data source, the disease database cannot be deleted.

[0104] The technical effect of the above technical solution is: by screening the data according to the preset inclusion and exclusion conditions, it can be ensured that only the data that meets the requirements of the specific disease library is included, thereby improving the accuracy and reliability of the data. Excluding the re-push of integrated data and the establishment of new disease library categories can discover and identify new disease types or under-recognized diseases, thereby optimizing the management and update of the disease library. Automated data processing processes (such as data screening, data integration, data re-push, etc.) can significantly improve the efficiency of data processing and reduce manual intervention and errors. More accurate and comprehensive disease library data can provide strong support for clinical decision-making and help doctors better understand the patient's disease condition. By discovering and establishing new disease library categories, it can promote research and development in the medical field and provide data support for the exploration of new disease diagnosis and treatment methods. Through sophisticated data processing and management, the accuracy and completeness of disease library data are improved.

[0105] Improve the quality of scientific research data: Through intelligent cleaning and multi-source data integration, ensure the accuracy, completeness and consistency of scientific research data, and provide a solid foundation for high-quality scientific research.

[0106] Enhance data security and credibility: Use blockchain technology to establish a trusted data circulation mechanism, protect patient privacy, prevent data leakage and tampering, and enhance the credibility and credibility of scientific research data.

[0107] Accelerate the transformation of scientific research results: Through artificial intelligence-assisted decision support, shorten the scientific research cycle, improve scientific research efficiency, accelerate the clinical application and transformation of scientific research results, and promote medical progress.

[0108] Promote scientific research cooperation and exchanges: Build a multi-center collaborative research platform, break down regional and institutional barriers, promote the sharing of scientific research resources and complementary advantages, and improve the overall scientific research level and innovation capabilities.

[0109] Optimize scientific research management processes: realize the full life cycle management of scientific research projects, from project establishment to results release, and standardize and streamline each step to improve the standardization and efficiency of scientific research management.

[0110] In one embodiment of the present invention, the function management module includes:

[0111] A block storage module, used to perform distributed storage of the disease library category data through a blockchain method to obtain distributed storage data;

[0112] A classification management module, used to obtain a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function categories of the preset function module to obtain multiple category management data;

[0113] The preset functional modules include a data access engine unit, a blockchain-based data trusted circulation management unit, a subject management unit, a medical record management unit, a medical record authority management unit, a medical order management unit, a bed management unit, a drug management unit, an IoT management unit, and data reports, etc.;

[0114] The preset functional categories include ethical review, statistical analysis, biobank management and data management, etc.;

[0115] The authentication push module is used to classify and encrypt each preset function category to obtain category encryption information;

[0116] The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

[0117] The working principle of the above technical solution is: using blockchain technology to store the disease library category data in a distributed manner. The distributed nature of blockchain ensures the security and immutability of data, while improving the reliability and availability of data. The process of distributed storage of data involves sharding and encrypting the data, and storing and verifying it on multiple nodes in the blockchain network. The system obtains preset functional modules, which include a data access engine unit, a blockchain-based data trusted circulation management unit, a subject management unit, a medical record management unit, a medical record authority management unit, a medical order management unit, a bed management unit, a drug management unit, an Internet of Things management unit, and data reports. According to the preset functional categories of these preset functional modules (such as ethical review, statistical analysis, biobank management, and data management, etc.), the distributed storage data is classified and managed. This means that the relevant data is assigned to the corresponding functional modules for processing and storage. In order to ensure the security and privacy of the data, the system classifies and encrypts each preset functional category and generates category encryption information. These encrypted information are used to protect the confidentiality of the data and prevent unauthorized access. When it is necessary to access or process data of a specific category, the system obtains the corresponding category decryption information and uses this information to decrypt the encrypted data to obtain data that can be used for management push. Based on the category decryption information, the system pushes the corresponding category management data to the corresponding functional module to obtain management push data for each functional category. After decryption and classification, these data can be used to support various medical management, research and analysis activities.

[0118] The technical effect of the above technical solution is: through the distributed storage and classified encryption technology of blockchain, the security and privacy of data are ensured. Even if the data is stored on multiple nodes, unauthorized access and tampering can be prevented. The introduction of preset function modules and preset function categories enables data to be classified and managed according to specific business needs, improving the efficiency and accuracy of data processing. The classified encryption and decryption mechanism enables data to be flexibly accessed and processed when needed while maintaining the confidentiality of the data. This can support various medical activities, such as statistical analysis, ethical review, etc. The blockchain-based data trusted circulation management unit supports the sharing and circulation of data between different medical institutions or research teams, which can promote the integration and utilization of medical data. Efficient and secure data management provides strong support for medical decision-making and research. Doctors and researchers can access and use relevant data more conveniently, so as to make more accurate diagnoses and formulate more effective treatment plans. The distributed storage and classified management of disease library category data through blockchain methods not only improves the security and privacy protection level of data, but also promotes data sharing and circulation.

[0119] In one embodiment of the present invention, the error adjustment module includes:

[0120] An error calculation module is used to obtain category push data and combine it with re-push data to calculate the data push error coefficient;

[0121] The calculation formula of the data push error coefficient is:

[0122]

[0123] Among them, TC is the data push error coefficient, n is the total number of category push data, D it Push the initial value of data for the i-th category, D ir is the value of the i-th category data after re-pushing, ∈ is a small positive number used to avoid the situation where the denominator is zero, and can be regarded as a smoothing term. In practical applications, the value of ∈ can be set according to the specific situation of the data, PC is the total number of data exclusions, and TS is the total number of data pushes;

[0124] An error comparison module, used to compare the data push error coefficient with a preset error threshold to obtain a push error comparison result;

[0125] A push error determination module, used to perform data push determination according to the push error comparison result, and obtain data push determination information;

[0126] The parameter push adjustment module is used to adjust and update the parameters of the preset constraint conditions according to the data push determination information until the data push error coefficient is less than the preset error threshold.

[0127] The working principle of the above technical solution is: obtain category push data and re-push data. Category push data is data that is classified and managed based on preset functional modules and preset functional categories, while re-push data may be data that is re-evaluated and pushed under certain conditions. The system calculates the difference between the two sets of data, that is, the data push error. This error can be quantified by comparing the number, content or attributes of the same or related records in the two sets of data, thereby obtaining a data push error coefficient. This coefficient reflects the degree of inaccuracy or inconsistency in the data push process; the system compares the calculated data push error coefficient with the preset error threshold. The preset error threshold is a standard set according to business needs and data accuracy requirements, which is used to determine whether the data push error is within an acceptable range. According to the push error comparison result, the system makes a data push judgment. If the data push error coefficient is less than or equal to the preset error threshold, it is determined that the data push is accurate and no further adjustment is required. If the data push error coefficient is greater than the preset error threshold, it is determined that there is an error in the data push and adjustment is required. According to the data push judgment information, the system adjusts and updates the parameters of the preset constraint conditions. This may involve adjusting the strictness of the inclusion and exclusion conditions, modifying the data classification standards, or optimizing the data processing process. The adjusted constraint conditions are reapplied to the data push process to reduce the data push error. This process may be an iterative process, requiring repeated adjustment of the constraint conditions and recalculation of the data push error coefficient until the data push error coefficient is less than a preset error threshold.

[0128] The technical effect of the above technical solution is: by calculating the data push error coefficient and comparing it with the preset error threshold, the system can timely discover the inaccuracy or inconsistency in the data push process and make corresponding adjustments. This can improve the accuracy of data push and ensure the integrity and reliability of data. By adjusting and updating the parameters of the preset constraints, the system can gradually optimize the data push process and reduce the occurrence of errors. This can improve the efficiency and quality of data management and provide more powerful support for subsequent data analysis and application. The iterative data push judgment and constraint condition update process enables the system to adapt to different data environments and business demand changes. This can enhance the robustness and adaptability of the system and ensure that the system can operate stably and provide accurate data support under various circumstances. By continuously improving the data push process and improving the accuracy of data push, the system can promote the improvement of overall data quality. This can improve the accuracy and reliability of medical decision-making and research, and provide strong support for the development and progress of the medical industry. By calculating the data push error coefficient and comparing it with the preset error threshold, and adjusting and updating the constraints according to the comparison results, the system can continuously improve the accuracy and reliability of data push and provide strong data support for medical decision-making and research.

[0129] In one embodiment of the present invention, the control method includes:

[0130] S1. Obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the constraints of the disease database, and obtain category data of the disease database;

[0131] S2. Distribute and manage the disease database category data by multiple functional categories, obtain category management data, and then obtain management push data for each functional category;

[0132] S3, calculating the data push error coefficient, judging the error data of the push data according to the data push error coefficient, adjusting the preset constraint adjustment data according to the judgment result, and adjusting the push error data, such as Figure 1 and 2 shown.

[0133] The working principle of the above technical solution is as follows: heterogeneous data is obtained from different preset sources (such as hospital information systems, electronic medical records, clinical research databases, etc.). The data are format converted, preprocessed and integrated to eliminate format differences and data inconsistencies, and finally multi-source integrated data is obtained. The multi-source integrated data is pushed to different category libraries to obtain category push data. According to the constraints of the disease library (such as disease definition, diagnostic criteria, exclusion criteria, etc.), each category push data is included and excluded to screen out the disease library category data that meets the requirements of the disease library. The disease library category data is distributedly stored to improve the efficiency and reliability of data storage. The data is classified and managed according to multiple functional categories to obtain category management data. According to the classified management data, management push data for each functional category is generated. The error coefficient in the data push process is calculated to evaluate the accuracy of the push data. The error data of the push data is judged according to the error coefficient, and the preset constraint adjustment data is adjusted according to the judgment result. By adjusting the preset constraint adjustment data, the push error data is corrected and optimized to improve the accuracy and reliability of data push.

[0134] The technical effects of the above technical solutions are: through a unified format conversion, preprocessing and integration process, integrated data from multiple sources can be obtained quickly and accurately. The inclusion and exclusion of data according to the constraints of the disease library can ensure the accuracy and completeness of the disease library data. Distributed storage and classification management can improve the efficiency of data storage and processing. By calculating the data push error coefficient, the error data in the push process can be discovered and corrected in time, improving the accuracy and reliability of data push. The adjustment of preset constraint adjustment data can further optimize the data push process and reduce the generation of error data. The management push data provided by the platform can provide comprehensive and accurate data support for scientific researchers. Through the data analysis and mining functions of the platform, scientific researchers can deeply explore the potential laws and associations in the data, providing more powerful support for all disease research.

[0135] In one embodiment of the present invention, the S1 includes:

[0136] Acquire heterogeneous data from multiple preset sources through different data interfaces;

[0137] Acquire data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data;

[0138] Preprocessing the converted data to obtain preprocessed data;

[0139] Integrate pre-processed data from multiple preset sources to obtain multi-source integrated data;

[0140] Acquire preset disease library category information, push each disease library category to multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories;

[0141] Obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain processed multiple disease library category data.

[0142] The working principle of the above technical solution is: through different data interfaces, heterogeneous data is obtained from multiple preset data sources. These data sources may include hospital information systems, public health databases, scientific research data platforms, etc. Heterogeneous data refers to data from different systems and different formats. These data may have different data structures, data types and data formats when they are obtained. It is necessary to convert the obtained multiple data formats into a preset unified data format. The conversion process may involve operations such as data parsing, data mapping, and data encoding to ensure that the converted data meets the requirements of subsequent processing. The converted data may contain missing values, outliers, duplicate values, and other problems. These problems will be processed in the data cleaning stage to improve the quality and accuracy of the data. Cleaning operations may include filling missing values, deleting duplicate values, correcting outliers, etc. The data needs to be standardized and normalized. Standardization is to scale the data to a similar range, while normalization is to scale the data to a fixed range. The preprocessed data comes from multiple different data sources, and these data need to be merged into a unified data set. Data merging may involve operations such as database join operations and data table merging. During the data merging process, data consistency check is required to ensure that the merged data is logically consistent. This may include data redundancy detection, data value conflict detection and processing, and other operations. According to business needs, obtain the preset disease library category information. This information may include the name, classification, and coding of the disease. According to the preset disease library category information, push the multi-source integrated data for each disease library category. This means that the relevant data is classified according to the disease library category and pushed to the corresponding disease library for storage and management. Before processing the disease library data, it is necessary to obtain the constraints of the disease library. These constraints may include data integrity constraints, data validity constraints, etc. According to the constraints of the disease library, process the data pushed for each category. The processing operations may include data verification, data conversion, data format adjustment, etc. to ensure that the data meets the requirements of the disease library.

[0143] The technical effect of the above technical solution is: heterogeneous data from multiple preset sources are obtained through different data interfaces, realizing cross-system and cross-platform data integration. The conversion of data formats ensures that data from different sources can be processed uniformly, improving the efficiency and accuracy of data processing. The converted data is preprocessed, such as cleaning, deduplication, format adjustment, etc., which effectively improves the quality and availability of the data. The preprocessing step reduces the noise and uncertainty in subsequent data analysis. The preprocessed data from multiple preset sources are integrated together to form a comprehensive and rich data set. Multi-source integrated data provides more comprehensive and accurate information support for researchers, clinicians and decision makers, allowing them to make more scientific decisions. According to the preset disease library category information, the multi-source integrated data is accurately pushed to ensure that each disease library category can obtain relevant data. The category push data provides strong data support for the update and maintenance of the disease library, which can improve the accuracy and practicality of the disease library. Obtaining the disease library constraints and processing the category push data according to these conditions ensures the accuracy and consistency of the data. The data processing steps follow strict constraints, reduce the possibility of data errors and anomalies, and improve the reliability of data processing. The processed data of multiple disease database categories provide rich data resources for the research of complex diseases. These data can support clinical decision-making, help doctors better understand the characteristics of the disease and the patient's condition, and thus formulate more personalized treatment plans. The data integration and processing process described in this method has significant technical effects in terms of efficient integration of heterogeneous data, improvement of data quality, enhanced decision support of multi-source integrated data, accurate push of disease database category data, ensuring data accuracy, and support for complex disease research and clinical decision-making.

[0144] In one embodiment of the present invention, the step of obtaining the disease library constraint conditions, performing data processing on each category of pushed data according to the disease library constraint conditions, and obtaining processed multiple disease library category data includes:

[0145] Obtaining preset constraints of the disease database, wherein the preset constraints include inclusion conditions and exclusion conditions;

[0146] Obtain category push data of the disease database, extract the category push data according to preset constraints, obtain extracted data, and incorporate the extracted data into the corresponding disease database;

[0147] Perform exclusion data extraction on the category push data according to the exclusion condition of the preset constraint condition to obtain exclusion extracted data, and exclude the exclusion extracted data from the corresponding disease library;

[0148] Obtaining the exclusion extraction data of the disease database, integrating the exclusion extraction data of all disease databases, and obtaining exclusion integration data;

[0149] Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing;

[0150] Obtain the excluded extracted data that has been excluded at least twice, establish a new disease library category, incorporate the excluded extracted data that has been excluded at least twice into the corresponding new disease library category, and obtain the disease library category data.

[0151] The working principle of the above technical solution is as follows: the preset constraints of each disease library are obtained. These constraints usually include inclusion conditions and exclusion conditions, which are used to determine which data should be included in the disease library and which data should be excluded. The system obtains the category push data of each disease library. These data are pushed from the multi-source integrated data according to the previous steps and are related to a specific disease library. The system screens the category push data according to the preset inclusion conditions, extracts the data that meets the inclusion conditions (inclusion extraction data), and includes these data in the corresponding disease library. The system also screens the category push data according to the preset exclusion conditions, extracts the data that meets the exclusion conditions (exclusion extraction data), and excludes these data from the corresponding disease library. The system obtains the exclusion extraction data of all disease libraries and integrates these data together to form exclusion integration data. The exclusion integration data may contain some valuable data that does not meet the constraints of the current disease library. In order to make full use of these data, the system re-pushes them, that is, re-evaluates whether these data should be included in other disease libraries according to new conditions or rules. During the re-pushing process, the system identifies the exclusion extraction data that has been excluded at least twice. These data may represent a new or under-recognized disease type. The system creates new disease library categories based on these data and incorporates these excluded extracted data that have been excluded at least twice into the corresponding new disease library categories.

[0152] The technical effect of the above technical solution is: by screening the data through preset inclusion and exclusion conditions, it can be ensured that only data that meets the requirements of a specific disease library is included, thereby improving the accuracy and reliability of the data. Excluding the re-push of integrated data and the establishment of new disease library categories can discover and identify new disease types or under-recognized diseases, thereby optimizing the management and update of the disease library. Automated data processing processes (such as data screening, data integration, data re-push, etc.) can significantly improve the efficiency of data processing and reduce manual intervention and errors. More accurate and comprehensive disease library data can provide strong support for clinical decision-making and help doctors better understand the patient's disease condition.

[0153] By discovering and establishing new disease database categories, we can promote research and development in the medical field and provide data support for the exploration of new disease diagnosis and treatment methods. Through sophisticated data processing and management, the accuracy and completeness of disease database data are improved.

[0154] In one embodiment of the present invention, S2 includes:

[0155] Distributed storage of the disease database category data is performed through a blockchain method to obtain distributed storage data;

[0156] Acquire a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function category of the preset function module to obtain multiple category management data;

[0157] The preset functional modules include a data access engine unit, a blockchain-based data trusted circulation management unit, a subject management unit, a medical record management unit, a medical record authority management unit, a medical order management unit, a bed management unit, a drug management unit, an IoT management unit, and data reports, etc.;

[0158] The preset functional categories include ethical review, statistical analysis, biobank management and data management, etc.;

[0159] Classify and encrypt each preset functional category to obtain category encryption information;

[0160] The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

[0161] The working principle of the above technical solution is: using blockchain technology to store the disease library category data in a distributed manner. The distributed nature of blockchain ensures the security and immutability of data, while improving the reliability and availability of data. The process of distributed storage of data involves sharding and encrypting the data, and storing and verifying it on multiple nodes in the blockchain network. The system obtains preset functional modules, which include a data access engine unit, a blockchain-based data trusted circulation management unit, a subject management unit, a medical record management unit, a medical record authority management unit, a medical order management unit, a bed management unit, a drug management unit, an Internet of Things management unit, and data reports. According to the preset functional categories of these preset functional modules (such as ethical review, statistical analysis, biobank management, and data management, etc.), the distributed storage data is classified and managed. This means that the relevant data is assigned to the corresponding functional modules for processing and storage. In order to ensure the security and privacy of the data, the system classifies and encrypts each preset functional category and generates category encryption information. These encrypted information are used to protect the confidentiality of the data and prevent unauthorized access. When it is necessary to access or process data of a specific category, the system obtains the corresponding category decryption information and uses this information to decrypt the encrypted data to obtain data that can be used for management push. Based on the category decryption information, the system pushes the corresponding category management data to the corresponding functional module to obtain management push data for each functional category. After decryption and classification, these data can be used to support various medical management, research and analysis activities.

[0162] The technical effect of the above technical solution is: through the distributed storage and classified encryption technology of blockchain, the security and privacy of data are ensured. Even if the data is stored on multiple nodes, unauthorized access and tampering can be prevented. The introduction of preset function modules and preset function categories enables data to be classified and managed according to specific business needs, improving the efficiency and accuracy of data processing. The classified encryption and decryption mechanism enables data to be flexibly accessed and processed when needed while maintaining the confidentiality of the data. This can support various medical activities, such as statistical analysis, ethical review, etc. The blockchain-based data trusted circulation management unit supports the sharing and circulation of data between different medical institutions or research teams, which can promote the integration and utilization of medical data. Efficient and secure data management provides strong support for medical decision-making and research. Doctors and researchers can access and use relevant data more conveniently, so as to make more accurate diagnoses and formulate more effective treatment plans. The distributed storage and classified management of disease library category data through blockchain methods not only improves the security and privacy protection level of data, but also promotes data sharing and circulation.

[0163] In one embodiment of the present invention, S3 includes:

[0164] Obtain category push data and combine it with re-push data to calculate the data push error coefficient;

[0165] The calculation formula of the data push error coefficient is:

[0166]

[0167] Among them, TC is the data push error coefficient, n is the total number of category push data, D it Push the initial value of data for the i-th category, D ir is the value of the i-th category data after re-pushing, ∈ is a small positive number used to avoid the situation where the denominator is zero, and can be regarded as a smoothing term. In practical applications, the value of ∈ can be set according to the specific situation of the data, PC is the total number of data exclusions, and TS is the total number of data pushes;

[0168] Compare the data push error coefficient with a preset error threshold to obtain a push error comparison result;

[0169] Performing data push determination according to the push error comparison result to obtain data push determination information;

[0170] The preset constraint conditions are parameter adjusted and updated according to the data push determination information until the data push error coefficient is less than the preset error threshold.

[0171] The working principle of the above technical solution is: obtain category push data and re-push data. Category push data is data that is classified and managed based on preset functional modules and preset functional categories, while re-push data may be data that is re-evaluated and pushed under certain conditions. The system calculates the difference between the two sets of data, that is, the data push error. This error can be quantified by comparing the number, content or attributes of the same or related records in the two sets of data, thereby obtaining a data push error coefficient. This coefficient reflects the degree of inaccuracy or inconsistency in the data push process; the system compares the calculated data push error coefficient with the preset error threshold. The preset error threshold is a standard set according to business needs and data accuracy requirements, which is used to determine whether the data push error is within an acceptable range. According to the push error comparison result, the system makes a data push judgment. If the data push error coefficient is less than or equal to the preset error threshold, it is determined that the data push is accurate and no further adjustment is required. If the data push error coefficient is greater than the preset error threshold, it is determined that there is an error in the data push and adjustment is required. According to the data push judgment information, the system adjusts and updates the parameters of the preset constraint conditions. This may involve adjusting the strictness of the inclusion and exclusion conditions, modifying the data classification standards, or optimizing the data processing process. The adjusted constraint conditions are reapplied to the data push process to reduce the data push error. This process may be an iterative process, requiring repeated adjustment of the constraint conditions and recalculation of the data push error coefficient until the data push error coefficient is less than a preset error threshold.

[0172] The technical effect of the above technical solution is: by calculating the data push error coefficient and comparing it with the preset error threshold, the system can timely discover the inaccuracy or inconsistency in the data push process and make corresponding adjustments. This can improve the accuracy of data push and ensure the integrity and reliability of data. By adjusting and updating the parameters of the preset constraints, the system can gradually optimize the data push process and reduce the occurrence of errors. This can improve the efficiency and quality of data management and provide more powerful support for subsequent data analysis and application. The iterative data push judgment and constraint condition update process enables the system to adapt to different data environments and business demand changes. This can enhance the robustness and adaptability of the system and ensure that the system can operate stably and provide accurate data support under various circumstances. By continuously improving the data push process and improving the accuracy of data push, the system can promote the improvement of overall data quality. This can improve the accuracy and reliability of medical decision-making and research, and provide strong support for the development and progress of the medical industry. By calculating the data push error coefficient and comparing it with the preset error threshold, and adjusting and updating the constraints according to the comparison results, the system can continuously improve the accuracy and reliability of data push and provide strong data support for medical decision-making and research.

[0173] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A full-disease research management platform, characterized by: The management platform includes: The push constraint module is used to obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the disease library constraint conditions, and obtain disease library category data; Function management module, used for distributed storage of disease category data and classification management of multiple functional categories, obtaining category management data, and then obtaining management push data for each functional category; The error adjustment module is used to calculate the data push error coefficient, judge the error data of the pushed data according to the data push error coefficient, adjust the preset constraint adjustment data according to the judgment result, and adjust the pushed error data.

2. According to claim 1, a full-disease scientific research management platform is characterized in that: The push constraint module includes: A data acquisition module is used to acquire heterogeneous data from multiple preset sources through different data interfaces; A format conversion module, used to obtain data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data; A preprocessing module, used for preprocessing the conversion data to obtain preprocessed data; A data integration module is used to integrate pre-processed data from multiple preset sources to obtain multi-source integrated data; A data push module is used to obtain preset disease library category information, push each disease library category to the multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories; The data constraint processing module is used to obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain multiple disease library category data after processing.

3. According to claim 1, a full-disease scientific research management platform is characterized in that: The data constraint processing module comprises: A condition acquisition module is used to acquire preset constraints of the disease library, wherein the preset constraints include inclusion conditions and exclusion conditions; An inclusion module is used to obtain category push data of the disease database, extract inclusion data from the category push data according to preset constraints, obtain inclusion extraction data, and include the inclusion extraction data into the corresponding disease database; An exclusion module is used to extract exclusion data from the category push data according to the exclusion conditions of the preset constraint conditions, obtain exclusion extraction data, and exclude the exclusion extraction data from the corresponding disease library; An exclusion integration module is used to obtain the exclusion extraction data of the disease library, integrate the exclusion extraction data of all disease libraries, and obtain exclusion integration data; Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing; A new category establishment module is used to obtain exclusion extraction data that has been excluded at least twice, establish a new disease library category, incorporate the exclusion extraction data that has been excluded at least twice into the corresponding new disease library category, and obtain disease library category data.

4. According to claim 1, a full-disease research management platform is characterized in that: The function management module includes: A block storage module, used to perform distributed storage of the disease library category data through a blockchain method to obtain distributed storage data; A classification management module, used to obtain a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function categories of the preset function module to obtain multiple category management data; The authentication push module is used to classify and encrypt each preset function category to obtain category encryption information; The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

5. According to claim 1, a full-disease research management platform is characterized in that: The error adjustment module comprises: An error calculation module is used to obtain category push data and combine it with re-push data to calculate the data push error coefficient; An error comparison module, used to compare the data push error coefficient with a preset error threshold to obtain a push error comparison result; A push error determination module, used to perform data push determination according to the push error comparison result, and obtain data push determination information; The parameter push adjustment module is used to adjust and update the parameters of the preset constraint conditions according to the data push determination information until the data push error coefficient is less than the preset error threshold.

6. A control method for a full-disease scientific research management platform, characterized in that: The control method comprises: S1. Obtain heterogeneous data from multiple preset sources, perform format conversion, preprocessing and integration, obtain multi-source integrated data, push data for multi-source integrated data, obtain category push data, include and exclude each category push data according to the constraints of the disease database, and obtain category data of the disease database; S2. Distribute and manage the disease database category data by multiple functional categories, obtain category management data, and then obtain management push data for each functional category; S3. Calculate the data push error coefficient, determine the error data of the push data according to the data push error coefficient, adjust the preset constraint adjustment data according to the determination result, and adjust the push error data.

7. The control method of the all-disease scientific research management platform according to claim 6, characterized in that: The S1 includes: Acquire heterogeneous data from multiple preset sources through different data interfaces; Acquire data formats of heterogeneous data from multiple preset sources, convert the multiple data formats into a preset data format, and obtain converted data; Preprocessing the converted data to obtain preprocessed data; Integrate pre-processed data from multiple preset sources to obtain multi-source integrated data; Acquire preset disease library category information, push each disease library category to multi-source integrated data according to the preset disease library category information, and obtain category push data of multiple disease library categories; Obtain the disease library constraint conditions, perform data processing on each category of push data according to the disease library constraint conditions, and obtain processed multiple disease library category data.

8. The control method of the all-disease scientific research management platform according to claim 6, characterized in that: The obtaining of the disease database constraint conditions, performing data processing on each category of push data according to the disease database constraint conditions, and obtaining processed multiple disease database category data, includes: Obtaining preset constraints of the disease database, wherein the preset constraints include inclusion conditions and exclusion conditions; Obtain category push data of the disease database, extract the category push data according to preset constraints, obtain extracted data, and incorporate the extracted data into the corresponding disease database; Perform exclusion data extraction on the category push data according to the exclusion condition of the preset constraint condition to obtain exclusion extracted data, and exclude the exclusion extracted data from the corresponding disease library; Obtaining the exclusion extraction data of the disease database, integrating the exclusion extraction data of all disease databases, and obtaining exclusion integration data; Re-pushing the excluded integrated data to obtain the excluded integrated data after re-pushing; Obtain the excluded extracted data that has been excluded at least twice, establish a new disease library category, incorporate the excluded extracted data that has been excluded at least twice into the corresponding new disease library category, and obtain the disease library category data.

9. The control method of the all-disease scientific research management platform according to claim 6, characterized in that: The S2 includes: Distributed storage of the disease database category data is performed through a blockchain method to obtain distributed storage data; Acquire a preset function module, and perform classification management of multiple function categories on the distributed storage data according to the preset function category of the preset function module to obtain multiple category management data; Classify and encrypt each preset functional category to obtain category encryption information; The category decryption information of each preset functional category is obtained, and the corresponding category management data is pushed according to the category decryption information to obtain the management push data of each functional category.

10. The control method of the all-disease scientific research management platform according to claim 6, characterized in that: The S3 includes: Obtain category push data and combine it with re-push data to calculate the data push error coefficient; Compare the data push error coefficient with a preset error threshold to obtain a push error comparison result; Performing data push determination according to the push error comparison result to obtain data push determination information; The parameters of the preset constraint conditions are adjusted and updated according to the data push determination information until the data push error coefficient is less than the preset error threshold.

Images