Medical data sharing privacy visualization method, device and equipment based on multi-party constraints

By performing multi-constrained privacy visualization processing on the medical data sharing platform, combining the needs of hospitals and researchers, privacy protection and effective data utilization are achieved, personalized sharing and privacy leakage in the existing technology are solved, and data is improved Shared security and utility.

CN118627124BActive Publication Date: 2024-12-03NAT UNIV OF DEFENSE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411089681.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-03
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

The existing medical data sharing technology has personalized problems in privacy protection, which makes it difficult for data owners to understand privacy settings, and the researchers' utility is unsatisfactory, which suppresses research cooperation enthusiasm and poses a risk of privacy leakage.

Method used

Using a multi-party constraint-based privacy visualization method, targeted desensitization is carried out by obtaining medical data and data setting information uploaded by the hospital, combining the researchers' data usage application and task preferences, and visually displaying it on the sharing platform. and approval process to ensure privacy protection and effective use of data.

Benefits of technology

It realizes privacy-aware personalized data sharing, allowing researchers to specify utility boundaries, and data owners can easily grasp privacy risks and desensitization benefits, and support the secure sharing of medical data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118627124B_ABST
    Figure CN118627124B_ABST
Patent Text Reader

Abstract

The present invention relates to a privacy visualization method, device and equipment for sharing medical data based on multi-party constraints. The method realizes privacy-perceivable and guaranteed medical information sharing with effective data utilization through the provision of medical data by hospitals, the customization of attribute importance by researchers, and the provision of professional desensitization services by sharing platforms. Compared with the prior art, a dedicated visualization sharing platform is designed to provide adaptive data desensitization, allowing researchers to specify utility boundaries and enabling data owners to easily and intuitively grasp privacy risks and desensitization benefits, so as to support the safe sharing of medical data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of medical data information sharing, and relates to a medical data sharing privacy visualization method, device and equipment based on multi-party constraints. Background Art

[0002] In the modern medical system, the sharing of medical information such as electronic medical records plays an important role. Medical information sharing improves the collaboration between medical staff, patients and other stakeholders, which is crucial to improving medical diagnosis, treatment decisions and patient experience. It also facilitates technical exchanges and case studies for medical researchers. However, there are also hidden dangers and risks of privacy leakage. The characteristics of diverse information types, large scale and public sharing make it easy for cyber attackers to obtain a large amount of user data, mine user privacy information, cause user privacy leakage, and threaten personal property and personal safety.

[0003] Based on the data privacy promises of current privacy-enhancing protocols, existing medical data sharing usually only desensitizes the data once, with a "one-size-fits-all" framework for all researchers to publish the same data. For data owners, such frameworks usually require cumbersome privacy settings, but only provide vague privacy feedback. For different researchers, the published data is context-agnostic and static for different analysis tasks. Such a framework makes the privacy of data owners difficult to understand and the utility of researchers unsatisfactory, thereby inhibiting the enthusiasm for research collaboration. The problem of privacy-preserving personalized data sharing has not yet been properly addressed. Summary of the invention

[0004] In response to the problems existing in the above-mentioned traditional methods, the present invention proposes a privacy visualization method for medical data sharing based on multi-party constraints, a privacy visualization device for medical data sharing based on multi-party constraints, and a computer device, which can effectively solve the problem of personalized data sharing with privacy protection.

[0005] In order to achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] On the one hand, a privacy visualization method for medical data sharing based on multi-party constraints is provided, comprising the steps of:

[0007] Obtain the medical data and data setting information that record patient attributes uploaded by the hospital; the data setting information includes the data validity period, visible scope and data description of the medical data;

[0008] Obtain data usage requests, attribute constraints, and task preferences issued by researchers when they are looking for suitable target medical data on the sharing platform;

[0009] Set preferences for target medical data based on task preferences and perform desensitization processing in accordance with privacy regulations based on attribute constraints;

[0010] Push the desensitized target medical data and data use application to the hospital of the target medical data owner and display them visually;

[0011] Obtain the application approval result given by the hospital after reviewing the target medical data before and after desensitization treatment;

[0012] Based on the application approval results, the target medical data agreed by the hospital will be pushed to the researchers or the researchers will be informed that the application has failed.

[0013] On the other hand, a medical data sharing privacy visualization device based on multi-party constraints is also provided, comprising:

[0014] The data acquisition module is used to acquire the medical data and data setting information that record the patient's attributes uploaded by the hospital; the data setting information includes the validity period, visible range and data description of the medical data;

[0015] The demand acquisition module is used to obtain data use applications, attribute constraints, and task preferences issued by researchers when they are looking for suitable target medical data on the sharing platform;

[0016] The preference desensitization module is used to set preferences for target medical data according to task preferences and perform desensitization processing in accordance with privacy regulations based on attribute constraints;

[0017] Visual push module, used to push the desensitized target medical data and data use application to the hospital of the target medical data owner and display them visually;

[0018] The approval acquisition module is used to obtain the application approval results given by the hospital after reviewing the target medical data before and after desensitization;

[0019] The data push module is used to push the target medical data agreed by the hospital to the researchers according to the application approval results or to inform the researchers that the application has failed.

[0020] On the other hand, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for privacy visualization of medical data sharing based on multi-party constraints are implemented.

[0021] One of the above technical solutions has the following advantages and beneficial effects:

[0022] The above-mentioned privacy visualization method, device and equipment for sharing medical data based on multi-party constraints are based on the patient's medical data, the hospital's professional knowledge restrictions, the researchers' utility demands and the constraints of the sharing platform. First, the medical data that records the patient's attributes uploaded by the hospital is obtained. The researchers find suitable target medical data on the sharing platform and then issue a data use application. The researchers browse the introduction information of the medical data on the sharing platform and customize the attribute constraints for the research objectives and set task preferences. The sharing platform satisfies the researchers' preferences and performs desensitization processing in accordance with privacy regulations. The desensitized target medical data is pushed to the hospital of the owner of the medical data and visualized. Subsequently, the hospital can view the relevant information of the medical data before and after the desensitization processing, agree or reject the relevant data use application, and finally, the sharing platform pushes the agreed target medical data to the researchers or informs the researchers that the application fails.

[0023] Through the provision of medical data by hospitals, researchers customize the importance of attributes, and the sharing platform provides professional desensitization services, privacy-aware and guaranteed medical information sharing with effective data usage is achieved. Compared with existing technologies, a dedicated visual sharing platform is designed to provide adaptive data desensitization, allowing researchers to specify utility boundaries and enabling data owners to easily and intuitively grasp privacy risks and desensitization benefits to support the secure sharing of medical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 It is a flowchart of a privacy visualization method for medical data sharing based on multi-party constraints in one embodiment;

[0026] Figure 2 A schematic diagram of the overall architecture of a privacy visualization method for medical data sharing based on multi-party constraints in one embodiment;

[0027] Figure 3 Schematic diagram of the module structure of a medical data sharing privacy visualization device based on multi-party constraints in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0029] It should be noted that the reference to "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The presentation of this phrase at various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It will be appreciated by those skilled in the art that the embodiments described herein may be combined with other embodiments. The term "and / or" used in the specification of the present invention and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0030] The following will describe the implementation of the present invention in detail with reference to the accompanying drawings in the embodiment diagram of the present invention.

[0031] In one embodiment, Figure 1 As shown, a privacy visualization method for medical data sharing based on multi-party constraints is provided, which may include the following processing steps S10 to S20:

[0032] S10, obtaining medical data and data setting information recording patient attributes uploaded by the hospital; the data setting information includes the data validity period, visible scope and data description of the medical data;

[0033] S12, obtains data usage applications, attribute constraints, and task preferences issued by researchers when they search for suitable target medical data on the sharing platform;

[0034] S14, setting preferences for target medical data according to task preferences and performing desensitization processing in accordance with privacy regulations according to attribute constraints;

[0035] S16, pushing the desensitized target medical data and data use application to the hospital of the target medical data owner and performing visual display;

[0036] S18, obtaining the application approval result given by the hospital after reviewing the target medical data before and after desensitization processing;

[0037] S20, based on the application approval result, pushes the target medical data agreed by the hospital to the researcher or informs the researcher that the application has failed.

[0038] It is understandable that in practical applications, the relevant constraints of patients' medical data, hospital expertise limitations, researchers' utility demands, and the privacy regulations of sharing platforms can be explained in advance. Among them, patients generate various types of medical data when they visit hospitals. These medical data record the patient's vital signs and contact information, and even sensitive information such as asset data and address. This information belongs to privacy protection content. Hospitals have the obligation to properly keep and not arbitrarily spread patient medical data. At the same time, researchers need to use high-quality patient medical data for data analysis to assist disease diagnosis and drug development. Medical staff who undertake data sharing tasks in hospitals usually lack professional knowledge related to privacy protection and need the assistance of sharing platforms. Researchers need task-specific high-quality medical data for scientific research, and sharing platforms that assist hospitals in publishing data need to follow privacy-related regulations. Therefore, when hospitals upload medical data to the sharing platform, they need to set the basic information of the data. Hospitals can upload the medical data that records patient attributes to the sharing platform through their hospital servers or clients.

[0039] like Figure 2 As shown in the figure, the overall architecture diagram of the privacy visualization method for medical data sharing based on multi-party constraints is shown, and the people on the left are researchers. Specifically, the hospital will upload the medical data that records the patient's vital signs and basic personal information to a trusted third-party sharing platform, or a sharing platform maintained and operated by the hospital itself, and set basic data setting information such as data validity period, visible range and data description. The sharing platform can automatically classify the attributes of medical data into classification or numerical types, and standardize the value range of each attribute of medical data, such as averaging missing values, etc., to standardize medical data and improve the usability and applicability of data. The sharing platform can display the data in the platform database within the validity period of the corresponding medical data according to the hospital's upload settings.

[0040] After researchers find suitable medical data as target medical data on the sharing platform, they can apply for data use: researchers can browse the introduction information of medical data on the sharing platform, customize attribute constraints for research objectives, and set task preferences; among them, the attribute constraints for research objectives are custom rankings of selected attributes constructed by researchers. The higher the ranking of an attribute, the more important it is in the researchers' opinion and the more necessary it is to maintain the original data distribution status.

[0041] Specifically, researchers can present their identity tokens to the sharing platform. After obtaining the corresponding sharing platform identity permissions, they can browse the valid medical data, view the attribute content, data size and data set introduction of the medical data, and initiate data use applications for the desired data within the identity permissions on the sharing platform. Researchers can browse the general introduction information of medical data through the sharing platform to further understand the data set. After browsing the complete attribute list of the data, researchers can check the required attributes and set the task type and utility loss limit.

[0042] Researchers can sort the selected attributes by importance according to their own task requirements and professional knowledge, and put the attributes they want to keep in their original state at the front of the list. At the same time, researchers can also use the importance sorting algorithm provided by the sharing platform to automatically sort. Researchers can also fill in the data application instructions and push them to the hospital through the sharing platform along with the data use application to assist the hospital in determining whether the data can be provided and improve the accuracy of data application and approval.

[0043] The sharing platform desensitizes the medical data to meet the researchers' preferences and comply with privacy regulations; the sharing platform pushes the desensitized target medical data to the hospital of the target medical data owner and displays it visually. Desensitization includes blurring and noise addition to the data, so that the processed data can maximize the degree of privacy protection while meeting the utility requirements as much as possible. The visualization provided by the sharing platform includes a visualized heat map of the privacy distribution of the data before and after desensitization, the specific desensitization process and noise addition distribution, and an explanation of the corresponding privacy content.

[0044] The sharing platform can reorganize medical data according to the attribute importance ranking set by researchers. Attributes with lower rankings will face more privacy violation instances and require more desensitization, resulting in greater changes in the distribution of attribute data. The sharing platform uses desensitization methods such as fuzzification and noise addition to desensitize medical data, searches for the best desensitization effect scheme that meets the researcher's utility constraints among many desensitization schemes, and implements desensitization on medical data.

[0045] The sharing platform can send data download reminders to the hospital of the medical data owner, and provide visualizations including heat maps of the privacy distribution of data before and after desensitization, the specific desensitization process, and noise distribution. The sharing platform will also explain to the hospital the corresponding privacy regulations and whether the data violates the privacy settings to help the hospital decide whether to agree to authorize the data release.

[0046] The hospital that owns the target medical data will review the relevant information of the medical data before and after the desensitization process, and agree or reject the application for the use of the relevant data; the sharing platform will push the agreed target medical data to the researcher who issued the application or inform the researcher that the application has failed. The researchers obtain the required medical data and can evaluate the data quality or reapply for the data after using the data. Among them, the hospital can agree or reject the data use request of the corresponding researcher after reviewing the desensitization visualization analysis and medical regulations and policy interpretation provided by the sharing platform. Only data authorized by the hospital will be released to the corresponding researchers.

[0047] The above-mentioned privacy visualization method for sharing medical data based on multi-party constraints is based on the patient's medical data, the hospital's professional knowledge restrictions, the researchers' utility demands and the constraints of the sharing platform. First, the medical data that records the patient's attributes uploaded by the hospital is obtained. The researchers find suitable target medical data on the sharing platform and then apply for data use. The researchers browse the introduction information of the medical data on the sharing platform and customize the attribute constraints for the research objectives and set task preferences. The sharing platform satisfies the researchers' preferences and performs desensitization processing in accordance with privacy regulations. The desensitized target medical data is pushed to the hospital of the medical data owner and visualized. Subsequently, the hospital can view the relevant information of the medical data before and after the desensitization processing, agree or reject the relevant data use application, and finally, the sharing platform pushes the agreed target medical data to the researchers or informs the researchers that the application fails.

[0048] Through the provision of medical data by hospitals, researchers customize the importance of attributes, and the sharing platform provides professional desensitization services, privacy-aware and guaranteed medical information sharing with effective data usage is achieved. Compared with existing technologies, a dedicated visual sharing platform is designed to provide adaptive data desensitization, allowing researchers to specify utility boundaries and enabling data owners to easily and intuitively grasp privacy risks and desensitization benefits to support the secure sharing of medical data.

[0049] In one embodiment, the process of pushing the target medical data agreed by the hospital to the researcher according to the application approval result in step S20 may specifically include the following processing:

[0050] Push the desensitized target medical data to the researcher's account and remind the researcher to download the data within the validity period;

[0051] Visualize the preliminary utility evaluation of the target medical data and the degree of attribute change during the desensitization process;

[0052] Get data quality ratings from researchers after using the data.

[0053] It is understandable that the hospital can view the visualization heat map of the privacy distribution of the data before and after desensitization, the specific desensitization process and noise distribution, and the interpretation of medical regulations provided by the sharing platform, and can also combine the data usage instructions filled in by the researchers to more accurately agree or reject the data requests of the corresponding researchers. After the sharing platform pushes the medical data agreed by the hospital to the researcher's account, the researcher can download the data within the validity period, view the preliminary utility evaluation of the data through the sharing platform, and fine-tune the subsequent training tasks according to the degree of change of the attributes in the desensitization process provided, and assist the researchers in adjusting the data analysis results. After using the data for medical research, the researchers can also score the utility of the data (i.e., data quality evaluation) within the specified time to assist other researchers in selecting data, guide hospitals to share more and higher-quality medical data, and improve the quality of data sharing.

[0054] In one embodiment, the process of informing the researcher of the application failure according to the application approval result in step S20 may specifically include the following processing:

[0055] Inform the researcher that the application has failed, and show the researcher the reason to further improve the application or inform the researcher to lower the utility expectations.

[0056] Understandably, if the hospital refuses to release the data, the sharing platform will inform the researchers and remind them to further improve the reasons for their application, or lower their utility expectations, etc., in order to reapply for the data.

[0057] In one embodiment, before the above step S18, the above medical data sharing privacy visualization method based on multi-party constraints may further include the following processing steps:

[0058] If the hospital fails to make an approval decision within the set time limit, it will be deemed that the hospital agrees by default and pushes the desensitized target medical data to the researcher's account.

[0059] It is understandable that if the hospital does not make a decision within the set time limit, the sharing platform will determine that the hospital agrees by default and push the desensitized data to the researcher's account to improve data sharing efficiency.

[0060] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps can be executed in other orders. Moreover, Figure 1At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0061] In one embodiment, Figure 3 As shown, a privacy visualization device 100 for sharing medical data based on multi-party constraints is provided, comprising a data acquisition module 11, a demand acquisition module 13, a preference desensitization module 15, a visualization push module 17, an approval acquisition module 19 and a data push module 21. Among them, the data acquisition module 11 is used to obtain medical data and data setting information that record patient attributes uploaded by the hospital; the data setting information includes the data validity period, visible range and data description of the medical data. The demand acquisition module 13 is used to obtain the data use application, attribute constraints and task preferences issued by researchers when they are looking for suitable target medical data on the sharing platform. The preference desensitization module 15 is used to set preferences for the target medical data according to the task preferences and perform desensitization processing in accordance with the privacy regulations according to the attribute constraints. The visualization push module 17 is used to push the target medical data and data use application after desensitization processing to the hospital of the target medical data owner and perform visual display. The approval acquisition module 19 is used to obtain the application approval result given by the hospital after checking the target medical data before and after the desensitization processing. The data push module 21 is used to push the target medical data agreed by the hospital to the researchers according to the application approval result or inform the researchers that the application failed.

[0062] The above-mentioned medical data sharing privacy visualization device 100 based on multi-party constraints, based on the patient's medical data, the hospital's professional knowledge restrictions, the researchers' utility demands and the constraints of the sharing platform, first obtains the medical data that records the patient's attributes uploaded by the hospital, and the researchers find suitable target medical data on the sharing platform and then issue a data use application. The researchers browse the introduction information of the medical data on the sharing platform and customize the attribute constraints for the research objectives and set task preferences; the sharing platform satisfies the researchers' preferences and performs desensitization processing in accordance with privacy regulations, and pushes the desensitized target medical data to the hospital of the medical data owner and displays it visually. Subsequently, the hospital can view the medical data-related information before and after the desensitization processing, agree or reject the relevant data use application, and finally, the sharing platform pushes the agreed target medical data to the researchers or informs the researchers that the application has failed.

[0063] Through the provision of medical data by hospitals, researchers customize the importance of attributes, and the sharing platform provides professional desensitization services, privacy-aware and guaranteed medical information sharing with effective data usage is achieved. Compared with existing technologies, a dedicated visual sharing platform is designed to provide adaptive data desensitization, allowing researchers to specify utility boundaries and enabling data owners to easily and intuitively grasp privacy risks and desensitization benefits to support the secure sharing of medical data.

[0064] In one embodiment, the data push module 21 pushes the target medical data agreed by the hospital to the researcher according to the application approval result, and is used to push the desensitized target medical data to the researcher's account and remind the researcher to download the data within the validity period; visualize the preliminary utility evaluation of the target medical data and the degree of change of the attributes during the desensitization process; and obtain the data quality evaluation given by the researcher after using the data.

[0065] In one embodiment, the data push module 21 is used to inform researchers of application failures in the process of informing researchers of application failures according to application approval results, and at the same time show researchers reasons for further improving the application or inform researchers to lower utility expectations.

[0066] In one embodiment, the medical data sharing privacy visualization device 100 based on multi-party constraints can also include a default approval module, which is used to determine that the hospital agrees by default and push the desensitized target medical data to the researcher's account when the hospital fails to make an approval decision within a set time limit.

[0067] For the specific limitations of the privacy visualization device for medical data sharing based on multi-party constraints, please refer to the limitations of the privacy visualization method for medical data sharing based on multi-party constraints above, which will not be repeated here. Each module in the above-mentioned privacy visualization device for medical data sharing based on multi-party constraints can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0068] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the following processing steps when executing the computer program: obtaining medical data and data setting information that record patient attributes uploaded by a hospital; the data setting information includes the data validity period, visible range and data description of the medical data; obtaining data use applications, attribute constraints and task preferences issued by researchers when searching for suitable target medical data on a sharing platform; setting preferences for the target medical data according to the task preferences and performing desensitization processing in accordance with privacy regulations according to the attribute constraints; pushing the desensitized target medical data and data use application to the hospital of the target medical data owner and displaying them visually; obtaining the application approval result given by the hospital after reviewing the target medical data before and after the desensitization processing; and pushing the target medical data agreed by the hospital to the researchers or informing the researchers of the application failure according to the application approval result.

[0069] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following processing steps are implemented: obtaining medical data and data setting information that record patient attributes uploaded by a hospital; the data setting information includes the data validity period, visible range and data description of the medical data; obtaining data use applications, attribute constraints and task preferences issued by researchers when searching for suitable target medical data on a sharing platform; setting preferences for the target medical data according to the task preferences and performing desensitization processing in accordance with privacy regulations according to the attribute constraints; pushing the desensitized target medical data and data use application to the hospital of the target medical data owner and displaying them visually; obtaining the application approval result given by the hospital after reviewing the target medical data before and after the desensitization processing; and pushing the target medical data agreed by the hospital to the researchers or informing the researchers of the application failure according to the application approval result.

[0070] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus dynamic random access memory (RambusDRAM, referred to as RDRAM) and interface dynamic random access memory (DRDRAM).

[0071] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of protection of the invention. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the attached claims.

Claims

1. A privacy visualization method for medical data sharing based on multi-party constraints, characterized by: Includes steps: Obtaining medical data and data setting information that record patient attributes uploaded by the hospital; the data setting information includes the data validity period, visible scope and data description of the medical data; Obtain data use applications, attribute constraints, and task preferences issued by researchers when they are looking for suitable target medical data on the sharing platform; the attribute constraints are custom rankings of selected attributes constructed by researchers, and researchers rank the selected attributes in importance based on their own task requirements and professional knowledge, and place the attributes they want to keep in their original state at the front of the list, or use the importance ranking algorithm provided by the sharing platform to automatically sort them; Setting preferences for the target medical data according to the task preferences and performing desensitization processing in accordance with privacy regulations according to the attribute constraints; The sharing platform reorganizes the medical data according to the attribute importance ranking set by the researchers, and the attributes with lower rankings undergo more desensitization processing; The target medical data and the data use application after desensitization are pushed to the hospital of the target medical data owner and visualized; the visualization includes a visualized heat map of the privacy distribution of the data before and after desensitization, the specific desensitization process and the noise distribution, wherein the data application instructions filled in by the researchers are also pushed to the hospital of the target medical data owner; Obtaining the application approval result given by the hospital after reviewing the target medical data before and after desensitization processing; According to the application approval result, the target medical data agreed by the hospital is pushed to the researcher or the researcher is informed that the application has failed.

2. The privacy visualization method for medical data sharing based on multi-party constraints according to claim 1 is characterized in that: The process of pushing the target medical data agreed by the hospital to the researcher according to the application approval result includes: Push the desensitized target medical data to the researcher's account and remind the researcher to download the data within the validity period; Visually display the preliminary utility evaluation of the target medical data and the degree of change of the attributes during the desensitization process; Get data quality ratings from researchers after using the data.

3. The privacy visualization method for medical data sharing based on multi-party constraints according to claim 1 is characterized in that: The process of informing researchers of application failures based on the application approval results includes: Inform the researcher that the application has failed, and show the researcher the reason to further improve the application or inform the researcher to lower the utility expectations.

4. The privacy visualization method for medical data sharing based on multi-party constraints according to claim 1 is characterized in that: Before the step of obtaining the application approval result given by the hospital after reviewing the target medical data before and after desensitization, it also includes: If the hospital fails to make an approval decision within the set time limit, it will be deemed that the hospital agrees by default and pushes the desensitized target medical data to the researcher's account.

5. A privacy visualization device for medical data sharing based on multi-party constraints, characterized in that: include: A data acquisition module is used to acquire medical data and data setting information that record patient attributes uploaded by the hospital; the data setting information includes the data validity period, visible range and data description of the medical data; The demand acquisition module is used to obtain data use applications, attribute constraints and task preferences issued by researchers when they are looking for suitable target medical data on the sharing platform; the attribute constraints are custom sorting of selected attributes constructed by researchers. Researchers sort the selected attributes by importance based on their own task requirements and professional knowledge, and put the attributes they want to keep in their original state at the front of the list, or use the importance sorting algorithm provided by the sharing platform to automatically sort them; A preference desensitization module, used to set preferences for the target medical data according to the task preferences and perform desensitization processing in accordance with privacy regulations according to the attribute constraints; The sharing platform reorganizes the medical data according to the attribute importance ranking set by the researchers, and the attributes with lower rankings undergo more desensitization processing; A visualization push module is used to push the target medical data and the data use application after desensitization to the hospital of the target medical data owner and perform visualization display; the visualization includes a visualization heat map of the privacy distribution of the data before and after desensitization, the specific desensitization process and the noise distribution, and the data application instructions filled in by the researchers are also pushed to the hospital of the target medical data owner; An approval acquisition module, used to obtain the application approval result given by the hospital after reviewing the target medical data before and after desensitization processing; The data push module is used to push the target medical data approved by the hospital to the researchers according to the application approval result or to inform the researchers that the application has failed.

6. The privacy visualization device for medical data sharing based on multi-party constraints according to claim 5 is characterized in that: The data push module pushes the target medical data agreed by the hospital to the researcher according to the application approval result, and is used to push the desensitized target medical data to the researcher's account and remind the researcher to download the data within the validity period; visualize the preliminary utility evaluation of the target medical data and the degree of change of the attributes during the desensitization process; and obtain the data quality evaluation given by the researcher after using the data.

7. The medical data sharing privacy visualization device based on multi-party constraints according to claim 5 is characterized in that: The data push module is used to inform the researcher of the application failure in the process of informing the researcher of the application failure according to the application approval result, and at the same time show the researcher the reasons for further improving the application or inform the researcher to lower the utility expectation.

8. The medical data sharing privacy visualization device based on multi-party constraints according to claim 5 is characterized in that: Also includes: The default approval module is used to determine that the hospital agrees by default and push the desensitized target medical data to the researcher's account when the hospital fails to make an approval decision within a set time limit.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the medical data sharing privacy visualization method based on multi-party constraints as described in any one of claims 1 to 4 are implemented.