Medical operation data privacy protection system and method

Abstract

The present invention discloses a medical operation data privacy protection system and method, which specifically relates to the field of data protection technology, including a data acquisition module, a medical privacy protection demand assessment module, an algorithm processing module and an algorithm optimization assessment module; monitor and collect information data generated during the user's medical process, and obtain the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established. Based on the monitoring and analysis of parameters such as information data generated during the user's medical process, the present invention evaluates whether the target data requires medical operation data privacy protection data optimization processing, and establishes a differential privacy-homomorphic encryption combined algorithm model for the required data, adds differential privacy noise in the homomorphic encryption state, and then constructs an algorithm optimization assessment model, generates privacy protection effect information and computing optimization information based on the algorithm model's processing of the data, and determines whether the algorithm model is applicable to the target data.

Description

Technical Field

[0001] The present invention relates to the field of data protection technology, and more specifically, to a medical operation data privacy protection system and method. Background Art

[0002] 020Medical operation data privacy protection refers to a system that protects operation data and user privacy in Online to Offline medical services. Its application areas include data transmission protection, data storage protection, data sharing and exchange, and access control and identity authentication. The specifically designed devices are mainly divided into three categories: encryption devices, identity authentication devices, and network security devices. Encryption devices include encryption hardware modules such as HSM (hardware security module) and secure USB drives. Authentication devices include smart cards and card readers for confirming the identity of medical personnel, as well as biometric devices for secure login. Network security devices include firewalls, intrusion detection systems (IDS), and intrusion prevention systems (IPS).

[0003] Compared with traditional methods, the 020 medical operation data privacy protection system has higher security, better data management, and can improve data sharing and collaboration. It has extremely high compliance and transparency, and can greatly promote medical technology innovation. However, the 020 medical operation data privacy protection system needs to have different response strategies when treating different patients, and it should be adjusted according to the degree of attention paid to personal privacy in different regions and countries. At the same time, when facing rarer and more harmful diseases, considering the overall human survival safety, the degree of protection of patient data privacy should be adjusted. How to decide on the intensity and direction of the adjustment is an important issue that the existing 020 medical operation data privacy protection system and methods should consider. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a medical operation data privacy protection system and method, which is based on the monitoring and analysis of parameters such as information data generated during the user's medical process, evaluates whether the target data requires medical operation data privacy protection data optimization processing, and establishes a differential privacy-homomorphic encryption combined algorithm model for the required data, adds differential privacy noise in the homomorphic encryption state, and then constructs an algorithm optimization evaluation model. According to the processing of the algorithm model on the data, it generates privacy protection effect information and computational optimization information, and determines whether the algorithm model is applicable to the target data.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for protecting privacy of medical operation data comprises the following steps:

[0007] Step S1, monitor and collect information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtain the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established;

[0008] Step S2, constructing a medical privacy protection demand assessment model, and determining the degree of medical operation data privacy protection required by the patient, and whether medical operation data privacy protection data optimization processing is required;

[0009] Step S3, for the target data that needs medical operation data privacy protection data optimization processing, establish a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise in the homomorphic encryption state;

[0010] Step S4, construct an algorithm optimization evaluation model, generate privacy protection effect information and calculation optimization information based on the algorithm model's processing of the data, and determine whether the algorithm model is applicable to the target data.

[0011] Specifically, in step S1, the existing O2O medical operation data privacy protection systems are diverse, ranging from mobile phone software for consulting medical conditions to live broadcasts and recordings of patient surgery video content, processing relevant information to achieve the dual goals of privacy protection and medical value conversion, thereby achieving the purpose of medical progress without infringing on patient privacy. In actual production, due to factors such as equipment cost and the necessity of real-time monitoring, the present invention is based on the premise of continuously monitoring patient information in the case that the existing medical operation data privacy protection system works for a long time and the operating environment is relatively stable, which may lead to abnormal privacy data protection at a certain monitoring moment.

[0012] In step S2, the user's data information is evaluated to confirm the classification of the user's privacy information that should be protected in the system. The specific process is to collect the user's medical privacy protection awareness information and privacy value information, where the privacy protection awareness information includes the patient's privacy protection coefficient, which is calibrated as H. yb The privacy value information includes the patient's disease abnormality coefficient and medical progress coefficient, which are marked as J hy and Y jz ;

[0013] The patient privacy protection coefficient is obtained by analyzing the patient's behavior and obtaining the number of privacy settings and data access times within a week, which are marked as Y sc and S fc , and count the number of privacy-related complaints from patients after each stage of treatment, denoted as T ys , then the patient privacy protection coefficient H yb =T ys ×(Y sc +Sfc );

[0014] The abnormal coefficient of the patient's disease is obtained by collecting the number of new cases of the patient's disease each year and calibrating it as B xm , the total population is labeled as R z , the total number of deaths and disabilities in the statistical cases, denoted as Z sc , then the patient's disease abnormality coefficient J hy =B xm ÷R z ×Z sc 2 ;

[0015] When the staged treatment is completed, the medical progress coefficient records the patient's physiological parameters, counts the abnormal physiological parameters before treatment, collects the physiological parameters after treatment, and calibrates them as C x , x is the project number, x=1,2,3...n, n is a positive integer, and the average value of the physiological parameter is Medical Progress Factor

[0016] The medical privacy protection demand assessment model is constructed by weighting the patient's privacy awareness information and privacy value information to generate the medical privacy protection demand assessment index YB pg , and the corresponding coefficients are respectively the patient privacy protection coefficient H yb , Patient disease abnormality coefficient J hy and the medical progress coefficient Y jz , the formula is YB pg =a1×H yb +a2×J hy -a3×Y jz ;

[0017] At the same time, a1, a2, and a3 are set according to actual conditions. For example, the expert empowerment method is adopted, that is, experts in related fields are invited to determine the weights of various indicators through professional opinion surveys and comprehensive evaluations to ensure that the weight coefficients can accurately reflect the importance of various indicators in the medical privacy protection needs assessment. In addition, various methods such as hierarchical analysis method and fuzzy comprehensive evaluation method can also be considered to determine the weight coefficients to ensure the objectivity and scientificity of the weight coefficients. I will not elaborate on this here.

[0018] In step S2, the medical privacy protection needs assessment index obtained in the medical privacy protection needs assessment model is used to reflect the degree of privacy protection of medical operation data required by the target patient. The larger its value is, the more attention the patient pays to medical privacy protection, the more specific the disease is and the more important the research is, and the greater the progress of the medical technology involved.

[0019] In step S2, when the medical privacy protection demand assessment index YB pg When it is greater than the set protection threshold, it means that the target patient needs a high degree of privacy protection for medical operation data, and a signal for strengthening medical privacy is sent, and the system is optimized for operation;

[0020] When the medical privacy protection needs assessment index YB pg When it is less than or equal to the set protection threshold, it means that the target patient needs a low level of privacy protection for medical operation data, and no medical privacy enhancement signal is sent. The existing medical operation data privacy protection system and method will continue to be used, and no subsequent steps will be taken.

[0021] In step S3, a differential privacy-homomorphic encryption combined algorithm model is constructed. Differential privacy controls the strength of privacy protection through the privacy budget. By adding noise to the query results, the existence or absence of any single record will not significantly affect the results, thereby preventing information leakage. Homomorphic encryption protects the calculation process and does not affect the noise processing process added by differential privacy. The combined algorithm makes data encryption more complete and comprehensive.

[0022] Furthermore, the construction method of the differential privacy-homomorphic encryption combined algorithm model of the present invention is as follows:

[0023] Step S3.1, after receiving the medical privacy enhancement signal, clean and format the patient data to remove erroneous or duplicate data and ensure data structure consistency;

[0024] Step S3.2, differential privacy implementation, using the Laplace mechanism to add noise, ensuring that the noise added to the query results has statistical properties and protects individual information. The formula for differential privacy is: Pr[f(D)=g]≤e ∈ Pr[f(D′)=g], where D and D′ are datasets with only one record different, ∈ is the privacy budget parameter, y is the query result, and the Laplace addition formula is: Δf is the sensitivity of the query function. Calculating the sensitivity of Δf can obtain the maximum impact of the change of any record in the data set on the query result.

[0025] Step S3.3, without decrypting the data, the calculation is performed using the encrypted data operation method. For example, the addition operation is: Enc(x)+Enc(y)=Enc(x+y). The total process after combining differential privacy and homomorphic encryption is:

[0026] The first step is to homomorphically encrypt the original data: Enc(D) = {Enc(d1), Enc(d2), ..., Enc(d n)}, the second step is to perform calculations on the encrypted data, such as the calculation of the query function f: Enc(f(D)) = f(Enc(D)), the third step is to add noise to the encrypted calculation result, calculate the sensitivity Δf, and generate Laplace noise And add it to the encrypted query result: The fourth step is to decrypt the encrypted calculation result and obtain the query result of differential privacy protection: f′(D)=Dec(Enc(f′(D))).

[0027] In step S4, an algorithm optimization evaluation model is constructed. The specific process is to collect privacy protection effect information and computational optimization information in the differential privacy-homomorphic encryption combined algorithm model, where the privacy protection effect information includes the privacy protection effect coefficient, calibrated as X yb , the calculation optimization information includes the calculation efficiency coefficient and the optimization strategy coefficient, which are marked as J xl and Y cl ;

[0028] The privacy protection effect coefficient is obtained by analyzing the privacy budget and key length in the algorithm model obtained in step S3. The privacy budget and key length determine the protection effect of differential privacy and homomorphic encryption respectively. The two are marked as Y ys and M cd ,in where Δf is the sensitivity of the query function, is the standard deviation of the added noise, then the privacy protection effect coefficient X yb =Y ys ×M cd ;

[0029] The computational efficiency coefficient is evaluated by computing time and resource consumption, and is expressed as i Indicates the encryption time of a single data item, T i Indicates the decryption time of a single data item, i is the data item number, i=1,2,3...v, v is a positive integer, then calculate the efficiency coefficient

[0030] The optimization strategy coefficient is calculated by collecting the cost of performing data privacy protection optimization, denoted as S cb , count the medical expenses that patients need to pay, denoted as F yl , then the optimization strategy coefficient Y c1 =F y1 ÷S cb ;

[0031] The algorithm optimization evaluation model is constructed by weighting the privacy protection effect information and computational optimization information in the algorithm model to generate the algorithm optimization evaluation index SY pg , and the corresponding coefficients are the privacy protection effect coefficient Xyb , calculate the efficiency coefficient J x1 and optimization strategy coefficient Y cl , the formula is SY pg =β1×X yb -β2×J x1 +β3×Y c1 ;

[0032] In step S4, the algorithm optimization evaluation index obtained in the algorithm optimization evaluation model is used to reflect the actual effect of the differential privacy-homomorphic encryption combined algorithm model. The higher the computational efficiency, the lower the economic cost.

[0033] In step S4, when the algorithm optimizes the evaluation index SY pg When it is greater than or equal to the set optimization threshold, it means that the differential privacy-homomorphic encryption combined algorithm model can provide high protection for the target medical privacy data, and the current algorithm model will continue to be used;

[0034] When the algorithm optimizes the evaluation index SY pg When it is less than the set optimization threshold, it means that the differential privacy-homomorphic encryption combined algorithm model fails to achieve the ideal protection effect on the target medical privacy data. The machine learning method is used to optimize the established algorithm model.

[0035] A medical operation data privacy protection system, used in the above-mentioned medical operation data privacy protection method, comprising:

[0036] The data collection module monitors and collects information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtains the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established;

[0037] Medical privacy protection demand assessment module: builds a medical privacy protection demand assessment model, and determines the degree of medical operation data privacy protection required by patients, and confirms whether medical operation data privacy protection data optimization processing is required;

[0038] The algorithm processing module establishes a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise under the homomorphic encryption state for target data that requires optimized processing of medical operation data privacy protection data;

[0039] The algorithm optimization and evaluation module builds an algorithm optimization and evaluation model, generates privacy protection effect information and computational optimization information based on the algorithm model's processing of data, and determines whether the algorithm model is applicable to the target data.

[0040] Technical effects and advantages of the present invention:

[0041] The present invention is based on the monitoring and analysis of parameters such as information data generated during the user's medical process, evaluates whether the target data requires medical operation data privacy protection data optimization processing, and establishes a differential privacy-homomorphic encryption combined algorithm model for the required data, adds differential privacy noise in the homomorphic encryption state, and then constructs an algorithm optimization evaluation model. According to the algorithm model's processing of the data, it generates privacy protection effect information and computational optimization information to determine whether the algorithm model is applicable to the target data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a medical operation data privacy protection method of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The present invention is a medical operation data privacy protection system and method. It is based on the monitoring and analysis of parameters such as information data generated during the user's medical process, evaluates whether the target data requires medical operation data privacy protection data optimization processing, and establishes a differential privacy-homomorphic encryption combined algorithm model for the required data, adds differential privacy noise in the homomorphic encryption state, and then constructs an algorithm optimization evaluation model. According to the processing of the algorithm model on the data, it generates privacy protection effect information and calculation optimization information, and determines whether the algorithm model is applicable to the target data.

[0045] Example 1

[0046] like Figure 1 As shown, a method for protecting privacy of medical operation data has the following steps:

[0047] Step S1, monitor and collect information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtain the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established;

[0048] Step S2, constructing a medical privacy protection demand assessment model, and determining the degree of medical operation data privacy protection required by the patient, and whether medical operation data privacy protection data optimization processing is required;

[0049] Step S3, for the target data that needs medical operation data privacy protection data optimization processing, establish a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise in the homomorphic encryption state;

[0050] Step S4, construct an algorithm optimization evaluation model, generate privacy protection effect information and calculation optimization information based on the algorithm model's processing of the data, and determine whether the algorithm model is applicable to the target data.

[0051] Specifically, in step S1, the existing O2O medical operation data privacy protection systems are diverse, ranging from mobile phone software for consulting medical conditions to live broadcasts and recordings of patient surgery video content, processing relevant information to achieve the dual goals of privacy protection and medical value conversion, thereby achieving the purpose of medical progress without infringing on patient privacy. In actual production, due to factors such as equipment cost and the necessity of real-time monitoring, the present invention is based on the premise of continuously monitoring patient information in the case that the existing medical operation data privacy protection system works for a long time and the operating environment is relatively stable, which may lead to abnormal privacy data protection at a certain monitoring moment.

[0052] In step S2, the user's data information is evaluated to confirm the classification of the user's privacy information that should be protected in the system. The specific process is to collect the user's medical privacy protection awareness information and privacy value information, where the privacy protection awareness information includes the patient's privacy protection coefficient, which is calibrated as H. yb The privacy value information includes the patient's disease abnormality coefficient and medical progress coefficient, which are marked as J hy and Y jz ;

[0053] The patient privacy protection coefficient is obtained by analyzing the patient's behavior and obtaining the number of privacy settings and data access times within a week, which are marked as Y sc and S fc , and count the number of privacy-related complaints from patients after each stage of treatment, denoted as T ys , then the patient privacy protection coefficient H yb =T ys ×(Y sc +S fc );

[0054] The abnormal coefficient of the patient's disease is obtained by collecting the number of new cases of the patient's disease each year and calibrating it as B xm , the total population is labeled as R z , the total number of deaths and disabilities in the statistical cases, denoted as Z sc , then the patient's disease abnormality coefficient J hy =B xm ÷R z ×Z sc 2 ;

[0055] When the staged treatment is completed, the medical progress coefficient records the patient's physiological parameters, counts the abnormal physiological parameters before treatment, collects the physiological parameters after treatment, and calibrates them as C x , x is the project number, x=1,2,3...n, n is a positive integer, and the average value of the physiological parameter is Medical Progress Factor

[0056] The medical privacy protection demand assessment model is constructed by weighting the patient's privacy awareness information and privacy value information to generate the medical privacy protection demand assessment index YB pg , and the corresponding coefficients are respectively the patient privacy protection coefficient H yb , Patient disease abnormality coefficient J hy and the medical progress coefficient Y jz , the formula is YB pg =a1×H yb +a2×J hy -a3×Y jz ;

[0057] At the same time, a1, a2, and a3 are set according to actual conditions. For example, the expert empowerment method is adopted, that is, experts in related fields are invited to determine the weights of various indicators through professional opinion surveys and comprehensive evaluations to ensure that the weight coefficients can accurately reflect the importance of various indicators in the medical privacy protection needs assessment. In addition, various methods such as hierarchical analysis method and fuzzy comprehensive evaluation method can also be considered to determine the weight coefficients to ensure the objectivity and scientificity of the weight coefficients. I will not elaborate on this here.

[0058] In step S2, the medical privacy protection needs assessment index obtained in the medical privacy protection needs assessment model is used to reflect the degree of privacy protection of medical operation data required by the target patient. The larger its value is, the more attention the patient pays to medical privacy protection, the more specific the disease is and the more important the research is, and the greater the progress of the medical technology involved.

[0059] In step S2, when the medical privacy protection demand assessment index YB pg When it is greater than the set protection threshold, it means that the target patient needs a high degree of privacy protection for medical operation data, and a signal for strengthening medical privacy is sent, and the system is optimized for operation;

[0060] When the medical privacy protection needs assessment index YB pg When it is less than or equal to the set protection threshold, it means that the target patient needs a low level of privacy protection for medical operation data, and no medical privacy enhancement signal is sent. The existing medical operation data privacy protection system and method will continue to be used, and no subsequent steps will be taken.

[0061] In step S3, a differential privacy-homomorphic encryption combined algorithm model is constructed. Differential privacy controls the strength of privacy protection through the privacy budget. By adding noise to the query results, the existence or absence of any single record will not significantly affect the results, thereby preventing information leakage. Homomorphic encryption protects the calculation process and does not affect the noise processing process added by differential privacy. The combined algorithm makes data encryption more complete and comprehensive.

[0062] Furthermore, the construction method of the differential privacy-homomorphic encryption combined algorithm model of the present invention is as follows:

[0063] Step S3.1, after receiving the medical privacy enhancement signal, clean and format the patient data to remove erroneous or duplicate data and ensure data structure consistency;

[0064] Step S3.2, differential privacy implementation, using the Laplace mechanism to add noise, ensuring that the noise added to the query results has statistical properties and protects individual information. The formula for differential privacy is: Pr[f(D)=g]≤e ∈ Pr[f(D′)=g], where D and D′ are datasets with only one record different, ∈ is the privacy budget parameter, y is the query result, and the Laplace addition formula is: Δf is the sensitivity of the query function. Calculating the sensitivity of Δf can obtain the maximum impact of the change of any record in the data set on the query result.

[0065] Step S3.3, without decrypting the data, the calculation is performed using the encrypted data operation method. For example, the addition operation is: Enc(x)+Enc(y)=Enc(x+y). The total process after combining differential privacy and homomorphic encryption is:

[0066] The first step is to homomorphically encrypt the original data: Enc(D) = {Enc(d1), Enc(d2), ..., Enc(d n )}, the second step is to perform calculations on the encrypted data, such as the calculation of the query function f: Enc(f(D)) = f(Enc(D)), the third step is to add noise to the encrypted calculation result, calculate the sensitivity Δf, and generate Laplace noise And add it to the encrypted query result: The fourth step is to decrypt the encrypted calculation result and obtain the query result of differential privacy protection: f′(D)=Dec(Enc(f′(D))).

[0067] In step S4, an algorithm optimization evaluation model is constructed. The specific process is to collect privacy protection effect information and computational optimization information in the differential privacy-homomorphic encryption combined algorithm model, where the privacy protection effect information includes the privacy protection effect coefficient, calibrated as Xyb , the calculation optimization information includes the calculation efficiency coefficient and the optimization strategy coefficient, which are marked as J xl and Y cl ;

[0068] The privacy protection effect coefficient is obtained by analyzing the privacy budget and key length in the algorithm model obtained in step S3. The privacy budget and key length determine the protection effect of differential privacy and homomorphic encryption respectively. The two are marked as Y ys and M cd ,in where Δf is the sensitivity of the query function, is the standard deviation of the added noise, then the privacy protection effect coefficient X yb =Y ys ×M cd ;

[0069] The computational efficiency coefficient is evaluated by computing time and resource consumption, and is expressed as i Indicates the encryption time of a single data item, T i Indicates the decryption time of a single data item, i is the data item number, i=1,2,3...v, v is a positive integer, then calculate the efficiency coefficient

[0070] The optimization strategy coefficient is calculated by collecting the cost of performing data privacy protection optimization, denoted as S cb , count the medical expenses that patients need to pay, denoted as F yl , then the optimization strategy coefficient Y c1 =F y1 ÷S cb ;

[0071] The algorithm optimization evaluation model is constructed by weighting the privacy protection effect information and computational optimization information in the algorithm model to generate the algorithm optimization evaluation index SY pg , and the corresponding coefficients are the privacy protection effect coefficient X yb , calculate the efficiency coefficient J x1 and optimization strategy coefficient Y cl , the formula is SY pg =β1×X yb -β2×J x1 +β3×Y c1 ;

[0072] In step S4, the algorithm optimization evaluation index obtained in the algorithm optimization evaluation model is used to reflect the actual effect of the differential privacy-homomorphic encryption combined algorithm model. The higher the computational efficiency, the lower the economic cost.

[0073] In step S4, when the algorithm optimizes the evaluation index SY pgWhen it is greater than or equal to the set optimization threshold, it means that the differential privacy-homomorphic encryption combined algorithm model can provide high protection for the target medical privacy data, and the current algorithm model will continue to be used;

[0074] When the algorithm optimizes the evaluation index SY pg When it is less than the set optimization threshold, it means that the differential privacy-homomorphic encryption combined algorithm model fails to achieve the ideal protection effect on the target medical privacy data. The machine learning method is used to optimize the established algorithm model.

[0075] Embodiment 2: This embodiment is a system embodiment of Embodiment 1, and is used to implement a medical operation data privacy protection method introduced in Embodiment 1, specifically including:

[0076] The data collection module monitors and collects information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtains the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established;

[0077] Medical privacy protection demand assessment module: builds a medical privacy protection demand assessment model, and determines the degree of medical operation data privacy protection required by patients, and confirms whether medical operation data privacy protection data optimization processing is required;

[0078] The algorithm processing module establishes a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise under the homomorphic encryption state for target data that requires optimized processing of medical operation data privacy protection data;

[0079] The algorithm optimization and evaluation module builds an algorithm optimization and evaluation model, generates privacy protection effect information and computational optimization information based on the algorithm model's processing of data, and determines whether the algorithm model is applicable to the target data.

[0080] The above formulas are all dimensionless and calculated numerically. Specific dimension removal can be achieved by various means such as standardization, which will not be elaborated here. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0081] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, an ATA hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0082] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile ATA hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for protecting privacy of medical operation data, characterized in that: The steps include: Step S1, monitor and collect information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtain the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established; Step S2, constructing a medical privacy protection demand assessment model, and determining the degree of medical operation data privacy protection required by the patient, and whether medical operation data privacy protection data optimization processing is required; Step S3, for the target data that needs medical operation data privacy protection data optimization processing, establish a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise in the homomorphic encryption state; Step S4, constructing an algorithm optimization evaluation model, generating privacy protection effect information and computational optimization information based on the processing of the algorithm model on the data, and determining whether the algorithm model is applicable to the target data; In step S2, the user's data information is evaluated to confirm the classification of the user's privacy information that should be protected in the system. The specific process is to collect the user's medical privacy protection awareness information and privacy value information, where the privacy protection awareness information includes the patient's privacy protection coefficient, which is calibrated as , the privacy value information includes the patient's disease abnormality coefficient and medical progress coefficient, which are marked as and ; The patient privacy protection coefficient is obtained by analyzing the patient's behavior and obtaining the number of privacy settings and data access times within a week, which are marked as and , and count the number of patient privacy-related complaints after the staged treatment, denoted as , then the patient privacy protection coefficient ; The abnormal coefficient of the patient's disease is obtained by collecting the number of new cases of the patient's disease each year and calibrating it as , the total population is marked as , the total number of deaths and disabilities in the statistical cases, denoted as , then the patient's disease abnormality coefficient ; When the staged treatment is completed, the medical progress coefficient records the patient's physiological parameters, counts the abnormal physiological parameters before treatment, collects the physiological parameters after treatment, and calibrates them as , x is the project number, x=1,2,3...n, n is a positive integer, and the average value of the physiological parameter is , then the medical progress coefficient ; The medical privacy protection demand assessment model is constructed by weighting the patient's privacy awareness information and privacy value information to generate a medical privacy protection demand assessment index. , and the corresponding coefficients are patient privacy protection coefficients , Patient disease abnormality coefficient and Medical Progress Factor , the formula is , where is the weight coefficient of the corresponding indicator.

2. A medical operation data privacy protection method according to claim 1, characterized in that: In step S2, when the medical privacy protection demand assessment index When it is greater than the set protection threshold, a medical privacy enhancement signal is issued and the system is optimized for operation; Medical Privacy Protection Needs Assessment Index When the value is less than or equal to the set protection threshold, no medical privacy enhancement signal will be issued, the existing medical operation data privacy protection system and method will continue to be used, and no subsequent steps will be taken.

3. A medical operation data privacy protection method according to claim 1, characterized in that: In step S3, a differential privacy-homomorphic encryption combined algorithm model is constructed; Furthermore, the construction method of the differential privacy-homomorphic encryption combined algorithm model is as follows: Step S3.1, after receiving the medical privacy enhancement signal, clean and format the patient data to remove erroneous and duplicate data and ensure data structure consistency; Step S3.2, differential privacy implementation, using the Laplace mechanism to add noise, ensuring that the noise added to the query results has statistical properties and protects individual information; Step S3.3, without performing calculations on the decrypted data, use the operation method of the encrypted data to obtain the overall process of combining differential privacy and homomorphic encryption.

4. A medical operation data privacy protection method according to claim 3, characterized in that: In step S4, an algorithm optimization evaluation model is constructed. The specific process is to collect privacy protection effect information and computational optimization information in the differential privacy-homomorphic encryption combined algorithm model, where the privacy protection effect information includes the privacy protection effect coefficient, which is calibrated as , the calculation optimization information includes the calculation efficiency coefficient and the optimization strategy coefficient, which are calibrated as and ; The privacy protection effect coefficient is obtained by analyzing the privacy budget and key length in the algorithm model obtained in step S3, and the two are calibrated as and ,in ,in is the sensitivity of the query function, is the standard deviation of the added noise, then the privacy protection effect coefficient ; The computational efficiency coefficient is evaluated by computing time and resource consumption, using Indicates the encryption time of a single data item, using Indicates the decryption time of a single data item, i is the data item number, i=1,2,3...v, v is a positive integer, then calculate the efficiency coefficient ; The optimization strategy coefficient is calibrated by collecting the cost of performing data privacy protection optimization , count the medical expenses that patients need to pay, denoted as , then the optimization strategy coefficient .

5. A medical operation data privacy protection method according to claim 4, characterized in that: The algorithm optimization evaluation model is constructed by weighting the privacy protection effect information and computational optimization information in the algorithm model to generate an algorithm optimization evaluation index. , and the corresponding coefficients are the privacy protection effect coefficients , calculate the efficiency coefficient and optimization strategy coefficients , the formula is .

6. A medical operation data privacy protection method according to claim 5, characterized in that: In step S4, when the algorithm optimizes the evaluation index When it is greater than or equal to the set optimization threshold, continue to use the current algorithm model; When the algorithm optimizes the evaluation index When it is less than the set optimization threshold, the machine learning method is used to optimize the established algorithm model.

7. A medical operation data privacy protection system, used to implement a medical operation data privacy protection method according to any one of claims 1 to 6, characterized in that: include: The data collection module monitors and collects information data generated during the user's medical treatment process, including the patient's setting, use and feedback of the data, as well as the condition and cost, and obtains the algorithm privacy budget, key length, and computing efficiency and cost data after the algorithm model is established; Medical privacy protection demand assessment module: builds a medical privacy protection demand assessment model, and determines the degree of medical operation data privacy protection required by patients, and confirms whether medical operation data privacy protection data optimization processing is required; The algorithm processing module establishes a differential privacy-homomorphic encryption combined algorithm model to add differential privacy noise under the homomorphic encryption state for target data that requires optimized processing of medical operation data privacy protection data; The algorithm optimization and evaluation module builds an algorithm optimization and evaluation model, generates privacy protection effect information and computational optimization information based on the algorithm model's processing of data, and determines whether the algorithm model is applicable to the target data.

Images