Data desensitization method and device using desensitization model

Abstract

The invention relates to the technical field of data security, and discloses a data desensitization method and device using a desensitization model, and the method comprises the steps: building a block chain, obtaining a desensitization demand, splitting the desensitization model, storing the desensitization model in each node in a distributed manner, generating desensitization data, transmitting the desensitization data, and updating the splitting and distributed storage of the desensitization model. The device corresponds to the method. According to the application, the desensitization demand is determined by utilizing the constructed block chain and analyzing each node, the desensitization model is divided into the plurality of subunits, the subunits are stored in a distributed manner, and the subunits are operated to desensitize the sensitive data, so that the desensitization demand adapting to massive different application scenes is realized, the subunits are adjusted based on different desensitization demands, the data desensitization adaptability is further improved, and the data desensitization efficiency is improved. According to the data desensitization method and system, the desensitization data is transmitted through the block chain encryption and verification mechanism, the safety of the desensitized data in the transmission process is guaranteed, it is ensured that the data is not tampered, and an efficient, safe and flexible solution is provided for data desensitization by combining the block chain technology and the desensitization model.

Description

Technical Field

[0001] The present application relates to the field of data security technology, and specifically to a data desensitization method and device using a desensitization model. Background Art

[0002] The amount of sensitive data is growing rapidly with the rapid development of information technology. Traditional data desensitization has caused the following technical problems in specific applications:

[0003] 1. Unable to adapt to the needs of massive data desensitization;

[0004] 2. Unable to dynamically adjust the desensitization method to adapt to different application scenarios;

[0005] 3. The transmission security of desensitized data cannot be guaranteed.

[0006] Chinese patent number CN117931280A discloses a method, device, equipment and medium for maintaining desensitized information. This invention only uses personal information as the basis for desensitization, which restricts its application scenarios and cannot guarantee the data security of desensitized data during transmission.

[0007] In summary, the existing technology urgently needs a new technical solution for data desensitization to adapt to the massive desensitization needs of different application scenarios and to ensure the data security of the desensitized data during the transmission process. Summary of the invention

[0008] The purpose of this application is to provide a data desensitization method and device using a desensitization model to solve the technical problems raised in the above background technology.

[0009] To achieve the above objectives, this application discloses the following technical solutions:

[0010] In a first aspect, the present application discloses a data desensitization method using a desensitization model, the method comprising:

[0011] S1: construct a blockchain including multiple nodes; wherein there is a one-to-one correspondence between the nodes and the locations where sensitive data are generated;

[0012] S2: Analyze the application scenarios of each of the nodes to obtain corresponding desensitization requirements; wherein, the desensitization requirements are used to characterize the corresponding requirements for desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust the specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data;

[0013] S3: Based on the desensitization requirement, the desensitization model is split into multiple sub-units, and the sub-units are distributedly stored on each of the nodes of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple sub-units, and the sub-units are used to perform corresponding data desensitization for a specific desensitization requirement;

[0014] S4: running the subunit to desensitize the sensitive data of the corresponding node to generate desensitized data; wherein the desensitized data is the sensitive data after desensitization;

[0015] S5: Transmitting the desensitized data using the encryption and verification mechanism of the blockchain;

[0016] S6: When there is an updated desensitization requirement, re-execute steps S3 to S5.

[0017] Preferably, the desensitization model is split into multiple sub-units, specifically comprising:

[0018] Obtain and analyze the desensitization requirement of the node to obtain the desensitization method and the desensitization computing power;

[0019] Matching the corresponding sub-units in the desensitization model using the desensitization method and the desensitization computing power;

[0020] The desensitizing model is split based on the matching result, and a first corresponding relationship between the sub-unit and the node is established; wherein the first corresponding relationship is used to characterize the corresponding relationship between the sub-unit and the node when the sub-unit is distributedly stored.

[0021] Preferably, the storage process of distributively storing the sub-units on each of the nodes of the blockchain specifically includes:

[0022] Acquire the first corresponding relationship;

[0023] The first corresponding relationship is parsed to obtain the corresponding relationship between the sub-units and the nodes stored in the current distributed manner by the sub-units, and the sub-units are stored in the corresponding nodes based on the corresponding relationship.

[0024] Preferably, the subunit stores a desensitization parameter adjustment tool and a desensitization strategy corresponding to the desensitization requirement; wherein, the desensitization parameter adjustment tool is used to trigger the adjustment of the desensitization parameters of the subunit based on the desensitization requirement, and the desensitization strategy is used for the combination of the desensitization methods and their execution order under different desensitization requirements.

[0025] Preferably, the triggering condition for adjusting the desensitization parameters of the subunit is specifically a change in the desensitization parameters and / or desensitization method of the desensitization requirement.

[0026] Preferably, the process of generating the desensitized data specifically includes:

[0027] Obtain the desensitization requirement, and obtain the desensitization parameter and the desensitization method;

[0028] When the triggering condition for adjusting the desensitization parameter of the subunit exists, the desensitization parameter is adjusted by using the desensitization parameter and in combination with the desensitization parameter adjustment tool;

[0029] Using the desensitization method, calling the desensitization strategy of the subunit;

[0030] The subunit after running and adjusting the desensitizing parameters executes the desensitizing strategy to generate the corresponding desensitized data.

[0031] Preferably, the encryption and verification mechanism of blockchain is used to transmit the desensitized data, specifically including:

[0032] Before data transmission, the desensitized data is encrypted using blockchain encryption technology;

[0033] During data transmission, each of the nodes uses the verification mechanism to verify the transmitted desensitized data.

[0034] Preferably, the encryption technology includes at least symmetric encryption, asymmetric encryption and a combination of corresponding encryption methods;

[0035] The verification mechanism includes at least hash verification and digital signature verification.

[0036] Preferably, when there is an updated desensitization requirement, re-execute steps S3 to S5, specifically including:

[0037] When there is an updated desensitizing requirement, based on the updated desensitizing requirement, the desensitizing model is split again to obtain a plurality of sub-units, and the sub-units are redistributed and stored on each of the nodes of the blockchain; the redistributed stored sub-units are run to desensitize the sensitive data of the corresponding nodes to generate the desensitized data; the desensitized data is transmitted again using the encryption and verification mechanism of the blockchain.

[0038] In a second aspect, the present application discloses a data desensitization device using a desensitization model, the device is applicable to the data desensitization method using a desensitization model as described above, and the device includes:

[0039] A blockchain module, wherein the blockchain module is configured to: construct a blockchain including a plurality of nodes; wherein there is a one-to-one correspondence between the nodes and the locations where the sensitive data is generated;

[0040] A desensitization requirement module, wherein the desensitization requirement module is configured to: analyze the application scenarios of each of the nodes to obtain corresponding desensitization requirements; wherein the desensitization requirements are used to characterize the corresponding requirements when desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data;

[0041] A subunit allocation module, wherein the subunit allocation module is configured to: based on the desensitization requirement, split the desensitization model into multiple subunits, and store the subunits in a distributed manner on each of the nodes of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple subunits, and the subunits are used to perform corresponding data desensitization for a specific desensitization requirement;

[0042] A subunit operation module, wherein the subunit operation module is configured to: operate the subunit to desensitize the sensitive data of the corresponding node to generate desensitized data; wherein the desensitized data is the sensitive data after desensitization;

[0043] A transmission module, wherein the transmission module is configured to: transmit the desensitized data using the encryption and verification mechanism of the blockchain;

[0044] A subunit update module, wherein the subunit update module is configured to: when there is an updated desensitization requirement, re-run the subunit allocation module, the subunit operation module and the transmission module.

[0045] Beneficial effect: The data desensitization method and device using a desensitization model of the present application utilize a blockchain that is constructed in one-to-one correspondence with the location where sensitive data is generated, and determines the desensitization requirements by analyzing each node. The desensitization model is split into multiple sub-units and distributedly stored on each node, and the sub-units are run to desensitize the sensitive data, thereby achieving desensitization requirements that adapt to a large number of different application scenarios, and adjusting the sub-units based on different desensitization requirements, further improving the adaptability of data desensitization, and then using the encryption and verification mechanism of the blockchain to transmit the desensitized data, thereby ensuring the security of the desensitized data during transmission and ensuring that the data is not tampered with. By combining blockchain technology with the desensitization model, an efficient, secure and flexible solution is provided for data desensitization. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A flowchart of a data desensitization method using a desensitization model provided in an embodiment of the present application;

[0048] Figure 2 A structural block diagram of a data desensitization device using a desensitization model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0050] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0051] In a first aspect, this embodiment discloses Figure 1 A data desensitization method using a desensitization model is shown, the method comprising:

[0052] S1: Build a blockchain including multiple nodes, where there is a one-to-one correspondence between the nodes and the locations where sensitive data is generated;

[0053] S2: Analyze the application scenarios of each node to obtain the corresponding desensitization requirements; wherein the desensitization requirements are used to characterize the corresponding requirements for desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust the specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data;

[0054] S3: Based on the desensitization requirements, the desensitization model is split into multiple sub-units, and the sub-units are distributed and stored on each node of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple sub-units, and the sub-units are used to perform corresponding data desensitization for a specific desensitization requirement;

[0055] S4: running the subunit to desensitize the sensitive data of the corresponding node, and generating desensitized data; wherein the desensitized data is the sensitive data after desensitization;

[0056] S5: Use blockchain encryption and verification mechanisms to transmit desensitized data;

[0057] S6: When there is an updated desensitization requirement, re-execute steps S3 to S5.

[0058] It should be noted that this embodiment utilizes the existing blockchain technology and combines the analysis of the location where the existing data is generated to perform corresponding node settings, so as to desensitize massive amounts of data through hardware foundation, wherein the desensitization requirements are extracted based on the desensitization parameters, desensitization methods and corresponding desensitization computing power in the actual data desensitization. For example, desensitization parameters include randomization seeds, randomization ranges, etc., desensitization methods include numerical randomization, rounding, interval mapping, etc., and desensitization computing power includes the number of CPU operations, memory usage, processing time, etc.

[0059] Based on the above, this embodiment utilizes a blockchain constructed to correspond one-to-one with the location where sensitive data is generated, determines the desensitization requirements by analyzing each node, splits the desensitization model into multiple sub-units and stores them in a distributed manner on each node, and runs the sub-units to desensitize the sensitive data, thereby achieving desensitization requirements that adapt to a large number of different application scenarios, and adjusting the sub-units based on different desensitization requirements, further improving the adaptability of data desensitization, and then using the encryption and verification mechanism of the blockchain to transmit the desensitized data, thereby ensuring the security of the desensitized data during transmission and ensuring that the data is not tampered with. By combining blockchain technology with the desensitization model, an efficient, secure and flexible solution is provided for data desensitization.

[0060] Specifically, the desensitization model is split into multiple sub-units, which specifically includes:

[0061] Obtain and analyze the node's desensitization requirements, and obtain the desensitization method and desensitization computing power;

[0062] Use the desensitization method and desensitization computing power to match the corresponding sub-units in the desensitization model;

[0063] The desensitizing model is split based on the matching results, and a first correspondence between sub-units and nodes is established; wherein the first correspondence is used to characterize the correspondence between sub-units and nodes when distributed storage of sub-units is performed.

[0064] It should be noted that the desensitization model of this embodiment is obtained by pre-training using the deep learning model in the existing machine learning, and the further sub-unit realizes autonomous data desensitization corresponding to a specific desensitization requirement through the deep learning model, and obtains the desensitization model through the existing model fusion technology. The purpose of this design of this embodiment is to reduce the manpower and material costs of the model construction link and improve the generalization ability of the desensitization model by constructing a complete desensitization model and then performing corresponding splitting and distributed storage based on the application scenarios (i.e., desensitization requirements) of the nodes of different blockchains.

[0065] Based on the above, in the process of splitting the desensitizing model into multiple sub-units, this embodiment accurately determines the desensitizing method and desensitizing computing power required for a specific node by acquiring and parsing the desensitizing requirements of the node, thereby ensuring the first corresponding relationship between the split sub-units and the desensitizing requirements of the node, providing clear guidance for subsequent distributed storage, realizing efficient model splitting, improving the pertinence and efficiency of data desensitization, and laying the foundation for adapting to the desensitization needs of massive data in different application scenarios.

[0066] Specifically, the storage process of distributing the sub-units on each node of the blockchain includes:

[0067] Obtaining a first corresponding relationship;

[0068] The first corresponding relationship is parsed to obtain the corresponding relationship between the sub-units and nodes stored in the current sub-unit distributed manner, and the sub-units are stored in the corresponding nodes based on the corresponding relationship.

[0069] Specifically, the sub-unit stores a desensitization parameter adjustment tool and a desensitization strategy corresponding to the desensitization requirements; wherein, the desensitization parameter adjustment tool is used to trigger the adjustment of the desensitization parameters of the sub-unit based on the desensitization requirements, and the desensitization strategy is used for a combination of desensitization methods and their execution order under different desensitization requirements.

[0070] It should be noted that the desensitizing parameter adjustment tool of the present embodiment is obtained based on the actual desensitizing parameter adjustment process. For example, based on a supervised learning algorithm, historical desensitizing parameter adjustment cases are used as training data, and different application scenarios, desensitizing requirements, and corresponding initial desensitizing parameters and adjusted desensitizing parameters are used as features and labels to train a tool for adjusting desensitizing parameters based on new application scenarios and desensitizing requirements; the desensitizing strategy of the present embodiment is obtained based on the combination process of actual desensitizing methods. For example, if the security level of the data is required to be high, randomization processing can be performed first, such as randomly adjusting the value within a certain range, and then rounding the value, and finally encrypting it using an encryption algorithm. For example, for data from external partners with a low trust level, a strict desensitization strategy is adopted, such as multiple encryption combined with deep fuzzy processing, and strict verification and auditing must be performed at each stage of data reception and processing.

[0071] Based on the above, in the process of distributing and storing sub-units in various nodes of the blockchain, this embodiment realizes accurate storage by parsing the corresponding relationship. The desensitization parameter adjustment tool of the sub-unit realizes its own corresponding adjustment parameters, and uses the desensitization strategy based on the actual combination process to provide different desensitization strategies for different situations, so that data desensitization is more targeted and flexible, adapting to the needs of different scenarios, improving desensitization efficiency and security, providing a reliable solution for desensitizing massive data, and at the same time ensuring the security and accuracy of data during storage and processing at different nodes.

[0072] Specifically, the triggering condition for adjusting the desensitization parameters of the subunit is specifically the change of the desensitization parameters and / or the desensitization method required for desensitization.

[0073] Based on the above, this embodiment limits the triggering of the adjustment of the desensitization parameters of the sub-units through precise triggering conditions for the adjustment of the desensitization parameters of the sub-units, effectively controls the computing power cost, and provides sufficient computing power foundation for adapting to the desensitization of massive data.

[0074] Specifically, the process of generating desensitized data includes:

[0075] Obtain desensitization requirements, desensitization parameters and desensitization methods;

[0076] When there is a triggering condition for adjusting the desensitization parameters of the subunit, the desensitization parameters of the subunit are adjusted using the desensitization parameters in combination with the desensitization parameter adjustment tool;

[0077] Using the desensitization method, call the desensitization strategy of the subunit;

[0078] The subunit with adjusted desensitization parameters is run to execute the desensitization strategy and generate corresponding desensitized data.

[0079] Based on the above, in the process of generating desensitized data, this embodiment determines the desensitization parameters and desensitization methods based on the desensitization requirements, and only when the trigger conditions are met, the desensitization parameter adjustment tool is called, and the desensitization parameters of the sub-unit are flexibly adjusted based on the actual desensitization requirements, thereby improving the adaptability of the parameters. Furthermore, the desensitization strategies of the sub-units are called with full consideration of the needs of different application scenarios, and the data are accurately desensitized to generate high-quality desensitized data, thereby ensuring the accuracy and efficiency of desensitization, adapting to the desensitization needs of massive data in different scenarios, and at the same time ensuring the security and availability of the desensitized data, laying the foundation for the secure storage and transmission of data.

[0080] Specifically, the encryption and verification mechanism of blockchain is used to transmit the desensitized data, including:

[0081] Before data transmission, the desensitized data is encrypted using blockchain encryption technology;

[0082] During data transmission, each node uses a verification mechanism to verify the transmitted desensitized data.

[0083] Specifically, encryption technology includes at least symmetric encryption, asymmetric encryption and a combination of corresponding encryption methods;

[0084] The verification mechanism includes at least hash verification and digital signature verification.

[0085] It should be noted that blockchain technology has the characteristics of decentralization, immutability and encryption, and is suitable for the transmission and verification of desensitized data. The symmetric encryption, asymmetric encryption and the corresponding combination of encryption methods, hash verification and digital signature verification are all available to technical personnel in this field based on well-known experience.

[0086] Through the above, this embodiment significantly improves the security of data, provides a reliable basis for the transmission and verification of desensitized data, adapts to the desensitization needs of massive data, ensures the secure transmission of desensitized data in different application scenarios, and improves the credibility and availability of data.

[0087] Specifically, when there is an updated desensitization requirement, steps S3 to S5 are re-executed, specifically including:

[0088] When there is an updated desensitization requirement, the desensitization model is split again to obtain multiple sub-units based on the updated desensitization requirement, and the sub-units are redistributed and stored on each node of the blockchain; the redistributed storage sub-units are run to desensitize the sensitive data of the corresponding nodes to generate desensitized data; the desensitized data is transmitted again using the encryption and verification mechanism of the blockchain.

[0089] Through the above, this embodiment utilizes the capture of updated desensitization requirements to achieve dynamic splitting and distributed storage of desensitization models, providing a basic foundation for optimizing the adaptation of sub-units and nodes, thereby providing an efficient, secure and flexible data desensitization solution.

[0090] In a second aspect, this embodiment discloses Figure 2 A data desensitization device using a desensitization model is shown, and the device is applicable to the data desensitization method using a desensitization model as described above, and the device includes:

[0091] The blockchain module is configured to: construct a blockchain including a plurality of nodes; wherein there is a one-to-one correspondence between the nodes and the locations where the sensitive data is generated;

[0092] Desensitization requirement module, the desensitization requirement module is configured as follows: analyzing the application scenarios of each node to obtain the corresponding desensitization requirements; wherein the desensitization requirements are used to characterize the corresponding requirements when desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust the specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data;

[0093] The sub-unit allocation module is configured as follows: based on the desensitization requirement, the desensitization model is split into multiple sub-units, and the sub-units are distributedly stored on each node of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple sub-units, and the sub-units are used to perform corresponding data desensitization for a specific desensitization requirement;

[0094] The subunit operation module is configured to: operate the subunit to desensitize the sensitive data of the corresponding node to generate desensitized data; wherein the desensitized data is the sensitive data after desensitization;

[0095] A transmission module, the transmission module is configured to: utilize the encryption and verification mechanism of the blockchain to transmit the desensitized data;

[0096] The sub-unit update module is configured as follows: when there is a desensitizing requirement for update, the sub-unit allocation module, the sub-unit operation module and the transmission module are re-run.

[0097] It should be noted that the data desensitization device using a desensitization model in this embodiment corresponds to the aforementioned data desensitization method using a desensitization model. Therefore, the parts that are not specifically described in the data desensitization device using a desensitization model (including but not limited to technical effects, specific technical means, etc.) can be referred to in the specific records in the aforementioned data desensitization method using a desensitization model, and this text will not go into details here.

[0098] In summary, the data desensitization method and device using a desensitizing model in this embodiment utilizes a constructed blockchain that corresponds one-to-one to the location where sensitive data is generated, determines the desensitization requirements by analyzing each node, splits the desensitization model into multiple sub-units and stores them in a distributed manner on each node, and runs the sub-units to desensitize the sensitive data, thereby achieving desensitization requirements that adapt to a large number of different application scenarios, and adjusting the sub-units based on different desensitization requirements, further improving the adaptability of data desensitization, and then using the encryption and verification mechanism of the blockchain to transmit the desensitized data, thereby ensuring the security of the desensitized data during transmission and ensuring that the data is not tampered with. By combining blockchain technology with the desensitization model, an efficient, secure and flexible solution is provided for data desensitization.

[0099] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0100] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data desensitization method using a desensitization model, characterized in that: The method includes: S1: construct a blockchain including multiple nodes; wherein there is a one-to-one correspondence between the nodes and the locations where sensitive data are generated; S2: Analyze the application scenarios of each of the nodes to obtain corresponding desensitization requirements; wherein, the desensitization requirements are used to characterize the corresponding requirements for desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust the specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data; S3: Based on the desensitization requirement, the desensitization model is split into multiple sub-units, and the sub-units are distributedly stored on each of the nodes of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple sub-units, and the sub-units are used to perform corresponding data desensitization for a specific desensitization requirement; S4: running the subunit to desensitize the sensitive data of the corresponding node to generate desensitized data; wherein the desensitized data is the sensitive data after desensitization; S5: Transmitting the desensitized data using the encryption and verification mechanism of the blockchain; S6: When there is an updated desensitization requirement, re-execute steps S3 to S5.

2. The data desensitization method using a desensitization model according to claim 1, characterized in that: The desensitization model is split into multiple sub-units, specifically including: Obtain and analyze the desensitization requirement of the node to obtain the desensitization method and the desensitization computing power; Matching the corresponding sub-units in the desensitization model using the desensitization method and the desensitization computing power; The desensitizing model is split based on the matching result, and a first corresponding relationship between the sub-unit and the node is established; wherein the first corresponding relationship is used to characterize the corresponding relationship between the sub-unit and the node when the sub-unit is distributedly stored.

3. The data desensitization method using a desensitization model according to claim 2, characterized in that: The storage process of distributively storing the sub-units on each of the nodes of the blockchain specifically includes: Acquire the first corresponding relationship; The first corresponding relationship is parsed to obtain the corresponding relationship between the sub-units and the nodes stored in the current distributed manner by the sub-units, and the sub-units are stored in the corresponding nodes based on the corresponding relationship.

4. The data desensitization method using a desensitization model according to claim 1, characterized in that: The subunit stores a desensitization parameter adjustment tool and a desensitization strategy corresponding to the desensitization requirement; wherein, the desensitization parameter adjustment tool is used to trigger the adjustment of the desensitization parameters of the subunit based on the desensitization requirement, and the desensitization strategy is used for the combination of the desensitization methods and their execution order under different desensitization requirements.

5. The data desensitization method using a desensitization model according to claim 4, characterized in that: The triggering condition for adjusting the desensitization parameters of the subunit is specifically the change of the desensitization parameters and / or desensitization method of the desensitization requirement.

6. The data desensitization method using a desensitization model according to claim 5, characterized in that: The generation process of the desensitized data specifically includes: Obtain the desensitization requirement, and obtain the desensitization parameter and the desensitization method; When the triggering condition for adjusting the desensitization parameter of the subunit exists, the desensitization parameter is adjusted by using the desensitization parameter and in combination with the desensitization parameter adjustment tool; Using the desensitization method, calling the desensitization strategy of the subunit; The subunit after running and adjusting the desensitizing parameters executes the desensitizing strategy to generate the corresponding desensitized data.

7. The data desensitization method using a desensitization model according to claim 1, characterized in that: The encryption and verification mechanism of blockchain is used to transmit the desensitized data, specifically including: Before data transmission, the desensitized data is encrypted using blockchain encryption technology; During data transmission, each of the nodes uses the verification mechanism to verify the transmitted desensitized data.

8. The data desensitization method using a desensitization model according to claim 7, characterized in that: The encryption technology at least includes symmetric encryption, asymmetric encryption and a combination of corresponding encryption methods; The verification mechanism includes at least hash verification and digital signature verification.

9. The data desensitization method using a desensitization model according to claim 1, characterized in that: When there is an updated desensitization requirement, steps S3 to S5 are re-executed, specifically including: When there is an updated desensitizing requirement, based on the updated desensitizing requirement, the desensitizing model is split again to obtain a plurality of sub-units, and the sub-units are redistributed and stored on each of the nodes of the blockchain; the redistributed stored sub-units are run to desensitize the sensitive data of the corresponding nodes to generate the desensitized data; the desensitized data is transmitted again using the encryption and verification mechanism of the blockchain.

10. A data desensitization device using a desensitization model, the device being applicable to the data desensitization method using a desensitization model as described in any one of claims 1 to 9, characterized in that: The device includes: A blockchain module, wherein the blockchain module is configured to: construct a blockchain including a plurality of nodes; wherein there is a one-to-one correspondence between the nodes and the locations where the sensitive data is generated; A desensitization requirement module, wherein the desensitization requirement module is configured to: analyze the application scenarios of each of the nodes to obtain corresponding desensitization requirements; wherein the desensitization requirements are used to characterize the corresponding requirements when desensitizing the sensitive data of the node, and the desensitization requirements at least include at least desensitization parameters, desensitization methods and corresponding desensitization computing power, the desensitization parameters are used to control and adjust specific values ​​or settings of desensitization, the desensitization method is the method required to desensitize the sensitive data, and the desensitization computing power is the computing power required when the desensitization method is used for the sensitive data; A subunit allocation module, wherein the subunit allocation module is configured to: based on the desensitization requirement, split the desensitization model into multiple subunits, and store the subunits in a distributed manner on each of the nodes of the blockchain; wherein the desensitization model is obtained by pre-training using machine learning and includes multiple subunits, and the subunits are used to perform corresponding data desensitization for a specific desensitization requirement; A subunit operation module, wherein the subunit operation module is configured to: operate the subunit to desensitize the sensitive data of the corresponding node to generate desensitized data; wherein the desensitized data is the sensitive data after desensitization; A transmission module, wherein the transmission module is configured to: transmit the desensitized data using the encryption and verification mechanism of the blockchain; A subunit update module, wherein the subunit update module is configured to: when there is an updated desensitization requirement, re-run the subunit allocation module, the subunit operation module and the transmission module.

Images