Data encryption desensitization calculation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and provides a data encryption desensitization calculation method and device, electronic equipment and a storage medium, and the method specifically comprises the steps: forming transmission data of agricultural insurance through crop characteristic factors; performing first similarity comparison on the current transmission data of the agricultural insurance and the historical transmission data, and determining whether to reuse the historical encryption strategy; extracting historical decrypted data in the historical transmission data, performing second similarity comparison on the historical decrypted data and the current transmission data, and outputting a second similarity comparison result; constructing an encryption strength dynamic evolution model, optimizing the encryption strength of the data encryption strategy according to a second similarity comparison result, and outputting a preliminary encryption strategy; and establishing a differential coupling equation to carry out stability constraint on the encryption strategy change rate, and deciding and outputting a final encryption strategy. According to the invention, the problem of encryption resource waste caused by neglect of dynamic change of information value of data along with time in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and relates to a data encryption and desensitization calculation method, device, electronic equipment and storage medium. Background Art

[0002] In the field of agricultural insurance, data encryption and desensitizing technologies are the core links in protecting farmers' privacy and preventing insurance fraud. However, existing technical solutions have significant flaws when addressing the spatiotemporal dynamics and business complexity of agricultural data: First, traditional static encryption strategies fail to adapt to the sensitivity fluctuations of the crop growth cycle. For example, the difference in data security requirements between the sowing period and the harvest period is often overlooked, resulting in a mismatch between encryption strength and timeliness requirements; Second, the fusion analysis of multi-source heterogeneous data (such as meteorological mutations, soil moisture conditions, and regional fraud history) is insufficient. Existing methods mostly use single-dimensional similarity comparison (such as time or amount) and lack cross-spatiotemporal feature coupling modeling, making it difficult to capture complex correlations such as disaster transmission (such as the impact of floods on downstream areas) or the evolution of fraud patterns; Third, encryption strategy adjustments lack a stability control mechanism. Existing dynamic models are prone to policy oscillations due to short-term fluctuations. For example, frequent changes in encryption levels during typhoon warnings may interfere with the claims process; Fourth, the value of historical decrypted data is not fully mined, and a quantitative model has not been established to analyze the dynamic balance between data disclosure trends and encryption strength, resulting in resource waste (such as premature encryption strengthening) or risk exposure (such as delayed downgrade). Summary of the Invention

[0003] The technical problem to be solved by the present invention is to address the problem in the prior art of wasting encryption resources due to ignoring the dynamic changes in the information value of data over time, and propose a data encryption desensitization calculation method, device, electronic device and storage medium.

[0004] In order to achieve the above-mentioned object, the technical solution of the data encryption and desensitization calculation method of the present invention includes the following steps:

[0005] S1: Obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance;

[0006] S2: Collecting current transmission data and historical transmission data of agricultural insurance, performing a first similarity comparison between the current transmission data and the historical transmission data of agricultural insurance, and determining whether to reuse the historical encryption strategy based on the first similarity comparison result;

[0007] S3: When the output result of S2 is to reuse the historical encryption strategy, extract the historical decrypted data in the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output the second similarity comparison result;

[0008] S4: Extract the encryption strength of the data in the historical encryption strategy, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy;

[0009] S5: Extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

[0010] Specifically, S2 includes the following specific steps:

[0011] S21: standardize the current transmission data and historical transmission data of agricultural insurance, and add spatiotemporal tags to the current transmission data and historical transmission data of agricultural insurance;

[0012] S22: Input the current transmission data and the historical transmission data output by S21 into the cross entropy quantitative evaluation model to evaluate the agricultural cross entropy similarity ACE between the current transmission data and the historical transmission data;

[0013] S23: Extract the claim fraud factor from the crop characteristic factor and the agricultural cross entropy similarity and import them into the first similarity comparison strategy to obtain the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance.

[0014] Specifically, S2 also includes:

[0015] S24: comparing the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data with the dynamic matching threshold, and reusing the historical encryption strategy when the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data is greater than or equal to the dynamic matching threshold;

[0016] When the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance is less than the dynamic similarity threshold, the encryption algorithm strength is improved and a new encryption scheme is rebuilt;

[0017] The dynamic matching threshold is dynamically updated according to the seasonal disclosure factor in the historical decrypted data.

[0018] Specifically, S3 includes the following specific steps:

[0019] S31: extract the historical decrypted data from the historical transmission data and calculate the decryption characteristic factor of the historical decrypted data, wherein the decryption characteristic factor includes: decryption time decay factor , decrypted data similarity factor , seasonal exposure factor and risk transmission factors ;

[0020] S32: Importing the decryption characteristic factors of the historical decrypted data into the time-weighted similarity evaluation strategy to calculate and obtain the time-weighted similarity index;

[0021] ;

[0022] Among them, c is the current agricultural crop feature vector, is the kth historical transmission data record in the historical feature sample; m is the total number of historical transmission data;

[0023] To decrypt the time decay factor, It is the content similarity between the currently transmitted data and the historically decrypted data.

[0024] Specifically, S3 also includes the following specific steps:

[0025] S33: Extracting a time-weighted similarity index, performing a second similarity comparison between the historically decrypted data and the currently transmitted data, and obtaining a data disclosure trend index;

[0026] ;

[0027] in, is the temporal similarity index; is the constraint weight.

[0028] Specifically, S4 includes the following specific steps:

[0029] S41: Extract the encryption strength of data in historical encryption strategies and construct an encryption strength dynamic evolution model. The encryption strength dynamic evolution model is specifically:

[0030] ;

[0031] in, is the encryption strength after dynamic evolution of encryption strength;

[0032] The default encryption strength for the system; The threshold value for triggering encryption adjustment;

[0033] It is a seasonal sensitive regulatory factor; The historical public trend volatility of the current transmission data;

[0034] S42: Synchronously detect the similarity between current data and recent high-risk historical patterns, perform mutation detection on risk trigger patterns, and obtain detection status parameters ;

[0035] S43: Outputting a preliminary encryption strategy, specifically including the encryption strength after the dynamic evolution of the encryption strength.

[0036] Specifically, S5 includes the following steps:

[0037] S51: extracting the first similarity comparison result and the second similarity comparison result, establishing a differential coupling equation, and performing stability constraints on the encryption strategy change rate;

[0038] S53: Decision output of the final encryption strategy, including:

[0039] when The final encryption strategy is: ;

[0040] when When , the final encryption strategy is ;

[0041] When the currently transmitted data does not meet the above conditions, the preliminary encryption strategy is output as the final encryption strategy;

[0042] in, The encryption policy at the previous moment.

[0043] In addition, the data encryption and desensitization computing device of the present invention includes:

[0044] Data feature extraction module, first similarity comparison module, second similarity comparison module, encryption strength evolution module and encryption strategy output module;

[0045] The data feature extraction module is used to obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance;

[0046] The first similarity comparison module is used to collect current transmission data and historical transmission data of agricultural insurance, perform a first similarity comparison on the current transmission data of agricultural insurance and the historical transmission data, and determine whether to reuse the historical encryption strategy according to the first similarity comparison result;

[0047] The second similarity comparison module is used to extract historical decrypted data from the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output a second similarity comparison result;

[0048] The encryption strength evolution module is used to extract the encryption strength of data in historical encryption strategies, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy;

[0049] The encryption strategy output module is used to extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

[0050] A storage medium stores instructions, and when a computer reads the instructions, the computer executes the data encryption and desensitization calculation method.

[0051] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned data encryption and desensitization calculation method is implemented.

[0052] Compared with the prior art, the technical effects of the present invention are as follows:

[0053] 1. In terms of data processing, the present invention quantifies historical crop planting data in agricultural insurance into crop characteristic factors to form transmission data, accurately capturing the characteristics of agricultural data. Through a first similarity comparison, the current transmission data is compared with the historical transmission data to determine whether to reuse the historical encryption strategy. If the similarity coefficient is greater than or equal to the dynamic matching threshold, the strategy is reused; otherwise, the encryption algorithm strength is increased, avoiding unnecessary waste of encryption resources and improving encryption efficiency. Furthermore, when reusing the historical encryption strategy, a second similarity comparison is performed to extract historical decrypted data and calculate the decryption characteristic factors to obtain a data disclosure trend index. This is then used to construct a dynamic evolution model for encryption strength to optimize encryption strength. Sudden changes in risk trigger patterns are also detected simultaneously, allowing the encryption strategy to be flexibly adjusted based on data changes and potential risks.

[0054] Furthermore, the present invention establishes a differential coupling equation to constrain the rate of change of the encryption strategy, ensuring that the encryption strategy does not change too drastically and ensuring system stability. This method and device can adapt to the seasonal, regional, and dynamic characteristics of agricultural insurance data, providing a more secure, efficient, and flexible encryption and desensitization solution. This provides reliable protection for the transmission and storage of agricultural insurance data, and promotes the informatization and security development of the agricultural insurance industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0056] Figure 1 This is a schematic diagram of the structure of the data encryption and desensitization computing device of the present invention;

[0057] Figure 2 Schematic diagram of the data encryption and desensitization calculation method of the present invention;

[0058] Figure 3 This is a flow chart of the present invention for performing a first similarity comparison between current transmission data and historical transmission data of agricultural insurance. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0062] Example 1:

[0063] like Figure 1 As shown, the data encryption and desensitization computing device of the embodiment of the present invention is as follows Figure 1 As shown, it includes the following modules:

[0064] Data feature extraction module, first similarity comparison module, second similarity comparison module, encryption strength evolution module and encryption strategy output module;

[0065] The data feature extraction module is used to obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance;

[0066] The first similarity comparison module is used to collect current transmission data and historical transmission data of agricultural insurance, perform a first similarity comparison on the current transmission data of agricultural insurance and the historical transmission data, and determine whether to reuse the historical encryption strategy according to the first similarity comparison result;

[0067] The second similarity comparison module is used to extract historical decrypted data from the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output a second similarity comparison result;

[0068] The encryption strength evolution module is used to extract the encryption strength of data in historical encryption strategies, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy;

[0069] The encryption strategy output module is used to extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

[0070] Example 2:

[0071] like Figure 2 As shown, the data encryption and desensitization calculation method of the embodiment of the present invention is as follows Figure 2 As shown, the specific steps are as follows:

[0072] S1: Obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance;

[0073] The crop characteristic factors mentioned in S1 include: growth cycle encryption sensitivity factor, claim fraud factor, meteorological mutation factor and soil entropy factor;

[0074] Among them, the growth cycle encryption sensitivity factor is calculated based on the crop sowing date and the crop growth cycle; the claim fraud factor is calculated based on the number of historical fraud cases in the same region, the number of current claims applications, and the claim amount; the meteorological mutation factor is calculated based on the meteorological characteristic vector of the region to which the current transmission data belongs; and the soil entropy factor is calculated based on the soil moisture data of the region to which the current transmission data belongs.

[0075] For example, in this embodiment, the growth cycle encryption sensitive factor The calculation strategy is as follows: , where t is the timestamp of the current transmitted data, They are the sowing date of the crop and the growing cycle of the crop;

[0076] It's important to note that crop sensitivity to environmental factors (such as precipitation and temperature) varies cyclically across different growth stages (e.g., seedling, heading, and maturity). The cosine function can be used to simulate a single-peak sensitivity curve (low → high → low), which aligns with the characteristics of most crops: sensitivity in the middle (e.g., booting) and relative stability in the early and late stages. This quantifies the sensitivity of different growth stages at different time points and is used to weight meteorological data, providing dynamic weighting of the time dimension for claims assessment.

[0077] For example, in this embodiment, the claim fraud factor The calculation strategy is:

[0078] ,in, The number of historical fraud cases in the same region, reflecting the regional fraud risk baseline; The number of current claims applications is used to measure regional claims activity; The current single claim amount, used to identify large and abnormal claims; The historical average claim amount for the same crop is used to standardize the amount dimension; , is the smoothing factor;

[0079] It should be noted that the claim fraud factor is used to filter out "normal high-frequency small claims" and lock in suspicious cases of "low-frequency large claims and high historical fraud incidence";

[0080] For example, in this embodiment, the climate mutation factor The calculation strategy is:

[0081] ,in, is the current meteorological feature vector (such as temperature, precipitation, wind speed and other multi-dimensional data); is the meteorological feature vector one week ago; It is the standard deviation of regional meteorological characteristics, reflecting the normal state of local meteorological fluctuations.

[0082] It should be noted that meteorological mutation factors can be used to capture meteorological mutation events (such as typhoons and extreme high temperatures) in real time, quickly trigger risk warnings, and provide a basis for prioritizing claims investigations.

[0083] For example, in this embodiment, the soil entropy factor The calculation strategy is:

[0084] ,in, is the current soil moisture content; The optimal soil moisture content for crop growth;

[0085] It should be noted that, in S1, the currently transmitted data includes: the currently encrypted data of the agricultural insurance, and the historically transmitted data includes: the historically encrypted data and the historically decrypted data;

[0086] Exemplarily, in this embodiment, the historical encrypted data includes m decryption records;

[0087] Exemplarily, in this embodiment, the historical decrypted data is a data set with a decryption timestamp;

[0088] S2: Collecting current transmission data and historical transmission data of agricultural insurance, performing a first similarity comparison between the current transmission data and the historical transmission data of agricultural insurance, and determining whether to reuse the historical encryption strategy based on the first similarity comparison result;

[0089] like Figure 3 As shown, S2 includes the following specific steps:

[0090] S21: standardize the current transmission data and historical transmission data of agricultural insurance, and add spatiotemporal tags to the current transmission data and historical transmission data of agricultural insurance;

[0091] S22: Input the current transmission data and the historical transmission data output by S21 into the cross entropy quantitative evaluation model to evaluate the agricultural cross entropy similarity ACE between the current transmission data and the historical transmission data;

[0092] For example, in this embodiment, the output formula of the cross entropy quantization evaluation model is:

[0093] ;

[0094] Among them, i is the number index of the crop characteristic factor;

[0095] When i=1, is the KL divergence of the crop growth cycle, specifically: ;

[0096] It should be noted that the cross entropy based on growth cycle sensitivity measures the differences in sensitivity patterns of crops p and q at each growth stage.

[0097] When i=2, is the JS divergence of the disaster model, specifically:

[0098] ;

[0099] It should be noted that the symmetric KL divergence measures the two-way differences between crops p and q and the average state, avoiding the bias of the unidirectional KL divergence;

[0100] When i=3, is the Euclidean distance of meteorological mutation, which is: ; is the second norm; it should be noted that the L2 distance of the meteorological mutation factors of the two regions is calculated to reflect the difference in short-term meteorological impact;

[0101] When i=4, is the soil moisture correlation coefficient, specifically: ;

[0102] in, are the standard deviations of soil moisture weights for crops p and q, respectively;

[0103] For example, in this embodiment, the weight distribution of each crop characteristic factor is specifically as follows:

[0104] ;

[0105] S23: Extract the claim fraud factor from the crop characteristic factor and the agricultural cross entropy similarity and import them into the first similarity comparison strategy to obtain the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance.

[0106] For example, in this embodiment, a similarity comparison strategy is provided, specifically:

[0107] ;

[0108] Among them, k is the claim fraud factor in the crop characteristic factor.

[0109] S24: comparing the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data with the dynamic matching threshold, and reusing the historical encryption strategy when the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data is greater than or equal to the dynamic matching threshold;

[0110] When the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance is less than the dynamic similarity threshold, the encryption algorithm strength is improved and a new encryption scheme is rebuilt;

[0111] The dynamic matching threshold is dynamically updated according to the seasonal disclosure factor in the historical decrypted data.

[0112] For example, in this embodiment, a method for improving the strength of an encryption algorithm is provided, specifically including: when reconstructing a new encryption scheme, the encryption algorithm is switched from AES-128 to AES-256.

[0113] For example, in this embodiment, a calculation strategy for a dynamic matching threshold is further provided, specifically:

[0114] ;

[0115] in, is the dynamic matching threshold, is the seasonal disclosure factor;

[0116] S3: When the output result of S2 is to reuse the historical encryption strategy, extract the historical decrypted data in the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output the second similarity comparison result;

[0117] S3 includes the following specific steps:

[0118] S31: extract the historical decrypted data from the historical transmission data and calculate the decryption characteristic factor of the historical decrypted data, wherein the decryption characteristic factor includes: decryption time decay factor , decrypted data similarity factor , seasonal exposure factor and risk transmission factors ;

[0119] The decryption time decay factor is obtained by evaluating the timestamp of the current transmission data and the timestamp of the historical decrypted data; the decrypted data similarity factor is obtained by evaluating the timestamp of the previous transmission data and the data characteristics of the historical decrypted data; the seasonal disclosure factor is obtained by evaluating the sowing time of the crop; the risk transmission factor is obtained by

[0120] For example, in this embodiment, the decryption time decay factor is specifically:

[0121] ;

[0122] in, is the default decay rate of data timeliness, / sky; They are respectively the timestamp of the current transmitted data and the timestamp of the historical decrypted data;

[0123] It should be noted that the information value of data decays exponentially over time.

[0124] Exemplarily, in this embodiment, the decrypted data similarity factor is specifically:

[0125] ;

[0126] in, are the g-th dimension features of the currently transmitted data and the features corresponding to the historical decrypted data; is the L2 norm of the eigenvector;

[0127] For example, in this embodiment, the seasonal disclosure factor is specifically:

[0128] ;in, is the annual cycle frequency;

[0129] For example, in this embodiment, the risk transmission factor , specifically:

[0130] ;

[0131] Where S is the total number of risk history transmission data; is the risk event indicator function. If the historical transmission data belongs to the disaster-stricken area, the risk event indicator function is 1. Otherwise, the risk event indicator function is 0.

[0132] Indicates the geographic spatial similarity between the region to which the current transmission data belongs and the region to which the risk history transmission data belongs;

[0133] In this embodiment, The calculation strategy is: ,in, The geographical distance between the area where the risk historical transmission data belongs and the area where the current transmission data belongs, is the risk diffusion scale. For example, the diffusion scale in plain areas is 15 km, and the diffusion scale in mountainous areas is 8 km.

[0134] It should be noted that, considering the transmission effect of neighboring risk events on the current region, only the geographic spatial similarity of the disaster-affected historical transmission data is summed through the risk transmission factor.

[0135] S32: Importing the decryption characteristic factors of the historical decrypted data into the time-weighted similarity evaluation strategy to calculate and obtain the time-weighted similarity index;

[0136] ;

[0137] Among them, c is the current agricultural crop feature vector, is the kth historical transmission data record in the historical feature sample; m is the total number of historical transmission data;

[0138] To decrypt the time decay factor, It is the content similarity between the currently transmitted data and the historically decrypted data.

[0139] For example, in this embodiment, the content similarity calculation strategy is specifically as follows:

[0140] ;

[0141] are the feature vectors of the current transmission data crop and the historical transmission data crop, respectively;

[0142] S33: Extracting a time-weighted similarity index, performing a second similarity comparison between the historically decrypted data and the currently transmitted data, and obtaining a data disclosure trend index;

[0143] ;

[0144] in, is the temporal similarity index; is the constraint weight.

[0145] For example, in this embodiment, ;

[0146] S4: Extract the encryption strength of the data in the historical encryption strategy, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy;

[0147] S4 includes the following specific steps:

[0148] S41: Extract the encryption strength of data in historical encryption strategies and construct an encryption strength dynamic evolution model. The encryption strength dynamic evolution model is specifically:

[0149] ;

[0150] in, is the encryption strength after dynamic evolution of encryption strength;

[0151] The default encryption strength for the system;

[0152] Exemplarily, in this embodiment, the system preset basic encryption level is initialized according to the policy type (plantation insurance / breeding insurance) or data sensitivity;

[0153] The threshold value for triggering encryption adjustment;

[0154] For example, in this embodiment, the critical value is the median of the historical data disclosure trend index;

[0155] It is a seasonal sensitive regulatory factor; The historical public trend volatility of the current transmission data;

[0156] For example, in this embodiment, a calculation strategy for a seasonal sensitivity adjustment factor is provided: ;

[0157] For example, in this embodiment, a calculation strategy for historical public trend volatility is also provided: , is the average value of the data disclosure trend index of m historical decrypted data;

[0158] S42: Synchronously detect the similarity between current data and recent high-risk historical patterns, perform mutation detection on risk trigger patterns, and obtain detection status parameters ;

[0159] For example, in this embodiment, a specific implementation method of mutation detection is given, specifically:

[0160] When it is detected that the content similarity between the historical transmission data and the current transmission data is greater than 0.8 and the difference between the decryption timestamp of the historical transmission data and the timestamp of the current transmission data is less than the risk triggering time range, the output is the detection status parameter Is 1, otherwise output detection status parameters is 0.

[0161] For example, in this embodiment, the risk triggering time range is also provided. Specific confirmation strategy: ;in, It is a risk transmission factor.

[0162] S43: Outputting a preliminary encryption strategy, specifically including the encryption strength after the dynamic evolution of the encryption strength.

[0163] S5: Extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

[0164] S5 includes the following steps:

[0165] S51: extracting the first similarity comparison result and the second similarity comparison result, establishing a differential coupling equation, and performing stability constraints on the encryption strategy change rate;

[0166] For example, in this embodiment, a specific implementation strategy for constructing a differential coupling equation is provided, specifically:

[0167] ;

[0168] in, is the rate of change of encryption policy; is the partial derivative of the encryption strategy with respect to the public trend index, which indicates the sensitivity of the encryption strategy to changes in the public trend index;

[0169] is the rate of change of the open trend index; is the partial derivative of the encryption strategy with respect to the similarity coefficient ES, indicating the sensitivity of the encryption strategy to changes in the similarity coefficient ES; is the rate of change of the similarity coefficient ES;

[0170] For example, in this embodiment, it should be noted that: The negative sign indicates that the encryption policy changes in the opposite direction of the disclosure trend index. When the disclosure trend index increases, the encryption policy will be weakened to adapt to the new trend.

[0171] It should also be noted that Similar items between current transmission data and historical transmission data;

[0172] For example, in this embodiment, the stability constraint is specifically: 0.2 / day;

[0173] It should be noted that the constraints are set to ensure that the changes in encryption policies are not too drastic, thus ensuring the stability of the system;

[0174] S52: Decision output of the final encryption strategy, including:

[0175] when The final encryption strategy is: ;

[0176] when When , the final encryption strategy is ;

[0177] When the currently transmitted data does not meet the above conditions, the preliminary encryption strategy is output as the final encryption strategy;

[0178] in, The encryption policy at the previous moment.

[0179] For example, in this embodiment, the final decision output of the encryption policy is:

[0180] ;

[0181] in, For the final encryption strategy; is the encryption strategy at the previous moment;

[0182] In this embodiment, it should be noted that when , indicating that the current transmission data is highly similar to historical transmission data, and the public trend index is declining. At this time, to ensure data security, the encryption policy will be weakened, but will not be lower than 80% of the previous moment.

[0183] In this embodiment, it should be noted that when , indicating that a risk-triggered pattern mutation has been detected. At this time, the encryption strategy needs to be strengthened to deal with potential risks. The encryption strategy will be strengthened to 120% of the previous moment.

[0184] Example 3:

[0185] This embodiment provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0186] The processor executes the above-mentioned data encryption and desensitization calculation method by calling the computer program stored in the memory.

[0187] The electronic device may vary significantly due to different configurations or performance, and may include one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement the data encryption and desensitization calculation method provided in the above method embodiment. The electronic device may also include other components for implementing the device functions. For example, the electronic device may also have components such as wired or wireless network interfaces and input and output interfaces to facilitate data input and output. This embodiment will not be described in detail here.

[0188] Example 4:

[0189] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0190] When the computer program runs on a computer device, the computer device executes the above-mentioned data encryption and desensitization calculation method.

[0191] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0192] 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.

[0193] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.

[0194] The above embodiments can be implemented in whole or in part via 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. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0195] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0196] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0197] In the several embodiments provided by the present invention, 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 merely illustrative. For example, the division of units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, 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.

[0198] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0199] In addition, each functional unit in each embodiment of the present invention 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.

[0200] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0201] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. Data encryption and desensitization calculation method, characterized in that: The method comprises: S1: Obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance; S2: Collecting current transmission data and historical transmission data of agricultural insurance, performing a first similarity comparison between the current transmission data and the historical transmission data of agricultural insurance, and determining whether to reuse the historical encryption strategy based on the first similarity comparison result; S3: When the output result of S2 is to reuse the historical encryption strategy, extract the historical decrypted data in the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output the second similarity comparison result; S4: Extract the encryption strength of the data in the historical encryption strategy, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy; S5: Extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

2. The data encryption and desensitization calculation method according to claim 1, characterized in that: S2 includes the following specific steps: S21: standardize the current transmission data and historical transmission data of agricultural insurance, and add spatiotemporal tags to the current transmission data and historical transmission data of agricultural insurance; S22: Input the current transmission data and the historical transmission data output by S21 into the cross entropy quantitative evaluation model to evaluate the agricultural cross entropy similarity ACE between the current transmission data and the historical transmission data; S23: Extract the claim fraud factor from the crop characteristic factor and the agricultural cross entropy similarity and import them into the first similarity comparison strategy to obtain the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance.

3. The data encryption and desensitization calculation method according to claim 2, characterized in that: S2 also includes: S24: comparing the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data with the dynamic matching threshold, and reusing the historical encryption strategy when the similarity coefficient ES between the current agricultural insurance transmission data and the historical transmission data is greater than or equal to the dynamic matching threshold; When the similarity coefficient ES between the current transmission data and the historical transmission data of agricultural insurance is less than the dynamic similarity threshold, the encryption algorithm strength is improved and a new encryption scheme is rebuilt; The dynamic matching threshold is dynamically updated according to the seasonal disclosure factor in the historical decrypted data.

4. The data encryption and desensitization calculation method according to claim 3, characterized in that: S3 includes the following specific steps: S31: extract the historical decrypted data from the historical transmission data and calculate the decryption characteristic factor of the historical decrypted data, wherein the decryption characteristic factor includes: decryption time decay factor , decrypted data similarity factor , seasonal exposure factor and risk transmission factors ; S32: Import the decryption characteristic factors of the historical decrypted data into the time-weighted similarity evaluation strategy to calculate and obtain the time-weighted similarity index.

5. The data encryption and desensitization calculation method according to claim 4, characterized in that: S3 also includes the following specific steps: S33: Extract the time-weighted similarity index, perform a second similarity comparison between the historical decrypted data and the current transmission data, and obtain the data disclosure trend index ; ； in, is the temporal similarity index; is the constraint weight.

6. The data encryption and desensitization calculation method according to claim 5, characterized in that: S4 includes the following specific steps: S41: Extract the encryption strength of data in historical encryption strategies and construct an encryption strength dynamic evolution model. The encryption strength dynamic evolution model is specifically: ； in, is the encryption strength after dynamic evolution of encryption strength; The default encryption strength for the system; The threshold value for triggering encryption adjustment; It is a seasonal sensitive regulatory factor; The historical public trend volatility of the current transmission data; S42: Synchronously detect the similarity between current data and recent high-risk historical patterns, perform mutation detection on risk trigger patterns, and obtain detection status parameters ; S43: Outputting a preliminary encryption strategy, specifically including the encryption strength after the dynamic evolution of the encryption strength.

7. The data encryption and desensitization calculation method according to claim 6, characterized in that: S5 includes the following steps: S51: extracting the first similarity comparison result and the second similarity comparison result, establishing a differential coupling equation, and performing stability constraints on the encryption strategy change rate; S52: Decision output of the final encryption strategy, including: when The final encryption strategy is: ; when When , the final encryption strategy is ; When the currently transmitted data does not meet the above conditions, the preliminary encryption strategy is output as the final encryption strategy; in, The encryption policy at the previous moment.

8. A data encryption and desensitization computing device, configured to implement the data encryption and desensitization computing method according to any one of claims 1 to 7, characterized in that: The system comprises: Data feature extraction module, first similarity comparison module, second similarity comparison module, encryption strength evolution module and encryption strategy output module; The data feature extraction module is used to obtain historical planting data of the corresponding crops in agricultural insurance, and quantify the historical planting data into crop characteristic factors, which constitute the transmission data of agricultural insurance; The first similarity comparison module is used to collect current transmission data and historical transmission data of agricultural insurance, perform a first similarity comparison on the current transmission data of agricultural insurance and the historical transmission data, and determine whether to reuse the historical encryption strategy according to the first similarity comparison result; The second similarity comparison module is used to extract historical decrypted data from the historical transmission data, perform a second similarity comparison between the historical decrypted data and the current transmission data, and output a second similarity comparison result; The encryption strength evolution module is used to extract the encryption strength of data in historical encryption strategies, build an encryption strength dynamic evolution model, optimize the encryption strength of the data encryption strategy based on the second similarity comparison result, and output a preliminary encryption strategy; The encryption strategy output module is used to extract the first similarity comparison result and the second similarity comparison result, establish a differential coupling equation to constrain the stability of the encryption strategy change rate, and make a decision to output the final encryption strategy.

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

10. An electronic device, characterized in that: include: a memory for storing instructions; A processor is used to execute the instruction so that the device performs operations to implement the data encryption and desensitization calculation method as described in any one of claims 1 to 7.

Images