Cross-regional power grid data privacy protection collaborative analysis method and system

Abstract

The application discloses a cross-regional power grid data privacy protection collaborative analysis method and system, relates to the field of power system data security, and comprises the following steps: performing multidimensional attribute vector extraction of power grid data, and establishing a multidimensional attribute vector set; performing mapping matching of an encrypted graph based on the multidimensional attribute vector set, and establishing an encryption packaging scheme; analyzing a collaborative analysis task, and establishing an analysis result; after feedback to a data providing layer, performing power grid data dynamic adaptive analysis, and configuring a disturbance level control channel; after encrypting and packaging the power grid data by using the encryption packaging scheme, performing calling disturbance control of the packaged data by using the disturbance level control channel; and generating a collaborative risk prediction of the power grid according to a control result, and performing user feedback management. The application solves the technical problem that the existing cross-regional power grid data privacy protection collaborative analysis cannot balance data privacy protection and data availability, and achieves the technical effect of improving data availability under the premise of guaranteeing data privacy security.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system data security, in particular to a cross-regional power grid data privacy protection collaborative analysis method and system. BACKGROUND

[0002] In the field of power energy, the collaborative operation and management of cross-regional power grids are crucial for ensuring the stability of power supply, optimizing resource allocation, and improving the overall efficiency of the power grid. With the continuous improvement of informationization and intelligentization of power grids, the demand for sharing and collaborative analysis of cross-regional power grid data is increasingly urgent. However, the massive data privacy protection problem involved has become a key bottleneck restricting the collaborative development of power grids.

[0003] Currently, the main method to solve the problem of cross-regional power grid data privacy protection is to use traditional data encryption technology and access management strategies based on permission control. Traditional encryption technology ensures the confidentiality of data during transmission and storage by encrypting the data. Permission control access management strategies strictly control data access based on user roles and permissions. However, traditional encryption technology can only guarantee data security in a static state. In the context of cross-regional power grid collaborative analysis, data needs to be dynamically interacted and processed between different regions and different subjects. Simple static encryption cannot meet the complex collaborative analysis logic requirements and may significantly reduce data availability. Permission control-based access management strategies are difficult to achieve precise and flexible data access control in the face of complex multi-dimensional relationships between cross-regional power grid data, which may lead to data leakage risks and cannot meet the dual needs of cross-regional power grid data privacy protection and collaborative analysis.

[0004] At present, in the related technology, there is a technical problem of cross-regional power grid data privacy protection collaborative analysis that cannot balance data privacy protection and data availability. SUMMARY

[0005] The present application provides a cross-regional power grid data privacy protection collaborative analysis method and system, which uses multi-dimensional attribute vector extraction and encryption graph mapping matching technology. By extracting attribute vectors from multiple dimensions of power grid data such as data sensitivity, historical time series correlation, causal correlation, prediction target variables, and control intervention, and establishing a vector set, an encryption encapsulation scheme is generated through mapping and matching. Meanwhile, based on collaborative analysis task analysis, combined with dynamic adaptive analysis configuration disturbance level control channel, the channel is used to call and disturb the control of encrypted and encapsulated data, solving the technical problem of existing cross-regional power grid data privacy protection collaborative analysis that cannot balance data privacy protection and data availability, and achieving the technical effect of improving data availability in the collaborative analysis process under the premise of ensuring data privacy and security.

[0006] The application provides a cross-regional power grid data privacy protection collaborative analysis method, including: performing multi-dimensional attribute vector extraction of power grid data, establishing a multi-dimensional attribute vector set, the dimensions of the multi-dimensional attribute vector extraction including data sensitivity dimension, historical time sequence correlation dimension, causal correlation dimension, prediction target variable dimension, and control intervention dimension; performing mapping matching of the multi-dimensional attribute vector set to establish an encryption packaging scheme; after receiving a collaborative analysis task, analyzing the collaborative analysis task to establish an analysis result, the analysis result including an analysis logic abstract and a data type use declaration; after feeding back the analysis result to a data providing layer, performing power grid data dynamic adaptation analysis, configuring a disturbance level control channel based on a dynamic adaptation analysis result; after encrypting and packaging the power grid data by using the encryption packaging scheme, performing calling disturbance control of the packaged data by using the disturbance level control channel; generating a collaborative risk prediction of the power grid according to the calling disturbance control result, and performing user feedback management on the collaborative risk prediction.

[0007] In a possible implementation, after the analysis result is fed back to the data providing layer, the power grid data dynamic adaptation analysis is performed, and the disturbance level control channel is configured based on the dynamic adaptation analysis result, and the following processing is performed: the target power grid data is located by using the data providing layer; the use sensitivity is calculated by using the use sensitive analysis network of the data providing layer according to the target power grid data and the data type use declaration, and a first adaptation analysis result is generated; the analysis logic abstract is sent to the reversible backtracking network of the data providing layer, and then the original data restoration capability analysis of the target power grid data in the collaborative analysis task scene is performed, and a second adaptation analysis result is established; the sensitivity average of the multi-dimensional attribute vector set is obtained, and a third adaptation analysis result is established according to the sensitivity average; and the dynamic adaptation analysis result is established based on the first adaptation analysis result, the second adaptation analysis result and the third adaptation analysis result.

[0008] In a possible implementation, the use sensitivity is calculated by using the use sensitive analysis network of the data providing layer according to the target power grid data and the data type use declaration, and the following processing is performed: the data type use declaration is converted into a function chain structure by using the preprocessing layer of the use sensitive analysis network; the target power grid data is mapped into each function chain participating module, and a directly used field, a derived reasoning field and an indirect influence field are identified; the use path tension of each identified field is calculated by using the calculation layer of the use sensitive analysis network, and the use sensitivity calculation is completed according to the use path tension calculation result.

[0009] In a possible implementation, the calculation layer is as follows: ; wherein, the use sensitivity calculation result is represented, total number of fields, characterizing any one field, characterizing the base sensitive weight of the first field, characterizing whether the first field is directly used by the current use task, characterizing whether the first field is indirectly used by the task, characterizing the field use and control conflict degree of the first field, , weight factors of the indirect use component and the use control conflict component, respectively.

[0010] In a possible implementation manner, the disturbance level control channel is configured based on the dynamic adaptation analysis result, and the following processing is performed: a base trust level of the target power grid data is generated according to the set of multi-dimensional attribute vectors; a use trust level is established according to the data type use declaration; the field decision constraint is constructed by using the base trust level and the use trust level, and the disturbance level control channel is corrected by using the field decision constraint.

[0011] In a possible implementation manner, after the analysis logic summary is sent to the reversible backtracking network, the original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario is performed, and the following processing is performed: the data dependency structure in the analysis logic summary is extracted and converted into a data access graph; the field reconstruction chain is constructed by using the data access graph, and the field reconstruction chain represents the reverse restoration path; the reversibility index of each original data field is calculated by using the field reconstruction chain, and the feature dimensions of the calculation include the shortest path length of the original data field to the output result, the calculation feature type in the path, the participation frequency of the original data field, the statistical feature significance, and the stability of the field reconstruction chain; and the restoration capability analysis is completed based on the reversibility index.

[0012] In a possible implementation manner, after the collaborative analysis task is received, the following processing is performed: a task ontology recognition mechanism is activated, and the task intent deep semantic modeling based on the collaborative analysis task is performed by using the task ontology recognition mechanism; the conflict detection is performed by using the task intent deep semantic modeling result, and the conflict detection includes use overreach and use drift; and the conflict point prompt early warning is reported by using the conflict detection.

[0013] In a possible implementation manner, the disturbance level control channel is configured based on the dynamic adaptation analysis result, and the following processing is further performed: an adaptation game model of task efficiency and risk cost is established; the dynamic adaptation analysis result is synchronized to the adaptation game model, and the balance game is performed; and the disturbance level control channel is configured by using the balance game result.

[0014] In a possible implementation, the disturbance level control channel is configured by using the balanced game result, and the following processing is performed: a disturbance mapping table is created, which is one-to-one mapped with a task value; after evaluating the task value of the collaborative analysis task, the disturbance mapping table is called to establish a basic disturbance; a random disturbance factor is configured, and the basic disturbance, the random disturbance factor and the balanced game result are used to configure the disturbance level control channel.

[0015] The application also provides a cross-regional power grid data privacy protection collaborative analysis system, comprising: a multi-dimensional attribute vector extraction module, configured to perform multi-dimensional attribute vector extraction of power grid data, establish a multi-dimensional attribute vector set, and the dimensions of the multi-dimensional attribute vector extraction include data sensitivity dimension, historical time sequence correlation dimension, causal correlation dimension, prediction target variable dimension and control intervention dimension; an encryption packaging scheme establishment module, configured to perform mapping matching of an encryption graph based on the multi-dimensional attribute vector set, and establish an encryption packaging scheme; a collaborative analysis task analysis module, configured to analyze a collaborative analysis task after receiving the collaborative analysis task, and establish an analysis result, wherein the analysis result comprises an analysis logic abstract and a data type use declaration; a disturbance level control channel configuration module, configured to perform power grid data dynamic adaptation analysis after feeding back the analysis result to a data providing layer, and configure a disturbance level control channel based on a dynamic adaptation analysis result; a disturbance control calling module, configured to perform disturbance control calling of packaged data by using the disturbance level control channel after encrypting and packaging the power grid data by using the encryption packaging scheme; and a collaborative risk prediction generation module, configured to generate a collaborative risk prediction of the power grid according to a disturbance control calling result, and perform user feedback management on the collaborative risk prediction.

[0016] The cross-regional power grid data privacy protection collaborative analysis method and system provided in the application first perform multi-dimensional attribute vector extraction of power grid data, establish a multi-dimensional attribute vector set, and the dimensions of the multi-dimensional attribute vector extraction include data sensitivity dimension, historical time sequence correlation dimension, causal correlation dimension, prediction target variable dimension and control intervention dimension, then perform mapping matching of an encryption graph based on the multi-dimensional attribute vector set, establish an encryption packaging scheme, then analyze a collaborative analysis task after receiving the collaborative analysis task, establish an analysis result, wherein the analysis result comprises an analysis logic abstract and a data type use declaration, then perform power grid data dynamic adaptation analysis after feeding back the analysis result to a data providing layer, configure a disturbance level control channel based on a dynamic adaptation analysis result, then perform disturbance control calling of packaged data by using the disturbance level control channel after encrypting and packaging the power grid data by using the encryption packaging scheme, and finally generate a collaborative risk prediction of the power grid according to a disturbance control calling result, and perform user feedback management on the collaborative risk prediction. The technical effect of improving the usability of data in the collaborative analysis process under the premise of ensuring data privacy security is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below, and the flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application in this application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously according to needs. At the same time, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0018] Figure 1 The flowchart of the cross-regional power grid data privacy protection collaborative analysis method provided for the embodiments of the present application.

[0019] Figure 2 The structural diagram of the cross-regional power grid data privacy protection collaborative analysis system provided for the embodiments of the present application.

[0020] Explanation of reference signs: multi-dimensional attribute vector extraction module 10, encryption packaging scheme establishment module 20, collaborative analysis task analysis module 30, disturbance level control channel configuration module 40, call disturbance control module 50, collaborative risk prediction generation module 60. DETAILED DESCRIPTION

[0021] The above description is only a summary of the technical solutions of the present application, in order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0022] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings, and the described embodiments should not be regarded as limiting the present application, all other embodiments obtained by those skilled in the art without making creative labor belong to the scope of protection of the present application.

[0023] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict, and the term "first\second" referred to is only to distinguish similar objects, and does not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0024] The embodiments of the present application provide a cross-regional power grid data privacy protection collaborative analysis method, as shown in Figure 1 The method comprises the following steps:

[0025] Step S100, multi-dimensional attribute vector extraction of power grid data is performed, and a multi-dimensional attribute vector set is established, and the dimensions of the multi-dimensional attribute vector extraction include data sensitivity dimension, historical time sequence correlation dimension, causal correlation dimension, prediction target variable dimension and control intervention dimension.

[0026] Specifically, for the data sensitivity dimension, the risk level of data leakage is evaluated by an expert system, for example, a decision tree or a rule engine can be used to automatically evaluate and classify the sensitivity of the data. For the historical time sequence correlation dimension, time series analysis tools (such as the statsmodels library of Python) are used to extract time-related features, for example, ARIMA models or seasonal decomposition can be used to analyze time series data. For the causal correlation dimension, a causal inference framework (such as the DoWhy library) is applied to identify causal relationships, for example, Granger causality test or causal graph model can be used to determine the causal relationship between variables. For the prediction target variable dimension, based on the prediction target, relevant features are selected (such as using the feature_selection module of scikit-learn), for example, recursive feature elimination (RFE) or model-based feature selection methods can be used. For the control intervention dimension, the influence of control strategy on data is analyzed, and control-related features are extracted, for example, the specific influence of control strategy on data can be determined by simulation or historical data analysis.

[0027] For example, assume there is an electricity grid dataset containing the following fields: user ID, timestamp, power consumption (kWh), weather condition (sunny, cloudy, rainy), holiday (yes / no), device status (normal, malfunctioning). For the data sensitivity dimension, assess the sensitivity of each field, labeling user ID as "high sensitivity", power consumption as "medium sensitivity", and other fields like weather condition and holiday as "low sensitivity". For the historical temporal correlation dimension, analyze the trend of data over time, extracting hourly and daily averages of power consumption, as well as hourly and daily change rates. For the causal correlation dimension, use Granger causality tests to determine the causal relationship between weather condition and power consumption. For the prediction target variable dimension, select relevant features based on the prediction target, for example, if the target is to predict future power consumption, select past 24 hours of power consumption, past week of weather condition, and holiday information as prediction features. For the control intervention dimension, analyze the impact of control strategies on data, extracting time periods of demand response plan implementation and corresponding power consumption changes. Combine the extracted features into a set of multi-dimensional attribute vectors, each representing a feature set of a data record.

[0028] Step S200, mapping matching of the encryption atlas is performed with the multi-dimensional attribute vector set, and an encryption packaging scheme is established.

[0029] Specifically, an atlas is created that associates different data attribute groups with different encryption methods. These association rules can be stored through a database management system. For example, high sensitivity data is associated with CP-ABE encryption method, and low sensitivity data is associated with FHE-VTS encryption method. The multi-dimensional attribute vector extracted from step S100 is matched with the encryption atlas to identify the attributes of each data item and find the corresponding encryption method in the atlas. A machine learning classifier can be used to automatically match the encryption method. According to the mapping result, the most suitable encryption method is selected for each data item, and an encryption packaging scheme is established, which specifies how to encrypt the data and how to manage and control access to encrypted data. Security protocols and encryption standards (such as AES, RSA) can be used to achieve this. For example, if a data item is labeled as high sensitivity and needs strict access control, CP-ABE encryption method is selected.

[0030] For example, for high-sensitivity + controllable attributes, a policy-based CP-ABE + dynamic signature chain hash binding encryption method is used, allowing access only to specific policy signature chains matching the policy. For causal + predictive attributes, the polynomial approximate homomorphic encryption (HE-Poly) encryption method is used to preserve the gradient and residual direction of the model structure. This is suitable for scenarios that require predictive analysis in an encrypted state, such as the inference phase of machine learning models. For medium-sensitivity + derivable attributes, the perturbation injection secret state computation (Noisy Enc) encryption method is used to introduce semantically reversible perturbations into the secret state to protect the true change trajectory. This is suitable for scenarios with medium-sensitivity data that require some form of data analysis. For low-sensitivity + time series attributes, the fuzzy verifiable homomorphic sequence encryption (FHE-VTS) encryption method is used to ensure time series pattern analysis capabilities and hide node meaning. This is suitable for scenarios with low data sensitivity but the need to protect data time series patterns.

[0031] Consider the following power grid data attributes: Data A: High sensitivity, used for predictive analysis. Data B: Medium sensitivity, requiring time series analysis. Data C: Low sensitivity, requiring time series pattern protection. For Data A, due to its high sensitivity and predictive use, CP-ABE + dynamic signature chain hash binding is chosen to ensure data access only by authorized users and protect data integrity. For Data B, due to its medium sensitivity and the need for time series analysis, Noisy Enc is chosen to enable effective time series analysis while protecting data privacy. For Data C, due to its low sensitivity and the need for time series pattern protection, FHE-VTS is chosen to ensure accurate time series pattern analysis while concealing the data's specific meaning. This approach allows for the flexible selection of the most appropriate encryption method based on the specific attributes and usage scenarios of the data, ensuring effective data utilization while protecting data privacy.

[0032] Step S300: After receiving the collaborative analysis task, the collaborative analysis task is parsed to create a parsing result, which includes an analysis logic summary and a data type usage statement.

[0033] Specifically, a description of the collaborative analysis task is received from a user or other system, the task description is parsed using natural language processing (NLP) techniques to extract key information. For example, text classification is used to identify the task type (e.g., prediction, classification, clustering, etc.), and entity recognition is used to extract data fields and analysis targets. Based on the parsing results, an analysis logic summary is developed, including determining the steps of the analysis, such as data cleaning, feature engineering, model selection, parameter tuning, etc. For example, if the task is to predict power demand, the analysis logic can include steps such as time series analysis, feature selection, model training and validation, etc. The roles of different data types in the analysis task are clarified. For example, timestamps can be used for time series analysis, and weather conditions can be used as feature inputs to the prediction model. The data preprocessing requirements such as normalization, missing value handling, etc. can be included in the declaration.

[0034] In one possible implementation, after receiving the collaborative analysis task, step S300 further includes step S310 of activating a task ontology recognition mechanism, and using the task ontology recognition mechanism to perform deep semantic modeling of the task intent based on the collaborative analysis task. Specifically, using natural language processing (NLP) techniques and ontology methods, the task description is analyzed, key information is extracted, and a semantic model of the task is constructed. Through the task ontology recognition mechanism, the collaborative analysis task is deeply semantically modeled to accurately understand the intent and requirements of the task.

[0035] Step S320, using the results of the deep semantic modeling of the task intent to perform conflict detection, including purpose overreach and purpose drift. Specifically, based on the semantic modeling results obtained in step S310, the potential conflicts between the task intent and the data use policy are checked, including purpose overreach (the task intent exceeds the allowed use range of the data) and purpose drift (the task intent deviates from the original use of the data).

[0036] Step S330, using the conflict detection to report conflict point prompts for early warning. Specifically, using the results of the conflict detection, automatically generate early warning information, and notify relevant personnel through the user interface or message system.

[0037] For example, there is a power grid data analysis platform that needs to process power grid data from different regions and perform collaborative analysis tasks. A user submits a task that requires analyzing power demand in a specific region and predicting power load for the next week. The system activates the task ontology recognition mechanism and uses NLP technology to parse the task description. The system identifies key entities (such as "power demand", "specific region", "next week") and relationships (such as "analyze", "predict"). Based on the identified entities and relationships, the system constructs a semantic model that clearly defines the goal of the task as power demand analysis and load prediction. The system checks whether this task conflicts with existing data usage policies or rules. For example, it checks whether it is allowed to use data from a specific region for load prediction. If the policy states that certain data can only be used for internal analysis, and the task requires the results to be publicly released, this constitutes a use overreach. If the data is originally used for short-term load prediction, and the task requires long-term prediction, this constitutes a use drift. The system automatically detects these potential conflicts and assesses whether they violate data usage policies. If the system finds that the data usage required by the task exceeds the scope allowed by the policy, it generates a warning notification indicating "Use overreach detected: the task requires the results to be publicly released, but the policy states that the data can only be used for internal analysis." This warning is displayed to the task submitter through the user interface and sent to the system administrator via email or SMS. This implementation detects potential data usage conflicts in advance and prevents them, ensuring compliance with data usage and reducing the risk of data misuse.

[0038] Step S400, after feeding back the analysis result to the data providing layer, performing power grid data dynamic adaptation analysis, and configuring the perturbation level control channel based on the dynamic adaptation analysis result.

[0039] Specifically, according to the analysis result, the power grid data is adapted and analyzed, including data cleaning, feature conversion, data standardization, etc., to ensure that the data is suitable for collaborative analysis, i.e. the data format and content adapt to the specific analysis requirements, while considering data privacy protection. Based on the results of dynamic adaptation analysis, configure the perturbation level control channel, i.e. decide how much perturbation (such as adding noise) to introduce in the data to protect data privacy while not affecting the accuracy of data analysis. By controlling the level of perturbation, the balance between data privacy protection and data analysis accuracy is achieved.

[0040] In one possible implementation, after the analysis result is fed back to the data providing layer, the power grid data dynamic adaptation analysis is performed, and step S400 further includes step S410 to locate the target power grid data in the data providing layer. Specifically, using a data index or query system, according to the task requirements and data type declaration, locate the specific power grid data set, and accurately find the required power grid data in the data providing layer.

[0041] Step S420, the use-sensitive analysis network of the data providing layer is used to perform use sensitivity calculation according to the target power grid data and the data type use declaration, and a first adaptive analysis result is generated. Specifically, the use-sensitive analysis network of the data providing layer is used to calculate the sensitivity of the data in combination with the data type use declaration, and the risk level of the data under different uses is determined.

[0042] Step S430, the reversible backtracking network of the data providing layer is called, the analysis logic summary is sent to the reversible backtracking network, original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario is performed, and a second adaptive analysis result is established. Specifically, the reversible backtracking network of the data providing layer is called, the analysis logic summary is sent, and the reversibility of the data in the analysis process and the restoration capability of the original data are analyzed.

[0043] Step S440, the sensitivity mean of the multi-dimensional attribute vector set is obtained, and a third adaptive analysis result is established according to the sensitivity mean. Specifically, the sensitivity data is extracted from the multi-dimensional attribute vector set, and the mean is calculated.

[0044] Step S450, the dynamic adaptive analysis result is established based on the first adaptive analysis result, the second adaptive analysis result and the third adaptive analysis result. Specifically, based on the results of steps S420 to S440, the first, second and third adaptive analysis results are integrated to form a comprehensive dynamic adaptive analysis result.

[0045] For example, suppose we need to analyze the power grid data of two different regions (Region A and Region B) to predict future power demand and optimize grid operation. The data includes user ID, timestamp, power consumption, weather conditions, holidays, and device status, etc. First, use the data indexing system to locate the relevant power grid data sets of Region A and Region B from the data provision layer according to the task requirements (such as predicting power demand) and data type declarations (such as power consumption, weather conditions). Use the purpose-sensitive analysis network of the data provision layer to calculate the sensitivity of the data combined with the data type purpose declaration. For example, the sensitivity of user ID is marked as high, and the sensitivity of weather conditions is marked as low. Call the reversible backtracking network of the data provision layer, send the analysis logic summary, and analyze the reversibility of the data in the analysis process and the restoration ability of the original data. For example, evaluate whether accurate power consumption data can be restored without leaking user ID. Extract the sensitivity data from the multi-dimensional attribute vector set and calculate its mean value. For example, calculate the average sensitivity of all attributes. Integrate the above results to form a comprehensive dynamic adaptation analysis result to guide how to adjust the use and protection strategy of the data. This implementation enhances the data privacy protection measures through purpose sensitivity calculation and original data restoration ability analysis, ensuring the security of the data in the analysis process. By considering the average sensitivity of the multi-dimensional attribute vector, the reliability and accuracy of data analysis are improved.

[0046] In one possible implementation, the dynamic adaptation analysis result is used to configure the perturbation level control channel. Step S400 further includes step S460, establishing an adaptive game model of task efficiency and risk cost. Specifically, an adaptive game model is constructed, which considers the efficiency (such as analysis speed, accuracy) and risk cost (such as the possibility of privacy leakage, the degree of data distortion) of task execution. Define relevant parameters for the model, such as task type, data sensitivity, expected analysis result accuracy, privacy protection level, etc.

[0047] Step S470, synchronize the dynamic adaptation analysis result to the adaptive game model and execute the balanced game. Specifically, input the dynamic adaptation analysis result into the adaptive game model, run the model, and find the optimal solution or satisfactory solution by simulating different strategies and parameter settings, that is, maximize the efficiency of task execution while ensuring data privacy.

[0048] At step S480, the disturbance level control channel is configured using the balanced game result. Specifically, according to the balanced game result obtained at step S470, the disturbance level control channel is configured, including adjusting the encryption strength, the level of disturbance injection, etc. The configured disturbance level control channel is applied to the data encryption and analysis process to ensure that data privacy can be effectively protected when performing collaborative analysis tasks. This implementation can find the best balance between protecting data privacy and improving task execution efficiency by adapting the game model. Through dynamic adaptation analysis and balanced game, the system can adapt to different task requirements and data characteristics, and provide more flexible privacy protection strategies.

[0049] In a possible implementation, the disturbance level control channel is configured based on the dynamic adaptation analysis result, and step S400 further includes step S490 of generating a basic trust level of the target power grid data according to the multi-dimensional attribute vector set. Specifically, a basic trust level is generated for each data field or data set by analyzing factors such as the source of the data, the historical accuracy, and the collection method. The basic trust level is an initial trust level generated for the target power grid data based on the multi-dimensional attribute vector set of the data, which reflects the inherent credibility of the data.

[0050] At step S4100, a use trust level is established according to the data type use declaration. Specifically, according to the data type use declaration, the applicability and credibility of the data in this use are evaluated, and a use trust level is established, which reflects the credibility of the data in the specific use.

[0051] At step S4110, the field decision constraints are constructed using the basic trust level and the use trust level, and the disturbance level control channel is corrected using the field decision constraints. Specifically, the field decision constraints are constructed using the basic trust level and the use trust level, which are used to guide how to adjust the disturbance level control channel to ensure the privacy and usability of the data. According to the field decision constraints, the disturbance level control channel is corrected to ensure that the usability and analysis accuracy of the data are not affected while protecting the privacy of the data. This implementation can more accurately control the disturbance level of the data by establishing trust levels and field decision constraints, thereby reducing the impact on data analysis accuracy while protecting privacy.

[0052] For example, suppose a cross-regional power grid dataset containing user electricity information is being processed, and the goal is to analyze these data to predict power demand while protecting user privacy. First, the base trust level of each field of the dataset is evaluated. For example: user ID: the base trust level is low (e.g., 2 / 10) due to the involvement of personal privacy; electricity consumption: this is a relatively less sensitive indicator, and the base trust level is high (e.g., 8 / 10); timestamp: although the timestamp itself is not sensitive, it is associated with user behavior, so the trust level is medium (e.g., 5 / 10). Next, adjust the trust level according to the data usage declaration. For example: user ID: when used for predicting power demand, the usage trust level is further reduced due to privacy risks (e.g., 1 / 10); electricity consumption: directly used for prediction analysis, the usage trust level remains unchanged or slightly increases (e.g., 8 / 10 or 9 / 10); timestamp: if used to analyze the periodic changes of power demand, the usage trust level increases (e.g., 6 / 10). Finally, construct field decision constraints according to the base trust level and usage trust level, and correct the perturbation level control channel accordingly. For example: user ID: due to the low trust level, more perturbation (e.g., increase noise) needs to be introduced to protect user privacy; electricity consumption: due to the high trust level, less perturbation can be introduced to maintain the accuracy of the analysis; timestamp: the medium trust level means that perturbation and accuracy need to be balanced, and moderate perturbation can be selected.

[0053] In one possible implementation, the usage-sensitive analysis network utilizing the data providing layer performs usage sensitivity calculation according to the target grid data and the data type usage declaration, and step S420 further includes step S421 of transforming the data type usage declaration into a functional chain structure by using the preprocessing layer of the usage-sensitive analysis network. Specifically, the data type usage declaration is transformed into a functional chain structure by using the preprocessing layer of the usage-sensitive analysis network, i.e., the data usage is decomposed into a series of functional modules and their relationships, so as to better understand and analyze the data usage.

[0054] Step S422, map the target grid data into each module participating in the functional chain, identify the directly used fields, derived reasoning fields, and indirectly affected fields. Specifically, map the target grid data into each module participating in the functional chain, and identify different usage modes of data fields. Among them, the directly used fields are data fields directly used in analysis, such as electricity consumption. The derived reasoning fields are data fields inferred by analyzing the directly used fields, such as user behavior patterns. The indirectly affected fields are data fields that have indirect effects on the analysis results, such as weather conditions.

[0055] Step S423, use the calculation layer of the use-sensitive analysis network to perform use path tension calculation on each identified field, and complete use sensitivity calculation according to the use path tension calculation result, wherein the calculation layer is as follows:

[0056] ;

[0057] wherein, characterizes the use sensitivity calculation result, is the total number of fields, characterizes any one field, characterizes the base sensitivity weight of the th field, characterizes whether the th field is directly used by the current use task, characterizes whether the th field is indirectly used, characterizes the field use and control conflict degree of the th field, , are weight factors of the indirect use component and the use control conflict component, respectively. Specifically, the use path tension of each field is calculated to complete the use sensitivity calculation. The calculation layer of the use-sensitive analysis network is used to calculate according to the formula.

[0058] For example, assuming there is a power grid data set containing the following fields: user ID, power consumption, timestamp, weather condition. These data need to be analyzed to predict power demand while protecting user privacy. The data type use declaration is converted into a function chain structure, and in this example, the use declaration is "analyze power demand", which can be converted into the following function chain structure: function module 1: data collection (collect user ID, power consumption, timestamp, weather condition); function module 2: data preprocessing (clean and format data); function module 3: feature extraction (extract hour and date information from timestamp); function module 4: model training (use power consumption and weather condition to train a prediction model); function module 5: predict power demand (use the trained model to make predictions). Map the target power grid data into each function chain participating module, identify the directly used fields, derived reasoning fields, and indirectly affected fields, and in this example, the directly used fields are power consumption (directly used in model training and prediction), the derived reasoning fields are none (in this simple example, there are no data fields obtained through reasoning), and the indirectly affected fields are weather conditions. Use the calculation layer of the use-sensitive analysis network to perform use path tension calculation on each identified field, and complete use sensitivity calculation according to the use path tension calculation result. The example calculation process is as follows, for example, for user ID: base sensitivity weight = 0.8 (assuming that user ID is very sensitive), directly used = 0 (User ID is not directly used for prediction), indirect use = 1 (User ID indirectly affects prediction), use and control conflict = 0.5 (assuming that the use of User ID has some conflict), weight factor = 0.3, = 0.2, use sensitivity = 0.8 x (0 + 0.3 x 1 + 0.2 x 0.5) = 0.32. This implementation can more accurately calculate the use sensitivity of data by analyzing the different use of data fields in detail. By identifying and calculating the use sensitivity, sensitive data can be more targeted to protect and reduce the risk of privacy leakage.

[0059] In one possible implementation, after sending the analysis logic summary to the reversible backtracking network, the original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario is performed, and step S430 further includes step S431 of extracting the data dependency structure in the analysis logic summary and converting it into a data access graph. Specifically, the natural language processing (NLP) technology is used to analyze the analysis logic summary, and the data dependency structure is extracted from the analysis logic summary, including the direct and indirect dependency relationship between the data fields. The dependency relationship is converted into a data access graph using a graph database (such as Neo4j) or a graph processing library (such as GraphX), and the nodes in the graph represent the data fields and the edges represent the dependency relationship between the fields.

[0060] Step S432, constructing a field reconstruction chain using the data access graph, the field reconstruction chain representing the reverse restoration path. Specifically, starting from the output result node, the data access graph is traversed in reverse using a graph traversal algorithm (such as depth-first search DFS or breadth-first search BFS), and the path from the output result to each original data field is recorded during the traversal process. These paths constitute the field reconstruction chain, and these chains represent the path from the output result to the original data field in reverse.

[0061] Step S433, reconstruct the chain using the field to calculate the reversibility index of each original data field, the characteristic dimensions of the calculation include the shortest path length from the original data field to the output result, the calculation feature type in the path, the participation frequency of the original data field, the statistical feature significance, the stability of the field reconstruction chain, and the restoration ability analysis is completed based on the reversibility index. Specifically, the shortest path length from the original data field to the output result is calculated using a graph algorithm (such as Dijkstra algorithm). By analyzing the calculation operation in the logical summary or by recording the calculation nodes on the path during graph traversal, the calculation types involved in the path (such as addition, multiplication, aggregation function, etc.) are analyzed. The number of times of appearance of the original data field in all field reconstruction chains is counted as its participation frequency. The importance of the field in statistical analysis is evaluated using statistical methods (such as correlation analysis, feature importance score). The stability of the field reconstruction chain is evaluated by simulating different analysis scenarios, that is, the reliability of the chain in different scenarios. Based on these characteristic dimensions, the reversibility index of each field is calculated to help understand which data fields are more likely to be restored in collaborative analysis tasks, so as to take corresponding privacy protection measures. This implementation can more accurately identify and protect sensitive data by analyzing the reversibility of data fields in detail. By evaluating the restoration ability of data fields, data privacy protection and data usability can be better balanced.

[0062] In a possible implementation, the step S480 of configuring the perturbation level control channel using the balanced game result further includes step S481 of creating a perturbation mapping table, and the perturbation mapping table is one-to-one mapped with the task value. Specifically, the evaluation criteria of the task value are defined, including the urgency of the task, the influence on the decision, the sensitivity of the data, etc. A perturbation level is defined for each task value, and the perturbation level determines the degree of data perturbation. For example, a high-value task corresponds to a lower perturbation level, and a low-value task corresponds to a higher perturbation level. A database or a configuration file is used to store these mapping relationships, so as to quickly find when the task is executed.

[0063] Step S482, after evaluating the task value of the collaborative analysis task, the perturbation mapping table is called to establish the basic perturbation. Specifically, a pre-defined evaluation model or algorithm is used to evaluate the value of the task, such as using an expert system, a machine learning model or a simple rule engine. According to the evaluation result, the corresponding perturbation level is found from the perturbation mapping table as the basic perturbation.

[0064] Step S483, configure a random disturbance factor, and configure the disturbance level control channel using the basic disturbance, the random disturbance factor, and the balanced game result. Specifically, in order to increase the randomness of data protection, a random disturbance factor is introduced by generating a random number or using a random process (such as Gaussian noise). The balanced game result (such as the optimal or satisfactory solution) is applied to the configuration of the disturbance level control channel to ensure that the efficiency of task execution is maximized while protecting privacy. In combination with the basic disturbance, the random disturbance factor, and the balanced game result, the disturbance level control channel is configured, including adjusting the data encryption strength, the level of disturbance injection, etc. This implementation dynamically adjusts the disturbance level, and can flexibly protect data privacy according to different requirements and values of tasks.

[0065] Step S500, after the power grid data is encrypted and packaged using the encryption packaging scheme, the disturbance control of the packaged data is performed using the disturbance level control channel.

[0066] Specifically, the disturbance control of the data after encryption and packaging is performed using the configured disturbance level control channel, including introducing a certain degree of random noise into the data through a data disturbance algorithm, such as adding Gaussian noise or Laplace noise, increasing the protection of data privacy without significantly affecting the data analysis results.

[0067] Step S600, generating a collaborative risk prediction of the power grid according to the disturbance control result, and performing user feedback management on the collaborative risk prediction.

[0068] Specifically, based on the data after disturbance control, a collaborative risk prediction of the power grid is generated using a suitable analysis model (such as a machine learning model), including predicting power demand, power grid failure risk, etc. The collaborative risk prediction result is fed back to the user, and the user's feedback is collected through the design of the user interface or feedback collection tools, etc. to ensure that the user can understand and utilize the prediction result, and at the same time, the prediction model and analysis process are continuously optimized according to the user's feedback.

[0069] The embodiment of the present application adopts multi-dimensional attribute vector extraction and encryption atlas mapping matching technology, extracts attribute vectors from multiple dimensions of power grid data such as data sensitivity, historical time sequence correlation, causal correlation, prediction target variable, and control intervention, and establishes a vector set, and then maps and matches to generate an encryption packaging scheme. Meanwhile, based on collaborative analysis task analysis, the disturbance level control channel is configured by dynamically adapting the analysis, and the data after encryption and packaging is disturbed and controlled using the channel. Technical means such as this solve the technical problem that the existing cross-regional power grid data privacy protection collaborative analysis cannot balance data privacy protection and data usability, and achieve the technical effect of improving the usability of data in the collaborative analysis process on the premise of ensuring data privacy and security.

[0070] In the foregoing, reference is made to Figure 1 A cross-regional power grid data privacy protection collaborative analysis method according to an embodiment of the present application is described in detail. Next, a cross-regional power grid data privacy protection collaborative analysis system according to an embodiment of the present application will be described with reference to Figure 2 A cross-regional power grid data privacy protection collaborative analysis system according to an embodiment of the present application is described in detail. Next, a cross-regional power grid data privacy protection collaborative analysis system according to an embodiment of the present application will be described with reference to

[0071] The cross-regional power grid data privacy protection collaborative analysis system according to the embodiment of the present application is used to solve the technical problem that the existing cross-regional power grid data privacy protection collaborative analysis is difficult to balance data privacy protection and data availability, and achieve the technical effect of improving the availability of data in the collaborative analysis process on the premise of ensuring data privacy security. The cross-regional power grid data privacy protection collaborative analysis system comprises: a multi-dimensional attribute vector extraction module 10, an encryption packaging scheme establishment module 20, a collaborative analysis task analysis module 30, a disturbance level control channel configuration module 40, a disturbance control module 50, and a collaborative risk prediction generation module 60.

[0072] The multi-dimensional attribute vector extraction module 10 is used to perform multi-dimensional attribute vector extraction of power grid data, establish a multi-dimensional attribute vector set, and the dimensions of the multi-dimensional attribute vector extraction include data sensitivity dimension, historical time sequence correlation dimension, causal correlation dimension, prediction target variable dimension, and control intervention dimension. The encryption packaging scheme establishment module 20 is used to perform mapping matching of an encryption atlas based on the multi-dimensional attribute vector set, and establish an encryption packaging scheme. The collaborative analysis task analysis module 30 is used to analyze the collaborative analysis task after receiving the collaborative analysis task, and establish an analysis result, wherein the analysis result includes an analysis logic abstract and a data type use declaration. The disturbance level control channel configuration module 40 is used to perform power grid data dynamic adaptation analysis after feeding back the analysis result to the data providing layer, and configure a disturbance level control channel based on the dynamic adaptation analysis result. The disturbance control module 50 is used to perform disturbance control of the packaged data by using the disturbance level control channel after encrypting and packaging the power grid data by using the encryption packaging scheme. The collaborative risk prediction generation module 60 is used to generate a collaborative risk prediction of the power grid according to the disturbance control result, and perform user feedback management on the collaborative risk prediction.

[0073] The specific configuration of the disturbance level control channel configuration module 40 will be described in detail below. After the analysis result is fed back to the data providing layer, the power grid data dynamic adaptation analysis is performed, and the disturbance level control channel is configured based on the dynamic adaptation analysis result. The disturbance level control channel configuration module 40 can further include: a target power grid data positioning unit for positioning target power grid data in the data providing layer; a use sensitivity calculation unit for performing use sensitivity calculation on the target power grid data and the data type use declaration based on the use sensitivity analysis network of the data providing layer, generating a first adaptation analysis result; an original data restoration capability analysis unit for calling the reversible backtracking network of the data providing layer, sending the analysis logic summary to the reversible backtracking network, and performing original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario, establishing a second adaptation analysis result; a sensitivity mean value acquisition unit for acquiring the sensitivity mean value of the multi-dimensional attribute vector set, and establishing a third adaptation analysis result based on the sensitivity mean value; and a dynamic adaptation analysis result establishment unit for establishing the dynamic adaptation analysis result based on the first adaptation analysis result, the second adaptation analysis result, and the third adaptation analysis result.

[0074] The use sensitivity calculation unit can further include: a preprocessing subunit for converting the data type use declaration into a function chain structure by using the preprocessing layer of the use sensitivity analysis network; a field identification subunit for mapping the target power grid data into each function chain participating module to identify directly used fields, derived reasoning fields, and indirectly affected fields; and a use path tension calculation subunit for performing use path tension calculation on each identified field by using the calculation layer of the use sensitivity analysis network, and completing use sensitivity calculation based on the use path tension calculation result.

[0075] The calculation layer of the use path tension calculation subunit can further include: ; wherein, characterizes the use sensitivity calculation result, is the total number of fields, and characterizes any one field, characterizes the base sensitivity weight of the first field, characterizes whether the first field is directly used by the current use task, characterizes whether the first field is indirectly used by the task, characterizes the field use and control conflict degree of the first field, , weighting factors for indirect use components and use conflict components, respectively.

[0076] The configuration of the disturbance level control channel based on the dynamic adaptation analysis result can further include: a basic trust level generation unit configured to generate a basic trust level of the target power grid data according to the set of multi-dimensional attribute vectors; a use trust level establishment unit configured to establish a use trust level according to the data type use declaration; and a disturbance level control channel correction unit configured to construct a field decision constraint by using the basic trust level and the use trust level, and correct the disturbance level control channel by using the field decision constraint.

[0077] After the analysis logic summary is sent to the reversible backtracking network, the original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario can be performed. The original data restoration capability analysis unit can further include: a data access graph transformation subunit configured to extract a data dependency structure in the analysis logic summary and transform it into a data access graph; a field reconstruction chain construction subunit configured to construct a field reconstruction chain by using the data access graph, the field reconstruction chain representing a reverse restoration path; and a reversibility index calculation subunit configured to calculate a reversibility index of each original data field by using the field reconstruction chain, the characteristic dimensions of the calculation including a shortest path length of the original data field to the output result, a calculation feature type in the path, a participation frequency of the original data field, a statistical feature significance, and a stability of the field reconstruction chain, and the restoration capability analysis is completed based on the reversibility index.

[0078] Next, the specific configuration of the collaborative analysis task analysis module 30 will be described in detail. As described above, after receiving the collaborative analysis task, the collaborative analysis task analysis module 30 can further include: a task intention deep semantic modeling unit configured to activate a task ontology recognition mechanism and perform task intention deep semantic modeling based on the collaborative analysis task by using the task ontology recognition mechanism; a conflict detection unit configured to perform conflict detection by using the task intention deep semantic modeling result, the conflict detection including use overreach and use drift; and a conflict point prompt early warning reporting unit configured to report a conflict point prompt early warning by using the conflict detection.

[0079] The configuration of the disturbance level control channel based on the dynamic adaptation analysis result can further include: an adaptation game model establishment unit configured to establish an adaptation game model of task efficiency and risk cost; a balanced game unit configured to synchronize the dynamic adaptation analysis result to the adaptation game model and perform a balanced game; and a disturbance level control channel configuration unit configured to configure the disturbance level control channel by using the balanced game result.

[0080] The disturbance level control channel is configured by using the balanced game result, and the disturbance level control channel configuration unit can further include: a disturbance mapping table creating subunit configured to create a disturbance mapping table, the disturbance mapping table being one-to-one mapped with the task value; a basic disturbance establishing subunit configured to establish a basic disturbance by calling the disturbance mapping table after evaluating the task value of the collaborative analysis task; and a disturbance level control channel configuration subunit configured to configure a random disturbance factor, and configure the disturbance level control channel by using the basic disturbance, the random disturbance factor and the balanced game result.

[0081] The cross-regional power grid data privacy protection collaborative analysis system provided by the embodiments of the present application can execute the cross-regional power grid data privacy protection collaborative analysis method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0082] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and each unit and module included is only divided according to the functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0083] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps described in the present application can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A collaborative analysis method for cross-regional power grid data privacy protection, characterized by: The method comprises: Perform multi-dimensional attribute vector extraction on power grid data and establish a multi-dimensional attribute vector set. The dimensions of the multi-dimensional attribute vector extraction include data sensitivity dimension, historical time series correlation dimension, causal correlation dimension, prediction target variable dimension, and control intervention dimension. Performing mapping matching of the encrypted graph using the multidimensional attribute vector set to establish an encryption encapsulation scheme; After receiving the collaborative analysis task, the collaborative analysis task is parsed to create a parsing result, wherein the parsing result includes an analysis logic summary and a data type usage statement; After feeding back the analysis results to the data provision layer, performing dynamic adaptive analysis of the power grid data, and configuring the disturbance level control channel based on the dynamic adaptive analysis results; After the power grid data is encrypted and encapsulated using the encryption encapsulation solution, the call disturbance control of the encapsulated data is performed using the disturbance level control channel; Generating a collaborative risk prediction of the power grid based on the results of the disturbance control call, and performing user feedback management on the collaborative risk prediction; After the analysis result is fed back to the data providing layer, a dynamic adaptation analysis of the power grid data is performed, and a disturbance level control channel is configured based on the dynamic adaptation analysis result, including: Locating target power grid data using the data providing layer; Utilizing the usage sensitivity analysis network of the data providing layer to perform usage sensitivity calculation according to the target power grid data and the data type usage statement, to generate a first adaptation analysis result; Invoking the reversible traceability network of the data provision layer, sending the analysis logic summary to the reversible traceability network, performing original data restoration capability analysis of the target power grid data in the collaborative analysis task scenario, and establishing a second adaptation analysis result; Obtaining a sensitivity mean of the multidimensional attribute vector set, and establishing a third adaptation analysis result according to the sensitivity mean; Establishing the dynamic adaptation analysis result based on the first adaptation analysis result, the second adaptation analysis result, and the third adaptation analysis result; The use sensitivity analysis network using the data providing layer performs use sensitivity calculation according to the target power grid data and the data type use statement, including: Using a preprocessing layer of a usage-sensitive analysis network to convert the data type usage declaration into a function chain structure; Mapping the target power grid data to the modules involved in each functional chain, identifying directly used fields, derived reasoning fields, and indirectly affected fields; The calculation layer of the use sensitivity analysis network is used to calculate the use path tension of each identified field, and the use sensitivity calculation is completed based on the use path tension calculation results; After sending the analysis logic summary to the reversible traceability network, performing an analysis of the original data restoration capability of the target power grid data in the collaborative analysis task scenario includes: Extracting the data dependency structure in the analysis logic summary and converting it into a data access graph; Constructing a field reconstruction chain using the data access graph, wherein the field reconstruction chain represents a reverse restoration path; The reversibility index of each original data field is calculated using the field reconstruction chain. The calculated feature dimensions include the shortest path length from the original data field to the output result, the type of calculated features in the path, the participation frequency of the original data field, the statistical feature significance, and the stability of the field reconstruction chain. The reduction ability analysis was performed based on the reversibility index.

2. The cross-regional power grid data privacy protection collaborative analysis method according to claim 1, characterized in that: The computational layers are as follows: ； in, Characterize the results of sensitivity calculations for usage, is the total number of fields, Represents any field, Characterization The basic sensitivity weight of each field, Characterization Whether the field is directly used by the current purpose task, Characterization Whether the field is indirectly used by the task, Characterization The field usage and control conflict of each field, 、 are the weight factors for the indirect use component and the use control conflict component respectively.

3. The cross-regional power grid data privacy protection collaborative analysis method according to claim 1, characterized in that: The configuring of the disturbance level control channel based on the dynamic adaptation analysis result includes: generating a basic trust level of target power grid data according to the multidimensional attribute vector set; Establishing a usage trust level based on the data type usage statement; A field decision constraint is constructed using the basic trust level and the purpose trust level, and the disturbance level control channel is corrected using the field decision constraint.

4. The cross-regional power grid data privacy protection collaborative analysis method according to claim 1, characterized in that: After receiving the collaborative analysis task, the steps include: Activate the task ontology recognition mechanism and use the task ontology recognition mechanism to perform deep semantic modeling of task intent based on collaborative analysis tasks; Utilize the deep semantic modeling results of task intent to perform conflict detection, including use exceeding authority and use drift; Use conflict detection to report conflict points and provide early warning.

5. The cross-regional power grid data privacy protection collaborative analysis method according to claim 1, characterized in that: The configuration of the disturbance level control channel based on the dynamic adaptation analysis result further includes: Establish an adaptive game model of task efficiency and risk cost; Synchronizing the dynamic adaptation analysis results to the adaptation game model to execute the equilibrium game; The equilibrium game results are used to configure the perturbation hierarchy control channel.

6. The cross-regional power grid data privacy protection collaborative analysis method according to claim 5, characterized in that: The configuration of the disturbance level control channel using the equilibrium game result includes: Creating a disturbance mapping table, wherein the disturbance mapping table is mapped one-to-one with the task value; After evaluating the task value of the collaborative analysis task, calling the perturbation mapping table to establish a basic perturbation; A random perturbation factor is configured, and a perturbation level control channel is configured using the basic perturbation, the random perturbation factor, and the equilibrium game result.

7. A cross-regional power grid data privacy protection collaborative analysis system, characterized by: The system is used to implement the cross-regional power grid data privacy protection collaborative analysis method according to any one of claims 1 to 6, and the system includes: A multidimensional attribute vector extraction module is used to extract multidimensional attribute vectors from power grid data and establish a multidimensional attribute vector set. The dimensions of the multidimensional attribute vector extraction include data sensitivity, historical time series correlation, causal correlation, predicted target variable, and control intervention. An encryption encapsulation scheme establishing module, used to perform mapping matching of the encryption graph using the multi-dimensional attribute vector set to establish an encryption encapsulation scheme; A collaborative analysis task parsing module is used to parse the collaborative analysis task after receiving it and create a parsing result, wherein the parsing result includes an analysis logic summary and a data type usage statement; A disturbance level control channel configuration module is configured to feed back the analysis results to the data provision layer, perform dynamic adaptation analysis of the power grid data, and configure the disturbance level control channel based on the dynamic adaptation analysis results; A calling disturbance control module is used to perform calling disturbance control of the encapsulated data by using the disturbance level control channel after encrypting and encapsulating the power grid data by using the encryption encapsulation solution; The collaborative risk prediction generation module is used to generate a collaborative risk prediction of the power grid according to the result of calling disturbance control, and perform user feedback management on the collaborative risk prediction.

Images