An artificial intelligence-based shared service operation method and system

Abstract

The application provides a shared service operation method and system based on artificial intelligence, comprising the following steps: S1 receiving a service request initiated by a requester, wherein the service request comprises requester information, a service type, and required shared data description; S2 extracting requester features, data type features, time features, and region features according to the obtained service request, and constructing a demand feature matrix; S3 matching and calling corresponding data and mirror data from a shared database according to the obtained demand feature matrix; and S4 generating a corresponding encryption key based on the demand feature matrix, performing encryption processing on the mirror data, and transmitting the encrypted data to the requester. The shared service operation method and system help to realize the sharing and public use of data resources, and effectively improve the security and reliability in the data resource sharing process.

Description

Technical Field

[0001] This invention relates to the field of shared service operation and management, and in particular to a shared service operation method and system based on artificial intelligence. Background Technology

[0002] With the development of digital operation and management technology for the power industry, more and more services in the power industry rely on shared databases to be completed. By establishing shared databases, reliable and authentic data support can be provided for power service scenarios.

[0003] Currently, in the power sector, when service providers request data during service provision, it is difficult to accurately match the required data for different service requests, leading to reduced accuracy and utilization of shared data. Furthermore, in the operation and management of digital shared services, data security issues can easily arise when shared data is retrieved based on service requests. Therefore, there is an urgent need for a shared service operation method and system that balances data distribution security with meeting personalized needs. Summary of the Invention

[0004] To address the aforementioned problems, this invention aims to provide a shared service operation method and system based on artificial intelligence.

[0005] The objective of this invention is achieved through the following technical solution: In a first aspect, the present invention discloses a shared service operation method based on artificial intelligence, comprising: S1 receives a service request initiated by the requester, wherein the service request includes requester information, service type, and description of the required shared data; S2 extracts requester characteristics, data type characteristics, time characteristics, and region characteristics from the obtained service requests to construct a demand characteristic matrix; S3 matches and retrieves the corresponding data from the shared database based on the obtained demand feature matrix, and retrieves the corresponding mirror data; S4 generates a corresponding encryption key based on the demand feature matrix to encrypt the mirror data and transmits the encrypted data to the requester.

[0006] Preferably, the method further includes: AS1 performs security verification on the requester's access request and obtains the security verification result from the requester.

[0007] Preferably, step S1 includes: The service request initiated by the requesting party includes a request form, which records the requesting party's information, the type of service provided by the shared data, and a description of the required shared data.

[0008] Preferably, step S2 includes: Based on the obtained service request, the requester information is used to construct the first-level feature. ;in This represents the requester's identity feature vector; The second-level feature is constituted based on the service type information provided by the shared data. Where TY represents the service type feature vector; Based on the descriptive information of the shared data, the time range and location information of the required data are extracted using semantic features to form the third-level features. ,in Represents a feature vector over a time range. Represents the feature vector of the attribution location; A demand feature matrix is ​​constructed based on the obtained primary, secondary, and tertiary features. .

[0009] Preferably, in step S3, matching and retrieving corresponding data from the shared database based on the obtained demand feature matrix and retrieving corresponding mirror data specifically includes: Based on the acquired requirement feature matrix, the first-level and second-level features are matched with the preset permission level vector to obtain the corresponding permission level, and the matching data range is locked in the shared database according to the permission level. Based on the third-level feature, match the data that matches the third-level feature in the shared database, and extract the corresponding mirror data based on the matched data.

[0010] Preferably, the shared database stores power grid business data collected and recorded under different power grid scenarios. Each power grid business data carries corresponding data type, permission level, timestamp information and data source information, which together form the data's metadata feature vector. Step S3 includes: The requester's identity permission level is obtained based on the requester's identity feature vector of the first-level features; the service permission level corresponding to the service type is obtained based on the service type feature vector of the second-level features; and the corresponding range of shared data is locked from the shared database based on the identity permission level and the service permission level. Similarity analysis is performed on the third-level features of the demand feature matrix and the metadata feature vectors of the shared data within the matching range. When the similarity exceeds the preset standard, the corresponding shared data is marked as matching data, and the corresponding mirror data is further extracted based on all the matching data.

[0011] Preferably, in step S4, a corresponding encryption key is generated based on the demand feature matrix to encrypt the mirror data, and the encrypted data is transmitted to the requester, specifically including: Calculate the hash feature value of the obtained requirement feature matrix and generate the encryption key:

[0012] in, This represents the encryption key. Indicates based on The key derivation function of a hash function. Indicates a splicing operation; The image data is encrypted using the obtained encryption key to obtain encrypted data. ; The encrypted data is transmitted to the requester.

[0013] Preferably, step S4 further includes: After obtaining the encrypted data Z, the encrypted data Z is transmitted to the HSM security management system, and a data return instruction is transmitted to the requester. This allows the requester to respond to the received return instruction, extract the same demand feature matrix based on its own service request, calculate the hash feature value of the matrix, generate a decryption key, and send it to the HSM security management system. The HSM security management system then decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

[0014] Preferably, step S4 further includes: the requester's data access point is also equipped with a PMU synchronization phasor measurement device, and the requester's local power grid frequency is obtained through the PMU synchronization phasor measurement device. ; When the requesting party sends the decryption key to the HSM security management system and requests the HSM security management system to decrypt the encrypted data, it also sends its own identity information and real-time local power grid frequency information. The HSM safety management system, based on the identity information and corresponding timestamp information sent by the requester, retrieves the actual power grid frequency at the corresponding timestamp from the shared database for the region recorded by the requester. Furthermore, the power grid state verification factor was calculated. ;in This represents the preset security sensitivity coefficient. When based on the obtained power grid state verification factor ,when Greater than the preset standard value When the requester's access point is secure, the system further decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

[0015] Secondly, this invention discloses an artificial intelligence-based shared service operation system, including a request module, a feature extraction module, a demand matching module, and a resource allocation module; wherein, The request module is used to receive service requests initiated by the requester, which include requester information, service type, and description of the required shared data. The feature extraction module is used to extract requester features, data type features, time features, and regional features from the obtained service requests, and construct a demand feature matrix; The demand matching module is used to match and retrieve the corresponding data from the shared database based on the obtained demand feature matrix, and retrieve the corresponding mirror data. The resource distribution module is used to generate corresponding encryption keys based on the demand feature matrix, encrypt the image data, and transmit the encrypted data to the requester.

[0016] The beneficial effects of this invention are as follows: Based on the shared service operation method and system proposed in this invention, when the server receives a service request from a data requester, it first extracts features from the service request and constructs a demand feature matrix. This demand feature matrix provides a multi-dimensional and accurate feature representation of the service request. Furthermore, based on the feature demand matrix, intelligent retrieval is performed to accurately match and retrieve the most suitable mirrored data resources from the shared database, significantly improving matching efficiency and resource utilization. After matching the required data, the data mirror retrieved from the shared database is encrypted. During encryption, the encryption key is generated using the constructed demand feature matrix. This dynamic encryption method effectively improves the security of shared data retrieval. This contributes to improving the overall intelligence and security performance of the shared service process, from request understanding and intelligent matching to secure distribution. Attached Figure Description

[0017] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the steps of a shared service operation method based on artificial intelligence, as shown in an embodiment of the present invention. Figure 2 This is a framework diagram of an artificial intelligence-based shared service operation system according to an embodiment of the present invention. Detailed Implementation

[0019] The present invention will be further described in conjunction with the following application scenarios.

[0020] See Figure 1The embodiment illustrates an artificial intelligence-based shared service operation method, including: S1 receives a service request initiated by the requester, wherein the service request includes requester information, service type, and description of the required shared data; S2 extracts requester characteristics, data type characteristics, time characteristics, and region characteristics from the obtained service requests to construct a demand characteristic matrix; S3 matches and retrieves the corresponding data from the shared database based on the obtained demand feature matrix, and retrieves the corresponding mirror data; S4 generates a corresponding encryption key based on the demand feature matrix to encrypt the mirror data and transmits the encrypted data to the requester.

[0021] In the above embodiments of the present invention, when the server receives a service request from a data requester, it first extracts features from the service request and constructs a demand feature matrix. This demand feature matrix provides a multi-dimensional and accurate representation of the service request. Furthermore, based on the demand feature matrix, intelligent retrieval is performed to accurately match and retrieve the most suitable mirrored data resources from the shared database, significantly improving matching efficiency and resource utilization. After matching the required data, the data mirror retrieved from the shared database is encrypted. During encryption, the encryption key is generated using the constructed demand feature matrix. This dynamic encryption method effectively improves the security of shared data retrieval. This contributes to improving the overall intelligence and security performance of the shared service, from request understanding and intelligent matching to secure distribution.

[0022] In one scenario, the above method can be built on an operation server or other management system for a shared database. The operation server can provide power grid data support for different shared service modules. When the requester runs power grid services for different scenarios in the service module, it can obtain the power grid business data required by the power grid service from the shared database through the operation server and rely on the obtained power grid business data to complete the corresponding power grid service.

[0023] The power grid services include power grid status analysis, load forecasting, emergency command, electricity bill inquiry, and other power grid services designed for different power grid business scenarios.

[0024] Preferably, the method further includes: AS1 performs security verification on the requester's access request and obtains the security verification result from the requester.

[0025] Before the server receives the service request from the requester, it first performs a security verification of the requester's identity information. Once the security verification is successful, the server will then receive the service request from the requester.

[0026] Preferably, step S1 includes: The service request initiated by the requesting party includes a request form, which records the requesting party's information, the type of service provided by the shared data, and a description of the required shared data.

[0027] In one scenario, the requester information includes the requester's identity information, such as organization code and unit name; the service type information includes the type of service for which the shared data needs to be used, such as status analysis, business query, and fault warning; and the shared data description information includes a description of the shared data required, which generally includes the required data type, as well as key information such as the time range and location of the data.

[0028] In one scenario, the service types include: power plant load monitoring, substation operation monitoring, line monitoring, load forecasting center, new energy power generation forecasting, meteorological monitoring and forecasting, equipment asset recording, fault repair, emergency command, customer service, electricity management, power grid planning, safety and operation management, integrated energy services, and other service types corresponding to different business scenarios.

[0029] When a requester needs to access specific power grid data to support different power grid services, the requester generates a service request and sends it to the operations server. The operations server then verifies, matches, and processes the service request, returning the necessary power grid data to support the requester in completing the corresponding power grid service.

[0030] The service request sent by the requester can be generated through a form or a command.

[0031] Preferably, step S2 includes: Based on the obtained service request, the requester information is used to construct the first-level feature. ;in This represents the requester's identity feature vector; The second-level feature is constituted based on the service type information provided by the shared data. Where TY represents the service type feature vector; Based on the descriptive information of the shared data, the time range and location information of the required data are extracted using semantic features to form the third-level features. ,in This represents the feature vector of the required data type. Represents a feature vector over a time range. Represents the feature vector of the attribution location; A demand feature matrix is ​​constructed based on the obtained primary, secondary, and tertiary features. .

[0032] In the above implementation, the server extracts key feature information from the obtained service request. The first feature is based on the requester's identity information, the second feature is based on the service type information, and the third feature is based on the required data type and conditions. By using feature information in three dimensions, the characteristics of the power grid business data required by the current service request can be comprehensively and accurately represented. This helps to improve the adaptability and accuracy of subsequent matching of corresponding data from the shared database based on the feature vector matrix.

[0033] In one scenario, the requester's identity feature vector is composed of the requester's unique ID and permission level (e.g., G=T3+688713), while the service type feature vector is composed of the service code corresponding to the power grid service (e.g., TY=0084A). The shared data description generally includes the time range, data type and regional range, security level range, and data type of the data to be shared. Based on the description information of the shared data, the feature vector of the required data type, as well as the time range feature vector and the location feature vector of the required data are finally determined.

[0034] In one scenario, based on the form information in the service request—specifically, the distribution network status data for area B within the past 60 minutes required by the fault management center in its fault analysis request for area B—the following features can be extracted: First-level feature: [Fault Management Center, T1 permission level]; Second-level feature: [Real-time fault analysis]; Third-level feature: [Distribution network status data; K time period; Area B]; A requirement feature matrix is ​​constructed based on these three levels of features.

[0035] Preferably, in step S3, matching and retrieving corresponding data from the shared database based on the obtained demand feature matrix and retrieving corresponding mirror data specifically includes: Based on the acquired requirement feature matrix, the first-level and second-level features are matched with the preset permission level vector to obtain the corresponding permission level, and the matching data range is locked in the shared database according to the permission level. Based on the third-level feature, match the data that matches the third-level feature in the shared database, and extract the corresponding mirror data based on the matched data.

[0036] Preferably, the shared database stores power grid business data collected and recorded under different power grid scenarios. Each power grid business data carries corresponding data type, permission level, timestamp information and data source information, which together form the data's metadata feature vector.

[0037] Based on the feature information of the feature vector matrix, and then based on the metadata feature vector of the power grid business data stored in the shared database, a matching analysis is performed to obtain data that meets the conditions or has high feature similarity and to extract the corresponding mirror data.

[0038] Preferably, step S3 includes: The requester's identity permission level is obtained based on the requester's identity feature vector of the first-level features; the service permission level corresponding to the service type is obtained based on the service type feature vector of the second-level features; and the corresponding range of shared data is locked from the shared database based on the identity permission level and the service permission level.

[0039] In one scenario, a shared database contains power grid business data collected and recorded under different power grid scenarios. These scenarios include: power plant load monitoring, substation operation monitoring, line monitoring, load forecasting center, new energy power generation forecasting, meteorological monitoring and forecasting, equipment asset records, fault repair, emergency command, customer service, electricity management, power grid planning, safety and operation management, integrated energy services, and other data sources corresponding to different business scenarios. The acquired power grid business data includes real-time / near real-time SCADA measurement data, PMU data, equipment status monitoring data (online monitoring), power generation plans, load forecasting, new energy power forecasting, power grid models, topology information, and equipment management departments need to comprehensively consider equipment ledger information, historical defect / fault records, inspection reports, online monitoring data (such as oil chromatography, partial discharge, temperature, vibration), test data, environmental data, etc., to assess equipment health status, predict fault risks, and optimize maintenance plans. This includes basic equipment information (ledger), historical operation and maintenance records (defects, faults, maintenance), real-time / historical online monitoring data, inspection results, preventive test reports, and environmental data. The data includes: meteorological and pollution data, GIS spatial information, fault trip signals, protection action information, SCADA remote signaling changes, fault indicator signals, power outage range analysis results (based on topology), affected customer information (customer-transformer relationship), GIS geographic information, emergency repair resource status and trajectory, emergency repair progress, power restoration notice, customer basic files, real-time / historical metered electricity (AMI), electricity bill information, power outage plans and fault outage information, application process status, service work order status, adjustable load resource information (capacity, status), electricity price information, long-term historical load data, load density data, load forecast results, new energy development plans and output characteristics, power grid equipment ledger and capacity, power grid topology model, GIS spatial data and land information, regional economic development data, work plans, work permit / operation ticket information, personnel qualification information, real-time personnel location and trajectory, on-site video images, equipment energized / de-energized status, GIS geographic information and risk labeling, user electricity consumption data (refined), power grid operation status (affecting access), distributed energy output data, meteorological data, and other user energy data (if any), etc.

[0040] Preferably, step S3 includes: Similarity analysis is performed on the third-level features of the demand feature matrix and the metadata feature vectors of the shared data within the matching range. When the similarity exceeds the preset standard, the corresponding shared data is marked as matching data, and the corresponding mirror data is further extracted based on all the matching data.

[0041] Preferably, in step S4, a corresponding encryption key is generated based on the demand feature matrix to encrypt the mirror data, and the encrypted data is transmitted to the requester, specifically including: Calculate the hash feature value of the obtained requirement feature matrix and generate the encryption key:

[0042] in, This represents the encryption key. Indicates based on The key derivation function of a hash function. Indicates a splicing operation; These represent the first-level features, second-level features, and third-level features in the demand feature matrix, respectively. The image data is encrypted using the obtained encryption key to obtain encrypted data. ; The encrypted data is transmitted to the requester.

[0043] In the above embodiments, the acquired image data is first encrypted using an encryption process before being transmitted to the requester. A scheme is also proposed to generate an encryption key based on a demand feature matrix corresponding to the service request. Encrypting the image data using a dynamically generated key further enhances data encryption security.

[0044] Preferably, step S4 further includes: After obtaining the encrypted data Z, the encrypted data Z is transmitted to the HSM security management system, and a data return instruction is transmitted to the requester. This allows the requester to respond to the received return instruction, extract the same demand feature matrix based on its own service request, calculate the hash feature value of the matrix, generate a decryption key, and send it to the HSM security management system. The HSM security management system then decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

[0045] In one scenario, the HSM destroys the acquired decryption key and / or encrypted data after completing the decryption process to improve data security.

[0046] In the above implementation, after obtaining the encrypted data, it is not directly transmitted to the requester, but rather transmitted to the HSM security management system for temporary management. The requester then establishes a data connection with the corresponding HSM security management system (based on its service request), and, based on its own service request, obtains the first-level, second-level, and third-level features using the same method / rules, and then uses the same hash key derivation function (…). The system generates a decryption key and transmits it to the HSM security management system. The HSM security management system then decrypts the encrypted data using the decryption key and transmits the decrypted power grid business data back to the requesting party. After transmitting the decrypted power grid business mirror data to the requesting party, the HSM security management system deletes the relevant data and key information.

[0047] The proposed indirect data decryption and transmission method based on the HSM security management system reduces the probability of targeted data interception and improves data transmission security by eliminating the direct transmission of encrypted data from the operations server to the requester. Furthermore, the encrypted data is encrypted using a dynamic encryption key generated based on the characteristics corresponding to the service request. The encryption and decryption keys are generated independently on the operations server and the requester respectively, without being transmitted, effectively reducing the risk of key interception during transmission. The HSM security management system, responsible for data storage, does not handle key storage management; encrypted data is destroyed immediately after successful decryption and transmission, further reducing the risk of data leakage even if the data management center is attacked. This comprehensively improves the security of power grid business data distribution and transmission during shared services.

[0048] In addition, considering that when the requester requests the decryption of power grid business data from the HSM security management system based on the generated decryption key, there is also the possibility that the request may be forged to obtain the data, the present invention further proposes a dynamic verification method based on the HSM security management system and the requester to further improve the security of decrypted data distribution.

[0049] Preferably, step S4 further includes: The requesting party's data access point is also equipped with a PMU (Phasor Measurement Unit) synchronization phasor measurement device, which is used to obtain the current local power grid frequency of the requesting party. ; When the requesting party sends the decryption key to the HSM security management system and requests the HSM security management system to decrypt the encrypted data, it also sends its own identity information and real-time local power grid frequency information. The HSM safety management system, based on the identity information and corresponding timestamp information sent by the requester, retrieves the actual power grid frequency at the corresponding timestamp from the shared database for the region recorded by the requester. Furthermore, the power grid state verification factor was calculated. ;in This represents the preset security sensitivity coefficient. When based on the obtained power grid state verification factor When it is greater than the preset standard value When the requester's access point is secure, the system further decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

[0050] In one scenario, when retrieving the actual power grid frequency of the region corresponding to the requester in the shared database, PMU measurement data of the same time and region can be obtained from the SCADA / Wide Area Measurement System of the dispatch center at the same time and in the same region based on the regional information corresponding to the requester's identity, and used as the actual power grid frequency of that region.

[0051] In one scenario, the accuracy between the acquired local power grid frequency and the actual acquired regional power grid frequency reaches ±0.01 Hz or higher. In the above implementation, during the process of the requester requesting decrypted data from the HSM security management system, the authenticity of the requester is further verified by the power grid frequency characteristics of the requester's access point. Specifically, the security of the requester's access status is verified based on the local power grid frequency characteristics obtained by the requester and the actual power grid frequency characteristics of the requester's area obtained from the database (since the requester can only obtain its own power grid frequency information and not the power grid frequency information of its area, it can be determined whether the requester's access point is consistent with the location where the requester should be). The security verification is completed using the proposed power grid status verification factor. This further improves the security of power grid business data distribution.

[0052] See Figure 2 It demonstrates an AI-based shared service operation system, including a request module, a feature extraction module, a demand matching module, and a resource allocation module; among which, The request module is used to receive service requests initiated by the requester, which include requester information, service type, and description of the required shared data. The feature extraction module is used to extract requester features, data type features, time features, and regional features from the obtained service requests, and construct a demand feature matrix; The demand matching module is used to match and retrieve the corresponding data from the shared database based on the obtained demand feature matrix, and retrieve the corresponding mirror data. The resource distribution module is used to generate corresponding encryption keys based on the demand feature matrix, encrypt the image data, and transmit the encrypted data to the requester.

[0053] Preferably, the system also includes an access management module; wherein, The access management module is used to perform security verification on the requester's access request and obtain the security verification result from the requester.

[0054] It should be noted that the modules in the AI-based shared service operation system shown above are also used to achieve, for example... Figure 1 The corresponding steps and specific implementation methods in the AI-based shared service operation method shown herein will not be repeated here.

[0055] It should be noted that the functional units / modules in the various embodiments of the present invention can be integrated into one processing unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated into one unit / module. The integrated unit / module described above can be implemented in hardware or in the form of software functional units / modules.

[0056] From the above description of the embodiments, those skilled in the art will clearly understand that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field-Programmable Gate Array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein, or combinations thereof. For software implementation, some or all of the processes of the embodiments can be implemented by a computer program instructing the associated hardware. During implementation, the program can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code having the form of instructions or data structures and accessible to a computer.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should be able to analyze that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A shared service operation method based on artificial intelligence, characterized in that, include: S1 receives a service request initiated by the requester, wherein the service request includes requester information, service type, and description of the required shared data; S2 extracts requester characteristics, data type characteristics, time characteristics, and region characteristics from the obtained service requests to construct a demand characteristic matrix; Specifically, it includes: Based on the obtained service request, the requester information is used to construct the first-level feature. ;in This represents the requester's identity feature vector; The second-level feature is constituted based on the service type information provided by the shared data. Where TY represents the service type feature vector; Based on the descriptive information of the shared data, the time range and location information of the required data are extracted using semantic features to form the third-level features. ,in Represents a feature vector over a time range. Represents the feature vector of the attribution location; A demand feature matrix is ​​constructed based on the obtained primary, secondary, and tertiary features. ; S3 matches and retrieves the corresponding data from the shared database based on the obtained demand feature matrix, and retrieves the corresponding mirror data; S4 generates a corresponding encryption key based on the demand feature matrix to encrypt the image data and transmits the encrypted data to the requester; specifically including: Calculate the hash feature value of the obtained requirement feature matrix and generate the encryption key: in, This represents the encryption key. Indicates based on The key derivation function of a hash function. Indicates a splicing operation; The image data is encrypted using the obtained encryption key to obtain encrypted data. ; After obtaining the encrypted data Z, the encrypted data Z is transmitted to the HSM security management system, and a data return instruction is transmitted to the requester. This allows the requester to respond to the received return instruction, extract the same demand feature matrix based on its own service request, calculate the hash feature value of the matrix, generate a decryption key, and send it to the HSM security management system. The HSM security management system then decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

2. The shared service operation method based on artificial intelligence according to claim 1, characterized in that, The method also includes: The system performs security verification on the requester's access request and obtains the security verification result from the requester.

3. The shared service operation method based on artificial intelligence according to claim 1, characterized in that, Step S1 includes: The service request initiated by the requesting party includes a request form, which records the requesting party's information, the type of service provided by the shared data, and a description of the required shared data.

4. The shared service operation method based on artificial intelligence according to claim 1, characterized in that, In step S3, based on the obtained demand feature matrix, the corresponding data is matched and retrieved from the shared database, and the corresponding mirror data is retrieved. Specifically, this includes: Based on the acquired requirement feature matrix, the first-level and second-level features are matched with the preset permission level vector to obtain the corresponding permission level, and the matching data range is locked in the shared database according to the permission level. Based on the third-level feature, match the data that matches the third-level feature in the shared database, and extract the corresponding mirror data based on the matched data.

5. The shared service operation method based on artificial intelligence according to claim 4, characterized in that, The shared database stores power grid business data collected and recorded under different power grid scenarios. Each power grid business data carries corresponding data type, permission level, timestamp information and data source information, which together form the data's metadata feature vector. Step S3 includes: The requester's identity permission level is obtained based on the requester's identity feature vector of the first-level features; the service permission level corresponding to the service type is obtained based on the service type feature vector of the second-level features; and the corresponding range of shared data is locked from the shared database based on the identity permission level and the service permission level. Similarity analysis is performed on the third-level features of the demand feature matrix and the metadata feature vectors of the shared data within the matching range. When the similarity exceeds the preset standard, the corresponding shared data is marked as matching data, and the corresponding mirror data is further extracted based on all the matching data.

6. The shared service operation method based on artificial intelligence according to claim 1, characterized in that, The requesting party's data access point is also equipped with a PMU (Phasor Measurement Unit) synchronization phasor measurement device, which is used to obtain the current local power grid frequency of the requesting party. ; When the requesting party sends the decryption key to the HSM security management system and requests the HSM security management system to decrypt the encrypted data, it also sends its own identity information and real-time local power grid frequency information. The HSM safety management system, based on the identity information and corresponding timestamp information sent by the requester, retrieves the actual power grid frequency at the corresponding timestamp from the shared database for the region recorded by the requester. ; And further calculate the power grid state verification factor. ;in This represents the preset security sensitivity coefficient. When based on the obtained power grid state verification factor ,when Greater than the preset standard value When the requester's access point is secure, the system further decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

7. A shared service operation system based on artificial intelligence, characterized in that, It includes a request module, a feature extraction module, a demand matching module, and a resource allocation module; among which, The request module is used to receive service requests initiated by the requester, which include requester information, service type, and description of the required shared data. The feature extraction module is used to extract requester features, data type features, time features, and region features from the acquired service requests, and construct a demand feature matrix; specifically including: Based on the obtained service request, the requester information is used to construct the first-level feature. ;in This represents the requester's identity feature vector; The second-level feature is constituted based on the service type information provided by the shared data. Where TY represents the service type feature vector; Based on the descriptive information of the shared data, the time range and location information of the required data are extracted using semantic features to form the third-level features. ,in Represents a feature vector over a time range. Represents the feature vector of the attribution location; A demand feature matrix is ​​constructed based on the obtained primary, secondary, and tertiary features. ; The demand matching module is used to match and retrieve the corresponding data from the shared database based on the obtained demand feature matrix, and retrieve the corresponding mirror data. The resource distribution module is used to generate corresponding encryption keys based on the demand feature matrix, encrypt the image data, and transmit the encrypted data to the requester; specifically, it includes: Calculate the hash feature value of the obtained requirement feature matrix and generate the encryption key: in, This represents the encryption key. Indicates based on The key derivation function of a hash function. Indicates a splicing operation; The image data is encrypted using the obtained encryption key to obtain encrypted data. ; After obtaining the encrypted data Z, the encrypted data Z is transmitted to the HSM security management system, and a data return instruction is transmitted to the requester. This allows the requester to respond to the received return instruction, extract the same demand feature matrix based on its own service request, calculate the hash feature value of the matrix, generate a decryption key, and send it to the HSM security management system. The HSM security management system then decrypts the encrypted data Z using the received decryption key and returns the decrypted shared data to the requester.

Images