Private data encryption method and system for information service platform

Abstract

The invention relates to the technical field of data processing, in particular to a privacy data encryption method and system of an information service platform. The method comprises the following steps: acquiring running state data of the information service platform and privacy data of a user; constructing an adaptive homomorphic encryption parameter model according to the running state data and the privacy data; and encrypting the privacy data of the user by using the self-adaptive homomorphic encryption parameter model. According to the embodiment of the invention, the operation state of the information service platform and the privacy estimation value of the user privacy data are combined, and the dynamically adjusted self-adaptive homomorphic encryption model is adopted, so that the encryption strength can be automatically adjusted according to the resource load and the data privacy requirement of the platform. Through the mode, on the premise that the privacy of the user is protected, the encryption efficiency and effect can be improved, and the platform performance bottleneck caused by overhigh load in the encryption process is avoided.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and specifically relates to a privacy data encryption method and system for an information service platform. Background Art

[0002] While providing convenient services to users, information service platforms have also accumulated a large amount of user privacy data, including personal identity information, payment information, communication records, etc. Since user privacy data is an important part of their personal rights and interests, the leakage or abuse of this data may lead to identity theft, economic losses and other serious consequences, so it is necessary to encrypt user privacy data.

[0003] However, the current platform encryption algorithm has poor efficiency and poor encryption effect when encrypting user privacy data. Therefore, how to improve the encryption efficiency and effect of user privacy data has become an urgent problem that information service platforms need to solve. Summary of the invention

[0004] In order to solve the above problems, the embodiments of the present application provide a privacy data encryption method and system for an information service platform.

[0005] According to a first aspect of an embodiment of the present application, there is provided a method for encrypting private data of an information service platform, the method comprising: obtaining operation status data of the information service platform and private data of a user; Constructing an adaptive homomorphic encryption parameter model according to the operating status data and the privacy data; The user's private data is encrypted using the adaptive homomorphic encryption parameter model.

[0006] Optionally, constructing an adaptive homomorphic encryption parameter model includes: Constructing a state surface of the information service platform according to the load data of the server of the information service platform; According to the state surface, obtaining a usage gradient of the server; Acquiring encryption state parameters of the server according to a usage gradient of the server; Evaluating the private data to obtain a privacy valuation of the private data; An adaptive homomorphic encryption parameter model is constructed according to the encryption state parameters and the privacy valuation.

[0007] Optionally, constructing a state surface of the information service platform according to load data of a server of the information service platform includes: Obtaining usage rates of components of the server, the components including: CPU, disk, and network; Sorting the usage rates of the components of the server to obtain a component usage ranking; A three-dimensional rectangular coordinate system is constructed with time as the horizontal axis, the component utilization rate ranking number as the vertical axis, and the utilization rate as the vertical axis; According to the usage rate of the components of the server, obtaining a usage rate curve of the components of the server; The utilization rate curve of the component is mapped into the three-dimensional rectangular coordinate system, and all curves in the three-dimensional rectangular coordinate system are subjected to surface fitting using the least square method to obtain the state surface of the information service platform.

[0008] Optionally, obtaining the usage gradient of the server includes: Obtain the disk usage of the server at the kth moment; Obtain the CPU usage of the server at the kth moment; Obtaining the network usage rate of the server at the kth moment; A usage gradient of the server is obtained according to the disk usage, the CPU usage and the network usage.

[0009] Optionally, the obtaining the encryption status parameter of the server includes: Get the CPU usage of the server at the current moment; Obtaining the usage gradient change rate of the server at the current moment; Obtaining the usage gradient change deviation rate of the server at the current moment; The encryption state parameters of the server are obtained according to the CPU usage rate at the current moment, the usage rate gradient change rate, and the usage rate gradient change deviation rate.

[0010] Optionally, obtaining the usage gradient change rate of the server at the current moment includes: Obtain the usage gradient of all moments within a preset proximity range of the current moment; Performing straight line fitting on the usage rate gradient to obtain a usage rate gradient change straight line at the current moment; The slope of the usage rate gradient change straight line is used as the usage rate gradient change rate of the server at the current moment.

[0011] Optionally, obtaining the usage gradient change deviation rate of the server at the current moment includes: Acquire the Euclidean distance data between the usage rate gradient at all times and the usage rate gradient change line; Obtaining the standard deviation of the Euclidean distance data; The standard deviation is used as the usage gradient change deviation rate of the server at the current moment.

[0012] Optionally, the evaluating the private data to obtain a privacy valuation of the private data includes: Classifying the privacy data to obtain classified privacy data; Obtaining information entropy of the classified privacy data; A privacy valuation of the private data is obtained according to the information entropy of the classified private data.

[0013] Optionally, the adaptive homomorphic encryption parameter model includes the number of addition operations of the encryption algorithm of the private data, the number of multiplication operations of the encryption algorithm of the private data, and the number of total operation operations of the encryption algorithm of the private data. Constructing the adaptive homomorphic encryption parameter model includes: Taking a vector formed by privacy valuations corresponding to different categories of privacy data in the privacy data as a data point, a scatter plot of all user privacy data is obtained; According to the scatter plot of the privacy data, all users in the information service platform are clustered using the DBSCAN clustering algorithm to obtain a number of user clusters; For any of the user clusters, based on the privacy valuation of the private data, each type of private data in the user cluster is classified using a support vector machine to obtain a number of encrypted clusters; Obtaining a cumulative value of privacy valuations of all private data in the encryption cluster; Acquire a first data volume of all private data in the encryption cluster; Acquire a second data volume of all private data in the user cluster where the encryption cluster is located; According to the encryption state parameter and the first data amount, obtaining the number of addition operations of the encryption algorithm of all the private data in the encryption cluster; Obtaining the number of multiplication operations of the encryption algorithm of all private data in the encryption cluster according to the encryption state parameter, the accumulated value, the first data amount, and the second data amount; The total number of operation operations of the encryption algorithm for all the private data in the encryption cluster is obtained according to the sum of the number of addition operations and the number of multiplication operations.

[0014] According to a second aspect of an embodiment of the present application, a privacy data encryption system for an information service platform is provided, the system comprising an information service platform, the information service platform comprising: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any method described in the first aspect.

[0015] In summary, the embodiments of the present application provide a privacy data encryption method and system for an information service platform, the method comprising: obtaining the operating status data of the information service platform and the privacy data of the user; constructing an adaptive homomorphic encryption parameter model based on the operating status data and the privacy data; and encrypting the privacy data of the user using the adaptive homomorphic encryption parameter model. The embodiments of the present application adopt a dynamically adjusted adaptive homomorphic encryption model by combining the operating status of the information service platform and the privacy valuation of the user's privacy data, so that the encryption strength can be automatically adjusted according to the resource load of the platform and the data privacy requirements. In this way, the encryption efficiency and effect can be improved while protecting the user's privacy, and the platform performance bottleneck caused by excessive load during the encryption process can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the implementation scheme of the present application, the drawings required for use in the implementation scheme will be briefly introduced below. It should be understood that the drawings only show certain implementation schemes of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on the drawings without paying creative work.

[0017] Figure 1 is a flow chart showing a privacy data encryption method of an information service platform according to an exemplary embodiment; Figure 2 is a flowchart of a method for constructing an adaptive homomorphic encryption parameter model according to an exemplary embodiment; Figure 3 is a flow chart showing a method for constructing a state surface of an information service platform according to an exemplary embodiment; Figure 4 is a flow chart showing a method for obtaining a usage gradient of a server according to an exemplary embodiment; Figure 5 is a flow chart showing a method for obtaining encryption state parameters of a server according to an exemplary embodiment; Figure 6 is a flow chart showing a method for obtaining a usage gradient change rate of a server at a current moment according to an exemplary embodiment; Figure 7 is a flow chart showing a method for obtaining a usage gradient change deviation rate of a server at a current moment according to an exemplary embodiment; Figure 8is a flow chart showing a method for obtaining a privacy valuation of private data according to an exemplary embodiment; Fig. 9 is a flowchart of another method for constructing an adaptive homomorphic encryption parameter model according to an exemplary embodiment; Fig.10 is a block diagram of a privacy data encryption system of an information service platform according to an exemplary embodiment; Fig.11 It is a block diagram of an information service platform according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] In order to clearly illustrate the technical features of the present solution, the present application is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0019] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0020] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0021] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0023] It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more". In the description of this application, unless otherwise specified, "multiple" means two or more than two, and other quantifiers are similar; "at least one item", "one or more items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one item a can represent any number of a; for another example, one or more items of a, b and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple; "and / or" is a kind of association relationship that describes the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0024] Although the operations or steps are described in a specific order in the drawings in the embodiments of the present application, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or to perform all the operations or steps shown to obtain the desired results. In the embodiments of the present application, these operations or steps can be performed in series; these operations or steps can also be performed in parallel; or some of these operations or steps can be performed.

[0025] At the same time, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the relevant laws and regulations and relevant provisions. The present application is described below in conjunction with specific embodiments.

[0026] Figure 1 FIG. 1 is a flow chart showing a method for encrypting private data of an information service platform according to an exemplary embodiment. Figure 1 As shown, the embodiment of the present application provides a method for encrypting private data of an information service platform, and the method may include the following steps:

[0027] In step S10, the operation status data of the information service platform and the privacy data of the user are obtained.

[0028] In this step, the operation status data of the information service platform and the privacy data of the user are obtained. For example, monitoring tools (such as Prometheus and Grafana) can be used to obtain the operation status data of the information service platform in real time. The operation status data may include: server load: CPU, disk and network usage; response time: average response time and delay of various requests; user request frequency: number of requests per second, most active users and access paths, etc.; log records: collect access logs and analyze user usage habits, operation frequency and abnormal behavior.

[0029] The acquisition of user privacy data may include: user registration / login information: collecting basic information provided by the user when registering on the platform (such as name, email address, phone number); transaction data: recording the user's payment information on the platform (such as credit card number, payment method); user behavior data: recording the user's operation records (such as search history, browsing history).

[0030] Data preprocessing can include data cleaning: removing duplicate data and invalid data (such as missing values); formatting user input information (for example, standardizing date formats). Data standardization: standardizing numerical data to ensure that various indicators are at the same level for subsequent analysis.

[0031] Mark and classify the user's private data: treat the user's payment information and ID number-related data as Class I data; treat communication records and personal preference-related data as Class II data; treat the user's general usage habits when using the information service platform as Class III data. By labeling data, labels are added to different data categories to facilitate subsequent processing and the selection of encryption strategies.

[0032] In step S20, an adaptive homomorphic encryption parameter model is constructed according to the operating status data and the privacy data.

[0033] In this step, an adaptive homomorphic encryption parameter model is constructed based on the running state data and the privacy data. Exemplarily, the state surface of the information service platform can be constructed based on the load data of the server of the information service platform, and then the usage gradient of the server can be obtained based on the state surface, and then the encryption state parameter of the server can be obtained based on the usage gradient of the server, and then the user privacy data is evaluated to obtain the privacy valuation of the user privacy data, and finally the adaptive homomorphic encryption parameter model is constructed based on the encryption state parameter and the privacy valuation.

[0034] In step S30, the user's private data is encrypted using the adaptive homomorphic encryption parameter model.

[0035] In this step, the user's private data is encrypted using the adaptive homomorphic encryption parameter model. The model combines the operating status of the information service platform and the privacy valuation of the user's private data, and automatically adjusts the encryption strength (encryption operation amount) according to the resource load of the platform and the data privacy requirements. Exemplarily, the user's private data can be encrypted according to the adaptive homomorphic encryption parameter model to generate ciphertext, ensure that its format is compatible with the storage system, and record any abnormalities in the generation process. Generate a key that meets security standards. The key should have sufficient randomness and complexity, and use a secure hardware module (HSM, Hardware Security Module) or a cloud key management service (KMS, Key Management Service) to store the key to ensure that the key can only be accessed by authorized services. Use an encrypted database or a dedicated ciphertext storage solution to save the ciphertext to ensure the security of data in static storage. Set up a monitoring mechanism to monitor the usage and security status of encrypted data in real time to ensure that any abnormal behavior can be identified in a timely manner; collect user feedback on privacy protection measures, analyze the feedback data, and adjust the encryption strategy of the adaptive homomorphic encryption model to improve security and user experience.

[0036] In summary, the embodiment of the present application provides a privacy data encryption method for an information service platform, the method comprising: obtaining the operating status data of the information service platform and the privacy data of the user; constructing an adaptive homomorphic encryption parameter model based on the operating status data and the privacy data; and encrypting the privacy data of the user using the adaptive homomorphic encryption parameter model. The embodiment of the present application adopts a dynamically adjusted adaptive homomorphic encryption model by combining the operating status of the information service platform and the privacy valuation of the user's privacy data, so that the encryption strength can be automatically adjusted according to the resource load of the platform and the data privacy requirements. In this way, the encryption efficiency and effect can be improved while protecting the user's privacy, and the platform performance bottleneck caused by excessive load during the encryption process can be avoided.

[0037] Figure 2 FIG. 1 is a flowchart of a method for constructing an adaptive homomorphic encryption parameter model according to an exemplary embodiment. Figure 2 As shown, the construction of the adaptive homomorphic encryption parameter model may include the following steps:

[0038] In step S201, a state surface of the information service platform is constructed according to load data of the server of the information service platform.

[0039] In this step, the state surface of the information service platform is constructed according to the load data of the server of the information service platform. Exemplarily, the utilization rate of the components of the server can be obtained first, and the components include: CPU, disk and network, and then the utilization rate of the components of the server is sorted to obtain the component utilization rate sorting, and then a three-dimensional rectangular coordinate system is constructed with time as the horizontal axis, the component utilization rate sorting number as the vertical axis, and the utilization rate as the vertical axis, and then the utilization rate curve of the components of the server is obtained according to the utilization rate of the components of the server, and finally the utilization rate curve of the components is mapped to the three-dimensional rectangular coordinate system, and the least squares method is used to perform surface fitting on all curves in the three-dimensional rectangular coordinate system, and finally the state surface of the information service platform is obtained.

[0040] In step S202, the usage gradient of the server is obtained according to the state surface.

[0041] In this step, the usage gradient of the server is obtained according to the state surface. For example, the disk usage of the server at the kth moment can be obtained first, then the CPU usage of the server at the kth moment can be obtained, and then the network usage of the server at the kth moment can be obtained, and finally the usage gradient of the server can be obtained according to the disk usage, CPU usage and network usage.

[0042] In step S203, the encryption state parameter of the server is obtained according to the usage gradient of the server.

[0043] In this step, the encryption state parameters of the server are obtained according to the usage gradient of the server. Exemplarily, the CPU usage of the server at the current moment can be obtained first, then the usage gradient change rate of the server at the current moment can be obtained, and then the usage gradient change deviation rate of the server at the current moment can be obtained, and finally the encryption state parameters of the server can be obtained according to the CPU usage at the current moment, the usage gradient change rate, and the usage gradient change deviation rate.

[0044] In step S204, the private data is evaluated to obtain a privacy valuation of the private data.

[0045] In this step, the private data is evaluated to obtain a privacy valuation of the private data. For example, the private data may be classified to obtain classified private data, then the information entropy of the classified private data may be obtained, and finally the privacy valuation of the private data may be obtained based on the information entropy of the classified private data.

[0046] In step S205, an adaptive homomorphic encryption parameter model is constructed according to the encryption state parameters and the privacy valuation.

[0047] In this step, an adaptive homomorphic encryption parameter model is constructed based on the encryption state parameters and the privacy valuation. The adaptive homomorphic encryption parameter model includes the number of addition operations of the encryption algorithm of the private data, the number of multiplication operations of the encryption algorithm of the private data, and the number of total operation operations of the encryption algorithm of the private data. Exemplarily, a scatter plot of all user privacy data can be obtained first, and then all users in the information service platform are clustered using the DBSCAN clustering algorithm based on the scatter plot of privacy data to obtain several user clusters. Then, for any user cluster, based on the privacy valuation of the privacy data, each type of privacy data in the user cluster is classified using a support vector machine to obtain several encryption clusters, and then the cumulative value of the privacy valuation of all privacy data in the encryption cluster is obtained, and then the first data volume of all privacy data in the encryption cluster is obtained, and then the second data volume of all privacy data in the user cluster where the encryption cluster is located is obtained, and then the number of addition operations of the encryption algorithm of all privacy data in the encryption cluster is obtained according to the encryption state parameter and the first data volume, and then the number of multiplication operations of the encryption algorithm of all privacy data in the encryption cluster is obtained according to the encryption state parameter, the cumulative value, the first data volume and the second data volume, and finally the total number of operation operations of the encryption algorithm of all privacy data in the encryption cluster is obtained according to the sum of the number of addition operations and the number of multiplication operations. The model can automatically adjust the encryption strength (encryption operation volume) according to the resource load of the platform and the data privacy valuation.

[0048] Figure 3 FIG. 1 is a flow chart showing a method for constructing a state surface of an information service platform according to an exemplary embodiment. Figure 3 As shown, constructing the state surface of the information service platform according to the load data of the server of the information service platform may include the following steps:

[0049] In step S2011, the usage rates of components of the server are obtained, where the components include: CPU, disk and network.

[0050] In this step, the usage of the components of the server is obtained, and the components include: CPU, disk and network. Exemplarily, the usage of the components of the server may include CPU usage, disk usage and network usage.

[0051] In step S2012, the usage rates of the components of the server are sorted to obtain a component usage ranking.

[0052] In this step, the usage of the components of the server is sorted, such as CPU usage, disk usage and network usage, to obtain a component usage ranking. For example, the ranking can be from high to low or from low to high.

[0053] In step S2013, a three-dimensional rectangular coordinate system is constructed with time as the horizontal axis, the component usage rate sorting number as the vertical axis, and the usage rate as the vertical axis.

[0054] In this step, a three-dimensional rectangular coordinate system is constructed with time as the horizontal axis, component utilization rate sorting number as the vertical axis, and utilization rate as the vertical axis.

[0055] In step S2014, a usage curve of the components of the server is obtained according to the usage of the components of the server.

[0056] In this step, according to the usage of the components of the server, the usage curve of the components of the server is obtained. Exemplarily, the usage curve of the components of the server may include a CPU usage curve, a disk usage curve and a network usage curve.

[0057] In step S2015, the usage curve of the component is mapped into the three-dimensional rectangular coordinate system, and the least square method is used to perform surface fitting on all curves in the three-dimensional rectangular coordinate system to obtain the state surface of the information service platform.

[0058] In this step, the utilization curve of the component can be mapped into a three-dimensional rectangular coordinate system, and the least square method is used to perform surface fitting on all the curves in the three-dimensional rectangular coordinate system, thereby obtaining the state surface of the information service platform.

[0059] Figure 4 FIG. 1 is a flow chart showing a method for obtaining a usage gradient of a server according to an exemplary embodiment. Figure 4 As shown, obtaining the usage gradient of the server may include the following steps:

[0060] In step S2021, the disk usage of the server at the kth moment is obtained.

[0061] In this step, the disk usage of the server at the kth moment is obtained. .

[0062] In step S2022, the CPU usage rate of the server at the kth moment is obtained.

[0063] In this step, get the CPU usage of the server at the kth moment .

[0064] In step S2023, the network usage rate of the server at the kth moment is obtained.

[0065] In this step, the network usage of the server at the kth moment is obtained. .

[0066] In step S2024, the usage gradient of the server is obtained according to the disk usage, the CPU usage and the network usage.

[0067] In this step, based on the server's disk usage 、CPU usage and network usage , get the usage gradient of the server at the kth moment For example, the usage gradient of the server at the kth moment is It can be obtained by the following formula:

[0068] Formula 1 Among them, the utilization rate gradient It reflects the focus of the server when processing user privacy data at the corresponding time k. When the server usage gradient is larger, the server is more inclined to the encryption calculation process at the corresponding time k; conversely, the server is more inclined to the data transmission and storage process at the corresponding time k. It should be noted that the disk usage rate Network usage The sum of is not zero.

[0069] Figure 5 FIG. 1 is a flow chart showing a method for obtaining encryption status parameters of a server according to an exemplary embodiment. Figure 5 As shown, the obtaining of the encryption state parameter of the server may include the following steps:

[0070] In step S2031, the CPU usage rate of the server at the current moment is obtained.

[0071] In this step, get the CPU usage of the server at the current moment .

[0072] In step S2032, the usage gradient change rate of the server at the current moment is obtained.

[0073] In this step, obtain the usage gradient change rate of the server at the current moment For example, the usage gradients of all moments within a preset proximity range of the current moment can be obtained first; for example, the preset proximity range can be a range of 10 moments near the current moment, and then a straight line fitting is performed on the usage gradient to obtain a usage gradient change straight line at the current moment; then the slope of the usage gradient change straight line is used as the usage gradient change rate of the server at the current moment. .

[0074] In step S2033, the usage gradient change deviation rate of the server at the current moment is obtained.

[0075] In this step, obtain the usage gradient change deviation rate of the server at the current moment For example, the Euclidean distance data between the usage gradient at all times and the usage gradient change line can be obtained first; then the standard deviation of these Euclidean distance data can be obtained; and then the standard deviation can be used as the usage gradient change deviation rate of the server at the current moment. .

[0076] In step S2034, the encryption state parameters of the server are obtained according to the CPU usage rate at the current moment, the usage rate gradient change rate, and the usage rate gradient change deviation rate.

[0077] In this step, based on the current CPU usage , usage rate gradient change rate , usage rate gradient change deviation rate , get the encryption status parameters of the server . Exemplary, the encryption state parameter of the server , can be obtained by the following formula:

[0078] Formula 2 Among them, the encryption state parameter It reflects the encryption load of the information service platform when encrypting user privacy data at the current moment, that is, the encryption status parameter The larger the value is, the greater the data processing pressure faced by the CPU component of the server when the information service platform encrypts the user's private data. Therefore, in order to reduce the encryption calculation pressure of the CPU component of the information service platform during the encryption process, the encryption strength (amount of calculation) currently used in encryption using the homomorphic encryption algorithm should be dynamically adjusted to improve encryption efficiency and effectiveness and avoid platform performance bottlenecks caused by excessive load during the encryption process.

[0079] Figure 6 FIG. 1 is a flow chart showing a method for obtaining the usage gradient change rate of a server at the current moment according to an exemplary embodiment. Figure 6 As shown, obtaining the usage gradient change rate of the server at the current moment may include the following steps:

[0080] In step S20321, the usage gradient of all moments within a preset proximity range of the current moment is obtained.

[0081] In this step, the usage gradients of all moments within a preset proximity range of the current moment are obtained. Exemplarily, the preset proximity range may be a range of 10 moments adjacent to the current moment.

[0082] In step S20322, a straight line fitting is performed on the usage rate gradient to obtain a usage rate gradient change line at the current moment.

[0083] In this step, a linear fitting is performed on the usage rate gradient to obtain a usage rate gradient change line at the current moment. Exemplarily, a linear fitting can be performed on the usage rate gradient using a least squares method to obtain a usage rate gradient change line at the current moment.

[0084] In step S20323, the slope of the usage rate gradient change line is used as the usage rate gradient change rate of the server at the current moment.

[0085] In this step, the slope of the usage gradient change line can be used as the usage gradient change rate of the server at the current moment. Exemplarily, the usage gradient change rate reflects the change trend of the encryption load of the server within a short time range at the current moment.

[0086] Figure 7 FIG. 1 is a flow chart showing a method for obtaining a usage gradient change deviation rate of a server at the current moment according to an exemplary embodiment. Figure 7 As shown, obtaining the usage gradient change deviation rate of the server at the current moment may include the following steps:

[0087] In step S20331, the Euclidean distance data between the usage rate gradient at all times and the usage rate gradient change line is obtained.

[0088] In this step, the Euclidean distance data between the usage rate gradient at all times within the preset proximity range and the usage rate gradient change line is obtained.

[0089] In step S20332, the standard deviation of the Euclidean distance data is obtained.

[0090] In this step, the standard deviation of these Euclidean distance data is obtained.

[0091] In step S20333, the standard deviation is used as the usage gradient change deviation rate of the server at the current moment.

[0092] In this step, the standard deviation obtained in the previous step is used as the usage gradient change deviation rate of the server at the current moment. Exemplarily, the usage gradient change deviation rate reflects the confidence level of describing the encrypted load state of the CPU component of the server at the current moment using the usage gradient change rate. The smaller the usage gradient change deviation rate, the higher the confidence level. Otherwise, the lower the confidence level.

[0093] Figure 8 FIG. 1 is a flow chart showing a method for obtaining a privacy valuation of private data according to an exemplary embodiment. Figure 8 As shown, the evaluating the private data to obtain the privacy valuation of the private data may include the following steps:

[0094] In step S2041, the privacy data is classified to obtain classified privacy data.

[0095] In this step, the private data is classified to obtain classified private data. Exemplarily, the method of classifying the private data to obtain classified private data can refer to the description of the aforementioned step S10 embodiment, and this application will not repeat it here.

[0096] In step S2042, the information entropy of the classified privacy data is obtained.

[0097] In this step, the information entropy of the i-th category classified privacy data is obtained .

[0098] In step S2043, a privacy valuation of the private data is obtained according to the information entropy of the classified private data.

[0099] In this step, the information entropy of the classified privacy data is , get the privacy valuation of the i-th type of private data For example, the privacy valuation of the i-th type of private data is It can be obtained by the following formula:

[0100] Formula 3 For example, i can be equal to 1, 2 or 3. Privacy Valuation It reflects the encryption strength required when the privacy data of the i-th user is encrypted on the information service platform, that is, the privacy valuation The larger the value is, the higher the encryption strength required for the privacy data of the i-th category of users during the encryption process. This will dynamically adjust the encryption calculation strength of different privacy data, reduce the total encryption calculation amount and improve the efficiency and effectiveness of the encryption algorithm while ensuring data security.

[0101] Fig. 9FIG. 1 is a flowchart of another method for constructing an adaptive homomorphic encryption parameter model according to an exemplary embodiment. Fig. 9 As shown, the adaptive homomorphic encryption parameter model includes the number of addition operations of the encryption algorithm of the private data, the number of multiplication operations of the encryption algorithm of the private data, and the number of total operation operations of the encryption algorithm of the private data. The construction of the adaptive homomorphic encryption parameter model may include the following steps:

[0102] In step S2051, a vector formed by privacy valuations corresponding to different categories of privacy data in the privacy data is taken as a data point to obtain a scatter plot of all user privacy data.

[0103] In this step, the vector formed by the privacy valuation corresponding to the privacy data of different categories in the privacy data is taken as a data point to obtain a scatter plot of all user privacy data. For example, the vector formed by the privacy valuation corresponding to the privacy data of categories I, II, and III of the user can be taken as a data point to obtain a scatter plot of all user privacy data.

[0104] In step S2052, all users in the information service platform are clustered using the DBSCAN clustering algorithm according to the scatter plot of the privacy data to obtain a number of user clusters.

[0105] In this step, according to the scatter plot of privacy data, the DBSCAN clustering algorithm is used to cluster all users in the information service platform to obtain several user clusters.

[0106] In step S2053, for any one of the user clusters, based on the privacy valuation of the private data, each type of private data in the user cluster is classified using a support vector machine to obtain a number of encrypted clusters.

[0107] In this step, for any user cluster, based on the privacy valuation of the private data, each type of private data in the user cluster is classified using a support vector machine to obtain several encrypted clusters. Exemplarily, users with similar privacy valuations of private data can be classified into one category by clustering, and the private data of users in the user cluster can be further classified. Different types of private data can be adaptively homomorphically encrypted by dividing the private data in the information service platform. By balancing the encryption load of the CPU component in the server of the information service platform during the encryption process and the encryption requirements of different users and different private data in the information service platform, adaptive encryption can be performed to improve encryption efficiency and encryption effect.

[0108] In step S2054, the accumulated value of the privacy valuation of all the private data in the encryption cluster is obtained.

[0109] In this step, the cumulative value of the privacy valuation of all private data in encrypted cluster j is obtained .

[0110] In step S2055, a first data volume of all private data in the encryption cluster is obtained.

[0111] In this step, the first data volume of all private data in encrypted cluster j is obtained , the first data volume is the amount of encrypted private data in cluster j.

[0112] In step S2056, a second data volume of all private data in the user cluster where the encryption cluster is located is obtained.

[0113] In this step, the second data volume of all private data in the user cluster where the encryption cluster j is located is obtained , the second data volume is the amount of all private data in the user cluster where encrypted cluster j is located.

[0114] In step S2057, the number of addition operations of the encryption algorithm of all the private data in the encryption cluster is obtained according to the encryption state parameter and the first data volume.

[0115] In this step, according to the encryption state parameter and the first data volume , get the number of addition operations of the encryption algorithm for all private data in encryption cluster j For example, the number of addition operations of the encryption algorithm for all private data in encryption cluster j is It can be obtained by the following formula:

[0116] Formula 4 in, Represents the logarithmic function with a constant base of 2.

[0117] In step S2058, the number of multiplication operations of the encryption algorithm of all the private data in the encryption cluster is obtained according to the encryption state parameter, the accumulated value, the first data amount, and the second data amount.

[0118] In this step, according to the encryption state parameter , accumulated value , the first data volume and the second amount of data , get the number of multiplication operations of the encryption algorithm for all private data in encryption cluster j For example, the number of multiplication operations of the encryption algorithm for all private data in encryption cluster j is It can be obtained by the following formula:

[0119] Formula 5 in, Represents the floor function.

[0120] In step S2059, the total number of operation operations of the encryption algorithm for all the private data in the encryption cluster is obtained according to the sum of the number of addition operations and the number of multiplication operations.

[0121] In this step, according to the number of addition operations The number of multiplication operations The sum of the values ​​is used to obtain the total number of operations of the encryption algorithm for all private data in encryption cluster j. For example, the total number of operations of the encryption algorithm for all private data in encryption cluster j is It can be obtained by the following formula:

[0122] Formula 6 The adaptive homomorphic encryption parameter model adaptively processes the number of addition and multiplication operations in the fully homomorphic encryption algorithm by combining the operating status of the information service platform and the privacy valuation of the currently processed privacy data. It can effectively predict the server load demand and dynamically adjust the encryption strength during the encryption process, optimize resource utilization, and improve encryption efficiency and encryption effect.

[0123] In an exemplary embodiment, the present application also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the privacy data encryption method of the information service platform provided by the present application.

[0124] Fig.10 It is a block diagram of a privacy data encryption system of an information service platform according to an exemplary embodiment.

[0125] like Fig.10 As shown, an embodiment of the present application provides a privacy data encryption system 1000 for an information service platform, including an information service platform 1100.

[0126] Fig.11 1 is a block diagram of an information service platform according to an exemplary embodiment. For example, the information service platform 1100 may be provided as a server. Fig.11The information service platform 1100 includes a processing component 1122, which further includes one or more processors, and a memory resource represented by a memory 1132 for storing instructions that can be executed by the processing component 1122, such as an application. The application stored in the memory 1132 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1122 is configured to execute instructions to perform the privacy data encryption method of the above-mentioned information service platform.

[0127] The information service platform 1100 may also include a power supply component 1126 configured to perform power management of the information service platform 1100, a communication component port 1150 configured to connect the information service platform 1100 to a network, and an input / output interface 1158. The information service platform 1100 may operate based on an operating system stored in the memory 1132.

[0128] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable electronic device, and the computer program has a code portion for executing the privacy data encryption method of the above-mentioned information service platform when executed by the programmable electronic device.

[0129] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A privacy data encryption method for an information service platform, characterized in that: The method includes: obtaining the operating status data of the information service platform and the privacy data of the user; constructing an adaptive homomorphic encryption parameter model according to the operating status data and the privacy data; and encrypting the privacy data of the user using the adaptive homomorphic encryption parameter model.

2. The privacy data encryption method of the information service platform according to claim 1, characterized in that: The constructing of the adaptive homomorphic encryption parameter model includes: constructing a state surface of the information service platform according to load data of a server of the information service platform; According to the state surface, the usage gradient of the server is obtained; according to the usage gradient of the server, the encryption state parameters of the server are obtained; the privacy data is evaluated to obtain a privacy valuation of the privacy data; according to the encryption state parameters and the privacy valuation, an adaptive homomorphic encryption parameter model is constructed.

3. The privacy data encryption method of the information service platform according to claim 2, characterized in that: The state surface of the information service platform is constructed according to the load data of the server of the information service platform, including: obtaining the usage rate of the components of the server, the components including: CPU, disk and network; sorting the usage rate of the components of the server to obtain the component usage rate sorting; constructing a three-dimensional rectangular coordinate system with time as the horizontal axis, the component usage rate sorting number as the vertical axis, and the usage rate as the vertical axis; obtaining the usage rate curve of the components of the server according to the usage rate of the components of the server; The utilization rate curve of the component is mapped into the three-dimensional rectangular coordinate system, and all curves in the three-dimensional rectangular coordinate system are subjected to surface fitting using the least square method to obtain the state surface of the information service platform.

4. The privacy data encryption method of the information service platform according to claim 2, characterized in that: The obtaining of the usage gradient of the server includes: obtaining the disk usage of the server at the kth moment; obtaining the CPU usage of the server at the kth moment; obtaining the network usage of the server at the kth moment; and obtaining the usage gradient of the server according to the disk usage, the CPU usage and the network usage.

5. The privacy data encryption method of the information service platform according to claim 2, characterized in that: The method of obtaining the encryption status parameters of the server includes: obtaining the CPU usage rate of the server at the current moment; obtaining the usage gradient change rate of the server at the current moment; obtaining the usage gradient change deviation rate of the server at the current moment; and obtaining the encryption status parameters of the server based on the CPU usage rate at the current moment, the usage gradient change rate, and the usage gradient change deviation rate.

6. The privacy data encryption method of the information service platform according to claim 5, characterized in that: The obtaining of the usage gradient change rate of the server at the current moment includes: obtaining the usage gradients of all moments within a preset proximity range of the current moment; performing straight line fitting on the usage gradients to obtain a usage gradient change straight line at the current moment; The slope of the usage rate gradient change straight line is used as the usage rate gradient change rate of the server at the current moment.

7. The privacy data encryption method of the information service platform according to claim 6, characterized in that: The method of obtaining the usage gradient change deviation rate of the server at the current moment includes: obtaining the Euclidean distance data between the usage gradients at all moments and the usage gradient change straight line; obtaining the standard deviation of the Euclidean distance data; and using the standard deviation as the usage gradient change deviation rate of the server at the current moment.

8. The privacy data encryption method of the information service platform according to claim 2, characterized in that: The evaluating the privacy data to obtain a privacy valuation of the privacy data includes: classifying the privacy data to obtain classified privacy data; obtaining information entropy of the classified privacy data; and obtaining a privacy valuation of the privacy data based on the information entropy of the classified privacy data.

9. The privacy data encryption method of the information service platform according to claim 2, characterized in that: The adaptive homomorphic encryption parameter model includes the number of addition operations of the encryption algorithm of the privacy data, the number of multiplication operations of the encryption algorithm of the privacy data and the total number of operation operations of the encryption algorithm of the privacy data. The construction of the adaptive homomorphic encryption parameter model includes: taking the vector formed by the privacy valuation corresponding to the different categories of privacy data in the privacy data as a data point to obtain a scatter plot of all user privacy data; according to the scatter plot of the privacy data, using the DBSCAN clustering algorithm to cluster all users in the information service platform to obtain a number of user clusters; for any of the user clusters, based on the privacy valuation of the privacy data, and using a support vector machine to cluster each category of privacy data in the user cluster According to the classification, several encryption clusters are obtained; the cumulative value of the privacy valuation of all the private data in the encryption cluster is obtained; the first data volume of all the private data in the encryption cluster is obtained; the second data volume of all the private data in the user cluster where the encryption cluster is located is obtained; according to the encryption state parameter and the first data volume, the number of addition operations of the encryption algorithm for all the private data in the encryption cluster is obtained; according to the encryption state parameter, the cumulative value, the first data volume and the second data volume, the number of multiplication operations of the encryption algorithm for all the private data in the encryption cluster is obtained; according to the sum of the number of addition operations and the number of multiplication operations, the total number of operation operations of the encryption algorithm for all the private data in the encryption cluster is obtained.

10. A privacy data encryption system for an information service platform, characterized in that: The system includes an information service platform, which includes: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1 to 9.

Images