Data processing method and device, computer device, readable storage medium and program product

Abstract

The application relates to the field of big data data processing, and specifically discloses a data processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an initial data set from a database, wherein the initial data set comprises resource interaction data; determining to-be-processed data meeting a preset protection condition from the initial data set, and dividing the to-be-processed data according to a data protection level corresponding to the to-be-processed data, so as to obtain at least one to-be-processed data set, wherein the data protection levels of the data in each to-be-processed data set are the same; determining a target noise corresponding to each to-be-processed data set according to a noise parameter corresponding to the data protection level; and respectively performing noise adding processing on the corresponding to-be-processed data set by using the target noise, so as to obtain and store a data set after noise adding. The method can improve the security and reliability of data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data data processing, and in particular relates to a data processing method and device, computer equipment, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the development of the information age, big data technology emerges as the times require, and through data mining algorithms, rules and knowledge hidden in data can be found in massive data, which is of great significance to many fields such as social services. In the process of data transmission and use, there is a risk of personal privacy leakage, which brings great threat to personal safety and property safety. In order to ensure that sensitive data is not leaked, data security protection is crucial.

[0003] In related technologies, data security protection can be performed through key encryption technology, access permission control technology, identity verification and authorization technology and the like. However, part of the data attackers can analyze and process through the association between data to obtain sensitive data, and through the above-mentioned way of data security protection, it is impossible to effectively prevent the attackers from obtaining sensitive information through association analysis, and there is a high computing and storage overhead. SUMMARY

[0004] Therefore, it is necessary to provide a data processing method, device, computer equipment, computer readable storage medium and computer program product capable of improving encryption effect in view of the above technical problems.

[0005] In a first aspect, the present application provides a data processing method, which comprises:

[0006] obtaining an initial data set from a database, wherein the initial data set comprises resource interaction data;

[0007] determining to-be-processed data meeting a preset protection condition from the initial data set, and dividing the to-be-processed data according to a data protection level corresponding to the to-be-processed data, to obtain at least one to-be-processed data set, wherein the data protection levels of the data in each to-be-processed data set are the same;

[0008] determining a target noise corresponding to each to-be-processed data set according to a noise parameter corresponding to the data protection level;

[0009] respectively performing noise adding processing on the corresponding to-be-processed data set by using the target noise, to obtain and store a data set after noise adding.

[0010] In one of the embodiments, the determining of the target noise corresponding to each to-be-processed data set according to the noise parameter corresponding to the data protection level comprises:

[0011] For each to-be-processed data set, a target noise parameter is determined according to a data protection level corresponding to the to-be-processed data set, wherein the target noise parameter is negatively correlated with the data protection level;

[0012] According to the target noise parameter and a noise calculation strategy matched with the target noise parameter, a target standard deviation is determined;

[0013] According to the target standard deviation, a target noise is generated, and a standard deviation of the target noise is within a preset range of the target standard deviation.

[0014] In one of the embodiments, the target noise parameter includes a first parameter and a second parameter, and the determination of the target standard deviation according to the target noise parameter and the noise calculation strategy matched with the target noise parameter includes:

[0015] A first ratio of a preset value to the first parameter is determined, and a product of a square root of a logarithm of the first ratio and a data variation before and after noise addition is determined as a second ratio;

[0016] A third ratio between the second ratio and the second parameter is determined as the target standard deviation.

[0017] In one of the embodiments, the determination of the preset protection condition includes:

[0018] Historical data is obtained from a preset resource interaction database, and the historical data includes data that needs to be protected;

[0019] Description information corresponding to the historical data is obtained, and target description information is determined according to a correlation degree between the description information;

[0020] According to the target description information, a preset protection condition is determined.

[0021] In one of the embodiments, the determination of the target description information according to the correlation degree between the description information includes:

[0022] Feature data corresponding to the description information is determined, and a correlation degree between the description information is determined according to a similarity degree between the feature data;

[0023] Description information with a correlation degree greater than a preset threshold is determined as the target description information.

[0024] In one of the embodiments, the data set after noise addition is stored in a target database, and the method further includes:

[0025] Access information corresponding to the target database is obtained;

[0026] input the access information into a risk assessment model, output a risk level corresponding to the access information through the risk assessment model, and the risk assessment model is trained based on a corresponding relationship between access information samples and corresponding risk level labels;

[0027] send a warning message matching the risk level.

[0028] In a second aspect, the present application further provides a data processing device, comprising:

[0029] an acquisition module configured to acquire an initial data set from a database, wherein the initial data set comprises resource interaction data;

[0030] a division module configured to determine to-be-processed data meeting a preset protection condition from the initial data set, and divide the to-be-processed data according to a data protection level corresponding to the to-be-processed data, to obtain at least one to-be-processed data set, wherein the data protection levels of data in each to-be-processed data set are the same;

[0031] a determination module configured to determine a target noise corresponding to each to-be-processed data set according to a noise parameter corresponding to the data protection level;

[0032] a noise adding module configured to respectively add noise to the corresponding to-be-processed data set by using the target noise, to obtain and store a data set after noise adding.

[0033] In one of the embodiments, the determination module is further configured to:

[0034] for each to-be-processed data set, determine a target noise parameter according to a data protection level corresponding to the to-be-processed data set, wherein the target noise parameter is in a negative correlation relationship with the data protection level;

[0035] determine a target standard deviation according to the target noise parameter and a noise calculation strategy matching the target noise parameter;

[0036] generate a target noise according to the target standard deviation, and a standard deviation of the target noise is within a preset range of the target standard deviation.

[0037] In one of the embodiments, the target noise parameter comprises a first parameter and a second parameter, and the determination module is further configured to:

[0038] determine a first ratio of a preset value to the first parameter, and determine a second ratio as a product of a square root of a logarithm of the first ratio and a data variation before and after noise adding;

[0039] determine a third ratio between the second ratio and the second parameter as a target standard deviation.

[0040] In one of the embodiments, the apparatus further comprises a preset protection condition determination module, which is configured to:

[0041] acquire historical data from a preset resource interaction database, the historical data comprising data requiring data protection;

[0042] acquire description information corresponding to the historical data, and determine target description information according to the correlation between the description information;

[0043] determine a preset protection condition according to the target description information.

[0044] In one of the embodiments, the preset protection condition determination module is further configured to:

[0045] determine feature data corresponding to the description information, and determine the correlation between the description information according to the similarity between the feature data;

[0046] determine the description information with a correlation greater than a preset threshold as the target description information.

[0047] In one of the embodiments, the noise-added data set is stored in a target database, and the apparatus further comprises:

[0048] an acquisition submodule configured to acquire access information corresponding to the target database;

[0049] an input submodule configured to input the access information into a risk assessment model, and output a risk level corresponding to the access information through the risk assessment model, the risk assessment model being trained based on a corresponding relationship between access information samples and corresponding risk level labels;

[0050] a sending submodule configured to send a warning message matching the risk level.

[0051] In a third aspect, the embodiments of the present disclosure further provide a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in any one of the embodiments of the present disclosure when executing the computer program.

[0052] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method in any one of the embodiments of the present disclosure.

[0053] In a fifth aspect, the present disclosure also provides a computer program product. The computer program product includes a computer program, and the computer program, when executed by a processor, implements the steps of the method in any of the embodiments of the present disclosure.

[0054] The data processing method, device, computer device, computer readable storage medium and computer program product can obtain data that needs to be processed by first obtaining an initial data set, determining to-be-processed data that meets a preset protection condition from the initial data set, dividing the to-be-processed data into to-be-processed data sets according to data protection levels corresponding to the to-be-processed data, determining a target noise corresponding to each to-be-processed data set according to noise parameters corresponding to the data protection levels, and performing noise addition processing on the to-be-processed data set corresponding to the target noise to obtain and store a data set after noise addition. Thus, different noise addition processing can be performed according to different data protection levels, different data can correspond to different target noises, the security of the data is protected, and the security and reliability of the data are improved. Because the data protection levels are divided during noise addition processing, different data can correspond to different target noises, the risk of obtaining data by an attacker through correlation analysis is avoided, and the security and reliability of the data are further improved. In this embodiment, the noise addition processing can be quickly and accurately performed by setting the preset protection condition, the data protection levels and the noise parameters, the computing and storage overheads are reduced, the problem of resource waste is reduced, and the method is suitable for more application scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0056] Figure 1 An application environment diagram of a data processing method in an embodiment;

[0057] Figure 2 A flowchart of a data processing method in an embodiment;

[0058] Figure 3 A flowchart of a data processing method in another embodiment;

[0059] Figure 4 A flowchart of a data processing method in another embodiment;

[0060] Figure 5A flowchart of a determination manner of preset protection conditions in an embodiment;

[0061] Figure 6 A flowchart of a determination manner of preset protection conditions in another embodiment;

[0062] Figure 7 A flowchart of a data processing method in another embodiment;

[0063] Figure 8 A flowchart of a data processing method in another embodiment;

[0064] Figure 9 A structural block diagram of a data processing apparatus in an embodiment;

[0065] Figure 10 An internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0066] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0067] The acquisition, storage, use, processing and the like of data in the technical solutions of the present application all comply with the relevant provisions of national laws and regulations.

[0068] The data processing method provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal obtains an initial data set from the database of the server, and determines the to-be-processed data that meets the preset protection condition from the initial data set, and divides the to-be-processed data according to the data protection level corresponding to the to-be-processed data to obtain a to-be-processed data set; the terminal determines the target noise corresponding to each to-be-processed data set according to the noise parameter corresponding to the data protection level, and respectively uses the target noise to perform noise processing on the to-be-processed data set to obtain and store the noise-added data set. Among them, the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, projection devices, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0069] In an exemplary embodiment, as Figure 2 shown, a data processing method is provided, which is applied to Figure 1 the terminal in

[0070] Step S210, obtaining an initial data set from the database, the initial data set including resource interaction data;

[0071] Exemplarily, the database can include a database corresponding to a resource interaction mechanism, and the database stores resource interaction data. In an example, the initial data set can be obtained from the database through a database corresponding interface and tool, and through a preset interface and tool, it is convenient for relevant personnel to use and manage data. The initial data set can include a data set that needs to be added with noise. The resource interaction data can include but is not limited to account data of resource interaction accounts, resource interaction amount data, resource amount data, etc., which can be determined according to actual application scenarios.

[0072] In an example, the type of data that needs to be judged and processed can be determined according to the actual application scenario and stored in the corresponding data storage area of the database, and when the initial data set is obtained from the database, the data set is obtained from the data storage area, that is, the initial data set.

[0073] Step S220, determining to-be-processed data meeting a preset protection condition from the initial data set, and dividing the to-be-processed data according to a data protection level corresponding to the to-be-processed data, to obtain at least one to-be-processed data set, data in each to-be-processed data set having the same data protection level;

[0074] For example, to-be-processed data meeting a preset protection condition is determined from the initial data set, where the preset protection condition can be determined in advance according to an actual application scenario. In some possible implementation manners, the preset protection condition can be that description information of data meets target description information, and the target description information can be determined according to historical data; the preset protection condition can also be that an attribute of data meets a preset attribute, and the preset attribute can be determined according to historical data.

[0075] In one example, when data meets the preset protection condition, it can be considered that the data needs to be protected, i.e., to be subjected to noise processing, and the data is determined to be to-be-processed data; when data does not meet the preset protection condition, it can be considered that the data does not need to be protected.

[0076] Optionally, the to-be-processed data corresponds to a data protection level, which can be determined according to data features such as an attribute and a category of the to-be-processed data. In one example, a level evaluation model can be trained according to a correspondence between historical resource interaction data samples and corresponding data protection level labels, and the to-be-processed data is input into the level evaluation model to output the data protection level of the to-be-processed data by the level evaluation model.

[0077] For example, when the to-be-processed data is divided, to-be-processed data having the same data protection level is divided into a same to-be-processed data set, to obtain at least one to-be-processed data set.

[0078] Step S230, determining a target noise corresponding to each to-be-processed data set according to a noise parameter corresponding to the data protection level.

[0079] For example, different data protection levels correspond to different noise parameters, and each to-be-processed data set corresponds to a data protection level. The noise parameter can be determined according to an actual application scenario, and the noise parameter can include one or more parameters. In one example, a mapping relationship between the data protection level and the noise parameter can be set, and based on the mapping relationship, the noise parameter corresponding to each to-be-processed data set can be determined.

[0080] Optionally, the target noise corresponding to the to-be-processed data set can be determined according to the noise parameter. In an example, the target noise can be determined in combination with the noise parameter and a corresponding noise calculation strategy. The noise calculation strategy can be determined according to an actual application scenario. Different to-be-processed data sets can correspond to different target noises. The noise type of the target noise can include, but is not limited to, Gaussian noise, impulse noise, etc. The target noise can be determined according to an actual application scenario.

[0081] In step S240, the corresponding to-be-processed data set is added with noise respectively by using the target noise, and a data set after noise addition is obtained and stored.

[0082] For example, the corresponding to-be-processed data set is added with noise respectively by using the target noise, and a data set after noise addition is obtained and stored. In an example, the target noise corresponding disturbance can be added to the data in the to-be-processed data set, and a data set after noise addition is obtained, which can hide or blur relevant information and reduce the identifiability of the data.

[0083] In the embodiment of the present disclosure, when the data is added with noise, the initial data set is obtained first, and the to-be-processed data meeting the preset protection condition is determined from the initial data set, so that the data needing to be added with noise can be obtained. According to the data protection level corresponding to the to-be-processed data, the to-be-processed data set is divided, so that different data protection levels are processed respectively. According to the noise parameter corresponding to the data protection level, the target noise corresponding to each to-be-processed data set is determined respectively, and the corresponding to-be-processed data set is added with noise by using the target noise, so that a data set after noise addition is obtained and stored. Therefore, different noise addition processing can be performed according to different data protection levels, different data can correspond to different target noises, the security protection of the data is realized, and the security and reliability of the data are improved. Since the data protection level is divided when the data is added with noise, different data can correspond to different target noises, the risk of obtaining data by an attacker through correlation analysis is avoided, and the security and reliability of the data are further improved. In the embodiment, the preset protection condition, the data protection level, and the noise parameter are set, so that the noise addition processing can be performed quickly and accurately, the calculation and storage overheads are reduced, the problem of resource waste is reduced, and the embodiment is suitable for more application scenarios.

[0084] In one of the embodiments, as shown in Figure 3 The target noise corresponding to each to-be-processed data set is determined according to the noise parameter corresponding to the data protection level.

[0085] In step S231, for each to-be-processed data set, the target noise parameter is determined according to the data protection level corresponding to the to-be-processed data set, wherein the target noise parameter and the data protection level have a negative correlation relationship.

[0086] In step S232, a target standard deviation is determined according to the target noise parameter and a noise calculation strategy matched with the target noise parameter.

[0087] In step S233, a target noise is generated according to the target standard deviation, and a standard deviation of the target noise is within a preset range of the target standard deviation.

[0088] For example, when the target noise is determined, because each data set to be processed can correspond to different data protection levels, the target noise parameter is determined for each data set to be processed respectively, and the corresponding target noise is generated. Different data sets to be processed can correspond to different target noises.

[0089] In an example, the target noise parameter is determined according to the data protection level corresponding to the data set to be processed. The target noise parameter and the data protection level have a negative correlation relationship. That is, the lower the data protection level, the larger the corresponding target noise parameter, and the higher the data protection level, the smaller the corresponding target noise parameter. For example, the higher the data protection level, the more noise needs to be added to protect the data.

[0090] The target standard deviation is determined according to the noise calculation strategy matched with the target noise parameter and the target noise parameter. The noise calculation strategy can be determined according to an actual application scenario. In an example, the noise calculation strategy can be determined according to a preset noise calculation formula.

[0091] The target noise is generated according to the target standard deviation. The standard deviation of the target noise is within a preset range of the target standard deviation. For example, the preset range can be determined according to an actual application scenario. In an example, the preset range can be a smaller data range containing the target standard deviation determined according to an actual application scenario. When the standard deviation of the noise is within the preset range, it can be considered that the standard deviation of the noise is within an error allowable range of the target standard deviation, and the noise can be determined as the target noise.

[0092] In the embodiments of the present disclosure, when the target noise is determined, the target noise parameter is determined according to the data protection level corresponding to the data set to be processed, and the target standard deviation is determined according to the target noise parameter and the noise calculation strategy matched with the target noise parameter. The corresponding target noise is generated, so that the corresponding target noise can be generated based on different target noise parameters corresponding to different data protection levels, the data is graded and added with noise, and the security and reliability of the data are ensured. Through the negative correlation relationship between the target noise parameter and the data protection level, the target noise can be generated based on different data protection levels, the data security corresponding to different protection requirements in different scenarios is ensured, and the method is suitable for more application scenarios.

[0093] In one embodiment, as shown in Figure 4 The target noise parameter includes a first parameter and a second parameter, and the determination of the target standard deviation according to the target noise parameter and the noise calculation strategy matched with the target noise parameter includes:

[0094] In step S2321, a first ratio of a preset value and the first parameter is determined, and a product of a square root of a logarithm of the first ratio and a data change before and after the adding of noise is determined as a second ratio.

[0095] In step S2322, a third ratio between the second ratio and the second parameter is determined as the target standard deviation.

[0096] Exemplarily, in the determination of the target standard deviation according to the target noise parameter and the preset noise calculation strategy, a first ratio of a preset value and the first parameter is determined, wherein the preset value can be determined according to an actual application scenario. A square root of a logarithm of the first ratio is calculated, and a product of the square root and a data change before and after the adding of noise is determined as a second ratio. A third ratio between the second ratio and the second parameter is determined as the target standard deviation.

[0097] In one example, the data change before and after the adding of noise is associated with the target standard deviation, and thus, the target standard deviation can be solved on the basis of an equation that the third ratio between the second ratio and the second parameter is equal to the target standard deviation.

[0098] In one possible implementation, the target noise can include Gaussian noise, and the target standard deviation is determined according to the following equation: The corresponding adding of noise The target standard deviation satisfies wherein the preset value is 2, is the first parameter, is the second parameter, is the data change before and after the adding of noise. In one example, the standard deviation of the target noise is equal to the target standard deviation, that is, the target noise can be set as Gaussian noise The standard deviation of the noise is the target standard deviation .

[0099] In the embodiment of the present disclosure, when determining the target standard deviation, the target standard deviation is first determined, the first ratio of the preset value and the first parameter is determined, and the product of the square root of the logarithm of the first ratio and the data variation before and after adding noise is determined as the second ratio. The third ratio between the second ratio and the second parameter is determined as the target standard deviation. The smaller the first parameter and the second parameter are, the larger the corresponding target standard deviation is, so that larger target noise can be generated. Since the target noise parameter and the data protection level are negatively correlated, the higher the data protection level is, the larger the corresponding target noise is. The data is protected by hierarchical noise, and more noise is added to the data with a higher data protection level, further reducing the risk of data leakage. The target standard deviation is calculated by the noise calculation strategy, which ensures the correlation between the target noise and the data protection level, and improves the complexity of the correlation by setting two parameters and the calculation strategy, reduces the risk of the correlation being analyzed and processed by attackers, and further improves the security and reliability of the data.

[0100] In one embodiment, as shown in Figure 5 The determination manner of the preset protection condition comprises:

[0101] In step S510, historical data is obtained from the preset resource interaction database, and the historical data comprises data requiring data protection.

[0102] In step S520, description information corresponding to the historical data is obtained, and target description information is determined according to the correlation between the description information.

[0103] In step S530, the preset protection condition is determined according to the target description information.

[0104] Exemplarily, the preset protection condition can be determined according to the historical data. The preset resource interaction database can be a database storing resource interaction data requiring data protection. The historical data is obtained from the preset resource interaction database, and the historical data comprises data requiring data protection.

[0105] Optionally, the historical data corresponds to description information, and the description information can be information used to describe the historical data. The description information can comprise, but is not limited to, data attributes of the historical data, types of the historical data, and the like, and can be determined according to actual application scenarios. The target description information is determined according to the correlation between the description information. In one example, when the correlation between the description information is high, it can be considered as a common feature of the data requiring data protection. Therefore, the description information with a correlation greater than a preset threshold can be determined as the target description information. In one example, the description information with a correlation greater than a preset threshold can also be subjected to feature extraction to obtain the target description information.

[0106] According to the target description information, a preset protection condition is determined. In an example, the preset protection condition can be set as a similarity between the description information of the data and the target description information being greater than a preset similarity. At this time, it can be considered that the probability of the data needing data protection is greater, and the data is determined as the to-be-processed data.

[0107] In the embodiments of the present disclosure, when the preset protection condition is determined, historical data is obtained from the preset resource interaction database, and description information corresponding to the historical data is obtained. According to the correlation between the description information, the target description information is determined. According to the target description information, the preset protection condition is determined. Therefore, the preset protection condition can be quickly and accurately obtained according to the description information corresponding to the data needing data protection in the database, and the accuracy and efficiency of subsequent screening of the to-be-processed data from the initial data set are ensured.

[0108] In one of the embodiments, as shown in Figure 6 The target description information is determined according to the correlation between the description information, and includes:

[0109] In step S521, the feature data corresponding to the description information is determined, and the correlation between the description information is determined according to the similarity between the feature data.

[0110] In step S522, the description information with a correlation greater than a preset threshold is determined as the target description information.

[0111] Exemplarily, according to the description information, the corresponding feature data can be determined. In an example, the description information can be extracted by a preset text processing algorithm and the like to obtain the corresponding feature data. In an example, each historical data corresponds to feature data.

[0112] The correlation between the description information is determined according to the similarity between the feature data. In an example, the higher the similarity between the feature data, the closer the association relationship between the description information corresponding to the feature data, and the higher the correlation between the corresponding description information, that is, the correlation between the description information and the similarity between the feature data are in a positive correlation relationship.

[0113] The description information with a correlation greater than a preset threshold is determined as the target description information. The preset threshold can be the correlation determined according to the actual application scenario. When the correlation is greater than the preset threshold, it can be considered that the description information meets the common characteristics of the data needing data protection, and is determined as the target description information. When the correlation is less than or equal to the preset threshold, it can be considered that the description information does not meet the common characteristics of the data needing data protection.

[0114] In the embodiment of the present disclosure, when determining the target description information, the correlation between the description information is determined according to the similarity between the feature data corresponding to the description information, the description information with a correlation greater than a preset threshold is determined as the target description information, and it is ensured that the obtained target description information conforms to the characteristics of the historical data, so that the accurate preset protection condition can be determined based on the target description information, and the accuracy of screening the to-be-processed data is further improved.

[0115] In one embodiment, as shown in Figure 7 The method further includes:

[0116] In step S710, access information corresponding to the target database is obtained.

[0117] In step S720, the access information is input into a risk assessment model, and a risk level corresponding to the access information is output by the risk assessment model.

[0118] In step S730, a warning message matching the risk level is sent.

[0119] Exemplarily, risk assessment of data can also be performed. The noisy data set is stored in a target database, wherein the target database can be a database for storing the noisy data set determined in advance according to an actual application scenario.

[0120] Optionally, the access information corresponding to the target database can include, but is not limited to, access data and usage data of the data in the target database, and the corresponding access information is generated when the data in the target database is accessed or used.

[0121] In one example, the risk assessment model can be trained according to the correspondence between the access information samples and the corresponding risk level labels, wherein the access information samples and the corresponding risk level labels can be determined based on historical access information.

[0122] The access information is input into the risk assessment model, and the corresponding risk level is output by the risk assessment model. In one example, the higher the risk level, the greater the possibility of abnormality of the corresponding access information, and the greater the possibility of potential risks.

[0123] The warning information matching the risk level is sent. Different risk levels can correspond to different types and different contents of warning information, which can be determined according to actual application scenarios. In one example, the warning information can be sent to the corresponding operation and maintenance account, so that relevant personnel can discover abnormal behavior and potential risks in time.

[0124] In one example, the data protection effect can be quantitatively analyzed based on the access information and risk level data, and the noise adding process can be optimized and adjusted according to the analysis result.

[0125] According to the access information and the risk assessment model corresponding to the target database, a risk level is obtained, and early warning information matched with the risk level is sent, so that risk monitoring and assessment are realized, early warning information is sent in time, and the security and reliability of the data in the target database are further improved, which is suitable for more application scenarios.

[0126] Figure 8 To show a flowchart of a data processing method according to an exemplary embodiment, refer to Figure 8 As shown in the figure, data is analyzed and identified using data mining and machine learning algorithms, the data to be processed is identified from the initial data set, and is classified to obtain a data set to be processed; noise parameters are calculated according to the data protection level of the data set to be processed, and target noise is generated; the data set to be processed is added with noise using the target noise to add data disturbance, and a data set after noise addition is obtained and stored in a target database; and risk assessment and monitoring are performed according to the access information of the target database.

[0127] Through this embodiment, the attacker can be effectively prevented from obtaining information of a single data sample through correlation analysis; while protecting the data, the usability of the data is not affected, which is suitable for more application scenarios; the operation is simple, the calculation complexity is low, the performance is high, and resource waste is avoided.

[0128] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0129] Based on the same inventive concept, the embodiments of the present application also provide a data processing apparatus for implementing the above-mentioned data processing method. The implementation scheme of the apparatus for solving the problem is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more data processing apparatus embodiments provided below can refer to the limitations of the data processing method described above, which will not be repeated here.

[0130] In one exemplary embodiment, as shown in Figure 9 a data processing apparatus 900 is provided, comprising:

[0131] The acquisition module 910 is configured to acquire an initial data set from a database, wherein the initial data set comprises resource interaction data.

[0132] The division module 920 is configured to determine to-be-processed data that meets a preset protection condition from the initial data set, and divide the to-be-processed data according to a data protection level corresponding to the to-be-processed data, to obtain at least one to-be-processed data set, wherein the data protection levels of the data in each to-be-processed data set are the same.

[0133] The determination module 930 is configured to determine a target noise corresponding to each to-be-processed data set according to a noise parameter corresponding to the data protection level.

[0134] The noise adding module 940 is configured to respectively add noise to the corresponding to-be-processed data set by using the target noise, to obtain and store a data set after noise addition.

[0135] In one embodiment, the determination module is further configured to:

[0136] For each to-be-processed data set, determine a target noise parameter according to a data protection level corresponding to the to-be-processed data set, wherein the target noise parameter and the data protection level are in a negative correlation relationship.

[0137] Determine a target standard deviation according to the target noise parameter and a noise calculation strategy matched with the target noise parameter.

[0138] Generate a target noise according to the target standard deviation, wherein a standard deviation of the target noise is within a preset range of the target standard deviation.

[0139] In one embodiment, the target noise parameter comprises a first parameter and a second parameter, and the determination module is further configured to:

[0140] Determine a first ratio of a preset value to the first parameter, and determine a product of a square root of a logarithm of the first ratio and a data change amount before and after noise addition as a second ratio.

[0141] determine a third ratio between the second ratio and the second parameter as a target standard deviation.

[0142] In one of the embodiments, the apparatus further comprises a preset protection condition determination module, which is configured to:

[0143] obtain historical data from a preset resource interaction database, the historical data comprising data requiring data protection;

[0144] obtain description information corresponding to the historical data, and determine target description information according to a correlation between the description information;

[0145] determine a preset protection condition according to the target description information.

[0146] In one of the embodiments, the preset protection condition determination module is further configured to:

[0147] determine feature data corresponding to the description information, and determine the correlation between the description information according to a similarity between the feature data;

[0148] determine description information with a correlation greater than a preset threshold as the target description information.

[0149] In one of the embodiments, the noise-added data set is stored in a target database, and the apparatus further comprises:

[0150] an obtaining submodule configured to obtain access information corresponding to the target database;

[0151] an inputting submodule configured to input the access information into a risk assessment model, and output a risk level corresponding to the access information through the risk assessment model, the risk assessment model being trained based on a corresponding relationship between access information samples and corresponding risk level labels;

[0152] a sending submodule configured to send a warning message matching the risk level.

[0153] Each of the modules in the data processing apparatus can be realized by software, hardware, or a combination thereof. Each of the modules can be embedded in or independent of a processor in the computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each of the modules.

[0154] In one exemplary embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 10As shown in the figure. The computer device includes a processor, a memory, an Input / Output (I / O) interface, and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store data involved in the method described in the embodiment, such as to-be-processed data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a data processing method.

[0155] Those skilled in the art can understand that, Figure 10 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. A specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0156] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the method embodiments described above.

[0157] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments described above.

[0158] In one embodiment, a computer program product is provided, which includes a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments described above.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of related data need to comply with relevant regulations.

[0160] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0161] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0162] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A data processing method, characterized in that, The method includes: Obtain an initial dataset from the database, the initial dataset including resource interaction data; From the initial dataset, data to be processed that meets preset protection conditions is determined, and the data to be processed is divided according to the data protection level corresponding to the data to be processed, to obtain at least one dataset to be processed, wherein the data in each dataset to be processed has the same data protection level; the method for determining the preset protection conditions includes: obtaining historical data from a preset resource interaction database, the historical data including data that needs to be protected; obtaining descriptive information corresponding to the historical data, and determining target descriptive information based on the correlation between the descriptive information; and determining the preset protection conditions based on the target descriptive information; The step of determining the target description information based on the relevance between the description information includes: determining the feature data corresponding to the description information, and determining the relevance between the description information based on the similarity between the feature data; determining the description information with a relevance greater than a preset threshold as the target description information; Based on the noise parameters corresponding to the data protection level, determine the target noise for each dataset to be processed; The target noise is used to add noise to the corresponding datasets to be processed, and the noisy datasets are obtained and stored.

2. The method according to claim 1, characterized in that, The step of determining the target noise corresponding to each dataset to be processed based on the noise parameters corresponding to the data protection level includes: For each dataset to be processed, a target noise parameter is determined based on the data protection level corresponding to the dataset, wherein the target noise parameter is negatively correlated with the data protection level. The target standard deviation is determined based on the target noise parameters and the noise calculation strategy that matches the target noise parameters; Target noise is generated according to the target standard deviation, and the standard deviation of the target noise is within a preset range of the target standard deviation.

3. The method according to claim 2, characterized in that, The target noise parameters include a first parameter and a second parameter. Determining the target standard deviation based on the target noise parameters and a noise calculation strategy matching the target noise parameters includes: Determine the first ratio between the preset value and the first parameter, and determine the second ratio by the product of the square root of the logarithm of the first ratio and the change in data before and after noise addition; The third ratio between the second ratio and the second parameter is determined as the target standard deviation.

4. The method according to claim 1, characterized in that, The noisy dataset is stored in the target database, and the method further includes: Obtain the access information corresponding to the target database; The access information is input into the risk assessment model, and the risk assessment model outputs the risk level corresponding to the access information. The risk assessment model is trained based on the correspondence between the access information sample and the corresponding risk level label. Send an early warning message that matches the risk level.

5. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire an initial dataset from the database, the initial dataset including resource interaction data; The device includes a segmentation module for identifying data to be processed that meets preset protection conditions from the initial dataset, and segmenting the data to be processed according to the data protection level corresponding to the data to be processed, to obtain at least one dataset to be processed, wherein the data in each dataset to be processed has the same data protection level; the device also includes a module for determining the preset protection conditions, which is used to: obtain historical data from a preset resource interaction database, the historical data including data that needs to be protected; obtain descriptive information corresponding to the historical data, and determine target descriptive information based on the correlation between the descriptive information; and determine the preset protection conditions based on the target descriptive information; The module for determining the preset protection conditions is further configured to: determine the feature data corresponding to the description information, and determine the correlation between the description information based on the similarity between the feature data; and determine the description information with a correlation greater than a preset threshold as the target description information. The determination module is used to determine the target noise corresponding to each dataset to be processed based on the noise parameters corresponding to the data protection level. The noise-adding module is used to add noise to the corresponding datasets to be processed using the target noise, and to obtain and store the noise-adding datasets.

6. The apparatus according to claim 5, characterized in that, The determining module is also used for: For each dataset to be processed, a target noise parameter is determined based on the data protection level corresponding to the dataset, wherein the target noise parameter is negatively correlated with the data protection level. The target standard deviation is determined based on the target noise parameters and the noise calculation strategy that matches the target noise parameters; Target noise is generated according to the target standard deviation, and the standard deviation of the target noise is within a preset range of the target standard deviation.

7. The apparatus according to claim 6, characterized in that, The target noise parameters include a first parameter and a second parameter, and the determining module is further configured to: Determine the first ratio between the preset value and the first parameter, and determine the second ratio by the product of the square root of the logarithm of the first ratio and the change in data before and after noise addition; The third ratio between the second ratio and the second parameter is determined as the target standard deviation.

8. The apparatus according to claim 5, characterized in that, The noisy dataset is stored in the target database, and the device further includes: The acquisition submodule is used to acquire access information corresponding to the target database; The input submodule is used to input the access information into the risk assessment model, and the risk assessment model outputs the risk level corresponding to the access information. The risk assessment model is trained based on the correspondence between the access information sample and the corresponding risk level label. The sending submodule is used to send a warning message that matches the risk level.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images