Data security protection method and system for chip storage area

Abstract

The invention discloses a data security protection method and system for a chip storage area. The data security protection method comprises the following steps: acquiring a plurality of pieces of data information and basic information of the plurality of pieces of data information; grouping the plurality of pieces of data information based on the data source and the data processing task to obtain a plurality of data groups; obtaining N pieces of first abnormal data information from the plurality of pieces of data information based on the data feature vector and the data type; sending a data checking request to the data sources of the N pieces of first abnormal data information and receiving confirmation information transmitted by each data source; taking the first abnormal data information without the confirmation information in the N pieces of first abnormal data information as target abnormal data information; and intercepting the target abnormal data information. According to the method, the target abnormal data information which is accurately screened is intercepted, so that data transmitted by a malicious port is prevented from being disguised as to-be-stored data information to be stored in a storage area of a chip, and the data security protection effect on the storage area is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated circuit chips, and in particular to a data security protection method and system for a chip storage area. Background Art

[0002] As the amount of data processed by integrated circuit chips and the types of data processed increase, the amount of data processed by the chip per unit time is also gradually increasing. However, due to the long-term high-efficiency operation of the chip, the data iteration speed of the chip's storage area is also fast. Often malicious ports will disguise themselves as data information to be processed to steal data information in the storage area. Therefore, how to improve the data security protection effect of the storage area is the current research focus.

[0003] The traditional way to protect data security in storage areas is to identify the source of data information to determine whether the data information is from a malicious client. However, since the source data of a malicious client often disguises the data source address, the data security protection effect of the storage area is poor. Summary of the invention

[0004] The present invention provides a data security protection method and system for a chip storage area to solve the above technical problems and effectively improve the data security protection effect of the storage area.

[0005] In order to solve the above technical problems, the present invention provides a data security protection method for a chip storage area, comprising:

[0006] Acquire a plurality of data information to be stored and basic information of the plurality of data information; the basic information includes: data source, data processing task, data feature vector and data type;

[0007] Grouping a number of data information based on data sources and data processing tasks to obtain multiple data groups;

[0008] Based on the data feature vector and the data type, preliminarily screening the first abnormal data information in each data group to obtain N first abnormal data information from the plurality of data information, where N is a positive integer;

[0009] Sending a data verification request to the data sources of the N first abnormal data information, and receiving confirmation information transmitted by each data source;

[0010] Among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information;

[0011] The target abnormal data information is intercepted.

[0012] The beneficial effects of the present invention are:

[0013] The present invention divides each data information into multiple groups according to the data source and the data processing task, preliminarily screens the first abnormal data information by the data type and the data feature vector, and then performs a confirmation operation, that is, sending a data verification request to the data sources of N first abnormal data information, and receiving the confirmation information transmitted by each data source, and taking the first abnormal data information without confirmation information as the target abnormal data information, to realize the verification of the preliminarily screened first abnormal data information, avoid the situation that normal data information exists in the screened first abnormal data information, and improve the accuracy of the screened abnormal data information. Finally, by intercepting the accurately screened target abnormal data information, it is avoided that the data transmitted by the malicious port disguised as the data information to be stored is stored in the storage area of ​​the chip, thereby improving the data security protection effect of the storage area.

[0014] As a preferred solution, the data information is grouped based on the data source and the data processing task to obtain multiple data groups, including:

[0015] Dividing a number of data information into a plurality of initial data groups based on data sources;

[0016] For each initial data group, the similarity between the data processing tasks of each data information in the initial data group is obtained, and the data information in the initial data group is clustered based on the similarity to obtain multiple data groups.

[0017] As a preferred solution, the data information is divided into a plurality of initial data groups based on the data source, including:

[0018] Obtain the source port corresponding to each data source and the source server corresponding to each data source to determine the source port and source server of each data information;

[0019] Aggregate the data information from the same source server to obtain multiple initial sub-data groups;

[0020] Obtaining the port address of the source port of each data information in each initial sub-data group;

[0021] Calculate the distance information between each port address;

[0022] The data information corresponding to the port addresses less than the distance threshold is divided into the same initial data group to obtain multiple initial data groups.

[0023] This preferred solution improves the fault tolerance rate of identifying the data source of disguised data information by dividing the data information corresponding to the port addresses less than the distance threshold in the same source server into a unified data group.

[0024] As a preferred solution, the obtaining of the similarity between the data processing tasks of each data information in the data group includes:

[0025] Convert each data processing task into text information to obtain each text information;

[0026] Extracting text feature vectors of each text information to obtain each text feature vector;

[0027] Calculate the similarity distance between each text feature vector;

[0028] Based on the similarity distance between each text feature vector, the similarity between the data processing tasks of each data information is determined.

[0029] This preferred solution converts the text information corresponding to the data processing tasks, extracts feature vectors, calculates the similarities between the data processing tasks, and quantifies the data processing tasks, thereby improving the accuracy of the similarities between the determined data processing tasks.

[0030] As a preferred solution, after clustering the data information in the initial data group based on similarity to obtain multiple data groups, the method further includes:

[0031] Respectively in each piece of data information in each data group, obtaining discrete data information in each piece of data information;

[0032] The discrete data information is used as second abnormal data information.

[0033] This preferred solution avoids the situation where the difference information between the discrete data information and the data information with the same data source, the same data type and the same data processing task cannot be identified by directly using the discrete data information as the second abnormal data information.

[0034] As a preferred solution, the method for obtaining the data feature vector includes:

[0035] Get the feature extraction strategy for each data type;

[0036] Based on the data type and the feature extraction strategy of each data type, data feature vectors of each data information are obtained respectively.

[0037] This preferred solution uses feature extraction strategies for different data types to extract data feature vectors of data information of each data type, thereby improving the accuracy of extracting data feature vectors of data information of different data types.

[0038] As a preferred solution, the method of preliminarily screening the first abnormal data information in each data group based on the data feature vector and the data type to obtain N first abnormal data information from the plurality of data information includes:

[0039] In each data group, feature identification information corresponding to each data feature vector is obtained to obtain feature identification information corresponding to each data information;

[0040] Determine, according to the data type and the feature identification information corresponding to each piece of data information, a first data type corresponding to each piece of feature identification information;

[0041] Identifying difference information between feature identification information corresponding to the same first data type;

[0042] The data information corresponding to the difference information is used as the first abnormal data information.

[0043] This preferred solution identifies the first abnormal data information in each data information by screening the difference information existing in other data information, thereby improving the accuracy of identifying the first abnormal data information.

[0044] As a preferred solution, before sending the data verification request to the data sources of the N first abnormal data information, the method further includes:

[0045] Respectively obtain the abnormal feature identification information to which the difference information corresponding to each first abnormal data information belongs, so as to obtain each abnormal feature identification information;

[0046] Respectively obtain the abnormal data content corresponding to each abnormal feature identification information;

[0047] Generate first data identification information of N first abnormal data information;

[0048] Based on the abnormal data content and the first data identification information, N data verification requests for the first abnormal data information are generated respectively.

[0049] This preferred solution only sends the abnormal data content corresponding to the difference information, and directly verifies the abnormal data content with the user while avoiding privacy leakage of the data information. This not only improves the user's ability to identify whether the abnormal data content in the data information is the data information sent by the port, but also improves the privacy protection effect of each data information.

[0050] As a preferred solution, among the N first abnormal data information, taking the first abnormal data information without confirmation information as the target abnormal data information includes:

[0051] Obtain confirmation information of each data source, and identify second data identification information of the confirmation information;

[0052] Selecting the first abnormal data information corresponding to the data identification information from the N first abnormal data information as normal data information;

[0053] The first abnormal data information other than the normal data information is used as the target abnormal data information.

[0054] This preferred solution improves the accuracy of identifying the first abnormal data information by identifying the normal data information in each first abnormal data information to avoid erroneous interception of normal data information and affecting the normal operation of the chip.

[0055] Accordingly, in order to solve the above technical problems, the present invention also provides a data security protection system for a chip storage area, comprising: a data acquisition module, a data grouping module, a preliminary screening module, a target confirmation module and an abnormal interception module;

[0056] The data acquisition module is used to acquire a number of data information to be stored and basic information of a number of data information; the basic information includes: data source, data processing task, data feature vector and data type;

[0057] The data grouping module is used to group a number of data information based on data sources and data processing tasks to obtain multiple data groups;

[0058] The preliminary screening module is used to preliminarily screen the first abnormal data information in each data group based on the data feature vector and the data type, so as to obtain N first abnormal data information from the plurality of data information, where N is a positive integer;

[0059] The target confirmation module is used to send a data verification request to the data sources of N first abnormal data information, and receive confirmation information transmitted by each data source; among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information;

[0060] The abnormal interception module is used to intercept the target abnormal data information. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 : A flow chart of an embodiment of a data security protection method for a chip storage area provided by the present invention;

[0062] Figure 2 : A structural schematic diagram of an embodiment of a data security protection system for a chip storage area provided by the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The traditional way to protect data security in storage areas is to identify the source of data information to determine whether the data information is from a malicious client. However, since the source data of a malicious client often disguises the data source address, the data security protection effect of the storage area is poor.

[0065] Embodiment 1

[0066] In order to solve the above technical problems, the present invention provides a data security protection method and system for a chip storage area, which effectively improves the data security protection effect of the storage area.

[0067] Please refer to Figure 1 , Figure 1 A flowchart of an embodiment of a data security protection method for a chip storage area provided in an embodiment of the present invention.

[0068] like Figure 1 As shown, the data security protection method of the chip storage area includes steps 101 to 106, specifically:

[0069] Step 101: obtaining a plurality of data information to be stored and a plurality of basic information of the data information; the basic information includes: data source, data processing task, data feature vector and data type;

[0070] Step 102: grouping a number of data information based on data sources and data processing tasks to obtain a plurality of data groups;

[0071] Step 103: Preliminarily screening the first abnormal data information in each data group based on the data feature vector and the data type, so as to obtain N first abnormal data information from the plurality of data information, where N is a positive integer;

[0072] Step 104: Sending a data verification request to the data sources of the N first abnormal data information, and receiving confirmation information transmitted by each data source;

[0073] Step 105: Among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information;

[0074] Step 106: intercepting the target abnormal data information.

[0075] The present invention divides each data information into multiple groups according to the data source and the data processing task, preliminarily screens the first abnormal data information by the data type and the data feature vector, and then performs a confirmation operation, that is, sending a data verification request to the data sources of N first abnormal data information, and receiving the confirmation information transmitted by each data source, and taking the first abnormal data information without confirmation information as the target abnormal data information, to realize the verification of the preliminarily screened first abnormal data information, avoid the situation that normal data information exists in the screened first abnormal data information, and improve the accuracy of the screened abnormal data information. Finally, by intercepting the accurately screened target abnormal data information, it is avoided that the data transmitted by the malicious port disguised as the data information to be stored is stored in the storage area of ​​the chip, thereby improving the data security protection effect of the storage area.

[0076] Furthermore, in step 101, a plurality of data information to be stored is obtained by receiving data contents transmitted by each port, wherein the data source includes a source server of the data information and a source port of the data information.

[0077] Furthermore, in step 102, the plurality of data information are grouped based on the data source and the data processing task to obtain a plurality of data groups, including:

[0078] Dividing a number of data information into a plurality of initial data groups based on data sources;

[0079] For each initial data group, the similarity between the data processing tasks of each data information in the initial data group is obtained, and the data information in the initial data group is clustered based on the similarity to obtain multiple data groups.

[0080] Furthermore, the data information is divided into a plurality of initial data groups based on the data source, including:

[0081] Obtain the source port corresponding to each data source and the source server corresponding to each data source to determine the source port and source server of each data information;

[0082] Aggregate the data information from the same source server to obtain multiple initial sub-data groups;

[0083] Obtaining the port address of the source port of each data information in each initial sub-data group;

[0084] Calculate the distance information between each port address;

[0085] The data information corresponding to the port addresses less than the distance threshold is divided into the same initial data group to obtain multiple initial data groups.

[0086] In this embodiment, the distance information between the port addresses is obtained by calculating the straight-line distance between the geographical locations to which the two port addresses belong.

[0087] In this embodiment, the distance threshold is a preset value and can be set and adjusted according to actual needs.

[0088] The present invention improves the fault tolerance rate of identifying the data source of disguised data information by dividing the data information corresponding to the port addresses less than the distance threshold in the same source server into a unified data group.

[0089] Furthermore, the obtaining of the similarity between the data processing tasks of each data information in the data group includes:

[0090] Convert each data processing task into text information to obtain each text information;

[0091] Extracting text feature vectors of each text information to obtain each text feature vector;

[0092] Calculate the similarity distance between each text feature vector;

[0093] Based on the similarity distance between each text feature vector, the similarity between the data processing tasks of each data information is determined.

[0094] In this embodiment, a feature vector corresponding to the semantic information in each text information is extracted respectively by using a reinforcement learning-based feature extraction neural network to obtain a text feature vector of each text information.

[0095] In this embodiment, the similarity distance between each text feature vector can be calculated by, but is not limited to, a cosine similarity algorithm. The similarity is determined by presetting a similarity distance range corresponding to different similarities, and then determining the similarity distance range to which the similarity distance between each data processing task belongs, to obtain the similarity between each data processing task.

[0096] The present invention converts the text information corresponding to the data processing tasks, extracts feature vectors, calculates the similarities between the data processing tasks, and quantifies the data processing tasks, thereby improving the accuracy of the similarities between the determined data processing tasks.

[0097] Furthermore, after clustering the data information in the initial data group based on similarity to obtain multiple data groups, the method further includes:

[0098] Respectively in each piece of data information in each data group, obtaining discrete data information in each piece of data information;

[0099] The discrete data information is used as second abnormal data information.

[0100] In this embodiment, the discrete data information is data information that does not belong to any data group after clustering processing.

[0101] In this embodiment, the data security protection method of the chip storage area further includes: updating N first abnormal data information based on the second abnormal data information.

[0102] The present invention directly uses discrete data information as the second abnormal data information, thereby avoiding the situation where the difference information between the discrete data information and the data information with the same data source, the same data type and the same data processing task cannot be identified, and includes the discrete data information in the consideration scope as the target abnormal data information, thereby improving the accuracy of identifying whether the discrete data information is the target abnormal data information, ensuring the comprehensiveness of the screened target abnormal data information without missing any possible data information from malicious ports, thereby improving the data security protection effect of the storage area.

[0103] Furthermore, the method for obtaining the data feature vector includes:

[0104] Get the feature extraction strategy for each data type;

[0105] Based on the data type and the feature extraction strategy of each data type, data feature vectors of each data information are obtained respectively.

[0106] In this embodiment, different data types have different feature extraction strategies. For example, the feature extraction strategy for text type data information is to extract features based on a text semantic feature extraction network, the feature extraction strategy for picture type data information is to extract features based on a convolutional neural network for image feature recognition, and the feature extraction strategy for voice type data information is to identify the text information corresponding to the voice data information, and then extract the feature vector of the text information through a text semantic feature extraction network to obtain the feature vector of the voice data information.

[0107] The present invention uses feature extraction strategies for different data types to respectively extract data feature vectors of data information of each data type, thereby improving the accuracy of extracting data feature vectors of data information of different data types.

[0108] Furthermore, in step 103, based on the data feature vector and the data type, the first abnormal data information is preliminarily screened in each data group to obtain N first abnormal data information from the plurality of data information, including:

[0109] In each data group, feature identification information corresponding to each data feature vector is obtained to obtain feature identification information corresponding to each data information;

[0110] Determine, according to the data type and the feature identification information corresponding to each piece of data information, a first data type corresponding to each piece of feature identification information;

[0111] Identifying difference information between feature identification information corresponding to the same first data type;

[0112] The data information corresponding to the difference information is used as the first abnormal data information.

[0113] In this embodiment, the feature identification information is the content meaning information of the data content represented by the data feature vector. For example, the content meaning information of each data content in the picture data information includes the content category of the picture target content, such as a building, an object, a portrait of a person, etc. The content meaning of the picture signature content includes the author, date, location, etc. of the picture.

[0114] In this embodiment, the difference information is the same difference information that exists in data information of the same data type and other data information. For example, the feature identification information in image data information A is code information, and the code information is the difference information between image data information A and image data information B, image data information C, and image data information D. This proves that image data information A is abnormal data information, and the data content corresponding to the code information may be virus code actually transmitted to the chip by a malicious port, etc.

[0115] The present invention identifies the first abnormal data information in each data information by screening the difference information existing in other data information, thereby improving the accuracy of identifying the first abnormal data information.

[0116] Furthermore, in step 104, that is, before sending the data verification request to the data sources of the N first abnormal data information, the method further includes:

[0117] Respectively obtain the abnormal feature identification information to which the difference information corresponding to each first abnormal data information belongs, so as to obtain each abnormal feature identification information;

[0118] Respectively obtain the abnormal data content corresponding to each abnormal feature identification information;

[0119] Generate first data identification information of N first abnormal data information;

[0120] Based on the abnormal data content and the first data identification information, N data verification requests for the first abnormal data information are generated respectively.

[0121] The present invention only sends the abnormal data content corresponding to the difference information, and directly checks the abnormal data content with the user while avoiding the privacy leakage of the data information. This not only improves the user's ability to identify whether the abnormal data content in the data information is the data information sent by the port, but also improves the privacy protection effect of each data information.

[0122] Further, in step 105, among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information, including:

[0123] Obtain confirmation information of each data source, and identify second data identification information of the confirmation information;

[0124] Selecting the first abnormal data information corresponding to the data identification information from the N first abnormal data information as normal data information;

[0125] The first abnormal data information other than the normal data information is used as the target abnormal data information.

[0126] The present invention avoids the situation where the normal data information is mistakenly intercepted and the normal operation of the chip is affected by identifying the normal data information in each first abnormal data information, thereby improving the accuracy of identifying the first abnormal data information.

[0127] Furthermore, in step 106, by intercepting the accurately screened target abnormal data information, data transmitted by a malicious port disguised as data information to be stored is prevented from being stored in the storage area of ​​the chip, thereby improving the data security protection effect of the storage area.

[0128] The data security protection method for the chip storage area provided in the embodiment of the present application can be applied to the application environment of the storage area security protection of the Internet of Things chip. The method can be applied to a terminal, a server, or a system including a terminal and a server, and implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc.

[0129] Accordingly, in order to solve the above technical problems, the present invention also provides a data security protection system for a chip storage area. Figure 2 , which is a structural diagram of an embodiment of a data security protection system for a chip storage area provided by the present invention.

[0130] like Figure 2 As shown, the data security protection system 20 of the chip storage area includes: a data acquisition module 201, a data grouping module 202, a preliminary screening module 203, a target confirmation module 204 and an abnormal interception module 205;

[0131] The data acquisition module 201 is used to acquire a number of data information to be stored and basic information of a number of data information; the basic information includes: data source, data processing task, data feature vector and data type;

[0132] The data grouping module 202 is used to group a number of data information based on data sources and data processing tasks to obtain multiple data groups;

[0133] The preliminary screening module 203 is used to preliminarily screen the first abnormal data information in each data group based on the data feature vector and the data type, so as to obtain N first abnormal data information from the plurality of data information, where N is a positive integer;

[0134] The target confirmation module 204 is used to send a data verification request to the data sources of the N first abnormal data information, and receive confirmation information transmitted by each data source; among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information;

[0135] The abnormal interception module 205 is used to intercept the target abnormal data information.

[0136] Each module in the data security protection system of the chip storage area can be fully or partially implemented by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules. The implementation solution provided by the data security protection system of the chip storage area is similar to the implementation solution described in the above method, so the specific limitations in the data security protection system embodiment of one or more chip storage areas provided below can refer to the limitations of the data security protection method for the chip storage area above, and will not be repeated here.

[0137] 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 used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0138] 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, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, 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. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0139] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0140] The present invention divides each data information into multiple groups according to the data source and the data processing task of the data information, and then screens the first abnormal data information by the data type of the data information and the data feature vector of the data information, thereby directly screening the first abnormal data information by identifying the difference information between each data information of the same data type, data processing task and data source on the basis of removing the influence information of the malicious port by disguising the data type, data processing task, and data source, thereby improving the accuracy of screening the abnormal data information, and then through the secondary confirmation operation, the screened first abnormal data information is checked again for the second time to avoid the situation where normal data information exists in the screened first abnormal data information, thereby further improving the accuracy of the screened first abnormal data information. Finally, by intercepting the accurately screened target abnormal data information, the data transmitted by the malicious port disguised as the data information to be stored is prevented from being stored in the storage area of ​​the chip, thereby improving the data security protection effect of the storage area of ​​the chip.

[0141] It should be understood that, although the steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequentially, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned specific embodiments further describe the purpose, technical scheme and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A data security protection method for a chip storage area, characterized in that: include: Obtaining a number of data information to be stored and basic information of a number of data information; The basic information includes: data source, data processing task, data feature vector and data type; Grouping a number of data information based on data sources and data processing tasks to obtain multiple data groups; Based on the data feature vector and the data type, preliminarily screening the first abnormal data information in each data group to obtain N first abnormal data information from the plurality of data information, where N is a positive integer; Sending a data verification request to the data sources of the N first abnormal data information, and receiving confirmation information transmitted by each data source; Among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information; The target abnormal data information is intercepted.

2. A chip storage area data security protection method as claimed in claim 1, characterized in that: The data information is grouped based on the data source and the data processing task to obtain multiple data groups, including: Dividing a number of data information into a plurality of initial data groups based on data sources; For each initial data group, the similarity between the data processing tasks of each data information in the initial data group is obtained, and the data information in the initial data group is clustered based on the similarity to obtain multiple data groups.

3. A chip storage area data security protection method as claimed in claim 2, characterized in that: The method of dividing a plurality of data information into a plurality of initial data groups based on data sources includes: Obtain the source port corresponding to each data source and the source server corresponding to each data source to determine the source port and source server of each data information; Aggregate the data information from the same source server to obtain multiple initial sub-data groups; Obtaining the port address of the source port of each data information in each initial sub-data group; Calculate the distance information between each port address; The data information corresponding to the port addresses less than the distance threshold is divided into the same initial data group to obtain multiple initial data groups.

4. A chip storage area data security protection method as claimed in claim 2, characterized in that: The obtaining of the similarity between the data processing tasks of each data information in the data group includes: Convert each data processing task into text information to obtain each text information; Extracting text feature vectors of each text information to obtain each text feature vector; Calculate the similarity distance between each text feature vector; Based on the similarity distance between each text feature vector, the similarity between the data processing tasks of each data information is determined.

5. A chip storage area data security protection method as claimed in claim 2, characterized in that: After clustering the data information in the initial data group based on similarity to obtain multiple data groups, the method further includes: Respectively in each piece of data information in each data group, obtaining discrete data information in each piece of data information; The discrete data information is used as second abnormal data information.

6. A chip storage area data security protection method as claimed in claim 1, characterized in that: The method for obtaining the data feature vector includes: Get the feature extraction strategy for each data type; Based on the data type and the feature extraction strategy of each data type, data feature vectors of each data information are obtained respectively.

7. A chip storage area data security protection method as claimed in claim 1, characterized in that: The method of preliminarily screening the first abnormal data information in each data group based on the data feature vector and the data type to obtain N first abnormal data information from the plurality of data information includes: In each data group, feature identification information corresponding to each data feature vector is obtained to obtain feature identification information corresponding to each data information; Determine, according to the data type and the feature identification information corresponding to each piece of data information, a first data type corresponding to each piece of feature identification information; Identifying difference information between feature identification information corresponding to the same first data type; The data information corresponding to the difference information is used as the first abnormal data information.

8. A chip storage area data security protection method as claimed in claim 7, characterized in that: Before sending the data verification request to the data sources of the N first abnormal data information, the method further includes: Respectively obtain the abnormal feature identification information to which the difference information corresponding to each first abnormal data information belongs, so as to obtain each abnormal feature identification information; Respectively obtain the abnormal data content corresponding to each abnormal feature identification information; Generate first data identification information of N first abnormal data information; Based on the abnormal data content and the first data identification information, N data verification requests for the first abnormal data information are generated respectively.

9. A chip storage area data security protection method as claimed in claim 1, characterized in that: The first abnormal data information without confirmation information among the N first abnormal data information is used as the target abnormal data information, including: Obtain confirmation information of each data source, and identify second data identification information of the confirmation information; Selecting the first abnormal data information corresponding to the data identification information from the N first abnormal data information as normal data information; The first abnormal data information other than the normal data information is used as the target abnormal data information.

10. A data security protection system for a chip storage area, characterized in that: include: Data acquisition module, data grouping module, preliminary screening module, target confirmation module and abnormal interception module; The data acquisition module is used to acquire a number of data information to be stored and basic information of a number of data information; the basic information includes: data source, data processing task, data feature vector and data type; The data grouping module is used to group a number of data information based on data sources and data processing tasks to obtain multiple data groups; The preliminary screening module is used to preliminarily screen the first abnormal data information in each data group based on the data feature vector and the data type, so as to obtain N first abnormal data information from the plurality of data information, where N is a positive integer; The target confirmation module is used to send a data verification request to the data sources of N first abnormal data information, and receive confirmation information transmitted by each data source; among the N first abnormal data information, the first abnormal data information without confirmation information is used as the target abnormal data information; The abnormal interception module is used to intercept the target abnormal data information.

Images