Submission violation identification method, device and equipment for supervising secret-related data, and computer program product

Abstract

The invention discloses a submission violation identification method, device and equipment for supervising secret-related data and a computer program product, and the method comprises the steps: collecting brain wave information of an operator under stimulation events, and the stimulation events comprise a real stimulation event and a simulation stimulation event; processing the brain wave information to obtain a brain wave information processing result under the stimulation event; according to the brain wave information processing result under the stimulation event, a multi-dimensional violation recognition model is used for recognition, and a physiological violation recognition result and a psychological violation recognition result are obtained; and determining a final violation recognition result by using a violation judgment model according to the physiological violation recognition result and the psychological violation recognition result. According to the method, the stimulation event and the brain wave information are associated, useful brain wave information can be effectively focused, pertinence and accuracy of illegal behavior recognition are improved, brain wave baseline data are provided for subsequent illegal behavior recognition by simulating the stimulation event, and accuracy of illegal behavior judgment is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of confidential data supervision, and in particular to a method, device and equipment for identifying violations in the reporting of confidential data, and a computer program product. Background Art

[0002] Regulatory data refers to data reported to regulatory authorities at their request. Regulatory authorities set the length, content and standards of the reporting fields. If the reported data involves corporate secrets, it is regulatory confidential data.

[0003] In order to ensure the security of reporting of confidential regulatory data, it is necessary to monitor and identify the illegal behavior of operators who report confidential regulatory data. In the existing technology, the illegal operation of operators is mainly identified through proprietary equipment and video monitoring. Proprietary equipment solves the problem of illegal operation in space, and video monitoring solves the problem of being able to observe illegal operation. It cannot solve the problem of malicious copying under body cover, taking pictures with special equipment, and even copying after the brain memory leaves, etc., which leaks confidential data and cannot fully identify the illegal behavior of operators. In the case of malicious destruction and modification of confidential regulatory data, all existing logs and permission controls have room for human manipulation, and are mainly based on post-event discovery and prevention, lacking an in-event discovery mechanism. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus and equipment, and a computer program product for identifying violations in the reporting of confidential data, so as to improve the accuracy and timeliness of identifying violations and ensure the security of enterprise data and regulatory data.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying violations in reporting of confidential data, the method comprising:

[0007] Collecting brain wave information of operators under stimulation events, wherein the stimulation events refer to reporting events of confidential data, the stimulation events include real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information;

[0008] Processing the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result;

[0009] According to the brain wave information processing result under the stimulation event, a multi-dimensional violation recognition model is used to perform recognition to obtain a violation recognition result, wherein the violation recognition result includes a physiological violation recognition result and a psychological violation recognition result;

[0010] According to the physiological violation identification result and the psychological violation identification result, a violation determination model is used to determine a final violation identification result.

[0011] Optionally, collecting brain wave information of the operator under the stimulation event includes:

[0012] The brain wave information of the operator under the stimulation event is collected by using a brain wave collection device in a preset electrode lead mode;

[0013] Among them, the preset electrode lead mode is used to monitor the brain wave information of key brain areas, and the key brain areas include visual areas and high-level psychological function areas.

[0014] Optionally, the brain wave information is an EGG image, and the processing of the brain wave information of the operator to obtain the brain wave information processing result includes:

[0015] Splitting the EGG image of the operator according to the category of brain wave information and the type of stimulation event to obtain a plurality of EGG images of brain wave categories corresponding to each type of stimulation event, wherein the plurality of EGG images of brain wave categories include a plurality of EGG images of physiological categories and a plurality of EGG images of psychological categories;

[0016] Aggregating EGG images of multiple brain wave categories corresponding to each type of stimulation event within a preset time period according to the type of stimulation event, to obtain aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period;

[0017] The aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period are superimposed according to the category of brain wave information to obtain the superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period;

[0018] The superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period are averaged and converted to obtain ERP images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period.

[0019] Optionally, the multidimensional violation recognition model includes a multidimensional physiological violation recognition model and a multidimensional psychological violation recognition model. The violation recognition result obtained by using the multidimensional violation recognition model for recognition based on the brain wave information processing result under the stimulation event includes:

[0020] According to the processing results of physiological brain wave information under the stimulation event, a multi-dimensional physiological violation recognition model is used to perform recognition and obtain the physiological violation recognition result;

[0021] According to the processing results of psychological brain wave information under the stimulus event, a multi-dimensional psychological violation recognition model is used to obtain the psychological violation recognition result.

[0022] Optionally, the multi-dimensional physiological violation recognition model includes a visual physiological violation recognition model, a physiological tension recognition model, and a writing operation violation recognition model; the multi-dimensional psychological violation recognition model includes a task processing time violation recognition model, an abnormal psychological behavior violation recognition model, and a judgment violation recognition model; the physiological violation recognition result obtained by using the multi-dimensional physiological violation recognition model for recognition based on the physiological brain wave information processing result under the stimulation event includes:

[0023] According to the physiological brain wave information processing result under the stimulation event, the visual physiological violation recognition model, the physiological tension recognition model and the writing operation violation recognition model are used to perform recognition respectively to obtain the visual physiological violation recognition result, the physiological tension recognition result and the writing operation violation recognition result;

[0024] According to the processing results of physiological brain wave information under the stimulation event, the task processing time violation identification model, the abnormal psychological behavior violation identification model and the judgment type violation identification model are used respectively to perform identification, and the task processing time violation identification results, the abnormal psychological behavior violation identification results and the judgment type violation identification results are obtained.

[0025] Optionally, the method for identifying violations in reporting of confidential data may further include:

[0026] Obtain brain wave information of operators’ historical reporting operations on confidential data;

[0027] Processing the brain wave information of the operator's historical reporting operation on the supervision of confidential data to obtain the processing result of the operator's historical brain wave information;

[0028] The multi-dimensional violation identification model is used to identify the violation according to the brain wave information processing result under the stimulation event, and the violation identification result obtained includes:

[0029] According to the brain wave information processing results under the real stimulation event, the brain wave information processing results of the simulated stimulation event and the historical brain wave information processing results of the operator, a multi-dimensional violation recognition model is used to perform recognition to obtain a violation recognition result.

[0030] Optionally, the violation determination model includes a physiological violation behavior activation function, a psychological violation behavior activation function, and a comprehensive activation function, and determining the final violation identification result using the violation determination model according to the physiological violation identification result and the psychological violation identification result includes:

[0031] Processing the physiological violation identification result using the physiological violation behavior activation function to obtain a physiological violation behavior activation result;

[0032] Processing the psychological violation identification result using the psychological violation behavior activation function to obtain a psychological violation behavior activation result;

[0033] The physiological violation behavior activation result and the psychological violation behavior activation result are processed by using the comprehensive activation function to obtain the final violation identification result.

[0034] In a second aspect, an embodiment of the present application further provides a device for identifying violations in reporting of confidential data, the device comprising:

[0035] A collection unit, used to collect brain wave information of operators under stimulation events, wherein the stimulation events refer to reporting events of supervision-related confidential data, the stimulation events include real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information;

[0036] A brain wave processing unit, used for processing the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result;

[0037] A violation identification unit, used to identify the violation using a multi-dimensional violation identification model according to the brain wave information processing result under the stimulation event, and obtain a violation identification result, wherein the violation identification result includes a physiological violation identification result and a psychological violation identification result;

[0038] The violation determination unit is used to determine a final violation identification result by using a violation determination model according to the physiological violation identification result and the psychological violation identification result.

[0039] In a third aspect, an embodiment of the present application further provides a device, including:

[0040] A processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute any of the aforementioned methods for identifying violations in the reporting of regulatory confidential data.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements any of the aforementioned methods for identifying violations in reporting of regulatory confidential data.

[0042] At least one of the above-mentioned technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the method for identifying violations in reporting of regulatory confidential data in the embodiments of the present application first collects brain wave information of the operator under a stimulation event, where the stimulation event refers to a reporting event of regulatory confidential data, and the stimulation event includes a real stimulation event and a simulated stimulation event, and the brain wave information includes physiological brain wave information and psychological brain wave information; then, the brain wave information of the operator under the stimulation event is processed to obtain a brain wave information processing result under the stimulation event, and the brain wave information processing result includes a physiological brain wave information processing result and a psychological brain wave information processing result; then, according to the brain wave information processing result under the stimulation event, a multi-dimensional violation identification model is used for identification to obtain a violation identification result, and the violation identification result includes a physiological violation identification result and a psychological violation identification result; finally, according to the physiological violation identification result and the psychological violation identification result, a violation determination model is used to determine the final violation identification result. The method for identifying violations in reporting of confidential regulatory data in the embodiment of the present application associates stimulation events with original brain wave information to monitor brain wave behavior, which can effectively focus on useful brain wave information, improve the pertinence, accuracy and timeliness of violation identification, and effectively solves the problem of insufficient initial data by simulating stimulation events, and also provides brain wave baseline data for the identification of subsequent violations, further improving the accuracy of violation determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 A flowchart of a method for identifying violations in supervising confidential data in an embodiment of the present application;

[0045] Figure 2 This is a schematic diagram of the overall process of identifying violations in the reporting of confidential data in an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the lead design between electrodes of a brain wave acquisition device in an embodiment of the present application;

[0047] Figure 4 This is a schematic diagram of a brain wave information processing flow in an embodiment of the present application;

[0048] Figure 5This is a structural diagram of a reporting violation identification device for supervising confidential data in an embodiment of the present application;

[0049] Figure 6 This is a schematic diagram of the structure of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0051] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0052] The main technical terms involved in this application include:

[0053] 1) EGG: It is the abbreviation of electroencephalogram in English, which is translated into Chinese as electroencephalogram. It collects the bioelectric signals in the brain through electrodes, amplifies them one million times, and presents them to humans in the form of a graph. It is a form of display of the brain's activity status.

[0054] 2) ERP: Event Related Potential in English, translated into Chinese as event-related brain wave potential. On the basis of EGG, a stimulus event is added, the EGG image after the stimulus event is processed, and then the ERP graph is obtained. The ERP graph can more accurately reflect the activity state of the brain after the stimulus event occurs.

[0055] This application comprehensively monitors all behaviors of operators by analyzing brain waves and discovers all possible illegal operations, because all illegal behaviors of operators belong to the advanced psychological functions of people, and will be reflected in brain activities. Brain activities are essentially changes in the electrical signals of brain neurons. According to the changes in electrical signals, the brain neural network reaction is formed. This electrical signal neural network does not lie and has been engraved in human genes. For example, if someone is very angry, he can control his emotions so that others will not find out, but no matter how he hides himself, his blood pressure will rise and his amygdala activity will increase, because this is the body and brain's instinctive reaction to anger. By monitoring the brain's amygdala brain wave activity, it can be found that he is actually angry. This means that all illegal operations can be monitored through brain waves. This is the monitoring method used in this application. In theory, the number of electrodes is large enough, the granularity of the covered brain neuron electrical signals is fine enough, and the possibility of illegal behavior being discovered is large enough.

[0056] Specifically, the present application embodiment provides a method for identifying violations in the reporting of confidential data, such as Figure 1 As shown, a flow chart of a method for identifying violations in reporting of confidential data in accordance with an embodiment of the present application is provided. The method for identifying violations in reporting of confidential data at least includes the following steps S110 to S140:

[0057] Step S110, collecting brain wave information of the operator under stimulation events, wherein the stimulation events refer to reporting events of confidential data, the stimulation events include real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information.

[0058] Combination Figure 2 , provides a schematic diagram of the overall process of identifying violations in reporting of confidential data in the present application embodiment. The data basis for analyzing and identifying violations of personnel who report confidential data in the present application embodiment is brain wave information. The operator receives information from the retina, reaches the thalamus through the optic nerve, then reaches the lateral geniculate nucleus LGN, and then enters the visual cortex (the back of the head, the medical term is the occipital lobe), and then enters the higher psychological function area. After processing, the higher psychological function area sends electrical signals to other areas of the cerebral cortex, and then other areas trigger various behaviors of people. By analyzing brain wave information, all behaviors of the operator can be fully monitored and all possible violations can be found.

[0059] Based on this, the embodiment of the present application needs to collect brain wave information of relevant operators under stimulation events in the scenario of supervision of confidential data reporting. The embodiment of the present application defines stimulation events as the reporting and processing of different confidential data, and the reporting and processing of the same type of confidential data is a type of stimulation event. Because in the specific supervision of confidential data reporting work, non-confidential data and confidential data are mixed together, confidential data requires secondary identity authentication, so the secondary identity authentication serves as the starting point for the operation of the stimulation event.

[0060] Stimulus events can be divided into real stimulation events and simulated stimulation events. Real stimulation events refer to reporting events in which operators actually receive regulatory confidential data in real reporting scenarios. Simulated stimulation events are events imposed on operators in various simulated scenarios before the actual violation behavior of operators is identified. The purpose is to collect as much brain wave information of illegal operations and subsequent scenarios as possible as baseline data for subsequent violation identification.

[0061] Since different people have different brain wave information and characteristics in the same scenario, collecting brain wave information under simulated stimulation events for each operator can achieve targeted and personalized brain wave analysis, thereby improving the accuracy of identifying violations.

[0062] Step S120, processing the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result.

[0063] Existing brain wave analysis schemes simply use EGG electroencephalogram information and lack association with stimulation events. The processing of brain wave information in the embodiments of the present application is mainly to associate stimulation events with EGG electroencephalogram information, and use the ERP images generated after processing to monitor brain wave behavior, which is more prepared and targeted and can effectively focus on useful brain wave information.

[0064] In addition, existing brain wave analysis schemes do not distinguish between physiological brain waves and psychological brain waves. In specific usage scenarios, the weights of physiological brain waves and psychological brain waves in the judgment results are bound to be different, and the processing procedures and model establishment of physiological brain waves and psychological brain waves are also bound to be different. This application refines the brain wave classification, and processes the physiological brain wave information and psychological brain wave information collected in the aforementioned steps separately, thereby further improving the recognition effect of subsequent models on different types of brain wave information.

[0065] Step S130, based on the brain wave information processing result under the stimulation event, a multi-dimensional violation recognition model is used to perform recognition to obtain a violation recognition result, wherein the violation recognition result includes a physiological violation recognition result and a psychological violation recognition result.

[0066] The embodiment of the present application establishes different multi-dimensional violation identification models for physiological brain wave information and psychological brain wave information respectively, and uses the multi-dimensional violation identification models corresponding to the physiological brain wave information and the psychological brain wave information to perform violation identification respectively, thereby improving the comprehensiveness of the identification of violation behavior characteristics and further improving the accuracy of violation behavior determination.

[0067] Step S140, determining a final violation identification result by using a violation determination model according to the physiological violation identification result and the psychological violation identification result.

[0068] After obtaining the physiological violation identification results and the psychological violation identification results, it is necessary to integrate the physiological violation identification results and the psychological violation identification results, and further use the violation judgment model to make a final judgment on the violation behavior. This method fully considers the difference in the impact of two different brain wave information on the judgment results, and improves the accuracy of violation behavior identification.

[0069] The method for identifying violations in reporting of confidential regulatory data in the embodiment of the present application associates stimulation events with original brain wave information to monitor brain wave behavior, which can effectively focus on useful brain wave information, improve the pertinence, accuracy and timeliness of violation identification, and effectively solves the problem of insufficient initial data by simulating stimulation events, and also provides brain wave baseline data for the identification of subsequent violations, further improving the accuracy of violation determination.

[0070] In some embodiments of the present application, brain wave information under simulated stimulation events can be collected in the following manner:

[0071] Simulated stimulus events are situational drills, which collect psychological and physiological information on illegal operations through answering questions. The drill scenarios include accidental and malicious destruction, change and leakage of regulatory confidential data. Specific scenarios are set through historical experience and expert methods. The question design needs to allow operators to simulate related behaviors. For example, a set of value data is first given, and the operator is asked to copy it into the input box below, and then enter the data he can remember on the next page. For example, the operator can first be asked to judge the value of the data, and then initiate the reporting task of Class A confidential data with lower value, Class B confidential data with higher value, and Class C confidential data with extremely high value according to the operator's judgment. The operator is required to calculate the value of each type of data in the black market based on the given value and data volume, design three stealing methods, and be required to evaluate which method is the safest and answer the lifestyle he chooses after receiving the corresponding money. Even if the operator knows the purpose of the scenario exercise, the brain wave reaction to a certain type of event is not controlled by humans. For example, if the operator is very angry about the behavior of the scenario exercise and does not want to be discovered, no matter how he hides himself, his blood pressure will rise and the activity of the amygdala will increase, because this is the body and brain's instinctive reaction to anger. In short, ensure that the scenario exercise can collect as much illegal operation and subsequent scene brain wave information as possible.

[0072] In some embodiments of the present application, the collecting of brain wave information of the operator under a stimulation event includes: collecting the brain wave information of the operator under the stimulation event by a brain wave collection device in a preset electrode lead mode; wherein the preset electrode lead mode is used to monitor the brain wave information of key brain areas, and the key brain areas include visual areas and higher psychological function areas.

[0073] The essence of brain wave monitoring is the monitoring of bioelectricity. Bioelectricity is an electrical signal generated by human activities. The inner side of the neuron cell membrane is a negative voltage, and the outer side is a positive voltage. When stimulated, sodium ions will pass through the cell membrane and flow into the inner side, breaking the original resting potential. The inner side becomes a positive voltage and the outer side becomes a negative voltage, thus forming bioelectricity. Bioelectricity will be transmitted from the axon to the nerve endings, and then transmitted downward again through the nerve endings.

[0074] The existing method of detecting brain activity bioelectricity is to place electrodes. The 10-20 system electrode placement method is the standard electrode placement method specified by the International Electroencephalography Society. The specific operation is to take 8 electrodes from each side of the brain, plus the frontal midpoint (Fz), central point (Cz), vertex (Pz) and two ear electrodes in the frontal and posterior positions, a total of 21 electrodes. The distance from the frontal midpoint to the root of the nose and the distance from the occipital point to the external occipital protuberance each account for 10% of the total length of this line, and the remaining points are separated by 20% of the total length of this line, so it is named the 10-20 system.

[0075] The 10-20 system electrode placement method only determines the position of the electrode, but does not determine how the electrodes are connected. Lead design is the design of the connection method between the electrodes. If there is a connection between the two electrodes, the potential difference between the areas represented by the two electrodes can be monitored, and the bioelectric flow between the two areas can be monitored. The 18-lead design is common in medicine.

[0076] It can be seen that the existing EEG detection solutions do not have lead designs suitable for violation scenarios. Many existing solutions do not introduce what kind of lead design to use. Most of the introduced solutions use the common single-stage lead-average electrode or single-stage lead-ear-level lead in medicine. These two scenarios are suitable for medical case examinations and monitoring of violations caused by sound, and cannot be directly applied to scenarios for identifying violations.

[0077] Based on this, the embodiment of the present application uses a proprietary brain wave acquisition device to collect brain wave information. The distribution of the acquisition electrodes uses the 10-20 system electrode placement method specified by the International Electroencephalography Association. Eight electrodes are taken from each side of the brain, plus the frontal midpoint (F z ), center point (C z ), Vertex(P z ) and two ear electrodes, a total of 21 electrodes. The distance from the midpoint of the frontal pole to the root of the nose and the distance from the occipital point to the external occipital protuberance each account for 10% of the total length of this line. The basic physiological activity information of the brain can be monitored through 21 electrodes.

[0078] Specifically, the embodiment of the present application sets a lead mode between the electrodes of the brain wave acquisition device according to the specific use scenario of supervising the reporting of confidential data, and monitors the psychological activity information of the brain after encountering a stimulation event through a unique lead mode. Figure 3 FIG. 1 is a schematic diagram of the lead design between electrodes of a brain wave acquisition device according to an embodiment of the present application. p1 , F p2 Monitoring point and F z, F3, F4, F7, F8, connect monitoring points F3, F4, F7, F8, monitoring points O1, O2 and other monitoring points, focus on monitoring the bio-computer wave signals between the visual area (through O1, O2 occipital lobe area of ​​the brain), the higher psychological function area (through F3, F4, F7, F8 monitoring the frontal lobe area of ​​the brain) and other areas.

[0079] Furthermore, existing solutions have problems with unreasonable settings and failure to eliminate useless brain wave information during the process of collecting brain wave information. For example, when using brain wave information, medical parameter settings are often used to refer to the sensitivity of 7μv / mm and low-frequency filtering of ≤1Hz. The purpose is to better display pathological electrical activities within the δ range, monitor whether the waveforms on both sides are symmetrical, and whether the frequency difference exceeds 20%, so as to determine whether one side of the brain has pathological problems and needs to collect and process olfactory brain wave information.

[0080] In the embodiment of the present application, for the specific use scenario of regulatory confidential data reporting, the sensitivity is set to a value suitable for the scenario of regulatory confidential data reporting, such as 8μv / mm, and the low-frequency filtering is no longer restricted to ≤1Hz. During the processing process, symmetrical brain wave information comparison is abandoned, and processing of other irrelevant brain wave information such as smell is abandoned.

[0081] In some embodiments of the present application, the collected physiological brain wave information mainly includes:

[0082] 1) Visual functional area: responsible for monitoring vision, image recognition, and image perception brain wave information, mainly through monitoring the neural activities of area O and other areas.

[0083] 2) Motor function area: responsible for monitoring voluntary muscle movement, mainly by monitoring the neural activity between the P and C areas and with other areas.

[0084] 3) Sensory functional area: responsible for monitoring the muscle and skin muscle movements, mainly by monitoring the nerve activity between the P, T and C areas and with other areas.

[0085] 4) Broca's area: responsible for monitoring the movement of the speech muscles, mainly by monitoring the neural activity between F7 and F8 and T3, T4 areas and other areas

[0086] 5) Wernicke's area: responsible for the writing center, mainly through monitoring the neural activity between T5, T6 and other areas.

[0087] 6) Auditory area: responsible for auditory information processing, mainly by monitoring the neural activities between A1, A2 and other areas.

[0088] The olfactory area is irrelevant to the scenario in which this application is applied, so monitoring the brain wave information of the olfactory area can be omitted.

[0089] The collected psychological brainwave information mainly includes:

[0090] Advanced psychological function area: responsible for processing information such as concentration, planning, judgment, emotion, creation and inhibition. p1 , F p2 , F z , the neural activities between F3, F4, F7, F8 and with other areas monitor this type of brain activity.

[0091] In some embodiments of the present application, the brain wave information is an EGG image, and the processing of the brain wave information of the operator to obtain the brain wave information processing result includes: splitting the EGG image of the operator according to the category of brain wave information and the type of stimulation event to obtain multiple EGG images of brain wave categories corresponding to each type of stimulation event, and the multiple EGG images of brain wave categories include multiple EGG images of physiological categories and multiple EGG images of psychological categories; aggregating the multiple EGG images of brain wave categories corresponding to each type of stimulation event within a preset time period according to the type of stimulation event to obtain aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; superimposing the aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period according to the category of brain wave information to obtain superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; performing average conversion on the superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period to obtain ERP images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period.

[0092] The processing of brain wave information can be divided into the processing of physiological brain wave information and the processing of psychological brain wave information. The processing flow of physiological brain wave information is the same as that of psychological brain wave information, but the data types processed are different. Therefore, the processing flow of psychological brain wave information is used as an example to illustrate here.

[0093] like Figure 4As shown, a schematic diagram of a brain wave information processing flow in an embodiment of the present application is provided. The processing flow of psychological brain wave information mainly includes four steps: splitting, aggregation, superposition, and average conversion. The first step is to split the EGG image into six psychological brain wave EGG graphs, and then split them into EGG graphs of respective stimulation events according to the type of stimulation event; the second step is to classify and aggregate the EGG graphs of the same type of stimulation events within a preset time period (which can be set to the maximum concentration time of general operators, such as 25 minutes); the third step is to superimpose the EGG graphs of the same type of stimulation events within a preset time period; the fourth step is to perform an average conversion on the superimposed EGG graph to obtain the six psychological brain wave ERP graphs of this type of stimulation event.

[0094] By correlating stimulus events with raw brain wave information for brain wave behavior monitoring, useful brain wave information can be effectively focused, improving the pertinence and accuracy of identifying violations.

[0095] In some embodiments of the present application, the multidimensional violation recognition model includes a multidimensional physiological violation recognition model and a multidimensional psychological violation recognition model. The identification based on the brain wave information processing result under the stimulation event using the multidimensional violation recognition model to obtain the violation recognition result includes: identifying based on the physiological brain wave information processing result under the stimulation event using the multidimensional physiological violation recognition model to obtain the physiological violation recognition result; identifying based on the psychological brain wave information processing result under the stimulation event using the multidimensional psychological violation recognition model to obtain the psychological violation recognition result.

[0096] The embodiment of the present application establishes a multi-dimensional physiological violation identification model and a multi-dimensional psychological violation identification model for physiological brain wave information and psychological brain wave information respectively. The multi-dimensional physiological violation identification model and the multi-dimensional psychological violation identification model can identify illegal behaviors according to the processing results of psychological brain wave information under the stimulus event, identify abnormal brain wave information in the ERP image, and identify various abnormalities such as abnormal frequency, abnormal amplitude, abnormal brain wave peak time, etc., so as to obtain physiological violation identification results and psychological violation identification results respectively.

[0097] In some embodiments of the present application, the multidimensional physiological violation recognition model includes a visual physiological violation recognition model, a physiological tension recognition model, and a writing operation violation recognition model; the multidimensional psychological violation recognition model includes a task processing time violation recognition model, an abnormal psychological behavior violation recognition model, and a judgment type violation recognition model; the multidimensional physiological violation recognition model is used to perform recognition based on the physiological brain wave information processing result under the stimulation event to obtain the physiological violation recognition result, including: according to the physiological brain wave information processing result under the stimulation event, the visual physiological violation recognition model, the physiological tension recognition model, and the writing operation violation recognition model are used to perform recognition respectively to obtain the visual physiological violation recognition result, the physiological tension recognition result, and the writing operation violation recognition result; according to the physiological brain wave information processing result under the stimulation event, the task processing time violation recognition model, the abnormal psychological behavior violation recognition model, and the judgment type violation recognition model are used to perform recognition respectively to obtain the task processing time violation recognition result, the abnormal psychological behavior violation recognition result, and the judgment type violation recognition result.

[0098] A VEPERP abnormality recognition model (visual physiological violation recognition model) is established for physiological violations to monitor the core visual physiological violations, a BetaERP abnormality recognition model (physiological tension recognition model) is established to monitor the physiological tension of operators, and a WAMERP abnormality recognition model (writing operation recognition model) is established to monitor whether there is writing operation in the Wernicke's area. Combining the physiological violation recognition results output by the above three models, the weight W1 of the physiological violation recognition result can be generated as the input of the subsequent violation judgment model.

[0099] A P300ERP abnormality recognition model (task processing time violation recognition model) is established for psychological violation behaviors. P300ERP is a positive wave that appears about 300 milliseconds after the target stimulus is presented. The P300ERP abnormality recognition model is used to determine whether there is an abnormal operation through the task processing time. The more difficult the task, the longer the processing time, and the later the peak value appears. If it exceeds the average task processing time threshold, the weight of the violation recognition result output by the P300ERP abnormality recognition model can be increased. The N270ERP abnormality recognition model (abnormal psychological behavior violation recognition model) is established to monitor operator conflicts and abnormal psychological behaviors such as cheating. The P2AERP abnormality recognition model (judgment violation recognition model) is established to monitor abnormal operation behaviors of the judgment class. Combining the psychological violation recognition results output by the above three models, the weight W2 of the psychological violation recognition result can be generated as the input of the subsequent violation judgment model.

[0100] The construction of the above six models can be flexibly determined by those skilled in the art in combination with existing technologies. For example, the recognition model can be trained by using neural networks and deep learning, and more types of violation recognition models can be expanded, which will not be elaborated here.

[0101] In some embodiments of the present application, the method for identifying violations in reporting of regulatory confidential data also includes: obtaining brain wave information of an operator's historical reporting operations on regulatory confidential data; processing the brain wave information of the operator's historical reporting operations on regulatory confidential data to obtain a processing result of the operator's historical brain wave information; identifying using a multi-dimensional violation identification model based on the brain wave information processing result under a stimulation event to obtain a violation identification result includes: identifying using a multi-dimensional violation identification model based on the brain wave information processing result under the real stimulation event, the brain wave information processing result of the simulated stimulation event, and the operator's historical brain wave information processing result to obtain a violation identification result.

[0102] The embodiment of the present application can also use the operator's historical operation behavior data to further improve the accuracy of model recognition. Specifically, the brain wave information of the operator's historical reporting operation of the supervision of confidential data can be obtained, and then the brain wave information of the operator's historical reporting operation can be processed, and the brain wave processing result of the operator's historical reporting operation can also be used as one of the inputs of each violation recognition model in the above embodiment to determine whether the current behavior is in violation of the law.

[0103] By introducing self-learning of historical data, the operating behavior characteristics of each operator can be analyzed, and then the weight W1 of the physiological violation recognition result and the weight W2 of the psychological violation recognition result can be dynamically adjusted. For example, through historical data analysis, it is found that the concentration time of some operators is significantly shorter than that of ordinary people, so the weight of the psychological violation recognition result of the concentration type can be appropriately reduced.

[0104] In addition, none of the existing technical solutions take into account the fact that the brain's processing efficiency tends to decrease as the monitoring behavior progresses. As time goes on, the brain's processing time itself increases, and this cannot be used as a basis for violating regulations. The existing solutions do not take this into account, and therefore the misjudgment rate is high.

[0105] Based on this, the embodiment of the present application can also adjust the model recognition results of the results within a certain period of time by setting physiological thresholds and psychological thresholds. The initial physiological threshold duration and psychological threshold duration are set to 25 minutes, for example, and are adjusted according to the physiological and psychological conditions of different operators analyzed according to historical operation data. After the adjustment, time-weighted parameters corresponding to the initial physiological threshold duration and psychological threshold duration are generated, thereby filtering out normal physiological and psychological behaviors such as decreased attention and wandering thoughts due to long-term work, reducing the possibility of misjudgment and improving the accuracy of the recognition results.

[0106] In some embodiments of the present application, the violation determination model includes a physiological violation behavior activation function, a psychological violation behavior activation function and a comprehensive activation function, and the determining the final violation identification result using the violation determination model according to the physiological violation identification result and the psychological violation identification result includes: processing the physiological violation identification result using the physiological violation behavior activation function to obtain a physiological violation behavior activation result; processing the psychological violation identification result using the psychological violation behavior activation function to obtain a psychological violation behavior activation result; and processing the physiological violation behavior activation result and the psychological violation behavior activation result using the comprehensive activation function to obtain the final violation identification result.

[0107] The embodiment of the present application sets up three different types of activation functions. The physiological violation activation function is used to activate physiological violation behavior, the psychological violation activation function is used to activate psychological violation behavior, and the final comprehensive activation function is used to activate the operator's violation behavior. Finally, the result of whether the operator has violated the regulations is obtained, thereby improving the accuracy of brain wave violation behavior judgment.

[0108] The specific activation function can be selected according to different violation recognition models, experimental accuracy, and expert experience, so as to most accurately describe the relationship between abnormal physiological and psychological brain waves and violation behaviors. For example, activation functions such as Sigmoid or RELU can be used, and no specific limitation is made here.

[0109] In summary, the improvements and technical effects of the method for identifying violations in reporting confidential data in this application compared with the prior art mainly include:

[0110] 1) Existing solutions do not select lead designs that are suitable for violation scenarios. Many solutions do not introduce the lead designs used. Most of the introduced solutions use single-stage leads-average electrodes or single-stage leads-ear-level leads, which are common in medicine. These two scenarios are suitable for medical case examinations and monitoring of violations caused by sound. This application sets up corresponding lead designs based on specific usage scenarios for regulatory confidential data reporting, focusing on monitoring bio-computer wave signals between the visual area and the advanced psychological function area and other areas, meeting the brain wave detection needs in the regulatory confidential data reporting scenario.

[0111] 2) The existing schemes have unreasonable settings in the process of collecting brain wave information and do not eliminate useless brain wave information. When using brain wave information, they often refer to medical parameter settings and need to collect and process olfactory brain wave information, etc. This application adjusts the sensitivity parameter settings according to the needs of the application scenario, no longer limits the range of low-frequency filtering, abandons symmetrical brain wave information comparison during processing, and abandons processing of other irrelevant brain wave information such as olfaction.

[0112] 3) Most existing solutions use video monitoring + brain waves, which requires more equipment and has problems such as transmission delay and slow analysis. This application takes into account that all information from video monitoring is already reflected in brain waves. For example, every time the eyes open and close, inhibition will appear in the α waveform. The human operation in the video is essentially the reaction of neurons. Therefore, the video monitoring link is omitted, and only brain wave information is used to monitor violations, which improves the efficiency of processing and identification.

[0113] 4) The existing solution simply uses EGG electroencephalogram information, which lacks association with stimulation events. This application associates stimulation events with EGG information and uses ERP to monitor brain wave behavior, which is more prepared and targeted and can effectively focus on useful brain wave information.

[0114] 5) None of the existing solutions take into account that the brain's processing efficiency will decrease as the monitoring behavior progresses. As time goes on, the brain's processing time itself will be extended, and it cannot be used as a basis for illegal behavior. This application reduces such misjudgments by setting the threshold time series adjustment to make the prediction results more accurate.

[0115] 6) The existing solution does not include scenario drills. For brain wave application areas, scenario drills can effectively solve the problem of insufficient initial data and provide a brain wave baseline for subsequent violations. Adding scenario drills can improve the accuracy of system judgments.

[0116] 7) The existing solutions do not distinguish between physiological brain waves and psychological brain waves. In specific usage scenarios, the weight of physiological brain waves and psychological brain waves on the judgment results must be different, and the processing procedures and model establishment of physiological brain waves and psychological brain waves must be different. This application improves the accuracy of illegal behavior judgment by refining brain wave classification and establishing different violation identification models.

[0117] This application comprehensively monitors all behaviors of operators by analyzing brain waves and discovers all possible illegal operations. In addition, this application proposes new ideas and implementation solutions in lead design, invalid brain wave information filtering, EGG information use, and stimulus event association, which can effectively improve the success rate and accuracy of identifying illegal behaviors through brain wave information.

[0118] It should be noted that the acquisition, use and analysis of all user information involved in this application have been explicitly authorized by the user.

[0119] The present application embodiment also provides a device 500 for identifying violations of confidential data reporting. Figure 5 As shown, a schematic diagram of the structure of a device for identifying violations of confidential data reporting in an embodiment of the present application is provided, wherein the device for identifying violations of confidential data reporting includes: a collection unit 510, a brain wave processing unit 520, a violation identification unit 530, and a violation determination unit 540, wherein:

[0120] The collection unit 510 is used to collect brain wave information of the operator under the stimulation event, the stimulation event refers to the reporting event of the supervision of confidential data, the stimulation event includes real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information;

[0121] The brain wave processing unit 520 is used to process the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result;

[0122] A violation identification unit 530 is used to identify the violation using a multi-dimensional violation identification model according to the brain wave information processing result under the stimulation event to obtain a violation identification result, wherein the violation identification result includes a physiological violation identification result and a psychological violation identification result;

[0123] The violation determination unit 540 is used to determine a final violation identification result by using a violation determination model according to the physiological violation identification result and the psychological violation identification result.

[0124] In some embodiments of the present application, the acquisition unit 510 is specifically used to: collect brain wave information of the operator under stimulation events through a brain wave acquisition device in a preset electrode lead mode; wherein the preset electrode lead mode is used to monitor brain wave information of key brain areas, and the key brain areas include visual areas and higher psychological function areas.

[0125] In some embodiments of the present application, the brain wave information is an EGG image, and the brain wave processing unit 520 is specifically used to: split the EGG image of the operator according to the category of brain wave information and the type of stimulation event, and obtain multiple EGG images of brain wave categories corresponding to each type of stimulation event, and the multiple EGG images of brain wave categories include multiple EGG images of physiological categories and multiple EGG images of psychological categories; aggregate the multiple EGG images of brain wave categories corresponding to each type of stimulation event within a preset time period according to the type of stimulation event, and obtain the aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; superimpose the aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period according to the category of brain wave information, and obtain the superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; average convert the superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period, and obtain the ERP images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period.

[0126] In some embodiments of the present application, the multidimensional violation recognition model includes a multidimensional physiological violation recognition model and a multidimensional psychological violation recognition model, and the violation recognition unit 530 is specifically used to: identify according to the physiological brain wave information processing results under the stimulation event, using the multidimensional physiological violation recognition model to obtain the physiological violation recognition result; identify according to the psychological brain wave information processing results under the stimulation event, using the multidimensional psychological violation recognition model to obtain the psychological violation recognition result.

[0127] In some embodiments of the present application, the multidimensional physiological violation recognition model includes a visual physiological violation recognition model, a physiological tension recognition model, and a writing operation violation recognition model; the multidimensional psychological violation recognition model includes a task processing time violation recognition model, an abnormal psychological behavior violation recognition model, and a judgment type violation recognition model; the violation recognition unit 530 is specifically used to: according to the physiological brain wave information processing results under the stimulation event, use the visual physiological violation recognition model, the physiological tension recognition model, and the writing operation violation recognition model to perform recognition, and obtain the visual physiological violation recognition result, the physiological tension recognition result, and the writing operation violation recognition result; according to the physiological brain wave information processing results under the stimulation event, use the task processing time violation recognition model, the abnormal psychological behavior violation recognition model, and the judgment type violation recognition model to perform recognition, and obtain the task processing time violation recognition result, the abnormal psychological behavior violation recognition result, and the judgment type violation recognition result.

[0128] In some embodiments of the present application, the device for identifying violations in reporting confidential regulatory data also includes: an acquisition unit, used to acquire brain wave information of the operator's historical reporting operations on confidential regulatory data; the brain wave processing unit 520 is also used to: process the brain wave information of the operator's historical reporting operations on confidential regulatory data, and obtain the operator's historical brain wave information processing results; the violation identification unit is specifically used to: use a multi-dimensional violation identification model to perform identification based on the brain wave information processing results under the real stimulation event, the brain wave information processing results of the simulated stimulation event, and the operator's historical brain wave information processing results to obtain a violation identification result.

[0129] In some embodiments of the present application, the violation determination model includes a physiological violation behavior activation function, a psychological violation behavior activation function and a comprehensive activation function, and the violation determination unit 540 is specifically used to: use the physiological violation behavior activation function to process the physiological violation identification result to obtain a physiological violation behavior activation result; use the psychological violation behavior activation function to process the psychological violation identification result to obtain a psychological violation behavior activation result; use the comprehensive activation function to process the physiological violation behavior activation result and the psychological violation behavior activation result to obtain the final violation identification result.

[0130] It can be understood that the above-mentioned device for identifying violations in reporting of regulatory confidential data can implement the various steps of the method for identifying violations in reporting of regulatory confidential data provided in the aforementioned embodiments, and the relevant explanations on the method for identifying violations in reporting of regulatory confidential data are applicable to the device for identifying violations in reporting of regulatory confidential data, and will not be repeated here.

[0131] Figure 6Schematic diagram of the structure of a device in the embodiment of the present application. Figure 6 As shown, the device includes one or more processors (or processing units), may further include one or more memories coupled to the processors, and may further include a communication module coupled to the processors.

[0132] The communication module can be used to communicate with other devices or apparatuses, such as the transmission or reception of data and / or signals. The communication module can have at least one communication module for communication. The communication module can include any interface necessary for communicating with other devices. Exemplarily, the communication module can be a transceiver, a circuit, a bus, a module, or other types of communication modules.

[0133] The processor may include, but is not limited to, at least one of the following: a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal controller (DSP), or one or more of a controller-based multi-core controller architecture. The device may have multiple processors, such as application-specific integrated circuit chips, which are time-dependent and synchronized with a clock of a main processor.

[0134] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not persist during the duration of a power outage.

[0135] The computer program includes computer executable instructions executed by an associated processor. The program can be stored in ROM. The processor can perform any suitable actions and processes by loading the program into RAM.

[0136] The possible implementation of the present application can be implemented by means of a program, so that the communication device can perform any process discussed in the above embodiments. The possible implementation of the present application can also be implemented by hardware or by a combination of software and hardware.

[0137] In some embodiments, the program may be tangibly contained in a computer-readable storage medium, which may be included in the device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable storage medium to the RAM for execution. The computer-readable storage medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0138] The present application embodiment also provides a computer-readable storage medium, on which computer instructions or program codes are stored, and when the processor runs the instructions or the program codes, the processor executes the methods and functions involved in any of the above embodiments. Computer-readable media can be any tangible medium containing or storing programs for or related to instruction execution systems, devices or equipment. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any suitable combination thereof. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrations. More detailed examples of computer-readable storage media include electrical connections with one or more wires, magnetic media (e.g., disks, floppy disks, hard disks, tapes, magnetic storage devices), optical media (e.g., optical storage devices, DVDs), semiconductor media (e.g., solid-state hard drives), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), or any suitable combination thereof, etc.

[0139] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The embodiment of the present application also provides at least one computer program product tangibly stored on a non-temporary computer-readable storage medium. The computer program product includes one or more computer executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the process, method and function involved in any of the above embodiments. When the computer program instruction is loaded and executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instruction can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0140] The present application embodiment also proposes a computer program product, including a computer program or instruction, when the computer program or instruction is run on a computer, the computer is made to perform the process, method and function in the above-mentioned embodiment. Usually, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or realize specific abstract data types. In various embodiments, the functions of program modules can be combined or divided between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0141] In general, various embodiments of the present application may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software, which may be performed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that the boxes, devices, systems, techniques, or methods described herein may be implemented as, for example, non-limiting examples, hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0142] It should be noted that although the embodiments of the present application are described above in conjunction with the accompanying drawings, the above embodiments are not independent of each other, and they can also be combined to obtain other embodiments. The division of the modes, situations, categories and embodiments in the embodiments of the present application is only for the convenience of description and should not constitute a special limitation. The features in the various modes, categories, situations and embodiments can be combined with each other in a logical manner. The various implementation methods of the present application can be combined arbitrarily to achieve different technical effects. The embodiments of the present application no longer list various combinations.

[0143] In addition, although the operation of the method of the present disclosure is described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flow chart can change the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0144] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0145] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for identifying violations in reporting of confidential data, characterized in that: The method for identifying violations in reporting of confidential data includes: Collecting brain wave information of operators under stimulation events, wherein the stimulation events refer to reporting events of confidential data, the stimulation events include real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information; Processing the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result; According to the brain wave information processing result under the stimulation event, a multi-dimensional violation recognition model is used to perform recognition to obtain a violation recognition result, wherein the violation recognition result includes a physiological violation recognition result and a psychological violation recognition result; A final violation identification result is determined using a violation determination model according to the physiological violation identification result and the psychological violation identification result.

2. The method for identifying violations in reporting confidential data according to claim 1 is characterized in that: The acquisition of brain wave information of the operator under the stimulation event includes: The brain wave information of the operator under the stimulation event is collected by using a brain wave collection device in a preset electrode lead mode; Among them, the preset electrode lead mode is used to monitor the brain wave information of key brain areas, and the key brain areas include visual areas and high-level psychological function areas.

3. The method for identifying violations in reporting confidential data according to claim 1 is characterized in that: The brain wave information is an EGG image, and the processing of the brain wave information of the operator to obtain the brain wave information processing result includes: Splitting the EGG image of the operator according to the category of brain wave information and the type of stimulation event to obtain a plurality of EGG images of brain wave categories corresponding to each type of stimulation event, wherein the plurality of EGG images of brain wave categories include a plurality of EGG images of physiological categories and a plurality of EGG images of psychological categories; Aggregating EGG images of multiple brain wave categories corresponding to each type of stimulation event within a preset time period according to the type of stimulation event, to obtain aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; The aggregated EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period are superimposed according to the category of brain wave information to obtain the superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period; The superimposed EGG images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period are averaged and converted to obtain ERP images of multiple brain wave categories corresponding to each type of stimulation event within the preset time period.

4. The method for identifying violations in reporting confidential data according to claim 1 is characterized in that: The multi-dimensional violation recognition model includes a multi-dimensional physiological violation recognition model and a multi-dimensional psychological violation recognition model. The violation recognition result obtained by using the multi-dimensional violation recognition model for recognition based on the brain wave information processing result under the stimulation event includes: According to the processing results of physiological brain wave information under the stimulation event, a multi-dimensional physiological violation recognition model is used to perform recognition and obtain the physiological violation recognition result; According to the processing results of psychological brain wave information under the stimulus event, a multi-dimensional psychological violation recognition model is used to obtain the psychological violation recognition result.

5. The method for identifying violations in reporting of confidential data according to claim 4 is characterized in that: The multi-dimensional physiological violation recognition model includes a visual physiological violation recognition model, a physiological tension recognition model, and a writing operation violation recognition model. The multi-dimensional psychological violation recognition model includes a task processing time violation recognition model, an abnormal psychological behavior violation recognition model, and a judgment violation recognition model. The physiological brain wave information processing result under the stimulus event is processed using the multi-dimensional physiological violation recognition model to obtain the physiological violation recognition result, which includes: According to the physiological brain wave information processing result under the stimulation event, the visual physiological violation recognition model, the physiological tension recognition model and the writing operation violation recognition model are used to perform recognition respectively to obtain the visual physiological violation recognition result, the physiological tension recognition result and the writing operation violation recognition result; According to the processing results of physiological brain wave information under the stimulation event, the task processing time violation identification model, the abnormal psychological behavior violation identification model and the judgment type violation identification model are used respectively to perform identification, and the task processing time violation identification results, the abnormal psychological behavior violation identification results and the judgment type violation identification results are obtained.

6. The method for identifying violations in reporting of confidential data according to any one of claims 1 to 5, characterized in that: The method for identifying violations in reporting of confidential data also includes: Obtain brain wave information of operators’ historical reporting operations on confidential data; Processing the brain wave information of the operator's historical reporting operation on the supervision of confidential data to obtain the processing result of the operator's historical brain wave information; The multi-dimensional violation identification model is used to identify the violation according to the brain wave information processing result under the stimulation event, and the violation identification result obtained includes: According to the brain wave information processing results under the real stimulation event, the brain wave information processing results of the simulated stimulation event and the historical brain wave information processing results of the operator, a multi-dimensional violation recognition model is used to perform recognition to obtain a violation recognition result.

7. The method for identifying violations in reporting confidential data according to claim 1, characterized in that: The violation determination model includes a physiological violation behavior activation function, a psychological violation behavior activation function, and a comprehensive activation function. The method of determining the final violation identification result using the violation determination model according to the physiological violation identification result and the psychological violation identification result includes: Processing the physiological violation identification result using the physiological violation behavior activation function to obtain a physiological violation behavior activation result; Processing the psychological violation identification result using the psychological violation behavior activation function to obtain a psychological violation behavior activation result; The physiological violation behavior activation result and the psychological violation behavior activation result are processed by using the comprehensive activation function to obtain the final violation identification result.

8. A device for identifying violations in reporting of confidential data, characterized in that: The reporting violation identification device for supervising confidential data includes: A collection unit, used to collect brain wave information of operators under stimulation events, wherein the stimulation events refer to reporting events of supervision-related confidential data, the stimulation events include real stimulation events and simulated stimulation events, and the brain wave information includes physiological brain wave information and psychological brain wave information; A brain wave processing unit, used for processing the brain wave information of the operator under the stimulation event to obtain the brain wave information processing result under the stimulation event, wherein the brain wave information processing result includes the physiological brain wave information processing result and the psychological brain wave information processing result; A violation identification unit, used to identify the violation using a multi-dimensional violation identification model according to the brain wave information processing result under the stimulation event, and obtain a violation identification result, wherein the violation identification result includes a physiological violation identification result and a psychological violation identification result; The violation determination unit is used to determine a final violation identification result by using a violation determination model according to the physiological violation identification result and the psychological violation identification result.

9. A device comprising: processor; And a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the method for identifying violations in reporting of regulatory confidential data as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method for identifying violations in reporting of regulatory confidential data as described in any one of claims 1 to 7 is implemented.

Images