Low-power-consumption dynamic control method and system for intelligent monitoring equipment

Abstract

The invention discloses a low-power-consumption dynamic control method and system for intelligent monitoring equipment, and relates to the field of security and protection, and the method comprises the steps: obtaining monitoring image data during the actual operation of the monitoring equipment; obtaining at least one potential abnormal feature; evaluating to obtain a risk coefficient of the potential abnormal features, and evaluating to obtain an occurrence frequency of the potential abnormal features; calculating an abnormal degree coefficient of the monitoring image data; forming a target value of the abnormal degree coefficient, and forming a characteristic value of the abnormal degree coefficient; when the abnormal degree coefficient is smaller than the characteristic value, a gap control scheme is used for monitoring and controlling the monitoring equipment; and when the abnormal degree coefficient is between the target value and the characteristic value, performing monitoring control on the monitoring equipment by using a progressive control scheme. By arranging the feature extraction module, the data calculation module, the boundary data formation module and the dynamic control module, the operation time of the monitoring equipment can be effectively controlled, and the power consumption of the monitoring equipment can be greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of security, and in particular to a low-power dynamic control method and system for intelligent monitoring equipment. Background Art

[0002] A typical monitoring system is mainly composed of two parts: front-end equipment and back-end equipment. The front-end equipment usually consists of cameras, manual or electric lenses, pan / tilts, protective covers, monitors, alarm detectors, and multi-function decoders. They each perform their own functions and establish corresponding connections with various devices in the central control system through wired, wireless or optical fiber transmission media. In actual TV monitoring systems, these front-end devices may not be used at the same time, but cameras and lenses for monitoring on-site image acquisition are essential. Therefore, its power consumption is mainly determined by image acquisition.

[0003] The existing power consumption reduction is usually controlled by monitoring equipment as the main body, but the power consumption reduction is limited and cannot effectively limit the overall power consumption of monitoring. There is still a large room for power consumption reduction. Summary of the invention

[0004] In order to solve the above technical problems, a low-power dynamic control method and system for intelligent monitoring equipment are provided. The technical solution solves the problem that the existing power consumption reduction proposed in the above background technology is usually controlled by the monitoring equipment as the main body, but the power consumption reduction is limited and cannot effectively limit the overall power consumption of the monitoring, and there is still a large room for reduction in power consumption.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A low-power dynamic control method for intelligent monitoring equipment, comprising: Obtain monitoring image data when the monitoring device is actually running; Acquire a monitoring environment of a monitoring device, extract features of the monitoring environment, and obtain at least one potential abnormal feature; Based on historical data, the risk factor of potential abnormal features is evaluated, and the frequency of occurrence of potential abnormal features is evaluated; Calculate the abnormality degree coefficient of the monitoring image data; Based on the probability calculation, a target value of the abnormality degree coefficient is formed, and based on the historical data, a characteristic value of the abnormality degree coefficient is formed, wherein the target value is greater than the characteristic value; When the abnormality degree coefficient is less than the characteristic value, a gap control scheme is formed for the monitoring equipment, and the gap control scheme is used to monitor and control the monitoring equipment; When the abnormality degree coefficient is between the target value and the characteristic value, a progressive control scheme is formed for the monitoring device, and the progressive control scheme is used to monitor and control the monitoring device; When the abnormality coefficient is greater than the target value, the monitoring device will monitor continuously.

[0006] Preferably, extracting features from the monitoring environment to obtain at least one potential abnormal feature comprises the following steps: Acquire at least one historical monitoring environment based on historical data, and acquire at least one historical abnormal situation that occurred in the historical monitoring environment; Obtain the locations where historical abnormalities occurred in the historical monitoring environment; Evenly divide the monitoring environment into at least one environment identification block; Evenly divide the historical monitoring environment into at least one historical environment identification block; The historical environment identification block that is consistent with the environment identification block is used as the target historical environment identification block; The historical anomalies that occurred in the target historical environment identification block, the target historical anomalies; The signs before the target's historical abnormal situation occurs are regarded as potential abnormal features.

[0007] Preferably, the evaluation of the risk factor of the potential abnormal feature comprises the following steps: Count the average time interval between the occurrence of the target historical abnormal situation corresponding to the potential abnormal feature after the potential abnormal feature appears; After the potential abnormal features appear, the abnormal scale and abnormal losses caused by the abnormal historical abnormal situations corresponding to the potential abnormal features are counted; Using the anomaly formula, calculate the risk factor of potential anomaly features; The exception formula is as follows: , where A is the risk coefficient, a is the average time interval, b is the abnormal scale, and c is the abnormal loss.

[0008] Preferably, the evaluating of the occurrence frequency of potential abnormal features comprises the following steps: After the potential abnormal feature appears, the probability of the target historical abnormal situation corresponding to the potential abnormal feature occurring is counted as the frequency of occurrence of the potential abnormal feature.

[0009] Preferably, the calculation of the abnormality degree coefficient of the monitoring image data comprises the following steps: Performing image recognition on the monitoring image data to obtain at least one potential abnormal feature appearing in the monitoring image data as a target potential abnormal feature; Use the abnormal risk formula to calculate the abnormal degree coefficient of the monitoring image data; The abnormal risk formula is as follows: , where B is the abnormality coefficient, i is the subscript, and n is the total number of potential abnormal features of the target. is the risk factor of the potential abnormal characteristics of the i-th target, is the occurrence frequency of the potential abnormal feature of the i-th target.

[0010] Preferably, the forming of the target value of the abnormality degree coefficient based on probability calculation comprises the following steps: The target potential abnormal features with risk coefficients greater than the preset coefficients are regarded as key potential abnormal features; Calculate the mean probability of occurrence of at least one key potential abnormal feature; Pair the abnormality degree coefficient with the mean occurrence probability, obtain at least one set of abnormality degree coefficient and occurrence probability based on historical data, and fit to obtain a probability fitting function, wherein the mean occurrence probability is the independent variable and the abnormality degree coefficient is the dependent variable; Based on historical data, a critical value of the mean probability of occurrence is obtained as a preset value, which satisfies that an abnormality in the monitoring environment corresponding to the monitoring image data whose mean probability of occurrence is equal to the critical value affects personnel; Substitute the preset value into the probability fitting function to obtain the target value of the abnormality degree coefficient.

[0011] Preferably, forming a characteristic value of anomaly degree coefficient based on historical data comprises the following steps: Multiply the preset value by the preset ratio to obtain the preset partial value; Substitute the preset partial values ​​into the probability fitting function to obtain the characteristic value of the abnormality degree coefficient.

[0012] Preferably, the forming of a gap control scheme for the monitoring equipment comprises the following steps: Obtain the average time interval between target historical abnormal situations corresponding to the target potential abnormal features as the target average time interval; The preset ratio is multiplied by the target average time interval to obtain the monitoring interval time; A gap control scheme is formed, and the gap control scheme is as follows: when the operating time of the monitoring device is equal to the length of the monitoring interval, the monitoring device enters sleep mode, and the sleep mode and monitoring are performed alternately.

[0013] Preferably, the forming of a progressive control scheme for the monitoring device comprises the following steps: Monitor using a gap control solution, obtain an abnormality degree coefficient of at least one monitoring image data, and calculate a change rate of the abnormality degree coefficients of adjacent monitoring image data; When the rate of change is greater than a preset value, the original monitoring interval is replaced by half of the monitoring interval used in the gap control scheme, and the updated gap control scheme is used to repeat the previous step until the rate of change does not exceed the preset value.

[0014] A low-power dynamic control system for intelligent monitoring equipment, used to implement the above-mentioned low-power dynamic control method for intelligent monitoring equipment, comprising: An image acquisition module, wherein the image acquisition module acquires monitoring image data when the monitoring device is actually running; A feature extraction module, wherein the feature extraction module obtains a monitoring environment of a monitoring device, extracts features from the monitoring environment, and obtains at least one potential abnormal feature; A data calculation module, which evaluates the risk coefficient of potential abnormal features based on historical data, evaluates the occurrence frequency of potential abnormal features, and calculates the abnormality degree coefficient of the monitoring image data; A demarcation data forming module, wherein the demarcation data forming module forms a target value of the abnormality degree coefficient based on probability calculation and forms a characteristic value of the abnormality degree coefficient based on historical data, wherein the target value is greater than the characteristic value; A dynamic control module, when the abnormality coefficient is less than the characteristic value, the dynamic control module forms a gap control scheme for the monitoring device, and uses the gap control scheme to monitor and control the monitoring device; when the abnormality coefficient is between the target value and the characteristic value, the dynamic control module forms a progressive control scheme for the monitoring device, and uses the progressive control scheme to monitor and control the monitoring device; when the abnormality coefficient is greater than the target value, the monitoring device monitors continuously.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By setting up a feature extraction module, a data calculation module, a boundary data formation module and a dynamic control module, starting from the environment monitored by the monitoring equipment, different abnormality degree coefficients are calculated according to different environments, so as to determine the control plan according to different abnormality degree coefficients. The control does not depend on the parameters of the monitoring equipment itself, but according to the specific circumstances of the external environment and the monitoring data, the control of the monitoring equipment is used as an auxiliary, so that an intermittent working mode of alternating sleep and monitoring can be adopted. While ensuring that the monitoring is not delayed, the operating time of the monitoring equipment can be effectively controlled, thereby significantly reducing the power consumption of the monitoring equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a low-power dynamic control method for intelligent monitoring equipment according to the present invention; Figure 2A schematic diagram of a process of extracting features from a monitoring environment to obtain at least one potential abnormal feature according to the present invention; Figure 3 A schematic diagram of a process for evaluating and obtaining a risk factor for a potential abnormal characteristic according to the present invention; Figure 4 A schematic diagram of a flow chart of calculating an abnormality degree coefficient of monitoring image data according to the present invention; Figure 5 It is a flow chart of forming a target value of anomaly degree coefficient based on probability calculation of the present invention; Figure 6 It is a schematic diagram of a process of forming a characteristic value of anomaly degree coefficient based on historical data of the present invention; Figure 7 A schematic diagram of a flow chart of a gap control scheme for monitoring equipment according to the present invention; Figure 8 The figure is a flow chart of the progressive control scheme for monitoring equipment according to the present invention. DETAILED DESCRIPTION

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0018] Reference Figure 1 As shown, a low-power dynamic control method for intelligent monitoring equipment includes: Obtain monitoring image data when the monitoring device is actually running; Acquire a monitoring environment of a monitoring device, extract features of the monitoring environment, and obtain at least one potential abnormal feature; Based on historical data, the risk factor of potential abnormal features is evaluated, and the frequency of occurrence of potential abnormal features is evaluated; Calculate the abnormality degree coefficient of the monitoring image data; Based on the probability calculation, a target value of the abnormality degree coefficient is formed, and based on the historical data, a characteristic value of the abnormality degree coefficient is formed, wherein the target value is greater than the characteristic value; When the abnormality degree coefficient is less than the characteristic value, a gap control scheme is formed for the monitoring equipment, and the gap control scheme is used to monitor and control the monitoring equipment; When the abnormality degree coefficient is between the target value and the characteristic value, a progressive control scheme is formed for the monitoring device, and the progressive control scheme is used to monitor and control the monitoring device; When the abnormality coefficient is greater than the target value, the monitoring device will monitor continuously.

[0019] In this scheme, the signs of abnormalities that may occur in different historical monitoring environments are extracted, so that the abnormality degree coefficient of the monitoring image data can be calculated based on this. The abnormality degree coefficient is used to evaluate the abnormalities in the monitoring environment. According to the characteristics of the existing abnormalities, the risk of abnormalities occurring is estimated before the abnormalities occur, and then different degrees of monitoring are performed according to different risk situations. To this end, target values ​​and characteristic values ​​are formed to judge the abnormality degree coefficient, and accordingly, different schemes are used for monitoring. These schemes limit the use time of the monitoring equipment to achieve the effect of reducing power consumption, because the power consumption of the monitoring equipment mainly depends on the acquisition of video and images. Therefore, when the power consumption of this part is reduced, the power consumption of the monitoring equipment can be greatly reduced. At the same time, since the monitoring interval time in the scheme is set according to the different abnormality degree coefficients and the changes in the actual monitoring situation, these schemes can meet the actual monitoring needs and will not cause abnormal warning delays.

[0020] Reference Figure 2 As shown, extracting features from the monitoring environment to obtain at least one potential abnormal feature includes the following steps: Acquire at least one historical monitoring environment based on historical data, and acquire at least one historical abnormal situation that occurred in the historical monitoring environment; Obtain the locations where historical abnormalities occurred in the historical monitoring environment; Evenly divide the monitoring environment into at least one environment identification block; Evenly divide the historical monitoring environment into at least one historical environment identification block; The historical environment identification block that is consistent with the environment identification block is used as the target historical environment identification block; The historical anomalies that occurred in the target historical environment identification block, the target historical anomalies; The signs before the target's historical abnormal situation occurs are regarded as potential abnormal features.

[0021] There is a large amount of available data in the historical monitoring environment, but the monitoring environment and the historical monitoring environment may not be completely equivalent. Therefore, they are divided into small blocks and compared, respectively, into environmental identification blocks and historical environmental identification blocks. The historical environmental identification blocks that are consistent with the environmental identification blocks here are not completely consistent, but the difference between the two is sufficiently small. Therefore, the target historical environmental identification block can be obtained, and the target historical abnormalities occurring in the target historical environmental identification block can be obtained. However, in this scheme, the monitoring is adjusted, and the basis for the adjustment is based on the degree of abnormality of the subsequent situation. Therefore, it does not judge the target historical abnormalities, but judges the precursors of the occurrence of target historical abnormalities. Therefore, it is necessary to take the signs before the occurrence of the target historical abnormalities as potential abnormal features.

[0022] Reference Figure 3 As shown, evaluating the risk factor of potential abnormal characteristics includes the following steps: Count the average time interval between the occurrence of the target historical abnormal situation corresponding to the potential abnormal feature after the potential abnormal feature appears; After the potential abnormal features appear, the abnormal scale and abnormal losses caused by the abnormal historical abnormal situations corresponding to the potential abnormal features are counted; Using the anomaly formula, calculate the risk factor of potential anomaly features; The exception formula is as follows: , where A is the risk coefficient, a is the average time interval, b is the abnormal scale, and c is the abnormal loss.

[0023] The risk is mainly related to the abnormal scale and abnormal loss. For the average time interval, the larger the average time interval is, the smaller the abnormality is. Because when the situation is very abnormal, it will inevitably happen very quickly after the signs appear. Therefore, it is easy to know that the risk coefficient is inversely proportional to the average time interval. Therefore, the abnormal formula is set as above.

[0024] Evaluating the frequency of occurrence of potentially abnormal features involves the following steps: After the potential abnormal feature appears, the probability of the target historical abnormal situation corresponding to the potential abnormal feature occurring is counted as the frequency of occurrence of the potential abnormal feature.

[0025] The frequency of occurrence is a statistical analysis of the probability of the occurrence of historical abnormalities of the target. The appearance of potential abnormal features does not necessarily lead to the occurrence of historical abnormalities of the target. There is a certain connection between the two, but it is not inevitable. Therefore, the frequency of occurrence is needed to describe the probability of the potential abnormal features leading to the corresponding historical abnormalities of the target.

[0026] Reference Figure 4 As shown, calculating the abnormality degree coefficient of monitoring image data includes the following steps: Performing image recognition on the monitoring image data to obtain at least one potential abnormal feature appearing in the monitoring image data as a target potential abnormal feature; Use the abnormal risk formula to calculate the abnormal degree coefficient of the monitoring image data; The abnormal risk formula is as follows: , where B is the abnormality coefficient, i is the subscript, and n is the total number of potential abnormal features of the target. is the risk factor of the potential abnormal characteristics of the i-th target, is the occurrence frequency of the potential abnormal feature of the i-th target.

[0027] The risk coefficient of an abnormal feature can characterize the degree of abnormality of the abnormal feature. It characterizes the severity of the abnormal situation when it is bound to occur. However, the abnormal situation caused by the abnormal feature is not bound to occur. Therefore, it needs to be weighted, and the weight is naturally the frequency of occurrence of the target potential abnormal feature.

[0028] Reference Figure 5 As shown, based on probability calculation, forming the target value of the abnormality degree coefficient includes the following steps: The target potential abnormal features with risk coefficients greater than the preset coefficients are regarded as key potential abnormal features; Calculate the mean probability of occurrence of at least one key potential abnormal feature; Pair the abnormality degree coefficient with the mean occurrence probability, obtain at least one set of abnormality degree coefficient and occurrence probability based on historical data, and fit to obtain a probability fitting function, wherein the mean occurrence probability is the independent variable and the abnormality degree coefficient is the dependent variable; Based on historical data, a critical value of the mean probability of occurrence is obtained as a preset value, which satisfies that an abnormality in the monitoring environment corresponding to the monitoring image data whose mean probability of occurrence is equal to the critical value affects personnel; Substitute the preset value into the probability fitting function to obtain the target value of the abnormality degree coefficient.

[0029] When different plans are formed according to the abnormality degree coefficient, it is necessary to determine the corresponding dividing value. First, at least one abnormality degree coefficient is paired with the mean probability of occurrence based on historical data, and thus a probability fitting function is obtained, which can estimate the value of the abnormality degree coefficient when the mean probability of occurrence is a preset value, and then obtain the target value of the abnormality degree coefficient.

[0030] Reference Figure 6 As shown, based on historical data, forming the characteristic value of the abnormal degree coefficient includes the following steps: Multiply the preset value by the preset ratio to obtain the preset partial value; Substitute the preset partial values ​​into the probability fitting function to obtain the characteristic value of the abnormality degree coefficient.

[0031] The characteristic value is used to judge whether the situation is not very serious relative to the target value, and therefore, it forms a preset partial value based on multiplying the preset value by the preset ratio.

[0032] Reference Figure 7 As shown, forming a gap control scheme for monitoring equipment includes the following steps: Obtain the average time interval between target historical abnormal situations corresponding to the target potential abnormal features as the target average time interval; The preset ratio is multiplied by the target average time interval to obtain the monitoring interval time; A gap control scheme is formed, and the gap control scheme is as follows: when the operating time of the monitoring device is equal to the length of the monitoring interval, the monitoring device enters sleep mode, and the sleep mode and monitoring are performed alternately.

[0033] When the abnormalities that occur in the monitored situation in the future are not very serious, the monitoring interval is used as the interval for alternating between sleep and monitoring. Because the abnormalities will not be very serious, alternating monitoring at this frequency is sufficient to respond in time and take corresponding measures when abnormalities occur.

[0034] Reference Figure 8 As shown, forming a progressive control scheme for the monitoring device includes the following steps: Monitor using a gap control solution, obtain an abnormality degree coefficient of at least one monitoring image data, and calculate a change rate of the abnormality degree coefficients of adjacent monitoring image data; When the rate of change is greater than a preset value, the original monitoring interval is replaced by half of the monitoring interval used in the gap control scheme, and the updated gap control scheme is used to repeat the previous step until the rate of change does not exceed the preset value.

[0035] When monitoring is performed using the gap control scheme, monitoring is performed again after each sleep, thereby obtaining at least one monitoring image data and calculating its corresponding abnormality degree coefficient; The calculation of the change rate is the ratio of the absolute value of the difference between the abnormality degree coefficients of adjacent monitoring image data to the sum of the abnormality degree coefficients of adjacent monitoring image data; For situations where abnormal features change quickly, more thorough monitoring is required. Therefore, the monitoring time is extended and the monitoring interval is shortened. As long as the image changes after each interval are within the allowable range, it means that the current monitoring solution is sufficiently matched. Otherwise, it means that the monitoring sleep time is too long and needs to be shortened.

[0036] A low-power dynamic control system for intelligent monitoring equipment, used to implement the above-mentioned low-power dynamic control method for intelligent monitoring equipment, comprising: An image acquisition module, wherein the image acquisition module acquires monitoring image data when the monitoring device is actually running; A feature extraction module, wherein the feature extraction module obtains a monitoring environment of a monitoring device, extracts features from the monitoring environment, and obtains at least one potential abnormal feature; A data calculation module, which evaluates the risk coefficient of potential abnormal features based on historical data, evaluates the occurrence frequency of potential abnormal features, and calculates the abnormality degree coefficient of the monitoring image data; A demarcation data forming module, wherein the demarcation data forming module forms a target value of the abnormality degree coefficient based on probability calculation and forms a characteristic value of the abnormality degree coefficient based on historical data, wherein the target value is greater than the characteristic value; A dynamic control module, when the abnormality coefficient is less than the characteristic value, the dynamic control module forms a gap control scheme for the monitoring device, and uses the gap control scheme to monitor and control the monitoring device; when the abnormality coefficient is between the target value and the characteristic value, the dynamic control module forms a progressive control scheme for the monitoring device, and uses the progressive control scheme to monitor and control the monitoring device; when the abnormality coefficient is greater than the target value, the monitoring device monitors continuously.

[0037] Furthermore, the present solution also proposes a low-power dynamic control method for intelligent monitoring equipment and a system storage medium, on which a computer-readable program is stored. When the computer-readable program is called, the above-mentioned low-power dynamic control method for intelligent monitoring equipment is executed.

[0038] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0039] In summary, the advantages of the present invention are: by setting a feature extraction module, a data calculation module, a boundary data formation module and a dynamic control module, starting from the environment monitored by the monitoring equipment, different abnormality degree coefficients are calculated according to different environments, so as to determine the control plan according to different abnormality degree coefficients, and its control does not depend on the parameters of the monitoring equipment itself, but according to the specific circumstances of the external environment and the monitoring data, the control of the monitoring equipment is used as an auxiliary, so that an intermittent working mode of alternating sleep and monitoring can be adopted, while ensuring that the monitoring is not delayed, the operation time of the monitoring equipment can be effectively controlled, thereby significantly reducing the power consumption of the monitoring equipment.

[0040] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A low-power dynamic control method for intelligent monitoring equipment, characterized in that: include: Obtain monitoring image data when the monitoring device is actually running; Acquire a monitoring environment of a monitoring device, extract features of the monitoring environment, and obtain at least one potential abnormal feature; Based on historical data, the risk factor of potential abnormal features is evaluated, and the frequency of occurrence of potential abnormal features is evaluated; Calculate the abnormality degree coefficient of the monitoring image data; Based on the probability calculation, a target value of the abnormality degree coefficient is formed, and based on the historical data, a characteristic value of the abnormality degree coefficient is formed, wherein the target value is greater than the characteristic value; When the abnormality degree coefficient is less than the characteristic value, a gap control scheme is formed for the monitoring equipment, and the gap control scheme is used to monitor and control the monitoring equipment; When the abnormality degree coefficient is between the target value and the characteristic value, a progressive control scheme is formed for the monitoring device, and the progressive control scheme is used to monitor and control the monitoring device; When the abnormality coefficient is greater than the target value, the monitoring device will monitor continuously.

2. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 1, characterized in that: Extracting features from the monitoring environment to obtain at least one potential abnormal feature comprises the following steps: Acquire at least one historical monitoring environment based on historical data, and acquire at least one historical abnormal situation that occurred in the historical monitoring environment; Obtain the locations where historical abnormalities occurred in the historical monitoring environment; Evenly divide the monitoring environment into at least one environment identification block; Evenly divide the historical monitoring environment into at least one historical environment identification block; The historical environment identification block that is consistent with the environment identification block is used as the target historical environment identification block; The historical anomalies that occurred in the target historical environment identification block, the target historical anomalies; The signs before the target's historical abnormal situation occurs are regarded as potential abnormal features.

3. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 2, characterized in that: The evaluation of the risk factor of the potential abnormal feature comprises the following steps: Count the average time interval between the occurrence of the target historical abnormal situation corresponding to the potential abnormal feature after the potential abnormal feature appears; After the potential abnormal features appear, the abnormal scale and abnormal losses caused by the abnormal historical abnormal situations corresponding to the potential abnormal features are counted; Using the anomaly formula, calculate the risk factor of potential anomaly features; The exception formula is as follows: , where A is the risk coefficient, a is the average time interval, b is the abnormal scale, and c is the abnormal loss.

4. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 3, characterized in that: The evaluation of the occurrence frequency of potential abnormal features comprises the following steps: After the potential abnormal feature appears, the probability of the target historical abnormal situation corresponding to the potential abnormal feature occurring is counted as the frequency of occurrence of the potential abnormal feature.

5. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 4, characterized in that: The calculation of the abnormality degree coefficient of the monitoring image data comprises the following steps: Performing image recognition on the monitoring image data to obtain at least one potential abnormal feature appearing in the monitoring image data as a target potential abnormal feature; Use the abnormal risk formula to calculate the abnormal degree coefficient of the monitoring image data; The abnormal risk formula is as follows: , where B is the abnormality coefficient, i is the subscript, and n is the total number of potential abnormal features of the target. is the risk factor of the potential abnormal characteristics of the i-th target, is the occurrence frequency of the potential abnormal feature of the i-th target.

6. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 5, characterized in that: The method of forming a target value of the abnormality degree coefficient based on probability calculation comprises the following steps: The target potential abnormal features with risk coefficients greater than the preset coefficients are regarded as key potential abnormal features; Calculate the mean probability of occurrence of at least one key potential abnormal feature; Pair the abnormality degree coefficient with the mean occurrence probability, obtain at least one set of abnormality degree coefficient and occurrence probability based on historical data, and fit to obtain a probability fitting function, wherein the mean occurrence probability is the independent variable and the abnormality degree coefficient is the dependent variable; Based on historical data, a critical value of the mean probability of occurrence is obtained as a preset value, which satisfies that an abnormality in the monitoring environment corresponding to the monitoring image data whose mean probability of occurrence is equal to the critical value affects personnel; Substitute the preset value into the probability fitting function to obtain the target value of the abnormality degree coefficient.

7. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 6, characterized in that: The method of forming the characteristic value of the abnormality degree coefficient based on historical data comprises the following steps: Multiply the preset value by the preset ratio to obtain the preset partial value; Substitute the preset partial values ​​into the probability fitting function to obtain the characteristic value of the abnormality degree coefficient.

8. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 7, characterized in that: The gap control scheme for the monitoring device comprises the following steps: Obtain the average time interval between target historical abnormal situations corresponding to the target potential abnormal features as the target average time interval; The preset ratio is multiplied by the target average time interval to obtain the monitoring interval time; A gap control scheme is formed, and the gap control scheme is as follows: when the operating time of the monitoring device is equal to the length of the monitoring interval, the monitoring device enters sleep mode, and the sleep mode and monitoring are performed alternately.

9. A low power consumption dynamic control method for intelligent monitoring equipment according to claim 8, characterized in that: The step of forming a progressive control scheme for the monitoring device comprises the following steps: Monitor using a gap control solution, obtain an abnormality degree coefficient of at least one monitoring image data, and calculate a change rate of the abnormality degree coefficients of adjacent monitoring image data; When the rate of change is greater than a preset value, the original monitoring interval is replaced by half of the monitoring interval used in the gap control scheme, and the updated gap control scheme is used to repeat the previous step until the rate of change does not exceed the preset value.

10. A low-power dynamic control system for an intelligent monitoring device, used to implement the low-power dynamic control method for an intelligent monitoring device according to any one of claims 1 to 9, characterized in that: include: An image acquisition module, wherein the image acquisition module acquires monitoring image data when the monitoring device is actually running; A feature extraction module, wherein the feature extraction module obtains a monitoring environment of a monitoring device, extracts features from the monitoring environment, and obtains at least one potential abnormal feature; A data calculation module, which evaluates the risk coefficient of potential abnormal features based on historical data, evaluates the occurrence frequency of potential abnormal features, and calculates the abnormality degree coefficient of the monitoring image data; A demarcation data forming module, wherein the demarcation data forming module forms a target value of the abnormality degree coefficient based on probability calculation and forms a characteristic value of the abnormality degree coefficient based on historical data, wherein the target value is greater than the characteristic value; A dynamic control module, when the abnormality coefficient is less than the characteristic value, the dynamic control module forms a gap control scheme for the monitoring device, and uses the gap control scheme to monitor and control the monitoring device; when the abnormality coefficient is between the target value and the characteristic value, the dynamic control module forms a progressive control scheme for the monitoring device, and uses the progressive control scheme to monitor and control the monitoring device; when the abnormality coefficient is greater than the target value, the monitoring device monitors continuously.

Images