A method, device, apparatus and storage medium for deploying control

Abstract

The application discloses a method, device and equipment for deploying control and a storage medium. In the scheme, an association relationship between different control types and control areas and control monitoring device clusters needs to be set in advance. After the association relationship is set, when a user issues a control task, the user can automatically determine a target control area and a target control monitoring device cluster having the association relationship according to the control type, so that the control area and the control monitoring device are quickly and accurately determined. Compared with a blind selection or experience selection mode, the selection mode can save control resources and improve control efficiency and control effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring, in particular to a control method and device, equipment and storage medium. BACKGROUND

[0002] With the increasing perfection of video monitoring construction, the currently deployable cameras can monitor the control target in the issued control task, and realize the control warning of the control target.

[0003] Currently, when performing control, a control area is selected when issuing a task. Since the control area is generally selected by blind selection or user experience, the selection accuracy is low, thereby affecting the effect of the control. For example, when selecting a control area, it is generally selected in the electric vehicle parking area near high-end supermarkets. If the control target is a thief who steals electric vehicles, the number of people riding electric vehicles is less than that of people driving private cars near high-end supermarkets. If the task of issuing the control of the thief who steals electric vehicles is selected in the area, resources are wasted, and better results cannot be achieved. SUMMARY

[0004] The purpose of the present application is to provide a control method, device, equipment and storage medium, so as to save control resources and improve the control effect.

[0005] To achieve the above purpose, the present application provides a control method, comprising:

[0006] determining the target control type of the control target;

[0007] determining the target control area and the target control monitoring device cluster corresponding to the target control type by using the pre-determined association relationship; the target control monitoring device cluster comprises at least one target control monitoring device belonging to the same type;

[0008] issuing the control task corresponding to the control target to the target control monitoring device cluster corresponding to the target control area, so as to monitor the control target.

[0009] Wherein, after determining the target control type of the control target, it further comprises:

[0010] determining the control time corresponding to the target control type by using the pre-determined association relationship.

[0011] Wherein, before determining the target control type of the control target, it further comprises:

[0012] determining the association relationship between the control type and the control area by using historical case data;

[0013] Determine the association between the control type and the control region by using historical control task data.

[0014] Cluster different types of monitoring devices and determine the association between the control type and the control monitoring device cluster.

[0015] The clustering of different types of monitoring devices includes:

[0016] The monitoring devices are clustered according to the scene labels of the monitoring devices, or the monitoring devices are clustered according to a clustering algorithm and historical control task data.

[0017] The target control task corresponding to the control target is distributed to the target control monitoring device cluster corresponding to the target control region, including:

[0018] Calculate the relevance of each target control region and each target control monitoring device cluster.

[0019] Determine the target control monitoring device cluster of the target control task corresponding to each target control region by using the relevance.

[0020] Distribute the control task of the control target to the target control monitoring device cluster of the target control task corresponding to each target control region.

[0021] The monitoring of the control target includes:

[0022] Obtain the target object monitored by the target control monitoring device cluster to which the control task is distributed.

[0023] Determine whether the similarity between the target object and the control target is greater than a first predetermined threshold value; if yes, determine that the target object is a highly suspected object and perform early warning.

[0024] If no, determine whether the similarity is less than a second predetermined threshold value; the first predetermined threshold value is greater than the second predetermined threshold value.

[0025] If less than the second predetermined threshold value, determine that the target object is a non-control target.

[0026] If not less than the second predetermined threshold value, determine the linkage monitoring device according to the position information of the target object, and determine whether the linkage monitoring device belongs to the target control monitoring device cluster to which the control task is distributed.

[0027] If yes, the step of monitoring the deployment target is continuously performed; if no, the target deployment area and the target deployment monitoring device to which the deployment task is to be issued are updated according to the linkage monitoring device, and the step of monitoring the deployment target is continuously performed.

[0028] The linkage monitoring device is determined according to the position information of the target object, and the linkage monitoring device comprises:

[0029] The linkage monitoring device is determined according to the position information of the target object.

[0030] The reference value of each linkage monitoring device is determined according to the distance parameter value, the travel direction consistency parameter value and the orientation angle consistency parameter value between each linkage monitoring device and the target object.

[0031] The linkage monitoring device is determined according to the reference value of each linkage monitoring device.

[0032] To achieve the above object, the present application further provides a deployment device, comprising:

[0033] The first determination module is used for determining the target deployment type of the deployment target.

[0034] The second determination module is used for determining the target deployment area and the target deployment monitoring device cluster corresponding to the target deployment type by using the pre-determined association relationship.

[0035] The task issuing module is used for issuing the deployment task corresponding to the deployment target to the target deployment monitoring device cluster corresponding to the target deployment area, so as to monitor the deployment target.

[0036] To achieve the above object, the present application further provides an electronic device, comprising:

[0037] The memory is used for storing the computer program.

[0038] The processor is used for executing the computer program to realize the steps of the above deployment method.

[0039] To achieve the above object, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the above deployment method.

[0040] It can be seen from the above scheme that the method for deploying and controlling provided by the embodiment of the application comprises the following steps: determining a target deployment and control type of a deployment and control target; determining a target deployment and control area and a target deployment and control monitoring device cluster corresponding to the target deployment and control type by using a pre-determined association relationship; the target deployment and control monitoring device cluster comprises at least one target deployment and control monitoring device belonging to the same type; and a deployment and control task corresponding to the deployment and control target is issued to the target deployment and control monitoring device cluster corresponding to the target deployment and control area, so as to monitor the deployment and control target. It can be seen that the application needs to pre-set an association relationship between different deployment and control types and deployment and control areas and deployment and control monitoring device clusters. After the association relationship is set, a user can automatically determine the target deployment and control area and the target deployment and control monitoring device cluster having the association relationship according to the deployment and control type when issuing a deployment and control task, so as to realize rapid and accurate determination of the deployment and control area and the deployment and control monitoring device. Compared with a blind selection or an experience selection mode, the selection mode can improve the deployment and control efficiency and the deployment and control effect on the basis of saving deployment and control resources. The application also discloses a deployment and control device and equipment and a storage medium, and the same technical effects can be achieved. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0042] Figure 1 A flowchart of a method for deploying and controlling disclosed by the embodiment of the application is shown in the figure.

[0043] Figure 2 An association relationship diagram disclosed by the embodiment of the application is shown in the figure.

[0044] Figure 3 A flowchart of a method for monitoring a deployment and control target disclosed by the embodiment of the application is shown in the figure.

[0045] Figure 4 A general flowchart of a method for accurately and dynamically deploying and controlling disclosed by the embodiment of the application is shown in the figure.

[0046] Figure 5 A structure diagram of a deployment and control device disclosed by the embodiment of the application is shown in the figure.

[0047] Figure 6 A structure diagram of an electronic device disclosed by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0048] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of the present application.

[0049] The embodiments of the present application disclose a control method, device and equipment and a storage medium, so as to improve the control effect on the basis of saving control resources.

[0050] Referring to Figure 1 , a control method flowchart provided by the embodiments of the present application; by Figure 1 It can be seen that the method comprises:

[0051] S101, determining a target control type of a control target;

[0052] Specifically, the control target in the present application can be a person, a vehicle or the like, and the control type is the type to which the person or the vehicle or the like belongs, for example, if the control target is a person, the control type can be car theft or money theft, and if the control target is a vehicle, the control type can be red light running or non-standard driving. In the present embodiment, in order to clearly illustrate the present solution, the control target is taken as a suspect, and the control type is taken as car theft as an example for illustration.

[0053] S102, determining a target control area and a target control monitoring device cluster corresponding to the target control type by using a predetermined association relationship; the target control monitoring device cluster comprises at least one target control monitoring device belonging to the same type;

[0054] S103, issuing a control task corresponding to the control target to the target control monitoring device cluster corresponding to the target control area, so as to monitor the control target.

[0055] In the present embodiment, in order to quickly and accurately determine the target control area and the target control monitoring device cluster for issuing a control task, it is necessary to pre-set the association relationship between the control type and the control area and the control monitoring device cluster, so that the user can automatically determine the target control area and the target control monitoring device cluster corresponding to the control type according to the pre-set association relationship when issuing a control task. It should be noted that the control monitoring device cluster in the present application comprises at least one target control monitoring device belonging to the same type, so when issuing a control task, the control task needs to be issued to each target control monitoring device in the target control monitoring device cluster.

[0056] Specifically, in determining the association relationship, the association relationship can be determined through analysis of a large amount of historical data, which can be historical case data and historical control task data. For example, through analysis of historical data, it is found that type A occurs with a higher probability in regions D1 and D2, type B occurs with a higher probability in region D3, type A obtains a control target through control monitoring device cluster A with a higher probability, and type B obtains a control target through control monitoring device cluster C with a higher probability. Therefore, if the user issues a control type of type B, the control task can be issued to control monitoring device cluster C corresponding to region D3, and the control target is monitored through the monitoring device in control monitoring device cluster C.

[0057] It should be noted that the control task issued by the present application can also include a control time and a warning condition. The control time can be user-defined or determined by the pre-determined association relationship corresponding to the target control type. For example, through analysis of historical data, it is found that type B obtains a control target through control monitoring device cluster C with a higher probability in the time period of 16:00-21:00. At this time, the control time is determined as 16:00-21:00, that is, the control task is issued to control monitoring device cluster C corresponding to region D3, and the monitoring device in control monitoring device cluster C monitors the control target from 16:00 to 21:00. Moreover, by setting the warning condition in the control task, when the control monitoring device obtains an object similar to the control target, the processing logic can be determined through the warning condition. For example, the warning condition is set as: warning when the similarity is greater than 80%. If the similarity between the target object obtained by the control monitoring device and the control target is greater than 80%, warning is performed, otherwise, no warning is performed.

[0058] As can be seen from the above, by the pre-set association relationship between different control types and control regions, control monitoring device clusters, when the user issues a control task, the target control region and the target control monitoring device cluster having the association relationship can be automatically determined according to the control type, so as to quickly and accurately determine the control region and the control monitoring device. Compared with the blind selection or experience selection method, the selection method can save control resources and improve control efficiency and control effect.

[0059] Based on the above embodiment, in the present embodiment, before determining the target control type of the control target, the relationship between the control type and the control region, the monitoring device cluster needs to be determined through the following three ways, which will be described in detail as follows:

[0060] Method one: determining the association relationship between the control type and the control region by using historical case data;

[0061] In the embodiment, the association between the control type and the control region can be determined according to historical case data. The historical case data can be historical case data. If the control type is a crime type, different crime types and different regions can be associated by way one to form an association mapping relationship between the control type and the control region. The association relationship is an association relationship between different crime types and different regions. Referring to Figure 2 The association relationship provided by the embodiment of the application is shown in the figure. By way one, the association relationship between the control type and the control region can be determined according to the historical case data. Figure 2 As can be seen, if Figure 2 The region A is a region associated with the control type A by way one.

[0062] Specifically, the data source of the historical case data can be case information in a police system. When the historical case data is analyzed by using big data technology, high-frequency crime types and regions can be associated according to the crime type reported by a reporter, the location where the crime occurs, and the time when the crime occurs. The association relationship is the association relationship between the control type and the control region. In this way, before a control task is issued, the system can recommend a corresponding target control region according to the control type. Referring to Table 1, a crime type and region association table provided by the embodiment of the application is shown:

[0063] Table 1

[0064] Type of crime Area of crime Time period Recommended value Type A D1, D2 T1 0.9 Type A D3 T2 0.7 Type B D4 T2, T4 0.8 Type C D5 T4 0.8

[0065] As can be seen from Table 1, after the historical case data is analyzed, the association relationship between different crime types and crime regions and time periods can be determined. The time period is the time period when the historical case data occurs. The recommendation value is the frequency of occurrence of a case of the type in a region. The higher the frequency, the greater the recommendation value. The crime type in Table 1 is the control type, and the crime region is the control region. When a control task is issued, the corresponding target control region can be found by using the association relationship between the control type and the control region. It should be noted that the number of control regions corresponding to the same control type can be multiple. In this case, the user can pre-set a selection rule. For example, the selection rule can be set as follows: all control regions corresponding to the control type are target control regions. The selection rule can be set as follows: a predetermined number of control regions with a larger recommendation value are selected as target control regions. In this case, the selection rule is not specifically limited and can be customized according to the actual needs of the user. Similarly, the association relationship between the control type and the time period in Table 1 can be used as a reference for setting the control time for the user, that is, the user can set the control time of the control task according to the needs, or the time period corresponding to the control type can be used as the control time.

[0066] The second way is to determine the association relationship between the control type and the control area by using historical control task data.

[0067] In the embodiment, in addition to determining the association relationship between the control type and the control area by using the historical case data, the association relationship between the control type and the control area can also be determined according to the results generated by the historical control task. Specifically, the historical control task data is the historical control task and the results generated by the historical control task, for example, in the historical control task data, most of the control results corresponding to the multiple control tasks issued for the type A are the area A, and then the association relationship between the type A and the area A can be set. When determining the association relationship, a heat map can be generated on the map according to the geographical position for display, the heat map shows the control positions corresponding to different control types, the heat map is labeled to obtain the association relationship between the control type and the control area in the heat map, in this way, a point corresponding relationship between the control type and the area is generated, see Figure 2 , Figure 2 The area B of the type A in FIG. 7 is the high-frequency area having the association relationship with the control type A determined by the second way.

[0068] It should be noted that when the association relationship is generated by the second way, the same control type can have the association relationship with multiple control areas, in this case, the selection rule can also be set according to the actual demand of the user, for example, the selection rule can be set as: all the control areas corresponding to the control type are the target control area, or the selection rule can be set as: the predetermined number of control areas with the larger recommended value are selected as the target control area, which is not limited specifically herein.

[0069] The third way is to cluster different types of monitoring devices to determine the association relationship between the control type and the monitoring device cluster.

[0070] It should be noted that at present, when the control task is issued, the common method for selecting the monitoring device is to issue the control task according to the physical position of the monitoring device or to manually select the camera for issuing the control task, which can easily cause the wide issuing area without pertinence, or the manual operation is complex and time-consuming. Therefore, in the embodiment, the association relationship between the control type and the monitoring device can be established after the monitoring device is clustered, so that the user can directly issue the control task to the monitoring device cluster corresponding to the control type when issuing the control task, which can accurately control and reduce the waste of resources. It should be noted that after the monitoring device is clustered, a line corresponding relationship between the control type and the area is generated, see Figure 3 The monitoring device cluster A and the monitoring device cluster B in FIG. 8 are two clusters having the association relationship with the control type A determined by the third way.

[0071] Specifically, in the embodiment, when different types of monitoring devices are clustered, the monitoring devices can be clustered by the following two clustering operations:

[0072] Clustering operation one: the monitoring devices are clustered according to the scene labels of the monitoring devices;

[0073] In the embodiment, when the monitoring devices are clustered, the scene labels of the monitoring devices need to be determined first. In the embodiment, the monitoring devices can be cameras, video cameras, and the like.

[0074] When the scene labels of the monitoring devices are determined, the scenes can be divided on the map according to different areas, so as to form the scene labels. For example, the following labels are divided according to the actual scenes of the areas: office building area, old residential area, high-end residential area, supermarket, pedestrian street, subway entrance, market, school, and the like. When the monitoring devices of the scene labels are added, the cameras at the actual positions can be classified under the above scene labels. For example, the monitoring devices near school A and the monitoring devices near school B can be classified under the same scene label. The monitoring devices belonging to the same scene label are a monitoring device cluster. When the deployment task is issued, the deployment task can be issued to the monitoring device clusters having the association relationship. For example, if the deployment type of the deployment target is theft near a school, the scene label is a school, that is, the monitoring devices having the association relationship with the deployment type are clustered as the monitoring device cluster with the scene label of a school. At this time, the deployment task can be issued to the monitoring device cluster with the scene label of a school, which can accurately deploy and use the least resources.

[0075] Clustering operation two: the monitoring devices are clustered according to the clustering algorithm and historical deployment task data.

[0076] In the embodiment, in addition to the association between the cameras and the scene labels, the automatic clustering of the monitoring devices can also be performed according to the historical deployment task data. The historical deployment task data includes the deployment type and the deployment result of each deployment task. The deployment result includes the position of the monitoring device monitoring the deployment target. Therefore, the monitoring devices can be clustered by the clustering algorithm and the historical deployment task data. Each group of the clustered monitoring devices has an association relationship with the deployment type.

[0077] In the embodiment, the clustering algorithm used is the K-Means clustering algorithm. When the positions of the monitoring devices generated by different deployment types are clustered, the positions of the monitoring devices are data points. The process of clustering the monitoring devices by the K-Means clustering algorithm is as follows:

[0078] (1) Calculate the distance between each data point and all other data points;

[0079] (2), calculate the M-distance value of each data point, and sort the M-distance set of all data points in ascending order, output the sorted M-distance value;

[0080] The M-distance refers to: given a data set K={k(i); i=0, 1,…n}, for any point k(i), calculate the distance between point k(i) and all points in the subset L={p(1), p(2),…, p(i-1), p(i+1),…, p(n)} of set K, the distance is sorted in ascending order, assuming that the sorted distance set is D={d(1), d(2),…, d(j-1), d(j), d(j+1),…, d(n)}, then d(j) is called M-distance;

[0081] (3), display the M-distance trend of all data points with scatter plot, and determine the value of radius R according to the scatter plot;

[0082] (4), according to the given data point number N=4 and the value of radius R, calculate all core points and establish the mapping of core points and points with distance less than radius R to core points;

[0083] (5), according to the obtained core point set and the value of radius R, calculate the core points that can be connected, and obtain the outlier points;

[0084] (6), put each group of core points that can be connected and the points with distance less than radius R to core points together to form a cluster.

[0085] Through the above steps, the clustered monitoring device cluster can be obtained. Since each monitoring device has its monitoring area, each monitoring device cluster will generate a corresponding monitoring device area. After clustering the monitoring devices, a label associated with the control type will be formed, and the generated cluster label can be recommended and issued according to the control type, such as: in the generated monitoring device cluster, each monitoring device has a cluster label of type A, then the monitoring device cluster has an association relationship with type A.

[0086] It can be seen from the above three ways that the control type has a correlation relationship with the control area and the monitoring device, and therefore before issuing the control task, the control area and the control monitoring device cluster corresponding to the control type need to be determined according to the correlation relationship. It should be noted that the high-frequency points of the heat map generated according to the frequency of the control area corresponding to the control type in the historical control task data can be directly used as a supplementary point of the control area. For example, when a car thief is controlled, there may be a place to sell stolen goods, which has no direct connection with the case area, but it frequently produces alarms related to the car theft case, so such a high-frequency point can play a supplementary role in the control area. As can be seen from the above, by using big data analysis technology to analyze historical case data and historical control task data, the point-line-surface correlation relationship between the control type and the control area can be formed, and the control area and the control monitoring device cluster are generated by using the relationship between the point-line-surface, thereby improving the control efficiency.

[0087] Based on the above embodiment, in the present embodiment, when the control task corresponding to the control target is issued to the target control monitoring device cluster corresponding to the target control area, since the number of control areas and control monitoring device clusters determined by the correlation relationship is multiple, the present embodiment can determine the target control monitoring device cluster to which the control task is finally issued in the following way:

[0088] Calculate the correlation degree of each target control area and each target control monitoring device cluster;

[0089] Determine the target control monitoring device cluster to which the control task is to be issued corresponding to each target control area by using the correlation degree;

[0090] Issue the control task of the control target to the target control monitoring device cluster to which the control task is to be issued corresponding to each target control area.

[0091] It should be noted that after the present application determines all target control monitoring device clusters, it can simultaneously or sequentially issue target tasks to all target control monitoring device clusters, or it can select some target control monitoring device clusters to simultaneously or sequentially issue control tasks. In the present embodiment, the correlation degree between the target control area and the target control monitoring device cluster can be used to determine the target control monitoring device cluster to which the control task is to be issued and the order of issuing the control task.

[0092] When calculating the correlation degree between the area and the monitoring device cluster, the following aspects can be calculated and judged:

[0093] I. According to the geographical position between the area and the monitoring device cluster, the closer the area and the monitoring device, the higher the correlation degree, such as Figure 2If the distance between the region A and the monitoring device cluster A is greater than the distance between the region A and the monitoring device cluster B, the relevance between the region A and the monitoring device cluster A is less than the relevance between the region A and the monitoring device cluster B.

[0094] II. According to the rationality of the time of the case and the time of the control result, the more reasonable the time is, the higher the relevance is. For example, through historical control task data analysis, it is known that the monitoring device cluster A obtains the control type A in the first time range, and the monitoring device cluster B obtains the control type A in the second time range. Since the region A appears the control type A in the first time range, it can be explained that the time of the region A and the monitoring device cluster A is more reasonable, and thus it can be determined that the relevance between the region A and the monitoring device cluster A is greater than the relevance between the region A and the monitoring device cluster B.

[0095] III. According to the analysis of the road network structure, for example, through the analysis of the map network structure, it is known that the monitoring device in the monitoring device cluster A is located at an intersection that the suspect must pass through when leaving the region A. Therefore, it can be determined that the relevance between the region A and the monitoring device cluster A is greater than the relevance between the region A and the monitoring device cluster B. It should be noted that in the embodiment, only the above three ways are used to explain the relevance, but it is not limited thereto.

[0096] Referring to Table 2, a control type and a control region recommendation table provided by the embodiment of the present application is shown. As shown in Table 2, for the control type A, there are three corresponding control regions: region A, region B and region C, and five corresponding camera clusters: camera clusters A-E, which are monitoring device clusters. The relevance in the table represents the recommended value, and the higher the relevance is, the higher the recommended value is. In Table 2, only several camera clusters with higher relevance are selected to illustrate the corresponding camera clusters of each region.

[0097] Table 2

[0098]

[0099] Specifically, after determining the relevance between each target deployment area and each target deployment monitoring device cluster, the target deployment monitoring device cluster corresponding to each target deployment area for which the deployment task is to be issued can be determined according to the relevance. The determination rule can be set according to user demand, for example, a relevance threshold is set, if the relevance is greater than the relevance threshold, the target deployment monitoring device cluster corresponding to the target deployment area for which the deployment task is to be issued is set, for example, the relevance threshold is set to 0.8, for area A, only the relevance of camera cluster A is greater than 0.8, therefore camera cluster A is set as the camera cluster corresponding to area A for which the deployment task is to be issued. The determination rule can also be set as: selecting the deployment monitoring device cluster with the greatest relevance, for area A, camera cluster A is set as the camera cluster corresponding to area A for which the deployment task is to be issued, for area B, camera cluster C is set as the camera cluster corresponding to area B for which the deployment task is to be issued, of course, other determination rules can also be set to select the target deployment monitoring device cluster for which the deployment task is to be issued, which is not limited herein. After determining the target deployment monitoring device cluster for which the deployment task is to be issued, the deployment task can be issued.

[0100] It should be noted that if the case frequent area analyzed through historical case data is a target deployment area, but the area can be a monitoring blind area, or the monitoring device of the area is intentionally blocked by a suspect, in this case, the monitoring device in the target deployment area will not capture the suspect, but in this case, the monitoring device in other places around the case can capture the suspect, therefore, in this embodiment, after generating the association between the deployment type generated according to historical deployment task data and the monitoring device cluster, a connection between the monitoring device cluster and the case frequent area is generated, which is the relevance between the monitoring device cluster and the case frequent area, the priority of the deployment recommended area is generated through the relevance, the deployment task is issued according to the priority, the greater the relevance, the higher the priority, for example, in table 2, the camera cluster with the greatest relevance to each area can be selected to issue the deployment task first, if the deployment target is not detected within a predetermined time, the camera cluster with the second greatest relevance can be selected to issue the deployment task, and so on.

[0101] It can be seen that, through the method of issuing the deployment task according to the relevance between the deployment area and the deployment monitoring device cluster, when the deployment area does not have a monitoring device, the deployment monitoring device cluster corresponding to the deployment area for which the deployment task is to be issued can be determined through the relevance, so that the deployment target can be detected through the deployment monitoring device cluster with high relevance around the deployment area, and the deployment effect is improved.

[0102] Referring to Figure 3 A deployment target monitoring flowchart is provided for this embodiment, through Figure 3It can be seen that the process of monitoring the target in the embodiment specifically includes the following steps:

[0103] S201, obtaining a target object monitored by a target monitoring device of a target monitoring device cluster under a control task;

[0104] S202, judging whether the similarity between the target object and the target under control is greater than a first predetermined threshold value;

[0105] If yes, S203 is executed: determining that the target object is a high-suspected object, and performing early warning;

[0106] If no, S204 is executed: judging whether the similarity is less than a second predetermined threshold value; the first predetermined threshold value is greater than the second predetermined threshold value;

[0107] If yes, S205 is executed: determining that the target object is a non-target under control;

[0108] If no, S206 is executed: determining a linkage monitoring device according to the position information of the target object, and judging whether the linkage monitoring device belongs to the target monitoring device cluster under the control task;

[0109] If yes, S201 is continuously executed;

[0110] If no, S207 is continuously executed: updating the target monitoring area and the target monitoring device under the control task according to the linkage monitoring device, and continuing S201.

[0111] It should be noted that after the control task is issued, if one of the monitoring devices obtains the target under control, the target under control needs to be dynamically processed to obtain the maximum information of the target under control. Specifically, after any monitoring device captures a target object, it can be determined according to a pre-set processing logic whether the obtained target object is a target under control. In the embodiment, the processing logic is: calculating the similarity between the target object and the target under control, specifically, calculating the similarity between the face image of the target object obtained by the monitoring device and the face image of the target under control pre-stored in the database, taking the similarity as the similarity between the target object and the target under control. If the similarity reaches a pre-set first predetermined threshold value, early warning processing is performed, otherwise, no processing is performed.

[0112] Specifically, after determining the similarity between the target object and the target under surveillance, the similarity can be compared with three preset ranges, including a range greater than a first predetermined threshold, a range less than or equal to the first preset threshold and greater than or equal to a second preset threshold, and a range less than the second preset threshold. When the similarity belongs to the first range, the target object is a highly suspected target for processing. When the similarity belongs to the second range, the target object is a re-confirmation processing object. When the similarity belongs to the third range, the target object is a non-target processing object.

[0113] For example, if the similarity S is less than 60%, it is set as C, if 60%≤S≤85%, it is set as B, and if S is greater than 85%, it is set as A. If the similarity reaches A, the target object is a highly suspected target for processing, and a warning is given. The face image of the target object is added to a new surveillance task, and the latest face data of the target under surveillance is added to increase the effect of surveillance. If the similarity reaches C, the target object is not the target under surveillance, and no warning is given. If the similarity reaches B, the target object is subjected to re-confirmation processing for further confirmation. It can be understood that in this embodiment, whether a warning is given after the similarity reaches B can be set according to actual needs, which is not specifically limited here.

[0114] Specifically, after the target object is photographed by any surveillance monitoring device, information related to the monitoring device can be found in the database to determine the latitude and longitude of the monitoring device, the angle, and the road network information of the location of the monitoring device in combination with map information. In addition, after the monitoring device photographs the picture of the target object, the orientation information of the target object can also be determined, such as the GPS position of the target object, the orientation information of the target object, the direction of movement of the target object, the speed of movement of the target object, and the like. Therefore, if the similarity between the target object and the target under surveillance reaches B, the position information of the target object can be obtained, and other cameras can be linked to perform target task re-confirmation according to the orientation of the target object and the cameras around the road network. According to the similarity of the re-identification, A, B, and C level processing can be performed.

[0115] It should be noted that when determining the linked monitoring device according to the position information of the target object, the to-be-linked monitoring device can be determined according to the position information of the target object, and the reference value of each to-be-linked monitoring device can be determined according to the distance parameter value between each to-be-linked monitoring device and the target object, the consistency parameter value of the travel direction, and the consistency parameter value of the orientation angle. The linked monitoring device can be determined according to the reference value of each to-be-linked monitoring device.

[0116] In the embodiment, when the to-be-linked monitoring device is determined according to the position information of the target object, the monitoring devices within a predetermined range around the current position of the target object can be obtained as the to-be-linked monitoring devices. In the embodiment, the position of the target object can be determined by obtaining the position of the monitoring device of the target object. For example, after the target camera M obtains the target object, the position of the target camera M is obtained as the current camera, and the camera M1, M2, …, and the like within one kilometer around the target camera M are obtained as the parameter information of the to-be-linked camera set T = {M1, M2, …, M n}, wherein the parameter information of the camera is pre-stored in the background database and can be directly obtained. The parameter information includes the position, orientation, angle, and the like of the camera.

[0117] Further, when the linked monitoring device is determined from the to-be-linked monitoring devices, the position information of the target object can be used to calculate the travel direction and speed of the target object, and the weight score of each factor can be calculated. In the embodiment, the weight score of each factor mainly includes the following parameter values: the distance parameter value P1 between the to-be-linked monitoring device and the target object, the travel direction consistency parameter value P2 between the to-be-linked monitoring device and the target object, and the orientation angle consistency parameter value P3 between the to-be-linked monitoring device and the target object. When the reference value of each to-be-linked monitoring device is determined according to the above parameter values, the parameter values of each factor can be determined according to the user's pre-set manner. In the embodiment, the parameter values of each factor are determined by a weight value function: P n = f(X1, X2), wherein f(X1, X2) is a calculation weight value function. In the embodiment, the specific form of the function is not limited as long as the parameter values of each factor can be calculated. P n is the weight parameter value of the nth factor, X1 is the actual factor value of the camera, and X2 is the expected factor value of the target object that can be captured.

[0118] For example, when the distance parameter value P1 is determined, the actual factor value X1 of the camera is the position of the camera, and the expected factor value X2 of the target object is the position of the target object. The distance parameter value P1 can be obtained by f(X1, X2). When the distance parameter value is determined, the closer the positions X1 and X2, the closer the target object and the to-be-linked monitoring device, and the clearer the image of the target object captured by the to-be-linked monitoring device. Therefore, the distance parameter value P1 can be set to be larger, that is, the closer the positions X1 and X2, the larger the distance parameter value P1.

[0119] After the parameter values of each factor of each to-be-linked monitoring device are determined in the above manner, the reference value of the to-be-linked monitoring device can be determined according to the parameter values, and the determination manner of the reference value is also not limited, which can be obtained by adding the parameter values of each factor, or obtained by multiplying the parameter values of each factor, for example: the reference value P of the to-be-linked monitoring device is P1.P2....P n After the reference values of each to-be-linked monitoring device are calculated, the to-be-linked monitoring devices can be arranged in descending order according to the reference values of each to-be-linked monitoring device, to obtain a to-be-linked camera subset U = {M1, M2,...., M x} and then determine the linked monitoring device according to a pre-set determination rule, which can be: selecting a larger predetermined number of to-be-linked monitoring devices as the linked monitoring device, or selecting a to-be-linked monitoring device with a reference value greater than a predetermined threshold as the linked monitoring device, or selecting all to-be-linked monitoring devices as the linked monitoring device, and the like.

[0120] It should be noted that after the linked monitoring device is determined, if the device is not in the initial determined target surveillance monitoring device cluster, the surveillance area and the surveillance monitoring device need to be updated: the area corresponding to the linked monitoring device is added to the target surveillance area, the linked monitoring device is taken as the target surveillance monitoring device, and the surveillance task is issued. Through this way of surveillance of the monitoring device through which the target object passes, a more accurate surveillance target can be captured, so that the minimum resources are used for the linkage between the monitoring devices, and more accurate linkage is achieved.

[0121] Referring to Figure 4 The overall flowchart of the precise dynamic surveillance disclosed by the embodiment of the application can be seen, after the preset first surveillance target, the surveillance area and the surveillance monitoring device corresponding to the surveillance type can be determined in three ways, and the surveillance task is issued. After the target is captured, the similarity is judged in three grades, if the similarity is high and falls into A grade, it is determined that the surveillance target is captured, at this time the image of the captured target object is added to the new surveillance task, the surveillance target is increased, if the similarity is low and falls into C grade, it is not processed, if the similarity falls into the middle B grade, the target is re-confirmed by linking other monitoring devices.

[0122] It can be seen that the application can improve the accuracy of surveillance by associating the surveillance type and the surveillance area and the monitoring device; in the surveillance, the surveillance target is updated, the camera is linked to update the surveillance area, the dynamic surveillance is realized, and the target recognition rate is improved.

[0123] The surveillance device provided by the embodiment of the application will be described below, and the surveillance device described below can be referred to with the surveillance method described above.

[0124] Referring to Figure 5 The embodiment of the present application provides a structure diagram of a control device, which comprises:

[0125] A first determining module 100 is configured to determine a target control type of a control target;

[0126] A second determining module 200 is configured to determine a target control area and a target control monitoring device cluster corresponding to the target control type by using a predetermined association relationship.

[0127] A task issuing module 300 is configured to issue a control task corresponding to the control target to the target control monitoring device cluster corresponding to the target control area, so as to monitor the control target.

[0128] The device further comprises:

[0129] A third determining module is configured to determine a control time corresponding to the target control type by using the predetermined association relationship.

[0130] The device further comprises an association relationship determining module, which comprises:

[0131] A first determining unit is configured to determine an association relationship between a control type and a control area by using historical case data;

[0132] A second determining unit is configured to determine an association relationship between a control type and a control area by using historical control task data;

[0133] A third determining unit is configured to cluster different types of monitoring devices and determine an association relationship between a control type and a control monitoring device cluster.

[0134] The third determining unit is specifically configured to cluster the monitoring devices according to scene labels of the monitoring devices, or cluster the monitoring devices according to a clustering algorithm and historical control task data, and determine the association relationship between the control type and the control monitoring device cluster.

[0135] The task issuing module comprises:

[0136] A calculating unit is configured to calculate a correlation degree of each target control area and each target control monitoring device cluster;

[0137] A fourth determining unit is configured to determine a target control monitoring device cluster of a to-be-issued control task corresponding to each target control area by using the correlation degree.

[0138] The issuing unit is configured to issue the deployment task of the deployment target to a target deployment monitoring device cluster corresponding to each target deployment region.

[0139] The device further includes a monitoring module, which includes:

[0140] The acquisition unit is configured to acquire a target object monitored by the target deployment monitoring device cluster to which the deployment task is issued.

[0141] The first judgment unit is configured to determine whether the similarity between the target object and the deployment target is greater than a first predetermined threshold value; if yes, a first determination unit is triggered; if no, a second judgment unit is triggered.

[0142] The first determination unit is configured to determine that the target object is a highly suspected object and to issue a warning.

[0143] The second judgment unit is configured to determine whether the similarity is less than a second predetermined threshold value; the first predetermined threshold value is greater than the second predetermined threshold value; if less than the second predetermined threshold value, a second determination unit is triggered; if not less than the second predetermined threshold value, a third judgment unit is triggered.

[0144] The second determination unit is configured to determine that the target object is a non-deployment target.

[0145] The third judgment unit is configured to determine a linkage monitoring device according to the position information of the target object and to determine whether the linkage monitoring device belongs to the target deployment monitoring device cluster to which the deployment task is issued; if yes, the monitoring module is triggered; if no, an updating unit is triggered.

[0146] The updating unit is configured to update the target deployment region and the target deployment monitoring device to which the deployment task is to be issued according to the linkage monitoring device and to trigger the monitoring module.

[0147] The third judgment unit includes:

[0148] The to-be-linked monitoring device determination subunit is configured to determine a to-be-linked monitoring device according to the position information of the target object.

[0149] The reference value determination subunit is configured to determine a reference value of each to-be-linked monitoring device according to a distance parameter value, a travel direction consistency parameter value, and an orientation angle consistency parameter value between each to-be-linked monitoring device and the target object.

[0150] The linkage monitoring device determination subunit is configured to determine a linkage monitoring device according to the reference value of each to-be-linked monitoring device.

[0151] Reference is made to Figure 6The embodiment of the present application also provides an electronic device structural diagram, which comprises:

[0152] a memory 11 for storing a computer program;

[0153] a processor 12 for executing the computer program to realize the steps of the surveillance method in any method embodiment.

[0154] In the embodiment, the device can be a PC (Personal Computer), and can also be a smart phone, a tablet computer, a palm computer, a portable computer or other terminal device.

[0155] The device can comprise the memory 11, the processor 12 and a bus 13.

[0156] The memory 11 comprises at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 can be an internal storage unit of the device in some embodiments, for example, a hard disk of the device. The memory 11 can also be an external storage device of the device in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 can comprise both the internal storage unit and the external storage device of the device. The memory 11 can be used to store application software and various data installed in the device, for example, program codes for executing the surveillance method, etc., and can also be used to temporarily store data that has been output or will be output.

[0157] The processor 12 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip in some embodiments, and is used to run program codes or process data stored in the memory 11, for example, program codes for executing the surveillance method, etc.

[0158] The bus 13 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 6 Only one thick line is used in the figure to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0159] Further, the device can also include a network interface 14, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is generally used to establish a communication connection between the device and other electronic devices.

[0160] Optionally, the device can also include a user interface 15, which can include a display, an input unit such as a keyboard, and optionally the user interface 15 can also include a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display information processed in the device and to display a visualized user interface.

[0161] Figure 6 Only the device with components 11-15 is shown, and those skilled in the art can understand that, Figure 6 The structure shown does not constitute a limitation on the device, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0162] The embodiment of the present application also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the control method in any method embodiment.

[0163] Among them, the storage medium can include: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various storage program codes.

[0164] In the specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts between each embodiment can be referred to each other.

[0165] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling, characterized by, The method comprises the following steps: determining a target control type of a control target; determining a target control area and a target control monitoring device cluster corresponding to the target control type by using a pre-determined association relationship; the target control monitoring device cluster comprises at least one target control monitoring device belonging to the same type; the association relationship is a pre-set association relationship between a control type and a control area, and an association relationship between a control type and a control monitoring device cluster; issuing a control task corresponding to the control target to the target control monitoring device cluster corresponding to the target control area, so as to monitor the control target; wherein, before the step of determining the target control type of the control target, the method further comprises the following steps: determining an association relationship between a control type and a control area by using historical case data, or determining an association relationship between a control type and a control area by using historical control task data; clustering different types of monitoring devices to determine an association relationship between a control type and a control monitoring device cluster; wherein, the step of clustering different types of monitoring devices comprises the following steps: clustering monitoring devices according to scene tags of the monitoring devices; or clustering monitoring devices according to a clustering algorithm and historical control task data.

2. The method of claim 1, wherein, after the step of determining the target control type of the control target, the method further comprises the following step: determining a control time corresponding to the target control type by using the pre-determined association relationship.

3. The method of claim 1, wherein, issuing the control task corresponding to the control target to the target control monitoring device cluster corresponding to the target control area comprises the following steps: calculating a correlation degree between each target control area and each target control monitoring device cluster; determining a target control monitoring device cluster to which a control task corresponding to each target control area is to be issued, by using the correlation degree; issuing the control task of the control target to the target control monitoring device cluster to which the control task corresponding to each target control area is to be issued.

4. The method according to any one of claims 1 to 3, wherein, the step of monitoring the control target comprises the following steps: obtaining a target object monitored by the target control monitoring device cluster to which the control task is issued; judging whether a similarity between the target object and the control target is greater than a first predetermined threshold value; if yes, determining that the target object is a high-suspected object, and performing early warning; if no, judging whether the similarity is less than a second predetermined threshold value; the first predetermined threshold value is greater than the second predetermined threshold value; if less than the second predetermined threshold value, determining that the target object is a non-control target; if not less than the second predetermined threshold value, determining a linkage monitoring device according to position information of the target object, and judging whether the linkage monitoring device belongs to the target control monitoring device cluster to which the control task is issued; if yes, continuing to execute the step of monitoring the control target; if no, updating a target control area and a target control monitoring device to which the control task is to be issued according to the linkage monitoring device, and continuing to execute the step of monitoring the control target.

5. The method of claim 4, wherein, the step of determining the linkage monitoring device according to the position information of the target object comprises the following steps: determining a to-be-linked monitoring device according to the position information of the target object; The reference value of each to-be-linked monitoring device is determined according to a distance parameter value between each to-be-linked monitoring device and the target object, a travel direction consistency parameter value, and an orientation angle consistency parameter value; The linked monitoring device is determined according to the reference value of each to-be-linked monitoring device.

6. A surveillance device, characterized in that, Comprise: The first determination module is used for determining the target deployment type of the deployment target; The second determination module is used for determining the target deployment area and the target deployment monitoring device cluster corresponding to the target deployment type by using the pre-determined association relationship; the association relationship is the pre-set association relationship between the deployment type and the deployment area, and the association relationship between the deployment type and the deployment monitoring device cluster; The task issuing module is used for issuing the deployment task corresponding to the deployment target to the target deployment monitoring device cluster corresponding to the target deployment area, so as to monitor the deployment target; The association relationship determination module comprises: The first determination unit or the second determination unit, the first determination unit is used for determining the association relationship between the deployment type and the deployment area by using the historical case data; the second determination unit is used for determining the association relationship between the deployment type and the deployment area by using the historical deployment task data; The third determination unit is used for clustering different types of monitoring devices, and determining the association relationship between the deployment type and the deployment monitoring device cluster; The third determination unit is specifically used for clustering the monitoring devices according to the scene labels of the monitoring devices; or clustering the monitoring devices according to the clustering algorithm and the historical deployment task data.

7. An electronic device, comprising: Comprise: The memory is used for storing the computer program; The processor is used for executing the computer program to realize the steps of the deployment method in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and the computer program is executed by the processor to realize the steps of the deployment method in any one of claims 1 to 5.

Images