CN117495063B

CN117495063B - Police resource scheduling method, apparatus, electronic device and computer readable medium

Info

Publication number: CN117495063B
Application number: CN202410004082.0A
Authority: CN
Inventors: 王海超; 陈海峰; 李翔宇; 李漫; 刘志强
Original assignee: Zhongguancun Smart City Co Ltd
Current assignee: Zhongguancun Smart City Co Ltd
Priority date: 2024-01-03
Filing date: 2024-01-03
Publication date: 2024-04-12
Anticipated expiration: 2044-01-03
Also published as: CN117495063A

Abstract

The embodiment of the disclosure discloses a police resource scheduling method, a police resource scheduling device, electronic equipment and a computer readable medium. One embodiment of the method comprises the following steps: determining an initial people flow chart of a target area; performing initial police resource allocation according to the initial people flow chart; performing real-time personnel behavior detection on the real-time video to generate a personnel detection information group; in response to determining that the target person detection information exists in the set of person detection information sets, performing the following processing steps: determining the real-time traffic of the local area corresponding to the local area; determining the police resource adjustment amount through a pre-constructed police resource adjustment amount decision tree, real-time traffic of local areas and personnel behavior types included in target personnel detection information; generating a ring subgraph according to the initial police resource allocation graph; and dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinates included in the target personnel detection information as the center. This embodiment enables efficient scheduling of police resources.

Description

Police resource scheduling method, apparatus, electronic device and computer readable medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method, an apparatus, an electronic device, and a computer readable medium for scheduling police resources.

Background

As cities develop at high densities, corresponding areas of high density traffic are also growing. How to ensure the security level of high-density people flow areas is the important importance of improving the security capability of cities. Currently, in a high-density traffic area, the following methods are generally adopted: and the security problem treatment of the high-density traffic area is realized through saturated police resource scheduling.

However, the inventors found that when the above manner is adopted, there are often the following technical problems:

because the proportion of police resources to the number of people in the high-density people flow area is seriously unbalanced, the saturated police resource scheduling mode has low resource scheduling efficiency.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose alert resource scheduling methods, apparatus, electronic devices, and computer readable media to address one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a police resource scheduling method, the method comprising: determining an initial people flow chart of a target area, wherein the target area is a high-density people flow area to be subjected to police resource scheduling; and carrying out initial police strength resource allocation according to the initial traffic flow diagram to generate an initial police strength resource allocation diagram, wherein the initial police strength resource allocation diagram is an undirected diagram, and the initial police strength resource allocation diagram comprises: at least one graph node, wherein the graph node in the at least one graph node corresponds to the initially allocated police resource group; performing real-time personnel behavior detection on each real-time video in a real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video collected in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the personnel behavior type and the personnel position coordinates; in response to determining that the target person detection information exists in the person detection information group set, performing the following processing steps: determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located; determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the real-time traffic of the local area and the personnel behavior type included in the target personnel detection information; generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; and dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinate included in the target personnel detection information as the center.

In a second aspect, some embodiments of the present disclosure provide an alert resource scheduling apparatus, the apparatus comprising: a determining unit configured to determine an initial traffic pattern of a target area, wherein the target area is a high-density traffic area to be subjected to police resource scheduling; an initial police resource allocation unit configured to perform initial police resource allocation according to the initial traffic pattern to generate an initial police resource allocation pattern, where the initial police resource allocation pattern is an undirected pattern, and the initial police resource allocation pattern includes: at least one graph node, wherein the graph node in the at least one graph node corresponds to the initially allocated police resource group; the real-time personnel behavior detection unit is configured to detect the personnel behavior of each real-time video in the real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video acquired in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the personnel behavior type and the personnel position coordinates; an execution unit configured to execute the following processing steps in response to determining that the target person detection information exists in the person detection information group set: determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located; determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the real-time traffic of the local area and the personnel behavior type included in the target personnel detection information; generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; and dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinate included in the target personnel detection information as the center.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

The above embodiments of the present disclosure have the following advantageous effects: the police resource scheduling method improves the scheduling efficiency of the police resource. Specifically, the reason for the inefficiency of alert resource scheduling is that: because the proportion of police resources to the number of people in the high-density people flow area is seriously unbalanced, the saturated police resource scheduling mode has low resource scheduling efficiency. Based on this, the police resource scheduling method of the present disclosure first determines an initial traffic pattern of a target area, wherein the target area is a high-density traffic area to be subjected to police resource scheduling. In practice, people flow in an area often presents an uneven distribution situation, so that people flow characteristics of a target area can be well characterized by generating an initial people flow chart. Secondly, carrying out initial police strength resource allocation according to the initial traffic flow map to generate an initial police strength resource allocation map, wherein the initial police strength resource allocation map is an undirected map, and the initial police strength resource allocation map comprises: and the at least one graph node corresponds to the initially allocated police resource group. Thus, the initial allocation of police resources is realized by combining the flow of people. Then, performing real-time personnel behavior detection on each real-time video in the real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video collected in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the person behavior type and the person position coordinates. And the rapid behavior analysis is realized by a real-time personnel behavior detection mode. Further, in response to determining that the target person detection information exists in the person detection information group set, the following processing steps are performed: the first step, determining the real-time traffic of local areas corresponding to the local areas, wherein the local areas are areas where the personnel position coordinates included in the target personnel detection information are located. And secondly, determining the police resource adjustment amount through a pre-constructed police resource adjustment amount decision tree, the real-time traffic of people in the local area and the personnel behavior type included in the target personnel detection information. In practice, the conventional police resource scheduling mode is often point-to-point, and the police situation diffusion possibly generated at the police situation occurrence position due to higher people flow is ignored. Therefore, the method and the device can accurately determine the police resource scheduling amount by combining the real-time traffic of the local area and the personnel behavior types included in the target personnel detection information, so that the accurate scheduling of the police resource is realized. And thirdly, generating an annular subgraph according to the initial police resource allocation chart, wherein the annular subgraph is a subgraph taking personnel position coordinates included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount. By generating the annular subgraph, surrounding alarm condition treatment can be realized, and further diffusion of the alarm condition caused by high people flow is avoided. And fourthly, taking the personnel position coordinates included in the target personnel detection information as the center, and scheduling the police resource group corresponding to the graph node in the annular subgraph. By the mode, accurate and efficient scheduling of police resources is achieved according to the characteristics of the high-density traffic area.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of a police resource scheduling method according to the present disclosure;

FIG. 2 is a schematic diagram of the architecture of some embodiments of a police resource scheduling apparatus according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Referring to fig. 1, a flow 100 of some embodiments of a police resource scheduling method according to the present disclosure is shown. The police resource scheduling method comprises the following steps:

Step 101, determining an initial people flow chart of a target area.

In some embodiments, an executing body (e.g., computing device) of the police resource scheduling method may determine an initial people flow map of the target area. The target area is a high-density traffic area to be subjected to police resource scheduling. For example, the target area may be a tourist attraction area. The initial people flow map is used to characterize the people flow for each of the target areas.

As an example, the executing entity may obtain the street traffic of each street included in the target area through a wired connection or a wireless connection, so as to generate the initial traffic figure. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.

In some optional implementations of some embodiments, the determining, by the executing body, the initial people flow chart of the target area may include the following steps:

the first step, an electronic area map corresponding to the target area is obtained.

Wherein, the electronic area map comprises: a collection of electronic street areas. The electronic street region corresponds to a street contained in the target region.

Second, for each electronic street area in the set of electronic street areas, performing the following local people flow determination steps:

and a first sub-step of determining an initial people stream information group corresponding to the electronic street area.

Wherein the initial group of people flow information characterizes the people flow identified at each entrance corresponding to the electronic street area. The initial people flow information characterizes people flow at an entrance to the electronic street area. Specifically, the initial traffic information may include: a set of people feature codes and a people stream value. The personnel characteristic code is used for representing the identity characteristic of the identified personnel. The people stream value characterizes the number of people feature codes in the collection of people feature codes. In practice, the executing body can determine the flow quantity of the personnel identified at each entrance corresponding to the electronic street area through the personnel flow measuring device so as to generate an initial personnel flow information group. The people flow measuring device may be a camera device with personnel identification and counting functions. Specifically, the people flow measuring device at each entrance generates an initial people flow information group corresponding to the electronic street area on the premise of clock synchronization.

And a second sub-step of determining a traffic intersection corresponding to the initial traffic information in the initial traffic information group as a local traffic corresponding to the electronic street area.

As an example, for the electronic street area a, M entrances and exits may be included, so that M pieces of initial traffic information may be generated, in other words, the initial traffic information group a corresponding to the electronic street area a includes M pieces of initial traffic information. Because the entrance often corresponds to entrance and exit of people, the initial people flow information group a needs to take intersections of M initial people flow information, that is, take intersections of people feature code sets in M initial people flow information people included in the initial people flow information group a, and determine the number of the intersection people feature codes as local people flow.

And thirdly, projecting the local traffic volume corresponding to the electronic street areas in the electronic street area set to the electronic area map so as to generate the initial traffic volume map.

The computing device may be hardware or software. When the computing device is hardware, the computing device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices listed above. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein. It should be appreciated that the number of computing devices may have any number as desired for implementation.

And 102, performing initial police resource allocation according to the initial traffic flow diagram to generate an initial police resource allocation diagram.

In some embodiments, the executing entity may perform initial police resource allocation according to the initial traffic figure to generate an initial police resource allocation figure. Wherein, the initial police resource allocation graph is an undirected graph. The initial alert resource allocation map may include: at least one graph node. The graph node of the at least one graph node corresponds to the initially allocated police resource group. In practice, at fine granularity, the police resources in the police resource group may be individual police officers. At coarse granularity, the police resources in the police resource group may include at least two police officers.

As an example, first, the above-described execution subject may generate an empty initial police resource allocation map of a police resource group to be allocated. Specifically, the executing body may perform clustering processing on the initial traffic flow map according to the traffic flow, so as to generate a plurality of clusters. And then taking the cluster centers of the clusters as graph nodes to generate a null initial police resource allocation graph. Then, the executing body can determine the police strength resource group corresponding to the graph node in the empty initial police strength resource allocation graph through an optimization algorithm.

In some optional implementations of some embodiments, the executing entity performs initial police resource allocation according to the initial traffic map to generate an initial police resource allocation map, and may include the following steps:

and firstly, converting the initial people flow chart into an initial people flow thermodynamic chart.

And secondly, taking a local area with the area thermal value larger than the preset area thermal value in the initial people flow thermodynamic diagram as a first area to obtain a first area set.

And thirdly, generating graph nodes corresponding to the first areas in the first area set, and generating undirected graph edges among the graph nodes according to the area distances among the first areas in the first area set to obtain a candidate police resource allocation graph.

In practice, the region distance may be the physical distance of two graph nodes in the target region.

Fourth, for each first region in the first region set, performing the following police resource determining step:

and a first sub-step of determining a second region set corresponding to the first region.

The second area is an area adjacent to the first area, the area thermal value corresponding to the second area is smaller than the area thermal value corresponding to the first area, and the area thermal value corresponding to the second area is larger than the average area thermal value. In practice, high density people flow areas tend to exhibit high central people flow, with at least one area of higher people flow surrounding.

And a second sub-step of determining a police resource group of a graph node corresponding to the first region in the initial police resource allocation graph according to the region range and the region thermodynamic value corresponding to the first region and the region range and the region thermodynamic value corresponding to the second region in the second region set.

In practice, the execution subject may determine, by means of optimal matching, a police resource group of a graph node corresponding to the first region in the initial police resource allocation graph according to a region range and a region thermal value corresponding to the first region and a region range and a region thermal value corresponding to a second region in the second region set. Specifically, first, the executing body may determine the initial alert resource group according to a ratio of the area range corresponding to the first area to the unit area range, and a ratio of the area range corresponding to the second area in the second area set to the unit area range. The unit area range corresponds to a preset police resource demand. Then, the executing body may generate an alert resource increment according to the regional heating power value corresponding to the first region and the regional heating power value alert corresponding to the second region in the second region set, and update the initial alert resource group according to the alert resource increment, so as to generate an alert resource group of the map node corresponding to the first region in the initial alert resource allocation map.

And fifthly, carrying out graph updating on the candidate police resource allocation graph according to the obtained police resource group sequence so as to generate the initial police resource allocation graph.

In practice, the execution body may update the corresponding graph nodes in the candidate alert resource allocation graph in sequence according to the alert resource group sequence in the alert resource group sequence, so as to generate the initial alert resource allocation graph.

In some alternatives of some embodiments, the method further comprises:

and firstly, carrying out graph updating on the initial people flow graph at fixed time intervals to generate an updated people flow graph.

In practice, the executing body may determine, by using the traffic volume measuring device, the traffic volume identified at each entrance corresponding to the electronic street area at fixed time intervals, and update the initial traffic volume map to generate an updated traffic volume map. Specifically, the execution body may use the updated traffic flow map as the initial traffic flow map.

And secondly, according to the updated people flow rate diagram, carrying out diagram adjustment on the initial police resource allocation diagram.

In practice, the executing body may perform graph adjustment on the initial police resource allocation graph according to the updated traffic flow graph in the manner of generating the initial police resource allocation graph in step 102, which is not described herein again.

And step 103, performing real-time personnel behavior detection on each real-time video in the real-time video set to generate a personnel detection information set, and obtaining a personnel detection information set.

In some embodiments, the executing body may perform real-time personnel behavior detection on each real-time video in the real-time video set to generate a personnel detection information set, so as to obtain a personnel detection information set. Wherein the person detection information in the person detection information group set includes: the person behavior type and the person position coordinates. Specifically, the execution subject may perform real-time human behavior detection on the real-time video through the behavior detection model to generate a human detection information set. For example, the human behavior detection model may be a YOLO model.

In some optional implementations of some embodiments, the executing body performs real-time personnel behavior detection on each real-time video in the real-time video set to generate a personnel detection information set, and may include the following steps:

and a first sub-step of generating a local personnel image feature group set through a personnel positioning model included in a pre-trained personnel behavior detection model and the real-time video.

The local personnel image feature group corresponds to local image features of continuous frames of a single personnel in the real-time video. The personnel positioning model comprises: two time-series image feature extraction models are arranged in parallel. Specifically, the personnel positioning model includes: the time sequence type image feature extraction model A, the time sequence type image feature extraction model B and the feature fusion layer. The time sequence type image feature extraction model A is used for extracting image features of images included in the real-time video. The time sequence type image feature extraction model B is used for extracting optical flow features of optical flow images corresponding to images included in the real-time video. The time sequence type image feature extraction model A and the time sequence type image feature extraction model B are convolutional neural networks. In order to solve the problem of long videos, a time sequence type image feature extraction model A and a time sequence type image feature extraction model B in the application are used for carrying out video feature extraction of blocks on real-time videos by taking video blocks as units so as to generate a local personnel image feature group set. The feature fusion layer is used for superposing the image features output by the time sequence type image feature extraction model A and the time sequence type image feature extraction model B aiming at the single image and generating a corresponding frame of interest of the framing personnel. The local person image feature group characterizes local image features in a plurality of images corresponding to a single pedestrian. Specifically, the execution subject may use local image features defined by a plurality of (at least one) frames of interest corresponding to a single person as the local person image feature group.

And a second sub-step of generating a person behavior type which corresponds to the real-time video and is included in the person detection information group through the person behavior recognition model which is included in the person behavior detection model and the local person image feature group.

In practice, the personnel behavior recognition model can be formed by a Seq2Seq model and a multi-classifier.

And a third sub-step of performing position mapping on the relative positions of the image features of the target local personnel to generate personnel position coordinates corresponding to the real-time video and included in the personnel detection information group.

Wherein the target local personnel image feature is a local personnel image feature of a target frame in the local personnel image feature group, and the relative position is a position of the target local personnel image feature in the video image corresponding to the target frame in the real-time video. In practice, the execution body may project the relative position of the image feature of the target local person from the image coordinate system to the geodetic coordinate system according to the internal and external parameters of the camera, so as to generate the person position coordinate.

Step 104, in response to determining that the target person detection information exists in the person detection information group set, performing the following processing steps:

Step 1041, determining a local area real-time traffic flow corresponding to the local area.

In some embodiments, the target person detection information may be person detection information including a person behavior type belonging to a preset person behavior type pool. The preset personnel behavior type pool can be a pre-constructed data pool containing personnel behaviors affecting public security. The local area is an area where the target person detection information includes person position coordinates. In practice, the execution body may call the traffic measurement device corresponding to the local area, and determine the real-time traffic of the local area.

Step 1042, determining the police resource adjustment amount through a pre-constructed policy tree for police resource adjustment amount, real-time traffic of local area and personnel behavior types included in the target personnel detection information.

In some embodiments, the executing body may determine the alert resource adjustment amount through a pre-constructed alert resource adjustment decision tree, a real-time traffic of people in a local area, and a person behavior type included in the target person detection information. Wherein the amount of alert resource scheduling characterizes the amount of alert resources to be scheduled. For example, the alert resource metric may be M police officers. In practice, the police resource measurement decision tree can be realized by adopting a random forest.

Step 1043, generating a ring subgraph according to the initial police resource allocation map.

In some embodiments, the executing entity may generate the ring subgraph according to the initial police resource allocation map. The ring-shaped subgraph is a subgraph centering on a person position coordinate included in the target person detection information. The annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; in practice, the execution subject may determine, in a traversal form, a sub-graph looped with the person position coordinates included in the target person detection information, as a loop sub-graph.

In some optional implementations of some embodiments, the executing entity may generate the ring subgraph according to the initial police resource allocation map, and the method may include the following steps:

and determining a distance value between each of the at least one graph node and a person position coordinate included in the target person detection information.

The executing body may determine a distance value between a current position of the police resource group corresponding to the graph node and a person position coordinate included in the target person detection information.

And a second step of screening out the graph nodes with the corresponding distance values meeting the first screening condition from the at least one graph node as target graph nodes.

The target graph node is the minimum distance value corresponding to the graph node in at least one graph node.

And thirdly, traversing the initial vigilance resource allocation graph by taking the target graph node as a starting node to determine a candidate annular subgraph, thereby obtaining a candidate annular subgraph set.

The candidate annular subgraphs in the candidate annular subgraph set are closed areas which are surrounded by at least three graph nodes and are centered on the personnel position coordinates included in the target personnel detection information.

As an example, step 1: and determining graph nodes connected with the target graph nodes in the initial police resource allocation graph as candidate graph nodes, and obtaining a candidate graph node set. Step 2: and determining a distance value of a candidate graph node in the candidate graph node set and a personnel position coordinate included in the target personnel detection information, and selecting a candidate graph node with the minimum distance value as a current candidate graph node. Step 3: and adding the check ring candidate graph nodes into a target graph node sequence. Step 4: and responding to the current candidate graph node as the target graph node, and taking the ring subgraphs of the target graph node sequence surrounding city as a candidate ring subgraph set. Step 5: and in response to the current candidate graph node not being the target graph node, executing the steps 1 to 3 again.

As yet another example, the executing entity may traverse the initial police resource allocation graph through an ant colony algorithm to determine a candidate ring sub-graph, to obtain a candidate ring sub-graph set.

And step four, screening out the corresponding candidate annular subgraphs with the candidate police resources meeting the second screening condition from the candidate annular subgraphs set according to the police resources adjustment quantity, and taking the candidate annular subgraphs as the annular subgraphs.

In practice, first, the execution body may perform ascending sorting on the candidate annular subgraphs in the candidate annular subgraphs set according to the total police resource amount of the police resource group corresponding to each graph node included in the candidate annular subgraphs, so as to obtain a candidate annular subgraph sequence. Then, the executing body may divide the candidate annular sub-image sequence by using the alert resource metric as a dividing point, so as to obtain a first candidate annular sub-image sequence and a second candidate annular sub-image sequence. Wherein the total amount of alert resources for the last first candidate annular subgraph in the sequence of first candidate annular subgraphs is less than the amount of alert resources adjustment described above. And the total police strength resource amount of the first and second candidate annular subgraphs in the second candidate annular subgraphs is larger than or equal to the police strength resource adjustment amount. The execution body may then determine a first one of the second candidate ring sub-graph sequences as the ring sub-graph.

Step 1044, scheduling the police resource group corresponding to the graph node in the annular subgraph with the personnel position coordinates included in the target personnel detection information as the center.

In some embodiments, the executing body may schedule the police resource group corresponding to the graph node in the ring-shaped subgraph to approach the personnel position coordinate included in the target personnel detection information with the personnel position coordinate included in the target personnel detection information as a center.

In some optional implementations of some embodiments, the executing body may schedule the police resource group corresponding to the graph node in the ring-shaped subgraph with the personnel position coordinate included in the target personnel detection information as a center, and the method may include the following steps:

and step one, dispatching the police resource group corresponding to the target graph node to move to the personnel position coordinates included in the target personnel detection information.

In practice, the executing body may notify, through the communication device, that the police resource group corresponding to the target graph node moves to the personnel position coordinate included in the target personnel detection information.

And secondly, dispatching police resource groups corresponding to graph nodes except the target graph nodes in the annular subgraph, and carrying out annular contraction by taking personnel position coordinates included in the target personnel detection information as the center.

In practice, the executing body may instruct, through a communication device, a police resource group corresponding to a graph node other than the target graph node in the annular subgraph, and perform annular contraction with a person position coordinate included in the target person detection information as a center. In order to avoid the second alarm condition caused by the alarm condition occurring at the personnel position coordinates included in the target personnel detection information in the high-density people flow area.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a police resource scheduling apparatus, corresponding to those method embodiments shown in fig. 1, which may be particularly applicable in various electronic devices.

As shown in fig. 2, the alert resource scheduling apparatus 200 of some embodiments includes: a determining unit 201, an initial police resource allocation unit 202, a real-time personnel behavior detection unit 203 and an executing unit 204. Wherein the determining unit 201 is configured to determine an initial traffic figure of a target area, wherein the target area is a high-density traffic area to be subjected to police resource scheduling; an initial police resource allocation unit 202 configured to perform initial police resource allocation according to the initial traffic pattern, so as to generate an initial police resource allocation pattern, where the initial police resource allocation pattern is an undirected pattern, and the initial police resource allocation pattern includes: at least one graph node, wherein the graph node in the at least one graph node corresponds to the initially allocated police resource group; the real-time person behavior detection unit 203 is configured to perform real-time person behavior detection on each real-time video in the real-time video set to generate a person detection information set, so as to obtain a person detection information set, where the real-time video in the real-time video set is a monitoring video collected in real time by a camera set in the target area, and the person detection information in the person detection information set includes: the personnel behavior type and the personnel position coordinates; an execution unit 204 configured to execute, in response to determining that the target person detection information exists in the person detection information group set, the following processing steps: determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located; determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the real-time traffic of the local area and the personnel behavior type included in the target personnel detection information; generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; and dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinate included in the target personnel detection information as the center.

It will be appreciated that the elements described in the alert resource scheduling apparatus 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and beneficial effects described above with respect to the method are equally applicable to the police resource scheduling apparatus 200 and the units contained therein, and are not described herein.

Referring now to fig. 3, a schematic diagram of an electronic device (e.g., computing device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with programs stored in a read-only memory 302 or programs loaded from a storage 308 into a random access memory 303. In the random access memory 303, various programs and data necessary for the operation of the electronic device 300 are also stored. The processing means 301, the read only memory 302 and the random access memory 303 are connected to each other by a bus 304. An input/output interface 302 is also connected to the bus 304.

In general, the following devices may be connected to the I/O interface 302: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from read only memory 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: determining an initial people flow chart of a target area, wherein the target area is a high-density people flow area to be subjected to police resource scheduling; and carrying out initial police strength resource allocation according to the initial traffic flow diagram to generate an initial police strength resource allocation diagram, wherein the initial police strength resource allocation diagram is an undirected diagram, and the initial police strength resource allocation diagram comprises: at least one graph node, wherein the graph node in the at least one graph node corresponds to the initially allocated police resource group; performing real-time personnel behavior detection on each real-time video in a real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video collected in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the personnel behavior type and the personnel position coordinates; in response to determining that the target person detection information exists in the person detection information group set, performing the following processing steps: determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located; determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the real-time traffic of the local area and the personnel behavior type included in the target personnel detection information; generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; and dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinate included in the target personnel detection information as the center.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes a determination unit, an initial alertness resource allocation unit, a real-time personnel behavior detection unit, and an execution unit. The names of these units do not constitute a limitation of the unit itself in some cases, and the determining unit may also be described as "determining an initial people flow chart of a target area, which is a unit of a high-density people flow area to be subjected to police resource scheduling", for example.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A police resource scheduling method comprising:

determining an initial people flow chart of a target area, wherein the target area is a high-density people flow area to be subjected to police resource scheduling;

performing initial police strength resource allocation according to the initial traffic flow map to generate an initial police strength resource allocation map, wherein the initial police strength resource allocation map is an undirected map, and the initial police strength resource allocation map comprises: at least one graph node, wherein the graph node in the at least one graph node corresponds to an initially allocated police resource group;

performing real-time personnel behavior detection on each real-time video in a real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video collected in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the personnel behavior type and the personnel position coordinates;

in response to determining that the target person detection information exists in the person detection information group set, performing the following processing steps:

determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located;

Determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the local area real-time traffic and the personnel behavior type included in the target personnel detection information;

generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount;

taking the personnel position coordinates included in the target personnel detection information as the center, dispatching the police resource group corresponding to the graph node in the annular subgraph,

the method for detecting the real-time personnel behaviors of each real-time video in the real-time video set to generate a personnel detection information set comprises the following steps:

generating a local personnel image feature group set through a personnel positioning model included in a pre-trained personnel behavior detection model and the real-time video, wherein the local personnel image feature group corresponds to local image features of continuous frames of a single personnel in the real-time video, and the personnel positioning model comprises: the two time sequence type image feature extraction models which are arranged in parallel, and the personnel positioning model comprises: the method comprises the steps that a time sequence type image feature extraction model A, a time sequence type image feature extraction model B and a feature fusion layer are respectively a convolutional neural network, the time sequence type image feature extraction model A and the time sequence type image feature extraction model B are respectively used for carrying out video feature extraction on a real-time video in a blocking mode by taking video blocks as units so as to generate a local personnel image feature group set, the time sequence type image feature extraction model A is used for carrying out image feature extraction on images included in the real-time video, the time sequence type image feature extraction model B is used for carrying out optical flow feature extraction on optical flow images corresponding to the images included in the real-time video, and the feature fusion layer is used for superposing image features output by the time sequence type image feature extraction model A and the time sequence type image feature extraction model B aiming at a single image and generating an interest frame of a corresponding framing person;

For each local person image feature group in the local person image feature group set, performing the following person detection information generation step:

generating a person behavior type which corresponds to the real-time video and is included in the person detection information group through a person behavior recognition model included in the person behavior detection model and the local person image feature group;

performing position mapping on the relative position of the target local personnel image feature to generate personnel position coordinates corresponding to the real-time video and included in personnel detection information in a personnel detection information group, wherein the target local personnel image feature is a local personnel image feature of a target frame in the local personnel image feature group, the relative position is a position of the target local personnel image feature in a video image corresponding to the target frame in the real-time video, and the relative position is a position of the target local personnel image feature in the video image corresponding to the target frame,

generating a ring subgraph according to the initial police resource allocation graph, wherein the ring subgraph comprises the following steps:

determining a distance value between each of the at least one graph node and a person position coordinate included in the target person detection information;

selecting a graph node with a corresponding distance value meeting a first screening condition from the at least one graph node as a target graph node;

Traversing the initial police resource allocation graph by taking the target graph node as a starting node to determine a candidate annular sub graph, so as to obtain a candidate annular sub graph set, wherein the candidate annular sub graph in the candidate annular sub graph set is a closed area surrounded by at least three graph nodes by taking a personnel position coordinate included in the target personnel detection information as a center, and traversing the initial police resource allocation graph by taking the target graph node as the starting node to determine the candidate annular sub graph, and the obtaining the candidate annular sub graph set comprises:

step 1: determining graph nodes connected with target graph nodes in the initial police strength resource allocation graph as candidate graph nodes to obtain a candidate graph node set;

step 2: determining a distance value of a candidate graph node in the candidate graph node set and a personnel position coordinate included in target personnel detection information, and selecting a candidate graph node with the minimum distance value as a current candidate graph node;

step 3: adding the current candidate graph node into a target graph node sequence;

step 4: responding to the current candidate graph node as a target graph node, and taking an annular subgraph surrounded by a target graph node sequence as a candidate annular subgraph set;

Step 5: responding to the current candidate graph node not being the target graph node, and executing the steps 1 to 3 again;

for each candidate annular subgraph in the candidate annular subgraph set, determining a candidate police strength resource amount corresponding to the candidate annular subgraph according to a police strength resource group corresponding to a graph node in the candidate annular subgraph;

screening out a corresponding candidate annular subgraph meeting a second screening condition from the candidate annular subgraph set according to the police resource adjustment amount, wherein,

the step of dispatching the police resource group corresponding to the graph node in the annular subgraph by taking the personnel position coordinates included in the target personnel detection information as the center comprises the following steps:

scheduling the police resource group corresponding to the target graph node to move to the personnel position coordinates included in the target personnel detection information;

and dispatching police resource groups corresponding to graph nodes except the target graph node in the annular subgraph, and carrying out annular contraction by taking the personnel position coordinates included in the target personnel detection information as the center.

2. The method of claim 1, wherein the method further comprises:

Updating the initial people flow chart at fixed time intervals to generate an updated people flow chart;

and according to the updated traffic flow map, performing map adjustment on the initial police resource allocation map.

3. The method of claim 2, wherein the determining an initial traffic pattern for a target area comprises:

acquiring an electronic area map corresponding to the target area, wherein the electronic area map comprises: a set of electronic street areas;

for each electronic street area in the set of electronic street areas, performing the following local people flow determination step:

determining an initial people flow information group corresponding to the electronic street area, wherein the initial people flow information group represents the people flow conditions identified at each entrance and exit corresponding to the electronic street area;

determining a people flow intersection corresponding to the initial people flow information in the initial people flow information group as a local people flow corresponding to the electronic street area;

and projecting the local people flow corresponding to the electronic street areas in the electronic street area set to the electronic area map so as to generate the initial people flow map.

4. The method of claim 3, wherein said performing initial police resource allocation based on said initial traffic pattern to generate an initial police resource allocation pattern comprises:

Converting the initial people flow map into an initial people flow thermodynamic diagram;

taking a local area with an area heating power value larger than a preset area heating power value in the initial people flow thermodynamic diagram as a first area to obtain a first area set;

generating graph nodes corresponding to the first areas in the first area set, and generating undirected graph edges among the graph nodes according to the area distances among the first areas in the first area set to obtain a candidate police resource allocation graph;

for each first region in the first set of regions, performing the police resource determining step of:

determining a second region set corresponding to the first region, wherein the second region is a region adjacent to the first region, the thermal value of the region corresponding to the second region is smaller than that of the region corresponding to the first region, and the thermal value of the region corresponding to the second region is larger than that of the average region;

determining a police resource group of a graph node corresponding to the first region in the initial police resource allocation graph according to a region range and a region thermodynamic value corresponding to the first region and a region range and a region thermodynamic value corresponding to a second region in the second region set;

And according to the obtained police resource group sequence, carrying out graph updating on the candidate police resource allocation graph so as to generate the initial police resource allocation graph.

5. An alert resource scheduling apparatus comprising:

a determining unit configured to determine an initial traffic figure of a target area, wherein the target area is a high-density traffic area to be subjected to police resource scheduling;

the initial police strength resource allocation unit is configured to perform initial police strength resource allocation according to the initial traffic flow graph to generate an initial police strength resource allocation graph, wherein the initial police strength resource allocation graph is an undirected graph, and the initial police strength resource allocation graph comprises: at least one graph node, wherein the graph node in the at least one graph node corresponds to an initially allocated police resource group;

the real-time personnel behavior detection unit is configured to detect the personnel behavior of each real-time video in the real-time video set to generate a personnel detection information set to obtain a personnel detection information set, wherein the real-time video in the real-time video set is a monitoring video acquired in real time by a camera arranged in the target area, and the personnel detection information in the personnel detection information set comprises: the personnel behavior type and the personnel position coordinates;

An execution unit configured to execute the following processing steps in response to determining that the target person detection information exists in the person detection information group set: determining the real-time traffic of a local area corresponding to the local area, wherein the local area is an area where the personnel position coordinates included in the target personnel detection information are located; determining police resource adjustment quantity through a pre-constructed police resource adjustment quantity decision tree, the local area real-time traffic and the personnel behavior type included in the target personnel detection information; generating an annular subgraph according to the initial police resource allocation graph, wherein the annular subgraph is a subgraph taking a personnel position coordinate included in the target personnel detection information as a center, the annular subgraph is a closed area surrounded by a target number of graph nodes, and the target number is determined by the police resource scheduling amount; taking the personnel position coordinates included in the target personnel detection information as the center, dispatching the police resource group corresponding to the graph node in the annular subgraph,

6. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1 to 4.

7. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1 to 4.