CN-122018341-A - Event discovery method based on patrol robot and related equipment

CN122018341ACN 122018341 ACN122018341 ACN 122018341ACN-122018341-A

Abstract

The application is suitable for the technical field of artificial intelligence, and provides an event discovery method based on a patrol robot, which comprises the steps of acquiring a historical discovery event of a target area, wherein the historical event comprises an event type, an event discovery time and an event discovery place; the method comprises the steps of establishing an event discovery matrix corresponding to historical discovery events based on event types, event discovery time and event discovery places, establishing a route optimization model of a multi-target patrol robot by taking the residence time of the patrol robot in each statistical area, the patrol speed of the patrol robot and the accessibility of the patrol robot as constraint conditions and taking the event discovery probability of a preset event as an objective function, outputting an optimized patrol route of at least one patrol robot through the route optimization model of the multi-target patrol robot, and controlling the at least one patrol robot to execute the optimized patrol route to perform event discovery.

Inventors

Chen Yaowo
DAI XIANG
LENG PENGYU

Assignees

深圳云天励飞技术股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. An event discovery method based on a patrol robot, the method comprising the steps of: acquiring a historical discovery event of a target area, wherein the historical event comprises an event type, an event discovery time and an event discovery place; Based on the event type, the event discovery time and the event discovery place, constructing an event discovery matrix corresponding to the historical discovery event, wherein the event discovery matrix comprises a time dimension, a space dimension and an event characteristic value, the space dimension consists of a statistical area divided by longitude and latitude of the target area, and the event characteristic value is determined according to the discovery quantity of the historical discovery event and the event type; Taking the residence time of the patrol robot in each statistical area, the patrol speed of the patrol robot and the accessibility of the patrol robot as constraint conditions, and taking the event discovery probability of a preset event as a target function, so as to construct a route optimization model of the multi-target patrol robot; Outputting at least one optimized patrol route of the patrol robot through a route optimization model of the multi-target patrol robot, and controlling the at least one patrol robot to execute the optimized patrol route to perform event discovery.
2. The patrol robot-based event discovery method according to claim 1, wherein the constructing an event discovery matrix corresponding to the history discovery event based on the event type, the event discovery time, and the event discovery place comprises: dividing a time axis into a plurality of time slices according to a preset time slice length, and constructing a time dimension of the event discovery matrix based on the time slices; dividing the target area into a plurality of statistical areas according to longitude and latitude, and constructing the space dimension of the event discovery matrix based on the plurality of statistical areas; and adding event characteristic values to each statistical region according to the found number and event types of the historical found events which occur in each time slice in each statistical region to obtain the event found matrix.
3. The patrol robot-based event discovery method according to claim 2, wherein the dividing the target area into a plurality of statistical areas according to longitude and latitude, and constructing the spatial dimension of the event discovery matrix based on the plurality of statistical areas comprises: Dividing the target area into a plurality of grid units according to preset grid precision, wherein each grid unit is used as one statistical area, and the grid precision is set according to the perception range of the patrol robot and the event positioning precision; And associating the latitude and longitude range corresponding to the statistical region according to the latitude and longitude information of the target region to obtain the space dimension of the event discovery matrix.
4. The patrol robot-based event discovery method according to claim 2, wherein said adding an event feature value for each of said statistical areas according to a discovery number and an event type of a history discovery event that occurs in each of said time slices for each of said statistical areas comprises: calculating the discovery number corresponding to each event type according to each time slice for each statistical region; The event type and the discovery quantity are subjected to length coding to obtain the event characteristics corresponding to the event type in each time slice, wherein the length of the event characteristics is positively related to the discovery quantity; and adding the event characteristics to the corresponding statistical region.
5. The patrol robot-based event discovery method according to claim 4, wherein the constructing a route optimization model of a multi-objective patrol robot with a maximum event discovery probability and an event discovery efficiency of a predetermined event as an objective function with a residence time of the patrol robot in each statistical region, a patrol speed of the patrol robot, and a reachability of the patrol robot as constraint conditions comprises: taking the residence time of the patrol robot in any statistical area between a preset minimum residence time threshold value and a preset maximum residence time threshold value as residence time constraint; Taking the maximum distance that the patrol robot can travel at a preset maximum patrol speed in a corresponding time interval as patrol speed constraint, wherein the moving distance of the patrol robot between two adjacent statistical areas is not more than the maximum distance; taking the path relation between two adjacent statistical areas as accessibility constraint; Taking the maximized event discovery probability as a first objective function, wherein the event discovery probability is calculated according to event feature values of a statistical region traversed by the patrol robot in a corresponding time slice; Taking maximized event discovery efficiency as a second objective function, wherein the event discovery efficiency is based on event characteristic values of a statistical region traversed by patrol robots in corresponding time slices and a ratio of patrol resource consumption, and the patrol resource consumption comprises at least one of the number of robots participating in patrol, patrol total duration of all patrol robots or patrol path total length of all patrol robots; And constructing a route optimization model of the multi-target patrol robot based on the residence time constraint, the patrol speed constraint, the accessibility constraint, the first objective function and the second objective function.
6. The patrol robot-based event discovery method according to any one of claims 1-5, wherein said outputting at least one optimized patrol route of said patrol robot by a route optimization model of a multi-objective patrol robot comprises: solving the route optimization model by adopting a multi-objective evolutionary algorithm to generate a pareto optimal solution set which is of the preset event and comprises a plurality of non-dominant solutions; acquiring the number of the patrol robots currently available or preset resource budget constraints; and selecting a solution from the pareto optimal solution set as output according to the number of the currently available patrol robots or preset resource budget constraint, wherein the solution comprises at least one optimized patrol route of the patrol robots.
7. The patrol robot-based event discovery method according to any one of claims 1-5, wherein after said controlling said at least one patrol robot to perform an optimized patrol route for event discovery, said method further comprises: in the patrol process, newly discovered event information is obtained in real time, wherein the newly discovered event information comprises a new event type, new event discovery time and a new event discovery place; incremental updating is carried out on the event discovery matrix according to the newly discovered event information, and event characteristic values of the corresponding statistical region in the corresponding time slices are updated; Carrying out local re-planning on the rest of unexecuted patrol routes according to the updated event discovery matrix, and generating dynamically adjusted patrol routes; and issuing the dynamically adjusted patrol route to a corresponding patrol robot for execution.
8. An event discovery apparatus based on a patrol robot, the event discovery apparatus based on a patrol robot comprising: The acquisition module is used for acquiring historical discovery events of the target area, wherein the historical events comprise event types, event discovery time and event discovery places; The first construction module is used for constructing an event discovery matrix corresponding to the historical discovery event based on the event type, the event discovery time and the event discovery place, wherein the event discovery matrix comprises a time dimension, a space dimension and an event characteristic value, the space dimension consists of a statistical region divided by longitude and latitude of the target region, and the event characteristic value is determined according to the discovery number of the historical discovery event and the event type; The second construction module is used for constructing a route optimization model of the multi-target patrol robot by taking the residence time of the patrol robot in each statistical area, the patrol speed of the patrol robot and the accessibility of the patrol robot as constraint conditions and taking the event discovery probability of a preset event as the maximum and the event discovery efficiency as an objective function; The event discovery module is used for outputting at least one optimized patrol route of the patrol robot through a route optimization model of the multi-target patrol robot, and controlling the at least one patrol robot to execute the optimized patrol route to perform event discovery.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the patrol robot-based event discovery method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the patrol robot-based event discovery method according to any one of claims 1 to 7.

Description

Event discovery method based on patrol robot and related equipment Technical Field The application belongs to the technical field of artificial intelligence, and particularly relates to an event discovery method based on a patrol robot and related equipment. Background With the rapid development of robot technology and artificial intelligence, patrol robots are increasingly widely applied in the fields of security protection, park management, traffic inspection and the like. At present, a traditional patrol robot generally adopts a fixed route patrol mode, a random patrol mode or a path planning mode based on simple rules, the fixed route cannot adapt to dynamic distribution of events in time and space, a high-incidence area cannot be fully covered, a low-incidence area occupies excessive resources, and the event discovery probability is low. Therefore, an event discovery method capable of comprehensively considering the space-time distribution of the event and high event discovery efficiency is needed, so as to solve the problems that the existing patrol robot adopts a path planning mode of fixed route patrol, random patrol or based on simple rules, the event occurrence rule is not fully considered, the dynamic distribution of the event in time and space cannot be adapted, and the dynamic matching between patrol and the event occurrence area and the event occurrence period is difficult to realize, so that the event discovery efficiency is low. Disclosure of Invention The embodiment of the application provides an event discovery method based on a patrol robot, which can solve the problems that the existing patrol robot adopts a path planning mode of fixed-route patrol, random patrol or simple rule-based, does not fully consider the event occurrence rule, cannot adapt to the dynamic distribution of events in time and space, and is difficult to realize the dynamic matching between patrol and event occurrence areas and event occurrence periods, so that the event discovery efficiency is low. By constructing an event discovery matrix containing time dimension, space dimension and event characteristic values, taking the residence time of the patrol robot in each statistical region, the patrol speed of the patrol robot and the accessibility of the patrol robot as constraint conditions, taking the event discovery probability of a preset event as an objective function, constructing a route optimization model of the multi-target patrol robot, outputting an optimized patrol route of at least one patrol robot through the route optimization model of the multi-target patrol robot, controlling the at least one patrol robot to execute the optimized patrol route to perform event discovery, effectively improving the event discovery efficiency of the patrol robot, solving the problems that the prior patrol robot adopts a path planning mode of fixed route patrol, random patrol or simple rule-based patrol, does not fully consider the event generation rule, cannot adapt to the dynamic distribution of the event in time and space, and is difficult to realize dynamic matching between the patrol area and the event generation period, and the event discovery efficiency is low. In a first aspect, an embodiment of the present application provides an event discovery method based on a patrol robot, the method including the steps of: acquiring a historical discovery event of a target area, wherein the historical event comprises an event type, an event discovery time and an event discovery place; Based on the event type, the event discovery time and the event discovery place, constructing an event discovery matrix corresponding to the historical discovery event, wherein the event discovery matrix comprises a time dimension, a space dimension and an event characteristic value, the space dimension consists of a statistical area divided by longitude and latitude of the target area, and the event characteristic value is determined according to the discovery quantity of the historical discovery event and the event type; Taking the residence time of the patrol robot in each statistical area, the patrol speed of the patrol robot and the accessibility of the patrol robot as constraint conditions, and taking the event discovery probability of a preset event as a target function, so as to construct a route optimization model of the multi-target patrol robot; Outputting at least one optimized patrol route of the patrol robot through a route optimization model of the multi-target patrol robot, and controlling the at least one patrol robot to execute the optimized patrol route to perform event discovery. Optionally, the constructing an event discovery matrix corresponding to the historical discovery event based on the event type, the event discovery time and the event discovery place includes: dividing a time axis into a plurality of time slices according to a preset time slice length, and constructing a time dimension of the event discovery matrix base