CN116823892B

CN116823892B - Identity determination method, device, equipment and medium based on building management and control

Info

Publication number: CN116823892B
Application number: CN202311107785.8A
Authority: CN
Inventors: 曹杰; 陈镇池; 曹嘉鑫
Original assignee: Gore Elevator Tianjin Co ltd
Current assignee: Gore Elevator Tianjin Co ltd
Priority date: 2023-08-31
Filing date: 2023-08-31
Publication date: 2023-11-17
Anticipated expiration: 2043-08-31
Also published as: CN116823892A

Abstract

The application relates to the field of identity recognition, in particular to an identity determining method, device, equipment and medium based on building management and control, wherein the method comprises the following steps: acquiring human body images of agents corresponding to the non-civilized behaviors; determining key human body characteristics of the human body image; tracking the track of the agent by utilizing the real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system; when the tracking result is that the agent enters the room, acquiring a first house number of the room in which the agent enters; obtaining identity information of the agent by using the first house number; when the tracking result is that the agent leaves the building, the history monitoring image and key human body characteristics are utilized to trace back the history track of the agent, so that a second door mark of a room where the agent historically enters is obtained; and obtaining the identity information of the agent according to the second door number. The application can improve the accuracy of the identity information of the agent.

Description

Identity determination method, device, equipment and medium based on building management and control

Technical Field

The application relates to the technical field of identity recognition, in particular to an identity determination method, device, equipment and medium based on building management and control.

Background

In a place where hotels, apartments, etc. are mainly provided with accommodation services and accommodation facilities, when a public place such as a hall area, a corridor, an elevator or an elevator is noisy, spitting out phlegm anywhere, throwing garbage randomly, etc. and other non-civilized behaviors occur, the guests in the public place may experience poor, thereby increasing the probability that the place is complained and even affecting the check-in rate of the place. It is therefore becoming increasingly important to ascertain the identity of agents in public places that have non-civilized behaviour and to alert them of the behaviour.

In the related art, a monitoring image of a certain public place to be monitored is generally obtained first, and a pre-trained behavior recognition model is utilized to recognize the civilized behaviors of personnel in the monitoring image so as to determine the civilized conditions of the behaviors of the human body in the monitoring image. When the occurrence of the non-civilized behavior of the person is detected, the identity of the agent can be identified by utilizing the face recognition technology. However, when the face of the agent is partially covered, the identity information of the agent cannot be determined by using the face recognition technology.

Therefore, how to improve the identity of the agent to be identified more accurately is a technical problem to be solved by those skilled in the art.

Disclosure of Invention

In order to improve accuracy of agent identity information, the application provides an identity determining method, device, equipment and medium based on building management and control.

In a first aspect, the present application provides a building management and control based identity determination method, which adopts the following technical scheme:

an identity determination method based on building management and control comprises the following steps:

acquiring human body images of agents corresponding to the non-civilized behaviors;

determining key human body characteristics of the human body image;

tracking the track of the agent by utilizing a real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system;

when the tracking result is that the agent enters a room, acquiring a first house number of the room in which the agent enters; obtaining identity information of the agent by using the first house number;

when the tracking result is that the agent leaves the building, the history monitoring image and the key human body characteristics are utilized to trace back the history track of the agent, so that a second door number of a room where the agent historically enters is obtained; and obtaining the identity information of the agent according to the second portal number.

The present application may be further configured in a preferred example to: the real-time monitoring image comprises a plurality of real-time image groups, the real-time image groups correspond to unique floors, and the real-time image groups at least comprise a plurality of real-time corridor images,

the step of tracking the track of the agent by utilizing the real-time monitoring image and the key human body characteristics to obtain a tracking result comprises the following steps:

acquiring a target floor identifier, wherein the target floor identifier is an identifier of an elevator stop floor;

determining a target real-time image group corresponding to the target floor mark in the plurality of real-time image groups;

determining target real-time corridor images in all the target real-time image groups according to the key human body characteristics, wherein the target real-time corridor images are real-time corridor images in which the track corresponding to the agent appears last;

and performing behavior analysis on the target real-time corridor image to obtain the tracking result.

The present application may be further configured in a preferred example to:

the real-time image group also comprises real-time elevator car images,

and determining the target real-time corridor image in all the target real-time image groups according to the key human body characteristics, wherein the method comprises the following steps:

Determining a final target real-time image group in all the target real-time image groups according to the key human body characteristics, wherein the real-time elevator cabin images of the final target real-time image group comprise the key human body characteristics;

determining a first real-time corridor image in the plurality of real-time corridor images of the final target real-time image group, wherein monitoring equipment corresponding to the first real-time corridor image is adjacent to monitoring equipment corresponding to the real-time elevator cabin corresponding to the final target real-time image group;

determining a predicted moving route of the agent according to the first real-time corridor image;

determining a second real-time corridor image in the plurality of real-time corridor images corresponding to the final target real-time image group according to the predicted moving route, wherein monitoring equipment corresponding to the second real-time corridor image is monitoring equipment on the predicted moving route;

carrying out personnel position and state analysis on each second real-time corridor image to obtain the behavior state of the agent in each second real-time corridor image;

and taking the behavior state as the second real-time corridor image of the through gate as the target real-time corridor image.

The present application may be further configured in a preferred example to:

after determining a second real-time corridor image from the plurality of real-time corridor images corresponding to the final target real-time image group according to the predicted moving route, the method further includes:

determining target lighting equipment information according to the predicted moving route, and controlling lighting equipment corresponding to the target lighting equipment information to start lighting;

acquiring a working state corresponding to each piece of target lighting equipment information, and determining fault lighting equipment information of which the working state is a fault state in all pieces of target lighting equipment information;

determining adjacent device information of each piece of fault lighting device information;

determining the equipment number of the fault lighting equipment information corresponding to the adjacent equipment information aiming at each piece of adjacent equipment information; and adjusting the brightness of the lighting equipment corresponding to the adjacent equipment information according to the equipment quantity.

The present application may be further configured in a preferred example to:

Judging whether a monitoring blind area exists on the predicted moving route or not;

if yes, acquiring the minimum moving speed of the agent and the blind area length of the monitoring blind area; calculating according to the minimum moving speed and the blind area length to obtain the estimated passing duration of the agent;

judging whether the agent passes through the monitoring blind area in real time according to all the second real-time corridor images;

if the agent passes through the monitoring blind area, acquiring the actual passing time of the agent passing through the monitoring blind area; judging whether the actual passing duration is greater than the expected passing duration or not; if the actual passing time length is longer than the expected passing time length, generating first prompt information, wherein the first prompt information is used for prompting a worker to check whether public facilities of the monitoring blind area are damaged or not;

if the agent does not pass through the monitoring blind area, acquiring the actual residence time of the agent in the monitoring blind area; judging whether the actual residence time is longer than the expected passing time; and if the actual stay time length is longer than the expected passing time length, generating second prompt information, wherein the second prompt information is used for prompting a worker to confirm the behavior of the agent in the monitoring blind area.

The present application may be further configured in a preferred example to:

before the obtaining of the human body image of the agent corresponding to the non-civilized behavior, the method further comprises:

for each elevator, acquiring elevator running information when the elevator stops and real-time elevator internal images when the elevator runs in real time, wherein the elevator running information at least comprises an elevator door state signal and elevator position information;

carrying out non-civilized behavior recognition on the image in the real-time elevator to obtain a first non-civilized behavior recognition result, wherein the first non-civilized behavior recognition result represents whether the non-civilized behavior exists in the elevator car;

determining a second non-civilized identification result according to the elevator running information, wherein the second non-civilized identification result represents whether a non-civilized behavior exists at a landing door of an elevator;

and when the first non-civilized identification result and/or the second non-civilized result is that the non-civilized behavior is identified, judging that the non-civilized behavior is monitored.

The present application may be further configured in a preferred example to:

the step of determining a second non-civilized identification result according to the elevator operation information comprises the following steps:

according to the elevator running information, determining an elevator door state and the elevator door state maintaining time length;

When the elevator door state is in a door opening state and the elevator door state maintaining time exceeds a preset door opening time, acquiring elevator position information, wherein the elevator position information is a floor identifier of a current stop floor of an elevator;

acquiring real-time elevator cab images corresponding to the elevator position information according to the elevator position information; and carrying out malicious blocking recognition on the elevator door on the real-time elevator cabin image corresponding to the elevator position information and the real-time elevator inner image, and determining the second non-civilized recognition result.

In a second aspect, the present application provides an identity determining apparatus based on building management and control, which adopts the following technical scheme:

an identity determination device based on building management and control, comprising:

the image acquisition module is used for acquiring the human body image of the agent corresponding to the non-civilized behavior;

the feature extraction module is used for determining key human body features of the human body image;

the tracking result determining module is used for tracking the track of the agent by utilizing a real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system; when the tracking result is that the agent enters a room, triggering a first identity information determining module; when the tracking result is that the agent leaves the building, triggering a second identity information determining module;

The first identity information determining module is used for obtaining a first house number of a room where the agent enters; obtaining identity information of the agent by using the first house number;

the second identity information determining module is used for carrying out historical track backtracking on the agent by utilizing the historical monitoring image and the key human body characteristics to obtain a second door number of a room where the agent historically enters; and obtaining the identity information of the agent according to the second portal number.

In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:

at least one processor;

a memory;

at least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application configured to perform the building management based identity determination method of any of the first aspects.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the building management based identity determination method of any of the first aspects.

In summary, the application at least comprises the following beneficial technical effects:

the method comprises the steps of obtaining human body images of agents corresponding to non-civilized behaviors, determining key human body characteristics of the human body images, and obtaining appearance characteristics when faces of the agents are shielded, so that an identity recognition process runs stably; compared with the method for directly tracking the real-time track of the human body image, the method for tracking the real-time track of the human body image by using the real-time monitoring image can track the real-time track of the human body image more accurately so as to determine whether an agent enters a room more accurately, thereby obtaining more accurate tracking results; on the one hand, when the tracking result is that the agent enters the room, the house number of the room in which the agent enters is obtained, and the identity information of the agent is obtained by utilizing the house number of the room in which the agent enters, so that the identity of the agent is accurately determined; on the other hand, when the tracking result is that the agent leaves the building, compared with the method of directly carrying out historical track backtracking on human body images, the method carries out historical track backtracking on key human body characteristics, so that a more accurate backtracking result is obtained, the house number of a room where the agent leaves is determined, and the identity information of the agent is obtained by using the house number of the room where the agent leaves, so that the accurate determination of the identity of the agent is realized.

Drawings

Fig. 1 is a schematic diagram of an application scenario of an identity determining method based on building management and control according to an embodiment of the present application.

Fig. 2 is a flow chart of an identity determining method based on building management and control according to an embodiment of the present application.

Fig. 3 is a schematic diagram of a floor structure according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a coordinate system of a floor plan view according to an embodiment of the present application.

Fig. 5 is a schematic diagram of a monitoring blind area according to an embodiment of the present application.

Fig. 6 is a schematic structural diagram of an identity determining apparatus based on building management and control according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to fig. 1 to 7.

The present embodiment is merely illustrative of the present application and is not intended to limit the present application, and those skilled in the art, after having read the present specification, may make modifications to the present embodiment without creative contribution as necessary, but are protected by patent laws within the scope of the present application.

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application are clearly and completely described, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.

Embodiments of the application are described in further detail below with reference to the drawings.

The embodiment of the application provides an identity determination method based on building management and control, which is executed by electronic equipment, wherein the electronic equipment can be a server or terminal equipment, and the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server for providing cloud computing service. The terminal device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto, and the terminal device and the server may be directly or indirectly connected through a wired or wireless communication manner, which is not limited herein.

As shown in fig. 1, the building management and control system at least comprises a monitoring system, and the monitoring system collects real-time monitoring images and then sends the real-time monitoring images to the electronic equipment; and the electronic equipment processes and analyzes the real-time monitoring image to judge whether the non-civilized behavior exists, and if the non-civilized behavior exists, the electronic equipment performs track tracking by using the real-time monitoring image or performs historical track backtracking by using the historical monitoring image so as to obtain the identity information of the agent of the non-civilized behavior.

Further, the building management and control system may further include an elevator system, where after the elevator system collects real-time elevator operation information, the elevator door operation information is sent to the electronic device; the electronic equipment processes the elevator running information and the real-time monitoring image simultaneously so as to judge whether the elevator door or the elevator inside has the non-civilized behavior.

Still further, the building management and control system may further include a lighting system, where the electronic device analyzes the real-time monitoring image to obtain a predicted moving route of the agent, and then determines target lighting device information in lighting devices corresponding to the lighting system; and the electronic equipment sends the target lighting equipment information to a lighting system, and the lighting system controls the lighting equipment corresponding to the target lighting equipment information to perform lighting.

As shown in fig. 2, the method includes steps S101 to S105, wherein:

step S101: and acquiring human body images of the agents corresponding to the non-civilized behaviors.

Specifically, after the monitoring system sends the collected real-time monitoring image to the electronic equipment, when the electronic equipment identifies that the elevator or the elevator door has the non-civilized behavior in at least one real-time image of the real-time monitoring image, the at least one real-time image is determined to be a target real-time image, wherein the real-time monitoring image comprises a plurality of real-time images, the plurality of real-time images can comprise real-time corridor images and/or real-time elevator car images, each real-time image comprises a plurality of human body images, and the number of the human body images is the same as the number of pedestrians in a monitoring area corresponding to the real-time images; for each target real-time image, the human body image identified as the non-civilized behavior is determined as the human body image of the agent.

Step S102: key human body characteristics of the human body image are determined.

Specifically, key human body characteristics of the human body image can be determined through principal component analysis, optical flow characteristic analysis or deep learning characteristic extraction and the like, wherein the key human body characteristics can include human body characteristics such as height, sex, clothing color and the like of an agent.

Step S103: and tracking the track of the agent by utilizing the real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained through a plurality of monitoring devices in the building management and control system.

It can be understood that the agent may be blocked by other pedestrians and/or obstacles in the moving process, and at this time, the human body image corresponding to the key human body feature cannot be identified through the real-time image, so that the moving human body image is only locked and tracked in the real-time image, and the problem of tracking interruption may occur. Therefore, the scheme can carry out human body tracking based on key human body characteristics of human body images so as to improve the stability of the track tracking process.

The tracking result is an action name corresponding to an action of the agent when the agent finally appears in the real-time monitoring image, the action name can be an entering room or an exiting building, and the building is a building managed by the building management and control system.

Step S104: when the tracking result is that the agent enters the room, acquiring a first house number of the room in which the agent enters; and obtaining the identity information of the agent by using the first house number.

Specifically, when the tracking result is that the agent enters the room, extracting a house number image of the agent entering the room to obtain a first house number image; identifying a first house number in the first house number image; the electronic equipment sends the first house number to a house information management system, and the house information management system determines the identity information of a house person corresponding to the first house number, wherein the identity information can comprise personal information such as the name, sex, personal crown-free image and the like of the house person; and the check-in information management system sends the identity information of the check-in personnel corresponding to the first house number to the electronic equipment, and the electronic equipment takes the identity information of the check-in personnel corresponding to the first house number as the identity information of the agent.

It can be understood that the person entering the room is not necessarily the resident in the room, but may be the visitor of the resident in the room, so the scheme can further determine whether the agent is the resident in the room corresponding to the first house number or the visitor of the resident corresponding to the first house number, so as to reduce the error probability of the identity information of the agent.

Further, after the first house number is obtained, the method specifically further includes: acquiring access control information corresponding to a room corresponding to a first house number when an agent enters a house, wherein the access control information represents whether an access control card identification process exists or not; when the access control information is that the access control card identification process does not exist, a visitor record of a room corresponding to the first house number is obtained, wherein the visitor record is visitor personal identity information and a target access room number, and can be obtained through a visiting module in an access information management system, and the visiting module is used for storing the visitor record of each room; and obtaining identity information of the agent by using the visitor records.

Step S105: when the tracking result is that the agent leaves the building, the history monitoring image and key human body characteristics are utilized to trace back the history track of the agent, so that a second door mark of a room where the agent historically enters is obtained; and obtaining the identity information of the agent according to the second door number.

The history monitoring image comprises a plurality of history image groups, each history image group corresponds to each floor, and each history image group at least comprises a plurality of history corridor images.

Specifically, when the tracking result is that the agent leaves the building, acquiring a riding floor identifier of the agent entering the elevator; determining a target historical image group in the plurality of historical image groups, wherein the target historical image group is a historical image group corresponding to the riding floor mark, and comprises a plurality of target historical corridor images; determining the occurrence time of the human body image corresponding to the key human body characteristics in each target historical image; taking a target history image corresponding to the earliest occurrence time as a target history corridor image; analyzing the target historical corridor image and determining a second door plate image corresponding to the room where the agent initially appears; identifying a second gate number in the second gate image; the electronic equipment sends the second gate number to a check-in information management system, and the check-in information management system determines the identity information of a check-in person corresponding to the second gate number; and the check-in information management system sends the identity information of the check-in personnel corresponding to the second door number to the electronic equipment, and the electronic equipment takes the identity information of the check-in personnel corresponding to the second door number as the identity information of the agent.

In the embodiment of the application, the human body image of the agent corresponding to the non-civilized behavior is obtained, the key human body characteristics of the human body image are determined, and the appearance characteristics can be obtained when the human face of the agent is shielded, so that the identity recognition process is stably operated; compared with the method for directly tracking the real-time track of the human body image, the method for tracking the real-time track of the human body image by using the real-time monitoring image can track the real-time track of the human body image more accurately so as to determine whether an agent enters a room more accurately, thereby obtaining more accurate tracking results; on the one hand, when the tracking result is that the agent enters the room, the house number of the room in which the agent enters is obtained, and the identity information of the agent is obtained by utilizing the house number of the room in which the agent enters, so that the identity of the agent is accurately determined; on the other hand, when the tracking result is that the agent leaves the building, compared with the method of directly carrying out historical track backtracking on human body images, the method carries out historical track backtracking on key human body characteristics, so that a more accurate backtracking result is obtained, the house number of a room where the agent leaves is determined, and the identity information of the agent is obtained by using the house number of the room where the agent leaves, so that the accurate determination of the identity of the agent is realized.

It should be understood that the building controlled by the building control system includes a plurality of floors, each floor has a plurality of monitoring devices, and the monitoring devices are used for collecting real-time images of the monitoring areas corresponding to the monitoring devices; as shown in fig. 3, each floor has areas such as a room, a corridor, an elevator room, and an elevator, and the elevator room is an area where a guest waits for taking an elevator; the real-time images corresponding to the monitoring equipment in the corridor in the monitoring area are real-time corridor images, the real-time images corresponding to the monitoring equipment in the elevator cab in the monitoring area are real-time elevator cab images, the real-time elevator cab images corresponding to each floor and the plurality of real-time corridor images form a unique real-time image group corresponding to the floor, and the real-time image groups corresponding to the floors can form real-time monitoring images.

In one possible implementation manner of the embodiment of the present application, step S103, track tracking is performed on an agent by using a real-time monitoring image and key human body features to obtain a tracking result, which may specifically include:

Determining target real-time corridor images in all target real-time image groups according to key human body characteristics, wherein the target real-time corridor images are real-time corridor images of which the track corresponding to the agent finally appears;

and performing behavior analysis on the target real-time corridor image to obtain a tracking result.

It can be understood that the real-time monitoring image includes a plurality of real-time images, the number of the real-time images is more, if the track of the agent is tracked simultaneously for all the real-time images, the situation that the electronic device is blocked due to the large data processing amount may occur, and the agent has an unclassified behavior in the elevator. Therefore, in order to reduce the number of real-time images for tracking the track of the agent, the track can be tracked only on the real-time images corresponding to the monitoring equipment arranged on the floor where the elevator where the agent leaves is likely to stop.

Specifically, after the elevator system collects the stop request of the elevator where the agent is located in real time, the stop request of the elevator where the agent is located is sent to the electronic equipment, wherein the stop request can be obtained through an elevator internal floor key signal and a signal corresponding to an elevator outbound button arranged in an elevator cabin, and the stop request at least can comprise a plurality of target stop floor identifiers of the elevator; the electronic equipment takes the elevator multiple target stop floor identifications as target floor identifications; determining a real-time image group corresponding to the target floor mark as a target real-time image group, wherein the floor mark corresponds to the real-time image group one by one; determining target real-time corridor images in all target real-time image groups according to the key human body characteristics; analyzing the target real-time corridor image to determine a first house number image corresponding to a room where the agent finally disappears; identifying a first house number in the first house number image; the electronic equipment sends the first house number to a house information management system, and the house information management system determines the identity information of the house personnel corresponding to the first house number; and the check-in information management system sends the identity information of the check-in personnel corresponding to the first house number to the electronic equipment, and the electronic equipment takes the identity information of the check-in personnel corresponding to the first house number as the identity information of the agent.

In the embodiment of the application, the floor identification corresponding to the floor where the agent possibly appears is determined by acquiring the target floor identification; determining a target real-time image group corresponding to the target floor mark in the plurality of real-time image groups so as to determine real-time images possibly containing human body images of agents and perform primary screening; according to the key human body characteristics, in all target real-time image groups subjected to preliminary screening, target real-time corridor images can be determined more quickly, and the occurrence probability of the condition that electronic equipment is blocked due to large data processing capacity is reduced; and performing behavior analysis on the target real-time corridor image to obtain a tracking result through a more stable process.

According to a possible implementation manner of the embodiment of the present application, determining target real-time corridor images in all target real-time image groups according to key human body features may specifically include:

determining a final target real-time image group in all target real-time image groups according to the key human body characteristics, wherein the real-time elevator cabin images of the final target real-time image group comprise the key human body characteristics;

determining a first real-time corridor image in a plurality of real-time corridor images of a final target real-time image group, wherein monitoring equipment corresponding to the first real-time corridor image is adjacent to monitoring equipment corresponding to a real-time elevator cabin corresponding to the final target real-time image group;

determining a second real-time corridor image in a plurality of real-time corridor images corresponding to the final target real-time image group according to the predicted moving route, wherein monitoring equipment corresponding to the second real-time corridor image is monitoring equipment on the predicted moving route;

carrying out personnel position state analysis on each second real-time corridor image to obtain the behavior state of the agent in each second real-time corridor image;

and taking the second real-time corridor image with the behavior state of passing through the gate as a target real-time corridor image.

It will be appreciated that agents take elevators for two purposes, entering the room and leaving the building: when the aim of the behaviours is to enter the room, the behaviours enter a certain floor through the elevator, specifically enter the elevator cabin through the elevator, enter the corridor through the elevator cabin, and finally enter the room through the corridor; when the aim of an actor is to leave the building, the actor will enter a floor which can be outside the building through an elevator, in particular, enter an elevator cabin through an elevator, enter a corridor through an elevator, and finally enter a door which can leave the building through the corridor. It is known that agents have the same type of travel route when entering a room or leaving a building, i.e. when entering an elevator car from an elevator car, then from the car to a corridor, finally through a corridor into a door, which can be a room door or a door that can leave the building. Therefore, the scheme can further screen the real-time image of the target for track tracking based on the travel route.

According to the key human body characteristics, determining a final target real-time image group in all target real-time image groups can specifically include: judging whether the real-time elevator car images in the target real-time image groups comprise human body images corresponding to key human body features or not according to each target real-time image group; if yes, the representative agent enters a floor corresponding to the target real-time image group, and the target real-time image group is determined to be a final target real-time image group so as to perform primary screening.

Determining a first real-time corridor image from a plurality of real-time corridor images of a final target real-time image group may specifically include: acquiring monitoring equipment identifiers corresponding to all real-time images in the final target real-time image group, wherein the monitoring equipment identifiers represent the installation position information of the monitoring equipment; according to the elevator cabin monitoring equipment identification corresponding to the real-time elevator cabin image in the final real-time image group, determining a first monitoring equipment identification in the corridor monitoring equipment identification corresponding to the real-time corridor image in the final real-time image group, wherein the first monitoring equipment identification is a monitoring equipment identification corresponding to monitoring equipment adjacent to the monitoring equipment corresponding to the elevator cabin monitoring equipment identification; and determining the real-time corridor image corresponding to the first monitoring equipment identifier as a first real-time corridor image.

Because the other real-time corridor images except the first real-time corridor image are farther from the elevator cab where the agent first appears than the monitoring device corresponding to the first real-time corridor image, the predicted moving route of the agent can be rapidly determined when the agent enters the corridor by determining the first real-time corridor image.

According to the first real-time corridor image, determining a predicted moving route of the agent may specifically include: determining a moving direction of a human body image corresponding to the key human body characteristic in a first real-time corridor image, wherein the moving direction can be forward to an n preset direction after leaving an elevator, n is a positive integer which can be preset by a technician and stored in electronic equipment, and the moving direction represents leftward movement or rightward movement of an agent after leaving the elevator; taking the position of the elevator of the floor corresponding to the final target real-time image group as a reference object, determining a left corridor of the reference object as a left moving route, and determining a right corridor of the reference object as a right moving route; when the moving direction is leftward movement, determining the predicted moving route as a left moving route; when the movement direction is rightward movement, the predicted movement route is determined as a rightward movement route.

According to the predicted moving route, determining a second real-time corridor image in the plurality of real-time corridor images corresponding to the final target real-time image group may specifically include: determining an initial moving route monitoring equipment identifier corresponding to the predicted moving route in the final target real-time image group; determining an initial moving route monitoring equipment identifier except the first monitoring equipment identifier as a moving route monitoring equipment identifier; and determining the real-time image corresponding to the mobile route monitoring equipment identifier as a second real-time corridor image.

The step of analyzing the personnel position and state of each second real-time corridor image to obtain the behavior state of the agent in each second real-time corridor image can specifically include: determining a first coordinate range of each door of the floor where the agent is located according to each second real-time corridor image, wherein the first coordinate range is a range of position coordinates of the door in a top view of the floor where the door is located; when the human body image corresponding to the key human body features is identified in the second real-time corridor image, determining a real-time second coordinate of the agent, wherein the second coordinate is a position coordinate of the human body image corresponding to the key human body features in a top view of a floor where the agent is located; and determining a behavior state according to the second coordinates and all the first coordinate ranges, wherein when the second coordinates belong to any one of the first coordinate ranges and the human body image corresponding to the key human body feature disappears in the second real-time corridor image, determining that the behavior state is a pass gate, otherwise, determining that the behavior state is a monitoring area corresponding to the second real-time corridor image.

For example, as shown in fig. 4, the first coordinate range of the room door of the room M is { (x, y) |x=x1, y1+.y+.ltoreq.y2 }, and the second coordinate of the agent is (x 0, y 0); when (x 0, y 0) ∈ { (x, y) |x=x1, y 1+.y+.y2 } and the human body image corresponding to the key human body feature disappears in the second real-time corridor image, the behavior state is determined to be a pass gate.

Wherein the door may be a room door or a hall door. When the key human body characteristics are identified and the human body images corresponding to the key human body characteristics enter the elevator entrance or the monitoring dead angle, the default behavior state is leaving.

It should be noted that, after determining the first real-time corridor image, the electronic device monitors the first real-time corridor image in real time until the human body image corresponding to the key human body feature can be monitored, and then determines the predicted moving route of the agent according to the first real-time corridor image; similarly, after the second real-time corridor images are determined, the electronic device monitors the second real-time corridor images in real time until the behavior state of the agent in any one of the second real-time corridor images is determined to be a pass gate.

In the embodiment of the application, according to key human body characteristics, a final target real-time image group corresponding to a floor where an agent enters is determined in all target real-time image groups, and the target real-time image groups are subjected to primary screening; determining a first real-time corridor image in a plurality of real-time corridor images of a final target real-time image group to determine real-time corridor images of monitoring equipment adjacent to an elevator cab of a floor where an agent is located, and then predicting a moving route to further reduce the track identification range, and performing secondary screening on the target real-time images; according to the predicted moving route, determining a second real-time corridor image corresponding to the predicted moving route in a plurality of real-time corridor images corresponding to the final target real-time image group, and thus carrying out three-time screening on the target real-time elevator car images; and (3) analyzing the personnel position state of each second real-time corridor image, and taking the second real-time corridor image with the behavior state of the agent passing through the gate as a target real-time corridor image after the behavior state of the agent in each second implementation corridor image is obtained, so that the target real-time corridor image in the target real-time image group is screened for three times based on the travelling route, and finally, the target real-time corridor image is accurately determined.

In one possible implementation manner of the embodiment of the present application, after determining the second real-time corridor image in the plurality of real-time corridor images corresponding to the final target real-time image group according to the predicted moving route, the method specifically may further include:

acquiring a working state corresponding to each piece of target lighting equipment information, and determining fault lighting equipment information with the working state being a fault state in all pieces of target lighting equipment information;

determining neighboring device information of each faulty lighting device information;

determining the equipment number of the fault lighting equipment information corresponding to the adjacent equipment information aiming at each piece of adjacent equipment information; and adjusting the brightness of the lighting equipment corresponding to the adjacent equipment information according to the equipment number.

It can be understood that, to save electric energy, the lighting device in public places is not in a normally-on state, but the lighting time of the lighting device when no person is present is reduced by the sound control lighting mode, so as to realize electric energy saving. However, when the sound emitted by the person is insufficient to trigger the illumination device to illuminate by the sound control manner, the illumination device cannot provide illumination for the person passing through, and the person passing through includes but is not limited to an agent, so that the problem that whether the person passes through cannot be quickly identified by utilizing the sound control manner exists in illumination, and the problem that the real-time image cannot accurately identify the human body image corresponding to the key human body feature may be caused by too dark light.

Therefore, the target lighting equipment information corresponding to the lighting equipment which needs to provide lighting for the agent can be determined through the prediction of the moving route, compared with the situation that the agent actively triggers the lighting equipment to work in a sound control mode, the electronic equipment can actively trigger the lighting equipment to work through the prediction of the moving route to improve the speed of the lighting equipment to identify whether personnel pass through or not, and therefore the human body images corresponding to the key human body features can be identified in the real-time images more accurately.

Further, the lighting device may be malfunctioning, and may not provide illumination for the agent to enhance the definition of the live image, so the agent may be provided with illumination by using the lighting device adjacent to the malfunctioning lighting device. The lighting system is provided with lighting equipment identifiers for all the lighting equipment, the lighting equipment identifiers can represent the installation positions of the lighting equipment corresponding to the lighting equipment identifiers in a building controlled by the building control system, the monitoring equipment corresponds to at least one lighting equipment, and the lighting equipment can be set by technicians according to the actual installation positions of the lighting equipment and stored in the electronic equipment in advance.

Specifically, determining a first brightness of a second real-time corridor image; determining a target lighting device identifier corresponding to a lighting device positioned on the predicted moving route according to the predicted moving route and all lighting device identifiers, wherein the target lighting device identifier is target lighting device information, and the lighting device identifier is lighting device information; generating an illumination instruction according to the target illumination equipment information, and controlling illumination equipment corresponding to the target illumination equipment information to illuminate by utilizing the illumination instruction; determining second brightness of the second real-time corridor image, judging whether a difference value between the first brightness and the second brightness is larger than a preset brightness threshold value, and pre-determining and storing the preset brightness threshold value in the electronic equipment by a technician; if yes, determining that the working state corresponding to the target lighting equipment information corresponding to the second real-time corridor image is a fault state, otherwise, determining that the working state corresponding to the target lighting equipment information corresponding to the second real-time corridor image is a normal state; determining target lighting equipment information with the working state being a fault state as fault lighting equipment information; determining adjacent device information corresponding to a lighting device adjacent to the failed lighting device information installation position among all the target lighting device information; determining a first equipment number of fault lighting equipment information corresponding to the adjacent equipment information and a second equipment number corresponding to the adjacent equipment information according to each adjacent equipment information, wherein the first equipment number is the number of lighting equipment corresponding to the fault lighting equipment information adjacent to the installation position of the lighting equipment corresponding to the adjacent equipment information, and the second equipment number is the number of all lighting equipment adjacent to the installation position of the lighting equipment corresponding to the adjacent equipment information; the method comprises the steps of obtaining current illumination power aiming at each piece of adjacent illumination equipment information, and obtaining illumination power increment value calculation corresponding to the adjacent equipment information by utilizing an illumination power increment value calculation formula according to the current illumination power, the first equipment number and the second equipment number, wherein the illumination power increment value calculation formula is as follows: illumination power increment value calculation = first device number/(second device number× (preset power threshold-current illumination power), preset power threshold being rated power of illumination device corresponding to adjacent device information, which may be stored in advance in electronic device by technician; and adjusting the brightness of the corresponding lighting equipment of the adjacent equipment information according to the lighting power increasing value.

It should be noted that the lighting device in the present solution supports illumination adjustment, and the illumination power adjustment can be achieved by adjusting the voltage or current to which the lighting device is connected.

According to the embodiment of the application, after the target lighting equipment information is determined according to the predicted moving route, the lighting equipment corresponding to the target lighting equipment information is controlled to start lighting so as to improve the accuracy of identifying the human body images corresponding to the key human body features in the real-time images; acquiring a working state corresponding to each piece of target lighting equipment information, so as to determine fault lighting equipment information with the working state being a fault state in all pieces of target lighting equipment information, and further determine lighting equipment which cannot provide illumination supplement for the second real-time corridor image; determining adjacent device information of each piece of fault lighting device information to determine adjacent lighting devices capable of lighting in place of the corresponding lighting device of the fault lighting device information; and determining the equipment quantity of the fault lighting equipment information corresponding to the adjacent equipment information aiming at each piece of adjacent equipment information so as to determine the degree to which the lighting equipment corresponding to the adjacent equipment information needs to be regulated, accurately regulating the brightness of the lighting equipment corresponding to the adjacent equipment information according to the equipment quantity, and increasing the illumination for the second real-time corridor image on the premise of energy conservation so as to further improve the accuracy of identifying the human body image corresponding to the key human body feature in the second real-time corridor image.

if yes, acquiring the minimum moving speed of the agent and the blind area length of the monitoring blind area; calculating according to the minimum moving speed and the length of the dead zone to obtain the estimated passing duration of the agent;

judging whether the agent passes through the monitoring blind area in real time according to all the first real-time corridor images;

if the agent passes through the monitoring blind area, acquiring the actual passing time length of the agent passing through the monitoring blind area; judging whether the actual passing time length is longer than the expected passing time length or not; if the actual passing time length is longer than the expected passing time length, generating first prompt information, wherein the first prompt information is used for prompting a worker to check whether public facilities of the monitoring blind area are damaged or not;

if the agent does not pass through the monitoring blind area, acquiring the actual stay time of the agent in the monitoring blind area; judging whether the actual residence time is longer than the expected passing time; and if the actual stay time is longer than the expected pass time, generating second prompt information which is used for prompting the staff to confirm the behavior of the agent in the monitoring blind area.

It can be understood that the probability of the agent appearing the non-civilized behavior again in the moving process is higher than that of other people, and when the monitoring blind area exists, whether the agent appears the non-civilized behavior again in the monitoring blind area can not be judged through the monitoring image; because the time is needed for the agent to appear in the monitoring blind area, the residence time of the agent in the monitoring area can be used for assisting in determining whether the agent has the non-civilized behavior in the monitoring area.

Specifically, judging whether any preset monitoring blind area exists on the predicted mobile route, wherein the position of the preset monitoring blind area can be preset by a technician and stored in the electronic equipment, each preset monitoring blind area comprises a blind area edge and a blind area vertex, and the blind area edge and the blind area vertex are connected to form a closed blind area; if yes, determining adjacent second real-time corridor images corresponding to monitoring equipment adjacent to the monitoring blind area; determining the minimum moving speed of the agent based on the historical corridor image, and acquiring the blind area length of the monitoring blind area, wherein the minimum moving speed is the minimum historical moving speed of the agent in the historical corridor image; and obtaining the estimated passing duration of the agent by an estimated passing duration calculation formula for the minimum moving speed and the length of the dead zone, wherein the estimated passing duration calculation formula is as follows: estimated passage time length=dead zone length +.min movement speed; judging whether the human body image corresponding to the key human body feature leaves from any adjacent second real-time corridor image or not in real time, and then appearing in the other adjacent second real-time corridor image;

If yes, determining that the agent passes through the monitoring blind area, and determining a first moment when a human body image corresponding to the key human body characteristics leaves from the adjacent second real-time corridor image and a second moment when the human body image enters into the other adjacent second real-time corridor image; determining the actual passing duration of the agent passing through the monitoring blind area according to the first moment and the second moment, wherein the actual passing duration is equal to the first moment-second moment; judging whether the actual passing time length is longer than the expected passing time length or not; if the actual passing time length is longer than the expected passing time length, characterizing that an agent possibly has an unclassified behavior in the monitoring blind area, and generating first prompting information to prompt a worker to check whether public facilities of the monitoring blind area are damaged; and if the actual passing duration is less than or equal to the expected passing duration, characterizing that the agent has no non-civilized behavior in the monitoring blind area.

If not, determining that the agent does not pass through the monitoring blind area, and determining the entering moment of the human body image corresponding to the key human body characteristics into any adjacent second real-time corridor image; determining the actual residence time between the entering time and the current time, wherein the actual residence time is the actual residence time of the agent in the monitoring area; judging whether the actual residence time is longer than the expected passing time; if the actual stay time is longer than the expected pass time, characterizing that the agent may be performing non-civilized behavior in the monitoring blind area, and generating second prompt information to prompt the staff to confirm the behavior of the agent in the monitoring blind area.

Further, obtaining the blind area length of the monitoring blind area may specifically include: determining a target second real-time corridor image entering the monitoring blind area in all second real-time corridor images by using a predicted route, wherein the predicted route can comprise a direction of the predicted route, and the target second real-time corridor image is a first adjacent second real-time corridor image in the direction of the predicted route in all adjacent second real-time corridor images; determining an entering position of the agent entering the monitoring blind area by using the target second real-time corridor image, wherein the entering position is a position coordinate of a position of the agent entering the monitoring area on an edge line of the monitoring blind area in a top view of a floor where the agent is located; according to the moving direction of the predicted route, the blind area vertex of the monitoring blind areaThe system comprises a first vertex group and a second vertex group, wherein the first vertex group and the second vertex group respectively comprise two blind area vertices, a blind area edge between the two blind area vertices of the first vertex group is a blind area edge for an agent to enter the monitoring blind area, and a blind area edge between the two blind area vertices of the second vertex group is a blind area edge for the agent to leave the monitoring blind area; determining preset vertex positions corresponding to the two blind area vertices of the second vertex group, wherein the preset vertex positions are determined in advance by a technician and stored in the electronic equipment; obtaining the blind area length of the monitoring blind area according to the entering position and the preset vertex positions corresponding to the two blind area vertices of the second vertex group, wherein the preset vertex positions are the position coordinates of the blind area vertices in the top view of the floor where the behavior person is located, ，/>Length of blind area>To enter the position->And->The vertex positions are two preset vertex positions of the second vertex group.

As shown in FIG. 5, points a and b are two blind area vertices of the second vertex group, and the position coordinates of point a are-The position coordinates of point b are +.>The entry position is->The length of the line segment 1 isThe length of line segment 2 is +.>The dead zone length is the maximum value of the length of line segment 1 and the length of line segment 2, i.e. +.>。

In the embodiment of the application, after the existence of the monitoring blind area on the predicted moving route is determined, the minimum moving speed of the agent and the blind area length of the monitoring blind area are obtained, so that the predicted passing time of the agent is calculated; when an agent passes through the monitoring blind area, if the actual passing time is longer than the expected passing time, prompting a worker to check whether public facilities of the monitoring blind area are damaged or not so as to avoid that the non-civilized behavior of the agent in the monitoring blind area can not be identified due to the monitoring blind area; when the agent does not pass through the monitoring blind area, if the actual stay time is longer than the expected pass time, prompting the staff to confirm the behavior of the agent in the monitoring blind area, so as to accurately identify the non-civilized behavior of the agent.

In one possible implementation manner of the embodiment of the present application, before the step S101 of obtaining the human body image of the agent corresponding to the non-civilized behavior, the method specifically may further include:

determining a second non-civilized identification result according to the elevator operation information, wherein the second non-civilized identification result represents whether a non-civilized behavior exists at a landing door of the elevator;

It can be understood that the non-civilized behavior about the elevator can not only occur in the elevator, but also can be recognized from two angles of the outside and the inside of the elevator only by means of real-time images of the inside of the elevator when the outside personnel of the elevator maliciously call the elevator or maliciously stop the elevator.

The elevator running information is an elevator running log, and can be collected by an elevator system and transmitted to electronic equipment; the elevator door status signal may be determined from the operating signal of a photoelectric sensor at the elevator door, it being understood that a photoelectric sensor is often used to determine whether an object has passed through the elevator door to determine whether the elevator door can be closed.

It is noted that the elevator operation includes not only the moving state of the elevator but also the state to be moved of the elevator, and the elevator is not operated when the elevator is not energized.

In the embodiment of the application, the acquired real-time elevator inner image is subjected to the non-civilized behavior recognition to determine whether the elevator car has the non-civilized behavior or not; the elevator operation information obtained is analyzed to determine whether the non-civilized behavior exists at the landing door of the elevator; when there is a non-civilized behavior at the landing door of the elevator and/or in the car of the elevator, it is accurately determined from a comprehensive point of view that the non-civilized behavior is monitored.

According to a possible implementation manner of the embodiment of the present application, according to the elevator operation information, determining the second non-civilized identification result may specifically include:

according to the elevator operation information, determining an elevator door state and an elevator door state maintaining time length;

when the elevator door state is in a door opening state and the elevator door state maintaining time length exceeds a preset door opening time length, acquiring elevator position information, wherein the elevator position information is a floor identifier of a current stopping floor of the elevator;

acquiring real-time elevator car images corresponding to the elevator position information according to the elevator position information; and carrying out malicious blocking recognition on the elevator door on the real-time elevator car image and the real-time elevator inner image corresponding to the elevator position information, and determining a second non-civilized recognition result.

It can be understood that when a person maliciously blocks an elevator door in an elevator cab so that the elevator door cannot be closed, key human body characteristics of the agent cannot be determined through images acquired by monitoring equipment installed in the elevator; therefore, the scheme can judge whether the elevator has the malicious door blocking behavior or not through the real-time image of the elevator cabin.

The elevator door state is an elevator door real-time state, and the real-time state can be a door opening state, a door closing state or a door closing state; the elevator door state maintaining time length is the time length of the elevator door in a real-time state, and can be directly extracted by an elevator operation log. The preset door opening time length is a historical door opening time length average value, and can be updated in real time and stored in the electronic equipment.

Specifically, the identifying of malicious blocking of the elevator door is performed on the real-time elevator car image and the real-time elevator inner image corresponding to the elevator position information, and the determining of the second non-civilized identifying result may specifically include: respectively carrying out malicious door blocking identification in preset non-civilized behaviors on a real-time elevator car image and a real-time elevator inner image corresponding to the elevator position information; when at least one image of the real-time elevator cabin image and the real-time elevator inner image corresponding to the elevator position information determines that malicious door blocking behaviors exist, determining that the second non-civilized recognition result is that non-civilized behaviors exist at the landing door of the elevator; when the malicious door blocking recognition in the preset non-civilized behaviors does not exist in the real-time elevator car image and the real-time elevator inner image corresponding to the elevator position information, determining that the second non-civilized recognition result is that the non-civilized behaviors do not exist at the landing door of the elevator.

According to the embodiment of the application, through elevator operation information, the elevator door state and the elevator door state maintaining time length are determined so as to determine whether the elevator is in a door opening state currently; when the elevator is in a door opening state, if the state maintaining time of the elevator door exceeds the preset door opening time, determining that the probability of maliciously blocking the elevator door is preliminarily determined; after the elevator position information is acquired, acquiring real-time elevator cab images corresponding to the elevator position information according to the elevator position information so as to determine the situation of an elevator cab; according to the elevator cabin condition and the elevator internal condition, whether malicious door blocking behaviors exist or not is determined together, and accuracy of the second non-civilized identification result can be improved.

The above embodiments introduce a building management-based identity determining method from the aspect of a method flow, and the following embodiments introduce a building management-based identity determining apparatus from the aspect of a virtual module or a virtual unit, specifically the following embodiments are described below.

The embodiment of the application provides an identity determining device based on building management and control, as shown in fig. 6, which specifically may include:

the image acquisition module 201 is configured to acquire a human body image of an agent corresponding to the non-civilized behavior;

A feature extraction module 202, configured to determine key human features of the human body image;

the tracking result determining module 203 is configured to track an agent by using a real-time monitoring image and key human body features to obtain a tracking result, where the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system; triggering the first identity information determination module 204 when the tracking result is that the agent enters the room; triggering the second identity information determining module 205 when the tracking result is that the agent leaves the building;

a first identity information determining module 204, configured to obtain a first house number of a room that the agent enters; obtaining identity information of the agent by using the first house number;

the second identity information determining module 205 is configured to trace back the historical track of the agent by using the historical monitoring image and the key human body features, so as to obtain a second door number of the room where the agent historically enters; and obtaining the identity information of the agent according to the second door number.

In one possible implementation manner of the embodiment of the present application, the real-time monitoring image includes a plurality of real-time image groups, the real-time image groups correspond to unique floors, and the real-time image groups at least include a plurality of real-time corridor images, and the tracking result determining module 203 is specifically configured to, when performing the track tracking on the agent by using the real-time monitoring image and the key human body features, obtain the tracking result:

In one possible implementation manner of the embodiment of the present application, the tracking result determining module 203 is specifically configured to, when determining the target real-time corridor image in all the target real-time image groups according to the key human body features:

One possible implementation manner of the embodiment of the present application is an identity determining apparatus based on building management and control, further including:

a lighting adjustment module for:

the monitoring blind area behavior early warning module is used for:

the non-civilized behavior detection module is used for:

In one possible implementation manner of the embodiment of the present application, the non-civilized behavior detection module is configured to, when executing the determination of the second non-civilized recognition result according to the elevator operation information:

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, a specific working process of the identity determining apparatus based on building management and control described above may refer to a corresponding process in the foregoing method embodiment, which is not described herein again.

In an embodiment of the present application, as shown in fig. 7, an electronic device shown in fig. 7 includes: a processor 301 and a memory 303. Wherein the processor 301 is coupled to the memory 303, such as via a bus 302. Optionally, the electronic device may also include a transceiver 304. It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device is not limited to the embodiment of the present application.

The processor 301 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 301 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

Bus 302 may include a path to transfer information between the components. Bus 302 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect Standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. Bus 302 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or type of bus.

The Memory 303 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

The memory 303 is used for storing application program codes for executing the inventive arrangements and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement what is shown in the foregoing method embodiments.

Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. But may also be a server or the like. The electronic device shown in fig. 7 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.

Embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above. Compared with the related art, the embodiment of the application acquires the human body image of the agent corresponding to the non-civilized behavior, determines the key human body characteristics of the human body image, and can still obtain the appearance characteristics when the human face of the behavioural is blocked, so that the identity recognition process runs stably; compared with the method for directly tracking the real-time track of the human body image, the method for tracking the real-time track of the human body image by using the real-time monitoring image can accurately track the real-time track so as to accurately determine whether the agent enters a room or not, so that an accurate tracking result is obtained; on the one hand, when the tracking result is that the agent enters the room, the house number of the room in which the agent enters is obtained, and the identity information of the agent is obtained by utilizing the house number of the room in which the agent enters, so that the identity of the agent is accurately determined; on the other hand, when the tracking result is that the agent leaves the building, compared with the method of directly carrying out historical track backtracking on human body images, the method carries out historical track backtracking on key human body characteristics, so that a more accurate backtracking result is obtained, the house number of a room where the agent leaves is determined, and the identity information of the agent is obtained by using the house number of the room where the agent leaves, so that the accurate determination of the identity of the agent is realized.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations should and are intended to be comprehended within the scope of the present application.

Claims

1. An identity determination method based on building management and control is characterized by comprising the following steps:

Determining key human body characteristics of the human body image;

tracking the track of the agent by utilizing a real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system, the real-time monitoring image comprises a plurality of real-time image groups, the real-time image groups also comprise real-time elevator car images, the real-time image groups correspond to unique floors, and the real-time image groups at least comprise a plurality of real-time corridor images;

when the tracking result is that the agent leaves the building, the history monitoring image and the key human body characteristics are utilized to trace back the history track of the agent, so that a second door number of a room where the agent historically enters is obtained; obtaining identity information of the agent according to the second portal number;

according to the key human body characteristics, determining target real-time corridor images in all the target real-time image groups, wherein the method comprises the following steps:

taking the second real-time corridor image with the behavior state of passing through a gate as the target real-time corridor image;

if the agent does not pass through the monitoring blind area, acquiring the actual residence time of the agent in the monitoring blind area; judging whether the actual residence time is longer than the expected passing time; if the actual stay time length is longer than the expected passing time length, generating second prompt information, wherein the second prompt information is used for prompting a worker to confirm the behavior of the agent in the monitoring blind area;

2. The building control-based identity determination method according to claim 1, further comprising, after determining a second real-time corridor image among the plurality of real-time corridor images corresponding to the final target real-time image group according to the predicted moving route:

3. The building control-based identity determination method according to claim 1, further comprising, before the acquiring the human body image of the agent corresponding to the non-civilized behavior:

4. The building control-based identity determination method according to claim 3, wherein the determining a second non-civilized recognition result according to the elevator operation information includes:

5. An identity determination device based on building management and control, which is characterized by comprising:

the tracking result determining module is used for tracking the track of the agent by utilizing a real-time monitoring image and the key human body characteristics to obtain a tracking result, wherein the real-time monitoring image is obtained by a plurality of monitoring devices in a building management and control system, the real-time monitoring image comprises a plurality of real-time image groups, and the real-time image groups also comprise real-time elevator car images; when the tracking result is that the agent enters a room, triggering a first identity information determining module; when the tracking result is that the agent leaves the building, triggering a second identity information determining module;

the second identity information determining module is used for carrying out historical track backtracking on the agent by utilizing the historical monitoring image and the key human body characteristics to obtain a second door number of a room where the agent historically enters; obtaining identity information of the agent according to the second portal number;

The tracking result determining module is used for tracking the track of the agent by utilizing the real-time monitoring image and the key human body characteristics to obtain a tracking result:

the identity determining device based on building management and control further comprises:

the prompt information generation module is used for:

6. An electronic device, comprising:

at least one processor;

a memory;

at least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application configured to perform the building management based identity determination method of any one of claims 1-4.

7. A computer readable storage medium, having stored thereon a computer program which, when executed in a computer, causes the computer to perform the building management based identity determination method of any of claims 1 to 4.