The reminding method and cloud system of waiting-timeout
Technical field
This application involves intelligent monitoring technology fields, the more particularly to reminding method and cloud system of waiting-timeout.
Background technology
The business hall of the industries such as bank, communication provides required respective services for client, and client enters business hall and takes row
It needs just handle related service after waiting for a period of time after team's number, long for client's stand-by period, customer action is abnormal
The problems such as, the method for service of existing business hall staff is incomplete, can not be carried for client's stand-by period long situation
For hommization and the service of diversification.
Invention content
The embodiment of the present application proposes the reminding method and cloud system of waiting-timeout, to solve to work in existing business hall
In, client's stand-by period is long and business hall staff does not have the technical issues of corresponding perfect method of service.
In one aspect, the embodiment of the present application provides a kind of reminding method of waiting-timeout, including:
Obtain video image information;
Determine the waiting time that personnel are preset in the video image information;
When the waiting time of the default personnel being more than preset duration, the waiting-timeout letter of the default personnel is sent
Breath.
On the other hand, the embodiment of the present application provides a kind of prompt cloud system of waiting-timeout, including:
Picture pick-up device, for acquiring video image information;
Arithmetic server, for obtaining video image information;And
Determine the waiting time that personnel are preset in the video image information;And
When the waiting time of the default personnel being more than preset duration, the waiting-timeout letter of the default personnel is sent
Breath.
On the other hand, the embodiment of the present application provides a kind of electronic equipment, and the electronic equipment includes:
Transceiver, memory, one or more processors;And
One or more modules, one or more of modules are stored in the memory, and are configured to by institute
One or more processors execution is stated, one or more of modules include the finger for executing each step in the above method
It enables.
On the other hand, the embodiment of the present application provides a kind of computer program production being used in combination with electronic equipment
Product, the computer program product include computer-readable storage medium and are embedded in computer program mechanism therein, institute
It includes the instruction for executing each step in the above method to state computer program mechanism.
It has the beneficial effect that:
In the present embodiment, arithmetic server determines the video figure according to the collected video image information of picture pick-up device
Waiting time as presetting personnel in information sends described pre- when the waiting time of the default personnel being more than preset duration
If the waiting-timeout information of personnel, so that staff can provide more people according to waiting-timeout information to presetting personnel accordingly
Property and diversification service, to effectively promoted staff service quality.
Description of the drawings
The specific embodiment of the application is described below with reference to accompanying drawings, wherein:
Fig. 1 is the method schematic that waiting-timeout prompts in the embodiment of the present application one;
Fig. 2 is the method flow schematic diagram that waiting-timeout prompts in the embodiment of the present application one;
Fig. 3 is the cloud system structure chart that waiting-timeout prompts in the embodiment of the present application two;
Fig. 4 is the structural schematic diagram of electronic equipment in the embodiment of the present application three.
Specific implementation mode
Below by way of specific example, the essence for embodiment technical solution that the present invention is furture elucidated.
In order to which the technical solution and advantage that make the application are more clearly understood, below in conjunction with attached drawing to the exemplary of the application
Embodiment is described in more detail, it is clear that and described embodiment is only a part of the embodiment of the application, rather than
The exhaustion of all embodiments.And in the absence of conflict, the feature in the embodiment and embodiment in this explanation can be mutual
It is combined.
Inventor notices during invention:
When client enter the industries such as bank, communication business hall take need to wait for a period of time after queue number after ability
Related service is handled, but it is long for client's stand-by period, the problems such as being impatient of, the service side of existing business hall work
Formula can not provide for client and pacify relevant service with mood.
Against the above deficiency/and it is based on this, the embodiment of the present application is proposed in client during holding areas waits for, and is led to
The waiting time of client in monitoring video is spent, impatient behavior and the business hall work such as walk up and down, pass in and out repeatedly occurs in client
The situation in holding areas is appeared in as personnel, distinguishes staff and client, and be based on convolutional neural networks (CNN:
Convolutional Neural Network) human testing and human body identify (Person Re-ID again:Person Re-
Identification) in the holding areas of stroke analysis business hall client waiting time, identify client's abnormal behaviour so that system
Accuracy higher between timing, identify client's complexity abnormal behaviour it is more adaptable, and without client carry additionally recognize
Equipment is demonstrate,proved, to effectively promote the service quality of business hall staff.
For the ease of the implementation of the application, following Examples illustrates.
Embodiment 1
Fig. 1 shows the method schematic that waiting-timeout prompts in the embodiment of the present application one, and Fig. 2 shows the application implementations
The method flow schematic diagram that waiting-timeout prompts in example one, as shown in Fig. 2, as shown in Figure 1 and Figure 2, this method includes:
Step 101:Obtain video image information.
Step 102:Determine the waiting time that personnel are preset in the video image information.
Step 103:When the waiting time of the default personnel being more than preset duration, the time-out of the default personnel is sent
Outstanding message.
In a step 101, picture pick-up device acquires the video image in the predeterminable area of business hall in real time, and video image is sent out
Arithmetic server is given, arithmetic server obtains video image information according to video image, and video image information includes preset areas
Personal information in domain.
In a step 102, arithmetic server judges whether the personnel occurred in video image are default personnel, if pre-
If personnel, then each unique ID of default personnel assignment is characterized as according to human region, and count the waiting time of each ID;If
It is not default personnel, then is not processed.
In step 103, after reaching the access time interval set, waiting time longest, Huo Zhechao are obtained
The information such as the human region sectional drawing of the default personnel of preset duration and corresponding waiting time are crossed, and are sent to dispatch server.
In implementation, the executive agent of above-mentioned steps can be cloud server, and the dispatch server in cloud server will
Waiting time longest, or default personnel more than preset duration human region sectional drawing and the information point such as corresponding waiting time
It is sent to the hand-held mobile terminal of business hall staff (for example, lobby manager), after staff receives information, according to default people
The human region characteristic image of member finds corresponding default personnel in holding areas, and provides corresponding service.
In the present embodiment, the default personnel are client, determine the waiting time of client in the video image information,
Including:
According to the human region feature of personnel in the video image information, identify whether the personnel are client;
If identifying, the personnel are client, it is determined that the waiting time of the client.
In the present embodiment, the personnel include staff and client, identify whether the personnel are client, including:
The human region feature of the personnel is searched from preset staff's feature database;
If the human region feature of the personnel is in preset staff's feature database, it is determined that the personnel are work
Personnel;
If the human region feature of the personnel is not in preset staff's feature database, it is determined that the personnel are visitor
Family.
In the present embodiment, the waiting time of the determination client, including:
If the human region feature of the client is not in preset client feature library, by the human region of the client
Feature is stored in preset client feature library, and the waiting time that the client is arranged is 0;
If the human region feature of the client is in preset client feature library, when updating the waiting of the client
It is long.
In implementation, by extracting the human region feature of all personnel in video image, client is determined whether, if visitor
Family then updates client feature library and client's waiting time.Specially:
1) position in video image where each personnel is judged whether in the holding areas of delimitation, if in holding areas
Interior, then the Person Re-ID algorithms based on CNN extract the human region feature of each personnel;
2) according to the human region feature of each personnel, being searched in staff's feature database and client feature library respectively is
No there are similar human region features (for example, similarity reaches given threshold Th), if a certain personnel are not in staff
It being found in feature database and client feature library, then it is assumed that the personnel are client, its human region feature is stored in client feature library, and
Unique ID numbers are distributed for it, are indicated with n, meanwhile, the initial time of holding areas is entered using current time T as the client
Sn, Sn=T, and the current waiting time Wn that the client is arranged is 0;If a certain personnel find in staff's feature database,
It is not processed;If being found in client feature library, updates human region of the client in client feature library and be characterized as currently
Human region feature, and the client corresponding waiting time Wn, Wn=T- are updated according to initial time Sn and current time T
Sn;
3) sequence according to waiting time Wn from big to small, when to comprising human region feature, initial time Sn and waiting
All Customer IDs of the information such as long Wn are ranked up.
In the present embodiment, the waiting time of the default personnel is more than preset duration, further includes:The default personnel go out
In the last frame video image of the present video image information.
In implementation, waiting time, which is more than the client of preset duration, should meet but be not limited to the following conditions:
1) there are the clients in the video image of present frame;
2) waiting time longest, or be more than preset duration (for example, preset duration is set as 10 minutes).
In the present embodiment, the waiting-timeout information includes the abnormal behavior information of the default personnel, the transmission
Before the waiting-timeout information of the default personnel, further include:Determine that the default human behavior is abnormal.
In the present embodiment, the determination default human behavior is abnormal, including:
If the history coordinate of the default personnel appears in preset multiple regions, it is determined that the default human behavior
It is abnormal.
In implementation, if arithmetic server judges the personnel occurred in video image as client, count the client etc.
It waits for duration, identifies the behavior of the client, and by waiting time is longer and/or the human region sectional drawing of the client of abnormal behavior, right
The waiting time and/or abnormal behavior information answered are sent to dispatch server together.Specially:
If 1) arithmetic server judges the human region feature of a certain personnel not in preset staff's feature database,
The personnel occurred in video image are judged as client, using current time T as initial time Sn, the Sn=T of the client, and are set
Set the client current waiting time Wn be 0, and record the client human region feature central point current time T's
Coordinate is (xT, yT);If arithmetic server judges the human region feature of a certain personnel in preset client feature library, more
New human region of the client in client feature library is characterized as current human's provincial characteristics, updates the client in client feature library
In coordinate be current time T coordinate (xT, yT), and according to initial time Sn and current time T to update the client corresponding
Waiting time Wn, Wn=T-Sn;
2) according to the waiting time of client and history coordinate, at least one of following abnormal behaviour is judged whether:
A) time-out delay (for example, waiting time is more than preset duration) is determined whether according to waiting time;
B) since history coordinate can draw out the action trail of client, client is judged according to the history coordinate of client
Whether abnormal behavior, for example, there is the holding areas that repeatedly comes in and goes out in the history Grid Track of client, or situations such as move back and forth;
Or human region feature is identified based on CNN, determine the behavior of client's current time with the presence or absence of abnormal.Preferably,
Abnormal behaviour can predefine a variety of abnormal behaviour patterns according to actual conditions, specifically, moved towards according to the track of history coordinate,
Situations such as scope of activities, identifies the behavior pattern of client, for example, by the way that multiple regions are arranged, if the action trail of client is long
Between repeatedly cross over multiple regions, it is determined that there are abnormal behaviors by the client.
If there are it is above-mentioned time-out be detained, abnormal behaviour, by the human region sectional drawing of the client, corresponding waiting time and
The information such as abnormal behaviour pattern are sent to dispatch server.
In the present embodiment, the determination default human behavior is abnormal, including:
Using human body critical point detection model, the human body that the default personnel are obtained according to the video image information is crucial
Point information;
If the human body key point information of the default personnel matches with preset abnormal behaviour template, it is determined that described pre-
If human behavior is abnormal.
In implementation, using the deep learning model based on human body critical point detection, preset according to video image information
The human body key point information of personnel carries out the human body key point information of obtained default personnel and preset abnormal behaviour template
Matching, if successful match, it is determined that default human behavior is abnormal, and identifies the abnormal behaviour corresponding to default personnel.
The application is described in detail the embodiment of the present application 1 by taking concrete scene as an example.
The embodiment of the present application application range includes but not limited to the business handling of bank bussiness hall, with the industry of bank bussiness hall
For business is handled, detailed process is as follows:
Step 201:Picture pick-up device obtains the video image in the holding areas of business hall in real time, and video image is sent to
Arithmetic server.
Step 202:Arithmetic server is using all personnel occurred in object detection method identification video image.
Step 203:The human region feature for extracting all personnel, utilizes preset staff's feature database and client characteristics
Library determines whether client, and client feature library, statistics client's waiting time and identification customer action are then updated if client.
Step 204:Step 202 and step 203 are repeated, after reaching the access time interval set, obtain etc.
Wait for human region sectional drawing figure, corresponding waiting time and the abnormal behavior of the client of duration longest (alternatively, being more than preset duration)
Information, and it is sent to dispatch server.
Step 205:Dispatch server divides the human region sectional drawing of client, corresponding waiting time and abnormal behavior information
Issue the hand-held mobile terminal of business hall staff.
Step 206:The hand-held mobile terminal of business hall staff shows the human region sectional drawing of client, corresponding waiting
Whether duration and abnormal behavior information are staff according to human region sectional drawing artificial judgment, if staff, then should
The human region sectional drawing of staff is added to staff's feature database described in step 203, to avoid by the staff
It is misidentified as client again, if not staff, then find according to the human region sectional drawing in holding areas corresponding
Client, and provide corresponding service according to its corresponding waiting time and abnormal behavior information.
Embodiment 2
Based on same inventive concept, a kind of prompt cloud system of waiting-timeout is additionally provided in the embodiment of the present application, due to
The principle that these equipment solve the problems, such as is similar to a kind of reminding method of waiting-timeout, therefore the implementation of these equipment may refer to
The implementation of method, overlaps will not be repeated.
Fig. 3 shows the cloud system structure chart that waiting-timeout prompts in the embodiment of the present application two, as shown in figure 3, time-out etc.
The prompt cloud system 300 waited for may include:Picture pick-up device 301, arithmetic server 302, dispatch server 303 and mobile terminal
304。
Picture pick-up device 301, for acquiring video image information.
Arithmetic server 302, for obtaining video image information;And
Determine the waiting time that personnel are preset in the video image information;And
When the waiting time of the default personnel being more than preset duration, the waiting-timeout information of the default personnel is sent
To mobile terminal 304.
In the present embodiment, the default personnel are client, determine the waiting time of client in the video image information,
Including:
According to the human region feature of personnel in the video image information, identify whether the personnel are client;
If identifying, the personnel are client, it is determined that the waiting time of the client.
In the present embodiment, the personnel include staff and client, identify whether the personnel are client, including:
The human region feature of the personnel is searched from preset staff's feature database;
If the human region feature of the personnel is in preset staff's feature database, it is determined that the personnel are work
Personnel;
If the human region feature of the personnel is not in preset staff's feature database, it is determined that the personnel are visitor
Family.
In the present embodiment, the waiting time of the determination client, including:
If the human region feature of the client is not in preset client feature library, by the human region of the client
Feature is stored in preset client feature library, and the waiting time that the client is arranged is 0;
If the human region feature of the client is in preset client feature library, when updating the waiting of the client
It is long.
In the present embodiment, the arithmetic server 302 further includes:The default personnel appear in the video image letter
In the last frame video image of breath.
In the present embodiment, the waiting-timeout information includes the abnormal behavior information of the default personnel, the algorithm
Server 302 further includes:Determine that the default human behavior is abnormal.
In the present embodiment, the determination default human behavior is abnormal, including:
If the history coordinate of the default personnel appears in preset multiple regions, it is determined that the default human behavior
It is abnormal.
In the present embodiment, the determination default human behavior is abnormal, including:
Using human body critical point detection model, the human body that the default personnel are obtained according to the video image information is crucial
Point information;
If the human body key point information of the default personnel matches with preset abnormal behaviour template, it is determined that described pre-
If human behavior is abnormal.
Embodiment 3
Based on same inventive concept, a kind of electronic equipment is additionally provided in the embodiment of the present application, due to its principle and one kind
The reminding method of waiting-timeout is similar, therefore its implementation may refer to the implementation of method, and overlaps will not be repeated.
Fig. 4 shows the structural schematic diagram of electronic equipment in the embodiment of the present application three, as shown in figure 4, the electronic equipment
Including:Transceiver 401, memory 402, one or more processors 403;And one or more modules, it is one or
Multiple modules are stored in the memory, and are configured to be executed by one or more of processors, it is one or
Multiple modules include the instruction for executing each step in any above method.
Embodiment 4
Based on same inventive concept, the embodiment of the present application also provides a kind of computer journeys being used in combination with electronic equipment
Sequence product implements the implementation that may refer to method, weight since its principle is similar to a kind of reminding method of waiting-timeout
Multiple place repeats no more.The computer program product includes computer-readable storage medium and is embedded in computer therein
Procedure mechanism, the computer program mechanism include the instruction for executing each step in any above method.
For convenience of description, each section of apparatus described above is divided into various modules with function and describes respectively.Certainly, exist
Implement each module or the function of unit can be realized in same or multiple softwares or hardware when the application.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of the application has been described, created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.