CN112699328A

CN112699328A - Network point service data processing method, device, system, equipment and storage medium

Info

Publication number: CN112699328A
Application number: CN202011587460.0A
Authority: CN
Inventors: 周波; 周晓; 柏杨
Original assignee: CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp
Priority date: 2020-12-28
Filing date: 2020-12-28
Publication date: 2021-04-23

Abstract

The invention provides a method, a device, a system, equipment and a storage medium for processing network service data, and relates to the technical field of data processing. The method comprises the following steps: the camera collects video stream data of a service network point and transmits the video stream data to the edge server; the edge server carries out cluster statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmits the image file to the Internet of things service platform; the Internet of things service platform acquires service data of a service network point according to the image file and transmits the service data to Internet of things application; and pushing service data to the terminal by the application of the Internet of things. The invention can realize the supervision of the staff service quality of the network, the real-time monitoring and early warning of regional heat, time-sharing people flow and the like of the network, and the monitoring of the security and protection dynamic state of the network.

Description

Network point service data processing method, device, system, equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a system, a device, and a storage medium for processing website service data.

Background

Traditional markets, business halls and the like mostly adopt manual management, the service management quality and the efficiency are low, and the requirements of users on diversified and personalized services cannot be met. In recent years, with the development and deepening of the internet and financial technologies, people propose a mode of realizing intelligent network services based on video stream real-time analysis and internet of things technology and assisting management and control operation of markets and business halls.

For example, in the solution of the website passenger flow statistics, the client information can be acquired by capturing pictures with a camera to perform face recognition, so that the client type recognition and the website flow statistics are realized. Or, in the user behavior analysis scheme of the intelligent network point, the operation state of the user on the equipment can be acquired through the intelligent terminal embedded point of the network point. Alternatively, it is also possible to realize passenger flow statistics for public service facilities such as shopping malls and communities.

However, the above-mentioned prior art has at least the following problems: 1) the quality of service of the staff of the network can not be monitored; 2) the regional heating power, time-interval people flow and the like of the network points cannot be monitored and early warned in real time; 3) the security dynamic of the network points cannot be monitored; 4) data information or operation reports of multi-dimensional security, operation and maintenance, staff service and the like are not formed, management and control of the network are inconvenient, and the requirements of network efficiency enhancement and income increase for intelligent transformation cannot be met.

Disclosure of Invention

Based on the problems in the prior art, embodiments of the present invention provide a method, an apparatus, a system, a device, and a storage medium for processing website service data.

In a first aspect, an embodiment of the present invention provides a method for processing website service data, where the method is applied to a website service system, and the website service system includes: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal; the method comprises the following steps: the camera collects video stream data of a service network point and transmits the video stream data to the edge server; the edge server carries out cluster statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmits the image file to the Internet of things service platform; the Internet of things service platform acquires service data of the service network points according to the image file and transmits the service data to the Internet of things application; and the application of the Internet of things pushes the service data to the terminal.

Optionally, the performing, by the edge server, cluster statistics on the video stream data to obtain an image file corresponding to each target person in the video stream data includes: the edge server reads the video stream data into a frame image; the edge server extracts an image containing a portrait in the frame image; and the edge server performs cluster statistics on the images containing the figures, clusters the images corresponding to the same target figure into groups, and obtains an image file corresponding to each target figure.

Optionally, after the edge server extracts an image containing a portrait from the frame image, the method further includes: and the edge server deletes abnormal images in the image containing the portrait.

Optionally, the terminal comprises a management terminal; the internet of things service platform acquires the service data of the service network according to the image file, and the method comprises the following steps: the Internet of things service platform acquires network operation data, network employee service data and regional network analysis data of the service network according to the image file; the pushing of the service data to the terminal by the application of the internet of things comprises the following steps: and the Internet of things application pushes the network point operation data, the network point staff service data and the regional network point analysis data to the management terminal.

Optionally, the terminal comprises an employee terminal; the internet of things service platform acquires the service data of the service network according to the image file, and the method comprises the following steps: the Internet of things service platform acquires visiting customer information of the service network according to the image file; the pushing of the service data to the terminal by the application of the internet of things comprises the following steps: and the Internet of things application pushes the visiting customer information to the employee terminal.

Optionally, the terminal comprises a security terminal; the internet of things service platform acquires the service data of the service network according to the image file, and the method comprises the following steps: the Internet of things service platform acquires security early warning information of the service network points according to the image file; the pushing of the service data to the terminal by the application of the internet of things comprises the following steps: and the Internet of things application pushes the security early warning information to the security terminal.

Optionally, the clustering the images containing the figures by the edge server, clustering the images corresponding to the same target person into groups, and obtaining an image file corresponding to each target person includes: the edge server identifies a target person in an image containing a portrait to obtain identification information of the target person in the image; the identification information includes: gender, age, emotional and behavioral abnormalities; and the edge server performs cluster statistics, clusters the images corresponding to the same target character into groups to obtain an image file corresponding to each target character, and retains the identification information of each target character in the corresponding image file.

Optionally, the recognizing, by the edge server, a target person in an image including a portrait to obtain recognition information of the target person in the image includes: and the edge server adopts a face recognition algorithm to recognize the target person in the image containing the portrait according to the characteristic point information of the face so as to obtain the recognition information of the target person in the image.

Optionally, the recognizing, by the edge server, a target person in an image including a portrait to obtain recognition information of the target person in the image includes: and the edge server adopts a human body recognition algorithm to recognize the target person in the image containing the portrait according to the clothing and the body type characteristic point information of the portrait, so as to obtain the recognition information of the target person in the image.

Optionally, the method further comprises: the edge server acquires coordinate information of a target person in an image containing a portrait at the service network; and the edge server marks the coordinate information of the target person in the image at the service network point for each frame of image containing the portrait.

The invention can realize the supervision of the staff service quality of the network, the real-time monitoring and early warning of regional heat, time-sharing people flow and the like of the network, and the monitoring of the security and protection dynamic state of the network.

For example, the invention can be applied to the aspects of banks in the fields of website customer classification, identification, intelligent distribution, customer behavior analysis, product planning, accurate marketing, compliance management and the like; customer requirements can be identified on the aspect of customers, and services can be handled quickly; and in the aspect of security, the control of unmanned fortification within 24 hours is realized through intelligent recognition and early warning. By means of digital operation, the efficiency and the income of the operation management of the network nodes are increased.

In a second aspect, an embodiment of the present invention provides a device for processing website service data, where the device is applied to an edge server; the device comprises a transceiving unit and a processing unit; the transceiving unit and the processing unit cooperate to implement the steps executed by the edge server in the mesh point service data processing method according to the first aspect.

In a third aspect, an embodiment of the present invention further provides a device for processing website service data, where the device is applied to a service platform of the internet of things; the device comprises a transceiving unit and a processing unit; the receiving and sending unit and the processing unit cooperate to implement the steps executed by the internet of things service platform in the website service data processing method according to the first aspect.

In a fourth aspect, an embodiment of the present invention provides a website service system, where the website service system includes: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal; the camera is used for collecting video stream data of a service network point and transmitting the video stream data to the edge server; the edge server is used for carrying out cluster statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmitting the image file to the Internet of things service platform; the Internet of things service platform is used for acquiring service data of the service network points according to the image file and transmitting the service data to the Internet of things application; the Internet of things application is used for pushing the service data to the terminal.

In a fifth aspect, an embodiment of the present invention provides an electronic device, including: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device is operated, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps executed by the service platform of the internet of things, the steps executed by the edge server, and the steps executed by the application of the internet of things in the method according to the first aspect.

In a sixth aspect, an embodiment of the present invention provides a storage medium, where the storage medium stores thereon a computer program, and the computer program is executed by a processor to perform the steps performed by the service platform of the internet of things, the steps performed by the edge server, or the steps performed by the application of the internet of things in the method according to the first aspect.

The beneficial effects described in the second to sixth aspects above can be referred to the first aspect, and are not described herein again.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic flow chart illustrating a network node service data processing method according to an embodiment of the present invention;

fig. 2 is another schematic flow chart of a network point service data processing method provided by an embodiment of the present invention;

fig. 3 is another schematic flow chart of a network point service data processing method provided by an embodiment of the present invention;

fig. 4 is a schematic diagram illustrating an architecture of a website service system provided by an embodiment of the present invention;

fig. 5 is a schematic flowchart illustrating a network point service data processing method according to an embodiment of the present invention;

FIG. 6 is a schematic processing flow diagram of an edge server according to an embodiment of the present invention;

fig. 7 is a schematic diagram illustrating a flow of a full congestion event according to an embodiment of the present invention;

fig. 8 is a schematic diagram illustrating a flow of an area congestion event provided by an embodiment of the present invention;

FIG. 9 is a schematic flow chart of an unattended event provided by an embodiment of the invention;

FIG. 10 is a schematic diagram illustrating a flow of a customer exception event provided by an embodiment of the present invention;

fig. 11 shows a schematic structural diagram of an electronic device provided in an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it should be understood that the drawings in the present invention are for illustrative and descriptive purposes only and are not used to limit the scope of the present invention. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this disclosure illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the direction of this summary, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments of the present invention are only some embodiments of the present invention, and not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the term "comprising" will be used in the embodiments of the invention to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features. It should also be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. In the description of the present invention, it should also be noted that the terms "first", "second", "third", and the like are used for distinguishing the description, and are not intended to indicate or imply relative importance.

In this background, an embodiment of the present invention provides a method for processing website service data, where the method is applied to a website service system, and the website service system includes: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal.

Fig. 1 is a schematic flow chart illustrating a network node service data processing method according to an embodiment of the present invention.

As shown in fig. 1, the method includes:

s101, the camera collects video stream data of a service network point and transmits the video stream data to the edge server.

S102, the edge server performs clustering statistics on the video stream data to obtain image files corresponding to each target character in the video stream data, and transmits the image files to the Internet of things service platform.

Fig. 2 is another schematic flow chart of a network point service data processing method according to an embodiment of the present invention.

Optionally, as shown in fig. 2, the performing, by the edge server, cluster statistics on the video stream data to obtain an image file corresponding to each target person in the video stream data includes:

s201, the edge server reads the video stream data into a frame image.

S202, the edge server extracts the image containing the portrait in the frame image.

S203, the edge server deletes abnormal images in the image containing the portrait.

S204, the edge server carries out cluster statistics on the images containing the figures, clusters the images corresponding to the same target person into groups, and obtains an image file corresponding to each target person.

Fig. 3 is another schematic flow chart of a network point service data processing method according to an embodiment of the present invention.

Optionally, as shown in fig. 3, the clustering the images containing the portrait by the edge server, and clustering the images corresponding to the same target person into groups to obtain an image file corresponding to each target person includes:

s301, the edge server identifies the target person in the image containing the portrait to obtain identification information of the target person in the image.

Wherein the identification information includes: gender, age, emotional abnormalities, and behavioral abnormalities.

S302, the edge server carries out cluster statistics, clusters the images corresponding to the same target person into groups to obtain an image file corresponding to each target person, and retains the identification information of each target person in the corresponding image file.

In some embodiments, the identifying the target person in the image containing the portrait by the edge server to obtain the identification information of the target person in the image includes: and the edge server adopts a face recognition algorithm to recognize the target person in the image containing the portrait according to the characteristic point information of the face so as to obtain the recognition information of the target person in the image.

In some other embodiments, the identifying the target person in the image containing the portrait by the edge server to obtain the identification information of the target person in the image includes: the edge server adopts a human body recognition algorithm to recognize the target person in the image containing the portrait according to the clothing and the body type characteristic point information of the portrait, and the recognition information of the target person in the image is obtained.

Optionally, the method further comprises: the edge server acquires coordinate information of a target person in an image containing a portrait at a service network; the edge server marks the coordinate information of the target person in the image containing the portrait for each frame at the service network point.

S103, the service platform of the Internet of things acquires service data of the service network points according to the image files and transmits the service data to the application of the Internet of things.

And S104, pushing service data to the terminal by the application of the Internet of things.

In some embodiments, the terminal comprises a management terminal; the internet of things service platform acquires service data of a service network according to the image file, and the method comprises the following steps: the Internet of things service platform acquires network operation data, network employee service data and regional network analysis data of a service network according to the image file. The pushing of service data to the terminal by the application of the internet of things comprises the following steps: the application of the Internet of things pushes network operation data, network employee service data and regional network analysis data to the management terminal.

In some other embodiments, the terminal further comprises an employee terminal; the internet of things service platform acquires service data of a service network according to the image file, and the method comprises the following steps: and the service platform of the Internet of things acquires the visiting customer information of the service network according to the image file. The pushing of service data to the terminal by the application of the internet of things comprises the following steps: and the application of the Internet of things pushes visiting client information to the employee terminal.

In still other embodiments, the terminal further comprises a security terminal; the internet of things service platform acquires service data of a service network according to the image file, and the method comprises the following steps: and the Internet of things service platform acquires security early warning information of the service network points according to the image file. The pushing of service data to the terminal by the application of the internet of things comprises the following steps: and the application of the Internet of things pushes security early warning information to the security terminal.

The following description will be made more specifically by taking the service network as a banking network.

Fig. 4 is a schematic diagram illustrating an architecture of a website service system according to an embodiment of the present invention.

As shown in fig. 4, the system includes a camera, an edge server, an internet of things service platform, an internet of things application, and a terminal. Wherein, the camera: the method is characterized in that the method is deployed to off-line physical mesh points, one mesh point is provided with a plurality of cameras, the mesh point can be divided into different areas, and a single camera or a plurality of cameras can be matched with a certain mesh point area through the arrangement mode of the cameras. The edge server: and the data information reported by the edge server belongs to the network when the edge server is deployed to the off-line physical network. The service platform of the Internet of things comprises: providing edge computing service, and carrying out data analysis by edge computing; the service platform of the Internet of things further provides a function of connecting the application of the Internet of things and the terminal. The application of the Internet of things comprises the following steps: the terminal is connected to the Internet of things platform and belongs to the terminal under the application of the Internet of things. The terminal: the system comprises a communication device (such as a mobile phone) which is connected to an internet of things service platform and belongs to one or more internet of things applications, and the communication device comprises a software and hardware terminal capable of receiving data, such as a website management platform installed on a PC (personal computer) terminal, an APP which can be operated by an employee through a mobile phone or a PAD (PAD), and a short message for receiving an abnormal alarm and a telephone.

Fig. 5 is a schematic flowchart illustrating a network node service data processing method according to an embodiment of the present invention. As shown in fig. 5, the specific process is as follows:

step 1: and collecting video stream data of the service network point through the camera.

Step 2: the camera transmits the video stream data to the edge server in real time.

And step 3: the edge server carries out real-time clustering statistics on the video stream files according to an algorithm; and clustering into groups, and uploading image information marked with time, gender, age, camera ID and track coordinates to an Internet of things platform.

Fig. 6 is a schematic processing flow diagram of an edge server according to an embodiment of the present invention. As shown in fig. 6, wherein step 3 comprises:

3.1, reading video stream data, and reading the video stream into a frame image; and intercepting the frame image as reserving the time node and the camera ID according to the video stream information.

3.2, extracting the pictures containing the portrait, and deleting the pictures with unqualified picture quality (such as pictures which cannot be identified by people, such as the portrait is too fuzzy and has no portrait); meanwhile, according to the camera ID and the position of the portrait in the picture, the geographic coordinate of the portrait at the physical website is calculated, and the picture is continuously assigned with the track coordinate (the camera ID is the position of the area corresponding to the website; the coordinate of the person in the area is calculated according to the position of the person on the picture, and the geographic coordinate information of the person at the actual website is calculated according to the coordinate information).

3.3, according to an algorithm, identifying personnel of the obtained image file, and processing the identified information: gender, age, emotional anomalies and behavioral anomalies are retained in the corresponding image files; giving face characteristic value, human body characteristic value, gender attribute and age attribute to the person, and outputting a unique characteristic code faceID of the person: .

Algorithm 1: face recognition algorithm: according to the characteristic point information of the face, image files of the same person can be identified as face clusters, and structural information of the gender and the age of the face is judged; at the same time, a portrait whose facial expression is angry can be identified and marked as a potential emotional anomaly.

And 2, algorithm: human body recognition algorithm: firstly, clustering image files of a human body identified as the same person into groups according to the clothing and body type characteristic point information of the portrait; secondly, through a human body recognition algorithm, a portrait with abnormal travel can be recognized, for example: and (4) bumping into walls, falling into the ground and other abnormal behaviors, and marking the portrait as a potential abnormal behavior.

3.4, clustering photos that the algorithm considers to be the same person into groups.

And 4, step 4: and the edge computing service of the Internet of things platform performs further real-time analysis on the clustered image files, such as identity recognition, passenger flow analysis, abnormal events, regional heating power, employee service response and the like.

It should be noted that, the modules involved in the real-time passenger flow information analysis provided in the embodiment of the present invention are relatively independent and logically decoupled, and thus, may be arbitrarily combined or further split according to the implemented functions.

Taking intelligent analysis of passenger flow at a bank outlet as an example, fig. 7 shows a schematic flow diagram of a full-scale crowded event provided by an embodiment of the present invention. As shown in fig. 7, the flow of the full congestion event in the edge computing service is as follows:

1) and the IOT edge computing service receives the kafka atom data sent by the edge server, stores the track data and then enters an analysis process.

2) Inquiring the time of the last appearance of the personnel by the camera: the properties of the network points, which can be provided with cameras at the inlet and the outlet, are an entrance camera and an exit camera; the event type of the person entering and exiting the network can be judged according to the attribute of the camera.

3) If the last occurrence of a person is more than 1 minute, this information is tagged into the atomic data.

4) By the properties of the camera: and the entering camera and the leaving camera judge the event type of the visitor entering and leaving the network.

5) And if the client is off-site, reporting the client off-site event.

6) If the entry is the entrance, the personnel comparison and filing process is carried out.

6.1) comparing with a personnel file database of the edge computing service, inquiring whether personnel exist, if so, confirming personnel identities (such as staff, VIP customers, white list customers, black list-such as escape personnel and lost people), historical visiting records and other files, and updating the visiting records of the personnel. (for the personnel file database of the passenger flow service search is a general default temporary passenger flow database, namely a database in the latest period of time, the default setting retains 30 days of passenger flow data; and can also be set as a permanent passenger flow database according to the requirement).

6.2) if the personnel file database of the edge computing service has no identity information of corresponding personnel, or the visit time of the personnel exceeds 30 days, calling the face recognition service in the row for further identity recognition, and updating the information returned by the face recognition service database to the personnel file database of the edge computing service: if the person exists in the face recognition result, updating the visit record of the person; if the databases do not have the identity information of the portrait, the portrait is identified as a newly added visitor of the website, and the newly added personnel file information is brought into a personnel file database of the edge computing service (the personnel is identified as secondary access and non-newly added customers after arriving at the website within 30 days next time); and reporting the client admission event, such as: and the VIP customer is reminded of the presence.

And (3) real-time data analysis: and calculating the pedestrian volume of the current website in real time according to the client admission event and the client departure event, and reporting the website congestion event if the pedestrian volume exceeds a threshold value.

Taking intelligent analysis of passenger flow at a bank outlet as an example, fig. 8 shows a schematic flow chart of an area congestion event provided by the embodiment of the present invention. As shown in fig. 8, in the flow of the area congestion event in the edge computing service, the number of people in the area reported by the area camera is obtained after the deduplication processing, and if the number of people in the area reported by the area camera exceeds a certain threshold, the area congestion event is reported.

Taking intelligent analysis of passenger flow at a bank outlet as an example, fig. 9 shows a schematic flow diagram of an unattended event provided by an embodiment of the present invention. As shown in fig. 9, the flow of unattended events in the edge computing service is as follows:

by inquiring the ID of the staff of the website and the ID of the corresponding work area camera in the atom database, whether the staff is on duty or not can be confirmed. The unattended event may be set as a timed query task, for example: and setting a system to inquire whether the staff is on duty or not once in half an hour, and reporting an unattended event if the staff is not on duty.

Taking intelligent analysis of customer flow at a bank outlet as an example, fig. 10 shows a schematic flow chart of a customer abnormal event provided by the embodiment of the present invention. As shown in fig. 10, the flow of customer exceptional events in the edge computing service is as follows:

the atomic data returned by the edge server are marked with potential emotion abnormality, potential behavior abnormality, track coordinates, time nodes and the like of the client, and abnormal events of the client can be analyzed through algorithm and assigned data:

emotional abnormality: if the marked customer potential emotional anomaly (such as anger) exists in the atom database, the emotional anomaly is identified when a certain time threshold value is exceeded by the edge calculation.

And (4) abnormal behaviors: if the behavior of a client such as falling to the ground, hitting a wall, smashing a gun and the like is marked in an atom database, the behavior is identified as abnormal; secondly, according to the track coordinates and time nodes of the clients in the sub-database, if the following calculation is carried out: the residence time of the client in one visit exceeds a certain threshold value; or the customer does not stay in the designated area after arriving, but directly goes to other areas to stay; a behavioral anomaly is identified.

Taking intelligent analysis of passenger flow at a bank outlet as an example, the service response event flow in the edge computing service is as follows:

the logic of the service response event judgment is as follows: after a client abnormity, an area/whole-field crowding event and an unattended event occur in a corresponding area in charge of network staff, a reminding message is pushed to a staff terminal through an internet of things platform, for example: after the employee smart screen ipad, the employee Bluetooth bracelet and the employee app, whether the employee arrives at the event site within a period of time after receiving the reminder.

Thus, the employee service response is a delay triggering event, a correlation event (associated with a customer abnormal behavior event, a full crowd event, an area crowd event via UID).

Push service response event rules:

aiming at the following events, the staff behaviors after the events are triggered are continuously analyzed, whether the staff has response behaviors or not is judged, and the events are triggered after response conditions are met:

a) an abnormal behavior event of the client, namely whether the staff provides service to the position of the client within a certain time after the reminding is sent out (the distance is within 1.5 meters, and the stay time is more than 30 seconds);

b) congestion event-whether the employee is leading in the congested area within a certain time after the reminder is sent out (stay longer than 30 seconds and move distance within 30 seconds more than 5 meters);

c) a long-time unattended event, namely whether the staff returns to a designated area within a certain time after the reminding is sent out (the designated area is the designated area of the long-time unattended event, and the continuous stay time exceeds a long-time unattended termination timing threshold T2);

the process is similar to the logic module in the above, including: the storage module, the query module, the judgment module, the calculation module and the like are not described in detail herein.

And 5: after the internet of things application receives the website analysis data through the internet of things platform, the analyzed data can be pushed to the terminal according to the type of the terminal; meanwhile, corresponding reminding messages such as people crowding in the area, VIP customer presence and the like can be pushed to the terminal aiming at the abnormal events.

Step 6: after the terminal of the network point analyzes the report/reminding message according to the received data, the corresponding service/management strategy can be adjusted, and the management efficiency and the income of the network point are improved.

Taking the example of a bank outlet, the following 3 types of terminals can be involved:

firstly, a management terminal:

the network management personnel can receive the operation data and the network personnel service data of the network

Network operation data: recording the number of on-site people of the network, visiting rules, staying time, queuing time and the like, forming situation analysis information such as thermodynamic diagrams, trajectory diagrams, queuing lengths (capable of analyzing the client response capability of the network and optimizing the configuration of management resources) and the like at a background of a management end, realizing real-time online of network point data and helping a manager to predict the business peak of the network point/bank; and the manpower resources of the network points are better allocated.

Network staff service data: the region is unattended: whether a worker (the identity of the worker is identified through face identification, clothing and a database) is in a designated work area can be identified, an unattended event is reported to a manager, and the occurrence rate of the unattended event in a website area is reduced;

response time of service personnel: by analyzing a designated area such as a lobby: the track contact ratio of the staff and the visitors can obtain the service response time of the staff in the work area.

Regional dot analysis data: by comprehensively analyzing the situation of a plurality of network points in a large area, the operation efficiency of the area can be examined from a more macroscopic perspective, and intelligent suggestions are provided in the scene of demand decisions such as resource allocation, personnel management and service arrangement of cross-network points, site selection of new network points and the like.

Second, staff terminal

Data reminders related to the on-site website service can be received, such as VIP customer visit, blacklist customer visit, white list customer visit and other customer information, and personalized service can be provided specifically. The wisdom screen that website staff used or staff's cell-phone APP can receive visitor's information and remind, and the example is like: 1VIP accurate marketing: after the VIP client enters the network, the network passenger flow statistical analysis system accurately identifies the high-net-value client, and the background application reminds a hall manager to provide close-fitting customized service so as to realize quick and timely response. As another example, other customer groups market: other customer groups handling the business at the network point can form multi-dimensional user pictures (the rules, ages and sexes such as time to store, frequency to store, stay time to store and the like, and the network point passenger flow intelligent analysis can also open a service system in the line, realize the recommendation of thousands of people and thousands of products and improve the conversion rate of users) based on the monitoring video and big data analysis of the network point camera; the method helps website personnel to identify the possible business requirements of the user in advance; therefore, the service is purposefully provided, and accurate marketing is realized.

Third, security terminal

The security terminal can be divided into 2 types of operation after receiving the prompt issued by the Internet of things platform, wherein the first type is active defense early warning (personnel precaution) for personnel; the second type is that the controlled security equipment facilities perform automatic alarm, close gate inhibition and the like (equipment intelligent security). In the first category, the network point scene is analyzed in real time: for unusual emotions such as persistent anger, and for some potentially safe behaviors such as: when the security personnel is in abnormal loitering, falling into the ground, hitting the wall, gathering people and the like, a reminding message can be issued to the interphone, the Bluetooth bracelet and the like of the security personnel in time, or the Internet of things platform can call a building bank short message to send an early warning short message to the security personnel at a website, so that the security personnel at the site can be reminded to carry out deployment control and early warning. In the second category, aiming at the 7 x 24 hour business ATM scene, the Internet of things platform can issue an instruction to control the security equipment, and can play a role in expanding the range of artificial services: in the time period that the security personnel can not cover in real time, illegal behaviors such as fire, robbery, equipment knocking and smashing and the like are identified and analyzed, and the equipment can perform operations such as real-time alarming, closing (such as entrance guard) and the like.

From the above, the invention can be applied to the aspects of banks in the fields of website customer classification, identification, intelligent distribution, customer behavior analysis, product planning, accurate marketing, compliance management and the like; customer requirements can be identified on the aspect of customers, and services can be handled quickly; and in the aspect of security, the control of unmanned fortification within 24 hours is realized through intelligent recognition and early warning. By means of digital operation, the efficiency and the income of the operation management of the network nodes are increased.

Optionally, some examples apply as follows:

1) VIP accurate marketing:

after the VIP client enters the network, the network camera accurately identifies, and the background application reminds a hall manager to provide close-fitting customized service, so that quick and timely response is realized.

2) Potential customer groups:

aiming at potential customers handling business at an incoming network point, forming a multi-dimensional user portrait based on the analysis of monitoring videos and big data of a network point camera; the method helps website personnel to identify the possible business requirements of the user in advance; therefore, the service is purposefully provided, and accurate marketing is realized.

3) And (3) network operation income increase:

recording the number of people on site, coordinates, visiting rules, queuing time and staying time of the network, forming situation analysis information such as thermodynamic diagrams, trajectory diagrams, high-frequency dynamic line events, staff attendance, service responses and the like at the background, and helping managers to predict the business peak of the network/bank; the manpower resources of the network points are better allocated; by comprehensively analyzing the situation of a plurality of network points in a large area, the operation efficiency of the area can be examined from a more macroscopic perspective, and intelligent suggestions are provided in the scene of demand decisions such as resource allocation, personnel management and service arrangement of cross-network points, site selection of new network points and the like.

4) Ensuring the safety:

aiming at an ATM scene of 7 x 24 hours of business, in a time period which cannot be covered by security personnel in real time, illegal behaviors such as fire, robbery, knocking and smashing equipment and the like are alarmed in real time, so that the effect of expanding the range of manual service can be achieved, the intellectualization of daily job-keeping work of security is facilitated, and the manpower is saved; the management of the power-assisted bank outlets is efficient and risk-controllable. Meanwhile, some potential safety behaviors such as abnormal loitering exist in business halls, security personnel of the network can be reminded in time to deploy control and early warning, management of the network of the bank is assisted, and risk control is achieved.

Based on the method of the foregoing embodiment, an embodiment of the present invention further provides a network point service system, where the network point service system includes: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal; the camera is used for collecting video stream data of a service network point and transmitting the video stream data to the edge server; the edge server is used for carrying out clustering statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmitting the image file to the Internet of things service platform; the Internet of things service platform is used for acquiring service data of a service network point according to the image file and transmitting the service data to Internet of things application; the Internet of things application is used for pushing service data to the terminal.

Based on the method of the foregoing embodiment, an embodiment of the present invention further provides a device for processing website service data, where the device is applied to an edge server; the device comprises a transceiving unit and a processing unit; the transceiving unit and the processing unit cooperate to implement the steps executed by the edge server in the mesh point service data processing method according to the foregoing embodiment.

Optionally, an embodiment of the present invention further provides a device for processing website service data, where the device is applied to a service platform of the internet of things; the device comprises a transceiving unit and a processing unit; the receiving and sending unit and the processing unit are matched to realize steps executed by the internet of things service platform in the website service data processing method according to the foregoing embodiment.

The above-mentioned apparatus can be integrated into a server, a computer, and other devices, and the present invention is not limited herein. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus may refer to the corresponding process of the method described in the foregoing method embodiment, and is not described in detail herein.

It should be understood that the above-described apparatus embodiments are merely exemplary, and that the apparatus and method disclosed in the embodiments of the present invention may be implemented in other ways. For example, the division of the modules into only one logical functional division may be implemented in other ways, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention or parts thereof which substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a processor to execute the steps of all or part of the method according to the embodiments of the present invention. That is, those skilled in the art will appreciate that embodiments of the present invention may be implemented in any form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.

Based on this, the embodiment of the present invention further provides a program product, where the program product may be a storage medium such as a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, and the storage medium may store a computer program, and when the computer program is executed by a processor, the computer program performs the steps performed by the service platform of the internet of things, or the steps performed by the edge server, or the steps performed by the application of the internet of things in the method described in the foregoing embodiment of the method. The specific implementation and technical effects are similar, and are not described herein again.

Optionally, an embodiment of the present invention further provides an electronic device, where the electronic device may be a server, a computer, or a like device, and fig. 11 illustrates a schematic structural diagram of the electronic device provided in the embodiment of the present invention. As shown in fig. 11, the electronic device may include: the internet of things service platform comprises a processor 1101, a storage medium 1102 and a bus 1103, wherein the storage medium 1102 stores machine-readable instructions executable by the processor 1101, when the electronic device runs, the processor 1101 communicates with the storage medium 1102 through the bus 1103, and the processor 1101 executes the machine-readable instructions to execute steps executed by the internet of things service platform, steps executed by the edge server, or steps executed by the internet of things application in the method described in the foregoing embodiment. The specific implementation and technical effects are similar, and are not described herein again.

For ease of illustration, only one processor is described in the above electronic device. However, it should be noted that in some embodiments, the electronic device in the present invention may further include multiple processors, and thus, the steps performed by one processor described in the present invention may also be performed by multiple processors in combination or individually.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the present invention shall be covered thereby. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A network point service data processing method is applied to a network point service system, and the network point service system comprises: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal; the method comprises the following steps:

the camera collects video stream data of a service network point and transmits the video stream data to the edge server;

the edge server carries out cluster statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmits the image file to the Internet of things service platform;

the Internet of things service platform acquires service data of the service network points according to the image file and transmits the service data to the Internet of things application;

and the application of the Internet of things pushes the service data to the terminal.

2. The method of claim 1, wherein the clustering the video stream data by the edge server to obtain an image file corresponding to each target person in the video stream data comprises:

the edge server reads the video stream data into a frame image;

the edge server extracts an image containing a portrait in the frame image;

and the edge server performs cluster statistics on the images containing the figures, clusters the images corresponding to the same target figure into groups, and obtains an image file corresponding to each target figure.

3. The method of claim 2, wherein after the edge server extracts the image containing the portrait from the frame image, the method further comprises:

and the edge server deletes abnormal images in the image containing the portrait.

4. The method of claim 1, wherein the terminal comprises a management terminal;

the internet of things service platform acquires the service data of the service network according to the image file, and the method comprises the following steps:

the Internet of things service platform acquires network operation data, network employee service data and regional network analysis data of the service network according to the image file;

the pushing of the service data to the terminal by the application of the internet of things comprises the following steps:

and the Internet of things application pushes the network point operation data, the network point staff service data and the regional network point analysis data to the management terminal.

5. The method of claim 1, wherein the terminal comprises an employee terminal;

the Internet of things service platform acquires visiting customer information of the service network according to the image file;

and the Internet of things application pushes the visiting customer information to the employee terminal.

6. The method of claim 1, wherein the terminal comprises a security terminal;

the Internet of things service platform acquires security early warning information of the service network points according to the image file;

and the Internet of things application pushes the security early warning information to the security terminal.

7. The method of claim 2, wherein the edge server performs cluster statistics on the images containing the figures, and clusters the images corresponding to the same target person into groups to obtain an image file corresponding to each target person, comprising:

the edge server identifies a target person in an image containing a portrait to obtain identification information of the target person in the image; the identification information includes: gender, age, emotional and behavioral abnormalities;

and the edge server performs cluster statistics, clusters the images corresponding to the same target character into groups to obtain an image file corresponding to each target character, and retains the identification information of each target character in the corresponding image file.

8. The method of claim 7, wherein the edge server identifying the target person in the image containing the portrait to obtain the identification information of the target person in the image comprises:

and the edge server adopts a face recognition algorithm to recognize the target person in the image containing the portrait according to the characteristic point information of the face so as to obtain the recognition information of the target person in the image.

9. The method of claim 7, wherein the edge server identifying the target person in the image containing the portrait to obtain the identification information of the target person in the image comprises:

and the edge server adopts a human body recognition algorithm to recognize the target person in the image containing the portrait according to the clothing and the body type characteristic point information of the portrait, so as to obtain the recognition information of the target person in the image.

10. The method of claim 7, further comprising:

the edge server acquires coordinate information of a target person in an image containing a portrait at the service network;

and the edge server marks the coordinate information of the target person in the image at the service network point for each frame of image containing the portrait.

11. A network point service data processing device is characterized in that the device is applied to an edge server; the device comprises a transceiving unit and a processing unit;

the transceiving unit and the processing unit cooperate to implement the steps performed by the edge server in the mesh point service data processing method according to any of claims 1 to 10.

12. A network service data processing device is characterized in that the device is applied to an Internet of things service platform; the device comprises a transceiving unit and a processing unit;

the transceiving unit and the processing unit cooperate to implement the steps executed by the internet of things service platform in the website service data processing method according to any one of claims 1 to 10.

13. A website service system, wherein the website service system comprises: the system comprises a camera, an edge server, an Internet of things service platform, an Internet of things application and a terminal;

the camera is used for collecting video stream data of a service network point and transmitting the video stream data to the edge server;

the edge server is used for carrying out cluster statistics on the video stream data to obtain an image file corresponding to each target figure in the video stream data, and transmitting the image file to the Internet of things service platform;

the Internet of things service platform is used for acquiring service data of the service network points according to the image file and transmitting the service data to the Internet of things application;

the Internet of things application is used for pushing the service data to the terminal.

14. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps performed by the service platform of the internet of things, the steps performed by the edge server, or the steps performed by the application of the internet of things in the method of any one of claims 1 to 10.

15. A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps performed by the internet of things service platform, or the steps performed by the edge server, or the steps performed by the internet of things application in the method of any one of claims 1 to 10.