CN112201046A

CN112201046A - Illegal data identification method and device and electronic equipment

Info

Publication number: CN112201046A
Application number: CN202011070362.XA
Authority: CN
Inventors: 王洵
Original assignee: Wuhan Zhongke Tongda High New Technology Co Ltd
Current assignee: Wuhan Zhongke Tongda High New Technology Co Ltd
Priority date: 2020-09-30
Filing date: 2020-09-30
Publication date: 2021-01-08
Anticipated expiration: 2040-09-30
Also published as: CN112201046B

Abstract

The application provides an illegal data identification method, a device and electronic equipment, based on the method, a data server firstly receives an http traffic data calling request sent by a traffic police terminal, converts the http traffic data calling request into an sip traffic data calling request, synchronously processing http state identification and sip state identification corresponding to the two types of requests, sending the sip traffic data calling request to a target camera through a 5G base station, then, the response content is called according to the returned sip traffic data, the identification content of the sip state identification and the http state identification is synchronously updated, when the identification content is that the call request is completed, generating a corresponding http traffic data call response and returning the http traffic data call response to the traffic police terminal, then receiving the traffic data returned by the front-end camera and sending the traffic data to the identification equipment for illegal data identification, and illegal data are returned to the traffic police terminal, and the whole calling process can be completed by the traffic police terminal only on a web browser or a platform.

Description

Illegal data identification method and device and electronic equipment

Technical Field

The application relates to the field of intelligent traffic, in particular to an illegal data identification method and device and electronic equipment.

Background

When illegal behaviors in traffic data are identified, a data calling request needs to be initiated for a front-end camera, when most security cameras on the market call the traffic data, in order to simplify the data calling request process, traffic data calling signaling of the front-end camera is usually packaged into signaling in an SDK (Software Development Kit) format, and then an SDK is called by a traffic police system and is developed and manufactured by an external manufacturer, and the traffic data shot by the front-end camera can be acquired by personnel in a non-traffic police system, namely, some potential safety hazards exist in the data calling mode.

Therefore, the existing illegal data identification method has the technical problem of low safety, and needs to be improved.

Content of application

The embodiment of the application provides a method for identifying illegal data by scheduling an external neural network based on an http protocol, which is used for improving the safety of a front-end camera traffic data calling process.

In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:

the application provides a method for identifying illegal data, is applicable to wisdom traffic system, wisdom traffic system includes front end camera, data server, identification equipment, 5G basic station and traffic police terminal, it has the neural network model to operate in the identification equipment, the front end camera is connected based on the sip agreement 5G basic station, the traffic police terminal is connected based on the http protocol data server with identification equipment, identification equipment is connected based on the http protocol data server, illegal data identification method is applied to data server, illegal data identification method includes:

receiving an http traffic data calling request sent by the traffic police terminal based on an http protocol, wherein the http traffic data calling request carries a terminal identifier, an identification device identifier and a target camera identifier, generating an sip traffic data calling request corresponding to the http traffic data calling request according to the target camera identifier, generating an http state identifier corresponding to the http traffic data calling request, synchronizing the identifier contents of the http state identifier and the sip state identifier in real time, and the identifier contents comprise a calling request completion state;

according to the target camera identification, a target camera and a target 5G base station corresponding to the target camera are determined, long connection between the target camera and the target 5G base station is determined, the sip traffic data calling request is sent to the target 5G base station through the long connection, so that the target 5G base station is controlled to send the sip traffic data calling request to the target camera through a sip private line based on a sip protocol, and a sip processing signaling returned by the target camera through the sip private line based on the sip protocol is received;

receiving the sip processing signaling returned by the target 5G base station through the long connection, generating an sip traffic data calling response according to the sip processing signaling, and synchronously updating the identification contents of the sip state identification and the http state identification according to the content of the sip traffic data calling response;

when the identification content of the http state identification is that the calling request is completed, generating an http traffic data calling response corresponding to the http state identification, and returning the http traffic data calling response to the traffic police terminal based on an http protocol according to the terminal identification;

receiving traffic data sent by the target camera, and sending the traffic data to the identification equipment according to the identification equipment;

and receiving illegal data which is identified from the traffic data by the identification equipment based on the neural network model, and returning the illegal data to the traffic police terminal based on an http protocol.

Simultaneously, this application embodiment still provides a device for recognizing illegal data, is applicable to wisdom traffic system, wisdom traffic system includes front end camera, data server, identification equipment, 5G basic station and traffic police terminal, it has the neural network model to operate in the identification equipment, the front end camera is connected based on the sip agreement 5G basic station, the traffic police terminal is connected based on the http agreement data server with identification equipment, identification equipment is connected based on the http agreement data server, illegal data recognition device sets up in the data server, illegal data recognition device includes:

the first synchronization module is used for receiving an http traffic data calling request sent by the traffic police terminal based on an http protocol, wherein the http traffic data calling request carries a terminal identifier, an identification device identifier and a target camera identifier, generating an sip traffic data calling request corresponding to the http traffic data calling request according to the target camera identifier, generating an http state identifier corresponding to the http traffic data calling request, synchronizing the identifier contents of the http state identifier and the sip state identifier in real time, and the identifier contents comprise a calling request completion state;

the first sending module is used for determining a target camera and a target 5G base station corresponding to the target camera according to the target camera identification, determining long connection between the target camera and the target 5G base station, sending the sip traffic data calling request to the target 5G base station through the long connection, controlling the target 5G base station to send the sip traffic data calling request to the target camera through a sip private line based on a sip protocol, and receiving a sip processing signaling returned by the target camera through the sip private line based on the sip protocol;

a second synchronization module, configured to receive the sip processing signaling returned by the target 5G base station through the long connection, generate an sip traffic data call response according to the sip processing signaling, and synchronously update the identifier contents of the sip state identifier and the http state identifier according to the content of the sip traffic data call response;

the first returning module is used for generating an http traffic data calling response corresponding to the http state identifier when the identifier content of the http state identifier is that the calling request is completed, and returning the http traffic data calling response to the traffic police terminal based on an http protocol according to the terminal identifier;

the second sending module is used for receiving the traffic data sent by the target camera and sending the traffic data to the identification equipment according to the identification equipment identifier;

and the second returning module is used for receiving the illegal data which is identified by the identification equipment from the traffic data based on the neural network model and returning the illegal data to the traffic police terminal based on an http protocol.

The application also provides an electronic device comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform any one of the operations of the illegal data identification method.

Has the advantages that: the application provides a front-end camera traffic data calling method, a device and electronic equipment, based on the method, firstly receiving a http traffic data calling request sent by a traffic police terminal based on an http protocol, converting the http traffic data calling request into a sip traffic data calling request which can be identified by a front-end camera, converting the sip traffic data calling response returned by the front-end camera into an http traffic data calling response, returning the http traffic data calling response to the traffic police terminal, receiving the traffic data returned by the front-end camera, sending the traffic data to the identification equipment for illegal data identification, and returning the illegal data to the traffic police terminal, wherein the whole calling process can be completed by the traffic police terminal only on a web browser or a platform without calling special SDK software, thereby ensuring the safety, and in the protocol conversion process, the generated sip traffic data calling response can be converted into the http traffic data calling response in time by synchronizing the identification contents of a sip state identification and the http state identification, the speed of returning the response is improved. In addition, the information transmission is carried out through the 5G base station, the speed is high, and the convenience of traffic data acquisition is improved. The illegal data are identified by adopting the trained neural network model, the identification efficiency is improved compared with manual identification, the identification process is independent of the data server, when the system needs to be upgraded, only the identification equipment needs to be upgraded, and the data server with large data volume does not need to be upgraded integrally, so that the upgrade efficiency is improved, and the cost of data maintenance is also reduced.

Drawings

The technical solution and other advantages of the present application will become apparent from the detailed description of the embodiments of the present application with reference to the accompanying drawings.

Fig. 1 is a schematic view of a scenario of an illegal data identification system according to an embodiment of the present application.

Fig. 2 is a schematic flowchart of an illegal data identification method according to an embodiment of the present application.

Fig. 3 is a schematic diagram of a first model of a process from sending a traffic data call request to receiving a traffic data call response in an embodiment of the present application.

Fig. 4 is a schematic diagram of a second model of a process from sending a traffic data call request to receiving a traffic data call response in the embodiment of the present application.

Fig. 5 is a schematic diagram of a third model of a process from sending a traffic data call request to receiving a traffic data call response in the embodiment of the present application.

Fig. 6 is a schematic view of a first page of a traffic police terminal in the illegal data identification method according to the embodiment of the present application.

Fig. 7 is a schematic diagram of a second page of a traffic police terminal in the illegal data identification method according to the embodiment of the present application.

Fig. 8 is a schematic structural diagram of an illegal data identification device according to an embodiment of the present application.

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the embodiment of the present application, the intelligent traffic system is an integrated network system that is constructed by comprehensively applying technologies such as audio/video monitoring, communication, computer network, system integration, etc. and has functions of information acquisition, transmission, exchange, control, display, storage, processing, etc. and can realize interconnection, intercommunication, and mutual control between different devices and systems in the traffic field for the purpose of maintaining national security and social stability and preventing and fighting against illegal criminal activities. The intelligent traffic system comprises a front-end camera, a data server, identification equipment, a 5G base station and a traffic police terminal, wherein a neural network model runs in the identification equipment, the front-end camera is connected with the 5G base station based on an sip protocol, the traffic police terminal is connected with the data server and the identification equipment based on an http protocol, and the identification equipment is connected with the data server based on the http protocol.

In the embodiment of the application, the front-end camera refers to a camera which is installed in a monitoring site in an intelligent traffic system and is used for information acquisition, encoding, processing, storage, transmission and safety control.

In the embodiment of the present application, the traffic police terminal refers to a client device registered and authorized by the intelligent transportation system and having an operation requirement on data and devices in the system, and may specifically include a client for traffic police and a client for developers.

In the embodiment of the application, the identification device is a device which operates with a neural network model and can identify illegal data by calling the neural network model, the device and the data server are mutually independent, and the identification device is only required to be independently updated when the system is updated, and the data server is not required to be comprehensively updated.

In the embodiment of the present application, the neural network model refers to an artificial neural network structure having a hierarchical structure, which includes an input layer, an output layer, and an intermediate layer (also called a hidden layer). In a neural network model, the number of nodes of an input layer and an output layer is often fixed, an intermediate layer can be freely designated, the topology and the arrows in a neural network structure diagram represent the flow direction of data in a prediction process, the key in the structure diagram is the connection among neurons, and each connecting line corresponds to a different weight (the value of which is called a weight), which is obtained by training. The neural network model is trained for multiple times based on the preprocessed training samples, and classification and identification of illegal data can be realized. After the traffic data are input into the trained neural network model, the traffic data enter the intermediate layer after feature extraction is carried out on the input layer, a series of complex operations such as convolution, pooling, regression processing and the like are carried out on the intermediate layer, various illegal behaviors can be identified, and corresponding illegal data are output by the output layer.

In the embodiment of the present application, the traffic data refers to data, such as vehicle information, pedestrian information, and operation parameters of vehicles and pedestrians, in a monitoring location, which are captured by a front-end camera, and is usually visual data such as video or image, where the vehicle information may include a brand, a model, a color, license plate number information, and the like of the vehicle, and the pedestrian information may include a gender, a height, clothing, a hairstyle, and the like of the pedestrian.

The embodiment of the application provides an illegal data identification method and device and electronic equipment. The illegal data identification device can be integrated in electronic equipment, and the electronic equipment can be a server or a terminal and other equipment.

Referring to fig. 1, fig. 1 is a schematic view of a scene of an illegal data identification system provided in an embodiment of the present application, where the system may include terminals and servers, and the terminals, the servers, and the terminals and the servers are connected and communicated through the internet formed by various gateways, and the like, where the application scene includes a traffic police terminal 11, a data server 12, a front-end camera 13, an identification device 14, and a 5G base station 15; wherein:

the traffic police terminal 11 and the recognition device 14 include, but are not limited to, a tablet Computer, a notebook Computer, a Personal Computer (PC), a mini processing box, or other devices;

the data server 12 comprises a local server and/or a remote server and the like;

the front-end camera 13 comprises video and image acquisition equipment arranged on a monitoring site;

the 5G base station 15 includes a radio transceiver station for information transfer with terminals through a communication switching center in a certain radio coverage area.

The traffic police terminal 11, the data server 12, the front-end camera 13, the identification device 14 and the 5G base station 15 are located in a wireless network or a wired network, the front-end camera 13 is connected with the 5G base station 15 based on an sip protocol, the traffic police terminal 11 is connected with the data server 12 and the identification device 14 based on an http protocol, the identification device 14 is connected with the data server 12 based on the http protocol, and the data server 12 is connected with the 5G base station 15 based on the 5G protocol, so that data interaction among the five is realized, wherein:

the data server 12 receives an http traffic data call request sent by the traffic police terminal 11 based on an http protocol, generates a corresponding sip traffic data call request, synchronizes the identification contents of an http state identification and an sip state identification corresponding to the traffic police terminal 11 in real time, selects a target camera from the front-end camera 13 based on the sip protocol, sends the sip traffic data call request to the target camera through the 5G base station 15, receives an sip traffic data call response returned by the target camera based on the sip protocol through the 5G base station 15, synchronously updates the identification contents of the sip state identification and the http state identification according to the content of the sip traffic data call response, generates an http traffic data call response corresponding to the http state identification when the identification content of the http state identification is the call request is completed, returns the http traffic data call response to the traffic police terminal 11 based on the http protocol, and receives traffic data sent by the target camera, and according to the identification of the identification device, the traffic data is sent to the identification device 14, the illegal data identified from the traffic data by the identification device 14 based on the neural network model is received, and the illegal data is returned to the traffic police terminal 11, so that the traffic police terminal 11 can identify the illegal data.

It should be noted that the system scenario diagram shown in fig. 1 is only an example, and the server and the scenario described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not form a limitation on the technical solution provided in the embodiment of the present application, and as a person having ordinary skill in the art knows, with the evolution of the system and the occurrence of a new service scenario, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems. The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.

Referring to fig. 2, fig. 2 is a schematic flowchart of a method for identifying illegal data according to an embodiment of the present application, where the method includes:

s201: the method comprises the steps of receiving an http traffic data calling request sent by a traffic police terminal based on an http protocol, wherein the http traffic data calling request carries a terminal identifier, an identification device identifier and a target camera identifier, generating an sip traffic data calling request corresponding to the http traffic data calling request according to the target camera identifier, generating an http state identifier corresponding to the http traffic data calling request, synchronizing the identification content of the http state identifier and the sip state identifier in real time, and the identification content comprises a calling request completion state.

The traffic police terminal can be used by internal personnel of the public security system and also can be used by developers who have access rights and data calls. The traffic police terminal sends an http traffic data calling request to the data server based on an http protocol, when the request is sent, a sender can be an internal person of a public security system and is used for obtaining traffic data of a monitored place to judge and process illegal behaviors, and the sender can also be a developer with access authority for video calling and is used for sending the traffic data calling request of the front-end camera and debugging calling parameters and related equipment according to traffic data calling response. The http traffic data calling request can be sent through a video monitoring platform which is developed independently, or can be sent directly through a web browser, and the corresponding traffic data calling response is received by a data server.

The http traffic data calling request carries an identification device identifier and a target camera identifier, wherein the identification device identifier comprises an IP address and a port of the identification device, and the target camera identifier comprises an ID of the target camera. After receiving the http traffic data calling request, determining a target camera from the front-end camera cluster information stored in the data server according to a target camera identification carried in the http traffic data calling request, acquiring an access address of the target camera, and generating a request head in the sip traffic data calling request according to the access address. And then, converting each calling command in the http traffic data calling request into a calling command under an sip protocol, generating the calling command into a message body in the sip traffic data calling request, and combining a request header and the message body to generate a corresponding sip traffic data calling request.

After the sip traffic data calling request corresponding to the http traffic data calling request is generated, corresponding http state identification and sip state identification are respectively generated for the http traffic data calling request and the sip traffic data calling request, and identification contents of the two state identifications comprise the starting time of the traffic data calling request and the data calling request completion state. And synchronizing the identification contents of the http state identification and the sip state identification, namely, when the identification content of one of the http state identification and the sip state identification changes at any moment, the identification content of the other one of the http state identification and the sip state identification changes in the same way.

S202: and determining a target camera and a target 5G base station corresponding to the target camera according to the target camera identification, determining long connection between the target camera and the target 5G base station, sending an sip traffic data calling request to the target 5G base station through the long connection, so as to control the target 5G base station to send the sip traffic data calling request to the target camera through an sip private line based on an sip protocol, and receiving an sip processing signaling returned by the target camera through the sip private line based on the sip protocol.

In a 5G scene, all front-end cameras in a certain area are correspondingly connected with a 5G base station, a one-to-many connection relation is formed between the 5G base station and the front-end cameras, and the connection relations are stored in a data server, so that a target camera corresponding to a target camera identifier can be determined according to the target camera identifier, and further the target camera can be determined to which 5G base station the target camera is connected, and the 5G base station is taken as the target 5G base station. And for all 5G base stations, long connection is established between the data server and the target 5G base station, after the target 5G base station is determined, the long connection between the data server and the target 5G base station can be found, and then the sip traffic data calling request is sent to the target 5G base station through the long connection.

The long connection between the data server and the target 5G base station is transmitted based on a 5G protocol, and the sip traffic data calling request is a request under the sip protocol, so that during transmission, the sip traffic data calling request is firstly packaged into a first packaging packet and then sent to the target 5G base station through the long connection, and the target 5G base station unpacks the first packaging packet into the sip traffic data calling request.

The target 5G base station is connected with the front-end cameras by a sip protocol, and each front-end camera is connected by a sip dedicated line to ensure data security, so that after the target 5G base station receives a sip traffic data calling request, the data server controls the target 5G base station to send the sip traffic data calling request to the target cameras through the sip dedicated lines based on the sip protocol, and after the target cameras process the sip traffic data calling request, the target cameras return sip processing signaling through the sip dedicated lines.

S203: and receiving an sip processing signaling returned by the target 5G base station through the long connection, generating an sip traffic data calling response according to the sip processing signaling, and synchronously updating the identification contents of the sip state identification and the http state identification according to the content of the sip traffic data calling response.

And after receiving the sip processing signaling, the target 5G base station returns the sip processing signaling to the data server through the long connection, and when returning, the target 5G base station encapsulates the sip processing signaling into a second encapsulation packet supporting the 5G protocol, and then unpacks the second encapsulation packet after receiving the sip processing signaling, so as to obtain the sip processing signaling.

And the data server generates an sip traffic data call response according to the sip processing signaling, and then synchronously updates the identification contents of the sip state identification and the http state identification according to the content of the sip traffic data call response. And when the content of the sip traffic data calling response is that the calling is completed, updating the identification content of the sip state identification and the http state identification to be that the calling request is completed.

S204: and when the identification content of the http state identification is that the calling request is completed, generating an http traffic data calling response corresponding to the http state identification, and returning the http traffic data calling response to the traffic police terminal based on an http protocol according to the terminal identification.

After the identification content of the sip state identification and the http state identification is updated, if the identification content of the http state identification is that the call request is completed, the data server generates a corresponding http traffic data call response, and the response content of the http traffic data call response is the same as the response content of the sip traffic data call response. And after generating the http traffic data call response, determining a traffic police terminal sending the http traffic data call request according to the terminal identifier, establishing an http session between the data server and the traffic police terminal, and returning the http traffic data call response to the traffic police terminal.

S205: and receiving traffic data sent by the target camera, and sending the traffic data to the identification equipment according to the identification of the identification equipment.

When the call response is that the call is completed, the data server receives traffic data sent by the target camera, the traffic data is usually a media bare stream shot by the front-end camera, before the traffic data is sent, the traffic data needs to be encapsulated to form a data packet, for example, the data packet can be packaged into an RTP data packet, then the data packet is sent to the data server, and after the data packet is received by the data server, the data packet is sent to the identification device based on an http protocol according to the identification device identifier.

S206: and receiving illegal data which is identified from the traffic data by the identification equipment based on the neural network model, and returning the illegal data to the traffic police terminal based on the http protocol.

And after receiving the traffic data, the identification equipment unpacks the traffic data, preprocesses the unpacked traffic data, such as removing some non-video data, interference data and the like, inputs the traffic data into a pre-trained neural network model, detects and tracks pedestrian targets and vehicle targets in each frame of image of the shot video, and determines the behavior track of the pedestrian targets and the vehicle targets. Then, the neural network model identifies the detected vehicle target to obtain attributes such as brand, vehicle type, license plate number, vehicle color and the like, and identifies the detected pedestrian target to obtain attributes such as gender, height, clothing, hairstyle and the like. After the detection, the attribute of the detected target may be stored in the identification device or the data server, so as to be used for performing a subsequent search query on the detected illegal target, thereby providing a basis for punishment. Then, the neural network model identifies the traffic signs of the road where the target is located, such as traffic signal lamps, traffic marking lines, speed limit boards and the like, and finally judges whether the traffic illegal behaviors exist in the target or not according to the detected information of the position where the target is located, the target behavior track, the target attribute, the traffic signs of the road where the target is located and the like. And after the traffic violation behaviors are identified, generating corresponding violation data, and returning the corresponding violation data to the traffic police terminal based on the http protocol according to the terminal identifier. And the traffic police terminal determines whether to punish the illegal target based on relevant legal provisions according to the illegal data.

It can be known from the above method that the illegal data recognition method provided in the embodiments of the present application, first, receives a http traffic data call request sent by a traffic police terminal based on an http protocol, converts the http traffic data call request into a sip traffic data call request recognizable by a front-end camera, converts a sip traffic data call response returned by the front-end camera into an http traffic data call response, returns the http traffic data call response to the traffic police terminal, receives traffic data returned by the front-end camera and sends the http traffic data call response to a recognition device for illegal data recognition, and returns illegal data to the traffic police terminal according to a terminal identifier, the whole call process can be completed by the traffic police terminal only on a web browser or a platform, and does not need to call dedicated SDK software, thereby ensuring security, and in the protocol conversion process, the generated sip traffic data call response can be timely converted into an http traffic data call response by synchronizing the identifier contents of the sip state identifier and the http state identifier, the speed of returning the response is improved. In addition, the information transmission is carried out through the 5G base station, the speed is high, and the convenience of traffic data acquisition is improved. The illegal data are identified by adopting the trained neural network model, the identification efficiency is improved compared with manual identification, the identification process is independent of the data server, when the system needs to be upgraded, only the identification equipment needs to be upgraded, and the data server with large data volume does not need to be upgraded integrally, so that the upgrade efficiency is improved, and the cost of data maintenance is also reduced.

As shown in fig. 3, the framework for sending a traffic data call request to receive a traffic data call response is divided into several modules, and the data server includes http-side processing logic 22, message synchronizer 23, and sip-side processing logic 24. After receiving an http traffic data call request 21 sent by a data server based on an http protocol, the traffic police terminal firstly sends the http traffic data call request to an http side processing logic 22 for processing, and then sends the http traffic data call request to a message synchronizer 23 through the http side processing logic 22; the message synchronizer 23 converts the http traffic data call request into an sip traffic data call request, generates an http state identifier for the http traffic data call request, generates an sip state identifier for the sip traffic data call request, synchronizes the identifier contents of the http state identifier and the sip state identifier, and then sends the sip traffic data call request to the sip side processing logic 24 for processing; after the processing by the sip-side processing logic 24 is completed, the sip traffic data invoking request is sent to the target 5G base station 25 through the long connection between the target 5G base stations 25, the target 5G base station 25 sends the sip traffic data invoking request to the target camera 26, and receives the sip processing signaling returned by the target camera 26 to the target 5G base station 25, the target 5G base station 25 returns the sip processing signaling to the sip side processing logic 24 based on the long connection, the sip side processing logic 24 generates a sip traffic data call response according to the returned sip processing signaling and sends the sip traffic data call response to the message synchronizer 23, the message synchronizer 23 calls the responding content according to the sip traffic data, synchronously updates the identification content of the http state identification and the sip state identification, when the identification content of the http state identification is that the call request is completed, generating an http traffic data call response and sending the http traffic data call response to the http side processing logic 22; the http side processing logic 22 returns an http traffic data call response 27 to the traffic police terminal, and the traffic police terminal determines the processing state of the traffic data call request according to the http traffic data call response 27.

As shown in fig. 4 and fig. 5, the http side processing logic 22 includes an http service module 221, a request parser 222, a validity judgment 223, an http message manager 224, and an http timer status notification queue 225, and the sip side processing logic 24 includes an sip call manager 241, an sip message manager 242, a user agent client 243, and a user agent server 244, and the method for recognizing illegal data according to the present application is specifically described below with reference to fig. 3 to fig. 5.

And the traffic police terminal sends an http traffic data calling request 21 to the http side processing logic 22, wherein the http traffic data calling request 21 carries the identification equipment identifier and the target camera identifier. The data server determines that the target camera is specifically located at the xx road junction of the xx region xx according to the target camera identification so as to send an http traffic data calling request 21 to the target camera, and then determines to which terminal the received traffic data calling response should be specifically sent according to the terminal identification. The identification device identification comprises an IP address and a port of the identification device, the data server determines which identification device the traffic data sent by the subsequent target camera should be forwarded to according to the identification device identification, and the identification device identifies the traffic violation type, the traffic violation time, the traffic violation vehicle or pedestrian information and other data according to the traffic behaviors of the vehicles or pedestrians at the intersection in the traffic data and returns the data to the traffic police terminal for further processing.

In the http side processing logic 22, the http traffic data invoking request 21 is received by the http service module 221, the http service module 221 includes an http gateway, and then the http traffic data invoking request 21 is transferred to the request parser 222. The request parser 222 parses each command parameter in the http traffic data invoking request 21, and then puts the http traffic data invoking request 21 into the http message manager 224. The http message manager 224 continuously processes the internal message cache while sending the newly incoming http traffic data call request 21 to the message synchronizer 23.

In an embodiment, before the step of placing the http traffic data invocation request 21 into the http message manager 224, the validity judgment 23 is further performed on the parsed http traffic data invocation request 21, which specifically includes: carrying out logic judgment on the http traffic data calling request 21 based on the traffic data calling request effective parameter set; and if the http traffic data call request 21 is legal, caching the http traffic data call request 21 into the http message manager 224, and if the http traffic data call request 21 is illegal, directly returning a termination request result to the traffic police terminal, wherein the termination request result is represented as an http traffic data call response 27 at the traffic police terminal. When the traffic police terminal sends out the http traffic data call request 21, the http traffic data call request 21 is sent out in a form of inputting a website on a web browser or a platform, the http traffic data call request 21 comprises parameters such as a target camera identifier and a call command, if the input of each identifier or call command is wrong, subsequent processing logic is affected, therefore, after analysis, firstly, logic judgment is carried out on the http traffic data call request 21 based on a traffic data call request effective parameter set, the traffic data call request effective parameter set comprises types of effective parameters, specific parameter values, an arrangement sequence of each parameter and the like, if the parameters are legal, the next step is carried out, the http traffic data call request 21 is cached in the http message manager 224, if the parameters are illegal, a termination request result is directly returned to the traffic police terminal, specific error types can be further displayed, if the input is an invalid parameter or a corresponding target camera cannot be found and the like, so that the http traffic data call request 21 can be adjusted and input again by the traffic police terminal.

In one embodiment, after the step of caching the http traffic data invocation request 21 to the http message manager 224, the method further comprises: judging whether the http traffic data calling request 21 has the same content as the http traffic data calling request entering in the previous preset time period or not; if the content is the same, the http traffic data invocation request 21 is removed from the http message manager 224, and if the content is different, the http traffic data invocation request 21 is sent to the message synchronizer 23. After the traffic police terminal sends the http traffic data call request 21, if no traffic data call response is received within an expected time, one or more refresh operations are usually performed, each refresh operation re-sends one traffic data call request 21, the content of each sent traffic data call request 21 is the same, and if the data server processes each request, resource waste is caused, so after the http traffic data call request 21 is cached in the http message manager 224, the http message manager 224 numbers the incoming requests in time sequence, such as No. 1, No. 2, No. 3, and the like, and each time a new http traffic data call request 21 is entered, the incoming requests are re-checked and judged.

Assuming that the number of the newly entered http traffic data invocation request 21 is n, the http message manager 224 first determines whether an n-1 th request enters within a preset time period from the time of the n-th request entering, where the preset time period may be set according to the sending behavior of the majority of request senders, for example, if the majority of request senders do not receive a response within 2 seconds after sending the request, the request senders may start to initiate a request again, and then 2 seconds may be used as the preset time period. If it is detected that no request n-1 is entered within the previous preset time period, the newly entered http traffic data call request may be directly sent to the message synchronizer 23. If an n-1 request is detected to enter in the previous preset time period, content duplication judgment is carried out on the n-1 request and the n request, when the contents are the same, the n request is a repeated request, the newly entered http traffic data calling request is removed from the http message manager 224, the n-1 request is continuously processed, when the contents are different, the n request is a new request, the newly entered http traffic data calling request is sent to the message synchronizer 23, and after the n-1 request is processed, the n request is continuously processed.

After receiving the http traffic data call request 21, the message synchronizer 23 generates an sip traffic data call request corresponding to the http traffic data call request according to the identification of the target camera. The data server stores cluster information of front-end cameras, the front-end cameras registered in the data server are all located in the cluster information, each front-end camera has a unique identifier, a target camera is determined from the cluster information of the front-end cameras according to the identifier of the target camera, an access address of the target camera is obtained, and a request head in a sip traffic data calling request can be generated according to the access address. Then, each call command in the http traffic data call request 21 is converted into a call command under the sip protocol, and then the call command is generated into a message body in the sip traffic data call request, and a request header and the message body are combined to generate a corresponding sip traffic data call request.

The message synchronizer 23 generates an http state identifier for the http traffic data call request 21, generates an sip state identifier for the sip traffic data call request, and synchronizes the http state identifier and the identification content of the sip state identifier in real time, wherein the identification content includes a call request completion state. In the message synchronizer 23, the identification contents of the http state identification and the sip state identification are the same at any moment, and the synchronization operation is realized by a corresponding synchronization program.

For the http traffic data call request 21 newly entering the message synchronizer 23, after the steps of format conversion and identification synchronization are completed, the sip traffic data call request is sent to the sip side processing logic 24, and then the sip side processing logic 24 sends the sip traffic data call request to the target camera corresponding to the target camera identification through the target 5G base station 25 based on the long connection with the target 5G base station 25. After the sending, the message synchronizer 23 will perform detection on the call request, if the sip side processing logic 24 has returned the sip traffic data call response, the message synchronizer 23 will generate a corresponding http traffic data call response, and place the http traffic data call response into the http timer state notification queue 225, the http timer state notification queue 225 notifies the http message manager 224 according to the sequence of the response entering, and the http message manager 224 returns the http traffic data call response 27 to the traffic police terminal, so that the traffic police terminal can obtain the processing result of the call request.

The sip traffic data invoking request is first sent to the sip invoking management 241, and the sip invoking management 241 generates a unique identifier for the sip traffic data invoking request and then caches the unique identifier into the sip message manager 242. Then, the user agent client 243 checks from the sip message manager 242 whether a new invocation request arrives or whether there is an update of the invocation request status, and sends a different request to the target 5G base station 25 according to the check result. When a new sip traffic data calling request arrives at the sip message manager 242, the target camera corresponding to the identifier is determined according to the target camera identifier carried in the sip traffic data calling request, and then the 5G base station to which the target camera is connected is determined, and the 5G base station is used as the target 5G base station 25. For all the 5G base stations, long connection is established between the base stations and the data server, after the target 5G base station 25 is determined, the long connection between the data server and the target 5G base station 25 can be found, and then the sip traffic data calling request is sent to the target 5G base station 25 through the long connection.

In one embodiment, the specific step of sending the sip traffic data invocation request to the target 5G base station 25 includes: caching the sip traffic data call request into the sip message manager 242; encapsulating the sip traffic data call request into a first encapsulation packet; the first encapsulated packet is sent over the long connection to the target 5G base station 25. Because the long connection between the data server and the target 5G base station 25 is based on 5G protocol transmission, and the sip traffic data call request is a request under the sip protocol, the sip traffic data call request is first encapsulated into a first encapsulation packet, and then sent to the target 5G base station 25 through the long connection, and the target 5G base station 25 then unpacks the first encapsulation packet into the sip traffic data call request.

In one embodiment, the specific step of sending the sip traffic data invocation request to the target 5G base station 25 further includes: acquiring a connection period of a target 5G base station 25 and a target camera 26; and in the connection period, sending an sip traffic data calling request to the target 5G base station 25 through the long connection so as to control the target 5G base station 25 to send the sip traffic data calling request to the target camera 26 through the sip private line based on the sip protocol. The target 5G base station 25 and all the front-end cameras within the connection range thereof form a one-to-many relationship, for each front-end camera, the target 5G base station 25 has a connection channel corresponding to the front-end camera, but the connection channels between the target 5G base station 25 and the front-end cameras are not communicated at all times, but are sequentially opened and closed according to a certain sequence, so that for each front-end camera, there is a corresponding connection period, and only in the connection period, the front-end camera and the target 5G base station 25 can realize communication, so that it is necessary to first acquire the connection period between the target 5G base station 25 and the target camera 26, and then in the connection period, control the target 5G base station 25 to send a sip traffic data call request to the target camera 26.

The target 5G base station 25 is connected with the front-end cameras by using an sip protocol, and each front-end camera is connected by using an sip dedicated line to ensure the safety of data, so that after the target 5G base station 25 receives an sip traffic data calling request, the data server controls the target 5G base station 25 to send the sip traffic data calling request to the target camera 26 through the sip dedicated line based on the sip protocol, and after the target camera 26 processes the sip traffic data calling request, the target 5G base station 25 returns an sip processing signaling to the target 5G base station 25 through the sip dedicated line.

And after receiving the sip processing signaling, the target 5G base station returns the sip processing signaling to the sip side processing logic 24 of the data server through long connection, and the sip side processing logic 24 generates a sip traffic data calling response according to the sip processing signaling, and synchronously updates the identification contents of the sip state identification and the http state identification according to the content of the sip traffic data calling response.

In one embodiment, the steps specifically include: receiving a second encapsulation packet returned by the target 5G base station 25 to the sip message manager 242 through the long connection, and unpacking the second encapsulation packet to obtain an sip processing signaling of the target camera 26; updating the identification content of the sip state identification corresponding to the sip traffic data calling request in the sip message manager 242 according to the sip processing signaling; when detecting that the identification content of the sip state identification is that the calling request is completed, generating and returning a sip traffic data calling response to the message synchronizer 23; and according to the content of the sip traffic data call response, synchronously updating the identification content of the sip state identification and the http state identification in the message synchronizer 23.

The sip processing signaling returned by the target camera 26 after processing the sip traffic data invocation request is sent to the sip side processing logic 24 and received by the user agent 244, and the user agent 244 updates the identification content of the sip status identification corresponding to the sip traffic data invocation request in the sip message manager 242 according to the sip processing signaling. Specifically, when the sip processing signaling is 200OK, indicating that the invocation request is completed, the user agent 244 matches the sip traffic data invocation request in the sip message manager 242, and updates the identification content of the corresponding sip status identifier to the invocation request completed.

When detecting that the identification content of the sip state identification is that the call request is completed, generating and returning a sip traffic data call response to the message synchronizer 23, then synchronously updating the identification content of the sip state identification and the http state identification in the message synchronizer 23 according to the content of the sip traffic data call response, and updating the identification content of the sip state identification and the http state identification to be that the call request is completed.

In one embodiment, the steps after returning the sip traffic data invocation response to the message synchronizer 23 include: the sip traffic data invocation request is removed from the sip message manager 242. At this point the invocation request has been processed and a corresponding invocation response has been generated, and thus, removing it from the sip message manager 242 frees up the cache space of the sip message manager 242 to facilitate the sip message manager 242 to re-process other request messages. In addition, after the removal, the data server can store the log related to the sip traffic data call response, classify a plurality of call responses in a certain period of time in the log, for example, classify according to the call request completion time, analyze the request flow with longer completion time, find the reason, facilitate the development personnel to perform BUG positioning and program debugging, and subsequently maintain and upgrade the system.

And when the identification content of the http state identification is that the call request is completed, the message synchronizer 23 generates a call response of the http traffic data with the completed call. And after generating the http traffic data calling response, returning the http traffic data calling response 27 to the traffic police terminal based on the http protocol according to the terminal identifier. The message synchronizer 23 determines which port of which client the call response should be sent to according to the terminal identifier, and then returns the http traffic data call response 27, and the traffic police terminal determines the processing result of the call request according to the content of the http traffic data call response 27.

In one embodiment, the step after returning the http traffic data invocation response 27 to the traffic police terminal includes: the http traffic data invocation request and the sip traffic data invocation request are removed from the message synchronizer 23. After removal, the internal space of the message synchronizer 23 is also released to facilitate the message synchronizer 23 to process other request messages.

After the traffic police terminal obtains the http traffic data call response 27, the target camera 26 packages the shot traffic data and sends the traffic data to the data server, and then the data server sends the packaged traffic data to the identification device according to the identification device IP address and the port in the identification device identifier. After receiving the traffic data, the identification device unpacks the traffic data, preprocesses the unpacked traffic data, such as removing some non-video data, interference data and the like, inputs the traffic data into a pre-trained neural network model, and identifies illegal data by the neural network model.

The neural network model firstly detects and tracks the pedestrian target and the vehicle target in each frame of image of the video and determines the behavior track of the pedestrian target and the vehicle target. In order to reduce the influence of false detection and missed detection, the system can judge that a new target enters only when M continuous frames of the target are detected, and can consider that the target disappears only when N continuous frames of the target are not detected, wherein M and N are positive integers and can be set to different values according to parameters such as the type of the target, the driving speed and the like. Specifically, in the target tracking process, the historical position of each target is recorded, an initial motion trajectory of the target is formed, and the initial motion trajectory of the target is subjected to smooth filtering by adopting a kalman filter, so that a target behavior trajectory is obtained.

Then, the neural network model identifies the detected vehicle target to obtain attributes such as brand, vehicle type, license plate number, vehicle color and the like, and identifies the detected pedestrian target to obtain attributes such as gender, height, clothing, hairstyle and the like. After the detection, the attribute of the detected target may be stored in the identification device or the data server, so as to be used for performing a subsequent search query on the detected illegal target, thereby providing a basis for punishment.

Then, the neural network model identifies the traffic signs of the road where the target is located, such as traffic signal lamps, traffic marking lines, speed limit boards and the like, and then judges whether traffic illegal behaviors exist in the target or not according to the detected information of the position where the target is located, the target behavior track, the target attribute, the traffic signs of the road where the target is located and the like.

For example, when it is recognized that the traffic signal lamp is in a red light state and the traffic marking of the current road includes a stop line, it is determined whether the position of the target exceeds the stop line within 15 meters before and after the stop line, and if so, there is illegal behavior of running the red light. For another example, when the traffic markings of the current road include road type markings, such as pedestrian lanes, motor lanes, and non-motor lanes, and the target attribute is not matched with the type of the current road, illegal road occupation behaviors exist.

After the traffic violation of the target is identified, the identification equipment generates corresponding violation data, the violation data comprises information such as violation time, violation places, violation targets and violation types, and then the violation data is returned to the data server based on the http protocol, and the data server returns the violation data to the traffic police terminal. And the traffic police terminal determines whether to punish the illegal target based on relevant legal provisions according to the illegal data.

In the embodiment of the application, illegal data are identified by using the identification equipment operated with the neural network model, and the identification efficiency of the neural network model is gradually increased after the neural network model is trained for multiple times. When the neural network model is trained, video data shot by a front-end camera needs to be acquired, all features of the video data are artificially labeled, the video data are input into the neural network model as a training sample for training, and the trained neural network model can have corresponding recognition capability when traffic data to be recognized are subsequently input.

In the training sample, the pedestrian target and the vehicle target are artificially labeled, and when traffic data is subsequently input, the trained neural network model can have the capacity of identifying the pedestrian target and the vehicle target. In the training sample, attributes of the pedestrian target and the vehicle target are labeled manually, and the trained neural network model can have the capability of identifying the attributes of the pedestrian target and the vehicle target. In the training sample, different labels are manually carried out on the pixels where the non-traffic marks are located and the pixels where the traffic marks are located, and the corresponding traffic mark types are labeled, so that the trained neural network model can have the capacity of identifying the traffic marks and the corresponding classes thereof. Through the three types of training, the neural network model can identify information such as the position of a target, a target behavior track, target attributes, traffic identification of a road where the target is located and the like according to input traffic data, so that understanding of a road traffic video is completed, and identification of illegal behaviors is achieved. In order to make the recognition effect of the neural network model better, training needs to be performed for enough times so that the recognition accuracy is not lower than a preset value.

It can be known from the above embodiments that the illegal data recognition method of the present application, firstly, receives the http traffic data call request sent by the traffic police terminal based on the http protocol, and converts the http traffic data call request into the sip traffic data call request recognizable by the front camera, converts the sip traffic data call response returned by the front camera into the http traffic data call response, and returns the http traffic data call response to the traffic police terminal, then receives the traffic data returned by the front camera and sends the traffic data to the recognition device for illegal data recognition, and returns the illegal data to the traffic police terminal according to the terminal identifier, the whole call process can be completed by the traffic police terminal only on the web browser or platform, and does not need to call the special SDK software, thereby ensuring the security, and in the protocol conversion process, the generated sip traffic data call response can be timely converted into the http traffic data call response by synchronizing the identifier content of the sip state identifier and the http state identifier, the speed of returning the response is improved. In addition, the information transmission is carried out through the 5G base station, the speed is high, and the convenience of traffic data acquisition is improved. The illegal data are identified by adopting the trained neural network model, the identification efficiency is improved compared with manual identification, the identification process is independent of the data server, when the system needs to be upgraded, only the identification equipment needs to be upgraded, and the data server with large data volume does not need to be upgraded integrally, so that the upgrade efficiency is improved, and the cost of data maintenance is also reduced.

As shown in fig. 6 and 7, in actual operation, the traffic police terminal inputs an http traffic data call request on the input frame 100 of the platform or the web browser shown in fig. 6 and sends the http traffic data call request, after receiving an http traffic data call response, the traffic data sent by the front-end camera is received by the data server, and is sent to the identification device for illegal data identification, and after identification, the illegal data is sent to the data server and is returned to the traffic police terminal, and the traffic police terminal can see, on the first display area 200 of the page shown in fig. 7, that the illegal data "a vehicle with a license plate number xxxxxx does not give way to a pedestrian at the xx intersection", and can also send the corresponding traffic data to the traffic police terminal, and display a video or an image corresponding to the illegal data in the second display area 300 of the page shown in fig. 7, so that the traffic police can confirm the illegal data conveniently.

On the basis of the method described in the foregoing embodiment, the embodiment will be further described from the perspective of an illegal data identification device, please refer to fig. 8, where fig. 8 specifically describes the illegal data identification device provided in the embodiment of the present application, which may include:

a first synchronization module 110, configured to receive an http traffic data call request sent by the traffic police terminal based on an http protocol, where the http traffic data call request carries a terminal identifier, an identification device identifier, and a target camera identifier, generate, according to the target camera identifier, an sip traffic data call request corresponding to the http traffic data call request, and generate an http state identifier corresponding to the http traffic data call request, where the sip state identifier corresponding to the sip traffic data call request synchronizes, identifier contents of the http state identifier and the sip state identifier in real time, where the identifier contents include a call request completion state;

a first sending module 120, configured to determine, according to the target camera identifier, a target camera and a target 5G base station corresponding to the target camera, determine a long connection with the target 5G base station, send the sip traffic data invocation request to the target 5G base station through the long connection, so as to control the target 5G base station to send the sip traffic data invocation request to the target camera through a sip dedicated line based on a sip protocol, and receive a sip processing signaling returned by the target camera through the sip dedicated line based on the sip protocol;

a second synchronization module 130, configured to receive the sip processing signaling returned by the target 5G base station through the long connection, generate an sip traffic data invocation response according to the sip processing signaling, and update the identifier contents of the sip state identifier and the http state identifier synchronously according to the content of the sip traffic data invocation response;

a first returning module 140, configured to generate an http traffic data calling response corresponding to the http state identifier when the identifier content of the http state identifier is that the calling request is completed, and return the http traffic data calling response to the traffic police terminal based on an http protocol according to the terminal identifier;

the second sending module 150 is configured to receive the traffic data sent by the target camera, and send the traffic data to the recognition device according to the recognition device identifier;

and a second returning module 160, configured to receive the illegal data identified by the identification device from the traffic data based on the neural network model, and return the illegal data to the traffic police terminal based on an http protocol.

In an embodiment, the illegal data identification device further includes a logic judgment module, configured to perform logic judgment on the http traffic data call request based on the traffic data call request valid parameter set after the first synchronization module 110 receives the http traffic data call request; and if the http traffic data calling request is legal, caching the http traffic data calling request to an http message manager, and if the http traffic data calling request is illegal, directly returning a termination request result to the traffic police terminal.

In one embodiment, the illegal data identification device further comprises a duplication checking module, wherein after the http traffic data calling request is cached to the http message manager, the duplication checking module is used for judging whether the http traffic data calling request has the same content with the http traffic data calling request entering in the previous preset time period; and if the contents are the same, removing the http traffic data calling request from the http message manager, and if the contents are different, sending the http traffic data calling request to the message synchronizer.

In an embodiment, the first sending module 120 specifically includes:

the caching unit is used for caching the sip traffic data calling request into the sip message manager;

the first encapsulation unit is used for encapsulating the sip traffic data call request into a first encapsulation packet;

and the first sending unit is used for sending the first encapsulating packet to the target 5G base station through the long connection.

In an embodiment, the second synchronization module 130 specifically includes:

a receiving unit, configured to receive a second encapsulation packet returned by the target 5G base station to an sip message manager through the long connection, and unpack the second encapsulation packet to obtain an sip processing signaling of the target camera;

the first updating unit is used for updating the identification content of the sip state identification corresponding to the sip traffic data calling request in the sip message manager according to the sip processing signaling;

the return unit is used for generating and returning a sip traffic data calling response to the message synchronizer when detecting that the identification content of the sip state identification is that the calling request is completed;

and the second updating unit is used for synchronously updating the identification contents of the sip state identification and the http state identification in the message synchronizer according to the content of the sip traffic data call response.

In an embodiment, the second updating unit is configured to update the identification contents of the sip state identifier and the http state identifier synchronously to that the call request is completed according to the content of the sip traffic data call response.

In an embodiment, the first returning module 140 is configured to generate an http traffic data invocation response that the invocation request is completed when the identification content of the http status identifier is that the invocation request is completed.

In an embodiment, the first sending module 120 specifically includes:

the period acquisition unit is used for acquiring the connection period of the target 5G base station and the target camera;

and the second sending unit is used for sending the sip traffic data calling request to the target 5G base station through the long connection in the connection period so as to control the target 5G base station to send the sip traffic data calling request to the target camera through a sip private line based on a sip protocol.

Different from the prior art, the illegal data recognition device provided by the application firstly receives an http traffic data call request sent by a traffic police terminal based on an http protocol, converts the http traffic data call request into an sip traffic data call request which can be recognized by a front-end camera, converts the sip traffic data call response returned by the front-end camera into an http traffic data call response, returns the http traffic data call response to the traffic police terminal, receives traffic data returned by the front-end camera, sends the traffic data to recognition equipment for illegal data recognition, and returns illegal data to the traffic police terminal according to a terminal identifier, the whole call process can be completed by the traffic police terminal on a web browser or a platform without calling special SDK software, so that the safety is ensured, and in the protocol conversion process, the generated sip traffic data call response can be timely converted into an http traffic data call response by synchronizing the identifier content of the sip state identifier and the http state identifier, the speed of returning the response is improved. In addition, the information transmission is carried out through the 5G base station, the speed is high, and the convenience of traffic data acquisition is improved. The illegal data are identified by adopting the trained neural network model, the identification efficiency is improved compared with manual identification, the identification process is independent of the data server, when the system needs to be upgraded, only the identification equipment needs to be upgraded, and the data server with large data volume does not need to be upgraded integrally, so that the upgrade efficiency is improved, and the cost of data maintenance is also reduced.

Accordingly, embodiments of the present application also provide an electronic device, as shown in fig. 9, which may include components such as a radio frequency circuit 901, a memory 902 including one or more computer-readable storage media, an input unit 903, a display unit 904, a sensor 905, an audio circuit 906, a WiFi module 907, a processor 908 including one or more processing cores, and a power supply 909. Those skilled in the art will appreciate that the electronic device architecture shown in fig. 9 does not constitute a limitation of a server and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. Wherein:

the rf circuit 901 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then sends the received downlink information to the one or more processors 908 for processing; in addition, data relating to uplink is transmitted to the base station. The memory 902 may be used to store software programs and modules, and the processor 908 executes various functional applications and data processing by operating the software programs and modules stored in the memory 902. The input unit 903 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

The display unit 904 may be used to display information input by or provided to the user and various graphical user interfaces of the server, which may be made up of graphics, text, icons, video, and any combination thereof.

The electronic device may also include at least one sensor 905, such as light sensors, motion sensors, and other sensors. The audio circuitry 906 includes a speaker that can provide an audio interface between a user and the electronic device.

WiFi belongs to short-distance wireless transmission technology, and the electronic equipment can help a user to send and receive e-mails, browse webpages, access streaming media and the like through the WiFi module 907, and provides wireless broadband internet access for the user. Although fig. 9 shows the WiFi module 907, it is understood that it does not belong to the essential constitution of the electronic device, and may be omitted entirely as needed within the scope not changing the essence of the application.

The processor 908 is a control center of the electronic device, connects various parts of the entire cellular phone using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 902 and calling data stored in the memory 902, thereby performing overall monitoring of the cellular phone.

The electronic device also includes a power supply 909 (e.g., a battery) that provides power to the various components, which may preferably be logically coupled to the processor 908 via a power management system, such that the functions of managing charging, discharging, and power consumption are performed via the power management system.

Although not shown, the electronic device may further include a camera, a bluetooth module, and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 908 in the electronic device loads an executable file corresponding to a process of one or more application programs into the memory 902 according to the following instructions, and the processor 908 executes the application programs stored in the memory 902, so as to implement the following functions:

receiving an http traffic data calling request sent by a traffic police terminal based on an http protocol, wherein the http traffic data calling request carries a terminal identifier, an identification device identifier and a target camera identifier, generating an sip traffic data calling request corresponding to the http traffic data calling request according to the target camera identifier, generating an http state identifier corresponding to the http traffic data calling request, synchronizing the identifier contents of the http state identifier and the sip state identifier in real time, and the identifier contents comprise a calling request completion state; determining a target camera and a target 5G base station corresponding to the target camera according to the target camera identification, determining long connection between the target camera and the target 5G base station, sending a sip traffic data calling request to the target 5G base station through the long connection, so as to control the target 5G base station to send the sip traffic data calling request to the target camera through a sip special line based on a sip protocol, and receiving a sip processing signaling returned by the target camera through the sip special line based on the sip protocol; receiving the sip processing signaling returned by the target 5G base station through long connection, generating an sip traffic data calling response according to the sip processing signaling, calling the response content according to the sip traffic data, and synchronously updating the identification content of the sip state identification and the http state identification; when the identification content of the http state identification is that the calling request is completed, generating an http traffic data calling response corresponding to the http state identification, and returning the http traffic data calling response to the traffic police terminal based on an http protocol according to the terminal identification; receiving traffic data sent by a target camera, and sending the traffic data to identification equipment according to identification equipment identification; and receiving illegal data which is identified from the traffic data by the identification equipment based on the neural network model, and returning the illegal data to the traffic police terminal based on the http protocol.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed description, and are not described herein again.

In an embodiment, the identification device provided by the present application may be used as a node in a blockchain system, and after the traffic data is processed by calling a neural network model, the illegal data is verified, and after the illegal data is verified, the illegal data is stored as a new block in the blockchain, so as to ensure that the illegal data is not tampered.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

The platform product service layer provides basic capability and an implementation framework of typical application, and developers can complete block chain implementation of business logic based on the basic capability and the characteristics of the superposed business. The application service layer provides the application service based on the block chain scheme for the business participants to use.

The method, the device and the electronic device for recognizing the illegal data provided by the embodiment of the application are introduced in detail, a specific example is applied in the text to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the technical scheme and the core idea of the application; those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not depart from the spirit and scope of the present disclosure as defined by the appended claims.

Claims

1. The illegal data identification method is applicable to a smart traffic system, the smart traffic system comprises a front-end camera, a data server, identification equipment, a 5G base station and a traffic police terminal, a neural network model runs in the identification equipment, the front-end camera is connected with the 5G base station based on a sip protocol, the traffic police terminal is connected with the data server and the identification equipment based on an http protocol, the identification equipment is connected with the data server based on the http protocol, the illegal data identification method is applied to the data server, and the illegal data identification method comprises the following steps:

2. The illegal data identification method according to claim 1, further comprising, before the step of generating a sip traffic data call request corresponding to the http traffic data call request according to the target camera identification, the steps of:

carrying out logic judgment on the http traffic data calling request based on the traffic data calling request effective parameter set;

and if the http traffic data calling request is legal, caching the http traffic data calling request to an http message manager, and if the http traffic data calling request is illegal, directly returning a termination request result to the traffic police terminal.

3. The method for illegal data identification according to claim 2, further comprising, after the step of caching the http traffic data call request to an http message manager:

judging whether the http traffic data calling request has the same content as the http traffic data calling request entering in the previous preset time period or not;

and if the contents are the same, removing the http traffic data calling request from the http message manager, and if the contents are different, sending the http traffic data calling request to a message synchronizer.

4. The illegal data identification method of claim 1, wherein the step of sending the sip traffic data invocation request to the target 5G base station through the long connection comprises:

caching the sip traffic data call request into a sip message manager;

encapsulating the sip traffic data call request into a first encapsulation packet;

and sending the first encapsulating packet to the target 5G base station through the long connection.

5. The illegal data identification method according to claim 1, wherein the step of receiving the sip processing signaling returned by the target 5G base station through the long connection, generating a sip traffic data call response according to the sip processing signaling, and synchronously updating the identification contents of the sip state identifier and the http state identifier according to the contents of the sip traffic data call response comprises:

receiving a second encapsulation packet returned to an sip message manager by the target 5G base station through the long connection, and unpacking the second encapsulation packet to obtain an sip processing signaling of the target camera;

updating the identification content of the sip state identification corresponding to the sip traffic data calling request in the sip message manager according to the sip processing signaling;

when detecting that the identification content of the sip state identification is that the calling request is completed, generating and returning a sip traffic data calling response to the message synchronizer;

and according to the content of the sip traffic data call response, synchronously updating the identification content of the sip state identification and the http state identification in the message synchronizer.

6. The illegal data recognition method according to claim 5, wherein the step of synchronously updating the identification contents of the sip state identifier and the http state identifier in the message synchronizer according to the content of the sip traffic data call response comprises:

and according to the content of the sip traffic data call response, synchronously updating the identification content of the sip state identification and the http state identification into the call request completed.

7. The method for identifying illegal data according to claim 5, wherein the step of generating http traffic data call response corresponding to the http state identifier when the identifier content of the http state identifier is that the call request is completed comprises:

and when the identification content of the http state identification is that the calling request is completed, generating an http traffic data calling response of which the calling request is completed.

8. The illegal data identification method according to claim 7, wherein the step of sending the sip traffic data invocation request to the target 5G base station through the long connection to control the target 5G base station to send the sip traffic data invocation request to the target camera through a sip private line based on a sip protocol includes:

acquiring a connection period between the target 5G base station and the target camera;

and in the connection period, sending the sip traffic data calling request to the target 5G base station through the long connection so as to control the target 5G base station to send the sip traffic data calling request to the target camera through an sip private line based on an sip protocol.

9. The utility model provides a device for recognizing illegal data, its characterized in that is applicable to wisdom traffic system, wisdom traffic system includes front end camera, data server, identification equipment, 5G basic station and traffic police terminal, it has the neural network model to operate in the identification equipment, the front end camera is connected based on the sip agreement 5G basic station, the traffic police terminal is connected based on the http agreement data server with identification equipment, identification equipment is connected based on the http agreement data server, illegal data recognition device sets up in the data server, illegal data recognition device includes:

10. An electronic device comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform the operations of the illegal data identification method according to any one of claims 1 to 8.