CN115731712A

CN115731712A - Traffic scene event analysis method, device, system and equipment

Info

Publication number: CN115731712A
Application number: CN202211459176.4A
Authority: CN
Inventors: 胡腾飞
Original assignee: Yunkong Zhixing Technology Co Ltd
Current assignee: Yunkong Zhixing Technology Co Ltd
Priority date: 2022-11-17
Filing date: 2022-11-17
Publication date: 2023-03-03

Abstract

The embodiment of the specification discloses a traffic scene event analysis method, wherein a streaming computing system acquires real-time traffic operation data sent by a first gateway through a gateway link so as to process the real-time traffic operation data to obtain target traffic scene event information; and then, sending the target traffic scene event information to the target intelligent networked vehicle by using a second gateway corresponding to the target intelligent networked vehicle related to the determined target traffic scene event information. According to the scheme, the real-time traffic operation data are directly sent through the first gateway, the target traffic scene event information is sent through the second gateway, and the real-time traffic operation data and the target traffic scene event information are prevented from entering and exiting the message queue, so that the time for entering and exiting the message queue is saved, the link time delay of traffic scene event analysis is effectively reduced, and the safety of automatic driving is guaranteed.

Description

Traffic scene event analysis method, device, system and equipment

Technical Field

The application relates to the technical field of Internet of vehicles and intelligent driving, in particular to a traffic scene event analysis method, device, system and equipment based on automatic driving.

Background

In recent years, with the innovation of science and technology, automatic driving becomes a key point and a hot point of automobile research at the present stage, and a cloud control platform is used as a brain of the automatic driving and is used for accessing various data including intelligent internet connection vehicle reported data, RCU perception data, video stream data and the like, so that scene event calculation is performed according to the received data, and abnormal scene events are issued to the intelligent internet connection vehicle, so that the safety of the automatic driving is ensured.

At present, the automatic driving scene event calculation is based on a streaming calculation framework, real-time data accessed to a cloud control platform is sent to an intermediate message queue, and the real-time data is read from the message queue during scene event calculation so as to generate a scene event according to the read real-time data; after the scene event is generated, assembling scene event data according to an issuing protocol and sending the scene event data to a message queue, and reading the scene event data from the message queue by a downstream application and sending the scene event data to a network connection vehicle; however, as the number of devices accessing the cloud control platform increases, the real-time data accessing the cloud control platform increases in multiples, and the process of entering each real-time data into the message queue and then exiting the message queue is at least millisecond-level, which causes that the time consumed by generating the whole scene event to the issued link is too long, so that the safety of automatic driving cannot be ensured.

Therefore, a method for reducing the time delay of full link transmission in the event calculation of the automatic driving scene is needed to meet the requirement of guaranteeing the safety of automatic driving.

Disclosure of Invention

The embodiment of the specification provides a traffic scene event analysis method, a device, a system and equipment, and aims to solve the problems that the existing traffic scene event analysis method is prolonged in a full link and cannot guarantee the safety of automatic driving.

In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:

an embodiment of the present specification provides a traffic scenario event analysis method, which may include:

the method comprises the steps that a streaming computing system obtains real-time traffic operation data sent by a first gateway through a gateway link;

processing the real-time traffic operation data by utilizing a flow calculation task for analyzing the traffic scene event to obtain target traffic scene event information;

determining a second gateway corresponding to a target intelligent networked vehicle related to the target traffic scene event information;

and sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway.

An embodiment of the present specification provides an apparatus for analyzing a traffic scene event, where the apparatus may include:

the data acquisition module is used for acquiring real-time traffic operation data sent by the first gateway through the gateway link by the stream computing system;

the event information generation module is used for processing the real-time traffic operation data by utilizing a flow calculation task for analyzing the traffic scene event to obtain target traffic scene event information;

the second gateway determining module is used for determining a second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information;

and the event information sending module is used for sending the target traffic scene event information to the target intelligent networked vehicle by utilizing the second gateway.

An embodiment of the present specification provides a traffic scenario event analysis system, where the system may include: a first gateway, a streaming computing system, and a second gateway;

the first gateway is used for acquiring real-time traffic operation data sent by road side equipment and a target vehicle and sending the real-time traffic operation data to the streaming computing system through a gateway link of the first gateway;

the stream type computing system is used for acquiring the first real-time traffic data sent by the first gateway through a network link of the first gateway, and processing the real-time traffic operation data by using a stream computing task for analyzing traffic scene events to obtain target traffic scene event information; determining a second gateway corresponding to a target intelligent networked vehicle related to the target traffic scene event information; sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway;

and the second gateway is used for receiving the target traffic scene information and sending the target traffic scene information to the target intelligent internet vehicle through a gateway link.

The embodiment of the present specification provides a streaming computing device for traffic scenario event analysis, including:

at least one processor; and (c) a second step of,

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring real-time traffic operation data sent by a first gateway through a gateway link;

determining a second gateway corresponding to a target intelligent networking vehicle related to the target traffic scene event information;

At least one embodiment in this specification can achieve the following advantageous effects:

acquiring real-time traffic operation data sent by a first gateway through a gateway link through a stream computing system, and processing the real-time traffic operation data by utilizing a stream computing task for analyzing traffic scene events to obtain target traffic scene event information; and then, determining a second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information, so as to send the target traffic scene event information to the target intelligent networked vehicle by using the second gateway. According to the scheme, the real-time traffic operation data is directly sent through the first gateway, and the target traffic scene event information is sent through the second gateway, so that the traffic operation data and the target traffic scene event information are prevented from entering and exiting the message queue, the time for the traffic operation data and the target traffic scene event information to enter and exit the message queue is saved, the link time delay of traffic scene event analysis is effectively reduced, and the safety of automatic driving is guaranteed.

Drawings

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic flow chart of a traffic scene event analysis method provided in an embodiment of the present specification;

fig. 2 is a schematic structural diagram of a traffic scene event analysis device provided in an embodiment of the present specification;

fig. 3 is a schematic structural diagram of a traffic scene event analysis system provided in an embodiment of the present specification;

fig. 4 is a schematic diagram of streaming computation for traffic scene event analysis according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of one or more embodiments of the present disclosure more apparent, the technical solutions of one or more embodiments of the present disclosure will be clearly and completely described below with reference to specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present specification, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from the embodiments given herein without making any creative effort fall within the scope of protection of one or more embodiments of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

In the prior art, the calculation of an automatic driving scene event is based on a streaming calculation framework, real-time data accessed to a cloud control platform is firstly sent to an intermediate message queue, when a calculation system needs to calculate the scene event, the real-time data needs to be read from the message queue so as to generate the scene event according to the read real-time data, after the scene event is generated, the calculation system needs to assemble the scene event data according to an issuing protocol, send the assembled scene event data to the message queue, and then read the scene event data from the message queue by a downstream application and send the scene event data to an intelligent internet vehicle; however, as the number of devices accessing the cloud control platform increases, the real-time data accessing the cloud control platform increases in multiples, and the process of entering each real-time data into the message queue and then exiting the message queue is at least millisecond-level, which causes that the time consumed by generating the whole scene event to the issued link is too long, so that the safety of automatic driving cannot be ensured.

In order to solve the defects in the prior art, the scheme provides the following embodiments:

fig. 1 is a schematic overall scheme flow diagram of a traffic scenario event analysis method in an embodiment of the present specification. From the program perspective, the execution subject of the process may be a cloud control platform for performing traffic scenario event analysis, as shown in fig. 1, the method may include the following steps:

step 102: the stream computing system acquires real-time traffic operation data sent by the first gateway through the gateway link.

In the embodiment of the present specification, the cloud control platform is generally used as a brain of the automatic driving in the automatic driving scene, and is used for acquiring data including: the intelligent internet vehicle reports data, roadside Computing Unit (RCU) perception data, video stream data and other data related to automatic driving, and the streaming Computing system is a system providing Computing functions for a cloud control platform.

In an embodiment of the present specification, the first gateway may establish a TCP normal connection with a roadside device through a load balancing server to receive real-time traffic operation data sent by the roadside device in real time, and directly send the received real-time traffic operation data to a streaming computing system in the cloud control platform through a gateway link, so as to reduce time for the real-time traffic operation data to enter a message queue, and reduce time for the streaming computing system to read data from the message queue, thereby reducing time delay for performing calculation for a traffic scene event according to the real-time traffic operation data, and ensuring safety of automatic driving.

In practical application, the roadside device may include an intelligent internet vehicle and a roadside computing unit, configured to obtain operation data of a vehicle; the real-time traffic operation data is used for reflecting the operation state of the vehicle, and specifically may include data reported by the intelligent internet vehicle and road side computing unit sensing data.

Step 104: and processing the real-time traffic operation data by utilizing a flow calculation task for analyzing the traffic scene event to obtain target traffic scene event information.

In an embodiment of the present specification, the streaming computing system includes a plurality of computing nodes, where the computing nodes are configured to execute a streaming computing task, and the computing nodes include a burst node (Spout) and a data processing node (Bolt), where the Spout node is used as a transaction stream distribution node, and is configured to acquire real-time traffic operation data through a gateway link and send the acquired real-time traffic operation data to the Bolt node, so that the Bolt node performs analysis and computation on a traffic scene event according to the real-time traffic operation data.

In practical applications, generally, one Spout node may send real-time traffic operation data to one or more Bolt nodes in the computing node; certainly, the Spout node may also send real-time traffic operation data to one or more Bolt nodes in the non-local computing node, so as to implement cross-network transmission; however, in order to reduce the data delay sent by the Spout node to the Bolt node in the example of this specification, it is preferable that the Spout node and the Bolt node may use a local distribution mode, the Spout node serves as a transaction flow distribution node, and only the real-time traffic operation data is sent to the Bolt node in the computing node.

In an embodiment of the present specification, the target traffic scenario event information may include: the vehicle position information, the vehicle identification information, the traffic scene event type information, the event occurrence time information, and the like of the vehicle in which the target traffic scene event occurs may be set according to specific needs, and other information included in the target traffic scene event information is not specifically limited herein.

Step 106: and determining a second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information.

In the embodiment of the present specification, the target intelligent networked vehicle is generally a vehicle that may be affected by a traffic scene event related to the target traffic scene event information, for example, if the traffic scene event related to the target traffic scene event information is an abnormal low-speed event of the vehicle, the target intelligent networked vehicle is an intelligent networked vehicle behind the vehicle where the abnormal low-speed scene event of the vehicle occurs, by a preset distance; and if the traffic scene event related to the target traffic scene event information is an abnormal low-speed event of the vehicle, the target intelligent networked vehicle is an intelligent networked vehicle in front of the vehicle and at two sides of the vehicle with the overspeed driving scene event.

In an embodiment of the present specification, the second gateway is capable of establishing connection with a target intelligent networked vehicle and communicating with the target intelligent networked vehicle, and is configured to send target traffic scene event information to the target intelligent networked vehicle.

In this embodiment, the streaming computing system may directly send the target traffic scene event information to the second gateway, so as to prevent the target traffic scene event information from entering and exiting the intermediate message queue, thereby reducing the time for the target traffic scene event information to exit the message queue, further reducing the time delay for computing for the traffic scene event according to the real-time traffic operation data, and ensuring the safety of automatic driving.

Step 108: and sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway.

In this embodiment, the second gateway may send the target traffic scenario event information to the target intelligent networked vehicle through the gateway link.

It should be understood that the order of some steps in the method described in one or more embodiments of the present disclosure may be interchanged according to actual needs, or some steps may be omitted or deleted.

In the method shown in fig. 1, a streaming computing system acquires real-time traffic operation data sent by a first gateway through a gateway link, so as to process the real-time traffic operation data by using a stream computing task for analyzing a traffic scene event, thereby obtaining target traffic scene event information; and then, determining a second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information, so as to send the target traffic scene event information to the target intelligent networked vehicle by using the second gateway. According to the scheme, the real-time traffic operation data is directly acquired through the first gateway, the target traffic scene event information is sent through the second gateway, and the traffic operation data and the target traffic scene event information are prevented from entering and exiting the message queue, so that the time for the traffic operation data and the target traffic scene event information to enter and exit the message queue is saved, the link delay of traffic scene event analysis is effectively reduced, and the timeliness of the traffic scene event analysis is guaranteed.

Based on the process of fig. 1, some specific embodiments of the process are also provided in the examples of this specification, which are described below.

In this embodiment of the present specification, generally, a data memory of real-time traffic operation data reported by a roadside device that is obtained by a first gateway is large, so that efficiency of a streaming computing system for obtaining the real-time traffic operation data is affected.

Based on this, the acquiring, by the streaming computing system, the real-time traffic operation data sent by the first gateway through the gateway link may specifically include:

the method comprises the steps that a streaming computing system obtains compressed real-time traffic operation data sent by a first gateway through a gateway link, wherein the compressed real-time traffic operation data are obtained by compressing the traffic operation data reported by road side equipment by the first gateway.

The processing the real-time traffic operation data by using the stream calculation task for analyzing the traffic scene event to obtain the target traffic scene event information may specifically include:

and decompressing the compressed real-time traffic operation data to obtain decompressed real-time traffic operation data.

And processing the decompressed real-time traffic operation data by utilizing a flow calculation task for analyzing the traffic scene event to obtain target traffic scene event information.

In this embodiment of the present specification, the first gateway may perform preprocessing such as abnormal value judgment, abnormal value deletion, missing value bit padding, and the like on the received real-time traffic operation data sent by the roadside device, because the roadside device may have data abnormality when acquiring and sending the real-time traffic operation data to the first gateway; the preprocessed real-time traffic operation data can be subjected to data compression so as to reduce the transmission of data packets of the real-time traffic operation data, thereby reducing the transmission time and further reducing the link delay of a traffic scene event analysis link.

In this illustrative embodiment, the Bolt node is configured to receive the compressed real-time traffic operation data sent by the Spout node in the computing node, and decompress the compressed real-time traffic operation data, so as to perform computation according to the decompressed real-time traffic operation data, thereby obtaining a target traffic scene event.

In practical application, after the Bolt node decompresses the compressed real-time traffic operation data, the decompressed real-time traffic operation data can be transmitted to a storage unit in the cloud control platform for storage, so that a target intelligent internet vehicle related to target traffic scene event information can be determined according to data information contained in the real-time traffic operation data subsequently.

In the embodiment of the present description, the first gateway compresses the real-time traffic operation data reported by the roadside device to reduce transmission of data packets of the real-time traffic operation data, so as to reduce time for the first gateway to transmit the real-time traffic operation data through a gateway link, thereby reducing link delay of a traffic scene event analysis link.

In this embodiment, the Spout node may send the received real-time traffic operation data of the same vehicle to the same Bolt node, so as to ensure the accuracy and timeliness of the traffic scene event calculation.

Based on this, the real-time traffic operation data may include: target vehicle identification information.

sending the real-time traffic operation data to a target data processing node; the target data processing node is a data processing node at the streaming computing system, which has a corresponding relationship with the target vehicle identification information.

And processing the real-time traffic operation data by utilizing the flow calculation task which is arranged at the target data processing node and is used for analyzing the traffic scene event to obtain target traffic scene event information related to the target intelligent networked vehicle with the vehicle identification information.

In this embodiment, the real-time traffic operation data may include target vehicle identification information, the roadside computing unit may define the target vehicle identification information for a target vehicle within a sensing range thereof, and is configured to identify identity information of the target vehicle within the sensing range thereof, and after receiving the real-time traffic operation data, the first gateway may perform hash processing on the target vehicle identification information, so as to ensure that the real-time traffic operation data of the same vehicle is sent to the same Spout node.

In practical application, the Spout node can send the real-time traffic operation data of the same target vehicle to the same target data processing node (target Bolt node) according to the identification information of the target vehicle, so as to ensure that the real-time traffic operation data of the target vehicle, which is acquired by the target Bolt node, is continuous within a certain time period, and thus the accuracy of the target Bolt node in calculating the traffic scene event of the target vehicle is ensured; meanwhile, the target Bolt node is prevented from acquiring the prior real-time traffic operation data of the target vehicle from other Bolt nodes or a storage unit, and the acquisition time of the real-time traffic operation data is shortened, so that the timeliness of the calculation of the target Bolt node for the traffic scene event of the target vehicle is ensured.

In practical applications, different traffic scene events may occur when a vehicle travels on a road, and the traffic scene events may include: at least one of an abnormal low speed event of the vehicle, an abnormal stop event of the vehicle, an overspeed driving event, an emergency braking event of the vehicle, a reverse driving event of the vehicle, a vulnerable traffic participant event, and a normal traffic event.

In practical application, different traffic scene events generally correspond to different traffic scene identification rules, and therefore, the real-time traffic operation data needs to be identified according to the different traffic scene identification rules, so as to determine whether the traffic scene event occurs.

Based on this, the processing the real-time traffic operation data by using the stream calculation task for analyzing the traffic scene event to obtain the target traffic scene event information may specifically include:

judging whether the real-time traffic operation data meets the traffic scene event recognition rule or not by utilizing a flow calculation task for analyzing the traffic scene event to obtain a first judgment result; the traffic scene event identification rule comprises a preset rule for identifying at least one traffic scene event.

And determining the satisfied traffic scene event identification rule according to the first judgment result.

And generating target traffic scene event information according to the traffic scene event corresponding to the satisfied traffic scene event identification rule.

In an embodiment of the present specification, the traffic scenario event identification rule may include: at least one of a vehicle abnormal low speed event recognition rule, a vehicle abnormal stop event recognition rule, an overspeed driving event recognition rule, a vehicle emergency braking event recognition rule, a vehicle reverse driving event recognition rule and a vulnerable traffic participant event recognition rule.

In the embodiment of the present specification, different traffic scene events correspond to different traffic scene event identification rules, and when the real-time traffic operation data of the vehicle meets a specific traffic scene event identification rule in the traffic scene time identification rules, it indicates that the vehicle has a traffic scene event corresponding to the met traffic scene time identification rule.

In an embodiment of the present specification, the real-time traffic operation data is distributed by the Spout node to a Bolt node for performing analysis of the traffic scenario event by the flow computing task, and the Bolt node extracts a field for identifying the traffic scenario event in the real-time traffic operation data, where the field may include: vehicle location, vehicle speed, vehicle acceleration, vehicle identification, vehicle heading angle, etc., to determine whether the extracted field satisfies one or more of the traffic scene event recognition rules.

In this embodiment of the present description, different traffic scene event identification rules may be used to identify different traffic scene events according to real-time traffic operation data, for example, whether a vehicle abnormal low speed event occurs in the vehicle may be determined according to a vehicle driving speed, and specifically, the traffic scene event identification rule may indicate: when the running speed of the vehicle is smaller than a preset value in the running process of the vehicle, determining that the vehicle has an abnormal low-speed event; whether the vehicle has the abnormal vehicle stopping event or not can be judged according to the vehicle running speed and the vehicle position, and specifically, the traffic scene event recognition rule can represent that: the method comprises the steps that in the running process of a vehicle, the speed of the vehicle is assumed to be zero, and the position of the vehicle is not changed compared with the previous moment, and the vehicle is determined to have an abnormal vehicle stopping event; whether the vehicle has a vehicle emergency braking event or not can be judged according to the vehicle acceleration, and specifically, the traffic scene event identification rule can indicate that: determining that a vehicle emergency braking event occurs in a vehicle when the acceleration of the vehicle is negative and rapidly increases during the running of the vehicle; and if the field in the real-time traffic operation data does not meet any traffic scene event identification rule, the traffic scene event is a normal traffic scene event.

In the embodiment of the specification, a traffic scene event is determined by judging whether a field in real-time traffic operation data meets one or more traffic scene event identification rules, and target traffic scene event information is generated according to the traffic scene event corresponding to the met traffic scene event identification rules; the target traffic scenario event information may include: the traffic scene event information includes vehicle identification information of a vehicle in which the traffic scene event occurs, event location information, event type information of the traffic scene event, event occurrence time, and the like, and specific information included in the target traffic scene event information may be added or deleted as needed, which is not limited specifically herein.

In this embodiment of the present specification, the event type information of the traffic scene event may include abnormal traffic scene event type information or normal traffic scene event type information.

In the embodiment of the present specification, in order to ensure the smoothness of the network link and save network resources, so as to ensure the timeliness of the target traffic scene event information sent to the target intelligent internet vehicle through the network link and reduce the time delay of the network link, the target traffic scene event information is usually sent only to the target intelligent internet vehicle affected by the abnormal traffic scene event.

Based on this, before determining the second gateway corresponding to the target intelligent networked vehicle related to the target traffic scenario event information, the method may further include:

and judging whether the traffic scene events corresponding to the satisfied traffic scene event identification rule contain abnormal traffic scene events or not to obtain a second judgment result.

And if the second judgment result shows that the traffic scene event corresponding to the satisfied traffic scene event identification rule comprises the abnormal traffic scene event, determining the event position information and the event type information of the abnormal traffic scene event.

Determining the target intelligent networked vehicle according to the event position information, the event type information and the current position information of each intelligent networked vehicle; the target intelligent networked vehicle is an intelligent networked vehicle expected to be influenced by the abnormal traffic scene event.

The determining of the second gateway corresponding to the target intelligent internet vehicle related to the target traffic scenario event information may specifically include:

and determining a second gateway capable of establishing communication connection with the target intelligent networking vehicle.

In an embodiment of the present specification, the abnormal traffic scenario event may include: at least one of an abnormal low speed event of the vehicle, an abnormal stop event of the vehicle, an overspeed driving event, an emergency braking event of the vehicle, a reverse driving event of the vehicle, and a vulnerable traffic participant event.

In the embodiment of the present specification, if the traffic scene event corresponding to the satisfied traffic scene event identification rule includes an abnormal traffic scene event, the vehicle is instructed to have the abnormal traffic scene event, and the position information and the event type information of the abnormal traffic scene event are acquired.

In this embodiment, the event location information may be used to reflect location information of an occurrence of an abnormal traffic scenario event, and the event type information may include: one or more of a vehicle abnormal low speed event type, a vehicle abnormal stop event type, an overspeed driving event type, a vehicle emergency braking event type, a vehicle reverse driving event type, a vulnerable traffic participant event type.

In the embodiment of the description, the intelligent internet vehicle can acquire the position information of the vehicle in real time and send the position information of the vehicle to the cloud control platform storage unit for storage through the gateway link by using the first gateway, so that the influence area of the abnormal traffic scene event can be determined according to the event position information and the event type information, whether the intelligent internet vehicle is in the influence area of the abnormal traffic scene event or not is judged according to the position information of the vehicle of the intelligent internet vehicle, and the intelligent internet vehicle in the influence area of the abnormal traffic scene event is determined as the target intelligent internet vehicle.

In this embodiment of the present description, high-precision map data may be cached in a cloud control platform storage unit for storage, where the map data may provide high-precision map service data for a cloud control platform, so as to determine a specific influence area of an abnormal traffic scene event by using event location information, event type information, and lane information in the map data, for example, if the abnormal traffic scene event is a vehicle abnormal low-speed event, the specific influence area of the abnormal traffic scene event is a same lane and an adjacent lane at a preset distance behind a vehicle location where the vehicle abnormal low-speed event occurs; the confirmation precision of the specific influence area is improved by using the high-precision map data, and the confirmation precision of the target intelligent networked vehicle is further improved.

In the embodiment of the specification, the loss computing system can directly acquire the map data from the cloud control platform storage unit, so that frequent reading of the map data from the map service system is avoided, the reading and writing operations of a magnetic disk are reduced, the link time delay of target scene event analysis is further reduced, and the safety of automatic driving is ensured.

In this embodiment, the target traffic scene event information may be sent to the target intelligent networked vehicle through a gateway link by using a second gateway that establishes a communication connection with the target intelligent networked vehicle.

In the embodiment of the description, the target traffic scene event information including the event position information and the event type information of the abnormal traffic scene event is sent only to the target intelligent networked vehicle affected by the abnormal traffic scene event, so that the data transmission pressure of a network link is reduced, and the timeliness of data transmission is ensured.

In practical application, in the prior art, after target traffic scene event information is generated, the generated target traffic scene event information is sent to an intermediate message queue, then downlink application reads the target traffic scene event information from the message queue to send the target traffic scene event information to a target intelligent internet vehicle, and the process that the target traffic scene event information enters the intermediate message queue and then exits the intermediate message queue is at least millisecond level, so that the target traffic scene event information is sent with delay, and automatic driving safety is influenced.

Based on this, the sending, by using the second gateway, the target traffic scenario event information to the target intelligent internet vehicle may specifically include:

the stream computing system sends the target traffic scene event information to a load balancing device through a gateway link, and the load balancing device is used for sending the target traffic scene event information to the second gateway; and the second gateway is used for sending the target traffic scene event information to the target intelligent networked vehicle through a gateway link.

In this embodiment of the present description, a second gateway having a stable connection relationship with a target intelligent networked vehicle may be determined according to the unique identifier of the intelligent networked vehicle, so that the load balancing device sends target traffic scene event information, which is sent by a streaming computing system and received through a gateway link, to the second gateway that can be determined according to the unique identifier of the target intelligent networked vehicle.

In this embodiment of the present specification, all gateways connected to the streaming computing system may also be determined, where the all gateways include a second gateway connected to the target intelligent internet vehicle, the load balancing device sends target traffic scene event information, which is received through a gateway link and sent by the streaming computing system, to all gateways connected to the streaming computing system, and all gateways determine whether to send the target traffic scene event information to the intelligent internet vehicle connected to the gateways according to needs.

In the embodiment of the present specification, the stream-oriented computing system directly sends the target traffic scene event information to the load balancing device through the gateway link, so as to reduce the time for the target traffic scene event information to enter and exit the intermediate message queue, thereby reducing the time delay for sending the target traffic scene event information and ensuring the safety of automatic driving.

By the method, real-time traffic operation data sent by a first gateway through a gateway link is obtained through a stream computing system, so that the real-time traffic operation data is processed by utilizing a stream computing task for analyzing traffic scene events to obtain target traffic scene event information; and then, determining a second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information, and sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway. According to the scheme, the real-time traffic operation data is directly acquired through the first gateway, the target traffic scene event information is sent through the second gateway, and the traffic operation data and the target traffic scene event information are prevented from entering and exiting the message queue, so that the time for the traffic operation data and the target traffic scene event information to enter and exit the message queue is saved, the link delay of traffic scene event analysis is effectively reduced, and the timeliness of the traffic scene event analysis is guaranteed.

Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method. Fig. 2 is a schematic structural diagram of a traffic scene event analysis device corresponding to fig. 1 provided in an embodiment of the present disclosure. As shown in fig. 2, the apparatus may include:

the data acquisition module 202 is used for the streaming computing system to acquire real-time traffic operation data sent by the first gateway through the gateway link;

the event information generating module 204 is configured to process the real-time traffic operation data by using a flow calculation task for analyzing a traffic scene event, so as to obtain target traffic scene event information;

a second gateway determining module 206, configured to determine a second gateway corresponding to a target intelligent internet vehicle related to the target traffic scenario event information;

and the event information transmission module 208 is configured to send the target traffic scene event information to the target intelligent internet vehicle by using the second gateway.

The examples of this specification also provide some specific embodiments of the process based on the apparatus of fig. 2, which is described below.

Optionally, the data obtaining module 202 may be specifically configured to:

the method comprises the steps that a streaming computing system obtains compressed real-time traffic operation data sent by a first gateway through a gateway link, wherein the compressed real-time traffic operation data are obtained by compressing the traffic operation data reported by intelligent road side equipment by the first gateway.

The event information generating module 204 may specifically be configured to:

Optionally, the real-time traffic operation data may include: target vehicle identification information.

The event information generating module 204 may be specifically configured to:

sending the real-time traffic operation data to a target data processing node; the target data processing node is a data processing node at the streaming computing system having a corresponding relationship with the target vehicle identification information.

Optionally, the traffic scene event includes: at least one of an abnormal low speed event of the vehicle, an abnormal stop event of the vehicle, an overspeed driving event, an emergency braking event of the vehicle, a reverse driving event of the vehicle, a vulnerable traffic participant event, and a normal traffic event.

Optionally, the event information generating module 204 may specifically include:

the judging unit is used for judging whether the real-time traffic operation data meets the traffic scene event recognition rule or not by utilizing a flow calculation task for analyzing the traffic scene event to obtain a first judgment result; the traffic scene event identification rule comprises a preset rule for identifying at least one traffic scene event;

the determining unit is used for determining the satisfied traffic scene event identification rule according to the first judgment result;

and the target traffic scene event information generating unit is used for generating target traffic scene event information according to the traffic scene event corresponding to the satisfied traffic scene event identification rule.

Optionally, the apparatus in fig. 2 may further include:

the judging module is used for judging whether the traffic scene events corresponding to the satisfied traffic scene event identification rule contain abnormal traffic scene events or not to obtain a second judgment result;

the first determining module is used for determining the event position information and the event type information of the abnormal traffic scene event if the second judgment result shows that the abnormal traffic scene event is contained in the traffic scene event corresponding to the satisfied traffic scene event identification rule;

the second determining module is used for determining the target intelligent networked vehicle according to the event position information, the event type information and the current position information of each intelligent networked vehicle; the target intelligent networked vehicle is an intelligent networked vehicle expected to be influenced by the abnormal traffic scene event;

the second gateway determining module 206 may be specifically configured to:

Optionally, the event information transmission module 208 may be specifically configured to:

Based on the same idea, the embodiment of the present specification further provides a system corresponding to the above method.

Fig. 3 is a schematic structural diagram of a traffic scene event analysis system corresponding to fig. 1 provided in an embodiment of the present disclosure. As shown in fig. 3, the system 300 may include: a first gateway 310, a streaming computing system 320, and a second gateway 330;

the first gateway 310 is configured to acquire real-time traffic operation data sent by road side equipment and a target vehicle, and send the real-time traffic operation data to the streaming computing system through a gateway link of the first gateway;

the streaming computing system 320 is configured to obtain the first real-time traffic data sent by the first gateway through a network link of the first gateway, and process the real-time traffic operation data by using a stream computing task for analyzing a traffic scene event to obtain target traffic scene event information; determining a second gateway corresponding to a target intelligent networked vehicle related to the target traffic scene event information; sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway;

the second gateway 330 is configured to receive the target traffic scene information, and send the target traffic scene information to the target intelligent internet vehicle through a gateway link.

Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method.

Fig. 4 is a schematic structural diagram of a streaming computing device for traffic scene event analysis, which corresponds to fig. 1 and is provided in an embodiment of the present specification. As shown in fig. 4, the apparatus 400 may include:

at least one processor 410; and the number of the first and second groups,

a memory 430 communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory 430 stores instructions 420 executable by the at least one processor 410 to enable the at least one processor 410 to:

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the streaming computing device for analyzing traffic scene events shown in fig. 4, since it is substantially similar to the method embodiment, the description is simple, and reference may be made to the partial description of the method embodiment for relevant points.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital symbol system is "integrated" onto a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Furthermore, nowadays, instead of manually manufacturing an Integrated Circuit chip, such programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as ABEL (Advanced Boolean Expression Language), AHDL (alternate Hardware Description Language), traffic, CUPL (computer unified programming Language), HDCal, jhddl (Java Hardware Description Language), lava, lola, HDL, PALASM, rhyd (Hardware Description Language), and vhigh-Language (Hardware Description Language), which is currently used in most popular applications. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in purely computer readable program code means, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information and/or data which can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A traffic scenario event analysis method, the method comprising:

2. The traffic scenario event analysis method of claim 1, characterized in that:

the method for acquiring the real-time traffic operation data sent by the first gateway through the gateway link by the streaming computing system specifically comprises the following steps:

the method comprises the steps that a streaming computing system obtains compressed real-time traffic operation data sent by a first gateway through a gateway link, wherein the compressed real-time traffic operation data are obtained by compressing the traffic operation data reported by intelligent road side equipment by the first gateway;

the processing the real-time traffic operation data by using the flow calculation task for analyzing the traffic scene event to obtain the target traffic scene event information specifically includes:

decompressing the compressed real-time traffic operation data to obtain decompressed real-time traffic operation data;

3. The traffic scenario event analysis method of claim 1, wherein the real-time traffic operation data comprises: target vehicle identification information;

the processing the real-time traffic operation data by using the stream calculation task for analyzing the traffic scene event to obtain the target traffic scene event information specifically comprises:

sending the real-time traffic operation data to a target data processing node; the target data processing node is a data processing node at the streaming computing system, which has a corresponding relationship with the target vehicle identification information;

4. The traffic scenario event analysis method of claim 1, wherein the traffic scenario event comprises: at least one of an abnormal low speed event of the vehicle, an abnormal stop event of the vehicle, an overspeed driving event, an emergency braking event of the vehicle, a reverse driving event of the vehicle, a vulnerable traffic participant event, and a normal traffic event.

5. The traffic scene event analysis method according to claim 1, wherein the processing the real-time traffic operation data by using a stream calculation task for analyzing the traffic scene event to obtain the target traffic scene event information specifically comprises:

judging whether the real-time traffic operation data meets the traffic scene event recognition rule or not by utilizing a flow calculation task for analyzing the traffic scene event to obtain a first judgment result; the traffic scene event identification rule comprises a preset rule for identifying at least one traffic scene event;

determining a satisfied traffic scene event identification rule according to the first judgment result;

6. The traffic scenario event analysis method according to claim 5, wherein before determining the second gateway corresponding to the target intelligent networked vehicle related to the target traffic scenario event information, the method further comprises:

judging whether the traffic scene events corresponding to the satisfied traffic scene event identification rule contain abnormal traffic scene events or not to obtain a second judgment result;

if the second judgment result shows that the traffic scene event corresponding to the satisfied traffic scene event identification rule comprises the abnormal traffic scene event, determining event position information and event type information of the abnormal traffic scene event to obtain the target traffic scene event information comprising the event position information and the event type information;

determining the target intelligent networked vehicle according to the event position information, the event type information and the current position information of each intelligent networked vehicle; the target intelligent networked vehicle is an intelligent networked vehicle expected to be influenced by the abnormal traffic scene event;

the determining of the second gateway corresponding to the target intelligent internet vehicle related to the target traffic scene event information specifically includes:

7. The traffic scenario event analysis method of claim 1, characterized in that: the sending the target traffic scene event information to the target intelligent internet vehicle by using the second gateway specifically includes:

8. An apparatus for analyzing traffic scene events, the apparatus comprising:

9. A traffic scenario event analysis system, the system comprising: a first gateway, a streaming computing system, and a second gateway;

the stream type computing system is used for acquiring the first real-time traffic data sent by the first gateway through a network link of the first gateway, and processing the real-time traffic operation data by using a stream computing task for analyzing traffic scene events to obtain target traffic scene event information; determining the second gateway corresponding to the target intelligent networked vehicle related to the target traffic scene event information; sending the target traffic scene event information to the target intelligent networked vehicle by using the second gateway;

and the second gateway is used for receiving the target traffic scene information and sending the target traffic scene information to the target intelligent networked vehicle through a gateway link.

10. A streaming computing device for traffic scenario event analysis, the device comprising:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,