WO2019205020A1

WO2019205020A1 - Road condition recognition method, apparatus and device

Info

Publication number: WO2019205020A1
Application number: PCT/CN2018/084451
Authority: WO
Inventors: 蒋新春; 刘文涛
Original assignee: 深圳市锐明技术股份有限公司
Priority date: 2018-04-25
Filing date: 2018-04-25
Publication date: 2019-10-31
Also published as: CN108513676B; CN108513676A

Abstract

A road condition recognition method, apparatus and device. The road condition recognition method comprises: collecting positioning data of a vehicle driving on a road (S201); determining a driving feature of the vehicle on the road according to the positioning data (S202); and importing the driving feature of the vehicle into a trained road condition training model, and obtaining a current road condition by means of calculation (S203). By means of collecting positioning data of a vehicle driving on a road, determining a driving feature of the vehicle according to the collected positioning data, and importing the driving feature into a trained road condition training model, a current road condition can be determined according to the determined driving feature. According to the present invention, a current road condition can be effectively recognized only by means of positioning data of a vehicle, thereby achieving a high level of timeliness and accuracy, and effectively saving on costs.

Description

Road condition recognition method, device and device

Technical field

The present application belongs to the field of intelligent travel, and particularly relates to a road condition recognition method, device and device.

Background technique

With the development of vehicle manufacturing technology and the improvement of people's living standards, more and more people have their own private vehicles and other means of transportation. As vehicles increase, the likelihood of congestion on the road will increase. In order to improve the convenience of traveling, the congestion information of the road to be traveled can be acquired before the vehicle travels, so that a relatively smooth route can be selected, the congestion time during driving can be reduced, and the convenience of travel can be improved.

The current acquisition of road condition information is generally taken by the camera to capture the scene, through the number of vehicles in the screen, and the speed of the vehicle to determine the congestion of the road segment, because the analysis of the painting requires more manpower And costly camera equipment, the cost is high, and the accuracy of the road information obtained is not high.

technical problem

In view of this, the embodiment of the present application provides a road condition identification method, device, and device, which solve the problem of high cost and low accuracy when the road condition is identified in the prior art.

Technical solution

A first aspect of the embodiments of the present application provides a road condition recognition method, where the method includes:

Collecting positioning data of vehicles driving on the road;

Determining, according to the positioning data, a driving characteristic of the vehicle on the road;

The driving characteristics of the vehicle are substituted into the trained road condition training model, and the current road condition is calculated.

With reference to the first aspect, in a first possible implementation manner of the first aspect, after the step of collecting the positioning data of the vehicle running on the road, the method further includes the step of cleaning the positioning data, specifically including :

The positioning coordinates of the cleaning positioning are not in the coordinate range in which the road is located;

And/or, the positioning data when the vehicle speed corresponding to the positioning data exceeds a predetermined speed value;

And/or cleaning the time-discontinuous positioning data in the uploaded positioning data;

And/or, cleaning the uploaded vehicle equipment to appear positioning data with abnormal serial number.

In conjunction with the first aspect, in a second possible implementation of the first aspect, the method is performed after the step of substituting the driving characteristic of the vehicle into the trained road condition training model to calculate the current road condition Also includes:

Performing the first classification of the driving characteristics according to the aging requirements and/or the frequency of use requirements;

The driving characteristics after the first classification are stored in different databases according to timeliness requirements or frequency requirements.

In conjunction with the second possible implementation of the first aspect, in a third possible implementation manner of the first aspect, the first classified driving characteristic includes a first classification feature and a second classification feature, the first The classification feature includes acceleration data, deceleration data, turn data or brake data, and the second classification feature includes current GPS point data and vehicle startup data;

The steps of storing the classified driving characteristics according to the timeliness requirement or the frequency of use requirements in different databases include:

The first classification feature is stored by batch importing into a Hadoop distributed file system HDFS storage medium, and the second classification feature is imported into a relational database or an in-memory database for storage.

With reference to the second possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, after the step of classifying the driving feature according to the aging requirement and/or the frequency of use requirement, The method also includes:

Performing a second classification of the driving characteristics according to the reported geographical location;

According to the reported time, the driving characteristics of the second classification are classified a third time, and the road point features after clustering are obtained.

With reference to the first aspect, in a fifth possible implementation manner of the first aspect, the step of substituting the driving characteristic of the vehicle into the trained road condition training model and calculating the current road condition comprises:

The location data is stored in the Hadoop distributed file system HDFS in a redundant backup manner, and the current road conditions are calculated according to the road condition training model by the computing nodes that communicate with each other.

A second aspect of the embodiments of the present application provides a road condition identifying apparatus, wherein the apparatus includes:

a positioning data collection unit for collecting positioning data of a vehicle traveling on a road;

a driving characteristic determining unit, configured to determine, according to the positioning data, a driving characteristic of the vehicle on the road;

The identification unit is configured to substitute the driving characteristic of the vehicle into the trained road condition training model, and calculate the current road condition.

In conjunction with the second aspect, in a first possible implementation of the second aspect, the apparatus further includes a cleaning unit, configured to:

A third aspect of the embodiments of the present application provides a road condition recognition apparatus, including: a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the processor The steps of the road condition recognition method according to any one of the first aspects are implemented when the computer program is executed.

A fourth aspect of the embodiments of the present application provides a computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the road condition according to any one of the first aspects The steps to identify the method.

Beneficial effect

Compared with the prior art, the embodiment of the present application has the beneficial effects of: collecting the positioning data of the vehicle traveling on the road, and determining the driving characteristics of the vehicle according to the collected positioning data, and substituting the driving characteristic into the already The trained road condition training model can determine the current road condition according to the determined driving characteristics. The present application only needs to effectively identify the current road condition according to the positioning data of the vehicle, has high real-time and high accuracy, and can effectively save costs.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only the present application. For some embodiments, other drawings may be obtained from those of ordinary skill in the art in light of the inventive workability.

1 is a schematic diagram of a road condition recognition scenario provided by an embodiment of the present application;

2 is a schematic flowchart of an implementation process of a road condition recognition method according to an embodiment of the present application;

3 is a schematic diagram of a road condition recognition apparatus according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a road condition recognition apparatus according to an embodiment of the present application.

Embodiments of the invention

In the following description, for purposes of illustration and description However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the application.

In order to explain the technical solutions described in the present application, the following description will be made by way of specific embodiments.

FIG. 1 is a schematic diagram of an implementation scenario corresponding to a road condition identification method according to an embodiment of the present disclosure. As shown in FIG. 1 , the implementation scenario includes a vehicle and a server, where the vehicle collects positioning data and sends the data to a server. The server can analyze and process the data collected by the vehicle to identify the road condition corresponding to the location of the vehicle. The vehicle may include a plurality of positioning data provided by a small number of vehicles, which may improve the accuracy of the identification of the road condition by the server.

The vehicle may be a mobile vehicle, such as a smart phone. The positioning data of the smart phone may be collected by a positioning device of the smart phone, and the positioning of the smart phone when the user holds the smart phone and is in a driving state. The data is the positioning data of the vehicle. The positioning data can be collected by setting the smart phone while driving, or the user can be automatically detected by the smart phone, for example, by recognizing the moving speed to determine that the user is in the driving state. Of course, when the user is in the driving state by means of automatic detection, when the user is in the riding state, the positioning data of the user is also collected by the vehicle to identify the road condition.

The vehicle may also be an onboard vehicle, and when the vehicle is in an activated state, the onboard vehicle is automatically turned on, and the positioning data is collected by the onboard vehicle.

FIG. 2 is a schematic flowchart of an implementation process of a road condition identification method according to an embodiment of the present disclosure, which is as follows:

In step S201, collecting positioning data of the vehicle traveling on the road;

Specifically, collecting the positioning data may be completed by a smart phone or other smart device held by the user. The positioning data of the vehicle is acquired by a positioning device in a smartphone or other smart device held by the user, and transmitted to the server in real time through a wireless communication circuit. Alternatively, the positioning data of the vehicle may be collected by the in-vehicle device, and the positioning data is transmitted by the in-vehicle device to the server.

In a preferred embodiment of the present application, after the positioning data of the vehicle is collected, a cleaning step of the positioning data is further included. The step of cleaning the collected data may include one or more of the following cleaning methods:

1. The positioning coordinates of the cleaning positioning are not in the coordinate range in which the road is located;

2. cleaning the positioning data when the vehicle speed corresponding to the positioning data exceeds a predetermined speed value;

3. Cleaning the time-discontinuous positioning data in the uploaded positioning data;

4. The positioning data of the serial number is abnormal when the uploaded vehicle equipment is cleaned.

Wherein, when the coordinates of the cleaning positioning are not in the positioning data in the coordinate range where the road is located, the coordinate range in which the road is located needs to be preset. When the coordinates of the collected positioning are not within the coordinate range of the road, the positioning data is indicated. The accuracy is not enough, or the vehicle is not currently in the road. Therefore, in order to identify a more accurate road condition, the positioning data in the coordinate range that does not conform to the road can be cleaned.

When the positioning data when the vehicle speed corresponding to the positioning data exceeds the predetermined speed value is performed, the speed value may be predetermined. When the speed of the vehicle is less than the predetermined speed value, the positioning data of the vehicle may not be considered to be floating or floating. Within acceptable limits. If the speed of the vehicle is greater than the predetermined speed value, it is considered that the position data of the vehicle floats too large, and the floating positioning data can be cleared.

When the time corresponding to the uploaded positioning data is not continuous, the positioning data may be collected, such as the location where the positioning data cannot be collected, or the communication circuit during uploading, etc., so that the collected positioning data is discontinuous. In order to reduce the positioning data with low precision, the positioning data with discontinuous upload time can be cleared.

In addition, since the server needs to receive a large number of vehicle positioning data at the same time, there may be some data abnormality of the vehicle. For example, the vehicle having the uploaded positioning data may have a serial number and a string data, that is, the positioning data between different vehicles may be Mismatching, matching the positioning data of the vehicle A to the vehicle B, and matching the positioning data of the vehicle B to the vehicle A. The positioning data uploaded by the vehicle with abnormal data is cleared.

In step S202, determining, according to the positioning data, a driving characteristic of the vehicle on the road;

Corresponding driving characteristics are calculated according to the collected positioning data. For example, the driving characteristics may include real-time position, acceleration, steering, and the like, including acceleration data, deceleration data, turn data, brake data, startup data, and the like.

In order to improve the processing speed of the data, the application may further include the step of classifying the data, and classifying the feature data according to the processing frequency of the feature data or according to the time requirement of the feature data. For example, the feature data may be classified into The first classification feature and the second classification feature, wherein the first classification feature may include acceleration data, deceleration data, turn data, or brake data, the second classification feature including current GPS point data, vehicle startup data. According to the classification of the feature data, the step of storing the classified data may be further performed. The storing the classified data may include:

You can use the batch import Hadoop as the storage medium in batches. You can cache the first classification feature in the local file system. When the first classification feature reaches a certain level, for example, 128M or 256M, you can use the HDFS mode to persist. The first classification feature is used to calculate the large amount of calculation, and the overall correction of the road data is completed.

For the second classification feature, including the positioning data of the latest GPS point, the vehicle startup data, etc., the abnormality of the road can be updated in real time by the second classification feature, so that the abnormal situation of the road can be determined more quickly and effectively.

In step S203, the driving characteristics of the vehicle are substituted into the trained road condition training model, and the current road condition is calculated.

As a preferred embodiment of the present application, before the calculation of the current road condition, the processing step of performing clustering learning on the driving feature according to the location may further include:

According to the vehicle's reported position data, vehicle azimuth, and reporting time point, statistical methods are used to classify geographical distances as one of the first steps of machine learning; and then according to the time and/or azimuth of vehicle reporting, Different vehicle driving directions are used to classify the geographical location data in the second round; after classification, statistical aggregation is performed according to the distance of the location points, and the aggregation location points represent the road points formed by the clustering.

According to the positioning data obtained after the statistical classification, information such as the pause interval, the traveling speed and the traveling direction of the vehicle can be determined, and the driving characteristics such as the pause interval, the traveling speed and the driving direction are substituted into the pre-trained road condition training model, thereby being able to calculate Generate current road conditions, including identification as intersections, traffic lights intersections, etc.

In a preferred embodiment, the corresponding road condition training model may be separately set according to the first classification feature and the second classification feature, respectively, for respectively determining the road condition and the second classification feature reflected by the first classification feature. The calculation is performed such that real-time road condition information can be generated according to the first classification feature, and overall road condition information is generated according to the second classification feature.

In a preferred embodiment, the positioning data reported by a small number of vehicles can be stored in a redundant backup manner on the Hadoop distributed file system HDFS storage medium by means of cluster parallel computing, and the storage node is located by using a Hadoop computing node. The data is reported one by one in the MAP operation. After the MAP operation is completed, the data is transmitted to different REDUCE nodes through inter-computer communication, and logical calculations are performed on these nodes. In the calculation process, if one node is abnormal, it may be other The node takes over and the corresponding calculation is completed by the node that takes over, and the final result of the parallel calculation is uniformly completed after the end of each node task.

In addition, the present application may pre-train the road condition training model through a set road model, such as a road point, a road area, a road interest point, a road index, a road speed, and the like, after the road condition model training is completed. , can provide traffic query services for other systems.

Generating driving characteristics by locating the collected vehicle data, and classifying the driving characteristics, including clustering according to the position corresponding to the driving feature, and aging requirements and frequency of use of the driving feature, and classifying according to the first classification feature The information of the overall road condition is generated, and the analysis and identification of the real-time road condition can be realized by the second classification feature. The combination of batch and real-time data is used to improve the efficiency of road recognition based on the full use of big data capabilities.

In addition, in the process of road condition recognition, the present application can further learn the identified road condition as a sample, and perform secondary learning on the data reported by the vehicle, which is beneficial to further improve the accuracy of the road condition recognition model.

In addition, road identification is carried out using the positioning data reported by the vehicle, and the intelligent data is subjected to secondary extruding by using the existing basic blackmail, and the algorithm is identified by the algorithm of the machine learning model, which is advantageous for reducing system cost and can be used repeatedly.

It should be understood that the size of the sequence of the steps in the above embodiments does not mean that the order of execution is performed. The order of execution of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.

FIG. 3 is a schematic structural diagram of a road condition recognition apparatus according to an embodiment of the present application, which is detailed as follows:

The road condition recognition device described in the present application includes:

The positioning data collecting unit 301 is configured to collect positioning data of the vehicle traveling on the road;

The driving feature determining unit 302 is configured to determine, according to the positioning data, a driving characteristic of the vehicle on the road;

The identifying unit 303 is configured to substitute the driving characteristic of the vehicle into the trained road condition training model, and calculate the current road condition.

Preferably, the device further comprises a cleaning unit for:

Preferably, the device further comprises:

a first classification unit, configured to perform the first classification of the driving feature according to a usage aging requirement and/or a usage frequency requirement;

The storage unit is configured to store the driving characteristics after the first classification in different databases according to the timeliness requirement or the frequency requirement.

Preferably, the first classified driving characteristic comprises a first classification feature and a second classification feature, the first classification feature comprises acceleration data, deceleration data, turn data or brake data, and the second classification feature comprises Current GPS point data, vehicle start data;

The storage unit is configured to: import the first classification feature into a Hadoop distributed file system HDFS storage medium for storage, and import the second classification feature into a relational database or an in-memory database.

The device also includes:

a second classification unit, configured to perform the second classification on the driving feature according to the reported geographic location;

The third classification unit is configured to perform the third classification on the driving characteristics after the second classification according to the reported time, and obtain the clustered road point features.

Preferably, the identification unit is used to:

The road condition identifying device of Fig. 3 corresponds to the road condition identifying method of Fig. 2.

FIG. 4 is a schematic diagram of a road condition recognition apparatus according to an embodiment of the present application. As shown in FIG. 4, the road condition recognition apparatus 4 of this embodiment includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and operable on the processor 40, such as a road condition recognition program. When the processor 40 executes the computer program 42, the steps in the foregoing embodiments of the respective road condition identification methods are implemented, such as steps 201 to 203 shown in FIG. 2. Alternatively, when the processor 40 executes the computer program 42, the functions of the modules/units in the foregoing device embodiments are implemented, such as the functions of the modules 301 to 303 shown in FIG.

Illustratively, the computer program 42 can be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 to complete This application. The one or more modules/units may be a series of computer program instruction segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer program 42 in the road condition recognition device 4. For example, the computer program 42 can be divided into a positioning data collection unit, a driving feature determining unit, and an identification unit, and the specific functions of each unit are as follows:

The road condition recognition device 4 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The road condition recognition device may include, but is not limited to, the processor 40 and the memory 41. It will be understood by those skilled in the art that FIG. 4 is only an example of the road condition recognition device 4, does not constitute a limitation of the road condition recognition device 4, may include more or less components than the illustration, or combine some components, or different. The components, such as the road condition recognition device, may also include input and output devices, network access devices, buses, and the like.

The so-called processor 40 can be a central processing unit (Central Processing Unit, CPU), can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

The memory 41 may be an internal storage unit of the road condition recognition device 4, such as a hard disk or a memory of the road condition recognition device 4. The memory 41 may also be an external storage device of the road condition recognition device 4, for example, a plug-in hard disk provided on the road condition recognition device 4, a smart memory card (SMC), and a secure digital (Secure Digital, SD) card, flash card (Flash Card) and so on. Further, the memory 41 may also include both an internal storage unit of the road condition recognition device 4 and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the road condition identifying device. The memory 41 can also be used to temporarily store data that has been output or is about to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the division of each functional unit and module described above is exemplified. In practical applications, the above functions may be assigned to different functional units as needed. The module is completed by dividing the internal structure of the device into different functional units or modules to perform all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be hardware. Formal implementation can also be implemented in the form of software functional units. In addition, the specific names of the respective functional units and modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application. For the specific working process of the unit and the module in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the above embodiments, the descriptions of the various embodiments are different, and the parts that are not detailed or described in a certain embodiment can be referred to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods to implement the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present application.

In the embodiments provided herein, it should be understood that the disclosed apparatus/vehicle apparatus and method may be implemented in other ways. For example, the device/vehicle device embodiments described above are merely illustrative. For example, the division of the modules or units is only one logical function division, and may be further divided in actual implementation, for example, multiple units. Or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware. The computer program may be stored in a computer readable storage medium. The steps of the various method embodiments described above may be implemented when the program is executed by the processor. . Wherein, the computer program comprises computer program code, which may be in the form of source code, object code form, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, a computer memory, a read only memory (ROM, Read-Only) Memory), random access memory (RAM, Random) Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media It does not include electrical carrier signals and telecommunication signals.

The above-mentioned embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing embodiments. The technical solutions described in the examples are modified or equivalently replaced with some of the technical features; and the modifications or substitutions do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in Within the scope of protection of this application.

Claims

A road condition recognition method, characterized in that the method comprises:

Collecting positioning data of vehicles driving on the road;

Determining, according to the positioning data, a driving characteristic of the vehicle on the road;

The driving characteristics of the vehicle are substituted into the trained road condition training model, and the current road condition is calculated.
The road condition recognition method according to claim 1, wherein after the step of collecting the positioning data of the vehicle running on the road, the method further includes the step of cleaning the positioning data, specifically comprising:

The positioning coordinates of the cleaning positioning are not in the coordinate range in which the road is located;

And/or, the positioning data when the vehicle speed corresponding to the positioning data exceeds a predetermined speed value;

And/or cleaning the time-discontinuous positioning data in the uploaded positioning data;

And/or, cleaning the uploaded vehicle equipment to appear positioning data with abnormal serial number.
The road condition recognition method according to claim 1, wherein before the step of substituting the traveling characteristic of the vehicle into the trained road condition training model to calculate the current road condition, the method further comprises:

Performing the first classification of the driving characteristics according to the aging requirements and/or the frequency of use requirements;

The driving characteristics after the first classification are stored in different databases according to timeliness requirements or frequency requirements.
The road condition recognition method according to claim 3, wherein the first classified driving characteristic comprises a first classification feature and a second classification feature, the first classification feature including acceleration data, deceleration data, and turning Data or brake data, the second classification feature including current GPS point data, vehicle startup data;

The steps of storing the classified driving characteristics according to the timeliness requirement or the frequency of use requirements in different databases include:

The first classification feature is stored by batch importing into a Hadoop distributed file system HDFS storage medium, and the second classification feature is imported into a relational database or an in-memory database for storage.
The road condition recognition method according to claim 3, wherein after the step of classifying the driving characteristics according to the aging requirement and/or the frequency of use requirement, the method further comprises:

Performing a second classification of the driving characteristics according to the reported geographical location;

According to the reported time, the driving characteristics of the second classification are classified a third time, and the road point features after clustering are obtained.
The road condition recognition method according to claim 1, wherein the step of substituting the driving characteristic of the vehicle into the trained road condition training model and calculating the current road condition comprises:

The location data is stored in the Hadoop distributed file system HDFS in a redundant backup manner, and the current road conditions are calculated according to the road condition training model by the computing nodes that communicate with each other.
A road condition recognition device, characterized in that the device comprises:

a positioning data collection unit for collecting positioning data of a vehicle traveling on a road;

a driving characteristic determining unit, configured to determine, according to the positioning data, a driving characteristic of the vehicle on the road;

The identification unit is configured to substitute the driving characteristic of the vehicle into the trained road condition training model, and calculate the current road condition.
The road condition recognition device according to claim 7, wherein the device further comprises a cleaning unit, configured to:

The positioning coordinates of the cleaning positioning are not in the coordinate range in which the road is located;

And/or, the positioning data when the vehicle speed corresponding to the positioning data exceeds a predetermined speed value;

And/or cleaning the time-discontinuous positioning data in the uploaded positioning data;

And/or, cleaning the uploaded vehicle equipment to appear positioning data with abnormal serial number.
A road condition recognition device comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the processor executes the computer program as claimed in claim 1 The steps of the road condition recognition method according to any one of the six.
A computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the road condition recognition method according to any one of claims 1 to 6. .