Road condition identification method and device, storage medium and electronic device

Abstract

The invention provides a road condition identification method and device, a storage medium and an electronic device, and the method comprises the steps: obtaining the vehicle driving data of a target vehicle in a historical time period; preprocessing the vehicle driving data to obtain a characteristic signal sequence; a plurality of pre-constructed working condition analysis models are called, each working condition analysis model comprises a standard cluster center, and each working condition analysis model corresponds to a road working condition type; the characteristic signal sequence is recognized through the multiple working condition analysis models, road working condition distribution data of the target vehicle in the historical time period are obtained, and the road working condition distribution data are used for representing the working conditions of a plurality of target roads where the target vehicle travels in the historical time period and the path duration of the target roads. According to the embodiment of the invention, the technical problem that the road condition distribution data of the vehicle cannot be accurately analyzed in the prior art is solved, and the objectivity, reliability and accuracy of the vehicle use habit data are ensured.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a method and apparatus for identifying road conditions, a storage medium, and an electronic device. Background Technology

[0002] In related technologies, the sales and penetration rate of new energy vehicles in the market are experiencing explosive growth, and new energy vehicles are gradually entering full marketization. Because the technological routes of new energy vehicles differ fundamentally from those of traditional fuel vehicles, the driving habits of new energy vehicle users differ significantly from those of traditional fuel vehicle users. User driving conditions, as a sub-item of user driving habits, play a crucial role in the research and development process of new energy vehicles. Researchers can use user driving condition data to simulate bench and road tests, effectively testing and verifying the entire vehicle and system components to continuously improve product quality.

[0003] In related technologies, the driving conditions of new energy vehicle users are mainly investigated through surveys and questionnaires. However, the sample size is limited and the results are highly subjective, making it impossible to objectively and truthfully reflect the actual driving conditions of users.

[0004] No efficient and accurate solution has yet been found to address the aforementioned issues in the relevant technologies. Summary of the Invention

[0005] This invention provides a method and apparatus for identifying road conditions, a storage medium, and an electronic device to solve technical problems in related technologies.

[0006] According to an embodiment of the present invention, a method for identifying road conditions is provided, comprising: acquiring vehicle driving data of a target vehicle in a historical period; preprocessing the vehicle driving data to obtain a feature signal sequence; retrieving a plurality of pre-constructed road condition analysis models, wherein each road condition analysis model includes a standard cluster center and each road condition analysis model corresponds to a road condition type; using the plurality of road condition analysis models to identify the feature signal sequence to obtain road condition distribution data of the target vehicle in the historical period, wherein the road condition distribution data is used to characterize several target road conditions and their durations traveled by the target vehicle in the historical period.

[0007] Optionally, before retrieving multiple pre-built working condition analysis models, the method further includes: acquiring sample driving data for each sample vehicle during the driving process of the sample vehicle set; slicing the sample driving data to obtain multiple sample driving data segments, wherein each sample driving data segment corresponds to a road working condition type for the sample vehicle; integrating all sample driving data segments of all sample vehicles using working condition characteristic signals to obtain multiple sample working condition data, wherein each sample working condition data corresponds to a road working condition type, and the working condition characteristic signals include at least one of the following: vehicle speed, engine speed, torque, gradient, and steering wheel angle; and clustering the multiple sample working condition data using a density peak clustering algorithm to obtain working condition analysis models for multiple road working condition types.

[0008] Optionally, obtaining sample driving data from a set of sample vehicles includes: selecting a set of sample vehicles within a preset distribution area, wherein each of the sample vehicles is equipped with a CAN data acquisition device, the CAN data acquisition device being connected to a cloud server, and the sample driving data including driving condition data, GPS positioning data, and external visual data collected by the corresponding sample vehicle in the set during driving; and receiving the sample driving data uploaded by the CAN data acquisition device.

[0009] Optionally, the sample driving data is sliced ​​to obtain multiple sample driving data segments, including: extracting GPS positioning data, external visual data, and driving condition data from the sample driving data; generating a map trajectory using the GPS positioning data; identifying the driving condition road segment to which the corresponding sample driving data belongs based on the map trajectory and the external visual data, and segmenting the sample driving data into multiple time segments according to the driving condition road segments; and further segmenting the driving condition data according to the multiple time segments to obtain multiple sample driving data segments.

[0010] Optionally, a density peak clustering algorithm is used to cluster the multiple sample working condition data to obtain working condition analysis models for multiple road working condition types. This includes: extracting the data value of each data item from the multiple sample working condition data, taking road working condition type as the unit, and unifying all data values ​​to the same standard scale. Each sample working condition data includes at least one of the following types of feature data items: vehicle speed, engine speed, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, slope, steering wheel angle, and steering wheel angular rate. All data values ​​are paired according to the type of feature data item to obtain a set of data combination points. The local density of each data combination point is calculated, and the adjacent distance between each data combination point and a specified data combination point is calculated. The specified data combination point is the data combination point with a local density greater than the current data combination point and the closest distance. Based on the local density and the adjacent distance, a standard cluster center is selected from the set of data combination points to obtain the working condition analysis model for the corresponding road working condition type.

[0011] Optionally, calculating the local density of each data combination point includes: for each data combination point, calculating the Euclidean distance between the current data combination point and other data combination points, and calculating the cutoff distance of the current data combination point; the current data combination point is calculated using the following formula. Local density : ;in, For the current data combination point Combined with other data points The Euclidean distance between them To cut off the distance, It is a logical judgment function. hour, ,otherwise , These are the two feature data items corresponding to the current data combination point.

[0012] Optionally, selecting a standard cluster center in the set of data combination points based on the local density and the adjacent distance includes: constructing multiple density peak distribution decision maps with the local density as the horizontal and vertical coordinates and the adjacent distance as the vertical coordinate, wherein each density peak distribution decision map corresponds to a combination dimension of a feature data item; selecting a target density peak distribution decision map with the highest feature degree among the multiple density peak distribution decision maps; calculating the sum of the local density and the height of the adjacent distance of each data combination point in the target density peak distribution decision map; selecting the data combination point with the largest height sum as the cluster center, and selecting the neighborhood region of the cluster center within a preset range as the standard cluster center.

[0013] Optionally, the road condition distribution data of the target vehicle in the historical time period is obtained by identifying the feature signal sequence using the multiple working condition analysis models, including: splitting the feature signal sequence according to unit duration to obtain multiple segmented feature signals; generating a real-time decision map for each feature signal using a density peak clustering algorithm; locating the real-time cluster center of the real-time decision map, and comparing the real-time cluster center with the standard cluster center of the multiple working condition analysis models respectively, and determining the road condition type of the standard cluster center closest to the real-time cluster center as the target road condition in the time period of the segmented feature signal, wherein the target road condition includes one of the following: urban road condition, highway road condition, mountain road condition, normal road condition; and calculating the road condition distribution data of the target vehicle in the historical time period based on the target road conditions in all time periods.

[0014] According to another embodiment of the present invention, a road condition identification device is provided, comprising: a first acquisition module for acquiring vehicle driving data of a target vehicle in a historical time period; a processing module for preprocessing the vehicle driving data to obtain a feature signal sequence; a retrieval module for retrieving a plurality of pre-constructed road condition analysis models, wherein each road condition analysis model includes a standard cluster center and each road condition analysis model corresponds to a road condition type; and an identification module for identifying the feature signal sequence using the plurality of road condition analysis models to obtain road condition distribution data of the target vehicle in the historical time period, wherein the road condition distribution data is used to characterize a plurality of target road conditions and their durations traveled by the target vehicle in the historical time period.

[0015] Optionally, the device further includes: a second acquisition module, configured to acquire sample driving data of each sample vehicle in the sample vehicle set during driving, before the retrieval module retrieves the pre-constructed multiple working condition analysis models; a slicing module, configured to slice the sample driving data to obtain multiple sample driving data segments, wherein each sample driving data segment corresponds to a road working condition type of the sample vehicle; an integration module, configured to integrate all sample driving data segments of all sample vehicles using working condition characteristic signals to obtain multiple sample working condition data, wherein each sample working condition data corresponds to a road working condition type, and the working condition characteristic signals include at least one of the following: vehicle speed, engine speed, torque, gradient, and steering wheel angle; and a clustering module, configured to cluster the multiple sample working condition data using a density peak clustering algorithm to obtain working condition analysis models for multiple road working condition types.

[0016] Optionally, the second acquisition module includes: a selection unit, used to select a set of sample vehicles within a preset distribution area, wherein each of the sample vehicles is equipped with a CAN data acquisition device, the CAN data acquisition device being connected to a cloud server, and the sample driving data including driving condition data, GPS positioning data, and external visual data collected by the corresponding sample vehicle in the sample vehicle set during driving; and a receiving unit, used to receive the sample driving data uploaded by the CAN data acquisition device.

[0017] Optionally, the slicing module includes: an extraction unit for extracting GPS positioning data, vehicle exterior visual data, and driving condition data from the sample driving data; a generation unit for generating a map trajectory using the GPS positioning data; and an identification unit for identifying the driving condition road segment to which the corresponding sample driving data belongs based on the map trajectory and the vehicle exterior visual data, and segmenting the sample driving data into multiple time segments according to the driving condition road segments; and segmenting the driving condition data according to the multiple time segments to obtain multiple sample driving data segments.

[0018] Optionally, the clustering module includes: an extraction unit, used to extract the data value of each data item in the multiple sample working condition data by road condition type, and unify all data values ​​to the same standard scale, wherein each sample working condition data includes at least one of the following types of feature data items: vehicle speed, engine speed, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, slope, steering wheel angle, and steering wheel angular rate; a combination unit, used to combine all data values ​​pairwise according to the type of feature data item to obtain a set of data combination points; a calculation unit, used to calculate the local density of each data combination point and the adjacent distance between each data combination point and a specified data combination point, wherein the specified data combination point is the data combination point with a local density greater than the current data combination point and the closest distance; and a selection unit, used to select a standard cluster center in the set of data combination points according to the local density and the adjacent distance to obtain a working condition analysis model corresponding to the road working condition type.

[0019] Optionally, the calculation unit includes: a first calculation subunit, configured to calculate, for each data combination point, the Euclidean distance between the current data combination point and other data combination points, and the cutoff distance of the current data combination point; and a second calculation subunit, configured to calculate the current data combination point using the following formula. Local density : ;in, For the current data combination point Combined with other data points The Euclidean distance between them To cut off the distance, It is a logical judgment function. hour, ,otherwise , These are the two feature data items corresponding to the current data combination point.

[0020] Optionally, the selection unit includes: a construction subunit, used to construct multiple density peak distribution decision maps with the local density as the horizontal and vertical coordinate values ​​and the adjacent distance as the vertical coordinate value, wherein each density peak distribution decision map corresponds to a combination dimension of a feature data item; a first selection subunit, used to select the target density peak distribution decision map with the highest feature degree of the target combination dimension from the multiple density peak distribution decision maps; a calculation subunit, used to calculate the local density and the height sum of the adjacent distances of each data combination point in the target density peak distribution decision map; and a second selection subunit, used to select the data combination point with the largest height sum as the cluster center, and select the neighborhood area of ​​the cluster center within a preset range as the standard cluster center.

[0021] Optionally, the identification module includes: a splitting unit, used to split the feature signal sequence according to a unit time duration to obtain multiple segmented feature signals; a generation unit, used to generate a real-time decision map for each feature signal using a density peak clustering algorithm; an identification unit, used to locate the real-time cluster center of the real-time decision map, and compare the real-time cluster center with the standard cluster centers of the multiple working condition analysis models respectively, and determine the road working condition type of the standard cluster center closest to the real-time cluster center as the target road working condition for the time period in which the segmented feature signal is located, wherein the target road working condition includes one of the following: urban road working condition, highway road working condition, mountain road working condition, and normal road working condition; and a calculation unit, used to calculate the road working condition distribution data of the target vehicle in the historical time period based on the target road working conditions of all time periods.

[0022] According to another aspect of the embodiments of this application, a storage medium is also provided, the storage medium including a stored program that executes the above steps when the program is run.

[0023] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the programs stored in the memory.

[0024] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0025] The beneficial effects of this invention are: 1. By collecting vehicle driving data in historical time periods and calling multiple working condition analysis models to identify the target road working conditions of the vehicles, the system can perform working condition analysis, classification and statistics on the big data of user vehicles in the background. This solves the technical problem that existing technologies cannot accurately analyze the road working condition distribution data of vehicles, and ensures the objectivity, reliability and accuracy of vehicle usage habit data. 2. Provide reliable data on the driving habits of new energy vehicle users to guide the product planning and development of new energy vehicles. Provide data support for the bench test cycle intensity of vehicle systems and components such as battery charge and discharge cycle conditions, motor cycle conditions, and range extender cycle conditions during the research and development of new energy vehicles. Provide data support for the vehicle-level test intensity of user simulated adaptive road tests and track durability road tests during the research and development of new energy vehicles. Provide a basis for the test specifications related to various user operating conditions in the research and development of new energy vehicles. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a hardware structure block diagram of a server according to an embodiment of the present invention; Figure 2 This is a flowchart of a road condition identification method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the density peak distribution decision map in an embodiment of the present invention; Figure 4 This is a schematic diagram of the three-dimensional density distribution effect in an embodiment of the present invention; Figure 5 This is a schematic diagram of the user driving condition analysis process according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a road condition identification device according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1 The method embodiment provided in Embodiment 1 of this application can be executed in an automobile, server, processor, controller, or similar processing device. Taking running on a server as an example, Figure 1 This is a hardware structure block diagram of a server according to an embodiment of the present invention. Figure 1 As shown, a server may include one or more ( Figure 1 Only one is shown in the image. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the server may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the server described above. For example, the server may also include components that are more complex than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] The memory 104 can be used to store server programs, such as application software programs and modules, like the server program corresponding to a road condition identification method for a server in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the server program stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the server via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the server's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0032] This embodiment provides a method for identifying road conditions. Figure 2 This is a flowchart of a road condition identification method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain vehicle driving data of the target vehicle in historical time periods; Optionally, the target vehicle can be a new energy vehicle. The historical period can be defined by year, month, or other units, such as obtaining the vehicle's driving data over the past year.

[0033] Optionally, vehicle driving data includes signals that characterize the user's driving conditions, such as vehicle speed, RPM, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, gradient, steering wheel angle, and steering wheel angular rate, in the power domain, chassis domain, and body domain.

[0034] Step S202: Preprocess the vehicle driving data to obtain a feature signal sequence; Optionally, the preprocessing of the vehicle driving data includes filtering and processing the vehicle driving data, such as selecting at least two dimensions of operating condition characteristic signals from the multidimensional data of the vehicle driving data, where the characteristic signal sequence is a sequence of time-related operating condition characteristic signals.

[0035] Step S203: Retrieve multiple pre-built working condition analysis models, wherein each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; Step S204: The multiple working condition analysis models are used to identify the feature signal sequence to obtain the road working condition distribution data of the target vehicle in the historical period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical period. For example, the historical period is 100 days, and the duration of urban operating conditions, highway operating conditions, mountain road operating conditions and normal road operating conditions is 50 days, 10 days, 10 days and 30 days respectively.

[0036] The target road conditions in this embodiment include urban conditions, highway conditions, mountain road conditions, and normal road conditions, and these four types of conditions can encompass all of the user's actual driving conditions.

[0037] Urban driving conditions include, but are not limited to, road conditions within urban areas that meet certain technical requirements and facilities. These conditions are characterized by numerous at-grade intersections, allowing non-motorized vehicles and pedestrians to pass, low speed limits (0-60 km / h), and similar road conditions such as urban traffic light sections, congested expressway sections, congested highway sections, roads within garages and parking lots, and rural roads without continuous curves.

[0038] High-speed driving conditions include, but are not limited to, driving conditions on multi-lane highways with controlled access, where vehicles travel at high speeds, in separate directions, and in separate lanes, with speeds of 100 km / h or higher. Examples include unobstructed highways, expressways, and similar road conditions.

[0039] Mountain road conditions include, but are not limited to, highways within mountainous areas. These roads are relatively narrow, typically two-lane roads in both directions. They are characterized by sharp bends and steep slopes, numerous curves or continuous curves, uphill or downhill sections, and driving speeds ranging from 0-60 km / h. Examples include mountain highways and rural roads with continuous curves.

[0040] Normal road conditions include, but are not limited to, multi-lane highways with a central median strip for fast-moving vehicles, allowing for separate lanes and directions. These are characterized by wide, straight roads without sharp bends or steep inclines, and driving speeds of 60-100 km / h. Examples include expressways, national highways, and provincial highways.

[0041] Through the above steps, vehicle driving data of the target vehicle in historical time periods is obtained; the vehicle driving data is preprocessed to obtain a feature signal sequence; multiple pre-constructed working condition analysis models are invoked, wherein each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; the feature signal sequence is identified using the multiple working condition analysis models to obtain the road working condition distribution data of the target vehicle in the historical time period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical time period. By collecting vehicle driving data in historical time periods and calling multiple working condition analysis models to identify the target road working conditions traveled by the vehicle, working condition analysis, classification and statistics of big data of user-driven vehicles can be performed in the background. This solves the technical problem that existing technologies cannot accurately analyze the road working condition distribution data of vehicles, ensuring the objectivity, reliability and accuracy of vehicle usage habit data, and providing accurate data support for subsequent vehicle experiments and development.

[0042] In one embodiment of this example, before retrieving multiple pre-built working condition analysis models, the method further includes: acquiring sample driving data of each sample vehicle during the driving process of the sample vehicle set; slicing the sample driving data to obtain multiple sample driving data segments, wherein each sample driving data segment corresponds to a road working condition type of the sample vehicle; integrating all sample driving data segments of all sample vehicles using working condition characteristic signals to obtain multiple sample working condition data, wherein each sample working condition data corresponds to a road working condition type, and the working condition characteristic signals include at least one of the following: vehicle speed, engine speed, torque, gradient, and steering wheel angle; and clustering the multiple sample working condition data using a density peak clustering algorithm to obtain working condition analysis models for multiple road working condition types.

[0043] In one example, obtaining sample driving data of a sample vehicle set includes: selecting a sample vehicle set within a preset distribution area, wherein each sample vehicle set is equipped with a CAN data acquisition device, the CAN data acquisition device being connected to a cloud server, and wherein the sample driving data includes driving condition data, GPS positioning data, and external visual data collected by the corresponding sample vehicle in the sample vehicle set during driving; and receiving the sample driving data uploaded by the CAN data acquisition device.

[0044] Within a defined geographical area, a certain number of car users are selected to ensure that the selected users and their numbers cover the usage habits of most users. Car CAN data acquisition devices are installed at these selected users to collect driving condition data, GPS positioning data, and camera video images during daily driving. The collected user driving data is copied periodically. The CAN data acquisition devices can collect user driving data, GPS positioning data, and camera video images from the car's CAN bus, which are used to establish the basic data for building user condition analysis models, serving as sample driving data.

[0045] The sample driving data collected and uploaded by the CAN data acquisition device includes signals that characterize the user's driving conditions, such as vehicle speed, RPM, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, gradient, steering wheel angle, and steering wheel angular rate, in the power domain, chassis domain, and body domain.

[0046] For example, the CAN data acquisition device in this embodiment has 11 functional interfaces, including COM, GPS, DISP, cellular network card (such as 3G, 4G, etc.), and CAM / TTS (used for information projection display, prompts, and voice interaction with the driver). The COM port is connected to the OBD interface of the vehicle CAN line for power supply and 4-channel CAN data acquisition; the GPS port is connected to the GPS positioning antenna for acquiring GPS positioning data; and the DISP port is connected to the camera for acquiring video image information of the road conditions in front of the vehicle and the surrounding scene.

[0047] In one example, the sample driving data is sliced ​​to obtain multiple sample driving data segments, including: extracting GPS positioning data, external visual data, and driving condition data from the sample driving data; generating a map trajectory using the GPS positioning data; identifying the driving condition road segment to which the corresponding sample driving data belongs based on the map trajectory and the external visual data, and segmenting the sample driving data into multiple time segments according to the driving condition road segments; and further segmenting the driving condition data according to the multiple time segments to obtain multiple sample driving data segments.

[0048] The collected GPS coordinate data is converted into map trajectory. The driving conditions (such as highways, mountain roads, etc.) of the user are identified by the map trajectory and external visual data such as video images. The collected user driving data is then segmented into data segments according to four conditions: urban conditions, highway conditions, mountain road conditions, and normal road conditions.

[0049] Optionally, during the data integration process of all sample driving data segments from all sample vehicles using operating condition characteristic signals, operating condition characteristic signals that can easily distinguish four types of operating conditions (urban operating conditions, highway operating conditions, mountain road operating conditions, and normal road operating conditions) are selected, such as vehicle speed, engine speed, torque, gradient, and steering wheel angle. Then, all sliced ​​data from the four operating conditions are integrated for the same operating condition. Finally, the integrated data from the four operating conditions undergoes data cleaning to remove noise and outliers, ensuring the accuracy of the analysis results.

[0050] In one example, a density peak clustering algorithm is used to cluster the multiple sample working condition data to obtain working condition analysis models for multiple road working condition types. This includes: extracting the data value of each data item from the multiple sample working condition data, taking each road working condition type as a unit, and unifying all data values ​​to the same standard scale. Each sample working condition data includes at least one of the following feature data items: vehicle speed, engine speed, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, gradient, steering wheel angle, and steering wheel angular rate. All data values ​​are then paired according to the type of feature data item to obtain a set of data combination points. The local density of each data combination point is calculated, and the adjacent distance between each data combination point and a specified data combination point is calculated. The specified data combination point is the data combination point with a local density greater than the current data combination point and the closest adjacent data combination point. Based on the local density and the adjacent distance, a standard cluster center is selected from the set of data combination points to obtain the working condition analysis model for the corresponding road working condition type.

[0051] A multi-dimensional combined analysis was performed on the characteristic data items of the above four types of working conditions. Examples include combinations of vehicle speed and engine speed data, vehicle speed and steering wheel angle data, vehicle speed and torque data, and gradient and steering wheel angle data. The data sample points after combining two sets of data were denoted as... .because These are two different feature signal data, with different numerical ranges and units. To facilitate the calculation of sample distance... , need to Values ​​are scaled to the same standard scale. For example, vehicle speed values ​​range from 0-200, and engine speed values ​​range from 0-5000; these values ​​are scaled proportionally. The feature signal values ​​are all scaled to a range of 0-100. Finally, the combination density at the same standard scale for each dimension combination can be obtained. and the distance of local high-density points .

[0052] Optionally, calculating the local density of each data combination point includes: for each data combination point, calculating the Euclidean distance between the current data combination point and other data combination points, and calculating the cutoff distance of the current data combination point; the current data combination point is calculated using the following formula. Local density : ;in, For the current data combination point Combined with other data points The Euclidean distance between them To cut off the distance, It is a logical judgment function. hour, ,otherwise , These are the two feature data items corresponding to the current data combination point.

[0053] Therefore Centered on The number of samples within the radius (excluding itself) can be used to measure the sample size. The higher the number, the more crowded the area.

[0054] Optionally, calculating the adjacent distance between each data combination point and a specified data combination point includes: calculating the current data combination point using the following formula. Adjacent distance : data points To the nearest data point with a local density greater than its own. The distance between the samples The shortest distance to higher density samples can measure the sample density. The greater the value of "isolation", the more isolated the value. The more likely it is to be a cluster center, if It is the sample with the highest global density (no) satisfy > ),but Top-level center.

[0055] Optionally, selecting a standard cluster center in the set of data combination points based on the local density and the adjacent distance includes: constructing multiple density peak distribution decision maps with the local density as the horizontal and vertical coordinates and the adjacent distance as the vertical coordinate, wherein each density peak distribution decision map corresponds to a combination dimension of a feature data item; selecting a target density peak distribution decision map with the highest feature degree among the multiple density peak distribution decision maps; calculating the sum of the local density and the height of the adjacent distance of each data combination point in the target density peak distribution decision map; selecting the data combination point with the largest height sum as the cluster center, and selecting the neighborhood region of the cluster center within a preset range as the standard cluster center.

[0056] Software such as Matlab can be used to analyze two characteristic signal data. The horizontal axis is... Using the vertical axis as the ordinate, plot the density peak distribution decision map for each combination dimension. Figure 3 This is a schematic diagram of the density peak distribution decision map in an embodiment of the present invention. Most of the data in the decision map is distributed at the bottom and has a small distance. Only a very small number of data points are clearly distinguishable from the data at the bottom, showing a significant difference. With density This type of data is set as the cluster center along with the top-level center. Therefore, multiple density peak distribution decision maps with different combinations of characteristic signals can be obtained for the same type of user driving conditions. The decision map with the most obvious features that can completely distinguish four types of user driving conditions—urban, highway, mountain, and normal road—is selected. Then, using the selected target density peak distribution decision map, the... and The points with relatively high values ​​are used as cluster centers, and finally, the distribution range within 80% of the cluster centers is used as the standard cluster centers for the four types of working conditions.

[0057] In addition, known user operating condition data can be used to verify the operating condition analysis model. A large amount of known user operating condition data can be calculated through the operating condition analysis model, and the accuracy of the analysis model can be verified based on the model output results. The judgment criteria for the standard cluster center and the proportion of data points within it can be continuously adjusted until the model output results are completely accurate.

[0058] In one embodiment of this example, the multiple working condition analysis models are used to identify the feature signal sequence to obtain the road working condition distribution data of the target vehicle in the historical time period. This includes: splitting the feature signal sequence according to unit duration to obtain multiple segmented feature signals; generating a real-time decision map for each feature signal using a density peak clustering algorithm; locating the real-time cluster center of the real-time decision map, and comparing the real-time cluster center with the standard cluster centers of the multiple working condition analysis models, determining the road working condition type of the standard cluster center closest to the real-time cluster center as the target road working condition for the time period in which the segmented feature signal is located, wherein the target road working condition includes one of the following: urban road working condition, highway road working condition, mountain road working condition, and normal road working condition; and calculating the road working condition distribution data of the target vehicle in the historical time period based on the target road working conditions for all time periods.

[0059] Based on the proportion of data points within each standard cluster of the four operating conditions derived from the above analysis, an analytical model of user driving conditions is constructed using Matlab. The characteristic signals in each dimension are represented by the horizontal and vertical axes, and the distribution density of the signal data is represented by the vertical axis. This allows us to plot the three-dimensional density distribution of the working condition analysis model under different combinations of signals in different dimensions. Figure 4 This is a schematic diagram of the three-dimensional density distribution effect in the embodiments of the present invention, including 4a - the clustering distribution effect of vehicle speed-rotation density peak of urban driving condition model, 4b - the clustering distribution effect of vehicle speed-torque density peak of urban driving condition model, 4c - the clustering distribution effect of vehicle speed-torque density peak of mountain road driving condition model, and 4d - the clustering distribution effect of vehicle speed-rotation density peak of high-speed driving condition model.

[0060] The driving condition analysis model uses the xls file at the target address as the target driving condition data. It segments the continuous target driving condition data into groups of five minutes and performs data scaling preprocessing. Then, it uses the selected decision map feature signals to derive the decision map for each group of driving condition data. The cluster centers of the target decision map are compared with the standard cluster centers of the four driving condition models to determine which driving condition the target driving condition belongs to. Because the cluster centers of the four driving condition models obtained by the density peak clustering algorithm can completely distinguish the four driving condition models, and the standard cluster centers can cover all user driving condition data without missing any target driving condition data, the model accumulates the driving time and mileage for that driving condition after determining its classification. Finally, the driving condition analysis model automatically outputs the total driving time, mileage, and driving condition percentage for each of the four driving condition models.

[0061] For example, by retrieving the driving big data of new energy vehicle users required by the vehicle cloud backend, and using the driving data of each user for one year, with a sampling point of 0.1 seconds, hundreds of millions of data samples can be obtained. Using the aforementioned operating condition analysis model, the operating condition data to be analyzed can be analyzed, and the usage time, mileage, and operating condition ratio of new energy vehicle users in urban operating conditions, highway operating conditions, mountain road operating conditions, and normal road operating conditions can be obtained. Furthermore, all users can be segmented and data extracted according to various dimensions such as geographical distribution, city level, vehicle type, and age distribution, to further analyze the usage time, mileage, and operating condition ratio of urban operating conditions, highway operating conditions, mountain road operating conditions, and normal road operating conditions under different regions, cities, vehicle types, and age groups.

[0062] This embodiment provides a method for analyzing the driving conditions of new energy vehicle users, performing driving condition analysis, classification, and statistics on the big data of user driving data from the cloud-based backend of new energy vehicles. This includes user driving data collection, user driving condition identification and slicing, selection of driving condition characteristic signals, data preprocessing, driving condition data analysis, construction of a driving condition analysis model, and big data driving condition analysis. The method analyzes the driving big data of new energy vehicle users in the vehicle cloud to determine the user's usage time, mileage, and driving condition percentage under urban, highway, mountain road, and normal road conditions.

[0063] Figure 5This is a schematic diagram of the user driving condition analysis process according to an embodiment of the present invention, including: S51. Collecting user driving data using a data acquisition device; S52. Identifying and slicing user driving data using GPS data and video images; S53. Selecting feature signals that can distinguish user driving conditions and preprocessing the data; S54. Analyzing the identified user driving condition data using a density peak clustering algorithm; S55. Constructing a MATLAB driving condition analysis model using the analysis results; S56. Verifying the driving condition analysis model using known user driving condition data; S57. Performing driving condition analysis on the user driving big data of the vehicle cloud using the driving condition analysis model.

[0064] The solution in this embodiment can analyze the actual usage time, mileage, and proportion of different operating conditions for new energy vehicle users in urban, highway, mountain, and normal road conditions. This can yield the following beneficial effects: providing reliable data on new energy vehicle user habits to guide product planning and development; providing data support for bench testing cycles of battery charge / discharge cycles, motor cycles, and range extender cycles during new energy vehicle R&D; providing data support for vehicle-level testing intensity, including simulated adaptive road tests and track durability road tests during new energy vehicle R&D; and providing a basis for testing specifications related to various user operating conditions during the new energy vehicle R&D process.

[0065] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0066] Example 2 This embodiment also provides a road condition identification device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0067] Figure 6This is a structural block diagram of a road condition identification device according to an embodiment of the present invention, such as... Figure 6 As shown, the device includes: The first acquisition module 61 is used to acquire vehicle driving data of the target vehicle in historical time periods; Processing module 62 is used to preprocess the vehicle driving data to obtain a feature signal sequence; The retrieval module 63 is used to retrieve multiple pre-built working condition analysis models, wherein each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; The identification module 64 is used to identify the feature signal sequence using the multiple working condition analysis models to obtain the road working condition distribution data of the target vehicle in the historical period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical period.

[0068] Optionally, the device further includes: a second acquisition module, configured to acquire sample driving data of each sample vehicle in the sample vehicle set during driving, before the retrieval module retrieves the pre-constructed multiple working condition analysis models; a slicing module, configured to slice the sample driving data to obtain multiple sample driving data segments, wherein each sample driving data segment corresponds to a road working condition type of the sample vehicle; an integration module, configured to integrate all sample driving data segments of all sample vehicles using working condition characteristic signals to obtain multiple sample working condition data, wherein each sample working condition data corresponds to a road working condition type, and the working condition characteristic signals include at least one of the following: vehicle speed, engine speed, torque, gradient, and steering wheel angle; and a clustering module, configured to cluster the multiple sample working condition data using a density peak clustering algorithm to obtain working condition analysis models for multiple road working condition types.

[0069] Optionally, the second acquisition module includes: a selection unit, used to select a set of sample vehicles within a preset distribution area, wherein each of the sample vehicles is equipped with a CAN data acquisition device, the CAN data acquisition device being connected to a cloud server, and the sample driving data including driving condition data, GPS positioning data, and external visual data collected by the corresponding sample vehicle in the sample vehicle set during driving; and a receiving unit, used to receive the sample driving data uploaded by the CAN data acquisition device.

[0070] Optionally, the slicing module includes: an extraction unit for extracting GPS positioning data, vehicle exterior visual data, and driving condition data from the sample driving data; a generation unit for generating a map trajectory using the GPS positioning data; and an identification unit for identifying the driving condition road segment to which the corresponding sample driving data belongs based on the map trajectory and the vehicle exterior visual data, and segmenting the sample driving data into multiple time segments according to the driving condition road segments; and segmenting the driving condition data according to the multiple time segments to obtain multiple sample driving data segments.

[0071] Optionally, the clustering module includes: an extraction unit, used to extract the data value of each data item in the multiple sample working condition data by road condition type, and unify all data values ​​to the same standard scale, wherein each sample working condition data includes at least one of the following types of feature data items: vehicle speed, engine speed, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, slope, steering wheel angle, and steering wheel angular rate; a combination unit, used to combine all data values ​​pairwise according to the type of feature data item to obtain a set of data combination points; a calculation unit, used to calculate the local density of each data combination point and the adjacent distance between each data combination point and a specified data combination point, wherein the specified data combination point is the data combination point with a local density greater than the current data combination point and the closest distance; and a selection unit, used to select a standard cluster center in the set of data combination points according to the local density and the adjacent distance to obtain a working condition analysis model corresponding to the road working condition type.

[0072] Optionally, the calculation unit includes: a first calculation subunit, configured to calculate, for each data combination point, the Euclidean distance between the current data combination point and other data combination points, and the cutoff distance of the current data combination point; and a second calculation subunit, configured to calculate the current data combination point using the following formula. Local density : ;in, For the current data combination point Combined with other data points The Euclidean distance between them To cut off the distance, It is a logical judgment function. hour, ,otherwise , These are the two feature data items corresponding to the current data combination point.

[0073] Optionally, the selection unit includes: a construction subunit, used to construct multiple density peak distribution decision maps with the local density as the horizontal and vertical coordinate values ​​and the adjacent distance as the vertical coordinate value, wherein each density peak distribution decision map corresponds to a combination dimension of a feature data item; a first selection subunit, used to select the target density peak distribution decision map with the highest feature degree of the target combination dimension from the multiple density peak distribution decision maps; a calculation subunit, used to calculate the local density and the height sum of the adjacent distances of each data combination point in the target density peak distribution decision map; and a second selection subunit, used to select the data combination point with the largest height sum as the cluster center, and select the neighborhood area of ​​the cluster center within a preset range as the standard cluster center.

[0074] Optionally, the identification module includes: a splitting unit, used to split the feature signal sequence according to a unit time duration to obtain multiple segmented feature signals; a generation unit, used to generate a real-time decision map for each feature signal using a density peak clustering algorithm; an identification unit, used to locate the real-time cluster center of the real-time decision map, and compare the real-time cluster center with the standard cluster centers of the multiple working condition analysis models respectively, and determine the road working condition type of the standard cluster center closest to the real-time cluster center as the target road working condition for the time period in which the segmented feature signal is located, wherein the target road working condition includes one of the following: urban road working condition, highway road working condition, mountain road working condition, and normal road working condition; and a calculation unit, used to calculate the road working condition distribution data of the target vehicle in the historical time period based on the target road working conditions of all time periods.

[0075] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0076] Example 3 Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0077] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps: S1, Obtain vehicle driving data of the target vehicle in historical time periods; S2, preprocess the vehicle driving data to obtain a feature signal sequence; S3 retrieves multiple pre-built working condition analysis models, where each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; S4, the multiple working condition analysis models are used to identify the feature signal sequence to obtain the road working condition distribution data of the target vehicle in the historical period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical period.

[0078] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0079] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0080] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0081] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program: S1, Obtain vehicle driving data of the target vehicle in historical time periods; S2, preprocess the vehicle driving data to obtain a feature signal sequence; S3 retrieves multiple pre-built working condition analysis models, where each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; S4, the multiple working condition analysis models are used to identify the feature signal sequence to obtain the road working condition distribution data of the target vehicle in the historical period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical period.

[0082] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0083] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0085] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0086] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for identifying road conditions, characterized in that, include: Obtain vehicle driving data for the target vehicle during historical time periods; The vehicle driving data is preprocessed to obtain a feature signal sequence; Retrieve multiple pre-built working condition analysis models, where each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type; The feature signal sequence is identified using the multiple operating condition analysis models to obtain the road operating condition distribution data of the target vehicle in the historical period. The road operating condition distribution data is used to characterize several target road operating conditions and their durations traveled by the target vehicle in the historical period.

2. The method according to claim 1, characterized in that, Before retrieving multiple pre-built working condition analysis models, the method further includes: Obtain sample driving data for each sample vehicle in the sample vehicle set during the driving process; The sample driving data is sliced ​​to obtain multiple sample driving data segments, wherein each sample driving data segment corresponds to a road condition type of the sample vehicle; The driving data segments of all sample vehicles are integrated using the working condition characteristic signal to obtain multiple sample working condition data. Each sample working condition data corresponds to a road working condition type. The working condition characteristic signal includes at least one of the following: vehicle speed, engine speed, torque, gradient, and steering wheel angle. Density peak clustering algorithm is used to cluster the multiple sample working condition data to obtain working condition analysis models for multiple road working condition types.

3. The method according to claim 2, characterized in that, Obtaining sample driving data for the sample vehicle set includes: A sample vehicle set is selected within a preset distribution area. Each sample vehicle set is equipped with a CAN data acquisition device, which is connected to a cloud server. The sample driving data includes driving condition data, GPS positioning data, and external visual data collected by the corresponding sample vehicle during driving. Receive sample driving data uploaded by the CAN data acquisition device.

4. The method according to claim 2, characterized in that, The sample driving data is sliced ​​to obtain multiple sample driving data segments, including: Extract GPS positioning data, vehicle exterior visual data, and driving condition data from the sample driving data; The GPS positioning data is used to generate a map trajectory; Based on the map trajectory and the vehicle exterior visual data, the driving condition road segment to which the corresponding sample driving data belongs is identified, and the sample driving data is divided into multiple time segments according to the driving condition road segment; The driving condition data is segmented according to the multiple time segments to obtain multiple sample driving data segments.

5. The method according to claim 2, characterized in that, The density peak clustering algorithm is used to cluster the multiple sample working condition data to obtain working condition analysis models for multiple road working condition types, including: Taking road condition type as the unit, extract the data value of each data item in the multiple sample condition data, and unify all data values ​​to the same standard scale. Each sample condition data includes at least one of the following types of feature data items: vehicle speed, engine speed, torque, accelerator pedal, brake pedal, longitudinal acceleration, lateral acceleration, slope, steering wheel angle, and steering wheel angle rate. All data values ​​are paired according to the type of feature data items to obtain a set of data combination points; Calculate the local density of each data combination point and calculate the adjacent distance between each data combination point and a specified data combination point, wherein the specified data combination point is the data combination point with a local density greater than the current data combination point and the closest distance; Based on the local density and the adjacent distance, a standard cluster center is selected from the set of data combination points to obtain the condition analysis model for the corresponding road condition type.

6. The method according to claim 5, characterized in that, Calculating the local density for each data combination point includes: For each data combination point, calculate the Euclidean distance between the current data combination point and other data combination points, and calculate the cutoff distance of the current data combination point; The current data combination point is calculated using the following formula. Local density : ； in, For the current data combination point Combined with other data points The Euclidean distance between them To cut off the distance, It is a logical judgment function. hour, ,otherwise , These are the two feature data items corresponding to the current data combination point.

7. The method according to claim 5, characterized in that, The selection of standard cluster centers in the set of data combination points based on the local density and the adjacent distance includes: Multiple density peak distribution decision maps are constructed using the local density as the horizontal and vertical coordinate values ​​and the adjacent distance as the vertical coordinate value, wherein each density peak distribution decision map corresponds to a combination dimension of a feature data item; Select the target density peak distribution decision map with the highest feature degree among the multiple density peak distribution decision maps; Calculate the local density and the height sum of adjacent distances for each data combination point in the target density peak distribution decision map; Select the data combination point with the highest height as the cluster center, and select the neighborhood area of ​​the cluster center within a preset range as the standard cluster center.

8. The method according to claim 1, characterized in that, The feature signal sequence is identified using the multiple operating condition analysis models to obtain the road operating condition distribution data of the target vehicle during the historical time period, including: The feature signal sequence is split according to a unit duration to obtain multiple segmented feature signals; For each feature signal, a density peak clustering algorithm is used to generate a real-time decision map; Locate the real-time cluster center of the real-time decision graph, and compare the real-time cluster center with the standard cluster centers of the multiple working condition analysis models. Determine the road working condition type of the standard cluster center that is closest to the real-time cluster center as the target road working condition for the time period in which the segmented feature signal is located. The target road working condition includes one of the following: urban road working condition, expressway road working condition, mountain road working condition, and normal road working condition. The road condition distribution data of the target vehicle in the historical period is calculated based on the target road conditions in all time periods.

9. A road condition identification device, characterized in that, include: The first acquisition module is used to acquire vehicle driving data of the target vehicle in historical time periods; The processing module is used to preprocess the vehicle driving data to obtain a feature signal sequence; The retrieval module is used to retrieve multiple pre-built working condition analysis models, where each working condition analysis model includes a standard cluster center and each working condition analysis model corresponds to a road working condition type. The identification module is used to identify the feature signal sequence using the multiple working condition analysis models to obtain the road working condition distribution data of the target vehicle in the historical period, wherein the road working condition distribution data is used to characterize several target road working conditions and their durations traveled by the target vehicle in the historical period.

10. The apparatus according to claim 9, characterized in that, The identification module includes: A splitting unit is used to split the feature signal sequence according to a unit duration to obtain multiple segmented feature signals; The generation unit is used to generate a real-time decision map for each feature signal using the density peak clustering algorithm; The identification unit is used to locate the real-time cluster center of the real-time decision map, and compare the real-time cluster center with the standard cluster center of the multiple working condition analysis models respectively, and determine the road working condition type of the standard cluster center that is closest to the real-time cluster center as the target road working condition of the time period in which the segmented feature signal is located. The target road working condition includes one of the following: urban road working condition, expressway road working condition, mountain road working condition, and normal road working condition. The calculation unit is used to calculate the road condition distribution data of the target vehicle in the historical period based on the target road conditions in all time periods.

11. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method described in any one of claims 1 to 8 when it is run.

12. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method as described in any one of claims 1 to 8.

Images