Vehicle driving road condition recognition method and device, vehicle and storage medium

Abstract

The invention provides a vehicle driving road condition recognition method and device, a vehicle and a storage medium, and relates to the technical field of vehicles. According to the scheme, a target road section is divided into a plurality of sub-road sections, and an iterative candidate road condition type recognition strategy is adopted to improve the overall recognition precision. Specifically, firstly, a target candidate road condition type is selected from a plurality of predefined road condition types, and on the basis of vehicle end parameters, with remarkable characterization characteristics, of a vehicle under the target candidate road condition type, all sub-road sections are recognized and matched. And for the sub-road sections of which the road condition types are not identified in the current round, automatically re-selecting the next target candidate road condition type from the remaining road condition types which are not selected, and performing re-identification by using the corresponding vehicle end parameter characteristics of the next target candidate road condition type. And finally, the identification results of all the sub-road sections are integrated to accurately determine the target road condition type to which the target road section belongs.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method and device for identifying vehicle road conditions, a vehicle, and a storage medium. Background Art

[0002] During the development of automotive products, obtaining statistical data on users' actual driving conditions is key to studying how to improve product quality and user experience.

[0003] Currently, the industry mainly relies on navigation map data to identify vehicle driving conditions, but this method has significant limitations. The main limitation is that in environments where satellite positioning signals are missing, such as tunnels, urban canyons, underground parking lots, etc., map data is easily missing, which affects the integrity and accuracy of the statistical results. Summary of the Invention

[0004] In view of the above problems, the present application provides a vehicle driving road condition identification method, device, vehicle and storage medium that overcome the above problems or at least partially solve the above problems. The technical solution is as follows: A method for identifying a road condition of a large vehicle, comprising: Determine the target road section of the road condition type to be identified during vehicle driving; Splitting the target road segment into at least two sub-road segments; A target candidate road condition type is selected from a plurality of predefined road condition types, and based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each of the sub-road sections, the sub-road section belonging to the target candidate road condition type is identified; and, if there is a sub-road section for which the road condition type has not been identified, a target candidate road condition type is re-selected from the plurality of road condition types that have not been selected, and based on vehicle-side parameters corresponding to the re-selected target candidate road condition type, the sub-road section belonging to the re-selected target candidate road condition type is identified; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; Based on the identification results of the road condition types of all the sub-road sections, the target road condition type to which the target road section belongs is determined.

[0005] Optionally, determining a target road section whose road condition type is to be identified during vehicle driving includes: determining a road section whose road condition type cannot be determined through a navigation map during vehicle driving as the target road section.

[0006] Optionally, based on the identification results of the road condition types of all the sub-road sections, the target road condition type to which the target road section belongs is determined, including: based on the proportion of road condition types corresponding to all the sub-road sections in the target road section, determining the target road condition type to which the target road section belongs.

[0007] Optionally, the target road condition type to which the target road section belongs is determined based on the identification results of the road condition types of all the sub-road sections, and is executed when any of the following conditions is met: the road condition types of all the sub-road sections of the target road section have been identified; there are no new target candidate road condition types available for selection from the multiple road condition types.

[0008] Optionally, the multiple road condition types include an off-road road condition type, and the vehicle-side parameters corresponding to the off-road road condition type include a driving mode; if the target candidate road condition type is the off-road road condition type, then based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-section, the sub-section belonging to the target candidate road condition type is identified, including: for the sub-section whose driving mode is indicated as an off-road related mode, its road condition type is identified as the off-road road condition type.

[0009] Optionally, the multiple road condition types include urban road condition types, general road condition types and expressway road condition types, and the vehicle-side parameters corresponding to the urban road condition types, the general road condition types and the expressway road condition types include driving speed; if the target candidate road condition type is the urban road condition type, the general road condition and the expressway road condition type, then based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-segment, identifying the sub-segment belonging to the target candidate road condition type includes: using driving speed as a clustering feature, clustering the pre-defined The theoretical driving speed values corresponding to the urban road condition type, the general road condition type and the highway road condition type are used as the initial cluster centers to cluster the sub-road sections whose road condition types have not been identified; for the sub-road sections that belong to the cluster of the urban road condition type after clustering, their road condition types are identified as the urban road condition type; for the sub-road sections that belong to the cluster of the general road condition type after clustering, their road condition types are identified as the general road condition type; for the sub-road sections that belong to the cluster of the highway road condition type after clustering, their road condition types are identified as the highway road condition type.

[0010] Optionally, the multiple road condition types include a mountain road condition type, and the vehicle-side parameters corresponding to the mountain road condition type include an altitude change parameter and a turning angle ratio parameter; if the target candidate road condition type is the mountain road condition type, then based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-section, the sub-section belonging to the target candidate road condition type is identified, including: for a sub-section whose altitude change within a unit distance is indicated by the altitude change parameter to be greater than a preset change threshold, its road condition type is identified as the mountain road condition type; for a sub-section with an altitude change parameter indicating that the altitude change within a unit distance is greater than a preset change threshold, its road condition type is identified as the mountain road condition type; For a sub-section where the elevation change parameter indicates that the number of positive and negative switching of the altitude change rate within a unit distance is greater than a first preset number threshold, its road condition type is identified as the mountainous road condition type; for a sub-section where the angle ratio parameter indicates that the steering wheel angle amount within a unit distance is greater than a preset angle amount threshold and the duration ratio is greater than a preset ratio threshold, its road condition type is determined to be the mountainous road condition type; for a sub-section where the angle ratio parameter indicates that the number of steering wheel angle direction switchings within a unit time is greater than a second preset number threshold, its road condition type is determined to be the mountainous road condition type.

[0011] A vehicle road condition recognition device, comprising: A road section determination module, used to determine a target road section of a road condition type to be identified during vehicle travel; A road segment splitting module, configured to split the target road segment into at least two sub-road segments; an iterative identification module, configured to select a target candidate road condition type from a plurality of predefined road condition types, and identify the sub-road section belonging to the target candidate road condition type based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section; and, if a sub-road section has a road condition type that has not been identified, reselect a target candidate road condition type from the plurality of road condition types that have not been selected, and identify the sub-road section belonging to the reselected target candidate road condition type based on vehicle-side parameters corresponding to the reselected target candidate road condition type; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; The comprehensive identification module is used to determine the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections.

[0012] A vehicle comprises: a processor; and a memory arranged to store computer-executable instructions, wherein when the computer-executable instructions are executed, the processor executes the above-mentioned vehicle driving road condition identification method.

[0013] A computer-readable storage medium stores a computer program, and when the computer program is executed, the above-mentioned vehicle driving road condition identification method is implemented.

[0014] The embodiment of the present application splits the target road section into multiple sub-road sections, and adopts an iterative candidate road condition type identification strategy to improve the overall recognition accuracy. Specifically, first, a target candidate road condition type is selected from a plurality of predefined road condition types, and each sub-road section is identified and matched based on the vehicle-side parameters that have significant characterization characteristics of the vehicle under the target candidate road condition type. For the sub-road section whose road condition type cannot be identified in this round, the next target candidate road condition type is automatically reselected from the remaining road condition types that have not been selected, and its corresponding vehicle-side parameter characteristics are used for re-identification. Finally, the target road condition type to which the target road section as a whole belongs can be accurately determined by combining the identification results of all sub-road sections. The entire solution does not rely on satellite positioning signals and external map data. Therefore, in an environment where satellite positioning signals are missing, effective identification of complete road condition types under complex road conditions can be achieved, providing more complete and accurate statistical data on users' actual driving conditions for vehicle research and development.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is a schematic diagram of the main process of the vehicle driving road condition identification method according to an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the vehicle driving road condition recognition method according to an embodiment of the present application, which clusters the vehicle driving road condition types according to urban road condition types, general road condition types and expressway road condition types.

[0019] Figure 3 This is a flow chart of the vehicle driving road condition recognition method corresponding to the first application scenario of an embodiment of the present application.

[0020] Figure 4 This is a flow chart of the vehicle driving road condition recognition method corresponding to the second application scenario of an embodiment of the present application.

[0021] Figure 5This is a schematic structural diagram of a vehicle driving road condition recognition device according to an embodiment of the present application.

[0022] Figure 6 This is a schematic structural diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this specification.

[0024] During the automotive product development process, especially in key areas like structural durability, powertrain durability, and vehicle testing and verification, obtaining statistical data on actual user driving conditions is crucial. This data forms the core basis for analyzing user usage scenarios, setting development goals, designing testing and verification plans (such as target mileage), and determining product material selection criteria. Therefore, accurately measuring the proportion of users driving on different typical road conditions (such as highways, urban roads, and mountainous roads) is crucial for improving product reliability, durability, and user experience.

[0025] Currently, one of the primary ways to obtain user traffic information is by using vehicle-side satellite positioning signals (such as GPS) to locate the vehicle through mapping services. This information then identifies the road code the vehicle is traveling on based on pre-defined road code classification rules. For example, highway codes are categorized as "highway conditions," urban road codes as "urban conditions," and provincial and county road codes as "general roads."

[0026] However, this road condition identification method based on navigation map road codes has significant limitations in actual application scenarios. Due to the complexity of the actual driving environment, such as when vehicles enter tunnels, urban canyons with high-rise buildings, underground parking lots, remote mountainous areas or signal-shielded areas, satellite positioning signals are easily lost or severely interfered with. At the same time, the update of map data often lags behind actual road construction and changes. These factors result in a considerable number of satellite positioning signals being unable to be successfully parsed and matched to specific road codes by the map service, and can only be generally classified as "other" or "unknown" in statistics. This not only reduces the overall coverage of road condition statistics, but more importantly, the detailed information of this part of the trip is lost, making the final road condition proportion statistics biased and incomplete.

[0027] To solve the above problems, the present application proposes a vehicle driving road condition identification solution, which can split the target road section of the road condition type to be identified into multiple sub-sections, and adopt an iterative candidate road condition type identification strategy to improve the overall identification accuracy. Specifically, first, a candidate road condition type is selected from a plurality of predefined road condition types, and each sub-section is identified and matched based on the vehicle-side parameters that have significant characterization characteristics under the candidate road condition type. For the sub-sections whose road condition type cannot be identified in this round, the next candidate road condition type is automatically reselected from the remaining road condition types that have not been selected, and its corresponding vehicle-side parameter characteristics are used for re-identification. Finally, by combining the identification results of all sub-sections, the target road condition type to which the target road section as a whole belongs can be accurately determined. The entire solution does not rely on satellite positioning signals and external map data. Therefore, even in an environment where satellite positioning signals are missing, it can achieve effective identification of complete road condition types under complex road conditions, providing more complete and accurate statistical data on users' actual driving conditions for vehicle research and development.

[0028] Specifically, the solution of the present application includes a vehicle driving road condition identification method, device, vehicle and storage medium, and each embodiment is introduced in detail below.

[0029] An embodiment of the present application provides a method for identifying vehicle driving road conditions. Figure 1 Schematic diagram of the process of the vehicle driving road condition recognition method, including: S101, determining a target road section of a road condition type to be identified during vehicle driving.

[0030] This embodiment can be used in conjunction with a navigation map to identify the road condition type of the vehicle's travel route. Specifically, only sections of the vehicle where the navigation map's road condition type cannot be determined (e.g., "unknown sections" due to GPS signal loss, missing map data, or insufficient timeliness) are marked as target sections. For example, if the vehicle enters a tunnel or remote mountainous area, the navigation map may not return a valid road code; in this case, the section is identified as a target section.

[0031] Furthermore, this embodiment can also determine the entire route as the target route without relying on navigation maps. For example, in an environment without satellite positioning signals or when avoiding map data interference, the road conditions can be analyzed independently based on vehicle-side parameters.

[0032] It should be noted that no matter which of the above modes is adopted, the road condition type analysis of the target section directly depends on the vehicle-side parameters actually collected in the target section. Therefore, the target section refers to the section where the vehicle has traveled or is traveling.

[0033] S102: Split the target road segment into at least two sub-road segments.

[0034] It should be noted that a complex road section may contain multiple road condition types (such as highways, urban areas, mountainous areas, etc.). If the road condition type of the target section is directly analyzed, the vehicle-side parameters corresponding to the target section will be averaged and difficult to accurately identify.

[0035] To avoid this problem, this embodiment splits the target road segment into at least two sub-segments to ensure that the road condition type within each sub-segment is uniform. Based on this, the system first accurately identifies the road condition type for the most uniform sub-segment. Then, the identification results for all sub-segments are combined to determine the road condition type for the entire target road segment, significantly improving the final identification accuracy.

[0036] As an example, the following methods can be used to split the target road segment: 1) Splitting based on fixed time windows: For example, the target road section can be divided into at least two sub-segments in 1-minute increments. This approach is suitable for scenarios with high real-time requirements. The road condition type of the entire target road section can be determined by analyzing the distribution of road conditions in different time periods.

[0037] 2) Splitting based on fixed distance windows: For example, the target road segment can be divided into at least two sub-segments in 2-kilometer increments. This approach is suitable for scenarios requiring high spatial consistency. The road condition type of the entire target road segment can be determined by analyzing the road condition scores within different distance ranges.

[0038] 3) Triggering splitting when a vehicle parameter changes suddenly: For example, splitting is performed when the steering angle changes by more than 90°. This approach can more intelligently capture the boundaries of road condition changes, thereby splitting sub-segments with more homogenous road condition types.

[0039] S103, selecting a target candidate road condition type from a plurality of predefined road condition types, and identifying the sub-road sections belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section; and, if there are sub-road sections whose road condition types have not been identified, reselecting a target candidate road condition type from the road condition types that have not been selected from the plurality of road condition types, and identifying the sub-road sections belonging to the re-selected target candidate road condition type based on the vehicle-side parameters corresponding to the re-selected target candidate road condition type; wherein, the vehicle-side parameters corresponding to any road condition type are affected by the road condition type.

[0040] This embodiment uses the direct impact of a specific road condition type on its vehicle-side parameters as a basis to identify the sub-road sections belonging to the target candidate road condition type according to the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section.

[0041] The following introduces several methods for identifying road conditions.

[0042] 1) Identification of off-road road conditions Vehicle-side parameters: driving mode; Judgment rule: If the vehicle's corresponding driving mode in a certain sub-section is a preset off-road related mode, the road condition type of the sub-section is determined to be off-road.

[0043] As an example, common off-road related modes include snow, mud, sand, rock, etc. Correspondingly, for a sub-road section where the driving mode is indicated as snow, mud, sand, rock, its road condition type can be identified as an off-road road condition type.

[0044] 2) Identification of urban road condition types, general road condition types, and highway road condition types Vehicle-side parameters: driving speed; Determination rules: A clustering algorithm (k-means clustering algorithm) is used, with driving speed as the clustering feature. The theoretical driving speed values corresponding to the pre-defined urban road condition types, general road condition types, and expressway road condition types are used as the initial cluster centers. Sub-segments with unidentified road condition types are clustered to determine the road condition type of the sub-segment; As an example, according to the speed regulations in the national standard "GB / T 38146.1-2019", low speed (≤30 km / h) is defined as the theoretical driving speed value for urban road conditions, medium speed (30–70 km / h) is defined as the theoretical driving speed value for general road conditions, and high speed (≥70 km / h) is defined as the theoretical driving speed value for high-speed road conditions. Figure 2As shown, three clusters are constructed, representing the classification of urban road conditions, general road conditions, and highway conditions, respectively. Within the defined theoretical driving speed range, 15 km / h is used as the cluster center for urban road conditions, 50 km / h as the cluster center for general road conditions, and 100 km / h as the cluster center for highway conditions. Subsequently, sub-segments for which no road condition type was identified are clustered using driving speed as the clustering dimension. This involves calculating the mathematical distance between the vehicle's driving degree in each sub-segment and the cluster center, and then classifying the sub-segments into the corresponding categories based on this mathematical distance. For example, if the vehicle's driving speed in sub-segment A is 90 km / h, then sub-segment A is closer to the cluster center for highway conditions and, therefore, is classified into the highway cluster after clustering. Finally, after clustering is completed, for the sub-segments of the cluster belonging to the urban road condition type, their road condition type is identified as the urban road condition type; for the sub-segments of the cluster belonging to the general road condition type, their road condition type is identified as the general road condition type; for the sub-segments of the cluster belonging to the expressway condition type, their road condition type is identified as the expressway condition type.

[0045] It should be noted that GB / T 38146.1-2019 also specifies characteristics such as the proportion of idling time, maximum deceleration, and number of stops per kilometer for low, medium, and high speeds. These characteristics can replace driving speed as clustering dimensions, or can be combined with driving speed as clustering dimensions (the characteristics of multiple clustering dimensions only need to be normalized to a unified dimension to complete the data distance calculation required for clustering).

[0046] 3) Identification of road conditions in mountainous areas Vehicle-side parameters: altitude change parameters and angle ratio parameters; Judgment rule: If a sub-segment meets any of the following conditions, its road condition type is identified as mountainous: Condition 1: The sub-segment indicates that the elevation change per unit distance is greater than a preset elevation change threshold (e.g., 500 meters / 100 kilometers), and the steering angle ratio parameter indicates that the steering wheel angle is greater than a preset steering angle threshold (e.g., 30 degrees) and the duration ratio is greater than a preset ratio threshold (e.g., 20%). It should be understood that condition 1 is equivalent to the driving scenario of "large altitude change + continuous large steering angle", which can cover the sub-sections in mountainous areas with continuous steep slopes and long curves.

[0047] Condition 2: The altitude change parameter indicates that the altitude change per unit distance is greater than a preset altitude change threshold (e.g., 500 meters / 100 kilometers), and the steering angle ratio parameter indicates that the number of steering wheel direction switches per unit time is greater than a first preset number threshold (e.g., 5 times / minute). It should be understood that condition 2 is equivalent to the driving scenario of "large altitude changes + high-frequency steering switching", which can cover sub-sections of steep slopes in mountainous areas where frequent direction corrections are required.

[0048] Condition 3: The altitude change parameter indicates that the number of positive and negative altitude change rate switches per unit distance (equivalent to the number of uphill / downhill switches) is greater than a second preset number threshold (e.g., 10 times / km), and the angle ratio parameter indicates that the steering wheel angle is greater than a preset angle threshold (e.g., 30°) and the duration ratio is greater than a preset ratio threshold (e.g., 20%). It should be understood that condition 3 is equivalent to the driving scenario of "high frequency uphill / downhill + continuous large steering angle", which is used to cover the sub-sections in mountainous areas where short-distance undulations and sharp turns are intertwined.

[0049] Condition 4: The sub-section has an altitude change parameter indicating that the number of positive and negative altitude change rate switches per unit distance is greater than a second preset threshold (e.g., 10 times / km), and a steering angle ratio parameter indicating that the number of steering wheel angle direction switches per unit time is greater than a first preset threshold (e.g., 5 times / minute).

[0050] It should be understood that condition 4 is equivalent to a driving scenario of "high-frequency uphill / downhill + high-frequency steering switching", which can cover sub-sections with severe terrain fluctuations and extreme control requirements in mountainous areas.

[0051] It should be noted that the above process can be understood as a process of iteratively identifying the road condition types of sub-road sections. The process can be terminated when the road condition types of all the sub-road sections of the target road section have been identified, or when there are no new target candidate road condition types to be selected from the multiple road condition types. This iterative identification mechanism can only ensure that the road condition types of all sub-road sections are effectively identified, thereby improving the accuracy of the subsequent overall identification of the road condition type of the entire target road section. In addition, during the iterative process, the order of selecting target candidate road condition types from the target candidate road condition types can be flexibly set according to needs and is not specifically limited herein.

[0052] S104: Determine the target road condition type to which the target road section belongs based on the identification results of the road condition types of all sub-road sections.

[0053] In this embodiment, the recognition results of the road condition types of all sub-road sections may be combined to be regarded as the target road condition type to which the target road section belongs.

[0054] As an example, assume that the target road segment is divided into 8 sub-segments according to distance as shown in the following table:

[0055] In this embodiment, the target road condition type of the target section can be split into sub-sections for representation, that is, sub-sections 1-2 are urban road condition types, sub-section 3 is expressway condition type, sub-sections 4-5 are general road condition types, and sub-sections 6-8 are expressway condition types.

[0056] Alternatively, the target road condition type to which the target road section belongs may be determined based on the proportion of road condition types corresponding to all the sub-road sections in the target road section.

[0057] As an example, we can still use the table above to determine: The proportion of urban road conditions is 10 km / (10 km + 10 km + 30 km + 30 km) = 12.5%; The proportion of highway road conditions is (10 km + 30 km) / (10 km + 10 km + 20 km + 30 km) = 50%; The proportion of general road conditions is 30 km / (10 km + 10 km + 30 km + 30 km) = 37.5%.

[0058] Correspondingly, the highway type with the largest proportion can be determined as the target road condition type for the target segment. Alternatively, a regularization condition can be introduced to remove road condition types with a proportion below 30%, and the remaining highway and general road types can be determined as the target road condition type for the target segment. In other words, the target segment has a mixed road condition of highways and general roads.

[0059] The following describes the vehicle driving road condition recognition method of this embodiment in detail in combination with actual application scenarios.

[0060] Application Scenario 1 This application scenario prioritizes the navigation map to identify the road condition type of the vehicle's driving section. For sections where the navigation map cannot identify the road condition type, it will be marked as a target section and further analyzed based on the vehicle-side parameters. The corresponding process is as follows: Figure 3 Shown, including: Step 1: Based on the vehicle's satellite positioning signal, determine the road code of the road the vehicle is traveling on the navigation map. Classify the road code and then count the road sections into urban road condition types, expressway road condition types, and general road condition types. It should be understood that due to loss of satellite positioning signals, there may be unidentified sections of "other road condition types." Therefore, sections corresponding to "other road condition types" are marked as target sections.

[0061] Step 2: Split the target road segment into multiple short sub-segments and first attempt to identify the off-road road condition type for each sub-segment. Specifically, determine the vehicle's driving mode for each sub-segment. Then, for sub-segments indicating off-road driving (e.g., snow, mud, sand, etc.), identify the road condition as off-road. For sub-segments with other driving modes, identify the road condition as non-off-road.

[0062] Step 3: Considering the ambiguity of the "non-off-road road condition type," the "non-off-road road condition type" is considered an invalid road condition type. If there are sub-segments with unidentified road condition types (including sub-segments with "non-off-road road condition type"), these sub-segments are then identified as urban road condition types, general road condition types, and highway condition types. Specifically, the vehicle's driving speed is determined for the sub-segments with unidentified road condition types. Then, using driving speed as the clustering dimension, the urban road condition type, general road condition type, and highway condition type are clustered. The sub-segments with unidentified road condition types are clustered, attempting to identify sub-segments belonging to the urban road condition type, general road condition type, and highway condition type.

[0063] Step 4: Given the ambiguity of the "general road condition type," the "general road condition type" is considered invalid. If there are sub-segments with unidentified road conditions (including those with "general road condition type" identified based on driving speed and those with "general road condition type" identified based on the navigation map), the sub-segments with unidentified road conditions are then identified as mountainous roads. This means first determining the altitude change parameters and turning angle ratio parameters for the vehicle on the sub-segments with unidentified road conditions. Afterwards, based on the altitude change parameters and the turning angle ratio parameters, the following four rules are used to determine the sub-sections belonging to the mountainous road condition type: 1) Sub-sections with an altitude change greater than 500 meters / 100 kilometers, a steering wheel angle greater than 30°, and a duration greater than 20% are determined as mountainous road condition types; 2) Sub-sections with an altitude change greater than 500 meters / 100 kilometers and a steering wheel angle direction switching frequency greater than 5 times / minute are determined as mountainous road condition types; 3) Sub-sections with an altitude change rate positive and negative switching frequency greater than 10 times / kilometer, a steering wheel angle greater than 30°, and a duration greater than 20% are determined as mountainous road condition types; 4) Sub-sections with an altitude change rate positive and negative switching frequency greater than 10 times / kilometer and a steering wheel angle direction switching frequency greater than 5 times / minute are determined as mountainous road condition types.

[0064] In summary, this application scenario, with its collaborative architecture based on navigation maps and vehicle-side parameter blind spot filling, creatively solves the problem of traditional solutions being unable to collect statistics on vehicle driving conditions due to loss of satellite positioning signals. Specifically, the navigation map is first used to efficiently identify basic road conditions such as urban areas, highways, and general roads, and vehicle-side parameter analysis is initiated for "unknown sections" where the signal is lost. A three-level precision blind spot filling strategy is then implemented: first, driving mode is used to capture off-road conditions, then driving speed clustering is used to separate urban and highway conditions, and finally, four-dimensional conditions (altitude change / frequency + steering wheel angle amplitude / frequency) are used to accurately filter out mountainous road conditions from the remaining "general roads," thereby achieving identification and completion of "unknown sections."

[0065] Application Scenario 2 This application scenario is completely independent of the navigation map and directly analyzes the road condition type based on the vehicle-side parameters. The corresponding process is as follows Figure 4 Shown, including: Step 1: Mark the road section that the vehicle has currently traveled and that requires road condition type identification as the target road section, and split the target road section into multiple short-distance sub-segments.

[0066] Step 2: Identify the urban, general, and expressway road condition types for all sub-segments. Specifically, determine the vehicle's driving speed for each sub-segment. Then, using driving speed as the clustering dimension, cluster the urban, general, and expressway road condition types. Cluster the sub-segments for which no road condition type has been identified, and attempt to identify those that fall into the urban, general, and expressway road condition types.

[0067] Step 3: The "general road condition type" is considered invalid. If there are sub-segments with unidentified road condition types (including sub-segments with the "general road condition type"), the off-road condition type is identified for these sub-segments. Specifically, the vehicle's driving mode is first determined for each sub-segment with unidentified road condition types. Then, for sub-segments where the driving mode indicates an off-road-related mode (such as snow, mud, or sand), the road condition type is identified as off-road. For sub-segments with other driving modes, the road condition type is identified as non-off-road.

[0068] Step 4: The "non-off-road road condition type" is considered invalid. If there are sub-sections with unrecognized road conditions (including the "non-off-road road condition type"), the mountain road condition type is identified for these sub-sections. In other words, the altitude change parameters and turning angle ratio parameters corresponding to the vehicle in the sub-sections with unrecognized road conditions are first determined. Afterwards, based on the altitude change parameters and the turning angle ratio parameters, the following four rules are used to determine the sub-sections belonging to the mountainous road condition type: 1) Sub-sections with an altitude change greater than 500 meters / 100 kilometers, a steering wheel angle greater than 30°, and a duration greater than 20% are determined as mountainous road condition types; 2) Sub-sections with an altitude change greater than 500 meters / 100 kilometers and a steering wheel angle direction switching frequency greater than 5 times / minute are determined as mountainous road condition types; 3) Sub-sections with an altitude change rate positive and negative switching frequency greater than 10 times / kilometer, a steering wheel angle greater than 30°, and a duration greater than 20% are determined as mountainous road condition types; 4) Sub-sections with an altitude change rate positive and negative switching frequency greater than 10 times / kilometer and a steering wheel angle direction switching frequency greater than 5 times / minute are determined as mountainous road condition types.

[0069] In summary, this second application scenario achieves accurate analysis of global road conditions without the need for navigation maps: first, speed clustering is used to quickly separate urban and highway conditions, and "general roads" are treated as invalid identification marks to trigger secondary analysis; then, off-road conditions are efficiently identified based on driving mode signals; finally, the four-dimensional mountain judgment conditions (altitude change / frequency + steering wheel angle amplitude / frequency) are used to accurately lock in mountainous road conditions in the remaining sections, which is superior to traditional solutions based on navigation maps in both recognition accuracy and coverage.

[0070] In addition, corresponding to Figure 1 In addition to the method shown, another embodiment of the present application further provides a vehicle driving road condition recognition device. Figure 5 FIG. 5 is a schematic structural diagram of the vehicle driving road condition recognition device 500, comprising: The road section determination module 510 is used to determine a target road section of a road condition type to be identified during vehicle driving.

[0071] The road segment splitting module 520 is configured to split the target road segment into at least two sub-road segments.

[0072] The iterative identification module 530 is used to select a target candidate road condition type from a plurality of predefined road condition types, and identify the sub-road section belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section; and, if there is a sub-road section whose road condition type has not been identified, reselect a target candidate road condition type from the road condition types that have not been selected from the plurality of road condition types, and identify the sub-road section belonging to the re-selected target candidate road condition type based on the vehicle-side parameters corresponding to the re-selected target candidate road condition type; wherein, the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type.

[0073] The comprehensive identification module 540 is configured to determine the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections.

[0074] The device of this embodiment splits the target road section into multiple sub-road sections, and adopts an iterative candidate road condition type identification strategy to improve the overall recognition accuracy. Specifically, first, a target candidate road condition type is selected from a plurality of predefined road condition types, and each sub-road section is identified and matched based on the vehicle-side parameters that have significant characterization characteristics of the vehicle under the target candidate road condition type. For the sub-road section whose road condition type cannot be identified in this round, the next target candidate road condition type is automatically reselected from the remaining road condition types that have not been selected, and its corresponding vehicle-side parameter characteristics are used for re-identification. Finally, by combining the identification results of all sub-road sections, the target road condition type to which the target road section as a whole belongs can be accurately determined. The entire solution does not rely on satellite positioning signals and external map data. Therefore, in an environment where satellite positioning signals are missing, it can also achieve effective identification of complete road condition types under complex road conditions, providing more complete and accurate statistical data on users' actual driving conditions for vehicle research and development.

[0075] Optionally, the road section determination module 510 determines a target road section of a road condition type to be identified during vehicle driving, including: determining a road section of a road condition type that cannot be determined through a navigation map during vehicle driving as the target road section.

[0076] Optionally, the iterative identification module 530 determines the target road condition type to which the target section belongs based on the identification results of the road condition types of all the sub-sections, including: determining the target road condition type to which the target section belongs based on the proportion of road condition types corresponding to all the sub-sections in the target section; or, taking the road condition types of all the sub-sections together as the target road condition type to which the target section belongs.

[0077] Optionally, the determining of the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections is performed when any of the following conditions is met: The road condition types of all the sub-road sections of the target road section have been identified; There is no new target candidate road condition type available for selection among the multiple road condition types.

[0078] Optionally, the multiple road condition types include an off-road road condition type, and the vehicle-side parameters corresponding to the off-road road condition type include a driving mode; if the target candidate road condition type is the off-road road condition type, the iterative identification module 530 identifies the sub-sections belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-section, including: for the sub-section whose driving mode is indicated as an off-road related mode, identifying its road condition type as the off-road road condition type.

[0079] Optionally, the multiple road condition types include urban road condition types, general road condition types and expressway road condition types, and the vehicle-side parameters corresponding to the urban road condition types, the general road condition types and the expressway road condition types include driving speed; if the target candidate road condition types are the urban road condition types, the general road condition types and the expressway road condition types, the iterative identification module 530 identifies the sub-segments belonging to the candidate road condition types based on the vehicle-side parameters corresponding to the candidate road condition types in each of the sub-segments, including: using driving speed as a clustering feature, clustering the pre-defined The theoretical driving speed values corresponding to the urban road condition type, the general road condition type and the highway road condition type are used as the initial cluster centers to cluster the sub-road sections whose road condition types are not identified; for the sub-road sections that belong to the cluster of the urban road condition type after clustering, their road condition types are identified as the urban road condition type; for the sub-road sections that belong to the cluster of the general road condition type after clustering, their road condition types are identified as the general road condition type; for the sub-road sections that belong to the cluster of the highway road condition type after clustering, their road condition types are identified as the highway road condition type.

[0080] Optionally, the multiple road condition types include a mountain road condition type, and the vehicle-side parameters corresponding to the mountain road condition type include an altitude change parameter and a turning angle ratio parameter; if the candidate road condition type is the mountain road condition type, the iterative identification module 530 identifies the sub-section belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the candidate road condition type in each sub-section, including: for the sub-section where the altitude change parameter indicates that the altitude change within a unit distance is greater than a preset change threshold, the turning angle ratio parameter indicates that the steering wheel angle within a unit distance is greater than a preset turning angle threshold and the duration ratio is greater than a preset ratio threshold, its road condition type is determined to be the mountain road condition type; for the sub-section where the altitude change parameter indicates that the altitude change within a unit distance is greater than a preset change threshold, the turning angle ratio parameter indicates that the steering wheel angle within a unit distance is greater than a preset turning angle threshold and the duration ratio is greater than a preset proportion threshold, the road condition type is determined to be the mountain road condition type; For the sub-section where the angle ratio parameter indicates that the number of steering wheel angle direction switches within a unit distance is greater than a first preset number threshold, its road condition type is determined to be the mountainous road condition type; for the sub-section where the altitude change parameter indicates that the number of positive and negative switches of the altitude change rate within a unit distance is greater than a second preset number threshold, and the angle ratio parameter indicates that the steering wheel angle amount within a kilometer is greater than the preset angle amount threshold and the duration ratio is greater than the preset ratio threshold, its road condition type is determined to be the mountainous road condition type; for the sub-section where the altitude change parameter indicates that the number of positive and negative switches of the altitude change rate within a unit distance is greater than a first preset number threshold, and the angle ratio parameter indicates that the number of steering wheel angle direction switches per unit time is greater than the first preset number threshold, its road condition type is determined to be the mountainous road condition type.

[0081] It should be noted that, regarding the vehicle driving road condition recognition device in the above embodiment, the specific manner in which each model performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0082] In addition, another embodiment of the present application provides a vehicle. Figure 6 6 is a schematic diagram of the structure of the vehicle, including a memory 601 and a processor 602. The memory 601 stores an executable program code 6011. The processor 602 is configured to call and execute the executable program code 6011 to perform the large model question-answering method provided in the above embodiment. The corresponding steps include: Determine the target road section of the road condition type to be identified during vehicle driving; Splitting the target road segment into at least two sub-road segments; A target candidate road condition type is selected from a plurality of predefined road condition types, and based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each of the sub-road sections, the sub-road section belonging to the target candidate road condition type is identified; and, if there is a sub-road section for which the road condition type has not been identified, a target candidate road condition type is re-selected from the plurality of road condition types that have not been selected, and based on vehicle-side parameters corresponding to the re-selected target candidate road condition type, the sub-road section belonging to the re-selected target candidate road condition type is identified; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; Based on the identification results of the road condition types of all the sub-road sections, the target road condition type to which the target road section belongs is determined.

[0083] This embodiment can divide the vehicle into functional modules based on the above-described method example. For example, each functional module can be mapped to a specific function, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used.

[0084] In the case of dividing the functional modules into corresponding functional modules, the vehicle may include: a road segment determination module, an information determination module, and an iteration identification module. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0085] It should be understood that the vehicle provided in this embodiment is used to execute the above-mentioned vehicle driving road condition identification method, and thus can achieve the same effect as the above-mentioned implementation method.

[0086] In the case of an integrated unit, the vehicle may include a processing module and a storage module. The processing module may be used to control and manage the vehicle's movements, while the storage module may be used to support the vehicle's execution of program codes and data.

[0087] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits disclosed herein. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing (DSP) and a microprocessor, and the storage module may be a memory.

[0088] In addition, another embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer program code. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a vehicle driving road condition identification method provided in the above embodiment, which correspondingly includes the following steps: Determine the target road section of the road condition type to be identified during vehicle driving; Splitting the target road segment into at least two sub-road segments; A target candidate road condition type is selected from a plurality of predefined road condition types, and based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each of the sub-road sections, the sub-road section belonging to the target candidate road condition type is identified; and, if there is a sub-road section for which the road condition type has not been identified, a target candidate road condition type is re-selected from the plurality of road condition types that have not been selected, and based on vehicle-side parameters corresponding to the re-selected target candidate road condition type, the sub-road section belonging to the re-selected target candidate road condition type is identified; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; Based on the identification results of the road condition types of all the sub-road sections, the target road condition type to which the target road section belongs is determined.

[0089] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0090] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0091] In the description of this application, it should be understood that if the terms "up", "down", "front", "back", "left" and "right" are used to indicate directions or positional relationships, they are based on the directions or positional relationships shown in the accompanying drawings. They are only used to facilitate the description of the present invention and simplify the description, and do not indicate or imply that the positions or elements referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limitations of this application.

[0092] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. It should also be noted that the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, commodity, or device comprising the element.

[0093] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for identifying vehicle road conditions, characterized in that: include: Determine the target road section of the road condition type to be identified during vehicle driving; Splitting the target road segment into at least two sub-road segments; Selecting a target candidate road condition type from a plurality of predefined road condition types, and identifying the sub-road section belonging to the target candidate road condition type based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section; and, if the sub-road segment for which the road condition type has not been identified exists, reselecting a target candidate road condition type from the road condition types that have not been selected among the multiple road condition types, and identifying the sub-road segment belonging to the reselected target candidate road condition type based on the vehicle-side parameters corresponding to the reselected target candidate road condition type; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; Based on the identification results of the road condition types of all the sub-road sections, the target road condition type to which the target road section belongs is determined.

2. The method according to claim 1, characterized in that The step of determining a target road section for a road condition type to be identified during vehicle travel includes: A road section whose road condition type cannot be determined through the navigation map during the vehicle's driving process is determined as the target road section.

3. The method according to claim 1, characterized in that Determining the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections includes: Determining a target road condition type to which the target road section belongs based on the proportions of road condition types corresponding to all the sub-road sections; or, The traffic condition types of all the sub-road sections are collectively used as the target traffic condition type to which the target road section belongs.

4. The method according to claim 1, wherein The step of determining the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections is performed when any of the following conditions is met: The road condition types of all the sub-road sections of the target road section have been identified; There is no new target candidate road condition type available for selection among the multiple road condition types.

5. The method according to any one of claims 1 to 4, characterized in that The multiple road condition types include an off-road road condition type, and the vehicle-side parameters corresponding to the off-road road condition type include a driving mode; If the target candidate road condition type is the off-road road condition type, identifying the sub-road section belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section includes: For the sub-road section where the driving mode is indicated as the off-road related mode, the road condition type thereof is identified as the off-road road condition type.

6. The method according to any one of claims 1 to 4, characterized in that The multiple road condition types include an urban road condition type, a general road condition type, and a highway road condition type, and the vehicle-side parameters corresponding to the urban road condition type, the general road condition type, and the highway road condition type include a driving speed; If the target candidate road condition type is the urban road condition type, the general road condition, and the expressway condition type, then identifying the sub-road section belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section includes: Using driving speed as a clustering feature, the theoretical driving speed values corresponding to the pre-defined urban road condition type, the general road condition type, and the highway road condition type are used as initial cluster centers, and the sub-segments for which no road condition type is identified are clustered; For the sub-segments of the cluster belonging to the urban road condition type after clustering, their road condition type is identified as the urban road condition type; for the sub-segments of the cluster belonging to the general road condition type after clustering, their road condition type is identified as the general road condition type; for the sub-segments of the cluster belonging to the expressway condition type after clustering, their road condition type is identified as the expressway condition type.

7. The method according to any one of claims 1 to 4, characterized in that The multiple road condition types include a mountainous road condition type, and the vehicle-side parameters corresponding to the mountainous road condition type include an altitude change parameter and a turning angle ratio parameter; If the target candidate road condition type is the mountain road condition type, identifying the sub-road section belonging to the target candidate road condition type based on the vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section includes: For the sub-section where the altitude change parameter indicates that the altitude change within a unit distance is greater than a preset altitude change threshold, the angle ratio parameter indicates that the steering wheel angle is greater than a preset angle threshold, and the duration ratio is greater than a preset ratio threshold, the road condition type is determined to be the mountainous road condition type; For the sub-section where the altitude change parameter indicates that the altitude change within a unit distance is greater than a preset altitude change threshold, and the angle ratio parameter indicates that the number of steering wheel angle direction switches within a unit time is greater than a first preset number threshold, determining the road condition type as the mountainous road condition type; For the sub-section where the altitude change parameter indicates that the number of positive and negative switching of the altitude change rate per unit distance is greater than a second preset number threshold, and the angle ratio parameter indicates that the steering wheel angle amount is greater than a preset angle amount threshold and the duration ratio is greater than a preset ratio threshold, the road condition type is determined to be the mountainous road condition type; For the sub-section where the altitude change parameter indicates that the number of positive and negative switching of the altitude change rate within a unit distance is greater than the second preset number threshold, and the angle ratio parameter indicates that the number of steering wheel angle direction switching within a unit time is greater than the first preset number threshold, its road condition type is determined to be the mountain road condition type.

8. A vehicle driving road condition recognition device, characterized in that: include: A road section determination module, used to determine a target road section of a road condition type to be identified during vehicle travel; A road segment splitting module, configured to split the target road segment into at least two sub-road segments; an iterative identification module, configured to select a target candidate road condition type from a plurality of predefined road condition types, and identify the sub-road section belonging to the target candidate road condition type based on vehicle-side parameters of the vehicle corresponding to the target candidate road condition type in each sub-road section; and, if the sub-road segment for which the road condition type has not been identified exists, reselecting a target candidate road condition type from the road condition types that have not been selected among the multiple road condition types, and identifying the sub-road segment belonging to the reselected target candidate road condition type based on the vehicle-side parameters corresponding to the reselected target candidate road condition type; wherein the vehicle-side parameters corresponding to any of the road condition types are affected by the road condition type; The comprehensive identification module is used to determine the target road condition type to which the target road section belongs based on the identification results of the road condition types of all the sub-road sections.

9. A vehicle comprising: processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images