Vehicle using scene recognition method, device and equipment and storage medium

Abstract

The invention discloses a vehicle using scene recognition method, device and equipment and a storage medium. The method comprises the following steps: acquiring a plurality of driving cycle data corresponding to different vehicles in original data; extracting driving scene features of each driving cycle from the plurality of driving cycle data; according to the driving scene features, each piece of driving cycle data is labeled with a category label so as to classify the driving cycle data, and driving cycles in the same category label are defined based on the defined vehicle using scene so as to determine the vehicle using scene corresponding to each driving cycle; and identifying the vehicle use scene of the vehicle according to the proportion of the vehicle use scene corresponding to the driving cycle in the same category. According to the invention, the vehicle usage scene can be accurately identified, and development resources are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle use scene recognition, and in particular to a vehicle use scene recognition method, device, equipment and storage medium. Background Art

[0002] The economic performance of diesel light trucks in the market is closely related to the scenarios in which they are used. When the same calibration strategy is used, the energy consumption deviation per 100 kilometers in different scenarios may be as high as 20%. However, the experimental data collection method requires a lot of manpower, and there may be selective bias, resulting in atypical road spectra or atypical data, which will affect subsequent strategy optimization. Therefore, the product optimization of the OEM needs to turn to the vehicles that have been sold in the market and make corresponding strategy adjustments based on the actual vehicle usage scenarios. The vehicle usage scenarios mainly include analysis dimensions such as terrain conditions, road properties, and transportation cycles. It is obviously difficult to operate through offline driver feedback on their usage scenarios.

[0003] In the prior art, vehicle usage scene recognition is performed manually on real vehicles, which is labor-intensive and may result in selective bias, resulting in low accuracy in vehicle usage scene recognition.

[0004] Therefore, how to accurately identify vehicle usage scenarios and save development resources is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the present invention is to provide a vehicle usage scene recognition method, device, equipment and storage medium, which can accurately identify vehicle usage scenes, save development resources, and provide data support for research and development.

[0006] In a first aspect, the present application provides a vehicle scene recognition method, wherein the method comprises the steps of:

[0007] Acquire multiple driving cycle data corresponding to different vehicles in the original data;

[0008] Extracting driving scene features of each driving cycle from the plurality of driving cycle data;

[0009] According to the driving scenario characteristics, each driving cycle data is labeled with a category label to classify the driving cycle data, and driving cycles in the same category label are defined based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle;

[0010] The vehicle usage scenarios are identified by the proportion of vehicle usage scenarios corresponding to the driving cycle in the same category.

[0011] In combination with the first aspect, as an optional implementation method, based on the purpose and use environment of the vehicle, a vehicle use scenario is defined, wherein the purpose includes: fixed-point operation type, township transportation type, urban logistics type, and trunk logistics type, and the use environment includes: climbing type and ordinary type;

[0012] If it is determined that in the driving characteristics corresponding to the driving cycle, the proportion of the vehicle speed in the first speed range is the highest, the number of starts and stops per kilometer is greater than the first threshold, and the proportion of the economic range is less than or equal to the first set percentage, then the driving cycle is defined as a fixed-point operation type;

[0013] If the vehicle speed is in the second speed range with the highest proportion, and the number of starts and stops per kilometer is greater than or equal to the second threshold, and the economic proportion interval is greater than or equal to the second set percentage, then the driving cycle is defined as a township transportation type;

[0014] If the vehicle speed is in the third speed range with the highest proportion, the number of starts and stops per kilometer is less than the second threshold, and the economic proportion interval is in the first percentage interval, then the driving cycle is defined as the urban logistics type;

[0015] If the vehicle speed is the highest above the fourth speed, the number of starts and stops per kilometer is less than the third threshold, and the economic zone accounts for more than the third set percentage, then the driving cycle is defined as a trunk logistics type;

[0016] If the cumulative pitch angle per kilometer of the driving cycle is greater than the set angle, it is marked as a climbing type; if it is less than the set angle, it is marked as a normal type;

[0017] By combining the vehicle's purpose and usage environment, the vehicle usage scenario corresponding to each driving cycle is determined.

[0018] In combination with the first aspect, as an optional implementation, raw data is obtained, the raw data including operating condition data of different vehicle models and different time periods, wherein the operating condition data includes: vehicle speed, engine speed, net output torque, instantaneous fuel injection amount and pitch angle;

[0019] Each vehicle is sorted in chronological order, and the time difference between two adjacent data is calculated to obtain the time difference between the two adjacent data;

[0020] If the time difference exceeds the set time, the vehicle is determined to be turned off, and each time the vehicle is turned off is marked as a driving cycle;

[0021] According to the driving cycle marking result, a plurality of driving cycle data corresponding to each vehicle are obtained.

[0022] In combination with the first aspect, as an optional implementation, according to the driving scene features of each driving cycle extracted from the data set, the driving scene features are used as adjustment parameters of the clustering model;

[0023] The driving cycle data is input into the clustering model, and a category label is assigned to each driving cycle to output a classification result of the driving cycle data.

[0024] In combination with the first aspect, as an optional implementation, a vehicle speed distribution feature, a start-stop frequency feature, a terrain feature, an energy consumption feature, and a driving behavior feature of each driving cycle are extracted; wherein the extraction of the vehicle speed distribution feature includes: for each driving cycle data segment, respectively extracting a duration of the vehicle speed in a first interval, a duration of the vehicle speed in a second interval, a duration of the vehicle speed in a third interval, and a duration of the vehicle speed in a fourth interval;

[0025] The start-stop number feature extraction includes: for each driving cycle data segment, extracting all vehicle speeds decreasing from a first speed to a second speed;

[0026] The data segments are continuously kept at the second speed for a set time or longer, and the number of data segments that meet the conditions is counted, and the parking and shutdown parts of the corresponding driving cycle data segments are removed as the start-stop number feature;

[0027] The extraction of terrain features includes: for each driving cycle data segment, based on pitch angle information, counting the vehicle's ramp climbing and descending in the driving cycle, wherein the pitch angle is the Y-axis angle collected by the vehicle's six-axis gyroscope, with a positive value indicating climbing and a negative value indicating descending;

[0028] The energy consumption characteristics extraction includes: taking the engine fuel efficiency greater than or equal to a set percentage as the economic interval, calculating the proportion of all vehicle operating condition data falling within the interval, and calculating the average fuel efficiency and average energy consumption of the engine;

[0029] The extraction of the driving behavior characteristics includes: taking the change in vehicle speed between two seconds greater than the set speed as the sudden acceleration threshold, and less than the set speed as the sudden deceleration threshold, counting the number of corresponding events in each driving cycle, and dividing it by the mileage of the driving cycle to obtain the number of sudden accelerations per kilometer and the number of sudden decelerations per kilometer.

[0030] In combination with the first aspect, as an optional implementation manner, it is determined whether there is a scattered point in the category label, wherein the scattered point is a category label of -1;

[0031] If it exists, the scattered points are removed.

[0032] In combination with the first aspect above, as an optional implementation method, in the same category, if the proportion of vehicle usage scenarios corresponding to any driving cycle is greater than a set threshold, the vehicle usage scenarios corresponding to the driving cycle will be used as vehicle usage scenarios for this category.

[0033] In a second aspect, the present application provides a vehicle scene recognition device, the device comprising:

[0034] An acquisition module, which is used to acquire a plurality of driving cycle data corresponding to different vehicles in the original data;

[0035] An extraction module, configured to extract driving scene features of each driving cycle from the plurality of driving cycle data;

[0036] A processing module, which is used to label each driving cycle data with a category label according to the driving scene characteristics to classify the driving cycle data, and define driving cycles in the same category label based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle;

[0037] The identification module is used to identify the vehicle usage scenario of the vehicle by the proportion of the vehicle usage scenarios corresponding to the driving cycle in the same category.

[0038] In a third aspect, the present application further provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method described in any one of the first aspects is implemented.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium storing computer program instructions, which, when executed by a computer, enables the computer to execute any of the methods described in the first aspect.

[0040] The present application provides a method, device, equipment and storage medium for identifying vehicle usage scenarios, wherein the method includes the following steps: obtaining multiple driving cycle data corresponding to different vehicles in the original data; extracting the driving scenario features of each driving cycle from the multiple driving cycle data; labeling each driving cycle data with a category label according to the driving scenario features to classify the driving cycle data, and defining the driving cycles in the same category label based on the defined vehicle usage scenarios to determine the vehicle usage scenarios corresponding to each driving cycle; identifying the vehicle usage scenarios of the vehicle by the proportion of the vehicle usage scenarios corresponding to the driving cycles in the same category. The present application can accurately identify vehicle usage scenarios, save development resources, and provide data support for research and development.

[0041] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0043] Figure 1 A flow chart of a vehicle scene recognition method provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a vehicle scene recognition device provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of a computer-readable program medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0048] Furthermore, the drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. Some of the blocks shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities.

[0049] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0050] Reference Figure 1 , Figure 1 FIG. 1 is a flow chart of a vehicle scene recognition method provided by the present invention. Figure 1 As shown, the method comprises the steps of:

[0051] Step S101: Acquire multiple driving cycle data corresponding to different vehicles in the original data.

[0052] Specifically, raw data is obtained, wherein the raw data includes operating data of different vehicle models and different time periods, wherein the operating data includes: vehicle speed, engine speed, net output torque, instantaneous fuel injection amount and pitch angle; each vehicle is sorted in chronological order, and the time difference between two adjacent data is subtracted to obtain the time difference between the two adjacent data; if the time difference exceeds the set time length, it is determined that the vehicle is stalled, and each stall is marked as a driving cycle; according to the driving cycle marking results, multiple driving cycle data corresponding to each vehicle are obtained.

[0053] For ease of understanding, let's take an example. The original data refers to the vehicle operating data collected and transmitted through T-Box (Telemat ics BOX, referred to as on-board T-BOX) and stored in the big data platform; the operating data covers the commonly used measurement points of diesel light trucks, such as vehicle speed, engine speed, net output torque, instantaneous injection volume, pitch angle and other variables.

[0054] 1-1) Constructing a driving cycle marker;

[0055] Step 1-1) Construct a driving cycle marker. The original data contains data from multiple vehicles and multiple time periods. Each vehicle is sorted in chronological order. The time difference between two adjacent data is calculated to obtain the time difference between the two adjacent data in seconds. The National VI protocol requires a sampling rate of 1Hz, so the time difference between two adjacent data is 1 second. In order to eliminate the impact of data interruption on the judgment of driving cycle continuity, when the time difference exceeds 60 seconds, the vehicle is judged to be turned off and enter the next driving cycle. An integer is used to mark the driving cycle, starting from 0. Each time the flameout judgment condition is triggered, the marker is increased by 1 to form the corresponding driving cycle marker.

[0056] 1-2) Split vehicle operating condition data.

[0057] Step 1-2) According to the driving cycle labeling results, each vehicle will have corresponding multiple driving cycle data. The original data is split with the vehicle and driving cycle label as the grouping unit to form a data set to be extracted.

[0058] It should be explained that the driving cycle data is from vehicle startup to vehicle shutdown, which is one driving cycle.

[0059] Step S102: extracting driving scene features of each driving cycle from the plurality of driving cycle data.

[0060] Specifically, the vehicle speed distribution characteristics, start-stop frequency characteristics, terrain characteristics, energy consumption characteristics and driving behavior characteristics of each driving cycle are extracted; wherein the extraction of the vehicle speed distribution characteristics includes: for each driving cycle data segment, respectively extracting the duration of the vehicle speed in the first interval, the duration of the vehicle speed in the second interval, the duration of the vehicle speed in the third interval, and the duration of the vehicle speed in the fourth interval;

[0061] The start-stop number feature extraction includes: for each driving cycle data segment, extracting all vehicle speeds decreasing from a first speed to a second speed;

[0062] The data segments are continuously kept at the second speed for a set time or longer, and the number of data segments that meet the conditions is counted, and the parking and shutdown parts of the corresponding driving cycle data segments are removed as the start-stop number feature;

[0063] The extraction of terrain features includes: for each driving cycle data segment, based on pitch angle information, counting the vehicle's ramp climbing and descending in the driving cycle, wherein the pitch angle is the Y-axis angle collected by the vehicle's six-axis gyroscope, with a positive value indicating climbing and a negative value indicating descending;

[0064] The energy consumption characteristics extraction includes: taking the engine fuel efficiency greater than or equal to a set percentage as the economic interval, calculating the proportion of all vehicle operating condition data falling within the interval, and calculating the average fuel efficiency and average energy consumption of the engine;

[0065] The extraction of the driving behavior characteristics includes: taking the change in vehicle speed between two seconds greater than the set speed as the sudden acceleration threshold, and less than the set speed as the sudden deceleration threshold, counting the number of corresponding events in each driving cycle, and dividing it by the mileage of the driving cycle to obtain the number of sudden accelerations per kilometer and the number of sudden decelerations per kilometer.

[0066] For easy understanding, an example is given, 2-1) extracting vehicle speed distribution characteristics;

[0067] Step 2-1) The data distribution of vehicle speed is the key data to describe the timeliness and period of vehicle use. Based on the data set to be extracted in step 1-2), for each driving cycle data segment, extract the duration of vehicle speed of 0 km / h, the duration of vehicle speed between 1 km / h and 20 km / h, the duration of vehicle speed between 21 km / h and 70 km / h, and the duration of vehicle speed above 71 km / h, to form four basic features;

[0068] 2-2) Extract the start-stop frequency features;

[0069] Step 2-2) Extract the start-stop frequency feature. For each driving cycle data segment, extract all data segments where the vehicle speed decreases from greater than 2 km / h to 0 km / h and remains at 0 km / h for more than 10 seconds. Count the number of data segments that meet the conditions, and remove the parking and shutdown parts of the corresponding driving cycle data segments as the start-stop frequency key feature to form one key feature.

[0070] 2-3) Extract terrain features;

[0071] Step 2-3) Extract terrain features. For each driving cycle data segment, based on the key information of pitch angle, count the vehicle's slope climbing and descending in the driving cycle. The pitch angle is the Y-axis angle collected by the vehicle's six-axis gyroscope. Positive values ​​are climbing and negative values ​​are descending. Count the cumulative slope changes of each driving cycle data segment and divide it by the total mileage to form a key feature.

[0072] 2-4) Extracting energy consumption characteristics;

[0073] Step 2-4) extracting energy consumption features, taking the engine fuel efficiency greater than or equal to 40% as the economic interval, calculating the proportion of all vehicle operating data falling within this interval, and calculating the average fuel efficiency and average energy consumption of the engine, and calculating the energy consumption per 100 kilometers to form three features;

[0074] 2-5) Extract driving behavior features.

[0075] Step 2-5) Extract driving behavior features, set the vehicle speed change between two seconds greater than 7km / h as the sudden acceleration threshold, and less than -7km / h as the sudden deceleration threshold. Count the number of corresponding events in each driving cycle and divide it by the mileage of the driving cycle to obtain the number of sudden accelerations per kilometer and the number of sudden decelerations per kilometer, forming two features.

[0076] Step S103: According to the driving scenario characteristics, each driving cycle data is labeled with a category label to classify the driving cycle data, and the driving cycles in the same category label are defined based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle.

[0077] Specifically, according to the driving scene features of each driving cycle extracted from the data set, the driving scene features are used as adjustment parameters of the clustering model; the driving cycle data are input into the clustering model, and a category label is assigned to each driving cycle to output the classification result of the driving cycle data (wherein, it should be explained that the classification result is to label the same type of data, such as label 1, label 2, label 3, etc., and there are multiple driving cycles in each label, and each driving cycle is identified. For example, 6 out of 10 driving cycles in label 1 are trunk logistics, then the vehicle use scenario of label 1 is trunk logistics, and there are 5 driving cycles in label 2, and 3 driving cycles are indoor logistics, then it is judged that the vehicle use scenario of the label is indoor logistics).

[0078] Based on 11 features corresponding to each driving cycle segment calculated in steps 2-1 to 2-5, the DBSCAN density clustering algorithm is used to divide the driving cycle segments into N categories according to the density of data clustering. After clustering by the DBSCAN algorithm, each driving cycle will be assigned a category label, and driving cycles with the same category label are of the same category. -1 in the clustering result represents a scattered point, which does not belong to any category, and the corresponding driving cycle data is no longer considered. The DBSCAN density clustering algorithm is a typical unsupervised machine learning algorithm, which is suitable for assigning unlabeled data to corresponding categories according to the density of distribution, without pre-determining the number of clustering categories, and is suitable for the recognition of diesel light truck usage scenarios.

[0079] Based on the defined vehicle usage scenarios, driving cycles in the same category tags are defined to determine the vehicle usage scenarios corresponding to each driving cycle, including: based on the purpose and usage environment of the vehicle, the vehicle usage scenarios are defined, the purposes include: fixed-point operation type, township transportation type, urban logistics type and trunk logistics type, and the usage environment includes: climbing type and ordinary type;

[0080] If it is determined that in the driving characteristics corresponding to the driving cycle, the proportion of the vehicle speed in the first speed range is the highest, the number of starts and stops per kilometer is greater than the first threshold, and the proportion of the economic range is less than or equal to the first set percentage, then the driving cycle is defined as a fixed-point operation type;

[0081] If the vehicle speed is in the second speed range with the highest proportion, and the number of starts and stops per kilometer is greater than or equal to the second threshold, and the economic proportion interval is greater than or equal to the second set percentage, then the driving cycle is defined as a township transportation type;

[0082] If the vehicle speed is in the third speed range with the highest proportion, the number of starts and stops per kilometer is less than the second threshold, and the economic proportion interval is in the first percentage interval, then the driving cycle is defined as the urban logistics type;

[0083] If the vehicle speed is the highest above the fourth speed, the number of starts and stops per kilometer is less than the third threshold, and the economic zone accounts for more than the third set percentage, the driving cycle is defined as a trunk logistics type; if the cumulative pitch angle per kilometer of the driving cycle is greater than the set angle, it is marked as a climbing type; if it is less than the set angle, it is marked as a normal type;

[0084] By combining the vehicle's purpose and usage environment, the vehicle usage scenario corresponding to each driving cycle is determined.

[0085] For easier understanding, examples are given to define vehicle usage scenarios from the two perspectives of purpose and environment.

[0086] Further analysis based on 3 months of data from 100 vehicles can yield corresponding type definitions and corresponding characteristic thresholds. From the perspective of vehicle use, vehicles with a speed of 1-20 km / h account for the highest proportion and with more than 5 starts and stops per kilometer, and an economic range of less than or equal to 20%, are defined as fixed-point operation types;

[0087] The vehicle speed is 20-70 km / h, the number of starts and stops per kilometer is greater than or equal to 0.4 times, and the economic proportion is greater than or equal to 70%, which is defined as township transportation;

[0088] The vehicles with the highest speed of 30-70km / h, less than 0.4 starts and stops per kilometer and an economic ratio of 50%-70% are defined as urban logistics;

[0089] Trunk logistics are defined as those that meet the conditions where vehicle speeds are above 71km / h, the economic zone accounts for more than 70%, and the number of starts and stops per kilometer is less than 0.2 times.

[0090] From the perspective of vehicle usage environment, if the cumulative pitch angle per kilometer in the driving cycle is greater than 10 degrees, it is marked as a climbing type; if it is less than 10 degrees, it is marked as a normal type. By combining the vehicle's purpose and usage environment, the vehicle's actual usage scenario (such as climbing trunk logistics and normal trunk logistics) is determined to achieve usage scenario recognition.

[0091] Step S104: Identify the vehicle usage scenario of the vehicle by the proportion of the vehicle usage scenarios corresponding to the driving cycle in the same category.

[0092] Specifically, in the same category, if the proportion of vehicle usage scenarios corresponding to any driving cycle is greater than the set threshold, the vehicle usage scenario corresponding to the driving cycle will be used as the vehicle usage scenario for this category. It can be understood that there are three categories, the first, second and third categories, and there are 8 driving cycles in each category. If the first category identifies that 6 driving cycles for the application vehicle scenario are township transportation, then the vehicle usage scenario corresponding to this type is township transportation. That is, when a certain category accounts for more than 50% of all driving cycle categories of the previous day, this category is used as the vehicle usage scenario of the current type. At the same time, this category is used as the analysis result of the previous day's data and recorded in the database for analysis by other applications.

[0093] To summarize, this application solves the problems of low coverage and sampling deviation that may exist when relying on real vehicle experiments to collect scene data. The use of market stock data can cover more vehicle usage scenarios and improve the accuracy of analysis. Under the condition of defining the vehicle usage scenario, it can provide key road spectrum data for the corresponding scenario, provide a basic data reference for subsequent experiments and tuning, and provide vehicle usage scenario markers for vehicles, which is convenient for subsequent OTA upgrades and reduces the overall cost of vehicle use.

[0094] Reference Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a vehicle scene recognition device provided by the present invention, such as Figure 2 As shown, the device comprises:

[0095] The acquisition module 201 is used to acquire a plurality of driving cycle data corresponding to different vehicles in the original data.

[0096] The extraction module 202 is used to extract the driving scene features of each driving cycle from the plurality of driving cycle data.

[0097] Processing module 203: It is used to label each driving cycle data with a category label according to the driving scenario characteristics to classify the driving cycle data, and define the driving cycles in the same category label based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle.

[0098] The identification module 204 is used to identify the vehicle usage scenario of the vehicle according to the proportion of the vehicle usage scenarios corresponding to the driving cycles in the same category.

[0099] Further, in a possible implementation, the processing module is further used to define a vehicle usage scenario based on the purpose and usage environment of the vehicle, wherein the purpose includes: fixed-point operation type, township transportation type, urban logistics type and trunk logistics type, and the usage environment includes: climbing type and ordinary type;

[0100] If it is determined that in the driving characteristics corresponding to the driving cycle, the proportion of the vehicle speed in the first speed range is the highest, the number of starts and stops per kilometer is greater than the first threshold, and the proportion of the economic range is less than or equal to the first set percentage, then the driving cycle is defined as a fixed-point operation type;

[0101] If the vehicle speed is in the second speed range with the highest proportion, and the number of starts and stops per kilometer is greater than or equal to the second threshold, and the economic proportion interval is greater than or equal to the second set percentage, then the driving cycle is defined as a township transportation type;

[0102] If the vehicle speed is in the third speed range with the highest proportion, the number of starts and stops per kilometer is less than the second threshold, and the economic proportion interval is in the first percentage interval, then the driving cycle is defined as the urban logistics type;

[0103] If the vehicle speed is the highest above the fourth speed, the number of starts and stops per kilometer is less than the third threshold, and the economic zone accounts for more than the third set percentage, then the driving cycle is defined as a trunk logistics type;

[0104] If the cumulative pitch angle per kilometer of the driving cycle is greater than the set angle, it is marked as a climbing type; if it is less than the set angle, it is marked as a normal type;

[0105] By combining the vehicle's purpose and usage environment, the vehicle usage scenario corresponding to each driving cycle is determined.

[0106] Further, in a possible implementation manner, the acquisition module is further used to acquire raw data, wherein the raw data includes operating condition data of different vehicle models and different time periods, wherein the operating condition data includes: vehicle speed, engine speed, net output torque, instantaneous fuel injection amount and pitch angle;

[0107] Each vehicle is sorted in chronological order, and the time difference between two adjacent data is calculated to obtain the time difference between the two adjacent data;

[0108] If the time difference exceeds the set time, the vehicle is determined to be turned off, and each time the vehicle is turned off is marked as a driving cycle;

[0109] According to the driving cycle marking result, a plurality of driving cycle data corresponding to each vehicle are obtained.

[0110] Furthermore, in a possible implementation manner, the processing module is further configured to use the driving scene features of each driving cycle extracted from the data set as adjustment parameters of the clustering model;

[0111] The driving cycle data is input into the clustering model, and a category label is assigned to each driving cycle to output a classification result of the driving cycle data.

[0112] Furthermore, in a possible implementation manner, the extraction module is further used to extract vehicle speed distribution characteristics, start-stop frequency characteristics, terrain characteristics, energy consumption characteristics and driving behavior characteristics of each driving cycle; wherein the extraction of the vehicle speed distribution characteristics comprises: for each driving cycle data segment, respectively extracting the duration of the vehicle speed in the first interval, the duration of the vehicle speed in the second interval, the duration of the vehicle speed in the third interval, and the duration of the vehicle speed in the fourth interval;

[0113] The start-stop number feature extraction includes: for each driving cycle data segment, extracting all vehicle speeds decreasing from a first speed to a second speed;

[0114] The data segments are continuously kept at the second speed for a set time or longer, and the number of data segments that meet the conditions is counted, and the parking and shutdown parts of the corresponding driving cycle data segments are removed as the start-stop number feature;

[0115] The extraction of terrain features includes: for each driving cycle data segment, based on pitch angle information, counting the vehicle's ramp climbing and descending in the driving cycle, wherein the pitch angle is the Y-axis angle collected by the vehicle's six-axis gyroscope, with a positive value indicating climbing and a negative value indicating descending;

[0116] The energy consumption characteristics extraction includes: taking the engine fuel efficiency greater than or equal to a set percentage as the economic interval, calculating the proportion of all vehicle operating condition data falling within the interval, and calculating the average fuel efficiency and average energy consumption of the engine;

[0117] The extraction of the driving behavior characteristics includes: taking the change in vehicle speed between two seconds greater than the set speed as the sudden acceleration threshold, and less than the set speed as the sudden deceleration threshold, counting the number of corresponding events in each driving cycle, and dividing it by the mileage of the driving cycle to obtain the number of sudden accelerations per kilometer and the number of sudden decelerations per kilometer.

[0118] Furthermore, in a possible implementation manner, the processing module is further configured to determine whether there is a scattered point in the category label, wherein the scattered point is a category label of -1;

[0119] If it exists, the scattered points are removed.

[0120] Furthermore, in a possible implementation, the identification module is also used to, in the same category, if the proportion of vehicle usage scenarios corresponding to any driving cycle is greater than a set threshold, use the vehicle usage scenarios corresponding to the driving cycle as vehicle usage scenarios for the category.

[0121] Refer to the following Figure 3 The electronic device 300 according to this embodiment of the present invention will be described. Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0122] like Figure 3 As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include but are not limited to: at least one processing unit 310, at least one storage unit 320, and a bus 330 connecting different system components (including the storage unit 320 and the processing unit 310).

[0123] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0124] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 321 and / or a cache memory unit 322 , and may further include a read-only memory unit (ROM) 323 .

[0125] The storage unit 320 may also include a program / utility 324 having a set (at least one) of program modules 325, such program modules 325 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0126] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0127] The electronic device 300 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 300, and / or communicate with any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 360. As shown, the network adapter 360 communicates with other modules of the electronic device 300 via a bus 330. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0128] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0129] According to the solution of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present invention described in the above "Exemplary Method" section of the present specification.

[0130] refer to Figure 4 As shown, a program product 400 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0131] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0132] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0133] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0134] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0135] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0136] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

[0137] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

Claims

1. A vehicle scene recognition method, characterized in that: include: Acquire multiple driving cycle data corresponding to different vehicles in the original data; Extracting driving scene features of each driving cycle from the plurality of driving cycle data; According to the driving scenario characteristics, each driving cycle data is labeled with a category label to classify the driving cycle data, and driving cycles in the same category label are defined based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle; The vehicle usage scenarios are identified by the proportion of vehicle usage scenarios corresponding to the driving cycle in the same category.

2. The method according to claim 1, characterized in that Defining driving cycles in the same category label based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle includes: Based on the purpose and use environment of the vehicle, define the vehicle use scenarios. The purpose includes: fixed-point operation type, township transportation type, urban logistics type and trunk logistics type. The use environment includes: climbing type and ordinary type. If it is determined that in the driving characteristics corresponding to the driving cycle, the proportion of the vehicle speed in the first speed range is the highest, the number of starts and stops per kilometer is greater than the first threshold, and the proportion of the economic range is less than or equal to the first set percentage, then the driving cycle is defined as a fixed-point operation type; If the vehicle speed is in the second speed range with the highest proportion, and the number of starts and stops per kilometer is greater than or equal to the second threshold, and the economic proportion interval is greater than or equal to the second set percentage, then the driving cycle is defined as a township transportation type; If the vehicle speed is in the third speed range with the highest proportion, the number of starts and stops per kilometer is less than the second threshold, and the economic proportion interval is in the first percentage interval, then the driving cycle is defined as the urban logistics type; If the vehicle speed is the highest above the fourth speed, the number of starts and stops per kilometer is less than the third threshold, and the economic zone accounts for more than the third set percentage, then the driving cycle is defined as a trunk logistics type; If the cumulative pitch angle per kilometer of the driving cycle is greater than the set angle, it is marked as a climbing type; if it is less than the set angle, it is marked as a normal type; By combining the vehicle's purpose and usage environment, the vehicle usage scenario corresponding to each driving cycle is determined.

3. The method according to claim 1, characterized in that The step of obtaining a plurality of driving cycle data corresponding to different vehicles in the original data includes: Acquire raw data, wherein the raw data includes operating condition data of different vehicle models and different time periods, wherein the operating condition data includes: vehicle speed, engine speed, net output torque, instantaneous fuel injection amount and pitch angle; Each vehicle is sorted in chronological order, and the time difference between two adjacent data is calculated to obtain the time difference between the two adjacent data; If the time difference exceeds the set time, the vehicle is determined to be turned off, and each time the vehicle is turned off is marked as a driving cycle; According to the driving cycle marking result, a plurality of driving cycle data corresponding to each vehicle are obtained.

4. The method according to claim 1, characterized in that: According to the driving scene characteristics, Each driving cycle data is labeled with a category label to classify the driving cycle data, including: According to the driving scene features of each driving cycle extracted from the data set, the driving scene features are used as adjustment parameters of the clustering model; The driving cycle data is input into the clustering model, and a category label is assigned to each driving cycle to output a classification result of the driving cycle data.

5. The method according to claim 1, characterized in that The extracting the driving scene feature of each driving cycle from the plurality of driving cycle data comprises: Extracting vehicle speed distribution characteristics, start-stop frequency characteristics, terrain characteristics, energy consumption characteristics and driving behavior characteristics of each driving cycle; wherein the extraction of the vehicle speed distribution characteristics comprises: for each driving cycle data segment, respectively extracting the duration of the vehicle speed in the first interval, the duration of the vehicle speed in the second interval, the duration of the vehicle speed in the third interval, and the duration of the vehicle speed in the fourth interval; The start-stop number feature extraction includes: for each driving cycle data segment, extracting all vehicle speeds decreasing from a first speed to a second speed; The data segments are continuously kept at the second speed for a set time or longer, and the number of data segments that meet the conditions is counted, and the parking and shutdown parts of the corresponding driving cycle data segments are removed as the start-stop number feature; The extraction of terrain features includes: for each driving cycle data segment, based on pitch angle information, counting the vehicle's ramp climbing and descending in the driving cycle, wherein the pitch angle is the Y-axis angle collected by the vehicle's six-axis gyroscope, with a positive value indicating climbing and a negative value indicating descending; The energy consumption characteristics extraction includes: taking the engine fuel efficiency greater than or equal to a set percentage as the economic interval, calculating the proportion of all vehicle operating condition data falling within the interval, and calculating the average fuel efficiency and average energy consumption of the engine; The extraction of the driving behavior characteristics includes: taking the change in vehicle speed between two seconds greater than the set speed as the sudden acceleration threshold, and less than the set speed as the sudden deceleration threshold, counting the number of corresponding events in each driving cycle, and dividing it by the mileage of the driving cycle to obtain the number of sudden accelerations per kilometer and the number of sudden decelerations per kilometer.

6. The method according to claim 4, characterized in that Also includes: Determine whether there is a scattered point in the category label, wherein the scattered point is a category label of -1; If it exists, the scattered points are removed.

7. The method according to claim 1, characterized in that The proportion of vehicle usage scenarios corresponding to the driving cycle in the same category to identify the vehicle usage scenarios includes: In the same category, if the proportion of vehicle usage scenarios corresponding to any driving cycle is greater than the set threshold, the vehicle usage scenarios corresponding to the driving cycle will be used as the vehicle usage scenarios of this category.

8. A vehicle scene recognition device, characterized in that: include: An acquisition module, which is used to acquire a plurality of driving cycle data corresponding to different vehicles in the original data; An extraction module, configured to extract driving scene features of each driving cycle from the plurality of driving cycle data; A processing module, which is used to label each driving cycle data with a category label according to the driving scene characteristics to classify the driving cycle data, and define driving cycles in the same category label based on the defined vehicle usage scenario to determine the vehicle usage scenario corresponding to each driving cycle; The identification module is used to identify the vehicle usage scenario of the vehicle by the proportion of the vehicle usage scenarios corresponding to the driving cycle in the same category.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer program instructions are stored therein, and when the computer program instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images