Vehicle operation scene label labeling method and device, equipment and storage medium

Abstract

The invention discloses a vehicle operation scene label labeling method, device and equipment and a computer readable storage medium, and the method comprises the steps: carrying out the preprocessing of a plurality of groups of obtained vehicle operation data according to a preset preprocessing rule, and generating a plurality of groups of target vehicle operation data; generating a feature curve graph based on the multiple groups of target vehicle operation data and a preset feature counter; based on a preset AI model, according to the feature curve graph, obtaining a clustering feature graph; analyzing the clustering feature map, and determining a vehicle operation scene label corresponding to each coordinate in the clustering feature map; and labeling the vehicle operation scene label for the vehicle operation data corresponding to each coordinate, thereby solving the technical problems of easy error and relatively low labeling efficiency of manual labeling of the label of the vehicle operation scene in the related technology, realizing labeling of the vehicle operation scene labels of different vehicle operation data through machine learning, and improving the labeling efficiency of the vehicle operation scene. And the accuracy and the efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and computer-readable storage medium for labeling vehicle operation scene labels. Background Art

[0002] Machine learning includes unsupervised learning, semi-supervised learning and supervised learning. Both semi-supervised learning and supervised learning require the use of labeled data for learning. At present, vehicles have become one of the indispensable means of transportation in people's lives. Different vehicle functions can be selected through different vehicle operation scenarios. However, the existing vehicle operation scenarios are all manually labeled by technicians or experts for the data to be learned. This not only requires technicians or experts to have a high level of professionalism, but also manual labeling is prone to errors and has low labeling efficiency. Summary of the invention

[0003] The present application provides a vehicle operation scene labeling method, device, equipment and computer-readable storage medium, which can solve the technical problems existing in the prior art that manual labeling of vehicle operation scene labels is not only prone to errors but also has low labeling efficiency.

[0004] In a first aspect, an embodiment of the present application provides a method for labeling a vehicle operation scenario label, wherein the labeling of the vehicle operation scenario label includes:

[0005] Preprocessing the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data;

[0006] Generate a characteristic curve graph based on the multiple groups of target vehicle operation data and a preset characteristic counter;

[0007] Based on the preset AI model, a clustering feature graph is obtained according to the feature curve graph;

[0008] Analyze the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph;

[0009] The vehicle operation data corresponding to each of the coordinates is labeled with the vehicle operation scene label.

[0010] In combination with the first aspect, in one implementation, obtaining a cluster feature graph based on the preset AI model and the feature curve graph includes:

[0011] Inputting the characteristic curve graph into the preset AI model;

[0012] The curve graph is clustered and analyzed by using the fuzzy C-means clustering function in the preset AI model to obtain a clustering feature graph output by the preset AI model.

[0013] In combination with the first aspect, in one implementation, analyzing the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph includes:

[0014] Analyze the cluster feature graph to obtain parameters of each coordinate in the cluster feature graph, wherein the parameters include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio;

[0015] The parameters of each of the coordinates are compared with the preset parameters to determine the vehicle operation scenario labels corresponding to each of the coordinates, wherein the vehicle operation scenario labels include fully loaded highway, fully loaded suburban, fully loaded city, unloaded highway, unloaded suburban and unloaded city.

[0016] In combination with the first aspect, in one implementation, preprocessing the acquired multiple sets of vehicle operation data according to preset preprocessing rules to generate multiple sets of target vehicle operation data includes:

[0017] Acquiring multiple groups of vehicle operation data and preset preprocessing rules, wherein the preset preprocessing rules include data filtering rules and data weighting rules;

[0018] Filtering each group of the vehicle operation data according to the vehicle speed range value in the data filtering rule to obtain multiple groups of filtered vehicle operation data;

[0019] The weight coefficients are defined for the filtered multiple groups of vehicle operation data by using the data weighting rule to generate multiple groups of target vehicle operation data.

[0020] In combination with the first aspect, in one implementation, generating a characteristic curve graph based on the multiple sets of target vehicle operation data and a preset characteristic counter includes:

[0021] The preset feature counter includes a first preset feature counter and a second preset feature counter;

[0022] The plurality of groups of target vehicle operation data are counted by using a preset long feature statistical matrix in the first preset feature statistical device to obtain a first statistical result;

[0023] The plurality of groups of target vehicle operation data are counted by using a preset short feature statistical matrix in the second preset feature statistical device to obtain a second statistical result;

[0024] The first statistical result and the second statistical result are weighted to generate a characteristic curve graph.

[0025] In combination with the first aspect, in one implementation, after obtaining the cluster feature graph according to the curve graph based on the preset AI model, the method further includes:

[0026] Analyze the cluster feature graph to obtain parameters of each center coordinate in the cluster feature graph, wherein the parameters of the center coordinate include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio;

[0027] Based on the comparison between the parameters of each of the center coordinates and the style parameters, the driving style is labeled for each group of vehicle operation data corresponding to each of the center coordinates, wherein the driving modes include aggressive, normal and gentle.

[0028] In combination with the first aspect, in one implementation, after comparing the parameters based on each of the center coordinates with the style parameters and labeling the driving style for each of the center coordinates corresponding to each group of vehicle operation data, the method further includes:

[0029] Get the current operation data of the vehicle;

[0030] Determining a driving style of a current driver according to the current operating data of the vehicle and the styles of each set of vehicle operating data;

[0031] Determining a corresponding target driving mode according to the driving style;

[0032] If the acquired current driving mode of the vehicle is inconsistent with the target driving mode, a prompt message is sent or the current driving mode of the vehicle is changed to the target driving mode.

[0033] In a second aspect, an embodiment of the present application provides a vehicle operation scene label label label label device, the vehicle operation scene label label label label device comprising:

[0034] A first generating module is used to pre-process the acquired multiple groups of vehicle operation data according to preset pre-processing rules to generate multiple groups of target vehicle operation data;

[0035] A second generating module, used for generating a characteristic curve graph based on the plurality of target vehicle operation data sets and a preset characteristic counter;

[0036] An acquisition module, used to acquire a clustering feature graph according to the feature curve graph based on a preset AI model;

[0037] A determination module, used to analyze the cluster feature graph and determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph;

[0038] The labeling module is used to label the vehicle operation data corresponding to each of the coordinates with the vehicle operation scene label.

[0039] In a third aspect, an embodiment of the present application provides a vehicle operation scenario label labeling device, the vehicle operation scenario label label labeling device comprising a processor, a memory, and a vehicle operation scenario label label labeling program stored in the memory and executable by the processor, wherein when the vehicle operation scenario label label labeling program is executed by the processor, the steps of the vehicle operation scenario label label labeling method as described above are implemented.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle operation scenario labeling program is stored. When the vehicle operation scenario labeling program is executed by a processor, the steps of the vehicle operation scenario labeling method as described above are implemented.

[0041] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0042] The method preprocesses the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data; generates a feature curve graph based on the multiple groups of target vehicle operation data and a preset feature counter; obtains a cluster feature graph based on the preset AI model and the feature curve graph; analyzes the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph; and labels the vehicle operation scene label for the vehicle operation data corresponding to each of the coordinates, thereby solving the technical problem in the related art that manual labeling of vehicle operation scenes is not only prone to errors but also has low labeling efficiency, and realizes labeling of vehicle operation scene labels for different vehicle operation data through machine learning, thereby improving accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of the first embodiment of the method for labeling vehicle operation scene labels of the present application;

[0044] Figure 2 It is a schematic diagram of characteristic curves in this application;

[0045] FIG3 is a schematic diagram of clustering features in this application;

[0046] Figure 4 This is a flow chart of a second embodiment of a method for labeling vehicle operation scene labels of the present application;

[0047] Figure 5 This is a schematic diagram of the functional modules of an embodiment of a device for labeling vehicle operation scene labels of the present application;

[0048] Figure 6 This is a schematic diagram of the hardware structure of the vehicle operation scenario labeling device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0052] In a first aspect, an embodiment of the present application provides a method for labeling vehicle operation scenario labels.

[0053] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle operation scene labeling method of the present application. Figure 1 As shown, the labeling method of the vehicle operation scene label includes:

[0054] Step S10: preprocessing the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data;

[0055] Exemplarily, multiple groups of vehicle operation data are obtained, each group of vehicle operation data includes the average speed of the vehicle, the average driving speed, the maximum speed, the parking ratio, the acceleration ratio, the deceleration ratio, the maximum acceleration, the maximum deceleration, the refueling ratio, the defueling ratio and the braking ratio. The preset preprocessing rules include data filtering rules or data weighting rules. For example, the multiple groups of vehicle operation data obtained are filtered by the data filtering rules. For example, the data filtering rules include the preset acceleration ratio 0.1m / s 2 , Preset deceleration ratio -0.1m / s 2, preset refueling ratio 5% / s, preset defueling ratio -5% / s, preset parking ratio and preset average driving speed. Compare the acceleration ratio in each set of vehicle operation data with the preset acceleration ratio 0.1m / s 2 Compare and filter out those whose acceleration ratio is less than the preset 0.1m / s 2 The acceleration ratio of each set of vehicle operation data is compared with the preset deceleration ratio -0.1m / s 2 Compare and filter the speed that is greater than the preset deceleration ratio -0.1m / s 2 deceleration ratio; compare the refueling ratio in each set of vehicle operation data with the preset refueling ratio of 5% / s, and filter the refueling ratio that is greater than the preset refueling ratio of 5% / s; compare the fuel reduction ratio in each set of vehicle operation data with the preset fuel reduction ratio of -5% / s, and filter the fuel reduction ratio that is greater than the preset fuel reduction ratio of -5% / s; filter the parking ratio of 0 in each set of vehicle operation data, and filter the average driving speed of 0 in each set of vehicle operation data, and generate multiple sets of target vehicle operation data.

[0056] Alternatively, the preset preprocessing rules include data weighting rules, which define a weight coefficient of 1 for the average speed, average driving speed, maximum speed, parking ratio, acceleration ratio, deceleration ratio, maximum acceleration, maximum deceleration, refueling ratio, refueling ratio and braking ratio in each set of vehicle operation data to generate multiple sets of target vehicle operation data.

[0057] Specifically, the method preprocesses the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data, including: acquiring multiple groups of vehicle operation data and preset preprocessing rules, wherein the preset preprocessing rules include data filtering rules and data weighting rules; filtering each group of the vehicle operation data according to the vehicle speed range value in the data filtering rules to acquire multiple groups of filtered vehicle operation data; defining weight coefficients for the filtered multiple groups of vehicle operation data according to the data weighting rules to generate multiple groups of target vehicle operation data.

[0058] Exemplarily, the preset preprocessing rules include data filtering rules and data weighting rules, and the acquired multiple sets of vehicle operation data are filtered by the data filtering rules. The data filtering rules include a preset acceleration ratio of 0.1m / s 2 , Preset deceleration ratio -0.1m / s 2 , preset refueling ratio 5% / s, preset defueling ratio -5% / s, preset parking ratio and preset average driving speed. Compare the acceleration ratio in each group of vehicle operation data with the preset acceleration ratio 0.1m / s 2Compare and filter out those whose speed is less than the preset acceleration ratio of 0.1m / s 2 The acceleration ratio of each set of vehicle operation data is compared with the preset deceleration ratio -0.1m / s 2 Compare and filter the speed that is greater than the preset deceleration ratio -0.1m / s 2 The deceleration ratio of each group of vehicle operation data is compared with the preset refueling ratio of 5% / s, and the refueling ratio greater than the preset refueling ratio of 5% / s is filtered; the reduction ratio of each group of vehicle operation data is compared with the preset reduction ratio of -5% / s, and the reduction ratio greater than the preset reduction ratio of -5% / s is filtered; the parking ratio of each group of vehicle operation data is filtered out, and the average driving speed of each group of vehicle operation data is filtered out. The weight coefficient of the average speed, average driving speed, maximum speed, parking ratio, acceleration ratio, deceleration ratio, maximum acceleration, maximum deceleration, refueling ratio, reduction ratio and braking ratio in each group of vehicle operation data after data filtering is defined as 1, and multiple groups of target vehicle operation data are generated.

[0059] Step S20: generating a characteristic curve graph based on the plurality of sets of target vehicle operation data and a preset characteristic counter;

[0060] Exemplarily, multiple groups of target vehicle operation data are input into a preset feature counter, and feature statistics are performed on each group of target vehicle operation data through the preset feature counter to generate a feature curve graph. The preset feature counter includes a long feature statistical matrix LPM (Long_Patten_Matrix) or a short feature statistical matrix SPM (Short_Patten_Matrix). The long feature statistical matrix includes starting to count from the moment when the vehicle speed / rotation speed is greater than 0 at the same time. After the counter runs for 3 hours, if the vehicle speed = 0 for 3 minutes, it is reset and counted again. The short feature statistical matrix includes starting to count from the moment when the vehicle speed / rotation speed is greater than 0 at the same time, and updating every 3 minutes.

[0061] Specifically, it includes: the preset feature statistic includes a first preset feature statistic and a second preset feature statistic; the plurality of target vehicle operation data are counted by the preset long feature statistical matrix in the first preset feature statistic to obtain a first statistical result; the plurality of target vehicle operation data are counted by the preset short feature statistical matrix in the second preset feature statistic to obtain a second statistical result; the first statistical result and the second statistical result are weighted to generate a feature curve diagram.

[0062] Exemplarily, the preset long feature statistical matrix in the first preset feature statistical device starts counting from the moment when the vehicle speed / rotation speed is greater than 0 at the same time. After the counter runs for 3 hours, if the vehicle speed = 0 for 3 minutes, the multiple sets of target vehicle operation data are counted by clearing and re-counting to obtain the first statistical result. The preset short feature statistical matrix in the second preset feature statistical device starts counting from the moment when the vehicle speed / rotation speed is greater than 0 at the same time and is updated every 3 minutes to obtain the second statistical result. The first statistical result and the second statistical result are weighted to generate the following: Figure 2 The characteristic curve diagram is shown.

[0063] Step S30: Based on the preset AI model, a clustering feature graph is obtained according to the feature curve graph;

[0064] Exemplarily, the characteristic curve graph is input into a preset AI model, and the clustering features are completed through continuous self-recognition and self-induction of the AI ​​model, thereby obtaining the clustering feature graph output by the preset AI model.

[0065] Specifically, the method of obtaining a clustering feature graph based on the characteristic curve graph based on the preset AI model includes: inputting the characteristic curve graph into the preset AI model; performing clustering analysis on the curve graph through the fuzzy C-means clustering function in the preset AI model to obtain the clustering feature graph output by the preset AI model.

[0066] Exemplarily, the characteristic curve graph is input into the preset AI model, and the curve graph is clustered analyzed by the fuzzy C-means clustering function in the preset AI model to obtain a clustering feature graph output by the preset AI model as shown in Figure 3, wherein UI, U2 and U3 are three different types of coordinates.

[0067] Step S40: analyzing the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph;

[0068] Demonstratively, the cluster feature map is analyzed to obtain parameters of each coordinate in the cluster feature map, wherein the parameters include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio; the parameters of each coordinate are compared with preset parameters to determine the vehicle operation scenario label corresponding to each coordinate, wherein the vehicle operation scenario labels include fully loaded highway, fully loaded suburban, fully loaded city, unloaded highway, unloaded suburban and unloaded city.

[0069] Step S50: marking the vehicle operation data corresponding to each of the coordinates with the vehicle operation scene label.

[0070] In this embodiment, multiple groups of acquired vehicle operation data are preprocessed according to preset preprocessing rules to generate multiple groups of target vehicle operation data; based on the multiple groups of target vehicle operation data and a preset feature counter, a feature curve graph is generated; based on a preset AI model, a cluster feature graph is obtained according to the feature curve graph; the cluster feature graph is analyzed to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph; the vehicle operation scene label is annotated to the vehicle operation data corresponding to each of the coordinates, thereby solving the technical problem in the related art that manual labeling of vehicle operation scenes is not only prone to errors but also has low labeling efficiency, thereby realizing the labeling of vehicle operation scene labels for different vehicle operation data through machine learning, thereby improving accuracy and efficiency.

[0071] In one embodiment, referring to Figure 4 , Figure 4 This is a flow chart of the second embodiment of the vehicle operation scene labeling method of the present application. Figure 4 As shown, the labeling method of the vehicle operation scene label includes:

[0072] Step S11: preprocessing the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data;

[0073] Exemplarily, multiple groups of vehicle operation data are obtained, each group of vehicle operation data includes the average speed of the vehicle, the average driving speed, the maximum speed, the parking ratio, the acceleration ratio, the deceleration ratio, the maximum acceleration, the maximum deceleration, the refueling ratio, the defueling ratio and the braking ratio. The preset preprocessing rules include data filtering rules or data weighting rules. For example, the multiple groups of vehicle operation data obtained are filtered by the data filtering rules. For example, the data filtering rules include the preset acceleration ratio 0.1m / s 2 , Preset deceleration ratio -0.1m / s 2 , preset refueling ratio 5% / s, preset defueling ratio -5% / s, preset parking ratio and preset average driving speed. Compare the acceleration ratio in each set of vehicle operation data with the preset acceleration ratio 0.1m / s 2 Compare and filter out those whose acceleration ratio is less than the preset 0.1m / s 2 The acceleration ratio of each set of vehicle operation data is compared with the preset deceleration ratio -0.1m / s 2 Compare and filter the speed that is greater than the preset deceleration ratio -0.1m / s 2deceleration ratio; compare the refueling ratio in each set of vehicle operation data with the preset refueling ratio of 5% / s, and filter the refueling ratio that is greater than the preset refueling ratio of 5% / s; compare the fuel reduction ratio in each set of vehicle operation data with the preset fuel reduction ratio of -5% / s, and filter the fuel reduction ratio that is greater than the preset fuel reduction ratio of -5% / s; filter the parking ratio of 0 in each set of vehicle operation data, and filter the average driving speed of 0 in each set of vehicle operation data, and generate multiple sets of target vehicle operation data.

[0074] Alternatively, the preset preprocessing rules include data weighting rules, which define a weight coefficient of 1 for the average speed, average driving speed, maximum speed, parking ratio, acceleration ratio, deceleration ratio, maximum acceleration, maximum deceleration, refueling ratio, refueling ratio and braking ratio in each set of vehicle operation data to generate multiple sets of target vehicle operation data.

[0075] Specifically, the method preprocesses the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data, including: acquiring multiple groups of vehicle operation data and preset preprocessing rules, wherein the preset preprocessing rules include data filtering rules and data weighting rules; filtering each group of the vehicle operation data according to the vehicle speed range value in the data filtering rules to acquire multiple groups of filtered vehicle operation data; defining weight coefficients for the filtered multiple groups of vehicle operation data according to the data weighting rules to generate multiple groups of target vehicle operation data.

[0076] Exemplarily, the preset preprocessing rules include data filtering rules and data weighting rules, and the acquired multiple sets of vehicle operation data are filtered by the data filtering rules. The data filtering rules include a preset acceleration ratio of 0.1m / s 2 , Preset deceleration ratio -0.1m / s 2 , preset refueling ratio 5% / s, preset defueling ratio -5% / s, preset parking ratio and preset average driving speed. Compare the acceleration ratio in each group of vehicle operation data with the preset acceleration ratio 0.1m / s 2 Compare and filter out those whose speed is less than the preset acceleration ratio of 0.1m / s 2 The acceleration ratio of each set of vehicle operation data is compared with the preset deceleration ratio -0.1m / s 2 Compare and filter the speed that is greater than the preset deceleration ratio -0.1m / s 2The deceleration ratio of each group of vehicle operation data is compared with the preset refueling ratio of 5% / s, and the refueling ratio greater than the preset refueling ratio of 5% / s is filtered; the reduction ratio of each group of vehicle operation data is compared with the preset reduction ratio of -5% / s, and the reduction ratio greater than the preset reduction ratio of -5% / s is filtered; the parking ratio of each group of vehicle operation data is filtered out, and the average driving speed of each group of vehicle operation data is filtered out. The weight coefficient of the average speed, average driving speed, maximum speed, parking ratio, acceleration ratio, deceleration ratio, maximum acceleration, maximum deceleration, refueling ratio, reduction ratio and braking ratio in each group of vehicle operation data after data filtering is defined as 1, and multiple groups of target vehicle operation data are generated.

[0077] Step S12: generating a characteristic curve diagram based on the plurality of sets of target vehicle operation data and a preset characteristic counter;

[0078] Exemplarily, multiple groups of target vehicle operation data are input into a preset feature counter, and feature statistics are performed on each group of target vehicle operation data through the preset feature counter to generate a feature curve graph. The preset feature counter includes a long feature statistical matrix LPM (Long_Patten_Matrix) or a short feature statistical matrix SPM (Short_Patten_Matrix). The long feature statistical matrix includes starting to count from the moment when the vehicle speed / rotation speed is greater than 0 at the same time. After the counter runs for 3 hours, if the vehicle speed = 0 for 3 minutes, it is reset and counted again. The short feature statistical matrix includes starting to count from the moment when the vehicle speed / rotation speed is greater than 0 at the same time, and updating every 3 minutes.

[0079] Specifically, it includes: the preset feature statistic includes a first preset feature statistic and a second preset feature statistic; the plurality of target vehicle operation data are counted by the preset long feature statistical matrix in the first preset feature statistic to obtain a first statistical result; the plurality of target vehicle operation data are counted by the preset short feature statistical matrix in the second preset feature statistic to obtain a second statistical result; the first statistical result and the second statistical result are weighted to generate a feature curve diagram.

[0080] Exemplarily, the preset long feature statistical matrix in the first preset feature statistical device starts counting from the moment when the vehicle speed / rotation speed is greater than 0 at the same time. After the counter runs for 3 hours, if the vehicle speed = 0 for 3 minutes, the multiple sets of target vehicle operation data are counted by clearing and re-counting to obtain the first statistical result. The preset short feature statistical matrix in the second preset feature statistical device starts counting from the moment when the vehicle speed / rotation speed is greater than 0 at the same time and is updated every 3 minutes to obtain the second statistical result. The first statistical result and the second statistical result are weighted to generate the following: Figure 2 The characteristic curve diagram is shown.

[0081] Step S13: Based on the preset AI model, a clustering feature graph is obtained according to the feature curve graph;

[0082] Exemplarily, the characteristic curve graph is input into a preset AI model, and the clustering features are completed through continuous self-recognition and self-induction of the AI ​​model, thereby obtaining the clustering feature graph output by the preset AI model.

[0083] Specifically, the method of obtaining a clustering feature graph based on the characteristic curve graph based on the preset AI model includes: inputting the characteristic curve graph into the preset AI model; performing clustering analysis on the curve graph through the fuzzy C-means clustering function in the preset AI model to obtain the clustering feature graph output by the preset AI model.

[0084] Exemplarily, the characteristic curve graph is input into the preset AI model, and the curve graph is clustered analyzed by the fuzzy C-means clustering function in the preset AI model to obtain a clustering characteristic graph output by the preset AI model as shown in FIG. 3 .

[0085] Step S14: Analyze the cluster feature graph to obtain parameters of each center coordinate in the cluster feature graph, wherein the parameters of the center coordinate include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio;

[0086] Step S15: Based on the comparison between the parameters of each of the center coordinates and the style parameters, the driving style is marked for each of the center coordinates corresponding to each group of vehicle operation data, wherein the driving modes include aggressive, normal and gentle.

[0087] Exemplarily, the parameters of each center coordinate are compared with the style parameters, and after marking the driving style for each center coordinate corresponding to each group of vehicle operating data, the current operating data of the vehicle is obtained; the driving style of the current driver is determined based on the current operating data of the vehicle and the styles of each group of vehicle operating data; the corresponding target driving mode is determined based on the driving style; if the acquired current driving mode of the vehicle is inconsistent with the target driving mode, a prompt message is sent or the current driving mode of the vehicle is changed to the target driving mode.

[0088] In this embodiment, multiple groups of vehicle operation data acquired are preprocessed according to preset preprocessing rules to generate multiple groups of target vehicle operation data; based on the multiple groups of target vehicle operation data and preset feature counters, feature curves are generated; based on the preset AI model, cluster feature graphs are acquired according to the feature curves, and the cluster feature graphs are analyzed to acquire parameters of each center coordinate in the cluster feature graph, wherein the parameters of the center coordinates include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio, and defueling ratio; based on the comparison of the parameters of each center coordinate with the style parameters, the driving style is annotated for each group of vehicle operation data corresponding to each center coordinate, wherein the driving modes include aggressive, general, and gentle. The technical problem of low efficiency of manual annotation of vehicle driving style in related technologies is solved.

[0089] In a second aspect, an embodiment of the present application also provides a device for labeling vehicle operation scenario labels.

[0090] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of a vehicle operation scene labeling device of the present application. Figure 5 As shown, the vehicle operation scene labeling device includes:

[0091] A first generating module 10 is used to pre-process the acquired multiple groups of vehicle operation data according to preset pre-processing rules to generate multiple groups of target vehicle operation data;

[0092] A second generating module 20, for generating a characteristic curve diagram based on the plurality of target vehicle operation data sets and a preset characteristic counter;

[0093] An acquisition module 30, configured to acquire a clustering feature graph based on a preset AI model and the feature curve graph;

[0094] A determination module 40 is used to analyze the cluster feature graph and determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph;

[0095] The labeling module 50 is used to label the vehicle operation data corresponding to each of the coordinates with the vehicle operation scene label.

[0096] Furthermore, in one embodiment, the acquisition module 30 is used to:

[0097] Inputting the characteristic curve graph into the preset AI model;

[0098] The curve graph is clustered and analyzed by using the fuzzy C-means clustering function in the preset AI model to obtain a clustering feature graph output by the preset AI model.

[0099] Furthermore, in one embodiment, the first determining module 40 is used to:

[0100] Analyze the cluster feature graph to obtain parameters of each coordinate in the cluster feature graph, wherein the parameters include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio;

[0101] The parameters of each of the coordinates are compared with the preset parameters to determine the vehicle operation scenario labels corresponding to each of the coordinates, wherein the vehicle operation scenario labels include fully loaded highway, fully loaded suburban, fully loaded city, unloaded highway, unloaded suburban and unloaded city.

[0102] Furthermore, in one embodiment, the first generating module 10 is used to:

[0103] Acquiring multiple groups of vehicle operation data and preset preprocessing rules, wherein the preset preprocessing rules include data filtering rules and data weighting rules;

[0104] Filtering each group of the vehicle operation data according to the vehicle speed range value in the data filtering rule to obtain multiple groups of filtered vehicle operation data;

[0105] The weight coefficients are defined for the filtered multiple groups of vehicle operation data by using the data weighting rule to generate multiple groups of target vehicle operation data.

[0106] Furthermore, in one embodiment, the second generating module 20 is used to:

[0107] The preset feature counter includes a first preset feature counter and a second preset feature counter;

[0108] The plurality of groups of target vehicle operation data are counted by using a preset long feature statistical matrix in the first preset feature statistical device to obtain a first statistical result;

[0109] The plurality of groups of target vehicle operation data are counted by using a preset short feature statistical matrix in the second preset feature statistical device to obtain a second statistical result;

[0110] The first statistical result and the second statistical result are weighted to generate a characteristic curve graph.

[0111] Furthermore, in one embodiment, the vehicle operation scene labeling device further includes a new module for:

[0112] Analyze the cluster feature graph to obtain parameters of each center coordinate in the cluster feature graph, wherein the parameters of the center coordinate include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio;

[0113] Based on the comparison between the parameters of each of the center coordinates and the style parameters, the driving style is labeled for each group of vehicle operation data corresponding to each of the center coordinates, wherein the driving modes include aggressive, normal and gentle.

[0114] Furthermore, in one embodiment, the vehicle operation scene labeling device further includes a new module for:

[0115] Get the current operation data of the vehicle;

[0116] Determining a driving style of a current driver according to the current operating data of the vehicle and the styles of each set of vehicle operating data;

[0117] Determining a corresponding target driving mode according to the driving style;

[0118] If the acquired current driving mode of the vehicle is inconsistent with the target driving mode, a prompt message is sent or the current driving mode of the vehicle is changed to the target driving mode.

[0119] Among them, the functional implementation of each module in the above-mentioned vehicle operation scene label labeling device corresponds to the various steps in the above-mentioned vehicle operation scene label label labeling method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0120] On the third aspect, an embodiment of the present application provides a vehicle operation scenario labeling device, which can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0121] Reference Figure 6 , Figure 6The hardware structure diagram of the vehicle operation scene labeling device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle operation scene labeling device may include a processor, a memory, a communication interface, and a communication bus.

[0122] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0123] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle operation scene labeling device, and the interface used to realize the interconnection of the vehicle operation scene labeling device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0124] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0125] The processor may be a general-purpose processor, which may call a labeling program for a vehicle operation scene label stored in a memory and execute a labeling method for a vehicle operation scene label provided in an embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the labeling program for a vehicle operation scene label is called may refer to the various embodiments of the labeling method for a vehicle operation scene label of the present application, which will not be described in detail here.

[0126] Those skilled in the art will understand that Figure 6 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0127] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0128] The computer-readable storage medium of the present application stores a vehicle operation scenario labeling program, wherein when the vehicle operation scenario labeling program is executed by a processor, the steps of the vehicle operation scenario labeling method as described above are implemented.

[0129] Among them, the method implemented when the vehicle operation scene labeling program is executed can refer to the various embodiments of the vehicle operation scene labeling method of the present application, and will not be repeated here.

[0130] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0131] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0132] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0133] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0134] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0136] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for labeling vehicle operation scene labels, characterized in that: The label marking of the vehicle operation scene includes: Preprocessing the acquired multiple groups of vehicle operation data according to preset preprocessing rules to generate multiple groups of target vehicle operation data; Generate a characteristic curve graph based on the multiple groups of target vehicle operation data and a preset characteristic counter; Based on the preset AI model, a clustering feature graph is obtained according to the feature curve graph; Analyze the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph; The vehicle operation data corresponding to each of the coordinates is labeled with the vehicle operation scene label.

2. The vehicle operation scene labeling method according to claim 1, characterized in that: The step of obtaining a clustering feature graph based on the preset AI model and the feature curve graph includes: Inputting the characteristic curve graph into the preset AI model; The curve graph is clustered and analyzed by using the fuzzy C-means clustering function in the preset AI model to obtain a clustering feature graph output by the preset AI model.

3. The vehicle operation scene labeling method according to claim 1, characterized in that: The analyzing the cluster feature graph to determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph includes: Analyze the cluster feature graph to obtain parameters of each coordinate in the cluster feature graph, wherein the parameters include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio; The parameters of each of the coordinates are compared with the preset parameters to determine the vehicle operation scenario labels corresponding to each of the coordinates, wherein the vehicle operation scenario labels include fully loaded highway, fully loaded suburban, fully loaded city, unloaded highway, unloaded suburban and unloaded city.

4. The vehicle operation scene labeling method according to claim 1, characterized in that: The preprocessing of the acquired multiple groups of vehicle operation data according to the preset preprocessing rules to generate multiple groups of target vehicle operation data includes: Acquiring multiple groups of vehicle operation data and preset preprocessing rules, wherein the preset preprocessing rules include data filtering rules and data weighting rules; Filtering each group of the vehicle operation data according to the vehicle speed range value in the data filtering rule to obtain multiple groups of filtered vehicle operation data; The weight coefficients are defined for the filtered multiple groups of vehicle operation data by using the data weighting rule to generate multiple groups of target vehicle operation data.

5. The vehicle operation scene labeling method according to claim 1, characterized in that: The generating of a characteristic curve graph based on the plurality of sets of target vehicle operation data and a preset characteristic counter comprises: The preset feature counter includes a first preset feature counter and a second preset feature counter; The plurality of groups of target vehicle operation data are counted by using a preset long feature statistical matrix in the first preset feature statistical device to obtain a first statistical result; The plurality of groups of target vehicle operation data are counted by using a preset short feature statistical matrix in the second preset feature statistical device to obtain a second statistical result; The first statistical result and the second statistical result are weighted to generate a characteristic curve graph.

6. The vehicle operation scene labeling method according to claim 1, characterized in that: After obtaining the cluster feature graph based on the preset AI model and the curve graph, the method further includes: Analyze the cluster feature graph to obtain parameters of each center coordinate in the cluster feature graph, wherein the parameters of the center coordinate include average vehicle speed, average driving speed, maximum vehicle speed, acceleration ratio, deceleration ratio, parking ratio, maximum acceleration, maximum deceleration, maximum throttle change value, refueling ratio and defueling ratio; Based on the comparison between the parameters of each of the center coordinates and the style parameters, the driving style is labeled for each group of vehicle operation data corresponding to each of the center coordinates, wherein the driving modes include aggressive, normal and gentle.

7. The vehicle operation scene labeling method according to claim 6, characterized in that: After comparing the parameters based on each of the center coordinates with the style parameters and marking the driving style for each group of vehicle operation data corresponding to each of the center coordinates, the method further includes: Get the current operation data of the vehicle; Determining a driving style of a current driver according to the current operating data of the vehicle and the styles of each set of vehicle operating data; Determining a corresponding target driving mode according to the driving style; If the acquired current driving mode of the vehicle is inconsistent with the target driving mode, a prompt message is sent or the current driving mode of the vehicle is changed to the target driving mode.

8. A vehicle operation scene labeling device, characterized in that: The vehicle operation scene labeling device includes: A first generating module is used to pre-process the acquired multiple groups of vehicle operation data according to preset pre-processing rules to generate multiple groups of target vehicle operation data; A second generating module, used for generating a characteristic curve graph based on the plurality of target vehicle operation data sets and a preset characteristic counter; An acquisition module, used to acquire a clustering feature graph according to the feature curve graph based on a preset AI model; A determination module, used to analyze the cluster feature graph and determine the vehicle operation scene label corresponding to each coordinate in the cluster feature graph; The labeling module is used to label the vehicle operation data corresponding to each of the coordinates with the vehicle operation scene label.

9. A vehicle operation scene labeling device, characterized in that: The vehicle operation scenario label labeling device includes a processor, a memory, and a vehicle operation scenario label labeling program stored in the memory and executable by the processor, wherein when the vehicle operation scenario label labeling program is executed by the processor, the steps of the vehicle operation scenario label label labeling method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle operation scenario labeling program, wherein when the vehicle operation scenario labeling program is executed by a processor, the steps of the vehicle operation scenario labeling method according to any one of claims 1 to 7 are implemented.

Images