Driving data dynamic adaptive method and device, vehicle and storage medium

Abstract

The invention relates to a driving data dynamic adaptive method and device, a vehicle and a storage medium. Comprising the steps of preprocessing actual driving data of a current vehicle, and determining current driving condition characteristics of the current vehicle based on the preprocessed actual driving data and GIS map information; determining at least one group of to-be-switched driving calibration data from a preset scene driving calibration database based on the basic hardware configuration data of the current vehicle and the current driving condition characteristics, and matching the preprocessed actual driving data with the at least one group of to-be-switched driving calibration data and the current driving calibration data of the current vehicle, and determining target driving data according to a matching result, so that the current vehicle drives based on the target driving data. Therefore, more adaptive vehicle driving calibration data is provided for the user in real time based on the actual driving scene, and the problem that the performance of existing driving calibration data in actual use cannot achieve the optimal cost performance in the whole scene is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method, device, vehicle and storage medium for dynamic self-adaptation of driving data. Background Art

[0002] The basic calibration data of the vehicle is a reference data obtained based on extensive engineering practice and experience accumulated in multiple extreme environment and road simulation tests, taking into account various environmental factors and driving demand factors. However, in each subdivided working scenario, the basic calibration data of the vehicle may not achieve the optimal economy.

[0003] In related technologies, by incorporating correction logic for parameters such as ambient temperature and altitude into the basic calibration strategy, the power unit can meet performance requirements under specific extreme conditions.

[0004] However, due to functional limitations, driving scenario condition judgment, etc., the performance of existing driving calibration data in actual use is still unable to achieve the optimal cost-effectiveness in all scenarios, and the effect of improving economy is limited, which needs to be solved urgently. Summary of the invention

[0005] The present application provides a method, device, vehicle and storage medium for dynamic self-adaptation of driving data to solve the problem that the performance of existing driving calibration data in actual use cannot achieve the optimal cost-effectiveness in all scenarios, thereby improving the economy and driving comfort of the entire vehicle.

[0006] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a driving data dynamic self-adaptation method, comprising the following steps:

[0007] Acquire basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain preprocessed actual driving data;

[0008] Determining the current driving condition characteristics of the current vehicle based on the pre-processed actual driving data and GIS (Geographic Information System) map information;

[0009] Based on the basic hardware configuration data and the current driving condition characteristics, at least one group of driving calibration data to be switched is determined from a preset scenario driving calibration database, and the preprocessed actual driving data is matched with the at least one group of driving calibration data to be switched and the current driving calibration data, respectively, and the target driving data is determined according to the matching result, so that the current vehicle drives based on the target driving data.

[0010] According to an embodiment of the present application, before determining at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, it further includes:

[0011] Obtain the basic hardware configuration data sets and actual driving data sets of multiple target vehicles, and preprocess the actual driving data sets to obtain preprocessed actual driving data sets;

[0012] Based on the GIS map information of each target vehicle, determine the actual driving condition characteristics of each target vehicle, and generate a configuration class label corresponding to the basic hardware configuration data of each target vehicle, a usage class label corresponding to the actual driving condition characteristics of each target vehicle, and a data class label corresponding to the preprocessed actual driving data of each target vehicle;

[0013] Based on the configuration class label corresponding to the basic hardware configuration data of each target vehicle, generate the preset scenario driving calibration database according to the mapping relationship between the usage class label corresponding to the actual driving condition characteristics of each target vehicle and the data class label corresponding to the preprocessed actual driving data of each target vehicle.

[0014] According to an embodiment of the present application, the step of respectively matching the preprocessed actual driving data with the at least one set of to-be-switched driving calibration data and the current driving calibration data, and determining the target driving data according to the matching result includes:

[0015] Respectively calculate the overlapping areas between the polygon radar map of the preprocessed actual driving data and the polygon radar maps of each to-be-switched driving calibration data and the polygon radar map of the current driving calibration data, to obtain multiple overlapping area values;

[0016] Determine the target driving data according to the multiple overlapping area values.

[0017] According to an embodiment of the present application, the step of determining the target driving data according to the multiple overlapping area values includes:

[0018] Identify the radar map with the largest overlapping area value among the multiple overlapping area values;

[0019] Take the driving calibration data corresponding to the radar map with the largest overlapping area value as the target driving data.

[0020] According to an embodiment of the present application, the step of respectively calculating the overlapping areas between the polygon radar map of the preprocessed actual driving data and the polygon radar maps of each to-be-switched driving calibration data and the polygon radar map of the current driving calibration data, to obtain multiple overlapping area values includes:

[0021] Determine at least one radar chart dimension and the weight of each radar chart dimension based on the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data;

[0022] Generate a polygon radar chart of the preprocessed actual driving data, a polygon radar chart of each to-be-switched driving calibration data, and a polygon radar chart of the current driving calibration data based on the at least one radar chart dimension and the weight of each radar chart dimension;

[0023] Overlap the polygon radar chart of the preprocessed actual driving data with the polygon radar charts of each to-be-switched driving calibration data and the polygon radar chart of the current driving calibration data in sequence, and obtain the multiple overlapping area values according to the overlapping results.

[0024] According to an embodiment of the present application, the generating a polygon radar chart of the preprocessed actual driving data, a polygon radar chart of each to-be-switched driving calibration data, and a polygon radar chart of the current driving calibration data based on the at least one radar chart dimension and the weight of each radar chart dimension includes:

[0025] Based on the at least one radar chart dimension, convert the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data into corresponding single-score representations respectively;

[0026] Generate a polygon radar chart of the preprocessed actual driving data, a polygon radar chart of each to-be-switched driving calibration data, and a polygon radar chart of the current driving calibration data based on the at least one radar chart dimension, the weight of each radar chart dimension, and the corresponding single-score representation results.

[0027] According to an embodiment of the present application, after determining the target driving data according to the matching result, it further includes:

[0028] Send the target driving data to a preset terminal, and determine whether an approval flashing instruction sent by the user based on the target driving data is received;

[0029] If the approval flashing instruction sent by the user based on the target driving data is received, flash the current vehicle based on the target driving data.

[0030] According to the driving data dynamic adaptation method proposed in the embodiments of the present application, by analyzing the basic hardware configuration data, actual driving data, and current driving calibration data of the vehicle, and combining with the GIS map information, the driving condition characteristics of the vehicle can be determined. Then, the driving condition characteristic data is used to match the preset scenario driving calibration database and the current driving calibration data, so as to provide the target driving data for the vehicle to optimize its driving performance. Thus, by providing more adaptable vehicle driving calibration data for the user in real time based on the actual driving scenario, the problem that the performance of the existing driving calibration data cannot achieve the optimal cost performance in all scenarios during actual use is solved, and the vehicle economy and driving comfort are improved.

[0031] To achieve the above object, an embodiment of the second aspect of the present application proposes a driving data dynamic adaptation device, including:

[0032] A processing module, configured to obtain the basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain the preprocessed actual driving data;

[0033] A determination module, configured to determine the current driving condition characteristics of the current vehicle based on the preprocessed actual driving data and the GIS map information;

[0034] A matching module, configured to determine at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, and respectively match the preprocessed actual driving data with the at least one set of to-be-switched driving calibration data and the current driving calibration data, and determine the target driving data according to the matching result, so that the current vehicle drives based on the target driving data.

[0035] According to an embodiment of the present application, before determining at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, the matching module is further configured to:

[0036] Obtain the basic hardware configuration data sets and actual driving data sets of multiple target vehicles, and preprocess the actual driving data sets to obtain the preprocessed actual driving data sets;

[0037] Based on the GIS map information of each target vehicle, determine the actual driving condition characteristics of each target vehicle, and generate a configuration class label corresponding to the basic hardware configuration data of each target vehicle, a usage class label corresponding to the actual driving condition characteristics of each target vehicle, and a data class label corresponding to the preprocessed actual driving data of each target vehicle;

[0038] Generate the preset scenario driving calibration database according to the mapping relationship between the usage class tags corresponding to the actual driving condition characteristics of each target vehicle and the data class tags corresponding to the preprocessed actual driving data of each target vehicle, based on the configuration class tags corresponding to the basic hardware configuration data of each target vehicle.

[0039] According to an embodiment of the present application, the matching module includes:

[0040] A calculation unit, configured to calculate the overlapping areas between the polygon radar map of the preprocessed actual driving data and the polygon radar maps of each to-be-switched driving calibration data and the polygon radar map of the current driving calibration data respectively, to obtain a plurality of overlapping area values;

[0041] A determination unit, configured to determine the target driving data according to the plurality of overlapping area values.

[0042] According to an embodiment of the present application, the determination unit is specifically configured to:

[0043] Identify the radar map with the largest overlapping area value among the plurality of overlapping area values;

[0044] Use the driving calibration data corresponding to the radar map with the largest overlapping area value as the target driving data.

[0045] According to an embodiment of the present application, the calculation unit includes:

[0046] A determination subunit, configured to determine at least one radar map dimension and the weight of each radar map dimension based on the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data;

[0047] A generation subunit, configured to generate the polygon radar map of the preprocessed actual driving data, the polygon radar maps of each to-be-switched driving calibration data, and the polygon radar map of the current driving calibration data based on the at least one radar map dimension and the weight of each radar map dimension;

[0048] An overlapping subunit, configured to sequentially overlap the polygon radar map of the preprocessed actual driving data with the polygon radar maps of each to-be-switched driving calibration data and the polygon radar map of the current driving calibration data, and obtain the plurality of overlapping area values according to the overlapping results.

[0049] According to an embodiment of the present application, the generation subunit is specifically configured to:

[0050] Based on the at least one radar chart dimension, respectively convert the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data into corresponding single-score representations;

[0051] Based on the at least one radar chart dimension, the weight of each radar chart dimension, and the corresponding single-score representation results, generate a polygon radar chart of the preprocessed actual driving data, a polygon radar chart of each to-be-switched driving calibration data, and a polygon radar chart of the current driving calibration data.

[0052] According to an embodiment of the present application, after determining the target driving data according to the matching result, the matching module is further configured to:

[0053] Send the target driving data to a preset terminal, and determine whether an approval flashing instruction sent by the user based on the target driving data is received;

[0054] In the case of receiving the approval flashing instruction sent by the user based on the target driving data, perform flashing on the current vehicle based on the target driving data.

[0055] According to the driving data dynamic adaptive device proposed in the embodiment of the present application, by analyzing the basic hardware configuration data, actual driving data, and current driving calibration data of the vehicle, and combining with GIS map information, the driving condition characteristics of the vehicle can be determined. Then, using the driving condition characteristic data to match the preset scenario driving calibration database and the current driving calibration data, so as to provide the target driving data for the vehicle to optimize its driving performance. Thus, by providing more adaptable vehicle driving calibration data for the user in real time based on the actual driving scenario, the problem that the existing driving calibration data cannot achieve the optimal cost performance in all scenarios during actual use is solved, and the vehicle economy and driving comfort are improved.

[0056] To achieve the above object, an embodiment of the third aspect of the present application proposes a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the driving data dynamic adaptive method as described in the above embodiment.

[0057] To achieve the above object, an embodiment of the fourth aspect of the present application proposes a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to be used to implement the driving data dynamic adaptive method as described in the above embodiment.

[0058] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0059] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, in which:

[0060] Figure 1 It is a flowchart of a method for dynamically adapting driving data according to an embodiment of the present application;

[0061] Figure 2 It is a schematic diagram of a polygon radar chart according to an embodiment of the present application;

[0062] Figure 3 It is a schematic diagram of overlapping and comparing different polygon radar charts according to an embodiment of the present application;

[0063] Figure 4 It is a schematic diagram of the comparison result after overlapping and comparing different polygon radar charts according to an embodiment of the present application;

[0064] Figure 5 It is a schematic diagram of the comparison result after overlapping and comparing different polygon radar charts according to another embodiment of the present application;

[0065] Figure 6 It is a schematic diagram of a driving data dynamic adaptation system according to an embodiment of the present application;

[0066] Figure 7 It is a schematic diagram of the working process of a driving data dynamic adaptation system according to an embodiment of the present application;

[0067] Figure 8 It is a block schematic diagram of a driving data dynamic adaptation device according to an embodiment of the present application;

[0068] Figure 9 It is a schematic diagram of the structure of a vehicle according to an embodiment of the present application. Detailed Embodiments

[0069] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0070] The driving data dynamic adaptation method, device, vehicle and storage medium according to embodiments of the present application will be described below with reference to the accompanying drawings. First, the driving data dynamic adaptation according to embodiments of the present application will be described with reference to the accompanying drawings.

[0071] Figure 1It is a flowchart of a method for dynamically adapting driving data according to an embodiment of the present application.

[0072] Exemplarily, as Figure 1 shown, the method for dynamically adapting driving data includes the following steps:

[0073] In step S101, obtain the basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain the preprocessed actual driving data.

[0074] It can be understood that the basic hardware configuration data of the current vehicle refers to the basic driving data configured when the vehicle rolls off the production line, including component information such as engine calibration data (such as engine model), transmission calibration data (such as transmission model), vehicle calibration data (such as tire model), and rear axle ratio. These data are developed based on the maximum generality of the vehicle to meet the needs of most usage scenarios. However, in actual applications, the driving condition characteristics faced by the vehicle during a specific period usually exhibit specific features (for example, high-speed driving, low-temperature environment, plain terrain, low-load condition, etc.). Since the basic driving data cannot be optimized for each specific scenario, the vehicle may not be able to achieve the best performance or optimize the vehicle's energy consumption in these specific scenarios. The actual driving data refers to the driving data of the current vehicle during actual driving, such as vehicle configuration information, engine operating condition data, vehicle driving position data, emission data, and transmission gear data (for example: the current vehicle mainly cruises on the highway, mainly drives at low speed + national road + heavy load, etc.). These data can be collected through TBOX (Telematics Box, in-vehicle electrical component) and vehicle-mounted controllers. The current driving calibration data refers to the driving calibration data currently used by the current vehicle, which is a control program written in the engine controller (Engine Control Unit, abbreviated as ECU) or other vehicle controllers and contains relevant control parameters such as engine ignition angle.

[0075] That is to say, after obtaining the basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, the actual driving data can be preprocessed (i.e., data cleaning). After summarizing, calculating, and clearing invalid information such as error frames from the actual driving data, corrected and continuous driving record information (i.e., the preprocessed actual driving data) can be obtained.

[0076] In step S102, based on the preprocessed actual driving data and GIS map information, determine the current driving condition characteristics of the current vehicle.

[0077] Specifically, by analyzing the preprocessed real-time driving data and combining with GIS map technology, the current driving path of the current vehicle can be reconstructed in detail, including information such as road characteristics, altitude, and climate conditions. These data can accurately identify and judge the current driving conditions of the current vehicle. For example, it can distinguish whether the vehicle is driving lightly loaded on a highway in a plain area (i.e., light load on plain highway) or heavily loaded on a highway in a plateau area (i.e., heavy load on plateau highway), etc. With the help of big data collection and analysis technology, the driving condition characteristics of the current vehicle in various usage scenarios can be deeply understood. Through these detailed data analyses, the economy of the vehicle can be evaluated and monitored in real time, so as to effectively identify those vehicles that perform abnormally in terms of energy consumption.

[0078] In step S103, based on the basic hardware configuration data and the current driving condition characteristics, at least one set of to-be-switched driving calibration data is determined from the preset scenario driving calibration database, and the preprocessed actual driving data is respectively matched with at least one set of to-be-switched driving calibration data and the current driving calibration data, and the target driving data is determined according to the matching results, so that the current vehicle drives based on the target driving data.

[0079] That is to say, after the driving condition characteristics of abnormal vehicle energy consumption are identified in step S102, by using the pre-constructed scenario driving calibration database (this database contains various possible driving scenarios with labels and corresponding driving calibration data), the current driving condition characteristics of the current vehicle are combined with the basic hardware configuration data, and at least one set of driving calibration data suitable for the current driving condition characteristics is selected from the preset scenario driving calibration database as the to-be-switched driving calibration data. Then, the preprocessed actual driving data is respectively subjected to matching analysis with at least one set of to-be-switched driving calibration data and the current driving calibration data, so as to determine a set of most suitable driving calibration data (which may be a certain set of the to-be-switched driving calibration data or the current driving calibration data) as the target driving data and apply it to the driving process of the current vehicle. These target driving data can help the current vehicle better adapt to the current driving environment, improve driving safety and efficiency, and enable the current vehicle to always be in a low-energy consumption operation state.

[0080] The following details how the system calculates the matching degree between the actual driving data and the target driving data of the vehicle.

[0081] As a possible implementation manner, in some embodiments, the preprocessed actual driving data is respectively matched with at least one set of to-be-switched driving calibration data and current driving calibration data, and the target driving data is determined according to the matching result, including: calculating the overlapping areas between the polygon radar map of the preprocessed actual driving data and the polygon radar map of each to-be-switched driving calibration data and the polygon radar map of the current driving calibration data respectively to obtain a plurality of overlapping area values; determining the target driving data according to the plurality of overlapping area values.

[0082] Specifically, in the embodiments of the present application, the polygon radar map formed by the preprocessed actual driving data can be respectively overlapped and compared with the polygon radar map formed by each set of to-be-switched driving calibration data and the polygon radar map formed by the current driving calibration data, and the overlapping areas between them are calculated to obtain a series of overlapping area values, and these values can reflect the similarity or matching degree between different data comparison groups. Finally, based on these overlapping area values, the target driving data that best conforms to the actual driving situation of the current vehicle can be determined.

[0083] Optionally, in some embodiments, determining the target driving data according to the plurality of overlapping area values includes: identifying the radar map with the largest overlapping area value among the plurality of overlapping area values; using the driving calibration data corresponding to the radar map with the largest overlapping area value as the target driving data.

[0084] That is to say, by respectively overlapping and comparing the polygon radar map of the preprocessed actual driving data with the polygon radar map of each set of to-be-switched driving calibration data and the polygon radar map of the current driving calibration data, the radar map with the largest overlapping area with the polygon radar map of the preprocessed actual driving data can be obtained, and the form calibration data corresponding to this radar map is regarded as the target driving data most suitable for the current vehicle under the current driving condition characteristics.

[0085] When performing the overlapping comparison of the polygon radar maps, in the embodiments of the present application, the polygon radar map of the preprocessed actual driving data can be first overlapped with the polygon radar map of each to-be-switched driving calibration data in turn to select the polygon radar map of the most suitable to-be-switched driving calibration data from the preset scenario driving calibration database, and then the polygon radar map of the preprocessed actual driving data is overlapped with the polygon radar map of the current driving calibration data, so as to determine the radar map with the largest overlapping area according to the overlapping results of these two groups.

[0086] For example, the polygon radar map of the preprocessed actual driving data of the current vehicle can be as Figure 2As shown in Figure 2 (a), the polygon radar chart of the most suitable driving calibration data to be switched selected from the preset scenario driving calibration database (that is, after the polygon radar chart formed by the preprocessed actual driving data is overlapped and compared with the polygon radar charts formed by each group of driving calibration data to be switched, the polygon radar chart of the driving calibration data to be switched with the largest overlapping area) can be as Figure 2 (b). The polygon radar chart of the current driving calibration data can be as Figure 2 (c). The polygon radar chart of the preprocessed actual driving data shown in Figure 2 (a) is respectively overlapped and compared with the polygon radar chart of the most suitable driving calibration data to be switched selected from the preset scenario driving calibration database shown in Figure 2 (b), and the polygon radar chart of the current driving calibration data shown in Figure 3 (c). As shown in Figure 4 and Figure 5 , the corresponding detailed comparison results are as Figure 4 and Figure 5 . The a - i in Figure 4 and Figure 5 represent different dimensions, such as vehicle acceleration distribution, environmental temperature distribution, etc. The number and corresponding meanings of specific dimensions are determined according to the actual situation and are not specifically limited here. It can be seen from the comparison results shown in Figure 4 and Figure 5 that the overlapping area between the polygon radar chart of the preprocessed actual driving data and the polygon radar chart of the most suitable driving calibration data to be switched selected from the preset scenario driving calibration database is larger than the overlapping area between the polygon radar chart of the preprocessed actual driving data and the polygon radar chart of the current driving calibration data. That is, the current vehicle is no longer in the best low - energy - consumption state when driving under the current driving calibration data, and the target driving data matched from the preset scenario driving calibration database is more suitable for the current driving condition characteristics, thereby improving the economy, power performance and comfort of the whole vehicle.

[0087] Optionally, in some embodiments, the overlapping areas between the polygon radar map of the preprocessed actual driving data and the polygon radar maps of each driving calibration data to be switched and the polygon radar map of the current driving calibration data are calculated respectively to obtain a plurality of overlapping area values, including: determining at least one radar map dimension and the weight of each radar map dimension based on the preprocessed actual driving data, the driving calibration data to be switched, and the current driving calibration data; generating the polygon radar map of the preprocessed actual driving data, the polygon radar maps of each driving calibration data to be switched, and the polygon radar map of the current driving calibration data based on the at least one radar map dimension and the weight of each radar map dimension; overlapping the polygon radar map of the preprocessed actual driving data with the polygon radar maps of each driving calibration data to be switched and the polygon radar map of the current driving calibration data in sequence, and obtaining a plurality of overlapping area values according to the overlapping results.

[0088] Specifically, the embodiments of the present application can divide the preprocessed actual driving data into multiple dimensions (i.e., radar map dimensions), such as vehicle speed, engine speed, engine torque, and ambient air temperature, etc. At the same time, different weights are assigned to the characterization of each dimension. Based on these dimensions and weights, the polygon radar map of the preprocessed actual driving data can be generated. Similarly, the polygon radar maps of each driving calibration data to be switched and the polygon radar map of the current driving calibration data are generated. These radar maps are created based on the preprocessed actual driving data, each driving calibration data to be switched, and the current driving calibration data. Each radar map is presented in the form of a polygon, where each vertex represents a measurement value of a dimension, and the weight of the dimension determines the position and importance of the vertex in the radar map. After generating the radar maps, the polygon radar map of the preprocessed actual driving data can be overlapped and compared with the polygon radar maps of each driving calibration data to be switched and the polygon radar map of the current driving calibration data respectively. Through this overlapping operation, the differences and similarities between different data sets can be intuitively seen. Finally, according to the overlapping conditions of these radar maps, a plurality of overlapping area values are calculated. These area values can quantitatively represent the matching degree between different data sets, thus providing strong data support for decision-making.

[0089] Optionally, in some embodiments, based on at least one radar map dimension and the weight of each radar map dimension, a polygon radar map of the preprocessed actual driving data, a polygon radar map of each driving calibration data to be switched, and a polygon radar map of the current driving calibration data are generated, including: based on at least one radar map dimension, respectively converting the preprocessed actual driving data, the driving calibration data to be switched, and the current driving calibration data into corresponding single-score representations; generating a polygon radar map of the preprocessed actual driving data, a polygon radar map of each driving calibration data to be switched, and a polygon radar map of the current driving calibration data based on at least one radar map dimension, the weight of each radar map dimension, and the corresponding single-score representation results.

[0090] Specifically, after the preprocessed actual driving data is divided into multiple dimensions (i.e., radar map dimensions) in the embodiments of the present application, for each specific dimension, it can be converted into a single score for representation. For example, in the dimension of vehicle speed, if the driving speed of more than 60% of the vehicles is 80 km / h, then this vehicle speed dimension can be represented as a score of 8; in the dimension of ambient temperature, if 60% of the ambient temperature is 35 °C, then this temperature dimension can be represented as a score of 7. After all dimensions are represented, further according to the sensitivity of the current vehicle's driving calibration data to the environment and related driving data, different weights can be assigned to the representation of each dimension. It can be understood that such weight assignment can ensure that the importance of each factor is appropriately reflected during the matching process. Based on the weight of each radar map dimension, a polygon radar map with N dimensions is comprehensively calculated, and this polygon radar map reflects the specific scenario conditions where the current vehicle is driving. It should be noted that the weights corresponding to each radar map dimension are not fixed and can be adjusted accordingly according to different vehicle models and different power sources to adapt to various vehicle configurations and performance requirements.

[0091] Similarly, in the embodiments of the present application, at least one set of driving calibration data to be switched and the current driving calibration data can also be converted into polygon radar maps of corresponding dimensions. After obtaining the polygon radar map of the preprocessed actual driving data, the polygon radar map of each driving calibration data to be switched, and the polygon radar map of the current driving calibration data, the polygon radar map of the preprocessed actual driving data can be overlapped with the polygon radar map of each driving calibration data to be switched and the polygon radar map of the current driving calibration data respectively, so as to obtain multiple overlap area values according to the overlap results.

[0092] In addition, for the driving calibration data with veto power in the preset scenario driving calibration database, an additional switch mechanism can be set to ensure that its veto function can be executed when necessary. For example, if the configuration of the current vehicle does not match a certain set of driving calibration data, then even if the overlapping area value between the polygon radar map of the pre-processed actual driving data and the polygon radar map of the driving calibration data is the largest, the driving calibration data is not applicable to the current vehicle. The setting of this switch mechanism can significantly improve the flexibility and adaptability of the system. By introducing the veto power driving calibration data, the system can dynamically adjust the evaluation results according to the specific configuration or state of the vehicle, thus avoiding the interference of inapplicable scenario labels on the driving data matching.

[0093] For ease of understanding, how to obtain the preset scenario driving calibration database will be described in detail below.

[0094] As a possible implementation method, in some embodiments, before determining at least one set of to-be-switched driving calibration data from the preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, it further includes: obtaining the basic hardware configuration data sets and the actual driving data sets of multiple target vehicles, and pre-processing the actual driving data sets to obtain the pre-processed actual driving data sets; based on the GIS map information of each target vehicle, determining the actual driving condition characteristics of each target vehicle, and generating a configuration class label corresponding to the basic hardware configuration data of each target vehicle, a usage class label corresponding to the actual driving condition characteristics of each target vehicle, and a data class label corresponding to the pre-processed actual driving data of each target vehicle; based on the configuration class label corresponding to the basic hardware configuration data of each target vehicle, generating a preset scenario driving calibration database according to the mapping relationship between the usage class label corresponding to the actual driving condition characteristics of each target vehicle and the data class label corresponding to the pre-processed actual driving data of each target vehicle.

[0095] Specifically, in order to construct the preset scenario driving calibration database, it is also necessary to first collect the basic hardware configuration data sets of multiple target vehicles (such as engine performance parameters, transmission performance parameters, tire specifications, etc.) and their relevant data sets during actual driving (actual driving data such as speed, acceleration, engine condition data, vehicle driving position data, fuel consumption, etc.). After obtaining these data, the actual driving data sets can be pre-processed to ensure the accuracy and availability of the data, so as to obtain the actually driving data sets that have been cleaned and formatted (i.e., the pre-processed actual driving data sets).

[0096] Next, by leveraging the powerful functions of the GIS map, the actual driving condition characteristics of each target vehicle in a specific environment can be accurately determined, including the road characteristics of the vehicle's driving path, such as road type, slope, curve conditions, etc.; altitude information to understand the vehicle's driving situation at different heights; and climate information, including temperature, humidity, precipitation, etc. These factors will all have an impact on the vehicle's driving performance.

[0097] In addition, by analyzing the preprocessed actual driving data set, the driving characteristics of each target vehicle within a certain time period (preset time interval) can also be extracted, including but not limited to road type distribution, engine torque and speed distribution, load distribution, throttle opening ratio, gear distribution ratio, etc. These driving characteristics are crucial for understanding the vehicle's operating state and the user's driving habits. It should be noted that the content of the driving characteristics output by the system has high flexibility and customizability, and can be updated and switched accordingly according to the power type of the optimized vehicle model to adapt to the specific needs and performance optimization goals of different vehicle models.

[0098] Finally, by combining the driving characteristics, actual driving condition characteristics, basic hardware configuration data set, and preprocessed actual driving data set, corresponding condition labels can be established for the basic hardware configuration data set, actual driving condition characteristics, and preprocessed actual driving data set respectively. These labels will help better classify and manage the data, providing convenience for subsequent data analysis and applications. After establishing the condition labels, these labeled actual driving data sets can be stored to form a preset scenario driving calibration database, which is designed to provide configuration selection support for subsequent vehicle model development, including power and torque selection of the powertrain, speed ratio selection of the transmission and the final drive, etc. At the same time, it can also serve the intelligent scenario matching system to facilitate the identification and definition of condition data characteristics. In addition, this database also has a dynamic update function and can promote the deep learning of the matching algorithm, thus realizing the continuous optimization of the algorithm.

[0099] It can be understood that the operating condition tags can be carefully divided into three major categories: configuration category, usage category, and data category. Specifically, corresponding configuration category tags are established for the basic hardware configuration data of each target vehicle. The configuration category tags are mainly used to describe and characterize the configuration attributes of the vehicle, including key information such as vehicle drive type, power unit model, transmission model, etc. When conducting calibration matching degree analysis, the configuration category tags play a decisive role and can have a veto effect on the final driving calibration data. Corresponding usage category tags are established for the actual driving condition characteristics of each target vehicle. The usage category tags reflect the performance of the vehicle under different usage scenarios, including but not limited to high-speed logistics, urban transportation, trunk transportation, cold chain transportation, green channel, etc. This information is crucial for fleet management and operation management and provides necessary support for relevant decisions. Corresponding data category tags are established for the preprocessed actual driving data of each target vehicle. The data category tags represent various situations of the power unit in actual use. These tags are crucial for subsequent vehicle calibration data matching and optimization work. They detail the usage of the power unit under different operating conditions, such as combinations of high-speed driving with low-temperature environment, plain terrain, low-load state, etc., and complex situations such as medium-speed driving with high-temperature environment, mountainous terrain, heavy-load state, etc.

[0100] Furthermore, in some embodiments, after matching the target driving data from the preset scenario driving calibration database, it further includes: sending the target driving data to a preset terminal and determining whether an approval write instruction sent by the user based on the target driving data is received; if the approval write instruction sent by the user based on the target driving data is received, then performing a write operation on the current vehicle based on the target driving data.

[0101] Specifically, after matching the target driving data from the preset scenario driving calibration database, the TBOX installed in the current vehicle can download the target driving data to the vehicle's cache storage. This download process has the function of resume breakpoint transfer, which means that even if the download is interrupted during the process, it can continue to download from the place where it was interrupted last time without affecting the normal use of the vehicle. During this period, the user does not need to perform any manual intervention, and the vehicle can continue to run normally without being disturbed by data updates. When the target driving data caching is completed, a notification of vehicle driving data update can be sent to the user. This notification can be conveyed in various ways, including but not limited to the user's mobile client (such as a mobile phone APP), and interactive devices such as the large screen or instrument inside the vehicle. After receiving the notification, the user can choose whether to immediately use the update according to their own situation and confirm whether the environment where the vehicle is located is suitable for performing a write operation on the relevant vehicle-mounted controller to ensure the safety and effectiveness of the update process.

[0102] After receiving the consent flashing instruction sent by the user based on the target driving data, the current vehicle can be flashed based on the target driving data, and the target driving data can be accurately written into the vehicle's control unit to ensure that the performance and functions of the vehicle are consistent with the target driving data. In addition, during the flashing operation, by using specific flag bits, information feedback can be carried out in real time, and this process ensures the immediacy and accuracy of the data.

[0103] Furthermore, when the entire flashing process is completed, the system will automatically generate a detailed flashing report. This report not only records all the key information during the flashing process, but also will be automatically saved by the system for subsequent review and analysis. In addition, if the system administrator needs to review the flashing records during the management process, these records can be easily retrieved through the background management interface. In this way, the administrator can regularly evaluate and manage the performance and accuracy of the system to ensure that the system is always in the best working condition.

[0104] To facilitate those skilled in the art to further understand the driving data dynamic adaptive method proposed in the embodiments of the present application, the following will be further elaborated in conjunction with Figure 6 and Figure 7 for further elaboration.

[0105] First, the driving data dynamic adaptive system involved in the driving data dynamic adaptive method will be introduced, in conjunction with Figure 6 and Figure 7As shown in the figure, the system can be composed of a cloud platform, in-vehicle devices (such as instrument panels, large screens, gateways, etc.), in-vehicle data devices, in-vehicle controllers (such as ECU (Electronic Control Unit), TCU (Transmission Control Unit), HCU (Hydraulic Control Unit), VCU (Vehicle Control Unit), etc.), mobile phone APP (Application), and GIS maps. Among them, the cloud platform is provided with a total of 4 subsystems, namely, "Scenario Working Condition Analysis System", "Intelligent Scenario Matching System", "Scenario Driving Calibration Database", and "Adaptive Calibration and Application Interaction System". Among them, the "Scenario Working Condition Analysis System" is used to extract vehicle road characteristics, vehicle driving characteristics, and analyze vehicle configurations. The "Intelligent Scenario Matching System" is used to manage customized scenario driving calibration data, analyze vehicle energy consumption, and perform scenario energy consumption database matching. The "Scenario Driving Calibration Database" includes vehicle operation label models, vehicle driving road type label models, and vehicle working condition type label models. The "Adaptive Calibration and Application Interaction System" is used to generate vehicle driving calibration data, issue vehicle driving data upgrade instructions, confirm vehicle driving data upgrade instructions by users, and monitor data writing, and is provided with a "Data Operation Analysis System" as a carrier for model, code compilation, and storage, and can also perform cleaning and analysis of driving data; the in-vehicle devices include a data push interface and a data writing confirmation and instruction activation interface; the in-vehicle data device TBOX, as a data interaction terminal between the vehicle and the cloud platform, has the functions of uploading driving data, downloading calibration data (i.e., target driving data), and receiving writing instructions; the mobile phone APP contains a data push interface and a data writing confirmation and instruction activation interface; the GIS map can provide real-time road condition information, weather information, location information, road slope information, etc.

[0106] According to the driving data dynamic adaptive method proposed in the embodiment of the present application, by analyzing the basic hardware configuration data, actual driving data, and current driving calibration data of the vehicle, and combining with GIS map information, the driving working condition characteristics of the vehicle can be determined. Then, using the driving working condition characteristic data to match the preset scenario driving calibration database and the current driving calibration data, so as to provide the vehicle with target driving data to optimize its driving performance. Thus, by providing more adaptable vehicle driving calibration data for users in real time based on the actual driving scenario, the problem that the existing driving calibration data cannot achieve the optimal cost performance in all scenarios during actual use is solved, and the vehicle economy and driving comfort are improved.

[0107] Next, the driving data dynamic adaptive device proposed in the embodiment of the present application is described with reference to the accompanying drawings.

[0108] Figure 8 It is a block diagram of a driving data dynamic adaptive device according to an embodiment of the present application.

[0109] As Figure 8 shown, the driving data dynamic adaptive device 10 includes: a processing module 100, a determination module 200, and a matching module 300.

[0110] Among them, the processing module 100 is configured to obtain the basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain the preprocessed actual driving data;

[0111] The determination module 200 is configured to determine the current driving condition characteristics of the current vehicle based on the preprocessed actual driving data and GIS map information;

[0112] The matching module 300 is configured to determine at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, and respectively match the preprocessed actual driving data with the at least one set of to-be-switched driving calibration data and the current driving calibration data, and determine the target driving data according to the matching result, so that the current vehicle drives based on the target driving data.

[0113] Further, in some embodiments, before determining at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, the matching module 300 is further configured to:

[0114] Obtain the basic hardware configuration data sets and actual driving data sets of multiple target vehicles, and preprocess the actual driving data sets to obtain the preprocessed actual driving data sets;

[0115] Based on the GIS map information of each target vehicle, determine the actual driving condition characteristics of each target vehicle, and generate a configuration class label corresponding to the basic hardware configuration data of each target vehicle, a usage class label corresponding to the actual driving condition characteristics of each target vehicle, and a data class label corresponding to the preprocessed actual driving data of each target vehicle;

[0116] Based on the configuration class label corresponding to the basic hardware configuration data of each target vehicle, generate a preset scenario driving calibration database according to the mapping relationship between the usage class label corresponding to the actual driving condition characteristics of each target vehicle and the data class label corresponding to the preprocessed actual driving data of each target vehicle.

[0117] Further, in some embodiments, the matching module 300 includes:

[0118] A calculation unit for calculating the overlapping areas between the polygon radar chart of the pre-processed actual driving data and the polygon radar charts of each driving calibration data to be switched and the polygon radar chart of the current driving calibration data respectively, obtaining a plurality of overlapping area values;

[0119] A determination unit for determining the target driving data according to the plurality of overlapping area values.

[0120] Further, in some embodiments, the determination unit is specifically configured to:

[0121] Identify the radar chart with the largest overlapping area value among the plurality of overlapping area values;

[0122] Take the driving calibration data corresponding to the radar chart with the largest overlapping area value as the target driving data.

[0123] Further, in some embodiments, the calculation unit includes:

[0124] A determination subunit for determining at least one radar chart dimension and the weight of each radar chart dimension based on the pre-processed actual driving data, the driving calibration data to be switched, and the current driving calibration data;

[0125] A generation subunit for generating the polygon radar charts of the pre-processed actual driving data, the polygon radar charts of each driving calibration data to be switched, and the polygon radar chart of the current driving calibration data based on at least one radar chart dimension and the weight of each radar chart dimension;

[0126] An overlapping subunit for sequentially overlapping the polygon radar chart of the pre-processed actual driving data with the polygon radar charts of each driving calibration data to be switched and the polygon radar chart of the current driving calibration data, and obtaining a plurality of overlapping area values according to the overlapping results.

[0127] Further, in some embodiments, the generation subunit is specifically configured to:

[0128] Based on at least one radar chart dimension, convert the pre-processed actual driving data, the driving calibration data to be switched, and the current driving calibration data into corresponding single-score characterizations respectively;

[0129] Generate the polygon radar charts of the pre-processed actual driving data, the polygon radar charts of each driving calibration data to be switched, and the polygon radar chart of the current driving calibration data based on at least one radar chart dimension, the weight of each radar chart dimension, and the corresponding single-score characterization results.

[0130] Further, in some embodiments, after matching the target driving data from the preset scenario driving calibration database, the matching module 300 is further configured to:

[0131] Send the target driving data to a preset terminal, and determine whether an approval flashing instruction sent by the user based on the target driving data is received;

[0132] In the case of receiving an approval flashing instruction sent by the user based on the target driving data, flash the current vehicle based on the target driving data.

[0133] It should be noted that the foregoing explanation of the embodiment of the driving data dynamic adaptation method also applies to the driving data dynamic adaptation device of this embodiment, and will not be elaborated here.

[0134] According to the driving data dynamic adaptation device provided by the embodiments of the present application, by analyzing the basic hardware configuration data, actual driving data and current driving calibration data of the vehicle, and combining with the GIS map information, the driving condition characteristics of the vehicle can be determined. Then, the driving condition characteristic data is used to match the preset scenario driving calibration database and the current driving calibration data, so as to provide the target driving data for the vehicle to optimize its driving performance. Thus, by providing more adaptable vehicle driving calibration data for the user in real time based on the actual driving scenario, the problem that the performance of the existing driving calibration data cannot achieve the optimal cost performance in the full scenario during actual use is solved, and the vehicle economy and driving comfort are improved.

[0135] Figure 9 This is a schematic structural diagram of the vehicle provided by the embodiments of the present application. The vehicle may include:

[0136] A memory 901, a processor 902, and a computer program stored on the memory 901 and executable on the processor 902.

[0137] When the processor 902 executes the program, it implements the driving data dynamic adaptation method provided in the foregoing embodiment.

[0138] Further, the vehicle further includes:

[0139] A communication interface 903 for communication between the memory 901 and the processor 902.

[0140] The memory 901 is used to store a computer program executable on the processor 902.

[0141] The memory 901 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0142] If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 can be interconnected via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] Optionally, in a specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a single chip, the memory 901, the processor 902, and the communication interface 903 can communicate with each other through an internal interface.

[0144] The processor 902 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0145] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned dynamic adaptive method for driving data is implemented.

[0146] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0147] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic descriptions of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0148] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A driving data dynamic adaptive method, characterized in that: The following steps are involved: Acquire basic hardware configuration data, actual driving data, and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain preprocessed actual driving data; Determining the current driving condition characteristics of the current vehicle based on the pre-processed actual driving data and GIS map information; Based on the basic hardware configuration data and the current driving condition characteristics, at least one group of driving calibration data to be switched is determined from a preset scenario driving calibration database, and the preprocessed actual driving data is matched with the at least one group of driving calibration data to be switched and the current driving calibration data, respectively, and the target driving data is determined according to the matching result, so that the current vehicle drives based on the target driving data.

2. The method according to claim 1, characterized in that Before determining at least one set of to-be-switched driving calibration data from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, the method further includes: Acquire basic hardware configuration data sets and actual driving data sets of multiple target vehicles, and preprocess the actual driving data sets to obtain preprocessed actual driving data sets; Based on the GIS map information of each target vehicle, the actual driving condition characteristics of each target vehicle are determined, and a configuration class label corresponding to the basic hardware configuration data of each target vehicle, a usage class label corresponding to the actual driving condition characteristics of each target vehicle, and a data class label corresponding to the preprocessed actual driving data of each target vehicle are generated; Based on the configuration class labels corresponding to the basic hardware configuration data of each target vehicle, the preset scenario driving calibration database is generated according to the mapping relationship between the usage class labels corresponding to the actual driving condition characteristics of each target vehicle and the data class labels corresponding to the preprocessed actual driving data of each target vehicle.

3. The method according to claim 1, characterized in that The pre-processed actual driving data is matched with the at least one set of driving calibration data to be switched and the current driving calibration data respectively, and the target driving data is determined according to the matching result, including: Respectively calculating the overlapping areas between the polygonal radar map of the preprocessed actual driving data and each polygonal radar map of the driving calibration data to be switched and the polygonal radar map of the current driving calibration data to obtain a plurality of overlapping area values; The target driving data is determined according to the multiple overlapping area values.

4. The method according to claim 3, characterized in that The determining the target driving data according to the multiple overlapping area values ​​comprises: Identifying a radar chart having a maximum overlapping area value among the multiple overlapping area values; The driving calibration data corresponding to the radar chart with the largest overlapping area value is used as the target driving data.

5. The method according to claim 3, characterized in that: The method of respectively calculating the overlapping areas between the polygonal radar map of the preprocessed actual driving data and each polygonal radar map of the driving calibration data to be switched and the polygonal radar map of the current driving calibration data to obtain a plurality of overlapping area values ​​includes: Determining at least one radar map dimension and a weight of each radar map dimension based on the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data; Based on the at least one radar chart dimension and the weight of each radar chart dimension, generating a polygonal radar chart of the preprocessed actual driving data, a polygonal radar chart of each driving calibration data to be switched, and a polygonal radar chart of the current driving calibration data; The polygonal radar map of the preprocessed actual driving data is overlapped with the polygonal radar map of each driving calibration data to be switched and the polygonal radar map of the current driving calibration data in sequence, and the multiple overlapping area values ​​are obtained according to the overlapping results.

6. The method according to claim 5, characterized in that The step of generating the polygonal radar map of the preprocessed actual driving data, the polygonal radar map of each to-be-switched driving calibration data, and the polygonal radar map of the current driving calibration data based on the at least one radar map dimension and the weight of each radar map dimension comprises: Based on the at least one radar chart dimension, respectively converting the preprocessed actual driving data, the to-be-switched driving calibration data, and the current driving calibration data into corresponding single score representations; A polygonal radar chart of the preprocessed actual driving data, a polygonal radar chart of each driving calibration data to be switched, and a polygonal radar chart of the current driving calibration data are generated based on the at least one radar chart dimension, the weight of each radar chart dimension, and the corresponding single score representation result.

7. The method according to claim 1, characterized in that After determining the target driving data according to the matching result, the method further includes: Sending the target driving data to a preset terminal, and determining whether a flash writing instruction sent by a user based on the target driving data is received; If a flashing instruction is received from the user based on the target driving data, the current vehicle is flashed based on the target driving data.

8. A driving data dynamic self-adaptive device, characterized in that: include: A processing module, used to obtain basic hardware configuration data of the current vehicle, actual driving data and current driving calibration data of the current vehicle, and preprocess the actual driving data to obtain preprocessed actual driving data; A determination module, used to determine the current driving condition characteristics of the current vehicle based on the pre-processed actual driving data and GIS map information; A matching module is used to determine at least one set of driving calibration data to be switched from a preset scenario driving calibration database based on the basic hardware configuration data and the current driving condition characteristics, and respectively match the preprocessed actual driving data with the at least one set of driving calibration data to be switched and the current driving calibration data, and determine the target driving data according to the matching results, so that the current vehicle drives based on the target driving data.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for dynamic self-adaptation of driving data as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the driving data dynamic adaptation method as described in any one of claims 1 to 7.

Images