Driving behavior scoring method and device, equipment and storage medium

Abstract

The invention discloses a driving behavior scoring method and device, equipment and a storage medium, and the method comprises the steps: building a preset driving behavior evaluation system through obtaining the vehicle networking data of a current vehicle networking; evaluating the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer index score; the comprehensive score of the driving behavior is calculated according to the operation layer index score, the accuracy and the intelligent level of the scoring system can be improved by dynamically adjusting the evaluation index of the driving behavior and adaptively adjusting the evaluation standard of the evaluation index, the fairness and the objectivity of the evaluation result are improved, and the evaluation efficiency is improved. The scoring result can help research, development, after-sales and users to know the influence of vehicle driving behaviors on economy in time and improve driving habits in time, so that the efficiency is improved, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of engine energy-saving control, and in particular to a driving behavior scoring method, device, equipment and storage medium. Background Art

[0002] Good driving behavior can significantly improve vehicle economy, reduce fuel consumption, lower operating costs, and have a positive impact on environmental protection; traditional driving behavior evaluation methods rely on simple rules and thresholds, which are difficult to fully reflect the complexity and diversity of driving behavior.

[0003] The existing driving behavior evaluation mainly focuses on ensuring the travel safety of driving users and reducing the frequency of traffic accidents; secondly, its evaluation relies on fixed evaluation indicators, such as speeding, sudden acceleration, sudden deceleration, sharp turns, etc.; thirdly, the selected evaluation indicators are used to evaluate driving behavior based on determined thresholds, rules or weights.

[0004] When using fixed evaluation indicators to analyze the impact on economy, some indicators with little relevance will be put into the evaluation system, which will distract the focus of the evaluation system and cause the evaluation results to deviate from the main goals; using certain thresholds or rules to evaluate fixed indicators will distort the evaluation results and make them lose accuracy. In the case of unreasonable weight setting, the evaluation results may be biased towards non-economic indicators, affecting the fairness and objectivity of the evaluation; if the indicators do not meet the actual needs of the drivers, it will reduce the user's acceptance of the evaluation results. Summary of the invention

[0005] The main purpose of the present invention is to provide a driving behavior scoring method, device, equipment and storage medium, aiming to solve the technical problems in the prior art that the use of fixed evaluation index analysis easily leads to the evaluation results deviating from the main objectives, the index evaluation accuracy is poor, and the evaluation results are biased towards non-economic indicators, affecting the fairness and objectivity of the evaluation, and the indicators are inconsistent with the actual needs of the driver, which will reduce the user's acceptance of the evaluation results.

[0006] In a first aspect, the present invention provides a driving behavior scoring method, the driving behavior scoring method comprising the following steps:

[0007] Obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system;

[0008] Evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score;

[0009] The comprehensive score of the driving behavior is calculated according to the operation layer indicator score.

[0010] Optionally, the obtaining of the Internet of Vehicles data of the current Internet of Vehicles and constructing a preset driving behavior evaluation system includes:

[0011] Acquire the Internet of Vehicles data of the current Internet of Vehicles, filter the Internet of Vehicles data, and obtain various data indicators;

[0012] Generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to the preset classification operation rules, and generate an operation layer;

[0013] Taking driving behavior as the target layer, a preset driving behavior evaluation system is constructed according to the indicator layer, the operation layer and the target layer.

[0014] Optionally, the obtaining of Internet of Vehicles data of the current Internet of Vehicles and screening of the Internet of Vehicles data to obtain various data indicators include:

[0015] Obtain the current Internet of Vehicles data and obtain the adaptive coefficient;

[0016] The Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators.

[0017] Optionally, the acquiring the Internet of Vehicles data of the current Internet of Vehicles and acquiring the adaptive coefficient includes:

[0018] Get the current Internet of Vehicles data;

[0019] The adaptive coefficient is calculated according to the following formula:

[0020]

[0021] Among them, ρ k is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

[0022] Optionally, the Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators, including:

[0023] Comparing the absolute value of the adaptive coefficient with a preset coefficient threshold;

[0024] Indicators in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold are used as various data indicators.

[0025] Optionally, evaluating the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score includes:

[0026] Determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the determination result;

[0027] Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library;

[0028] Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario;

[0029] Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula;

[0030]

[0031] Among them, B j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators;

[0032] The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

[0033] Optionally, calculating the comprehensive score of the driving behavior according to the operation layer indicator score includes:

[0034] The parameter scores of the corresponding parameters in the operation layer index score are multiplied by the corresponding weight coefficients, and the total sum after the multiplication is calculated, and the total sum is used as the comprehensive score of the driving behavior.

[0035] In a second aspect, in order to achieve the above-mentioned object, the present invention further proposes a driving behavior scoring device, the driving behavior scoring device comprising:

[0036] The data acquisition module is used to obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system;

[0037] An evaluation module, used to evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score;

[0038] The score calculation module is used to calculate the comprehensive score of the driving behavior according to the operation layer indicator score.

[0039] In a third aspect, to achieve the above-mentioned purpose, the present invention further proposes a driving behavior scoring device, which includes: a memory, a processor, and a driving behavior scoring program stored in the memory and executable on the processor, wherein the driving behavior scoring program is configured to implement the steps of the driving behavior scoring method described above.

[0040] In a fourth aspect, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a driving behavior scoring program is stored, and when the driving behavior scoring program is executed by a processor, the steps of the driving behavior scoring method described above are implemented.

[0041] The driving behavior scoring method proposed in the present invention acquires the Internet of Vehicles data of the current Internet of Vehicles to construct a preset driving behavior evaluation system; evaluates the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer index score; and calculates a comprehensive score of the driving behavior according to the operation layer index score. The method can improve the accuracy and intelligence level of the scoring system and the fairness and objectivity of the evaluation results by dynamically adjusting the evaluation indicators of the driving behavior and adaptively adjusting the evaluation criteria of the evaluation indicators. The scoring results can help R&D, after-sales, and users to timely understand the impact of vehicle driving behavior on economy and improve driving habits in a timely manner, thereby improving efficiency and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0043] Figure 2 This is a flow chart of a first embodiment of a driving behavior scoring method of the present invention;

[0044] Figure 3 This is a flow chart of a second embodiment of the driving behavior scoring method of the present invention;

[0045] Figure 4 Schematic diagram of the driving behavior evaluation index system in the driving behavior scoring method of the present invention;

[0046] Figure 5 This is a flow chart of a third embodiment of a driving behavior scoring method according to the present invention;

[0047] Figure 6 This is a flow chart of a fourth embodiment of a driving behavior scoring method according to the present invention;

[0048] Figure 7 1 is a functional module diagram of the first embodiment of the driving behavior scoring device of the present invention.

[0049] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0051] The solution of the embodiment of the present invention is mainly: by acquiring the Internet of Vehicles data of the current Internet of Vehicles, a preset driving behavior evaluation system is constructed; the Internet of Vehicles data is evaluated according to the preset driving behavior evaluation system to obtain the operation layer indicator score; the comprehensive score of the driving behavior is calculated according to the operation layer indicator score, and the evaluation index of the driving behavior can be dynamically adjusted and the evaluation standard of the evaluation index is adaptively adjusted, thereby improving the accuracy and intelligence level of the scoring system, and improving the fairness and objectivity of the evaluation results. The scoring results can help R&D, after-sales, and users to timely understand the impact of vehicle driving behavior on economy, and improve driving habits in time, thereby improving efficiency and reducing operating costs. It solves the technical problems in the prior art that the use of fixed evaluation index analysis easily leads to the deviation of the evaluation results from the main goals, the poor accuracy of the index evaluation, and the evaluation results will be biased towards non-economic indicators, affecting the fairness and objectivity of the evaluation, and the indicators are inconsistent with the actual needs of the driver, which will reduce the user's acceptance of the evaluation results.

[0052] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0053] like Figure 1 As shown, the device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory, or it may be a stable memory (Non-Volatile Memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0055] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating device, a network communication module, a user interface module, and a driving behavior scoring program.

[0056] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and performs the following operations:

[0057] Obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system;

[0058] Evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score;

[0059] The comprehensive score of the driving behavior is calculated according to the operation layer indicator score.

[0060] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0061] Acquire the Internet of Vehicles data of the current Internet of Vehicles, filter the Internet of Vehicles data, and obtain various data indicators;

[0062] Generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to the preset classification operation rules, and generate an operation layer;

[0063] Taking driving behavior as the target layer, a preset driving behavior evaluation system is constructed according to the indicator layer, the operation layer and the target layer.

[0064] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0065] Obtain the current Internet of Vehicles data and obtain the adaptive coefficient;

[0066] The Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators.

[0067] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0068] Get the current Internet of Vehicles data;

[0069] The adaptive coefficient is calculated according to the following formula:

[0070]

[0071] Among them, ρk is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

[0072] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0073] Comparing the absolute value of the adaptive coefficient with a preset coefficient threshold;

[0074] Indicators in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold are used as various data indicators.

[0075] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0076] Determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the determination result;

[0077] Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library;

[0078] Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario;

[0079] Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula;

[0080]

[0081] Among them, B j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators;

[0082] The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

[0083] The device of the present invention calls the driving behavior scoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0084] The parameter scores of the corresponding parameters in the operation layer index score are multiplied by the corresponding weight coefficients, and the total sum after the multiplication is calculated, and the total sum is used as the comprehensive score of the driving behavior.

[0085] Through the above scheme, this embodiment constructs a preset driving behavior evaluation system by acquiring the Internet of Vehicles data of the current Internet of Vehicles; evaluates the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain the operation layer index score; calculates the comprehensive score of the driving behavior according to the operation layer index score, and can improve the accuracy and intelligence level of the scoring system and the fairness and objectivity of the evaluation results by dynamically adjusting the evaluation indicators of the driving behavior and adaptively adjusting the evaluation standards of the evaluation indicators. The scoring results can help R&D, after-sales, and users to timely understand the impact of vehicle driving behavior on economy and improve driving habits in a timely manner, thereby improving efficiency and reducing operating costs.

[0086] Based on the above hardware structure, an embodiment of the driving behavior scoring method of the present invention is proposed.

[0087] Reference Figure 2 , Figure 2 FIG. 1 is a flow chart of a first embodiment of a driving behavior scoring method according to the present invention.

[0088] In a first embodiment, the driving behavior scoring method comprises the following steps:

[0089] Step S10: Acquire the Internet of Vehicles data of the current Internet of Vehicles and construct a preset driving behavior evaluation system.

[0090] It should be noted that by obtaining the Internet of Vehicles data of the current Internet of Vehicles, a preset driving behavior evaluation system can be constructed based on the data of the current Internet of Vehicles.

[0091] Step S20: Evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score.

[0092] It should be understood that the Internet of Vehicles data is evaluated according to the preset driving behavior evaluation system to obtain an indicator score at the operation level.

[0093] Furthermore, the step S20 specifically includes the following steps:

[0094] Determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the determination result;

[0095] Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library;

[0096] Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario;

[0097] Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula;

[0098]

[0099] Among them, B j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators;

[0100] The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

[0101] It should be noted that the adaptive fuzzy rule base is constructed, and the fuzzy rules are continuously updated and optimized through data-driven methods to adapt to the behavior patterns and driving habits of different drivers. The third-level indicators involved in the evaluation use the adaptive comment rule base to complete the evaluation of the indicators.

[0102] There are two ways to design the comment rule base.

[0103] Method 1: When the data distribution of the evaluation index conforms to the normal distribution and the range of the mean μ±3 times the standard deviation σ is within the current data range, the following rule base is used:

[0104]

[0105]

[0106] The rule base is not limited to the rules described in the above table, and the adaptive range of the comment items can be adjusted according to actual needs.

[0107] Method 2: When the data distribution of the evaluation index conforms to the normal distribution and the range of the mean ± 3 times the standard deviation is not within the current data range or the data distribution does not conform to the normal distribution, the index data is borrowed from the concept of quantile (for example, 0.2 means the 20% number after the data is arranged from small to large. Other values ​​are deduced in the same way.) and the following rule base is used:

[0108] Comments Adaptive coefficient>0 Adaptive coefficient < 0 very good <＝0.2 >0.8 good (0.2,0.6] (0.4,0.8] generally (0.6,0.9] (0.1,0.4] Difference >0.9 <＝0.1

[0109] The rule base is not limited to the rules described in the above table, and the adaptive range of the comment items can be adjusted according to actual needs.

[0110] It should be understood that dynamic adjustment of the weight coefficient can be achieved according to different usage scenarios and road conditions.

[0111] Clarify different usage scenarios (resource transportation, express logistics, cold chain transportation, etc.), road conditions (such as highways, national and provincial roads, and others), and terrain conditions (such as plains, mountainous areas, hills, etc.), classify each scenario and condition, and define corresponding evaluation indicators.

[0112] The weight coefficient is preliminarily set based on the importance of each scenario and condition. For example, taking the trunk express market segment as an example, the proportion of its driving on highways will be relatively large, so the weight of the vehicle speed in the secondary indicator can be reduced.

[0113] Based on real-time data, a feedback mechanism is established to dynamically adjust the weight coefficient. For example, when a long uphill slope is detected on the road, the weight of the throttle indicator in the secondary indicator can be reduced.

[0114] Use machine learning models to analyze historical data and identify the best weight combinations for different scenarios and conditions. By training the model, the weight coefficients can be adjusted automatically.

[0115] In the specific implementation, B in the above formula is a fuzzy evaluation set, and its specific number is called membership degree; a multi-level evaluation model can be established to carry out evaluation for indicators at different levels.

[0116] First, the weight judgment matrix of each indicator is calculated based on the indicator data of the third layer using the evaluation indicator comment rule base. For example, the average driving speed appears 2 times, 4 times, 1 time, and 3 times in very good, good, average, and poor, respectively, and the total number of times is 10 times, so the weight judgment matrix of the average driving speed is [0.2, 0.4, 0.1, 0.3].

[0117] Secondly, the weight judgment matrix of the third-layer indicators belonging to the second-layer operation layer and the weight coefficient matrix of the third layer are multiplied first and then added to obtain the evaluation matrix of the second-layer indicators.

[0118] Step S30: Calculate the comprehensive score of the driving behavior according to the operation layer indicator score.

[0119] It can be understood that the comprehensive score of driving behavior can be calculated based on the operation layer indicator score.

[0120] Through the above scheme, this embodiment constructs a preset driving behavior evaluation system by acquiring the Internet of Vehicles data of the current Internet of Vehicles; evaluates the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain the operation layer index score; calculates the comprehensive score of the driving behavior according to the operation layer index score, and can improve the accuracy and intelligence level of the scoring system and the fairness and objectivity of the evaluation results by dynamically adjusting the evaluation indicators of the driving behavior and adaptively adjusting the evaluation standards of the evaluation indicators. The scoring results can help R&D, after-sales, and users to timely understand the impact of vehicle driving behavior on economy and improve driving habits in a timely manner, thereby improving efficiency and reducing operating costs.

[0121] Further, Figure 3 FIG. 2 is a flow chart of a second embodiment of the driving behavior scoring method of the present invention. Figure 3 As shown, a second embodiment of the driving behavior scoring method of the present invention is proposed based on the first embodiment. In this embodiment, the step S10 specifically includes the following steps:

[0122] Step S11: Acquire the Internet of Vehicles data of the current Internet of Vehicles, filter the Internet of Vehicles data, and obtain various data indicators.

[0123] It should be noted that after obtaining the Internet of Vehicles data of the current Internet of Vehicles, the Internet of Vehicles data can be preliminarily screened to obtain various data indicators.

[0124] Step S12: Generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to preset classification operation rules, and generate an operation layer.

[0125] It can be understood that an indicator layer can be generated according to the various types of data indicators, and the data of each indicator layer can be classified according to a preset classification operation rule to generate an operation layer.

[0126] Step S13: Taking driving behavior as the target layer, a preset driving behavior evaluation system is constructed according to the indicator layer, the operation layer and the target layer.

[0127] It should be understood that, taking driving behavior as the target layer, a preset driving behavior evaluation system can be constructed according to the indicator layer, the operation layer and the target layer.

[0128] In the specific implementation, see Figure 4 , Figure 4 Schematic diagram of the driving behavior evaluation index system in the driving behavior scoring method of the present invention. Figure 4As shown in the figure, a driving behavior evaluation index system based on big data is divided into three levels. The first level is the driving behavior target level; the second level is the operation level that is closely related to the driver's driving operation, which is divided into five operation contents: vehicle speed control, speed control, throttle control, brake control, and gear control; the third level is a level of various indicators that can actually evaluate driving behavior, which are derived from the vehicle speed, speed, throttle, brake, and gear signals that can be obtained from the Internet of Vehicles.

[0129] Among them, vehicle speed control includes high speed proportion, average vehicle speed, average driving speed, average low speed proportion, rapid acceleration cumulative time, rapid acceleration proportion, rapid deceleration cumulative time, rapid deceleration proportion, starting time proportion, number of starts and stops per 100 kilometers, cruising time proportion and other indicators; speed control includes economic speed time proportion, economic working condition time proportion and other indicators; throttle control includes low load working condition time proportion, large throttle proportion, large torque proportion, engine high efficiency zone time proportion and other indicators; braking control includes braking time proportion, braking mileage proportion and other indicators; gear control includes clutch opening and closing times greater than the set value, clutch disconnection time greater than the set value, gear shifting speed, high-end high-end cumulative time proportion, high-speed high-end time proportion, gear shifting frequency, high-speed gear up frequency, high-speed gear down frequency, gear jump up frequency, gear jump down frequency, neutral gliding time proportion, gear gliding time proportion, cruising time proportion and other indicators.

[0130] The original data of each indicator in the indicator layer comes from the various data uploaded to the Internet of Vehicles by the on-board Tbox and the map information data in the cloud database, including engine control domain signals, instrument panel signals, GPS geographic information data, map data, etc.; the calculation of each indicator in the indicator layer is completed on the cloud server, and the signals from different signal domains are extracted from different databases to perform multi-dimensional data fusion and synchronization to complete the calculation.

[0131] Through the above scheme, this embodiment obtains the Internet of Vehicles data of the current Internet of Vehicles, screens the Internet of Vehicles data, and obtains various data indicators; generates an indicator layer according to the various data indicators, classifies the data of each indicator layer according to preset classification operation rules, and generates an operation layer; takes driving behavior as the target layer, and constructs a preset driving behavior evaluation system according to the indicator layer, the operation layer, and the target layer, which can quickly and comprehensively construct a preset driving behavior evaluation system and improve the speed and efficiency of driving behavior scoring.

[0132] Further, Figure 5 FIG. 4 is a flow chart of a third embodiment of the driving behavior scoring method of the present invention. Figure 5 As shown, a third embodiment of the driving behavior scoring method of the present invention is proposed based on the second embodiment. In this embodiment, the step S11 specifically includes the following steps:

[0133] Step S111: Obtain the Internet of Vehicles data of the current Internet of Vehicles and obtain the adaptive coefficient.

[0134] It should be noted that the Internet of Vehicles data of the current Internet of Vehicles is obtained, and the adaptive coefficient is obtained, and the adaptive coefficient is an adaptive parameter corresponding to different driving behavior indicators.

[0135] Furthermore, the step S111 specifically includes the following steps:

[0136] Get the current Internet of Vehicles data;

[0137] The adaptive coefficient is calculated according to the following formula:

[0138]

[0139] Among them, ρ k is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

[0140] It should be understood that before calculating each driving behavior index, first, according to the classification of the second layer, the third layer index belonging to the second layer is respectively calculated according to the above formula to complete the index adaptability calculation, X i Y is the various indicators of the indicator layer in the evaluation indicator system, such as high speed ratio, average speed, average driving speed and other indicators; i These are economic indicators of the vehicle, such as fuel consumption per 100 kilometers, fuel consumption per 100 kilometers without idling, and other indicators that reflect the economy of the vehicle.

[0141] Furthermore, the step of screening the Internet of Vehicles data according to the adaptive coefficient to obtain various data indicators specifically includes the following steps:

[0142] Comparing the absolute value of the adaptive coefficient with a preset coefficient threshold;

[0143] Indicators in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold are used as various data indicators.

[0144] It is understandable that the indicator in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold can be used as various data indicators.

[0145] In a specific implementation, the index whose absolute value of the adaptive coefficient can be calculated to be greater than m (the value range of m is [0,1]) is the third-level index selected in this driving behavior evaluation.

[0146] Step S112: Filter the Internet of Vehicles data according to the adaptive coefficient to obtain various data indicators.

[0147] It should be understood that after the adaptive coefficient is obtained, the Internet of Vehicles data can be screened according to the adaptive coefficient to obtain various data indicators.

[0148] In the specific implementation, Table 1 shows the established three-level indicator system, as well as the indicators of the third-level indicator layer and its adaptive coefficient.

[0149] Table 1 Driving behavior indicators and adaptive coefficients

[0150]

[0151]

[0152] Adaptive evaluation index comment rule base generated for the indicators in Table 1

[0153] Table 2 Evaluation index comment rule base

[0154]

[0155] Dynamic weight vector matrix established for secondary indicators.

[0156] Table 3 Secondary indicator dynamic weight vector matrix

[0157]

[0158] Make a weight judgment matrix for the index items based on the multi-day data of a certain vehicle.

[0159] Table 4 Weight judgment matrix (normalized)

[0160]

[0161] With the weight judgment matrix and weight vector moment, we can carry out multi-layer scoring calculation. First, we calculate the scores of the secondary indicator items.

[0162] Table 5 Secondary indicator scores

[0163]

[0164] Through the scores of the secondary indicators and their weights, the comprehensive score of driving behavior can be calculated.

[0165] The big data of the Internet of Vehicles can be used to obtain the scoring results of multiple vehicles. The differences in scores for different indicators of different vehicles can be used to make targeted improvements.

[0166] Through the above scheme, this embodiment obtains the Internet of Vehicles data of the current Internet of Vehicles and obtains an adaptive coefficient; the Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators, and various data indicators can be obtained quickly, thereby improving the speed and efficiency of driving behavior scoring.

[0167] Further, Figure 6 FIG. 4 is a flow chart of a fourth embodiment of the driving behavior scoring method of the present invention. Figure 6 As shown, a fourth embodiment of the driving behavior scoring method of the present invention is proposed based on the third embodiment. In this embodiment, the step S30 specifically includes the following steps:

[0168] Step S31: multiply the parameter scores of the corresponding parameters in the operation layer index score by the corresponding weight coefficients, calculate the total sum after the multiplication, and use the total sum as the comprehensive score of the driving behavior.

[0169] It should be noted that the parameter scores of the corresponding parameters in the operation layer index score are multiplied by the corresponding weight coefficients and summed to obtain a comprehensive score of the driving behavior.

[0170] It can be understood that the scores of the second operation layer are obtained by multiplying and adding each item of the second layer operation layer based on the evaluation matrix of the second layer and the weighted comment score matrix of the second layer; and the comprehensive score of the driving behavior is obtained by multiplying and adding each item of the second layer operation layer and the weight coefficient matrix of the second layer.

[0171] It should be understood that based on the data from the current Internet of Vehicles, a three-level evaluation system is established for driving behavior indicators that affect vehicle economy, and each vehicle's respective three-level indicators are adaptively generated based on the data. The comment rule library and weight coefficients of the three-level indicators are dynamically adjusted, and the secondary indicator scores and the comprehensive scores of driving behavior are calculated in layers. The driving behavior evaluation based on Internet-connected big data can provide an objective evaluation of driving behavior for R&D and after-sales analysis of vehicle fuel economy, and solve the problem of fleet management to evaluate driving behavior in order to improve the fuel economy of the fleet.

[0172] In the specific implementation, the evaluation indicators of driving behavior can be adjusted dynamically; the evaluation criteria of the evaluation indicators can be adjusted adaptively; the weight coefficient can be adjusted dynamically; the scoring system is evaluated at multiple levels, and the scoring system at least includes the controller, instrument system, vehicle-mounted T-BOX, cloud platform, R&D platform and mobile phone APP; the controller, instrument system and vehicle-mounted T-BOX are all installed on the vehicle, the cloud platform is a data network platform, and the mobile phone APP needs to be installed on the driver's mobile phone; the controller collects the engine control domain signal, instrument panel signal, and GPS geographic information data in real time, and sends it to the vehicle-mounted T-BOX, and the vehicle-mounted T-BOX sends the signal to the cloud platform, and the cloud platform will evaluate the driving behavior of the vehicle based on the collected signals and the map information stored on the cloud platform; the R&D platform can view the background data in real time to understand the vehicle's driving behavior score; the driving behavior score results and improvement suggestions are pushed to the vehicle-side instrument system and the driver's mobile phone APP according to the set time period, reminding the driver to adjust the driving behavior according to the comprehensive score of the driving behavior and the score of the operation layer.

[0173] Through the above scheme, this embodiment multiplies the parameter scores of the corresponding parameters in the operation layer index score by the corresponding weight coefficient, calculates the total sum after the multiplication, and uses the total sum as the comprehensive score of the driving behavior; constructs a preset driving behavior evaluation system by acquiring the Internet of Vehicles data of the current Internet of Vehicles; evaluates the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain the operation layer index score; calculates the comprehensive score of the driving behavior according to the operation layer index score, and can improve the accuracy and intelligence level of the scoring system and the fairness and objectivity of the evaluation results by dynamically adjusting the evaluation indicators of the driving behavior and adaptively adjusting the evaluation standards of the evaluation indicators. The scoring results can help R&D, after-sales, and users to timely understand the impact of vehicle driving behavior on economy and improve driving habits in a timely manner, thereby improving efficiency and reducing operating costs.

[0174] Accordingly, the present invention further provides a driving behavior scoring device.

[0175] Reference Figure 7 , Figure 7 1 is a functional module diagram of the first embodiment of the driving behavior scoring device of the present invention.

[0176] In the first embodiment of the driving behavior scoring device of the present invention, the driving behavior scoring device comprises:

[0177] The data acquisition module 10 is used to acquire the Internet of Vehicles data of the current Internet of Vehicles and build a preset driving behavior evaluation system.

[0178] The evaluation module 20 is used to evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score.

[0179] The score calculation module 30 is used to calculate the comprehensive score of the driving behavior according to the operation layer indicator score.

[0180] The data acquisition module 10 is also used to obtain the Internet of Vehicles data of the current Internet of Vehicles, screen the Internet of Vehicles data, and obtain various data indicators; generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to preset classification operation rules, and generate an operation layer; take driving behavior as the target layer, and construct a preset driving behavior evaluation system according to the indicator layer, the operation layer and the target layer.

[0181] The data acquisition module 10 is also used to acquire the Internet of Vehicles data of the current Internet of Vehicles and acquire an adaptive coefficient; and filter the Internet of Vehicles data according to the adaptive coefficient to acquire various data indicators.

[0182] The data acquisition module 10 is also used to acquire the Internet of Vehicles data of the current Internet of Vehicles;

[0183] The adaptive coefficient is calculated according to the following formula:

[0184]

[0185] Among them, ρ k is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

[0186] The data acquisition module 10 is further used to compare the absolute value of the adaptive coefficient with a preset coefficient threshold; and to use indicators in the Internet of Vehicles data whose absolute value of the adaptive coefficient is greater than the preset coefficient threshold as various data indicators.

[0187] The evaluation module 20 is further used to determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the judgment result;

[0188] Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library;

[0189] Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario;

[0190] Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula;

[0191]

[0192] Among them, B j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators;

[0193] The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

[0194] The score calculation module 30 is further used to multiply the parameter scores corresponding to each parameter in the operation layer index score by the corresponding weight coefficient, and calculate the total sum after the multiplication, and use the total sum as the comprehensive score of the driving behavior.

[0195] The steps implemented by each functional module of the driving behavior scoring device may refer to the various embodiments of the driving behavior scoring method of the present invention, and will not be described in detail here.

[0196] In addition, an embodiment of the present invention further provides a storage medium, on which a driving behavior scoring program is stored. When the driving behavior scoring program is executed by a processor, the following operations are implemented:

[0197] Obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system;

[0198] Evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score;

[0199] The comprehensive score of the driving behavior is calculated according to the operation layer indicator score.

[0200] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0201] Acquire the Internet of Vehicles data of the current Internet of Vehicles, filter the Internet of Vehicles data, and obtain various data indicators;

[0202] Generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to the preset classification operation rules, and generate an operation layer;

[0203] Taking driving behavior as the target layer, a preset driving behavior evaluation system is constructed according to the indicator layer, the operation layer and the target layer.

[0204] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0205] Obtain the current Internet of Vehicles data and obtain the adaptive coefficient;

[0206] The Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators.

[0207] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0208] Get the current Internet of Vehicles data;

[0209] The adaptive coefficient is calculated according to the following formula:

[0210]

[0211] Among them, ρ k is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

[0212] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0213] Comparing the absolute value of the adaptive coefficient with a preset coefficient threshold;

[0214] Indicators in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold are used as various data indicators.

[0215] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0216] Determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the determination result;

[0217] Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library;

[0218] Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario;

[0219] Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula;

[0220]

[0221] Among them, B j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators;

[0222] The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

[0223] Furthermore, when the driving behavior scoring program is executed by the processor, the following operations are also implemented:

[0224] The parameter scores of the corresponding parameters in the operation layer index score are multiplied by the corresponding weight coefficients, and the total sum after the multiplication is calculated, and the total sum is used as the comprehensive score of the driving behavior.

[0225] Those skilled in the art will appreciate that all or part of the steps in the above-mentioned implementation method can be accomplished by instructing related hardware through a program, and the program is stored in a storage medium, including a number of instructions for enabling a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each implementation method of the present application; and the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0226] 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.

[0227] 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.

[0228] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0229] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0230] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A driving behavior scoring method, characterized in that: The driving behavior scoring method comprises: Obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system; Evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score; The comprehensive score of the driving behavior is calculated according to the operation layer indicator score.

2. The driving behavior scoring method according to claim 1, characterized in that: The obtaining of the current Internet of Vehicles data and building of a preset driving behavior evaluation system includes: Acquire the Internet of Vehicles data of the current Internet of Vehicles, filter the Internet of Vehicles data, and obtain various data indicators; Generate an indicator layer according to the various data indicators, classify the data of each indicator layer according to the preset classification operation rules, and generate an operation layer; Taking driving behavior as the target layer, a preset driving behavior evaluation system is constructed according to the indicator layer, the operation layer and the target layer.

3. The driving behavior scoring method according to claim 2, characterized in that: The obtaining of the Internet of Vehicles data of the current Internet of Vehicles, screening the Internet of Vehicles data, and obtaining various data indicators include: Obtain the current Internet of Vehicles data and obtain the adaptive coefficient; The Internet of Vehicles data is screened according to the adaptive coefficient to obtain various data indicators.

4. The driving behavior scoring method according to claim 3, characterized in that: The obtaining of the current Internet of Vehicles data and the obtaining of the adaptive coefficient include: Get the current Internet of Vehicles data; The adaptive coefficient is calculated according to the following formula: Among them, ρ k is the adaptive coefficient, X i Y is the indicator of the third-level indicator layer calculated by the server. i is the vehicle economy index calculated by the server, N is the dimension of the data, k is the number of third-level indicators in the classification items belonging to the secondary operation layer, For X i The mean of Y i The mean of .

5. The driving behavior scoring method according to claim 3, characterized in that: The method of screening the Internet of Vehicles data according to the adaptive coefficient to obtain various data indicators includes: Comparing the absolute value of the adaptive coefficient with a preset coefficient threshold; Indicators in which the absolute value of the adaptive coefficient in the Internet of Vehicles data is greater than a preset coefficient threshold are used as various data indicators.

6. The driving behavior scoring method according to claim 1, characterized in that: The step of evaluating the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score includes: Determine whether the data distribution of the evaluation index data corresponding to the Internet of Vehicles data conforms to the normal distribution, and whether the range of the mean μ±3 times the standard deviation σ is within the preset data range, and select the corresponding target adaptive comment rule base according to the determination result; Obtaining the corresponding number of comments and the number of evaluation indicators from the target adaptive comment rule library; Acquire a current usage scenario of the current vehicle, and determine a weight coefficient matrix and a weight judgment matrix matching the target adaptive comment rule base according to the current usage scenario; Determine the operational level indicator evaluation matrix according to the number of comments, the number of evaluation indicators, the weight coefficient matrix and the weight judgment matrix through the following formula; Among them, N j is the operational level indicator evaluation matrix, A i is the weight coefficient matrix, R ij is the weight judgment matrix, m is the number of comments, and n is the number of evaluation indicators; The operation layer indicator score of each parameter in the Internet of Vehicles data is determined according to the operation layer indicator evaluation matrix.

7. The driving behavior scoring method according to claim 1, characterized in that: Calculating the comprehensive score of driving behavior according to the operation layer indicator score includes: The parameter scores of the corresponding parameters in the operation layer index score are multiplied by the corresponding weight coefficients, and the total sum after the multiplication is calculated, and the total sum is used as the comprehensive score of the driving behavior.

8. A driving behavior scoring device, characterized in that: The driving behavior scoring device comprises: The data acquisition module is used to obtain the current Internet of Vehicles data and build a preset driving behavior evaluation system; An evaluation module, used to evaluate the Internet of Vehicles data according to the preset driving behavior evaluation system to obtain an operation layer indicator score; The score calculation module is used to calculate the comprehensive score of the driving behavior according to the operation layer indicator score.

9. A driving behavior scoring device, characterized in that: The driving behavior scoring device comprises: a memory, a processor, and a driving behavior scoring program stored in the memory and executable on the processor, wherein the driving behavior scoring program is configured to implement the steps of the driving behavior scoring method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a driving behavior scoring program, which, when executed by a processor, implements the steps of the driving behavior scoring method according to any one of claims 1 to 7.

Images