Internet of vehicles series application method and system based on similar working conditions
By designing similarity features and using entropy weighting, the scientific and subjective issues of fuel consumption ranking and driving habit scoring are resolved, providing a more accurate and objective scoring method and enhancing the application of vehicle networking technology in vehicle management and intelligent transportation systems.
Patent Information
- Application Number
- CN202411199653.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the existing technology, fuel consumption ranking and driving habit scoring methods lack scientificity and rationality, cannot accurately reflect vehicle performance and driving behavior, and the scoring results are subjective and have limitations in application.
By designing similarity features, including single statistical indicators, statistical distributions, and multidimensional distributions, the similarity between vehicles is calculated. The entropy weight method is combined to calculate the weight of each indicator, and fuel consumption and driving habits are scored, providing a more scientific and objective scoring method.
It has achieved more accurate fuel consumption ranking and driving habit scoring, improved fuel economy and driving safety, and promoted the application of vehicle networking technology in vehicle management and intelligent transportation systems.
Smart Images

Figure CN119052747A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the technical field of vehicle networking data application, and in particular to a vehicle networking series application method and system based on similar working conditions. Background Art
[0002] Existing technologies mainly sort by direct fuel consumption results, and score by multiplying driving habit evaluation indicators by manually defined weights. However, fuel consumption is inseparable from the scene, and it is unreasonable and unscientific to directly evaluate fuel consumption. In addition, the scoring weights also change with the scene conditions, and it is unreasonable to specify weights. Summary of the invention
[0003] The embodiments of the present invention provide a vehicle networking series application method and system based on similar working conditions, which can provide users with more accurate and scientific fuel consumption rankings and driving habit scores, help users better understand their vehicle performance and driving habits, and thus improve driving efficiency and safety.
[0004] To achieve the above objectives, in a first aspect, the present invention provides a vehicle networking series application method based on similar working conditions, comprising:
[0005] Step S100, designing and determining similarity features, wherein the similarity features include single statistical indicators, statistical distribution, and multi-dimensional distribution;
[0006] Step S200, selecting data within a certain time range, using the similarity feature, calculating the similarity between the current vehicle and all vehicles, and obtaining a similarity result;
[0007] Step S300, ranking the fuel consumption per 100 kilometers based on the similarity results, and calculating the percentage of fuel consumption exceeding that of users with similar working conditions and the fuel consumption score;
[0008] Step S400, design driving habit scoring features, including multiple indicators related to fuel consumption and safety, normalize the features, use entropy weight method to calculate the weight of each indicator, and calculate the comprehensive score based on the weight and normalized characteristic value to obtain the fuel consumption related driving score and the safety related driving score.
[0009] In one embodiment of the present invention, step S100 includes:
[0010] Step S101, designing a single statistical index, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature;
[0011] Step S102, designing statistical distribution characteristics, including load distribution, slope distribution, environmental pressure distribution, and environmental temperature distribution;
[0012] Step S103, designing multi-dimensional distribution features, taking into account the joint distribution of multiple dimensions such as load, slope, and vehicle speed.
[0013] In one embodiment of the present invention, step S200 includes:
[0014] Step S201, selecting data within a certain time range;
[0015] Step S202, using the similarity feature, calculating the similarity between the current vehicle and all vehicles;
[0016] Step S203, based on the similarity calculation result, filter out a set of vehicles with similar operating conditions to the current vehicle to obtain a similarity result.
[0017] In one embodiment of the present invention, step S300 includes:
[0018] Step S301, based on the similarity result, obtaining the fuel consumption data of the vehicle per 100 kilometers;
[0019] Step S302, sorting based on the 100-kilometer fuel consumption data to obtain a fuel consumption sorting result;
[0020] Step S303, calculating the percentage of the fuel consumption of the vehicle exceeding that of users with similar working conditions;
[0021] Step S304, calculating the fuel consumption score of the vehicle according to the fuel consumption ranking result and the percentage.
[0022] In one embodiment of the present invention, step S400 includes:
[0023] Step S401, designing driving habit scoring features, including multiple first indicators related to fuel consumption and multiple second indicators related to safety, wherein the multiple first indicators include a sudden acceleration ratio, a sudden deceleration ratio, and a constant speed driving ratio, and the multiple second indicators include a speeding ratio and a sharp turn ratio;
[0024] Step S402, normalizing the plurality of first indicators and the plurality of second indicators;
[0025] Step S403, using an entropy weight method to calculate the weights of the plurality of first indicators and the plurality of second indicators;
[0026] Step S404, calculating a comprehensive score based on the weights and the normalized eigenvalues to obtain a fuel consumption-related driving score and a safety-related driving score.
[0027] In a second aspect, the present invention provides a vehicle networking series application system based on similar working conditions, the system comprising: a design determination module, a first calculation module, a second calculation module and a third calculation module. The design determination module is used to design and determine similarity features, and the similarity features include single statistical indicators, statistical distribution and multidimensional distribution. The first calculation module is used to select data within a certain time range, and use the similarity features to calculate the similarity between the vehicle and all vehicles, and obtain similarity results. The second calculation module is used to sort the fuel consumption per 100 kilometers based on the similarity results, and calculate the percentage of users with fuel consumption exceeding similar working conditions and the fuel consumption score. And the third calculation module is used to design driving habit scoring features, including multiple indicators related to fuel consumption and safety, normalize the features, use the entropy weight method to calculate the weight of each indicator, and calculate the comprehensive score based on the weight and the normalized feature value to obtain a fuel consumption-related driving score and a safety-related driving score.
[0028] In one embodiment of the present invention, the design determination module includes: a first design unit, a second design unit and a third design unit. The first design unit is used to design a single statistical indicator, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature. The second design unit is used to design statistical distribution characteristics, including load distribution, slope distribution, ambient pressure distribution and ambient temperature distribution. And the third design unit is used to design multi-dimensional distribution characteristics, considering the joint distribution of multiple dimensions such as load, slope, and vehicle speed.
[0029] In one embodiment of the present invention, the first calculation module includes: a selection unit, a first calculation unit and a screening unit. The selection unit is used to select data within a certain time range. The first calculation unit is used to calculate the similarity between the vehicle and all vehicles using the similarity feature. And the screening unit is used to screen out a set of vehicles with similar working conditions to the vehicle according to the similarity calculation result to obtain a similarity result.
[0030] In a third aspect, the present invention provides an electronic device, comprising:
[0031] at least one processor; and
[0032] a memory communicatively coupled to the at least one processor;
[0033] Among them, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle networking series application method based on similar working conditions as described above.
[0034] In a fourth aspect, the present invention provides a computer-readable storage medium, including a computer program and instructions. When the computer program or the instructions are run on a computer, the computer executes the vehicle networking series application method based on similar working conditions as described above.
[0035] Compared with the prior art, the vehicle networking series application method and system based on similar working conditions according to the present invention have the following beneficial effects:
[0036] 1. By considering the vehicle data under similar working conditions, the present invention can provide a more accurate fuel consumption ranking, avoiding the irrationality of directly comparing the fuel consumption of vehicles under different working conditions; the design of the similarity feature covers a variety of working condition parameters, making the fuel consumption comparison more comprehensive and scientific;
[0037] 2. The introduction of the concept of similar working conditions makes the driving habit scoring more consistent with the actual driving environment, improving the rationality and accuracy of the scoring; the use of the entropy weight method to calculate the weights of each indicator avoids the subjectivity and irrationality of artificially specified weights, making the scoring more objective;
[0038] 3. Accurate fuel consumption ranking and driving habit scores help users better understand their vehicle performance and driving habits, thereby guiding users to improve their driving methods, improve fuel economy and driving safety; users can adjust their driving behavior based on fuel consumption and driving habit scores to achieve energy conservation and emission reduction and reduce vehicle operating costs;
[0039] 4. The present invention provides new ideas and methods for the application of Internet of Vehicles data, and promotes the application of Internet of Vehicles technology in vehicle management and driving behavior analysis; the concept of similar working conditions can be extended to other Internet of Vehicles application fields, such as vehicle maintenance, fault diagnosis, etc., to further enhance the practical value of Internet of Vehicles technology.
[0040] 5. By providing more refined vehicle data analysis and application, the present invention contributes to the development of intelligent transportation systems and provides data support for urban transportation planning and management; accurate vehicle fuel consumption and driving habit data can provide a scientific basis for policymakers. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 It is a flow chart of a vehicle networking series application method based on similar working conditions in the first embodiment of the present invention;
[0042] Figure 2 It is a structural schematic diagram of a vehicle networking series application system based on similar working conditions in the second embodiment of the present invention;
[0043] Figure 3 It is a structural schematic diagram of an electronic device in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0044] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than to limit the embodiments of the present invention. It is also necessary to explain that, for ease of description, only parts related to the embodiments of the present invention are shown in the accompanying drawings, rather than all structures.
[0045] To facilitate understanding, the main implementation concepts of the embodiments of the present invention are first briefly described.
[0046] In the field of Internet of Vehicles data application, traditional fuel consumption ranking and driving habit scoring methods mainly rely on directly sorting fuel consumption results and scoring by multiplying preset driving habit evaluation indicators by manually defined weights. However, this method has several significant flaws:
[0047] 1. Fuel consumption is affected by many operating conditions, such as load, slope, speed, etc. Directly comparing the fuel consumption results under different operating conditions cannot accurately reflect the performance of the vehicle under different conditions. Existing technologies often ignore this point, resulting in a lack of scientificity and rationality in fuel consumption rankings.
[0048] 2. The weights of driving habit scores are usually set manually. This subjectivity means that the score results may not truly reflect the quality of driving behavior. Under different working conditions, the weights of each scoring indicator may change, and existing technologies often cannot flexibly adjust these weights.
[0049] 3. Traditional methods only use simple fuel consumption data and preset indicators for scoring, and fail to fully utilize the rich real-time data and multi-dimensional working condition information in the Internet of Vehicles. This limits the application potential of Internet of Vehicles data in vehicle performance evaluation, driving behavior analysis, etc.
[0050] In summary, the prior art has the following major defects:
[0051] 1. Lack of scientificity: Directly comparing the fuel consumption results under different working conditions cannot accurately reflect the vehicle performance.
[0052] 2. High subjectivity: Artificially set scoring weights may cause the scoring results to deviate from reality.
[0053] 3. Application limitations: Failure to fully utilize the advantages of Internet of Vehicles data has limited the application of data in vehicle management and driving behavior analysis.
[0054] The inventor discovered the technical defects of the prior art and proposed a series of vehicle networking application methods based on similar working conditions, which effectively solved the above problems. Specifically:
[0055] 1. A variety of similarity features are designed, including single statistical indicators, statistical distribution, multidimensional distribution, etc., to comprehensively describe the working conditions of vehicles. By calculating similarity, vehicles are divided into different sets of similar working conditions, making the fuel consumption ranking and driving habit scoring more scientific and reasonable.
[0056] 2. The introduction of scientific similarity calculation methods such as the Pearson correlation coefficient improves the accuracy of similarity calculation. The entropy weight method is used to calculate the weight of each scoring indicator, avoiding the subjectivity of artificially setting weights and making the scoring results more objective.
[0057] 3. Through a series of Internet of Vehicles application methods and systems based on similar working conditions, new ideas and methods are provided for Internet of Vehicles data applications, which promotes the application and development of Internet of Vehicles technology in the fields of vehicle performance evaluation, driving behavior analysis, and intelligent transportation systems.
[0058] Embodiment 1
[0059] Figure 1 is a flow chart of a vehicle networking series application method based on similar working conditions in the first embodiment of the present invention, such as Figure 2 As shown, embodiment 1 provides a vehicle networking series application method based on similar working conditions, including:
[0060] Step S100, designing and determining similarity features, wherein the similarity features include single statistical indicators, statistical distribution, and multi-dimensional distribution;
[0061] Specifically, step S100 is one of the key steps in the embodiment of the present invention, which involves designing and determining features for evaluating vehicle similarity. These features are subdivided into three categories: single statistical indicators, statistical distribution, and multidimensional distribution. Single statistical indicators include but are not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure, and average ambient temperature, which can directly reflect the basic operating conditions of vehicle operation. Statistical distribution features include load distribution, slope distribution, ambient pressure distribution, and ambient temperature distribution, which provide the distribution of operating parameters and help to understand the operating environment of the vehicle more comprehensively. Multidimensional distribution features further consider the joint distribution of multiple dimensions such as load, slope, and speed to capture more complex operating condition changes. Through the design of these similarity features, the present invention can more accurately evaluate the similarity between vehicles, thereby providing a scientific basis for subsequent fuel consumption rankings and driving habit scores. Among them, the method of the present invention can be applied to a controller or a server, for example, and the controller is connected to the Internet of Vehicles Big Data System for communication, or the server is built with an Internet of Vehicles Big Data System.
[0062] Step S200, selecting data within a certain time range, using the similarity feature, calculating the similarity between the current vehicle and all vehicles, and obtaining a similarity result;
[0063] Specifically, step S200 is one of the core links in the embodiment of the present invention, which involves selecting data within a certain time range, and using the designed similarity features to calculate the similarity between the vehicle and all vehicles, and finally obtain the similarity result. The specific execution process of this step is as follows: First, it is necessary to determine a suitable time range, which should be long enough to contain enough vehicle operation data, but not too long to avoid introducing too much invalid or outdated data. After the time range is selected, the relevant data of all vehicles can be extracted from this time range. Then, the similarity features designed and determined in step S100, including single statistical indicators, statistical distribution, and multidimensional distribution, are used to calculate the similarity between the vehicle and all vehicles. This calculation process may involve complex mathematical models and algorithms, but the core idea is to compare the similarity between the two vehicles in the similarity features. Finally, according to the similarity calculation results, a set of vehicles with similar working conditions to the vehicle is screened out. This screening process may involve setting a similarity threshold, and only vehicles with similarity exceeding this threshold will be considered similar and included in the similarity results.
[0064] Based on the above analysis, it can be seen that by executing step S200, a set of vehicles with similar operating conditions to the current vehicle can be obtained, and this set will be used for subsequent steps such as 100km fuel consumption ranking and fuel consumption score calculation. The execution of this step is of great significance for improving the accuracy and scientificity of fuel consumption ranking and driving habit scoring.
[0065] Step S300, ranking the fuel consumption per 100 kilometers based on the similarity results, and calculating the percentage of fuel consumption exceeding that of users with similar working conditions and the fuel consumption score;
[0066] Specifically, step S300 is a key step in the embodiment of the present invention, which sorts the fuel consumption per 100 kilometers of the vehicle based on the similarity result, and calculates the percentage of fuel consumption exceeding the users of similar working conditions and the fuel consumption score. The specific implementation method of this step is as follows: First, according to the similarity result obtained in step S200, a set of vehicles with similar working conditions to the vehicle is selected. The vehicles in this set are operated under working conditions similar to the vehicle, so their fuel consumption data can be used for comparison with the vehicle. Next, the fuel consumption per 100 kilometers data of each vehicle in this vehicle set is obtained. Fuel consumption per 100 kilometers is a commonly used indicator to measure the fuel economy of a vehicle, which indicates the amount of fuel consumed by the vehicle for 100 kilometers. Then, based on the obtained fuel consumption per 100 kilometers data, the vehicles are sorted. The basis for sorting is the fuel consumption, and the vehicles with lower fuel consumption are ranked in front, and the vehicles with higher fuel consumption are ranked in the back. In this way, a fuel consumption sorting result based on similar working conditions can be obtained. After obtaining the fuel consumption sorting result, the percentage of the fuel consumption of the vehicle exceeding the users of similar working conditions is calculated. This percentage indicates that under similar working conditions, the fuel consumption of this vehicle is lower than that of a certain proportion of users. This indicator can reflect the fuel economy level of this vehicle under similar working conditions. Finally, the fuel consumption score of this vehicle is calculated based on the fuel consumption ranking results and the percentage of users whose fuel consumption exceeds that of similar working conditions. The fuel consumption score is a comprehensive indicator that takes into account the fuel consumption level of the vehicle under similar working conditions and the proportion of users who exceed that of other users. The higher the fuel consumption score, the better the fuel economy of the vehicle under similar working conditions.
[0067] Based on the above analysis, it can be seen that step S300 provides a more accurate and scientific fuel consumption evaluation for the vehicle by ranking and scoring the fuel consumption based on the similarity results. This method avoids the irrationality of directly comparing the fuel consumption of vehicles under different working conditions, making the fuel consumption evaluation more in line with the actual driving environment.
[0068] Step S400, designing driving habit scoring features, including multiple fuel consumption related and safety related indicators, normalizing the features, calculating the weight of each indicator using the entropy weight method, and calculating the comprehensive score based on the weight and the normalized characteristic value to obtain a fuel consumption related driving score and a safety related driving score;
[0069] Specifically, step S400 is one of the key steps in the embodiment of the present invention, which mainly involves the design and processing of driving habit scoring features. Specifically, this step first designs a set of comprehensive driving habit scoring features, which include multiple first indicators related to fuel consumption, such as rapid acceleration ratio, rapid deceleration ratio, uniform speed driving ratio, etc., and also cover multiple second indicators related to safety, such as speeding ratio, sharp turn ratio, etc. The selection of these indicators is intended to fully reflect the driver's driving habits, focusing on both their impact on fuel consumption and their impact on driving safety. Next, step S400 normalizes these features to ensure comparability between different indicators and eliminate the influence of dimensions. After normalization, the entropy weight method, an objective weighting method, is used to calculate the weights of each indicator. The entropy weight method can determine the weights according to the degree of variation of each indicator value, thereby avoiding the subjectivity and irrationality of artificially specified weights, making the scoring more objective and scientific. Finally, step S400 calculates the comprehensive score by weighted summation based on the calculated weights and the normalized feature values, and then obtains the fuel consumption-related driving score and the safety-related driving score. These two scores can respectively reflect the driver's performance in fuel consumption and driving safety, providing the driver with more comprehensive and detailed feedback on driving habits.
[0070] In this embodiment, the step S100 includes:
[0071] Step S101, designing a single statistical index, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature;
[0072] Specifically, step S101 is to design a single statistical index, which is used to describe the working condition of the vehicle, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature. These indicators are selected based on their important impact on vehicle fuel consumption and driving behavior.
[0073] Step S102, designing statistical distribution characteristics, including load distribution, slope distribution, environmental pressure distribution, and environmental temperature distribution;
[0074] Specifically, step S102 involves designing statistical distribution features, which are used to describe the state distribution of the vehicle under different working conditions, so as to more comprehensively evaluate the similarity of the vehicle. Specifically, step S102 includes the following sub-steps: Determine the type of statistical distribution features: In this step, it is necessary to determine which types of statistical distribution features are important for describing the working conditions of the vehicle. For example, load distribution, slope distribution, ambient pressure distribution, and ambient temperature distribution. Collect relevant data: In order to construct these statistical distribution features, it is necessary to collect relevant data of the vehicle under different working conditions. This may include the vehicle's load record, slope information of the driving route, ambient pressure and temperature data, etc. Construct statistical distribution: Use the collected data to construct each statistical distribution feature. This may involve grouping the data, calculating the frequency or probability of each group, and drawing a distribution curve or histogram. Feature standardization: Since different statistical distribution features may have different dimensions and distribution ranges, they need to be standardized so that they can be fairly compared in subsequent similarity calculations. Feature selection: After constructing multiple statistical distribution features, feature selection may be required to remove features that are not important for evaluating vehicle similarity, thereby reducing computational complexity and improving the generalization ability of the model. By executing step S102, the invention can more comprehensively describe the working conditions of the vehicle and provide rich feature information for subsequent similarity calculations and fuel consumption rankings. This helps to improve the accuracy and scientificity of fuel consumption rankings, as well as the rationality and objectivity of driving habit scoring.
[0075] Step S103, designing multi-dimensional distribution features, considering the joint distribution of multiple dimensions such as load, slope, and vehicle speed;
[0076] Specifically, step S103 is the process of designing a multidimensional distribution feature, which considers the joint distribution of multiple dimensions such as load, slope, and speed. In actual operation, the design of the multidimensional distribution feature is to more comprehensively describe the working conditions of the vehicle so that the similarity between vehicles can be more accurately calculated in subsequent steps. Specifically, the multidimensional distribution feature may include but is not limited to the joint distribution of the following aspects: Joint distribution of load and slope: This feature describes the slope distribution of the vehicle under different load conditions, which helps to understand the driving conditions of the vehicle under different loads. Joint distribution of load and speed: Through this feature, the speed distribution of the vehicle under different loads can be understood, and then the driving performance of the vehicle under different loads can be analyzed. Joint distribution of slope and speed: This feature reflects the speed distribution of the vehicle on different slopes, which helps to evaluate the driving performance of the vehicle under different road conditions. Joint distribution of environmental factors and driving conditions: The joint distribution of environmental factors (such as ambient temperature, ambient pressure, etc.) and driving conditions (such as load, slope, speed, etc.) can also be considered to more comprehensively describe the vehicle working conditions. When designing multi-dimensional distribution features, it is necessary to use the rich real-time data in the Internet of Vehicles and extract these multi-dimensional joint distribution features through data analysis and mining technology. These features will provide stronger support for similarity calculation and fuel consumption ranking in subsequent steps, making the final fuel consumption ranking and driving habit score more scientific and accurate.
[0077] In this embodiment, step S200 includes:
[0078] Step S201, selecting data within a certain time range;
[0079] Specifically, this step is a key link in the vehicle networking series application method, which involves the screening and determination of data. Specifically, the purpose of step S201 is to select data within a specific time period from a large amount of vehicle networking data for subsequent analysis and processing. The determination of the time range is based on actual application needs. For example, data of one day, one week, one month or one year can be selected, depending on the time scale that the user wants to analyze. The selection of the time range should take into account the integrity and representativeness of the data. It should be ensured that the data within the selected time period can fully reflect the actual operating conditions of the vehicle. After determining the time range, all relevant data within the time period needs to be extracted from the vehicle networking database. The data screening process should ensure the accuracy and consistency of the data and exclude any abnormal or erroneous data points. Before performing similarity calculation, the data can be preprocessed, such as cleaning, denoising, normalization, etc. The purpose of preprocessing is to improve the availability and quality of the data and ensure the accuracy of the similarity calculation. Through step S201, a vehicle networking data set that has been screened and preprocessed within a specific time period can be obtained, which provides a basis for the subsequent calculation of the similarity between the vehicle and all vehicles (step S202). This step is critical to ensuring the accuracy and effectiveness of the entire range of connected vehicle application methods.
[0080] Step S202, using the similarity feature, calculating the similarity between the current vehicle and all vehicles;
[0081] Specifically, this step is one of the key steps in the invention, and its detailed implementation process is as follows: Ensure that data within a certain time range has been selected, and these data contain the working condition information of all vehicles. Prepare the similarity features designed and determined in step S100, including single statistical indicators, statistical distribution, and multidimensional distribution. For this vehicle, calculate its similarity with each vehicle in the data set. The calculation of similarity can be based on a variety of methods, such as Pearson correlation coefficient, Euclidean distance, cosine similarity, etc. The specific method to be selected depends on the nature and distribution of the similarity feature. When calculating the similarity, it is necessary to comprehensively consider the characteristics of multiple aspects such as single statistical indicators, statistical distribution, and multidimensional distribution. The calculated similarity results between each pair of this vehicle and other vehicles are stored for subsequent analysis and processing. Through step S202, the similarity results between this vehicle and all other vehicles in the data set can be obtained, and these results will be used for subsequent steps such as screening of similar working condition vehicles and fuel consumption ranking. The implementation of this step provides a scientific and reasonable method for the invention to compare vehicle performance under different working conditions, thereby avoiding the irrationality of directly comparing vehicle fuel consumption under different working conditions.
[0082] For example, there is a vehicle networking system that contains data on 100 vehicles, each of which has a series of operating parameters, such as load, slope, speed, etc. The goal is to calculate the similarity between one of the vehicles (called "this vehicle") and the remaining 99 vehicles. According to step S100, a variety of similarity features have been determined, including single statistical indicators (such as average load, average uphill slope, etc.), statistical distribution features (such as load distribution, slope distribution, etc.) and multidimensional distribution features (considering the joint distribution of multiple dimensions such as load, slope, speed, etc.). In step S201, data within a certain time range is selected, such as data within the past month, to ensure that the comparison is recent and relatively stable operating conditions. In step S202, the selected similarity features are used to calculate the similarity between this vehicle and the remaining 99 vehicles. This can be achieved through various similarity calculation methods, such as Pearson correlation coefficient, Euclidean distance, cosine similarity, etc. For example, the similarity between this vehicle and another vehicle in a single statistical indicator such as average load, average uphill slope, etc. can be calculated, and then their similarity in statistical distribution characteristics such as load distribution and slope distribution can be calculated. Finally, the similarity of multidimensional distribution characteristics can also be considered. The calculation results of each similarity feature are combined to obtain an overall similarity score. This score can be used to measure the similarity between the working conditions of the two vehicles. The above similarity calculation is performed on this vehicle and the remaining 99 vehicles, and 99 similarity scores are finally obtained. In step S203, a set of vehicles with similar working conditions to this vehicle can be screened out according to the similarity scores. For example, the top 10 vehicles with the highest similarity scores can be selected as a set of similar vehicles.
[0083] Step S203, based on the similarity calculation result, filter out a set of vehicles with similar working conditions to the current vehicle to obtain a similarity result;
[0084] Specifically, step S203 divides the vehicles into different sets of similar working conditions based on the previously calculated similarities. The purpose of this is to make the subsequent fuel consumption ranking and driving habit scoring more scientific and reasonable, because they are compared between vehicles with similar working conditions. With this set of vehicles with similar working conditions, more accurate fuel consumption ranking and driving habit scoring can be performed. For example, the fuel consumption ranking of this vehicle among these 100 vehicles with similar working conditions can be compared, and the percentage of fuel consumption exceeding that of users with similar working conditions can be calculated.
[0085] In this embodiment, step S300 includes:
[0086] Step S301, based on the similarity result, obtaining the fuel consumption data of the vehicle per 100 kilometers;
[0087] Specifically, step S301 connects the two links of similarity calculation and fuel consumption analysis. The following is a detailed description of this step: Similarity result: The output of step S200 includes the similarity calculation results between this vehicle and all other vehicles. Vehicle fuel consumption data: The fuel consumption data of all vehicles per 100 kilometers stored in the Internet of Vehicles database. According to the similarity results, determine the set of vehicles with similar working conditions to this vehicle. From the vehicle fuel consumption data, extract the fuel consumption data of these similar vehicles per 100 kilometers. The fuel consumption data set of similar vehicles per 100 kilometers is used for subsequent fuel consumption sorting and scoring calculation. This step realizes the screening of vehicle fuel consumption data based on similar working conditions, laying the foundation for providing scientific fuel consumption ranking and fuel consumption scoring in the future. By comparing only the fuel consumption of vehicles under similar working conditions, the irrationality of directly comparing the fuel consumption of vehicles under different working conditions is avoided, making the fuel consumption comparison more comprehensive and scientific. In summary, step S301 is the key link connecting similarity calculation and fuel consumption analysis, which ensures the scientificity and accuracy of subsequent fuel consumption ranking and scoring.
[0088] Step S302, sorting based on the 100-kilometer fuel consumption data to obtain a fuel consumption sorting result;
[0089] Specifically, in step S302, the system will sort the fuel consumption data per 100 kilometers in the set of vehicles that have been screened out based on the similarity results and have similar working conditions to the current vehicle. The purpose of sorting is to obtain a ranking result of fuel consumption from low to high, so that it can be clearly understood how the fuel consumption performance of each vehicle is under similar working conditions, which vehicles have lower fuel consumption, and which vehicles have higher fuel consumption. The fuel consumption data of this vehicle will also occupy a position in this ranking result. By comparing it with other vehicles under similar working conditions, it can be evaluated where the fuel consumption level of this vehicle is, whether it is relatively fuel-saving or fuel-consuming. This fuel consumption ranking result is the basis for the subsequent calculation of the fuel consumption score and the percentage of users whose fuel consumption exceeds that of similar working conditions.
[0090] Step S303, calculating the percentage of the fuel consumption of the vehicle exceeding that of users with similar working conditions;
[0091] Specifically, step S303 involves evaluating the fuel consumption performance of the vehicle after determining the set of users with similar working conditions. Specifically, the purpose of this step is to calculate the proportion of users whose fuel consumption performance exceeds that of the vehicle under similar working conditions. In detail, this step includes the following sub-steps: First, it is necessary to obtain the 100-kilometer fuel consumption data of all users who are determined to have similar working conditions to the vehicle in step S200. Then, for each user with similar working conditions, calculate the difference between their 100-kilometer fuel consumption and the 100-kilometer fuel consumption of the vehicle. This step is to determine whether the fuel consumption of the vehicle is high or low relative to that of other users. Then, count the number of users with similar working conditions whose 100-kilometer fuel consumption is higher than that of the vehicle, and calculate the proportion of this number to the total number of users with similar working conditions. This proportion represents the percentage of the vehicle whose fuel consumption exceeds that of users with similar working conditions. Finally, output this percentage as a quantitative indicator of the fuel consumption performance of the vehicle under similar working conditions. Through this step, users can get an intuitive quantitative indicator to understand how their vehicle's fuel consumption performance under similar operating conditions compares to that of other users, which helps users better evaluate their driving habits and vehicle performance and make improvements accordingly.
[0092] Step S304, calculating the fuel consumption score of the vehicle according to the fuel consumption ranking result and the percentage;
[0093] Specifically, in this step, the system will calculate the fuel consumption score of this vehicle based on the fuel consumption ranking results obtained in the previous step and the percentage of this vehicle's fuel consumption exceeding that of users with similar working conditions. This score is intended to more scientifically reflect the fuel consumption level of this vehicle in its similar working condition user group. Specifically, the fuel consumption ranking results show the ranking of all similar working condition vehicles from low to high in terms of fuel consumption per 100 kilometers, and the percentage indicates how many percentage of similar working condition users this vehicle's fuel consumption exceeds. When calculating the fuel consumption score, a method that comprehensively considers the ranking position and the percentage of surpassing can be used. For example, if the fuel consumption ranking of this vehicle is very high (i.e., the fuel consumption is low), and the percentage of similar working condition users surpassed is also high, then the fuel consumption score of this vehicle will be correspondingly high, otherwise it will be low. In this way, the fuel consumption score not only takes into account the absolute fuel consumption level of this vehicle, but also its relative position in the similar working condition user group, thereby providing a more comprehensive and scientific fuel consumption evaluation.
[0094] In this embodiment, step S400 includes:
[0095] Step S401, designing driving habit scoring features, including multiple first indicators related to fuel consumption and multiple second indicators related to safety, wherein the multiple first indicators include a sudden acceleration ratio, a sudden deceleration ratio, and a constant speed driving ratio, and the multiple second indicators include a speeding ratio and a sharp turn ratio;
[0096] Specifically, this step aims to build a comprehensive evaluation system for quantifying the quality of driving habits. Specifically, step S401 includes designing multiple first indicators related to fuel consumption and multiple second indicators related to safety. Multiple first indicators related to fuel consumption: These indicators mainly focus on the impact of driving behavior on fuel consumption. For example, the rapid acceleration ratio reflects the frequency of the driver's behavior of rapidly increasing the speed of the vehicle in a short period of time, which usually leads to an increase in fuel consumption. The rapid deceleration ratio reflects the frequency of the driver's behavior of rapidly reducing the speed of the vehicle in a short period of time, which also increases fuel consumption. The uniform speed driving ratio is a positive indicator, which reflects the proportion of drivers who maintain a stable speed. This driving style is usually conducive to reducing fuel consumption. Multiple second indicators related to safety: These indicators mainly focus on the impact of driving behavior on safety. For example, the speeding ratio reflects the frequency of the driver's behavior of driving at a speed exceeding the legal speed, which increases the risk of traffic accidents. The sharp turn ratio reflects the frequency of the driver's behavior of rapidly changing the driving direction in a short period of time, which also increases the risk of traffic accidents. By designing these specific indicators, step S401 provides a basis for the subsequent driving habit scoring. These indicators can comprehensively reflect the performance of driving habits in terms of fuel consumption and safety, making the scoring more scientific and comprehensive.
[0097] Step S402, normalizing the plurality of first indicators and the plurality of second indicators;
[0098] Specifically, step S402 is the process of normalizing the driving habit scoring feature. Normalization is a data preprocessing technology, the purpose of which is to convert data of different dimensions or magnitudes to the same dimension or magnitude for fair comparison and calculation. In the present invention, the driving habit scoring feature includes multiple first indicators related to fuel consumption (such as rapid acceleration ratio, rapid deceleration ratio, and uniform speed driving ratio) and multiple second indicators related to safety (such as speeding ratio and sharp turn ratio). These indicators may have different dimensions and magnitudes, and direct calculation may lead to inaccurate or biased results. Therefore, step S402 requires normalization of these indicators and converting them to the same numerical range (usually between 0 and 1). The specific method of normalization may include linear normalization, Z-score normalization, etc., and the specific method selected depends on the distribution and characteristics of the data. Through normalization, it can be ensured that different indicators have the same weight and influence when calculating the comprehensive score, thereby improving the accuracy and fairness of the scoring results.
[0099] Step S403, using an entropy weight method to calculate the weights of the plurality of first indicators and the plurality of second indicators;
[0100] Specifically, step S403 is "using the entropy weight method to calculate the weights of the multiple first indicators and the multiple second indicators". The purpose of this step is to objectively determine the weights of each driving habit scoring indicator to avoid the subjectivity of artificially setting weights. The entropy weight method is an objective weighting method based on information entropy theory. It measures the degree of variation of the indicator by calculating the information entropy value of each indicator, thereby determining the weight of the indicator.
[0101] Specifically, in information theory, entropy is a measure of the disorder of a system. The larger the information entropy, the more disordered the system is, that is, the greater the variation of the index value, the greater the role of the index in the comprehensive evaluation, and the greater its weight should be. On the contrary, the smaller the information entropy, the more ordered the system is, that is, the smaller the variation of the index value, the smaller the role of the index in the comprehensive evaluation, and the smaller its weight should be. Therefore, in step S403, it is first necessary to normalize each driving habit scoring index to eliminate the influence of different index dimensions and orders of magnitude. Then, the information entropy value and weight of each index are calculated using the entropy weight method. The specific calculation process includes: calculating the proportion of each index value, calculating the information entropy value of each index, calculating the difference coefficient of each index, and finally calculating the weight of each index according to the difference coefficient. Through step S403, the objective weights of multiple driving habit scoring indicators related to fuel consumption and safety can be obtained, providing a basis for the subsequent calculation of the comprehensive score.
[0102] Step S404, calculating a comprehensive score based on the weights and the normalized eigenvalues to obtain a fuel consumption-related driving score and a safety-related driving score;
[0103] Specifically, this step is performed after the driving habit scoring features (including multiple fuel consumption-related and safety-related indicators) have been determined, these features have been normalized, and the weights of each indicator have been calculated using the entropy weight method. Specifically, step S404 includes the following sub-steps: Obtaining normalized feature values: These feature values are obtained by normalizing the original driving habit scoring features in step S402, with the purpose of eliminating the dimensional differences between different features so that they can be compared and calculated on the same scale. Obtaining the weights of each indicator: These weights are calculated using the entropy weight method in step S403, reflecting the importance of each indicator in the driving habit scoring. The entropy weight method is an objective weighting method that determines the weight according to the degree of variation of the indicator value, avoiding the subjectivity and arbitrariness of artificial weighting. Calculating the comprehensive score: For the fuel consumption-related driving score and the safety-related driving score, the corresponding normalized feature values are multiplied by the weights, and the results are added to obtain a comprehensive score. This comprehensive score reflects the overall performance of the vehicle in terms of fuel consumption-related driving habits or safety-related driving habits. Obtain fuel consumption-related driving scores and safety-related driving scores: Based on the calculated comprehensive scores, fuel consumption-related driving scores and safety-related driving scores can be obtained respectively. These two scores can provide users with more comprehensive and detailed feedback on their driving habits, help users better understand their driving behavior, and guide users to make improvements.
[0104] In practical applications, the vehicle networking series application method based on similar working conditions of the present invention first performs:
[0105] Step 1, similarity feature design, including:
[0106] 11. Single statistical indicator
[0107] Average load: the mean of the load;
[0108] Average uphill slope: the average slope is greater than 0.1%;
[0109] Average downhill slope: The average slope is less than 0.1%;
[0110] Uphill ratio: time with a slope greater than 0.1% / total driving time;
[0111] Downhill ratio: time with a slope less than 0.1% / total driving time;
[0112] Average ambient pressure: the average value of ambient pressure (if not available, use average altitude: the average value of altitude);
[0113] Average ambient temperature: the average value of ambient temperature;
[0114] The above indicators are arranged into a one-dimensional matrix as the feature for calculating similarity.
[0115] 12. Statistical distribution
[0116] Load distribution: the proportion of time that the load is within a specified load range;
[0117] Slope distribution: the proportion of time in a specified slope interval of the slope;
[0118] Ambient pressure distribution: the proportion of time that the ambient pressure is within a specified ambient pressure range;
[0119] Ambient temperature distribution: the proportion of time that the ambient temperature is within a specified ambient temperature range;
[0120] Arrange them in order to form a 1D matrix as the feature for calculating similarity.
[0121] 13. Multidimensional Distribution
[0122] The three-dimensional matrix of the combined time proportion of load-slope-vehicle speed in the specified interval of each engine number is reshaped into a one-dimensional matrix.
[0123] Step 2: Select data within a certain time range, calculate the similarity between this car and all cars, and take a certain percentile or a certain number of similar engine numbers for application
[0124] The similarity calculation formula is as follows, where x is the feature of the current car and y is the feature of the other car when calculating similarity between two cars:
[0125]
[0126] Step 3: Sort the fuel consumption per 100 kilometers of similar engines in step 2, and calculate the percentage of each engine number whose fuel consumption exceeds that of users with similar working conditions:
[0127] The percentage of users with fuel consumption exceeding similar working conditions = (total ranking - ranking) / total ranking * 100%
[0128] Fuel consumption score = 100 (total number of similar engines - 1) * (total number of similar engines - fuel consumption ranking).
[0129] Step 4: The driving habit index of similar engines in step 2 is scored using the entropy weight method:
[0130] 41. Calculate driving habit scoring features
[0131] Fuel consumption related driving score:
[0132] Throttle mean (negative indicator): the mean of the throttle opening;
[0133] Braking mileage ratio (negative indicator): braking mileage / total mileage*100;
[0134] Economic operation range ratio (positive indicator): time within the speed range corresponding to a 3% deterioration in the engine's minimum fuel consumption / total driving time*100;
[0135] Idle ratio (negative indicator): parking idling time / total driving time*100;
[0136] Average speed (negative indicator): the average of vehicle speed;
[0137] Speed standard deviation (negative indicator): standard deviation of vehicle speed;
[0138] Rapid acceleration frequency (negative indicator): the number of times the acceleration is greater than the specified value / mileage*100;
[0139] Emergency braking frequency (negative indicator): number of times the acceleration is less than the specified value / mileage*100;
[0140] Safety-Related Driving Score:
[0141] Sharp turn frequency (negative indicator): (number of times when the curvature is greater than a certain value and the vehicle speed is greater than a certain value) / mileage*100;
[0142] Speeding mileage ratio (negative indicator): the mileage where the current vehicle speed is greater than the speed limit of the road at the current latitude and longitude / total mileage*100;
[0143] Night driving time ratio (negative indicator): driving time between (18:00-06:00) / total driving time;
[0144] Frequency of exceeding the maximum engine speed (negative indicator): the number of times the engine speed exceeds the maximum idle speed / mileage*100;
[0145] Fatigue driving ratio (negative indicator): time between 4 hours of continuous driving and 20 minutes of parking / total driving time*100;
[0146] Severe weather ratio (negative indicator): Check the current weather through the current latitude and longitude and the current timestamp. The time of rain and fog / total driving time*100.
[0147] 42. Normalized driving habit characteristics
[0148] Positive indicator normalization formula
[0149] X'=(X-Xmin) / (Xmax-Xmin)
[0150] Negative indicator normalization formula
[0151] X'=(Xmax-X) / (Xmax–Xmin)
[0152] Each indicator corresponds to the positive and negative descriptions and is normalized to obtain the X matrix.
[0153] 43. Get Rating
[0154] Import the characteristic values of all vehicles with similar working conditions into the entropy weight method and calculate the score
[0155] The formula is as follows:
[0156] Calculate the variability index and calculate the proportion of the index value of the i-th scheme under the j-th index:
[0157]
[0158] Calculate the information entropy and calculate the information entropy value of the jth live broadcast:
[0159]
[0160] Among them, k=1 / ln(n), satisfying e>0.
[0161] Calculate the information entropy redundancy and calculate the information entropy redundancy of the j-th indicator:
[0162] g j =1-e
[0163] Calculate the weight of each indicator and the weight of the jth indicator:
[0164]
[0165] Calculate the comprehensive score and calculate the comprehensive score of the i-th evaluation object:
[0166]
[0167] Where x = similar vehicles are rows, feature items are columns normalized, n is the number of similar engines, and m is the number of scoring indicators;
[0168] Finally, we get the fuel consumption-related driving score and the safety-related driving score.
[0169] Embodiment 2
[0170] Figure 2 is a structural diagram of a vehicle networking series application system based on similar working conditions in the second embodiment of the present invention, such as Figure 2As shown, the second embodiment provides a vehicle networking series application system based on similar working conditions, and the system includes: a design determination module 201, a first calculation module 202, a second calculation module 203 and a third calculation module 204. The design determination module 201 is used to design and determine similarity features, and the similarity features include single statistical indicators, statistical distribution and multidimensional distribution. The first calculation module 202 is used to select data within a certain time range, and use the similarity features to calculate the similarity between the current vehicle and all vehicles, and obtain similarity results. The second calculation module 203 is used to sort the fuel consumption per 100 kilometers based on the similarity results, and calculate the percentage of users with fuel consumption exceeding similar working conditions and the fuel consumption score. And the third calculation module 204 is used to design driving habit scoring features, including multiple indicators related to fuel consumption and safety, normalize the features, use the entropy weight method to calculate the weight of each indicator, and calculate the comprehensive score based on the weight and the normalized feature value to obtain the fuel consumption related driving score and the safety related driving score.
[0171] In this embodiment, the design determination module 201 includes: a first design unit, a second design unit and a third design unit. The first design unit is used to design a single statistical indicator, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature. The second design unit is used to design statistical distribution characteristics, including load distribution, slope distribution, ambient pressure distribution and ambient temperature distribution. And the third design unit is used to design multi-dimensional distribution characteristics, considering the joint distribution of multiple dimensions such as load, slope, and vehicle speed.
[0172] In this embodiment, the first calculation module 202 includes: a selection unit, a first calculation unit, and a screening unit. The selection unit is used to select data within a certain time range. The first calculation unit is used to calculate the similarity between the vehicle and all vehicles using the similarity feature. And the screening unit is used to screen out a set of vehicles with similar working conditions to the vehicle according to the similarity calculation result to obtain a similarity result.
[0173] In this embodiment, the second calculation module 203 includes: an acquisition unit, a obtaining unit, a second calculation unit, and a third calculation unit. The acquisition unit is used to obtain the vehicle's 100-kilometer fuel consumption data based on the similarity result. The obtaining unit is used to sort based on the 100-kilometer fuel consumption data to obtain a fuel consumption ranking result. The second calculation unit is used to calculate the percentage of the vehicle's fuel consumption exceeding that of users with similar working conditions. The third calculation unit is used to calculate the fuel consumption score of the vehicle based on the fuel consumption ranking result and the percentage.
[0174] In this embodiment, the third calculation module 204 includes: a fourth design unit, a normalization unit, a fourth calculation unit and a fifth calculation unit. The fourth design unit is used to design driving habit scoring features, including multiple first indicators related to fuel consumption and multiple second indicators related to safety, wherein the multiple first indicators include a sudden acceleration ratio, a sudden deceleration ratio, and a constant speed driving ratio, and the multiple second indicators include a speeding ratio and a sharp turn ratio. The normalization unit is used to normalize the multiple first indicators and the multiple second indicators. The fourth calculation unit is used to calculate the weights of the multiple first indicators and the multiple second indicators using the entropy weight method. The fifth calculation unit is used to calculate the comprehensive score based on the weights and the normalized characteristic values to obtain a fuel consumption-related driving score and a safety-related driving score.
[0175] The various variations and specific examples of the vehicle networking series application method based on similar working conditions provided in Example 1 are also applicable to the vehicle networking series application system based on similar working conditions provided in this embodiment. Through the above detailed description of a vehicle networking series application method based on similar working conditions, technical personnel in this field can clearly understand the implementation method of a vehicle networking series application system based on similar working conditions in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.
[0176] Embodiment 3
[0177] Figure 3 is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention, such as Figure 3 As shown, the third embodiment further provides an electronic device 300 , which may include: a processor 301 and a memory 302 .
[0178] The memory 302 is used to store programs. The memory 302 may include a volatile memory, such as a random access memory (RAM), such as a static random access memory (SRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), etc. The memory may also include a non-volatile memory, such as a flash memory. The memory 302 is used to store computer programs (such as applications, function modules, etc. for implementing the above method), computer instructions, etc. The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories 302. And the above computer programs, computer instructions, data, etc. may be called by the processor 301.
[0179] The above-mentioned computer programs, computer instructions, etc. may be stored in partitions in one or more memories 302 . And the above-mentioned computer programs, computer instructions, etc. may be called by the processor 301 .
[0180] The processor 301 is used to execute the computer program stored in the memory 302 to implement each step of the method involved in the above embodiment.
[0181] For details, please refer to the relevant description in the previous method embodiment.
[0182] The processor 301 and the memory 302 may be independent structures or integrated structures. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 may be coupled and connected via a bus 303 .
[0183] The electronic device of this embodiment can execute the technical solution in the above method, and its specific implementation process and technical principle are the same, which will not be repeated here.
[0184] Embodiment 4
[0185] Embodiment 4 further provides a computer-readable storage medium, including a computer program and instructions. When the computer program or instructions are executed on a computer, the computer executes a control method for preventing urea nozzle crystallization blockage according to any embodiment of the present invention.
[0186] Computer-readable storage media include: USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks, and other media that can store program codes.
[0187] This embodiment also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.
[0188] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the disclosure of the present invention can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.
[0189] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A vehicle networking series application method based on similar working conditions, characterized in that: include: Step S100, designing and determining similarity features, wherein the similarity features include single statistical indicators, statistical distribution, and multi-dimensional distribution; Step S200, selecting data within a certain time range, using the similarity feature, calculating the similarity between the current vehicle and all vehicles, and obtaining a similarity result; Step S300, ranking the fuel consumption per 100 kilometers based on the similarity results, and calculating the percentage of fuel consumption exceeding that of users with similar working conditions and the fuel consumption score; Step S400, design driving habit scoring features, including multiple indicators related to fuel consumption and safety, normalize the features, use entropy weight method to calculate the weight of each indicator, and calculate the comprehensive score based on the weight and normalized characteristic value to obtain the fuel consumption related driving score and the safety related driving score.
2. The vehicle networking series application method based on similar working conditions as claimed in claim 1 is characterized in that: The step S100 includes: Step S101, designing a single statistical index, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature; Step S102, designing statistical distribution characteristics, including load distribution, slope distribution, environmental pressure distribution, and environmental temperature distribution; Step S103, designing multi-dimensional distribution features, taking into account the joint distribution of multiple dimensions such as load, slope, and vehicle speed.
3. The vehicle networking series application method based on similar working conditions as claimed in claim 1 is characterized in that: The step S200 includes: Step S201, selecting data within a certain time range; Step S202, using the similarity feature, calculating the similarity between the current vehicle and all vehicles; Step S203, based on the similarity calculation result, filter out a set of vehicles with similar operating conditions to the current vehicle to obtain a similarity result.
4. The vehicle networking series application method based on similar working conditions as claimed in claim 1 is characterized in that: The step S300 includes: Step S301, based on the similarity result, obtaining the fuel consumption data of the vehicle per 100 kilometers; Step S302, sorting based on the 100-kilometer fuel consumption data to obtain a fuel consumption sorting result; Step S303, calculating the percentage of the fuel consumption of the vehicle exceeding that of users with similar working conditions; Step S304, calculating the fuel consumption score of the vehicle according to the fuel consumption ranking result and the percentage.
5. The vehicle networking series application method based on similar working conditions as claimed in claim 1 is characterized in that: The step S400 includes: Step S401, designing driving habit scoring features, including multiple first indicators related to fuel consumption and multiple second indicators related to safety, wherein the multiple first indicators include a sudden acceleration ratio, a sudden deceleration ratio, and a constant speed driving ratio, and the multiple second indicators include a speeding ratio and a sharp turn ratio; Step S402, normalizing the plurality of first indicators and the plurality of second indicators; Step S403, using an entropy weight method to calculate the weights of the plurality of first indicators and the plurality of second indicators; Step S404, calculating a comprehensive score based on the weights and the normalized eigenvalues to obtain a fuel consumption-related driving score and a safety-related driving score.
6. A vehicle networking series application system based on similar working conditions, characterized in that: include: A design determination module is used to design and determine similarity features, wherein the similarity features include a single statistical indicator, a statistical distribution, and a multi-dimensional distribution; The first calculation module is used to select data within a certain time range, and use the similarity feature to calculate the similarity between the current vehicle and all vehicles, and obtain a similarity result; A second calculation module is used to sort the fuel consumption per 100 kilometers based on the similarity results, and calculate the percentage of fuel consumption exceeding that of users with similar working conditions and the fuel consumption score; as well as The third calculation module is used to design driving habit scoring features, including multiple fuel consumption-related and safety-related indicators, normalize the features, use the entropy weight method to calculate the weight of each indicator, and calculate the comprehensive score based on the weight and normalized feature value to obtain the fuel consumption-related driving score and the safety-related driving score.
7. The vehicle networking series application system based on similar working conditions as claimed in claim 6 is characterized in that: The design determination module comprises: The first design unit is used to design a single statistical index, including but not limited to average load, average uphill slope, average downhill slope, uphill ratio, downhill ratio, average ambient pressure and average ambient temperature; A second design unit is used to design statistical distribution characteristics, including load distribution, slope distribution, environmental pressure distribution and environmental temperature distribution; and The third design unit is used to design multi-dimensional distribution characteristics, considering the joint distribution of multiple dimensions such as load, slope, and vehicle speed.
8. The vehicle networking series application system based on similar working conditions as claimed in claim 6, characterized in that: The first calculation module includes: Selection unit, used to select data within a certain time range; A first calculation unit is used to calculate the similarity between the current vehicle and all vehicles by using the similarity feature; and The screening unit is used to screen out a set of vehicles with similar working conditions to the current vehicle according to the similarity calculation result to obtain a similarity result.
9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle networking series application method based on similar working conditions as described in any one of claims 1-5.
10. A computer-readable storage medium, characterized in that: It includes computer programs and instructions. When the computer program or the instructions are run on a computer, the computer executes the vehicle networking series application method based on similar working conditions as described in any one of claims 1 to 5.
Citation Information
Patent Citations
Driving risk grading clustering method for intelligent network connection vehicle group testing
CN110633729A
Vehicle driving condition construction method based on machine learning and statistical verification
CN112948965A
Automobile driving condition construction method and system based on large database sample
CN113688558A
Driving assistance method and device, computer equipment and storage medium
CN114426025A
