Parameter analysis model training and parameter analysis method and device, equipment and medium

Abstract

The application discloses a kind of parameter analysis model training and parameter analysis method, device, equipment and medium, comprising: obtaining the other vehicle parameters corresponding to abnormal vehicle;Wherein, abnormal vehicle indicates that the vehicle of target vehicle parameter exists anomaly, other vehicle parameter indicates the vehicle parameter except target vehicle parameter;According to the parameter correlation between other vehicle parameters and target vehicle parameter, determine relevant vehicle parameter from other vehicle parameter;Determine the parameter influence between relevant vehicle parameter and target vehicle parameter, and according to relevant vehicle parameter, and the parameter influence between relevant vehicle parameter and target vehicle parameter, generate model training data;Using model training data set, model training is carried out to the model to be trained, and generates parameter analysis model.The application reduces the artificial cost of vehicle parameter analysis, and improves the accuracy and efficiency of vehicle parameter analysis.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and medium for training and analyzing parameter analysis models. Background Technology

[0002] In actual vehicle use, various vehicle parameters exist, some of which directly affect the user experience. When certain vehicle parameters become abnormal, the reasons for these abnormalities are varied and complex due to the complex and ever-changing operating conditions and the interactions between different vehicle parameters.

[0003] When a vehicle exhibits abnormal parameters, current technologies largely rely on the experience of technicians for manual analysis to pinpoint the cause of the anomaly. However, this undoubtedly incurs significant labor costs and suffers from low accuracy and efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for training and analyzing parameter analysis models, thereby reducing the manual cost of vehicle parameter analysis and improving the accuracy and efficiency of vehicle parameter analysis.

[0005] According to one aspect of the present invention, a method for training a parameter analysis model is provided, comprising:

[0006] Obtain other vehicle parameters corresponding to the abnormal vehicle; wherein, the abnormal vehicle refers to the vehicle whose target vehicle parameters are abnormal, and the other vehicle parameters refer to vehicle parameters other than the target vehicle parameters;

[0007] Based on the parameter correlation between the other vehicle parameters and the target vehicle parameters, relevant vehicle parameters are determined from the other vehicle parameters;

[0008] Determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters, and generate model training data based on the relevant vehicle parameters and the parameter influence between the relevant vehicle parameters and the target vehicle parameters;

[0009] The model training dataset is used to train the model to be trained, generating a parameter analysis model.

[0010] According to another aspect of the present invention, a parameter analysis method is provided, comprising:

[0011] Obtain the target vehicle parameters corresponding to the candidate vehicles, and determine the abnormal vehicles from the candidate vehicles based on the target vehicle parameters;

[0012] Obtain other vehicle parameters corresponding to the abnormal vehicle, and determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters;

[0013] The relevant vehicle parameters are input into the parameter analysis model to determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters;

[0014] The parameter analysis model is trained using the parameter analysis model training method disclosed in any one of the present invention.

[0015] According to another aspect of the present invention, a training apparatus for a parameter analysis model is provided, comprising:

[0016] The other vehicle parameter acquisition module is used to acquire other vehicle parameters corresponding to the abnormal vehicle; wherein, the abnormal vehicle refers to the vehicle whose target vehicle parameters are abnormal, and the other vehicle parameters refer to vehicle parameters other than the target vehicle parameters.

[0017] The relevant vehicle parameter determination module is used to determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters;

[0018] The model training data generation module is used to determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters, and to generate model training data based on the relevant vehicle parameters and the parameter influence between the relevant vehicle parameters and the target vehicle parameters.

[0019] The model training module is used to train the model to be trained using the model training dataset and generate a parameter analysis model.

[0020] According to another aspect of the present invention, a parameter analysis apparatus is provided, comprising:

[0021] An abnormal vehicle determination module is used to obtain target vehicle parameters corresponding to candidate vehicles, and determine abnormal vehicles from the candidate vehicles based on the target vehicle parameters.

[0022] The vehicle parameter acquisition module is used to acquire other vehicle parameters corresponding to the abnormal vehicle, and determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters.

[0023] The parameter influence determination module is used to input the relevant vehicle parameters into the parameter analysis model and determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters.

[0024] The parameter analysis model is trained using the parameter analysis model training method disclosed in any one of the present invention.

[0025] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0026] At least one processor; and

[0027] A memory communicatively connected to the at least one processor; wherein,

[0028] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the training method and / or parameter analysis method of the parameter analysis model according to any one of the present invention.

[0029] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the training method and / or parameter analysis method of the parameter analysis model according to any one of the present invention.

[0030] The technical solution of this invention obtains other vehicle parameters corresponding to abnormal vehicles; wherein, abnormal vehicles refer to vehicles with abnormal target vehicle parameters, and other vehicle parameters refer to vehicle parameters other than the target vehicle parameters; based on the parameter correlation between other vehicle parameters and target vehicle parameters, relevant vehicle parameters are determined from the other vehicle parameters; the parameter influence between relevant vehicle parameters and target vehicle parameters is determined, and model training data is generated based on relevant vehicle parameters and the parameter influence between relevant vehicle parameters and target vehicle parameters; the model training dataset is used to train the model to be trained, generating a parameter analysis model, which enables the parameter analysis model to analyze the parameter influence between vehicle parameters. This allows the parameter analysis model to assist technicians in quickly locating the cause of abnormal vehicle parameters, reducing the manual cost of vehicle parameter analysis, and improving the accuracy and efficiency of vehicle parameter analysis.

[0031] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart illustrating a training method for a parameter analysis model provided in Embodiment 1 of the present invention;

[0034] Figure 2 A flowchart illustrating a training method for a parameter analysis model provided in Embodiment 2 of the present invention;

[0035] Figure 3 A flowchart of a parameter analysis method provided in Embodiment 3 of the present invention;

[0036] Figure 4 This is a schematic diagram of the structure of a training device for a parameter analysis model provided in Embodiment 4 of the present invention;

[0037] Figure 5 This is a schematic diagram of the structure of a parameter analysis device provided in Embodiment 5 of the present invention;

[0038] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the training method and / or parameter analysis method of the parameter analysis model in the embodiments of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "other," "target," "related," "historical," "current," and "to be optimized," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0041] In actual vehicle use, idle speed control is a crucial indicator that directly impacts the user experience. The complex and varied operating conditions of users lead to significant variations in idle speed stability, with a wide range of causes that are complex to analyze.

[0042] To simulate real-world user experience, OEMs use remote IoT devices to collect extensive data on actual vehicle driving conditions. This comprehensive data analysis examines the correlation between the influencing factors and proposes targeted optimization solutions. Relying on manual analysis based on the experience of technical personnel is costly, and suffers from low accuracy and efficiency.

[0043] Example 1

[0044] Figure 1 This is a flowchart of a training method for a parameter analysis model provided in Embodiment 1 of the present invention. This embodiment is applicable to training a model for determining the influence of parameters between vehicle parameters. The method can be executed by a parameter analysis model training device, which can be implemented in hardware and / or software, such as using a server. Figure 1 As shown, the method includes:

[0045] S101. Obtain parameters of other vehicles corresponding to the abnormal vehicle.

[0046] Here, "abnormal vehicle" refers to a vehicle whose target vehicle parameters are abnormal, while "other vehicle parameters" refers to vehicle parameters other than those of the target vehicle. Vehicle parameters include, but are not limited to, the operating parameters and load parameters generated by the vehicle in the starting state, as well as the environmental parameters of the vehicle's environment. The target vehicle parameters can be any type of operating parameter or load parameter, such as vehicle speed, ignition angle, air-fuel ratio, air conditioning load, or electrical load, etc.

[0047] In one implementation, with user authorization, the server communicates with each vehicle to collect vehicle parameters from the vehicle's controller at a preset sampling frequency. Further, based on pre-defined target vehicle parameters, it identifies abnormal vehicles. The identification method includes both manual and automatic methods. Manual identification relies on the experience of technicians to identify vehicles with abnormal target vehicle parameters. Automatic identification involves the server comparing pre-defined abnormal parameter thresholds with the target vehicle parameter values ​​for each vehicle and automatically identifying abnormal vehicles based on the comparison results.

[0048] For example, assuming the target vehicle parameter is "instantaneous fuel consumption", then the abnormal parameter threshold value is the abnormal fuel consumption threshold value, and the parameter value of the target vehicle parameter is the fuel consumption value. The abnormal fuel consumption threshold value corresponding to the pre-calibrated "instantaneous fuel consumption" is compared with the fuel consumption value of each vehicle's "instantaneous fuel consumption", and abnormal vehicles are automatically identified based on the comparison results.

[0049] After identifying an abnormal vehicle, the server will take the vehicle parameters collected from the abnormal vehicle, excluding the target vehicle parameters, and use these as the other vehicle parameters corresponding to the abnormal vehicle. For example, assuming the abnormal vehicle parameters collected by the server include vehicle parameter A, vehicle parameter B, vehicle parameter C, and vehicle parameter D, and assuming the target vehicle parameter is set to vehicle parameter A, then vehicle parameters B, C, and D will be used as the other vehicle parameters corresponding to the abnormal vehicle.

[0050] S102. Based on the parameter correlation between other vehicle parameters and the target vehicle parameters, determine the relevant vehicle parameters from the other vehicle parameters.

[0051] Among them, parameter correlation is a term that measures the linear relationship between two vehicle parameters. The value of parameter correlation is usually between -1 and +1, where "-" indicates negative correlation and "+" indicates positive correlation. As the value of parameter correlation approaches 0, it means that the relationship between the vehicle parameters will weaken, and it is 0 when there is no correlation at all.

[0052] In one implementation, the server uses a correlation calculation algorithm to determine the parameter correlation between each other vehicle parameter and the target vehicle parameter. Optionally, the Pearson correlation coefficient matrix method is used to measure the parameter correlation between each other vehicle parameter and the target vehicle parameter.

[0053] Based on the correlation between other vehicle parameters and the target vehicle parameters, the other vehicle parameters are filtered, and the remaining other vehicle parameters are selected as relevant vehicle parameters. Optionally, a pre-defined correlation threshold is determined, and then the other vehicle parameters are filtered based on the correlation threshold and the correlation between the other vehicle parameters and the target vehicle parameters.

[0054] S103. Determine the parameter influence between relevant vehicle parameters and target vehicle parameters, and generate model training data based on relevant vehicle parameters and the parameter influence between relevant vehicle parameters and target vehicle parameters.

[0055] Parameter influence measures the importance and contribution of one vehicle parameter to another. In other words, a greater parameter influence of one vehicle parameter on another indicates a greater importance and contribution to that parameter; conversely, a smaller parameter influence indicates a smaller importance and contribution.

[0056] In one implementation, the server uses an influence calculation algorithm to determine the parameter influence between each relevant vehicle parameter and the target vehicle parameter. Optionally, algorithms such as Random Forest or XGBoost can be used to determine the parameter influence between each relevant vehicle parameter and the target vehicle parameter.

[0057] Based on the parameter influence between each relevant vehicle parameter and the target vehicle parameter, the relevant vehicle parameters are labeled to determine the parameter labels of each relevant vehicle parameter. Then, model training data is generated based on each relevant vehicle parameter and its parameter labels.

[0058] S104. Use the model training dataset to train the model to be trained and generate a parameter analysis model.

[0059] Here, the model to be trained refers to the initial model that has not yet been fully trained.

[0060] In one implementation, the server uses machine learning algorithms to train the model to be trained, such as through an automated optimization method (AutoML), to generate a parametric analysis model. It is understood that since the parametric analysis model is trained based on relevant vehicle parameters and the parameter influence between these parameters and the target vehicle parameters, the trained parametric analysis model possesses the ability to analyze the parameter influence between vehicle parameters. Therefore, the parametric analysis model can be used to assist technicians in quickly locating the causes of abnormal vehicle parameters.

[0061] The technical solution of this invention obtains other vehicle parameters corresponding to abnormal vehicles; wherein, abnormal vehicles refer to vehicles with abnormal target vehicle parameters, and other vehicle parameters refer to vehicle parameters other than the target vehicle parameters; based on the parameter correlation between other vehicle parameters and target vehicle parameters, relevant vehicle parameters are determined from the other vehicle parameters; the parameter influence between relevant vehicle parameters and target vehicle parameters is determined, and model training data is generated based on relevant vehicle parameters and the parameter influence between relevant vehicle parameters and target vehicle parameters; the model training dataset is used to train the model to be trained, generating a parameter analysis model. This invention enables the parameter analysis model to analyze the parameter influence between vehicle parameters, thereby allowing the parameter analysis model to assist technicians in quickly locating the cause of abnormal vehicle parameters, reducing the manual cost of vehicle parameter analysis, and improving the accuracy and efficiency of vehicle parameter analysis.

[0062] Example 2

[0063] Figure 2 This is a flowchart of a training method for a parameter analysis model provided in Embodiment 2 of the present invention. This embodiment further optimizes and extends the above embodiments and can be combined with the various optional implementation methods described above. Figure 2 As shown, the method includes:

[0064] S201. Obtain parameters of other vehicles corresponding to the abnormal vehicle.

[0065] S202. Compare the parameter correlation between other vehicle parameters and the target vehicle parameters with the correlation threshold value, and determine the relevant vehicle parameters from other vehicle parameters based on the comparison results.

[0066] In one implementation, the parameter correlation between each other vehicle parameter and the target vehicle parameter is compared with a correlation threshold value. If the absolute value of the parameter correlation between any other vehicle parameter and the target vehicle parameter is greater than the absolute value of the correlation threshold value, then that other vehicle parameter is considered a relevant vehicle parameter.

[0067] For example, assuming a correlation threshold of 0.5, other vehicle parameters whose absolute correlation with the target vehicle parameter is greater than 0.5 are considered as relevant vehicle parameters.

[0068] For example, assuming a correlation threshold of -0.7, other vehicle parameters whose absolute correlation with the target vehicle parameter is greater than 0.7 are considered as relevant vehicle parameters.

[0069] By comparing the parameter correlation between other vehicle parameters and the target vehicle parameters with a correlation threshold, and determining the relevant vehicle parameters from the other vehicle parameters based on the comparison results, some other vehicle parameters with low parameter correlation with the target vehicle parameters are eliminated. This ensures that the selected relevant vehicle parameters have a high parameter correlation with the target vehicle parameters, further improving the quality of the model training data.

[0070] S203. Determine the parameter influence between relevant vehicle parameters and target vehicle parameters, and generate model training data based on relevant vehicle parameters and the parameter influence between relevant vehicle parameters and target vehicle parameters.

[0071] S204. Take the relevant vehicle parameters as input to the model to be trained, and take the parameter influence between the relevant vehicle parameters and the target vehicle parameters as output to the model to be trained, train the model to be trained, and generate a parameter analysis model.

[0072] In one implementation, relevant vehicle parameters in the model training data are used as input parameters of the model to be trained, and the parameter influence between the relevant vehicle parameters in the model training data and the target vehicle parameters is used as output parameters of the model to be trained. A machine learning algorithm is used to train the model to be trained to generate a parameter analysis model.

[0073] By using relevant vehicle parameters as input to the model to be trained, and the parameter influence between the relevant vehicle parameters and the target vehicle parameters as output to the model to be trained, the model to be trained is trained to generate a parameter analysis model. This enables the trained parameter analysis model to analyze the parameter influence between vehicle parameters, thereby allowing technicians to quickly locate the cause of abnormal vehicle parameters.

[0074] Optionally, the target vehicle parameters include idle speed fluctuation parameters.

[0075] The idle speed fluctuation parameter represents the difference in vehicle idle speed over time intervals, and can be used to measure the vehicle's ability to control idle speed. Understandably, a smaller idle speed fluctuation parameter indicates better vehicle control over idle speed, a smoother ride, and a better driving experience for the user.

[0076] By setting target vehicle parameters, including idle speed fluctuation parameters, the training method of the parameter analysis model provided in this embodiment of the invention can be applied to scenarios that optimize vehicle idle speed, thus playing a positive role in improving vehicles with abnormal idle speed fluctuations.

[0077] Optionally, other vehicle parameters include at least one of vehicle operating parameters, vehicle load parameters, and vehicle environmental parameters.

[0078] Among them, vehicle operating parameters refer to the operating parameters generated by the vehicle in the start-up state. Vehicle load parameters refer to the workload generated by the vehicle in the start-up state. Vehicle environmental parameters refer to the environmental parameters of the natural environment in which the vehicle is currently located.

[0079] By setting other vehicle parameters, including at least one of vehicle operating parameters, vehicle load parameters, and vehicle environmental parameters, the types of other vehicle parameters are enriched, thus ensuring the quality of model training data.

[0080] Optionally, vehicle operating parameters include at least one of vehicle speed, combustion torque, torque loss, torque converter status, and gear information; vehicle load parameters include at least one of generator load, electrical load, air conditioning load, and transmission torque consumption; and vehicle environmental parameters include at least one of temperature, altitude, humidity, sunlight intensity, and wind speed.

[0081] By setting vehicle operating parameters including at least one of vehicle speed, combustion torque, torque loss, hydraulic torque converter status, and gear information; vehicle load parameters including at least one of generator load, electrical load, air conditioning load, and transmission torque consumption; and vehicle environmental parameters including at least one of temperature, altitude, humidity, solar irradiance, and wind speed, the parameter types of other vehicle parameters are further refined. This provides guidance for the training method of the parameter analysis model provided in this embodiment of the invention in real-world scenarios and is more conducive to the further implementation of the method.

[0082] Example 3

[0083] Figure 3 This is a flowchart of a parameter analysis method provided in Embodiment 3 of the present invention. This embodiment is applicable to situations where parameter analysis is performed using the parameter analysis model provided in this embodiment. The method can be executed by a parameter analysis device, which can be implemented in hardware and / or software, such as using a server. Figure 3 As shown, the method includes:

[0084] S301. Obtain the target vehicle parameters corresponding to the candidate vehicles, and determine the abnormal vehicles from the candidate vehicles based on the target vehicle parameters.

[0085] Among them, candidate vehicles refer to vehicles that can communicate with the server with data, provided that the user authorizes them.

[0086] In one implementation, the server collects the target vehicle parameters of each candidate vehicle at a preset acquisition frequency through the vehicle-side controller of each candidate vehicle. Furthermore, the server compares pre-calibrated parameter thresholds with the parameter values ​​of the target vehicle parameters for each vehicle and automatically identifies abnormal vehicles based on the comparison results.

[0087] Optionally, the target vehicle parameters include idle speed fluctuation parameters. Obtain the target vehicle parameters corresponding to the candidate vehicles, including:

[0088] Obtain the historical idle speed of the candidate vehicle at a historical time and the current idle speed at the current time; determine the idle speed fluctuation parameters based on the historical idle speed and the current idle speed.

[0089] Here, "current moment" refers to the moment at the current time node, while "historical moment" refers to the moment at a previous historical world node. It can be understood that "historical idle speed" represents the idle speed of the candidate vehicle at a historical time node, while "current idle speed" represents the idle speed of the candidate vehicle at the current time node.

[0090] In one implementation, the server obtains the historical idle speed and current idle speed of each candidate vehicle, and then determines the idle speed fluctuation parameter based on the difference between the historical idle speed and the current idle speed.

[0091] By obtaining the historical idle speed of candidate vehicles at historical times and the current idle speed at the current time, and determining the idle speed fluctuation parameters based on the historical and current idle speeds, the system achieves the effect of determining the idle speed fluctuation parameters, laying a data foundation for subsequent identification of abnormal vehicles based on the idle speed fluctuation parameters.

[0092] Optionally, abnormal vehicles can be identified from candidate vehicles based on target vehicle parameters, including:

[0093] The idle speed fluctuation parameter corresponding to any candidate vehicle is compared with the fluctuation parameter threshold value; if the idle speed fluctuation parameter is greater than the fluctuation parameter threshold value, the candidate vehicle is regarded as an abnormal vehicle.

[0094] For example, assuming the fluctuation parameter threshold is "200 rpm", and the idle speed fluctuation parameter for any candidate vehicle is "220 rpm", then that candidate vehicle is considered an abnormal vehicle.

[0095] By comparing the idle speed fluctuation parameter of any candidate vehicle with the fluctuation parameter threshold, the candidate vehicle is identified as an abnormal vehicle if the idle speed fluctuation parameter exceeds the fluctuation parameter threshold. This achieves the effect of identifying vehicles with abnormal idle speed fluctuation, which helps technicians to optimize the idle speed of abnormal vehicles in a timely manner and improve the user's driving experience.

[0096] S302. Obtain the parameters of other vehicles corresponding to the abnormal vehicle, and determine the relevant vehicle parameters from the parameters of other vehicles based on the parameter correlation between the parameters of other vehicles and the parameters of the target vehicle.

[0097] S303. Input the relevant vehicle parameters into the parameter analysis model to determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters.

[0098] The parameter analysis model is trained using any of the parameter analysis model training methods provided in this embodiment of the invention.

[0099] In one implementation, relevant vehicle parameters are input into a parameter analysis model, and the parameter influence between the relevant vehicle parameters and the target vehicle parameters is determined based on the output of the parameter analysis model.

[0100] S304. Based on the parameter influence between the relevant vehicle parameters and the target vehicle parameters, sort the relevant vehicle parameters in descending order, and determine the vehicle parameters to be optimized from the relevant vehicle parameters based on the descending order results.

[0101] The descending order sorting of relevant vehicle parameters means sorting the relevant vehicle parameters according to their influence from largest to smallest.

[0102] In one implementation, based on the descending sorting result, the relevant vehicle parameters whose sorting order is within a preset order are taken as the vehicle parameters to be optimized.

[0103] For example, assuming the preset order is "5", the five relevant vehicle parameters with the greatest influence will be selected as the vehicle parameters to be optimized.

[0104] S305. Send the vehicle parameters to be optimized to the target terminal, so that the technicians holding the target terminal can optimize the abnormal vehicle based on the vehicle parameters.

[0105] The target terminal can be any electronic device with communication capabilities, including but not limited to smartphones, smart tablets, or laptops.

[0106] In one implementation, the server sends the vehicle parameters to be optimized to the target terminal based on the communication connection between the server and the target terminal. Technicians then focus on optimizing these vehicle parameters, employing software / hardware methods to improve the performance of the abnormal vehicle. For example, the server may use OTA (Over-The-Air) technology to perform software optimization on the abnormal vehicle, thereby addressing the issue of abnormal vehicle parameters.

[0107] By sorting the relevant vehicle parameters in descending order based on the parameter influence between the relevant vehicle parameters and the target vehicle parameters, and determining the vehicle parameters to be optimized from the relevant vehicle parameters based on the descending order, the vehicle parameters to be optimized are sent to the target terminal. The technicians holding the target terminal can then optimize the abnormal vehicles based on the vehicle parameters to be optimized. This achieves the effect of timely optimization of abnormal vehicles, ensuring the user's driving experience and increasing user stickiness.

[0108] Example 4

[0109] Figure 4 This is a schematic diagram of the structure of a training device for a parameter analysis model provided in Embodiment 4 of the present invention. Figure 4 As shown, the device includes:

[0110] The other vehicle parameter acquisition module 41 is used to acquire other vehicle parameters corresponding to the abnormal vehicle; wherein, the abnormal vehicle refers to the vehicle whose target vehicle parameters are abnormal, and the other vehicle parameters refer to vehicle parameters other than the target vehicle parameters.

[0111] The relevant vehicle parameter determination module 42 is used to determine the relevant vehicle parameters from other vehicle parameters based on the parameter correlation between other vehicle parameters and the target vehicle parameters;

[0112] The model training data generation module 43 is used to determine the parameter influence between relevant vehicle parameters and target vehicle parameters, and to generate model training data based on the relevant vehicle parameters and the parameter influence between the relevant vehicle parameters and target vehicle parameters.

[0113] The model training module 44 is used to train the model to be trained using the model training dataset and generate a parameter analysis model.

[0114] Optionally, the relevant vehicle parameter determination module 42 is specifically used for:

[0115] The correlation between other vehicle parameters and the target vehicle parameters is compared with the correlation threshold value, and the relevant vehicle parameters are determined from the other vehicle parameters based on the comparison results.

[0116] Optional, model training module 44, specifically used for:

[0117] The relevant vehicle parameters are used as input to the model to be trained, and the parameter influence between the relevant vehicle parameters and the target vehicle parameters is used as the output of the model to be trained. The model is trained to generate a parameter analysis model.

[0118] Optionally, the target vehicle parameters include idle speed fluctuation parameters.

[0119] Optionally, other vehicle parameters include at least one of vehicle operating parameters, vehicle load parameters, and vehicle environmental parameters.

[0120] Optionally, vehicle operating parameters include at least one of vehicle speed, combustion torque, torque loss, torque converter status, and gear information; vehicle load parameters include at least one of generator load, electrical load, air conditioning load, and transmission torque consumption; and vehicle environmental parameters include at least one of temperature, altitude, humidity, sunlight intensity, and wind speed.

[0121] The training device for the parameter analysis model provided in this embodiment of the invention can execute the training method for the parameter analysis model provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] Example 5

[0123] Figure 5 This is a schematic diagram of a parameter analysis device provided in Embodiment 5 of the present invention. Figure 5 As shown, the device includes:

[0124] The abnormal vehicle determination module 51 is used to obtain the target vehicle parameters corresponding to the candidate vehicles, and determine the abnormal vehicles from the candidate vehicles based on the target vehicle parameters.

[0125] The vehicle parameter acquisition module 52 is used to acquire other vehicle parameters corresponding to the abnormal vehicle, and determine the relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters.

[0126] The parameter influence determination module 53 is used to input relevant vehicle parameters into the parameter analysis model and determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters.

[0127] The parameter analysis model is trained using any of the parameter analysis model training methods provided in this embodiment of the invention.

[0128] Optionally, the target vehicle parameters include idle speed fluctuation parameters; the abnormal vehicle determination module is specifically used for:

[0129] Obtain the historical idle speed of the candidate vehicle at a historical time, and the current idle speed at the current time;

[0130] The idle speed fluctuation parameter is determined based on the historical idle speed and the current idle speed.

[0131] Optional, an abnormal vehicle identification module, specifically used for:

[0132] The idle speed fluctuation parameter corresponding to any candidate vehicle is compared with the fluctuation parameter threshold value.

[0133] If the idle speed fluctuation parameter is greater than the fluctuation parameter threshold, the candidate vehicle is identified as an abnormal vehicle.

[0134] Optionally, the device further includes a parameter sending module, specifically used for:

[0135] Based on the parameter influence between the relevant vehicle parameters and the target vehicle parameters, the relevant vehicle parameters are sorted in descending order, and the vehicle parameters to be optimized are determined from the relevant vehicle parameters based on the descending order results.

[0136] The parameters of the vehicle to be optimized are sent to the target terminal, so that the technicians holding the target terminal can optimize the abnormal vehicle based on the parameters of the vehicle to be optimized.

[0137] The parameter analysis device provided in the embodiments of the present invention can execute the parameter analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0138] Example 6

[0139] Figure 6 A schematic diagram of an electronic device 60 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0140] like Figure 6As shown, the electronic device 60 includes at least one processor 61 and a memory, such as a read-only memory (ROM) 62 and a random access memory (RAM) 63, communicatively connected to the at least one processor 61. The memory stores computer programs executable by the at least one processor. The processor 61 can perform various appropriate actions and processes based on the computer program stored in the ROM 62 or loaded into the RAM 63 from storage unit 68. The RAM 63 may also store various programs and data required for the operation of the electronic device 60. The processor 61, ROM 62, and RAM 63 are interconnected via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0141] Multiple components in electronic device 60 are connected to I / O interface 65, including: input unit 66, such as keyboard, mouse, etc.; output unit 67, such as various types of monitors, speakers, etc.; storage unit 68, such as disk, optical disk, etc.; and communication unit 69, such as network card, modem, wireless transceiver, etc. Communication unit 69 allows electronic device 60 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0142] Processor 61 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 61 performs the various methods and processes described above, such as training methods and / or parameter analysis methods for parameter analysis models.

[0143] In some embodiments, the training method and / or parameter analysis method of the parameter analysis model may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 68. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 60 via ROM 62 and / or communication unit 69. When the computer program is loaded into RAM 63 and executed by processor 61, one or more steps of the training method and / or parameter analysis method of the parameter analysis model described above may be performed. Alternatively, in other embodiments, processor 61 may be configured to execute the training method and / or parameter analysis method of the parameter analysis model by any other suitable means (e.g., by means of firmware).

[0144] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0146] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0149] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0150] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0151] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A training method for a parameter analysis model, characterized in that, include: Obtain other vehicle parameters corresponding to the abnormal vehicle; wherein, the abnormal vehicle refers to the vehicle whose target vehicle parameters are abnormal, and the other vehicle parameters refer to vehicle parameters other than the target vehicle parameters; Based on the parameter correlation between the other vehicle parameters and the target vehicle parameters, relevant vehicle parameters are determined from the other vehicle parameters; Determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters, and generate model training data based on the relevant vehicle parameters and the parameter influence between the relevant vehicle parameters and the target vehicle parameters; The model training dataset is used to train the model to be trained, generating a parameter analysis model. The step of training the model to be trained using the model training dataset to generate a parameter analysis model includes: The relevant vehicle parameters are used as input to the model to be trained, and the parameter influence between the relevant vehicle parameters and the target vehicle parameters is used as output to train the model to generate a parameter analysis model; wherein, the parameter influence is used to measure the importance and contribution of one vehicle parameter to another vehicle parameter. The target vehicle parameters include idle speed fluctuation parameters; The other vehicle parameters include at least one of vehicle operating parameters, vehicle load parameters, and vehicle environmental parameters; wherein, the vehicle operating parameters represent the operating parameters generated by the vehicle in the start-up state; the vehicle load parameters represent the workload generated by the vehicle in the start-up state; and the vehicle environmental parameters represent the environmental parameters of the natural environment in which the vehicle is currently located. The vehicle operating parameters include at least one of vehicle speed, combustion torque, torque loss, hydraulic torque converter status, and gear information; the vehicle load parameters include at least one of generator load, electrical load, air conditioning load, and transmission torque consumption; the vehicle environmental parameters include at least one of temperature, altitude, humidity, sunlight intensity, and wind speed.

2. The method according to claim 1, characterized in that, The step of determining relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters includes: The correlation between the other vehicle parameters and the target vehicle parameters is compared with a correlation threshold value, and the relevant vehicle parameters are determined from the other vehicle parameters based on the comparison results.

3. A parameter analysis method, characterized in that, include: Obtain the target vehicle parameters corresponding to the candidate vehicles, and determine the abnormal vehicles from the candidate vehicles based on the target vehicle parameters; Obtain other vehicle parameters corresponding to the abnormal vehicle, and determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters; The relevant vehicle parameters are input into the parameter analysis model to determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters; wherein, the parameter influence is used to measure the importance and contribution of one vehicle parameter to another vehicle parameter; The parameter analysis model is trained using the parameter analysis model training method described in any one of claims 1-2; The target vehicle parameters include idle speed fluctuation parameters; obtaining the target vehicle parameters corresponding to the candidate vehicles includes: Obtain the historical idle speed of the candidate vehicle at a historical time, and the current idle speed at the current time; The idle speed fluctuation parameter is determined based on the historical idle speed and the current idle speed; The step of determining abnormal vehicles from the candidate vehicles based on the target vehicle parameters includes: The idle speed fluctuation parameter corresponding to any candidate vehicle is compared with the fluctuation parameter threshold value. If the idle speed fluctuation parameter is greater than the fluctuation parameter threshold, the candidate vehicle is identified as an abnormal vehicle. After determining the parameter influence between the relevant vehicle parameters and the target vehicle parameters, the method further includes: Based on the parameter influence between the relevant vehicle parameters and the target vehicle parameters, the relevant vehicle parameters are sorted in descending order, and the vehicle parameters to be optimized are determined from the relevant vehicle parameters based on the descending order sorting results. The parameters of the vehicle to be optimized are sent to the target terminal, so that the technicians holding the target terminal can optimize the abnormal vehicle based on the parameters of the vehicle to be optimized.

4. A training device for a parameter analysis model, characterized in that, include: The other vehicle parameter acquisition module is used to acquire other vehicle parameters corresponding to the abnormal vehicle; wherein, the abnormal vehicle refers to the vehicle whose target vehicle parameters are abnormal, and the other vehicle parameters refer to vehicle parameters other than the target vehicle parameters. The relevant vehicle parameter determination module is used to determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters; The model training data generation module is used to determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters, and to generate model training data based on the relevant vehicle parameters and the parameter influence between the relevant vehicle parameters and the target vehicle parameters. The model training module is used to train the model to be trained using the model training dataset and generate a parameter analysis model. The model training module is specifically used for: The relevant vehicle parameters are used as input to the model to be trained, and the parameter influence between the relevant vehicle parameters and the target vehicle parameters is used as the output of the model to be trained. The model to be trained is then trained to generate a parameter analysis model. The parameter influence is used to measure the importance and contribution of one vehicle parameter to another vehicle parameter. The target vehicle parameters include idle speed fluctuation parameters; Other vehicle parameters include at least one of vehicle operating parameters, vehicle load parameters, and vehicle environmental parameters; wherein, the vehicle operating parameters represent the operating parameters generated by the vehicle in the start-up state; the vehicle load parameters represent the workload generated by the vehicle in the start-up state; and the vehicle environmental parameters represent the environmental parameters of the natural environment in which the vehicle is currently located. Vehicle operating parameters include at least one of vehicle speed, combustion torque, torque loss, hydraulic torque converter status, and gear information; vehicle load parameters include at least one of generator load, electrical load, air conditioning load, and transmission torque consumption; vehicle environmental parameters include at least one of temperature, altitude, humidity, sunlight intensity, and wind speed.

5. A parameter analysis device, characterized in that, include: An abnormal vehicle determination module is used to obtain target vehicle parameters corresponding to candidate vehicles, and determine abnormal vehicles from the candidate vehicles based on the target vehicle parameters. The vehicle parameter acquisition module is used to acquire other vehicle parameters corresponding to the abnormal vehicle, and determine relevant vehicle parameters from the other vehicle parameters based on the parameter correlation between the other vehicle parameters and the target vehicle parameters. The parameter influence determination module is used to input the relevant vehicle parameters into the parameter analysis model and determine the parameter influence between the relevant vehicle parameters and the target vehicle parameters; wherein, the parameter influence is used to measure the importance and contribution of one vehicle parameter to another vehicle parameter; The parameter analysis model is trained using the parameter analysis model training method described in any one of claims 1-2; The target vehicle parameters include idle speed fluctuation parameters; the abnormal vehicle determination module is specifically used for: Obtain the historical idle speed of the candidate vehicle at a historical time, and the current idle speed at the current time; The idle speed fluctuation parameter is determined based on the historical idle speed and the current idle speed; The abnormal vehicle identification module is specifically used for: The idle speed fluctuation parameter corresponding to any candidate vehicle is compared with the fluctuation parameter threshold value. If the idle speed fluctuation parameter is greater than the fluctuation parameter threshold, the candidate vehicle is identified as an abnormal vehicle. The device further includes a parameter sending module, specifically used for: Based on the parameter influence between the relevant vehicle parameters and the target vehicle parameters, the relevant vehicle parameters are sorted in descending order, and the vehicle parameters to be optimized are determined from the relevant vehicle parameters based on the descending order sorting results. The parameters of the vehicle to be optimized are sent to the target terminal, so that the technicians holding the target terminal can optimize the abnormal vehicle based on the parameters of the vehicle to be optimized.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the training method of the parameter analysis model according to any one of claims 1-2, and / or, the parameter analysis method according to any one of claims 3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to execute the training method of the parameter analysis model according to any one of claims 1-2, and / or the parameter analysis method according to any one of claims 3.

Images