Method and device for predicting remaining mileage of vehicle, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a method and a device for predicting the remaining mileage of a vehicle, a storage medium and electronic equipment. The method comprises the following steps: acquiring current driving information corresponding to the vehicle; outputting an estimated remaining mileage based on the current driving information through a plurality of estimation models in a target estimation model framework of the vehicle; and predicting the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework. According to the technical scheme provided by the embodiment of the invention, when the current remaining mileage of the vehicle under the current driving information is predicted, the current remaining mileage can be determined by integrating the estimated remaining mileage output by the plurality of estimation models based on the current driving information; the accuracy and robustness of predicting the current remaining mileage based on the current driving information are improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle driving data analysis, and in particular to a method, device, storage medium and electronic device for predicting the remaining mileage of a vehicle. Background Art

[0002] With the development of modern automotive technology, predicting the current remaining mileage of a vehicle is crucial for drivers. It not only helps drivers plan their journeys reasonably and avoid getting into trouble due to running out of power or fuel, but also effectively improves the driving experience and enhances the overall intelligence level of the vehicle.

[0003] Traditional remaining range prediction methods often rely on a vehicle's average fuel or electricity consumption data, combined with the current remaining capacity of the fuel tank or battery, to perform simple calculations. However, the actual range of a vehicle is affected by driving habits, road conditions, environmental factors, and the vehicle's own state. This can lead to significant discrepancies between the remaining range predicted by traditional remaining range prediction methods and the actual range.

[0004] Therefore, how to improve the accuracy of predicting the remaining mileage of a vehicle has become an urgent problem to be solved. Summary of the Invention

[0005] To solve the above technical problems, embodiments of the present application provide a method, device, computer-readable storage medium, and electronic device for predicting the remaining mileage of a vehicle.

[0006] According to one aspect of an embodiment of the present application, a method for predicting the remaining mileage of a vehicle is provided, comprising: obtaining current driving information corresponding to the vehicle; outputting estimated remaining mileage based on the current driving information by multiple estimation models in a target estimation model framework of the vehicle; and predicting the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

[0007] According to one aspect of an embodiment of the present application, a device for predicting the remaining mileage of a vehicle is provided, comprising: an information acquisition module configured to obtain current driving information corresponding to the vehicle; a mileage calculation module configured to output an estimated remaining mileage based on the current driving information using multiple estimation models in a target estimation model framework of the vehicle; and a mileage prediction module configured to predict the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

[0008] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module is further configured to: obtain a mileage feature training set corresponding to the vehicle before the multiple estimation models in the target estimation model framework of the vehicle respectively output the estimated remaining mileage based on the current driving information; based on the mileage feature training set, execute the model training process for the multiple estimation models in the initial estimation model framework respectively to obtain the target estimation model framework; the model training process includes: screening a preset number of feature parameters from the standard driving information of the mileage feature training set, and generating training driving information through the preset number of feature parameters; training the estimation model based on the training driving information and the standard remaining mileage of the mileage feature training set; and configuring the target estimation model framework according to the trained estimation model.

[0009] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module is further configured to: determine the mileage influence degree corresponding to each characteristic parameter in the test driving information of the vehicle; wherein, the test driving information is the driving information used by the vehicle when testing the remaining mileage, and the mileage influence degree characterizes the ability of the characteristic parameter to affect the remaining mileage of the vehicle; based on the mileage influence degree corresponding to each characteristic parameter and the preset mileage influence degree threshold, the target characteristic parameter is screened out, and the standard driving information of the mileage feature training set is generated through the screened target characteristic parameter; wherein, the mileage influence degree of the target characteristic parameter is greater than the preset mileage influence degree threshold; the standard remaining mileage of the mileage feature training set is generated through the test remaining mileage of the vehicle; wherein, the test remaining mileage is the remaining mileage obtained when the vehicle is in the test driving information when testing the remaining mileage.

[0010] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module is further configured to: cyclically execute the steps of controlling the estimation model to output the estimated remaining mileage based on the training driving information, then calculating the error vector between the estimated remaining mileage and the standard remaining mileage, and adjusting the model parameters of the estimation model according to the error vector, until the change amplitude between the error vector calculated last time and the error vector calculated this time is lower than the preset change amplitude, and then stop the loop.

[0011] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module is further configured to: obtain the target weight values ​​corresponding to each of the multiple estimation models in the target estimation model framework under the current driving information; and respectively control the multiple estimation models to output the estimated remaining mileage based on the current driving information and their respective corresponding target weight values.

[0012] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module is further configured to: determine the target driving condition of the vehicle based on the current driving information; obtain the weight value associated with each estimation model in the target estimation model framework and the target driving condition; and use the weight value associated with each estimation model in the target estimation model framework and the target driving condition as the target weight value.

[0013] In some embodiments of the present application, based on the aforementioned scheme, the mileage prediction module is further configured to: calculate an average remaining mileage value based on the estimated remaining mileage output by each estimation model in the target estimation model framework; and use the average remaining mileage value as the current remaining mileage.

[0014] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the method for predicting the remaining mileage of a vehicle as described in the above embodiment.

[0015] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the method for predicting the remaining mileage of a vehicle as described in the above-mentioned embodiment.

[0016] In the technical solution of the embodiment of the present application, the current driving information corresponding to the vehicle is first obtained, and then the estimated remaining mileage is output based on the current driving information by multiple estimation models in the target estimation model framework of the vehicle, so as to predict the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework. Therefore, when predicting the current remaining mileage of the vehicle under the current driving information, the estimated remaining mileage output by multiple estimation models based on the current driving information can be combined to determine the current remaining mileage, thereby reducing the possibility of large abnormalities in the determined current remaining mileage due to deviations or errors in a single estimation model caused by differences in vehicle type, power battery type and driving conditions in the current driving information, thereby ensuring that a stable and accurate current remaining mileage can be provided in the process of predicting the current remaining mileage based on the current driving information, thereby improving the accuracy and robustness of the prediction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0018] Figure 1 This is a flowchart of a method for predicting the remaining mileage of a vehicle, shown in an exemplary embodiment of the present application;

[0019] Figure 2 yes Figure 1 The output diagram of step S120 in an exemplary embodiment is shown;

[0020] Figure 3 yes Figure 1 A flowchart in an exemplary embodiment before step S120 in the illustrated embodiment;

[0021] Figure 4 yes Figure 3 A flowchart of the model training process in an exemplary embodiment shown in the embodiment;

[0022] Figure 5 yes Figure 4 A schematic diagram of training in step S2 of the embodiment shown in an exemplary embodiment;

[0023] Figure 6 yes Figure 3 The flowchart of step S210 in the illustrated embodiment in an exemplary embodiment;

[0024] Figure 7 is a block diagram of a vehicle remaining mileage prediction device shown in an exemplary embodiment of the present application;

[0025] Figure 8 It is a structural diagram of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0027] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0030] It should be noted that the term "plurality" used in this document refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0031] The technical solution of the embodiment of the present application proposes a method for predicting the remaining mileage of a vehicle, specifically referring to Figure 1 As shown. This method can be executed by a controller on the vehicle, or by other devices in the vehicle, without limitation. The method includes at least steps S110 to S130, which are described in detail as follows:

[0032] In step S110 , current driving information corresponding to the vehicle is obtained.

[0033] Considering that the current remaining range of a vehicle is related to the vehicle's current driving information, where driving information includes but is not limited to characteristic parameters such as driving conditions (e.g., vehicle speed, accumulated mileage, and remaining energy), external environment (e.g., wind speed, wind direction, and road conditions), internal factors (e.g., vehicle load, total battery voltage, and battery temperature), and driving behavior (e.g., frequency of sudden acceleration, sudden braking, and speed changes), in order to obtain the vehicle's current remaining range, in the embodiments of this application, the vehicle's current driving information is first obtained.

[0034] In step S120 , multiple estimation models in the target estimation model framework of the vehicle respectively output an estimated remaining mileage based on the current driving information.

[0035] In an embodiment of the present application, after obtaining the current driving information corresponding to the vehicle, multiple estimation models in the vehicle's target estimation model framework can be used to output an estimated remaining range based on the current driving information. The estimated remaining range is the remaining range value of the vehicle calculated by the estimation model based on the current driving information.

[0036] In some embodiments of the present application, the estimation model can be flexibly selected as needed, for example, a weighted calculation model, an estimation model with multiple deep multi-head self-attention shrinkage blocks, a support vector machine regression model, and other estimation models.

[0037] The manner in which multiple estimation models in the target estimation model framework of the vehicle output the estimated remaining mileage based on the current driving information can be flexibly set as needed. In one example, the multiple estimation models in the target estimation model framework can be directly controlled to output the estimated remaining mileage based on the current driving information.

[0038] For example, refer to Figure 2 As shown, when the first estimation model is a weighted calculation model, the weighted calculation model can, after obtaining the current driving information, first calculate the remaining mileage value based on the driving conditions in the current driving information, and then adjust the remaining mileage value based on the weights corresponding to the characteristic parameters such as external factors, internal factors and driving behavior in the current driving information, so as to use the adjusted remaining mileage value as the estimated remaining mileage.

[0039] Continue to refer to Figure 2As shown, when the second estimation model is an estimation model with multiple deep multi-head self-attention contraction blocks, each deep multi-head self-attention contraction block in the estimation model is composed of several convolutional layers, a multi-head self-attention mechanism, and a batch normalization layer, and a residual strategy is also added to the block. The convolutional layer is used to process each feature parameter in the current driving information obtained by the estimation model to improve the correlation between each feature parameter in the current driving information and the remaining range value of the vehicle. The multi-head self-attention mechanism is used to map each feature parameter in the current driving information output by the convolutional layer to different representation spaces through multiple parallel processing heads, and calculate the similarity between each feature parameter and its corresponding query and key. Then, for each feature parameter, the softmax function is used to normalize its similarity output by multiple heads, and the feature parameters are weighted summed according to the normalized similarity to generate a new feature parameter for representation.

[0040] Secondly, after the first deep multi-head self-attention contraction block in the estimation model outputs new feature parameters, the estimation model can use another deep multi-head self-attention contraction block for iterative optimization until every deep multi-head self-attention contraction block in the estimation model participates in the iterative optimization of the current driving information, thereby further improving the correlation between each feature parameter in the current driving information and the remaining mileage.

[0041] In addition, the estimation model with multiple deep multi-head self-attention contraction blocks also includes a multi-layer perceptron, which outputs an estimated remaining mileage based on each feature parameter in the current driving information output by the deep multi-head self-attention contraction block.

[0042] In another example, considering that there are differences in the corresponding calculation accuracy of each estimation model in the target estimation model framework in the process of outputting the estimated remaining mileage based on the current driving information, based on this, the target weight values ​​corresponding to the multiple estimation models in the target estimation model framework under the current driving information can be obtained first, and then the multiple estimation models can be controlled separately to output the estimated remaining mileage based on the current driving information and their corresponding target weight values, thereby improving the accuracy of the estimated remaining mileage output by each estimation model.

[0043] For example, when the estimated remaining mileage output by the weighted calculation model and the estimation model with multiple deep multi-head self-attention shrinkage blocks are L1 and L2 respectively, the target weight values ​​corresponding to the weighted calculation model and the estimation model with multiple deep multi-head self-attention shrinkage blocks under the current driving information are obtained as P1 and P2 respectively, then the estimated remaining mileage output by the weighted calculation model is adjusted to L1*P1, and correspondingly, the estimated remaining mileage output by the estimation model with multiple deep multi-head self-attention shrinkage blocks is adjusted to L2*P2.

[0044] In some embodiments of the present application, in order to obtain the target weight values ​​corresponding to multiple estimation models under the current driving information, the weight values ​​associated with each estimation model and the current driving information can be directly obtained from the preset memory and used as the target weight values.

[0045] Alternatively, the target driving condition of the vehicle can be determined based on the current driving information, and then the weight value associated with each estimation model and the target driving condition in the target estimation model framework can be obtained. Thereafter, the weight value associated with each estimation model and the target driving condition in the target estimation model framework can be used as the target weight value. This can shorten the time spent on determining the target weight value corresponding to each estimation model under the current driving information while ensuring that the correlation between the target weight value, the estimation model and the current driving information is not easily reduced.

[0046] In step S130 , the current remaining mileage of the vehicle under the current driving information is predicted based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

[0047] In an embodiment of the present application, after multiple estimation models in the target estimation model framework output estimated remaining mileage based on the current driving information, the current remaining mileage of the vehicle under the current driving information can be predicted based on the estimated remaining mileage output by each estimation model in the target estimation model framework, so as to achieve the purpose of predicting the current remaining mileage of the vehicle under the current driving information after integrating the estimated remaining mileage output by multiple estimation models based on the current driving information. In this way, in the process of predicting the current remaining mileage based on the current driving information, the possibility of a large difference between the predicted current remaining mileage and the actual remaining mileage due to the deviation or error of a single estimation model caused by the differences in vehicle type, power battery type and driving conditions in the current driving information is reduced, thereby ensuring that a stable and accurate current remaining mileage can be provided based on the current driving information in the prediction process, thereby improving the accuracy and robustness of the prediction process.

[0048] Among them, the process of predicting the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework can be flexibly set as needed. In one example, the average remaining mileage value can be directly calculated based on the estimated remaining mileage output by each estimation model in the target estimation model framework, and the average remaining mileage can be used as the current remaining mileage to reduce the difference between the current remaining mileage and the actual remaining mileage.

[0049] In another example, the number of occurrences of the estimated remaining mileage output by each estimation model in the target estimation model framework may be counted, and the estimated remaining mileage corresponding to the maximum number of occurrences may be used as the current remaining mileage.

[0050] In addition, in the process of predicting the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework, taking into account that each estimation model has a certain deviation in the estimated remaining mileage output based on the current driving information, based on this, the standard deviation corresponding to the estimated remaining mileage output by each estimation model can be calculated respectively, and then the target estimated remaining mileage can be screened out based on the standard deviation corresponding to the estimated remaining mileage output by each estimation model and the preset standard deviation threshold, so as to predict the current remaining mileage of the vehicle under the current driving information through the screened target estimated remaining mileage, wherein the standard deviation corresponding to the target estimated remaining mileage is lower than the preset standard deviation threshold, so as to eliminate outliers and improve the effectiveness of the subsequent predicted current remaining mileage.

[0051] Through the above implementation, the current driving information corresponding to the vehicle is first obtained, and then the estimated remaining mileage is output based on the current driving information by multiple estimation models in the target estimation model framework of the vehicle, so as to predict the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework. Therefore, when predicting the current remaining mileage of the vehicle under the current driving information, the estimated remaining mileage output by multiple estimation models based on the current driving information can be combined to determine the current remaining mileage, thereby reducing the possibility of a large difference between the determined current remaining mileage and the actual remaining mileage due to the deviation or error of a single estimation model caused by differences in vehicle type, power battery type and driving conditions in the current driving information, thereby ensuring that a stable and accurate current remaining mileage can be provided in the process of predicting the current remaining mileage based on the current driving information, thereby improving the accuracy and robustness of the prediction process.

[0052] See also Figure 3 , Figure 3 FIG. 1 is a flow chart showing a method for predicting the remaining mileage of a vehicle according to another exemplary embodiment. Figure 3 As shown, in Figure 1 Before step S120 in the illustrated embodiment, the method may further include steps S210 to S220, which are described in detail as follows:

[0053] In step S210, a mileage feature training set corresponding to the vehicle is obtained.

[0054] The mileage feature training set includes the standard driving information of the vehicle and the standard remaining mileage determined by the vehicle under the standard driving information.

[0055] The method for obtaining the vehicle's corresponding mileage characteristic training set can be flexibly configured as needed. In one example, standard driving information and standard remaining mileage can be directly obtained from a preset memory. A mileage characteristic training set can then be generated using the standard driving information and standard remaining mileage to obtain the vehicle's corresponding mileage characteristic training set. In other words, the standard driving information used in a previous test for the vehicle and the standard remaining mileage derived from that standard driving information can be pre-associated and stored in the preset memory, thereby shortening the time required to obtain the vehicle's corresponding mileage characteristic training set.

[0056] In another example, considering that the remaining mileage of a vehicle under the same driving information will change with the driving time and the aging of the vehicle itself, based on this, the historical driving information and the historical remaining mileage corresponding to the historical driving information can be obtained from the vehicle's historical estimated remaining mileage table, and the historical driving information and the historical remaining mileage can be used as the standard driving information and the standard remaining mileage in the mileage feature training set respectively to generate a mileage feature training set, thereby improving the matching degree between the mileage feature training set and the vehicle while achieving the purpose of obtaining the vehicle's mileage feature training set.

[0057] In step S220 , a model training process is performed on each of the multiple estimation models in the initial estimation model framework based on the mileage feature training set to obtain a target estimation model framework.

[0058] In an embodiment of the present application, after obtaining the mileage feature training set corresponding to the vehicle, the model training process can be executed separately for multiple estimation models in the initial estimation model framework based on the mileage feature training set to obtain the target estimation model framework.

[0059] In some embodiments of the present application, Figure 4 As shown, the model training process may include S1 to S3, as follows:

[0060] S1, screening a preset number of feature parameters from standard driving information in a mileage feature training set, and generating training driving information using the preset number of feature parameters;

[0061] S2, a standard remaining range training estimation model based on the training driving information and mileage feature training set;

[0062] S3, configures the target estimation model framework according to the trained estimation model.

[0063] In the above process, the screening method used to screen a preset number of feature parameters from the standard driving information of the mileage feature training set can be a random screening method or a screening method according to preset custom conditions, which is not limited here.

[0064] Furthermore, considering that the greater the number of characteristic parameters in driving information, the higher the prediction accuracy of the estimation model after training based on the driving information and the vehicle's remaining range under that driving information, but correspondingly, the lower the efficiency of training the estimation model based on the driving information and remaining range. Based on this, generating training driving information using a preset number of characteristic parameters can streamline the input of the estimation model during the training process, thereby improving the training efficiency of the estimation model without reducing the prediction accuracy.

[0065] In an embodiment of the present application, the process of training the estimation model for the standard remaining mileage based on the training driving information and the mileage feature training set can be flexibly set as needed. In one example, the training driving information can be directly used as the input of the estimation model so that the estimation model outputs the estimated remaining mileage based on the training driving information. The model parameters in the estimation model are then adjusted according to the error between the estimated remaining mileage and the standard remaining mileage of the mileage feature training set to reduce the error between the estimated remaining mileage output by the estimation model and the standard remaining mileage, thereby improving the prediction accuracy of the estimation model, thereby achieving the purpose of training the estimation model for the standard remaining mileage based on the target feature parameters and the mileage feature training set.

[0066] For example, refer to Figure 5 As shown, after the first training driving information filtered from the standard driving information is input into the first estimation model, the estimated remaining mileage output by the first estimation model is L1, and the standard remaining mileage is Y. Then, the difference between the estimated remaining mileage and the standard remaining mileage can be determined to be X, that is, X = Y-L1; then, the model parameters in the estimation model are adjusted based on the difference X with the goal of reducing the error between the estimated remaining mileage output by the estimation model and the standard remaining mileage, thereby improving the prediction accuracy of the estimation model.

[0067] Secondly, after the training driving information is input into the estimation model, when the estimation model outputs the estimated remaining mileage based on the training driving information, the target weight value corresponding to the estimation model can be further obtained to adjust the estimated remaining mileage, so as to adjust the difference X between the estimated remaining mileage and the standard remaining mileage, so that the difference X = Y-(P*L1), thereby further shortening the training time of the estimation model while improving the prediction accuracy of the estimation model.

[0068] In another example, the steps of controlling the estimation model to output the estimated remaining mileage based on the training driving information, calculating the error vector between the estimated remaining mileage and the standard remaining mileage, and adjusting the model parameters of the estimation model according to the error vector can be executed cyclically until the change between the error vector calculated last time and the error vector calculated this time is lower than the preset change range, and then the loop is stopped to minimize the error between the estimated remaining mileage and the standard remaining mileage while avoiding too many cycles, which would lead to a decrease in the training efficiency of the estimation model.

[0069] In the model training process, after training the estimation model based on the standard remaining range of the training driving information and mileage feature training set, the target estimation model framework can be configured based on the trained estimation model. In some embodiments of the present application, the trained estimation model can be encapsulated into an easy-to-deploy and easy-to-integrate estimation model framework to obtain the target estimation model framework for practical application in the vehicle.

[0070] Through the above implementation, before outputting the estimated remaining mileage based on the current driving information respectively through multiple estimation models in the target estimation model framework, it is also possible to first obtain the mileage feature training set corresponding to the vehicle, and then execute the model training process for the multiple estimation models in the initial estimation model framework based on the mileage feature training set. When each estimation model in the initial estimation model framework executes the model training process, the target estimation model framework can be obtained, thereby achieving the purpose of outputting the estimated remaining mileage based on the current driving information respectively through multiple estimation models in the target estimation model framework.

[0071] See also Figure 6 , Figure 6 FIG. 1 is a flow chart showing a method for predicting the remaining mileage of a vehicle according to another exemplary embodiment. Figure 6 As shown, the process of obtaining the mileage feature training set corresponding to the vehicle may include steps S310 to S330, which are described in detail as follows:

[0072] In step S310 , the mileage influence degree corresponding to each characteristic parameter in the test driving information of the vehicle is determined.

[0073] The test driving information is the driving information used by the vehicle when testing the remaining mileage, and the mileage impact degree represents the ability of the characteristic parameters to affect the remaining mileage of the vehicle.

[0074] In an embodiment of the present application, in order to obtain a mileage feature training set corresponding to a vehicle, the mileage influence degree corresponding to each characteristic parameter in the test driving information of the vehicle can be first determined. Specifically, the mileage influence degree corresponding to the characteristic parameter can be determined by Pearson correlation coefficient analysis, Spearman rank correlation coefficient analysis, or Kendall rank correlation coefficient analysis, etc., and there is no limitation here.

[0075] In step S320, target feature parameters are screened out based on the mileage influence degree corresponding to each feature parameter and a preset mileage influence degree threshold, and standard driving information of the mileage feature training set is generated using the screened target feature parameters.

[0076] The mileage influence degree of the target characteristic parameter is greater than a preset mileage influence degree threshold.

[0077] In an embodiment of the present application, the mileage influence degree corresponding to each characteristic parameter of the vehicle in the test driving information is determined, and the target characteristic parameters can be screened out based on the mileage influence degree corresponding to each characteristic parameter and the preset mileage influence degree threshold, that is, the characteristic parameters with a high correlation with the remaining mileage of the vehicle in the test driving information are screened out, and then the standard driving information of the mileage characteristic training set is generated by the screened target characteristic parameters, so that the characteristic parameters with a high correlation with the remaining mileage of the vehicle are selected to constitute the standard driving information, so that when the model training process is subsequently executed for multiple estimation models based on the mileage characteristic training set, the input of the estimation model in the training process can be further streamlined, thereby shortening the training time of the estimation model.

[0078] In step S330 , a standard remaining mileage of a mileage feature training set is generated based on the vehicle's test remaining mileage.

[0079] The test remaining mileage is the remaining mileage obtained when the vehicle is in the test driving information.

[0080] In an embodiment of the present application, after the standard driving information of the mileage feature training set is generated, the standard remaining mileage of the mileage feature training set can be generated by testing the remaining mileage, thereby achieving the purpose of obtaining the mileage feature training set when the standard driving information of the mileage feature training set is generated by the screened target feature parameters and the standard remaining mileage of the mileage feature training set is generated by testing the remaining mileage.

[0081] In addition, the method of generating the standard remaining mileage of the mileage feature training set through the vehicle's test remaining mileage can be flexibly set as needed. In one example, the vehicle's test remaining mileage can be directly used as the standard remaining mileage of the mileage feature training set.

[0082] In another example, considering that the remaining mileage obtained during the test remaining mileage of a vehicle in test driving information may still have errors, a test remaining mileage range can be generated based on a preset error range and the test remaining mileage, and then the test remaining mileage range can be used as the standard remaining mileage of the mileage feature training set.

[0083] The following describes an embodiment of the device of the present application, which can be used to implement the method for predicting the remaining mileage of a vehicle in the above-mentioned embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for predicting the remaining mileage of a vehicle in the above-mentioned embodiment of the present application.

[0084] Figure 7 FIG. 1 is a block diagram of a device 100 for predicting remaining vehicle mileage according to an embodiment of the present application.

[0085] Reference Figure 7 As shown, according to one aspect of an embodiment of the present application, a device for predicting the remaining mileage of a vehicle is provided, including: an information acquisition module 110, configured to obtain current driving information corresponding to the vehicle; a mileage calculation module 120, configured to output an estimated remaining mileage based on the current driving information through multiple estimation models in a target estimation model framework of the vehicle; and a mileage prediction module 130, configured to predict the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

[0086] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module 120 is further configured to: obtain a mileage feature training set corresponding to the vehicle before outputting the estimated remaining mileage based on the current driving information through multiple estimation models in the target estimation model framework of the vehicle; execute a model training process for multiple estimation models in the initial estimation model framework based on the mileage feature training set to obtain a target estimation model framework; the model training process includes: screening a preset number of feature parameters from the standard driving information of the mileage feature training set, and generating training driving information through the preset number of feature parameters; training the estimation model based on the standard remaining mileage of the training driving information and the mileage feature training set; and configuring the target estimation model framework according to the trained estimation model.

[0087] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module 120 is further configured to: determine the mileage influence degree corresponding to each characteristic parameter in the test driving information of the vehicle; wherein the test driving information is the driving information used by the vehicle when testing the remaining mileage, and the mileage influence degree characterizes the ability of the characteristic parameter to affect the remaining mileage of the vehicle; based on the mileage influence degree corresponding to each characteristic parameter and the preset mileage influence degree threshold, the target characteristic parameters are screened out, and the standard driving information of the mileage feature training set is generated through the screened target characteristic parameters; wherein the mileage influence degree of the target characteristic parameter is greater than the preset mileage influence degree threshold; the standard remaining mileage of the mileage feature training set is generated through the test remaining mileage of the vehicle; wherein the test remaining mileage is the remaining mileage obtained when the vehicle is in the test driving information when testing the remaining mileage.

[0088] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module 120 is further configured to: cyclically execute the steps of controlling the estimation model to output an estimated remaining mileage based on the training driving information, then calculating the error vector between the estimated remaining mileage and the standard remaining mileage, and adjusting the model parameters of the estimation model according to the error vector, until the change amplitude between the error vector calculated last time and the error vector calculated this time is lower than the preset change amplitude, and then stop the loop.

[0089] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module 120 is also configured to: obtain the target weight values ​​corresponding to each of the multiple estimation models in the target estimation model framework under the current driving information; and control the multiple estimation models to output the estimated remaining mileage based on the current driving information and their respective corresponding target weight values.

[0090] In some embodiments of the present application, based on the aforementioned scheme, the mileage calculation module 120 is further configured to: determine the target driving condition of the vehicle based on the current driving information; obtain the weight value associated with each estimation model and the target driving condition; and use the weight value associated with each estimation model and the target driving condition as the target weight value.

[0091] In some embodiments of the present application, based on the aforementioned scheme, the mileage prediction module 130 is further configured to: calculate an average remaining mileage value based on the estimated remaining mileage output by each estimation model in the target estimation model framework; and use the average remaining mileage value as the current remaining mileage.

[0092] It should be noted that the vehicle remaining mileage prediction device 100 provided in the above embodiment and the vehicle remaining mileage prediction method provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.

[0093] An embodiment of the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions, which, when executed by the processor, implement the method for predicting the remaining mileage of a vehicle as described above.

[0094] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0095] It should be noted that Figure 8 The computer system 200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0096] like Figure 8As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 202 or the program loaded from the storage part 208 to the random access memory (RAM) 203, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 203. The CPU 201, ROM 202 and RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0097] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, and the like; an output section 207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 208 including a hard disk and the like; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 210 as needed, so that a computer program read therefrom can be installed into the storage section 208 as needed.

[0098] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 209, and / or installed from a removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the various functions defined in the system of the present application are executed.

[0099] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0102] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently without being incorporated into the electronic device. The computer-readable storage medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device implements the method described in the above embodiments.

[0103] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0104] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0105] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0106] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for predicting the remaining mileage of a vehicle, characterized in that: The method comprises: Get the current driving information corresponding to the vehicle; Outputting estimated remaining mileage based on the current driving information respectively by a plurality of estimation models in the target estimation model framework of the vehicle; The current remaining mileage of the vehicle under the current driving information is predicted based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

2. The method according to claim 1, characterized in that Before outputting the estimated remaining mileage based on the current driving information by using the multiple estimation models in the target estimation model framework of the vehicle, the method further includes: Obtaining a mileage feature training set corresponding to the vehicle; Based on the mileage feature training set, a model training process is performed on each of the multiple estimation models in the initial estimation model framework to obtain the target estimation model framework; The model training process includes: Screening a preset number of characteristic parameters from the standard driving information in the mileage characteristic training set, and generating training driving information using the preset number of characteristic parameters; training the estimation model based on the training driving information and the standard remaining mileage of the mileage feature training set; The target estimation model framework is configured according to the trained estimation model.

3. The method according to claim 2, characterized in that The obtaining of the mileage feature training set corresponding to the vehicle includes: Determining a mileage impact degree corresponding to each characteristic parameter in the test driving information of the vehicle; wherein the test driving information is driving information used when testing the remaining mileage of the vehicle, and the mileage impact degree represents the ability of the characteristic parameter to affect the remaining mileage of the vehicle; Filtering out target feature parameters based on the mileage influence degree corresponding to each feature parameter and a preset mileage influence degree threshold, and generating standard driving information of the mileage feature training set using the filtered target feature parameters; wherein the mileage influence degree of the target feature parameter is greater than the preset mileage influence degree threshold; The standard remaining mileage of the mileage feature training set is generated through the test remaining mileage of the vehicle; wherein the test remaining mileage is the remaining mileage obtained when the vehicle in the test driving information is in the test remaining mileage.

4. The method according to claim 2, characterized in that The estimating model is trained based on the training driving information and the standard remaining mileage of the mileage feature training set, including: The estimation model is controlled to output an estimated remaining mileage based on the training driving information, an error vector is calculated between the estimated remaining mileage and the standard remaining mileage, and model parameters of the estimation model are adjusted according to the error vector, until a change between the error vector calculated last time and the error vector calculated this time is less than a preset change, and the loop is stopped.

5. The method according to claim 1, characterized in that The estimated remaining mileage outputted by the multiple estimation models in the target estimation model framework of the vehicle based on the current driving information respectively includes: Obtaining target weight values ​​corresponding to each of the multiple estimation models in the target estimation model framework under the current driving information; The plurality of estimation models are respectively controlled to output the estimated remaining mileage based on the current driving information and the respective corresponding target weight values.

6. The method according to claim 5, characterized in that The obtaining of target weight values ​​corresponding to the plurality of estimation models in the target estimation model framework includes: determining a target driving condition of the vehicle according to the current driving information; Obtaining a weight value associated with each estimation model in the target estimation model framework and the target driving condition; The weight value associated with each estimation model in the target estimation model framework and the target driving condition is used as the target weight value.

7. The method according to claim 1, characterized in that The predicting the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework includes: Calculating an average remaining mileage value based on the estimated remaining mileage output by each estimation model in the target estimation model framework; The average remaining mileage value is used as the current remaining mileage.

8. A vehicle remaining mileage prediction device, characterized in that: include: An information acquisition module configured to acquire current driving information corresponding to the vehicle; a mileage calculation module configured to output an estimated remaining mileage based on the current driving information using a plurality of estimation models in a target estimation model framework of the vehicle; The mileage prediction module is configured to predict the current remaining mileage of the vehicle under the current driving information based on the estimated remaining mileage output by each estimation model in the target estimation model framework.

9. A computer-readable storage medium, characterized in that Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the method for predicting the remaining mileage of a vehicle according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the method for predicting the remaining mileage of a vehicle as described in any one of claims 1 to 7.

Images