Vehicle travel determination method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a vehicle travel determination method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: inputting a departure place parameter into a preset prediction model, and generating a destination parameter; determining a first vehicle travel based on the departure place parameter, the destination parameter and / or the historical driving data; and if the destination parameter is not generated within the preset time, determining a second vehicle travel based on the driven path of the vehicle and the historical driving data. Therefore, the destination of the vehicle travel is predicted according to the travel rule of the vehicle owner, and the driving path is recommended according to the historical driving data of the vehicle owner, so that the driving path of the vehicle travel is accurately predicted under the condition that the problem of limited predicted destinations is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, electronic device and readable storage medium for determining a vehicle range. Background Art

[0002] With the continuous advancement of science and technology, the development of artificial intelligence has gradually matured. It is of great significance to predict the vehicle's travel trajectory. Traditional vehicle navigation is generally achieved by users directly entering the starting and ending points of the trip on an electronic map.

[0003] On this basis, the existing technology can predict the owner's home and workplace addresses in advance by allowing the owner to enter the address of the owner's home in the morning when the owner is at home, and predict the owner's return home in the afternoon when the owner is at the company, and then recommend a driving route based on the real-time traffic conditions and the user's input route selection preferences. However, the above method has shortcomings: the predicted destinations are limited and only applicable to office workers with a very fixed travel pattern, and can only predict two locations: home and workplace. Summary of the invention

[0004] The purpose of the present application is to provide a vehicle itinerary determination method, device, electronic device and computer-readable storage medium, which predict the destination of the vehicle itinerary based on the travel patterns of the vehicle owner, and then recommend a driving route based on the vehicle owner's historical driving data, thereby solving the problem of limited predicted destinations and achieving accurate prediction of the driving route of the vehicle itinerary.

[0005] To achieve the above objectives:

[0006] In a first aspect, an embodiment of the present application provides a method for determining a vehicle range, the method comprising:

[0007] Input the departure place parameters into the preset prediction model to generate the destination parameters;

[0008] Determining a first vehicle trip based on the departure location parameter, the destination parameter and / or the historical travel data;

[0009] If the destination parameter is not generated within a preset time, a second vehicle trip is determined based on the vehicle's traveled path and the historical travel data.

[0010] In one embodiment, the method further comprises a step of training the preset prediction model, wherein the training step comprises:

[0011] Detecting a destination associated with a departure parameter of the vehicle in historical travel data of the vehicle;

[0012] If the number of the same destination in the detected destination parameters is greater than or equal to a preset first threshold, using the travel data associated with the same destination in the historical driving data as a training sample;

[0013] The initial preset prediction model is trained based on the training samples.

[0014] In one embodiment, the preset prediction model includes a neural network model and a linear regression model; and the training of the initial preset prediction model based on the training sample includes:

[0015] Inputting the trip endpoint information in the training sample into the embedding layer of the neural network model for vectorization processing;

[0016] Inputting the data output after processing by the embedding layer and the numerical features of the travel in the training sample into the hidden layer of the neural network model for feature fusion;

[0017] The data output after the hidden layer processing and the trip cross-features calculated by the linear regression model based on the trip numerical features are input into the output layer of the neural network to perform feature enhancement through the output layer.

[0018] In one embodiment, determining the first vehicle trip based on the departure location parameter, the destination parameter and / or the historical driving data includes:

[0019] Determining at least one historical driving path corresponding to the departure location parameter and the destination parameter in the historical driving data of the vehicle;

[0020] The first similarity between the historical driving paths is detected, and the first vehicle trip is determined according to the first historical driving paths with the largest number; the first historical driving paths are historical driving paths whose first similarity exceeds a preset second threshold.

[0021] In one embodiment, if the destination parameter is not generated within a preset time, determining a second vehicle trip based on the vehicle's traveled path and the historical travel data includes:

[0022] Determining a second similarity between the traveled path of the vehicle and at least one historical travel path in the historical travel data;

[0023] The second vehicle trip is determined according to a second historical driving path with the highest similarity; the second historical driving path is a historical driving path with the second similarity exceeding a preset third threshold.

[0024] In one embodiment, the method further comprises:

[0025] After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route;

[0026] According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested;

[0027] If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

[0028] In a second aspect, an embodiment of the present application provides a vehicle range determination device, the device comprising:

[0029] The destination detection module is used to input the departure place parameters into the preset prediction model to generate the destination parameters;

[0030] A first path detection module, configured to determine a first vehicle trip based on the departure location parameter, the destination parameter and / or the historical travel data;

[0031] The second path detection module is used to determine a second vehicle trip based on the vehicle's traveled path and the historical travel data if the destination parameter is not generated within a preset time.

[0032] In one embodiment, the device further comprises a neural network training module, specifically configured to:

[0033] Detecting a destination associated with a departure parameter of the vehicle in historical travel data of the vehicle;

[0034] If the number of the same destination in the detected destination parameters is greater than or equal to a preset first threshold, using the travel data associated with the same destination in the historical driving data as a training sample;

[0035] The initial preset prediction model is trained based on the training samples.

[0036] In one embodiment, the neural network training module is specifically used to:

[0037] Inputting the trip endpoint information in the training sample into the embedding layer of the neural network model for vectorization processing;

[0038] Inputting the data output after processing by the embedding layer and the numerical features of the travel in the training sample into the hidden layer of the neural network model for feature fusion;

[0039] The data output after the hidden layer processing and the trip cross-features calculated by the linear regression model based on the trip numerical features are input into the output layer of the neural network to perform feature enhancement through the output layer.

[0040] In one implementation, the first path detection module is specifically configured to:

[0041] Determining at least one historical driving path corresponding to the departure location parameter and the destination parameter in the historical driving data of the vehicle;

[0042] The first similarity between the historical driving paths is detected, and the first vehicle trip is determined according to the first historical driving paths with the largest number; the first historical driving paths are historical driving paths whose first similarity exceeds a preset second threshold.

[0043] In one implementation, the second path detection module is specifically configured to:

[0044] Determining a second similarity between the traveled path of the vehicle and at least one historical travel path in the historical travel data;

[0045] The second vehicle trip is determined according to a second historical driving path with the highest similarity; the second historical driving path is a historical driving path with the second similarity exceeding a preset third threshold.

[0046] In one embodiment, the device further includes a reminder module, which is specifically configured to:

[0047] After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route;

[0048] According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested;

[0049] If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

[0050] In a third aspect, an embodiment of the present application discloses an electronic device, specifically comprising:

[0051] processor;

[0052] a memory for storing instructions executable by the processor;

[0053] The processor is configured to execute the instructions to execute the vehicle range determination method as described in the first aspect.

[0054] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can implement the vehicle range determination method as described in the first aspect.

[0055] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for determining a vehicle trip, the method comprising: inputting a departure point parameter into a preset prediction model to generate a destination parameter; determining a first vehicle trip based on the departure point parameter, the destination parameter and / or historical driving data; if the destination parameter is not generated within a preset time, determining a second vehicle trip based on the vehicle's travel path and the historical driving data. In this way, the destination of the vehicle trip is predicted based on the owner's travel pattern, and then the driving path is recommended based on the owner's historical driving data, so as to achieve accurate prediction of the vehicle's driving path while solving the problem of limited predicted destinations. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flow chart of a vehicle travel determination method provided by an embodiment of the present invention Figure 1 ;

[0057] Figure 2 A schematic diagram of data collection in the vehicle travel determination method provided by an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of a preset prediction model in a vehicle range determination method provided by an embodiment of the present invention;

[0059] Figure 4 A flow chart of a vehicle travel determination method provided by an embodiment of the present invention Figure 2 ;

[0060] Figure 5 A schematic diagram of a vehicle travel determination device provided by an embodiment of the present invention;

[0061] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0063] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0064] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of..." or "when..." or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate that there are described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0065] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0066] It should be noted that in this article, step codes such as S1 and S2 are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the order. When implementing the step, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the scope of protection of this application.

[0067] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0069] See also Figure 1 , is a vehicle trip determination method provided in an embodiment of the present application. The vehicle trip determination method can be executed by a vehicle trip determination device provided in an embodiment of the present application. The vehicle trip determination device can be implemented in software and / or hardware, such as a server, a computer or other electronic device. The vehicle trip determination method provided in this embodiment includes:

[0070] Step S1: Input the departure place parameters into the preset prediction model to generate the destination parameters.

[0071] like Figure 2As shown, first, when the vehicle is started, the vehicle data, including vehicle ID, start time, parameters of the vehicle's departure location, etc., are collected through the vehicle terminal, and the collected data is sent to the cloud. Among them, the departure location parameters can be the location coordinates of the departure location or the location name of the departure location, etc. Secondly, after receiving the collected data information, the cloud sends the information to the Kafka message component to decouple the data information through the Kafka message component, so as to store the consumption data in the data warehouse. Then, after receiving the data information, the data warehouse analyzes and processes the data, and inputs the vehicle's departure location into the preset prediction model. Finally, the destination of the vehicle's trip is detected through the preset prediction model.

[0072] In one embodiment, the method further comprises a step of training the preset prediction model, wherein the training step comprises:

[0073] Detecting a destination associated with a departure parameter of the vehicle in historical travel data of the vehicle;

[0074] If the number of the same destination in the detected destination parameters is greater than or equal to a preset first threshold, using the travel data associated with the same destination in the historical driving data as a training sample;

[0075] The initial preset prediction model is trained based on the training samples.

[0076] Optionally, the historical driving data of the vehicle can be collected by inserting code in an application, website, mobile application or system in the form of setting buried data. Specifically, the relevant historical driving data can be obtained by burying points on the electronic map on the vehicle or the electronic map on the user terminal, so as to perform data modeling through the buried data and the historical driving data. Among them, the high-frequency itinerary characteristics of the user on weekdays include the starting and ending point information, the number of trips, the travel distance, the travel duration, the most common departure time, the most common departure day (i.e., the day of the week), etc. Here, the high-frequency itinerary characteristics of the user on weekdays in the historical driving data, as well as the information such as the number of days from the last departure to today, are determined according to actual needs, and after determining the high-frequency itinerary characteristics of the user on weekdays, the specific route of the corresponding itinerary is saved, and according to the data reporting rules, the latitude and longitude of the waypoints are stored in chronological order, and matched with the electronic map to generate a fitting of the vehicle's itinerary route. The calculated high-frequency itinerary characteristics of the user on weekdays and the itinerary route obtained by fitting are stored to generate historical driving data. Here, the historical driving data of the vehicle within a certain time period can be obtained according to the actual needs of the user. For example, the corresponding historical driving data can be generated based on the driving data of the vehicle in the previous year, or based on the driving data of the vehicle in the previous quarter.

[0077] Optionally, based on the obtained departure point parameter of the vehicle, a destination parameter associated with the departure point parameter of the vehicle is detected in the generated historical driving data, that is, a destination corresponding to a trip whose departure point parameter in the historical driving data of the vehicle is consistent with the departure point parameter of the current vehicle is detected. For example, when it is determined that the departure point of the vehicle is place A, a destination parameter corresponding to the trip whose departure point is place A in the historical driving data of the vehicle is detected. Here, there may be multiple destination parameters associated with the departure point parameter of the vehicle in the historical driving data of the vehicle.

[0078] Optionally, in the historical driving data, the destination parameter associated with the departure parameter of the vehicle is determined, and it is determined whether at least one of the detected destination parameters is consistent, and whether the number of the same destination among the detected destinations is greater than or equal to a preset first threshold. If the number of the same destination among the detected destinations is greater than or equal to the preset first threshold, the travel data associated with the same destination in the historical driving data is used as a training sample to train the initial preset prediction model through the training sample; if the number of the same destination among the detected destinations is less than the preset first threshold, no processing is performed. The preset first threshold can be confirmed based on the historical travel in the historical driving data of the vehicle, so as to avoid the influence of one or several occasional historical travels on the destination prediction through the preset first threshold.

[0079] In one embodiment, the preset prediction model includes a neural network model and a linear regression model; and the training of the initial preset prediction model based on the training sample includes:

[0080] Inputting the trip endpoint information in the training sample into the embedding layer of the neural network model for vectorization processing;

[0081] Inputting the data output after processing by the embedding layer and the numerical features of the travel in the training sample into the hidden layer of the neural network model for feature fusion;

[0082] The data output after the hidden layer processing and the trip cross-features calculated by the linear regression model based on the trip numerical features are input into the output layer of the neural network model to perform feature enhancement through the output layer.

[0083] like Figure 3As shown, the preset prediction model includes a neural network model and a linear regression model, and the preset prediction model is constructed by combining the linear regression model and the neural network model to analyze and learn the training samples, so that the preset prediction model has the ability to directly learn and use the items or features in the historical data to achieve the "co-occurrence frequency", and has the ability to transfer the relevance of features and discover the relevance between sparse or even rare features that have never appeared and the final label. Here, the initial preset prediction model is trained through the training samples, specifically including:

[0084] The trip endpoint information in the training sample is input into the embedding layer in the neural network model to map the trip endpoint information into a vector with real values ​​through the embedding layer. The trip endpoint information includes the latitude and longitude information of the starting point and destination of the trip, as well as the corresponding trip classification features. Here, the trip classification features include the location information such as the departure point and the community and street where the destination is located in the historical driving data, as well as the time information such as the month and week corresponding to the trip in the historical driving data.

[0085] Optionally, the data processed and output by the embedding layer and the numerical features of the trips in the training samples are input into the hidden layer of the neural network model. The numerical features of the trips are the frequency of occurrence of the same trip in the historical driving data of the vehicle. The input of the hidden layer can be expressed as:

[0086] h 1 =Relu(Wx+b)

[0087] Where x represents the feature vector, including the features transformed by the embedding layer and the user numerical features; h 1 represents the first hidden layer.

[0088] h (l+1) =Relu(W l h l +b l )

[0089] Among them, h represents the activation value of the hidden layer; b represents the constant term of the hidden layer, l represents the current number of hidden layers; Relu represents the activation function; h l+1 represents the l+1th hidden layer.

[0090] Optionally, the trip numerical features are input into a linear regression model to calculate the corresponding trip cross features. Here, the linear regression model can be expressed as:

[0091] y=W T φ(x)+b

[0092] Among them, y represents the target variable; φ(x) represents the characteristics of the cross-trip, W represents the set parameters; and b represents the set constant term.

[0093] Among them, the characteristics of the cross-stroke can be specifically expressed as:

[0094]

[0095] Among them, k represents the kth combined feature; x i represents the i-th feature; when the i-th feature is part of the k-th combined feature, c ki =1, otherwise c ki =0; m represents the total number of features.

[0096] Optionally, the trip cross features calculated by the linear regression model and the data output by the hidden layer are input into the output layer of the neural network model to perform feature enhancement through the output layer. Here, the loss function combining the linear regression model part and the neural network model part is expressed as:

[0097]

[0098] Among them, σ represents the nonlinear activation function; h n represents the activation value of the last hidden layer; W liner Represents the parameters of the linear regression model set; represents the output of the hidden layer.

[0099] Step S2: Determine a first vehicle trip based on the departure location parameters, destination parameters and / or historical driving data.

[0100] Specifically, after the preset prediction model determines the corresponding destination, since there can be multiple driving paths between the departure point and the destination, in order to better fit the driving habits of the car owner, dynamic planning can be used to detect the similarity between historical driving paths of the same departure point and destination in the historical driving data, so as to determine the first vehicle trip based on the similarity.

[0101] In one embodiment, determining the first vehicle trip based on the departure location parameter, the destination parameter and / or the historical driving data includes:

[0102] Determining at least one historical driving path corresponding to the departure location parameter and the destination parameter in the historical driving data of the vehicle;

[0103] The first similarity between the historical driving paths is detected, and the first vehicle trip is determined according to the first historical driving paths with the largest number; the first historical driving paths are historical driving paths whose first similarity exceeds a preset second threshold.

[0104] Optionally, at least one historical driving path corresponding to the departure and destination parameters of the vehicle in the historical driving data is obtained, and the first similarity between each historical driving path and other historical driving paths is detected. If the first similarity exceeds a preset second threshold, the historical driving path is determined as the first historical driving path, and any one of the first historical driving paths with the largest number of paths is determined as a specific driving path in the first vehicle trip. The second vehicle trip is determined based on the determined specific driving path, as well as the departure and destination parameters of this trip. Here, the first similarity between each historical driving path and other historical driving paths can be calculated by the Fréchet distance. The measure of similarity can be determined based on features such as the shape, length, and direction of the path.

[0105] Optionally, after determining the driving path of the vehicle trip, it is also possible to determine whether the proportion of the driving path in the first historical driving path is greater than a preset ratio. If so, any historical driving path in the first historical driving path with the largest number of paths is determined as the current vehicle trip.

[0106] Step S3: If the destination parameter is not generated within a preset time, a second vehicle trip is determined based on the vehicle's traveled path and the historical travel data.

[0107] Specifically, when the preset prediction model does not detect the destination of the vehicle trip, the path information that the vehicle has traveled is obtained, and the second vehicle trip is determined based on the path that has been traveled and the historical trips of the vehicle in the historical driving data. The path information that the vehicle has traveled can be obtained in real time or at intervals, or the corresponding path information that has been traveled can be obtained based on a certain distance that the vehicle has traveled. The path information that the vehicle has traveled can be obtained in the form of a series of coordinate points.

[0108] In one embodiment, if the destination parameter is not generated within a preset time, determining a second vehicle trip based on the vehicle's traveled path and the historical travel data includes:

[0109] Determining a second similarity between the traveled path of the vehicle and at least one historical travel path in the historical travel data;

[0110] The second vehicle trip is determined according to a second historical driving path with the highest similarity; the second historical driving path is a historical driving path with the second similarity exceeding a preset third threshold.

[0111] Optionally, when the vehicle is traveling, the user's current path data may be collected in the form of a sequence of coordinate points. Here, the Fleche distance algorithm or other path similarity algorithm may be used to calculate the similarity between at least one historical driving path in the historical driving data and the current driving path. Here, the measure of similarity may be determined based on features such as the shape, length, and direction of the path.

[0112] In one embodiment, the method further comprises:

[0113] After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route;

[0114] According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested;

[0115] If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

[0116] Optionally, the interface of the electronic map is called through the cloud to send the determined driving route of the vehicle to the connected electronic map through the called interface. Correspondingly, after receiving the driving route, the electronic map determines the driving time for the driving route at this stage. The determined driving time is compared with the time threshold standard to determine whether there is congestion on the driving path of the vehicle, and when it is determined that there is congestion, a corresponding congestion reminder is issued. Among them, the electronic map can be Baidu Map, Amap, etc., which is not limited here.

[0117] In summary, in the vehicle itinerary determination method provided in the above embodiment, the destination of the vehicle itinerary is predicted based on the travel patterns of the vehicle owner, and then the driving route is recommended based on the vehicle owner's historical driving data, thereby solving the problem of limited predicted destinations and achieving accurate prediction of the driving route of the vehicle itinerary.

[0118] Based on the same inventive concept as the above-mentioned embodiment, the vehicle trip determination method provided by the present embodiment is described in detail below through a specific example. The vehicle trip determination method is mainly implemented by the vehicle terminal, the big data service and the model warehouse, and specifically includes:

[0119] See also Figure 4 , is a vehicle trip determination method provided in an embodiment of the present application, the vehicle trip determination method is mainly implemented by an online push module, an interactive data module and an offline training module, and includes the following steps:

[0120] Step S201: The user starts the vehicle computer and requests service.

[0121] Optionally, when starting the vehicle, the vehicle data is collected through the vehicle terminal, including vehicle ID, start time, vehicle departure parameters, etc. The departure parameters may be the location coordinates of the departure location or the location name of the departure location, etc.

[0122] Step S202: query the database for high-frequency trips to obtain relevant feature data.

[0123] Optionally, in the historical driving data of the vehicle, the destination parameters of the trips associated with the departure parameters of the vehicle are detected. If the number of trips with one destination parameter is detected to be greater than or equal to a preset first threshold, relevant feature data is obtained in the historical driving data.

[0124] Step S203: calling a preset prediction model according to the vehicle departure location information.

[0125] Step S204: Output the detected destination parameters according to the preset prediction model.

[0126] Step S205: query the historical driving data of the vehicle to determine the vehicle journey, and determine the congestion situation of the vehicle journey.

[0127] Optionally, after the preset prediction model determines the corresponding destination parameters, since there can be multiple driving paths between the departure and the destination, in order to better suit the driving habits of the car owner, dynamic planning can be used to detect the similarity between historical driving paths with consistent departure parameters and destination parameters in the historical driving data, so as to determine the vehicle itinerary based on the similarity.

[0128] Optionally, the interface of the electronic map is called through the cloud to send the determined driving route of the vehicle to the connected electronic map through the called interface. Correspondingly, after receiving the driving route, the electronic map determines the driving time for the driving route at this stage. The determined driving time is compared with the time threshold standard to determine whether there is congestion on the driving path of the vehicle, and when it is determined that there is congestion, a corresponding congestion reminder is issued. Among them, the electronic map can be Baidu Map, Amap, etc., which is not limited here.

[0129] Step S206: Output the vehicle's driving path and the corresponding congestion situation.

[0130] In summary, in the vehicle itinerary determination method provided in the above embodiment, the destination of the vehicle itinerary is predicted based on the travel patterns of the vehicle owner, and then the driving route is recommended based on the vehicle owner's historical driving data, thereby solving the problem of limited predicted destinations and achieving accurate prediction of the driving route of the vehicle itinerary.

[0131] Based on the same inventive concept as the above embodiments, refer to Figure 5 The vehicle journey determination device provided in the embodiment of the present application includes a destination detection module, a first path detection module, and a second path detection module, wherein:

[0132] The destination detection module is used to input the departure place parameters into the preset prediction model to generate the destination parameters;

[0133] A first path detection module, configured to determine a first vehicle trip based on the departure location parameter, the destination parameter and / or the historical travel data;

[0134] The second path detection module is used to determine a second vehicle trip based on the vehicle's traveled path and the historical travel data if the destination parameter is not generated within a preset time.

[0135] In one embodiment, the device further comprises a neural network training module, specifically configured to:

[0136] Detecting a destination associated with a departure parameter of the vehicle in historical travel data of the vehicle;

[0137] If the number of the same destination in the detected destination parameters is greater than or equal to a preset first threshold, using the travel data associated with the same destination in the historical driving data as a training sample;

[0138] The initial preset prediction model is trained based on the training samples.

[0139] In one embodiment, the neural network training module is specifically used to:

[0140] Inputting the trip endpoint information in the training sample into the embedding layer of the neural network model for vectorization processing;

[0141] Inputting the data output after processing by the embedding layer and the numerical features of the travel in the training sample into the hidden layer of the neural network model for feature fusion;

[0142] The data output after the hidden layer processing and the trip cross-features calculated by the linear regression model based on the trip numerical features are input into the output layer of the neural network to perform feature enhancement through the output layer.

[0143] In one implementation, the first path detection module is specifically configured to:

[0144] Determining at least one historical driving path corresponding to the departure location parameter and the destination parameter in the historical driving data of the vehicle;

[0145] The first similarity between the historical driving paths is detected, and the first vehicle trip is determined according to the first historical driving paths with the largest number; the first historical driving paths are historical driving paths whose first similarity exceeds a preset second threshold.

[0146] In one implementation, the second path detection module is specifically configured to:

[0147] Determining a second similarity between the traveled path of the vehicle and at least one historical travel path in the historical travel data;

[0148] The second vehicle trip is determined according to a second historical driving path with the highest similarity; the second historical driving path is a historical driving path with the second similarity exceeding a preset third threshold.

[0149] In one embodiment, the device further includes a reminder module, which is specifically configured to:

[0150] After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route;

[0151] According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested;

[0152] If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

[0153] The specific definition of the vehicle travel determination device can refer to the definition of the vehicle travel determination method above, which will not be repeated here. Each module in the above-mentioned vehicle travel determination device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0154] In summary, in the vehicle trip determination device provided by the above embodiment, the destination of the vehicle trip is determined by the destination detection module, the vehicle driving path is detected by the first path detection module when the trip destination is determined, and the vehicle driving path is detected by the second path detection module when the trip destination is uncertain. In this way, the destination of the vehicle trip is predicted according to the travel pattern of the owner, and then the driving path is recommended according to the historical driving data of the owner, so as to achieve accurate prediction of the driving path of the vehicle trip while solving the problem of limited predicted destinations.

[0155] Based on the same inventive concept as the above embodiments, an embodiment of the present invention provides an electronic device, such as Figure 6 As shown, the electronic device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 6 The processor 310 shown in the figure is not used to indicate that the number of the processor 310 is one, but is only used to indicate the positional relationship of the processor 310 relative to other devices. In actual applications, the number of the processor 310 may be one or more; similarly, Figure 6 The memory 311 shown in the figure has the same meaning, that is, it is only used to refer to the position relationship of the memory 311 relative to other devices. In practical applications, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the method for determining the vehicle range described above is implemented.

[0156] The electronic device may also include: at least one network interface 312. The various components in the electronic device are coupled together via a bus system 313. It is understood that the bus system 313 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 313 is not used in the following examples. Figure 6 Various buses are labeled as bus system 313.

[0157] The memory 311 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. The nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 311 described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable types of memories.

[0158] The memory 311 in the embodiment of the present invention is used to store various types of data to support the operation of the electronic device. Examples of these data include: any computer program used to operate on the electronic device, such as an operating system and an application; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application program may include various applications, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. Here, the program that implements the method of the embodiment of the present invention may be included in the application program.

[0159] Based on the same inventive concept as the above-mentioned embodiment, this embodiment further provides a computer-readable storage medium, in which a computer program is stored. The computer-readable storage medium may be a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it may also be various devices including one or any combination of the above-mentioned memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc. When the computer program stored in the computer-readable storage medium is executed by the processor, it is applied to the above-mentioned vehicle trip determination method. For the specific steps implemented when the computer program is executed by the processor, please refer to Figure 1 The description of the illustrated embodiment will not be repeated here.

[0160] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] In this document, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than those listed and may also include additional elements not expressly listed.

[0162] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for determining a vehicle travel distance, characterized in that: The method comprises: Input the departure place parameters into the preset prediction model to generate the destination parameters; Determining a first vehicle trip based on the departure location parameter, the destination parameter and / or the historical travel data; If the destination parameter is not generated within a preset time, a second vehicle trip is determined based on the vehicle's traveled path and the historical travel data.

2. The method according to claim 1, characterized in that The method further comprises a step of training the preset prediction model, wherein the training step comprises: Detecting a destination associated with a departure parameter of the vehicle in historical travel data of the vehicle; If the number of the same destination in the detected destination parameters is greater than or equal to a preset first threshold, using the travel data associated with the same destination in the historical driving data as a training sample; The initial preset prediction model is trained based on the training samples.

3. The method according to claim 2, characterized in that The preset prediction model includes a neural network model and a linear regression model; the training of the initial preset prediction model based on the training sample includes: Inputting the trip endpoint information in the training sample into the embedding layer of the neural network model for vectorization processing; Inputting the data output after processing by the embedding layer and the numerical features of the travel in the training sample into the hidden layer of the neural network model for feature fusion; The data output after the hidden layer processing and the trip cross-features calculated by the linear regression model based on the trip numerical features are input into the output layer of the neural network model to perform feature enhancement through the output layer.

4. The method according to claim 1, characterized in that: The determining of the first vehicle trip based on the departure location parameter, the destination parameter and / or the historical driving data comprises: Determining at least one historical driving path corresponding to the departure location parameter and the destination parameter in the historical driving data of the vehicle; The first similarity between the historical driving paths is detected, and the first vehicle trip is determined according to the first historical driving paths with the largest number; the first historical driving paths are historical driving paths whose first similarity exceeds a preset second threshold.

5. The method according to claim 1, characterized in that If the destination parameter is not generated within the preset time, determining a second vehicle trip based on the vehicle's traveled path and the historical travel data includes: Determining a second similarity between the traveled path of the vehicle and at least one historical travel path in the historical travel data; The second vehicle trip is determined according to a second historical driving path with the highest similarity; the second historical driving path is a historical driving path with the second similarity exceeding a preset third threshold.

6. The method according to claim 1, characterized in that The method further comprises: After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route; According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested; If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

7. A vehicle travel determination device, characterized in that: The device comprises: The destination detection module is used to input the departure place parameters into the preset prediction model to generate the destination parameters; A first path detection module, configured to determine a first vehicle trip based on the departure location parameter, the destination parameter and / or the historical travel data; The second path detection module is used to determine a second vehicle trip based on the vehicle's traveled path and the historical travel data if the destination parameter is not generated within a preset time.

8. The device according to claim 7, characterized in that The device also includes a reminder module, which is specifically used for: After determining the vehicle itinerary, the electronic map interface is called through the cloud to obtain the travel time of the route; According to the historical driving data, an average historical driving time corresponding to the vehicle journey is obtained, and the product of the average driving time and a preset parameter is used as a time threshold standard for determining whether the vehicle journey is congested; If the travel time of the travel route is greater than the time threshold standard, it is determined that there is congestion in the vehicle journey and a congestion reminder is issued.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the vehicle range determination method according to any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor, the vehicle range determination method according to any one of claims 1 to 6 is implemented.

Images