Travel behavior prediction method and device, vehicle and storage medium

Abstract

The invention relates to a travel behavior prediction method and device, a vehicle and a storage medium, and relates to the field of data analysis. The method comprises the following steps: acquiring travel initial data and a travel prediction probability model of a vehicle; the travel initial data comprises various types of theme data; the travel prediction probability model is used for representing the probability of at least one travel behavior corresponding to the subject data set; the subject data set is used for representing combinations of various types of subject data; and determining a travel behavior prediction result based on the travel initial data and the travel prediction probability model. Therefore, the accuracy of behavior prediction of a single trip of the user can be improved, the current demand of the user can be accurately identified, the potential demand of the user can be mined, and the personalized demand can be better met.

Description

Technical Field

[0001] The present application relates to the field of data analysis, and specifically to a travel behavior prediction method, device, vehicle and storage medium. Background Art

[0002] Nowadays, the number of cars on the road is increasing. In order to adapt to the ever-changing needs and technological innovations, it is often necessary to accurately understand the user's driving behavior each time by predicting the user's single trip behavior, so as to more accurately identify the user's explicit needs and tap into the user's potential needs, so that the vehicle can be equipped with more functions that adapt to the user's actual usage needs, making it smarter and more considerate.

[0003] Existing travel behavior prediction methods mainly rely on historical data and simple statistical models. Although they can provide some useful information to a certain extent, these methods still have problems such as a single data source, insufficient prediction accuracy and lack of personalized analysis.

[0004] Therefore, a travel behavior prediction method is needed to improve the accuracy and real-time performance of the prediction and better meet the personalized needs of users. Summary of the Invention

[0005] This application provides a travel behavior prediction method, device, vehicle, and storage medium to solve the technical problem of inaccurate identification of user driving needs. The technical solution of this application is as follows:

[0006] According to the first aspect provided by the present application, a travel behavior prediction method is provided, including: obtaining a vehicle's trip start data and a travel prediction probability model; the trip start data includes multiple types of subject data; the travel prediction probability model is used to characterize the probability of at least one travel behavior corresponding to the subject data set; the subject data set is used to characterize the combination of various types of subject data; based on the trip start data and the travel prediction probability model, a travel behavior prediction result is determined.

[0007] Based on the above technical means, the travel behavior prediction method provided by this application obtains a vehicle's trip start data and a travel prediction probability model; then, based on the trip start data and the travel prediction probability model, determines a travel behavior prediction result. This allows for rapid and accurate prediction of user travel behavior using limited computing resources.

[0008] In one possible embodiment, the above method further includes: obtaining historical travel data of the vehicle; the historical travel data includes: historical trip start data and actual travel behavior data; the historical travel data includes multiple types of subject data; based on the historical trip start data, constructing a travel behavior possibility matrix; the possibility matrix includes a possibility set of travel behaviors corresponding to the subject data set; based on the possibility set and the actual travel behavior data, determining a travel prediction probability model.

[0009] Based on the above technical means, the travel behavior prediction method provided in this application obtains historical travel data of a vehicle; the historical travel data includes historical trip start data and actual travel behavior data; constructs a travel behavior possibility matrix based on the historical trip start data; and determines a travel prediction probability model based on the possibility set and the actual travel behavior data. Based on this, a travel prediction probability model can be accurately determined based on the vehicle's historical travel data.

[0010] In one possible approach, a travel prediction probability model is determined based on a possibility set and actual travel behavior data, including: splitting historical travel data into multiple single historical travel data; determining the probability of each travel behavior in the possibility set corresponding to the subject data set based on each single historical travel data and the possibility matrix; and determining a travel prediction probability model based on the probability of each travel behavior in the possibility set.

[0011] Based on the above technical means, the travel behavior prediction method provided in this application breaks down historical travel data into multiple single-trip historical trip data sets; based on each single-trip historical trip data set and a probability matrix, the probability of each travel behavior in the possibility set corresponding to the subject data set is determined; and based on the probability of each travel behavior in the possibility set, a travel prediction probability model is determined. Based on this, the probability of each travel behavior in the possibility set corresponding to the subject data set can be obtained based on the historical travel data for each single trip, thereby comprehensively and accurately determining the travel prediction probability model.

[0012] In one possible approach, the probability of each travel behavior in the possibility set corresponding to each subject data set is determined based on each single historical trip data and the possibility matrix, including: determining the possibility set corresponding to each single historical trip based on the subject data set and the possibility matrix included in each single historical trip data; determining the actual travel behavior of each single historical trip based on the starting location and the end location of the trip included in each single historical trip data; for any subject data set, determining the probability of each travel behavior in the possibility set corresponding to each subject data set based on the ratio of the number of each actual travel behavior in the possibility set corresponding to the subject data set.

[0013] Based on the above technical means, the travel behavior prediction method provided by this application determines the possibility set corresponding to each single historical trip based on the theme data set and possibility matrix included in each single historical trip data; determines the actual travel behavior of each single historical trip based on the trip starting location and trip ending location included in each single historical trip data; and for any theme data set, determines the probability of each travel behavior in the possibility set corresponding to each theme data set based on the proportion of the number of each actual travel behavior in the possibility set corresponding to the theme data set. Based on this, the probability of each travel behavior can be more accurately determined based on the vehicle's historical travel data.

[0014] In one possible manner, the subject data includes one or more of: a trip start time, a trip start location, a trip start weather, whether it is a weekday, whether it is a holiday, and a navigation destination.

[0015] In one possible embodiment, the historical travel data further includes at least one of a driving speed, a charging state, and a charging mode; the charging mode is used to characterize the type of charging pile used for charging; the type includes a public type and a private type;

[0016] The historical travel data is split into multiple single historical travel data, including: determining the time boundary of the single historical travel based on at least one of the driving speed, the charging status and the charging mode; and splitting the historical travel data into multiple single historical travel data based on the time boundary.

[0017] Based on the above technical means, the travel behavior prediction method provided by this application determines the time boundary of a single historical trip based on at least one of the vehicle speed, charging status, and charging mode; and splits the historical travel data into multiple single historical trip data based on the time boundary. In this way, the historical travel data can be accurately split into single historical trip data.

[0018] According to a second aspect of the present application, a travel behavior prediction device is provided. The device includes a first acquisition unit configured to acquire vehicle trip start data and a travel prediction probability model; the trip start data includes multiple types of topic data; the travel prediction probability model is configured to represent the probability of at least one travel behavior corresponding to a topic dataset; and the topic dataset is configured to represent a combination of the various types of topic data. A first determination unit is configured to determine a travel behavior prediction result based on the trip start data and the travel prediction probability model.

[0019] In one possible embodiment, the travel behavior prediction device further includes: a second acquisition unit configured to acquire historical travel data of a vehicle; the historical travel data includes historical trip start data and actual travel behavior data; and the historical travel data includes multiple types of topic data. A construction unit configured to construct a travel behavior probability matrix based on the historical trip start data; the probability matrix includes a set of travel behavior possibilities corresponding to the topic data set. A second determination unit configured to determine a travel prediction probability model based on the set of possibilities and the actual travel behavior data.

[0020] In one possible approach, the second determination unit is specifically used to split the historical travel data into multiple single historical travel data; determine the probability of each travel behavior in the possibility set corresponding to the subject data set based on each single historical travel data and the possibility matrix; and determine the travel prediction probability model based on the probability of each travel behavior in the possibility set.

[0021] In one possible manner, the second determination unit is specifically used to determine the possibility set corresponding to each single historical trip based on the subject data set and the possibility matrix included in each single historical trip data; determine the actual travel behavior of each single historical trip based on the starting position and the end position of the trip included in each single historical trip data; for any subject data set, determine the probability of each travel behavior in the possibility set corresponding to each subject data set based on the ratio of the number of each actual travel behavior in the possibility set corresponding to the subject data set.

[0022] In one possible manner, the subject data includes one or more of: a trip start time, a trip start location, a trip start weather, whether it is a weekday, whether it is a holiday, and a navigation destination.

[0023] In one possible approach, the historical travel data also includes at least one of vehicle speed, charging status, and charging mode; the charging mode is used to identify the type of charging station used for charging, including public and private types. The second determination unit is further specifically configured to determine the time boundary of a single historical trip based on at least one of the vehicle speed, charging status, and charging mode; and to split the historical travel data into multiple single historical trip data based on the time boundary.

[0024] According to the third aspect provided by the present application, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of an electronic device, the electronic device is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0026] According to the fifth aspect provided by the present application, a computer program product is provided, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation method thereof.

[0027] Therefore, the above technical features of this application have the following beneficial effects:

[0028] (1) By obtaining the vehicle's trip start data and the travel prediction probability model, the travel behavior prediction results are determined based on the trip start data and the travel prediction probability model. Based on this, the user's travel behavior can be predicted quickly and accurately using limited computing resources.

[0029] (2) By obtaining the historical travel data of the vehicle; the historical travel data includes historical trip start data and actual travel behavior data; based on the historical trip start data, a travel behavior possibility matrix is constructed; based on the possibility set and the actual travel behavior data, a travel prediction probability model is determined. Based on this, a travel prediction probability model can be accurately determined based on the historical travel data of the vehicle.

[0030] (3) By splitting the historical travel data into multiple single historical travel data, the probability of each travel behavior in the possibility set corresponding to the subject data set is determined based on each single historical travel data and the probability matrix. Based on the probability of each travel behavior in the possibility set, a travel prediction probability model is determined. Based on this, the probability of each travel behavior in the possibility set corresponding to the subject data set can be obtained based on the historical travel data of each single trip, thereby comprehensively and accurately determining the travel prediction probability model.

[0031] (4) Based on the subject data set and the probability matrix included in each single historical trip data, the probability set corresponding to each single historical trip is determined; based on the starting and ending locations of each single historical trip data, the actual travel behavior of each single historical trip is determined; for any subject data set, based on the proportion of the number of actual travel behaviors in the possibility set corresponding to the subject data set, the probability of each travel behavior in the possibility set corresponding to each subject data set is determined. Based on this, the probability of each travel behavior can be determined more accurately based on the vehicle's historical travel data.

[0032] (5) Determine the time boundary of a single historical trip based on at least one of the vehicle speed, the charging state, and the charging mode; and split the historical trip data into multiple single historical trip data based on the time boundary. In this way, the historical trip data can be accurately split into single historical trip data.

[0033] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0036] Figure 1 is a schematic structural diagram of a vehicle according to an exemplary embodiment;

[0037] Figure 2 is a flow chart illustrating a method for predicting travel behavior according to an exemplary embodiment;

[0038] Figure 3 This is a schematic diagram of a process for constructing a travel prediction probability model according to an exemplary embodiment;

[0039] Figure 4 is a schematic diagram showing a possibility matrix according to an exemplary embodiment;

[0040] Figure 5 is a schematic diagram of a process for determining a travel prediction probability model according to an exemplary embodiment;

[0041] Figure 6 is a block diagram of a travel behavior prediction device according to an exemplary embodiment;

[0042] Figure 7 The figure is a block diagram of an electronic device in a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] In order to enable ordinary people in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0044] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0045] In the embodiments of this application, words such as "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0046] The data involved in this application may be data authorized by the user or fully authorized by all parties.

[0047] As car ownership continues to grow, software-defined cars are becoming increasingly important. Through highly integrated electrical and electronic architectures, advanced software platforms, and powerful computing capabilities, vehicles can dynamically adjust their functions and services to adapt to changing needs and technological innovations. All functions, services, and even specific algorithms must be based on the automaker's understanding of the user. Predicting user behavior during individual trips is crucial. Accurately understanding each user's driving behavior allows for more precise identification of explicit needs and exploration of potential needs, enabling vehicles to be equipped with more features tailored to actual user needs, making them smarter and more personalized.

[0048] Existing travel behavior prediction methods mainly rely on historical data and simple statistical models. Although they can provide some useful information to a certain extent, these methods have the following problems:

[0049] 1. Single data source: Relying only on limited data sources such as GPS tracks, it cannot fully reflect people’s travel needs.

[0050] 2. Insufficient prediction accuracy: Traditional statistical models react slowly to emergencies (such as severe weather) and have weak predictive capabilities.

[0051] 3. Lack of personalized analysis: Existing methods often use the uniform behavior of cars to predict individual behavior, ignoring the differences between models and users, resulting in inaccurate prediction results.

[0052] To address the above issues, the present invention proposes a travel behavior prediction method, device, vehicle, and storage medium. This method obtains a vehicle's trip start data and a travel prediction probability model. The trip start data includes multiple types of topic data. The travel prediction probability model is used to characterize the probability of at least one travel behavior corresponding to the topic dataset. The topic dataset is used to characterize the combination of various types of topic data. Based on the trip start data and the travel prediction probability model, a travel behavior prediction result is determined. This method aims to improve the accuracy and real-time performance of travel behavior predictions and better meet personalized needs.

[0053] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0054] Figure 1 The figure is a schematic structural diagram of a vehicle according to an exemplary embodiment.

[0055] The travel behavior prediction method provided in the embodiment of the present application can be applied to a vehicle 100. A vehicle may also be referred to as a vehicle, a mobile carrier, an electric vehicle (EV), a hybrid electric vehicle (HEV), a plug-in hybrid electric vehicle (PHEV), a fuel cell vehicle (FCV), an autonomous vehicle, an intelligent and connected vehicle (ICV), a driverless vehicle, etc.

[0056] In the embodiments of the present application, the vehicle 100 may be a sedan, a sport utility vehicle (SUV), a truck, an electric vehicle, a motorcycle, a tricycle, a special vehicle (such as an ambulance, fire truck, police car, etc.), a driverless taxi, a smart connected bus, an autonomous logistics vehicle, an electric truck, etc. Furthermore, the method is also applicable to various special vehicles, such as agricultural vehicles, mining vehicles, forestry vehicles, airport vehicles, and port vehicles. This application does not impose any specific restrictions on this.

[0057] For ease of understanding, the travel behavior prediction method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0058] Figure 2 FIG. 1 is a flow chart of a travel behavior prediction method according to an exemplary embodiment. Figure 2 As shown, the travel behavior prediction method includes the following steps:

[0059] S201. Obtain the vehicle's trip start data and travel prediction probability model; the trip start data includes multiple types of subject data; the travel prediction probability model is used to characterize the probability of at least one travel behavior corresponding to the subject data set; the subject data set is used to characterize the combination of various types of subject data.

[0060] In a possible implementation, the theme data includes one or more of: a trip start time, a trip start location, a trip start weather, whether it is a weekday, whether it is a holiday, and a navigation destination.

[0061] In some embodiments, real-time data of the vehicle at the start of the trip is obtained, and the real-time data is processed to obtain trip start data. The trip start data includes the start time of the vehicle's trip, the starting location, the weather of the trip, and whether the trip is a weekday or a holiday.

[0062] For example, the vehicle's trip occurs on a weekday, the weather is sunny, the trip starts at 8:00 am, and the starting point is home.

[0063] In some embodiments, the vehicle's trip start data can be obtained through a sensor module, which may include a vehicle speed sensor, a battery voltage sensor, a battery current sensor, an ambient temperature sensor, a charging state sensor, and the like.

[0064] In some embodiments, a travel prediction probability model is obtained, wherein the travel prediction probability model includes the probability of travel behavior corresponding to the combination of various subject data. The method of constructing the travel prediction probability model is described in detail below and is not repeated here.

[0065] S202: Determine a travel behavior prediction result based on the trip start data and the travel prediction probability model.

[0066] In some embodiments, the trip start time, starting location, whether it is a statutory holiday, whether it is a weekday, and the weather conditions at the start of the trip, as contained in the vehicle's trip start data, are substituted into a travel prediction probability model to obtain the probability of each travel behavior in the trip start data. Based on the probability of each travel behavior in the trip start data, the travel behavior with the highest probability is selected as the travel behavior prediction result for the current trip.

[0067] For example, the starting data for this trip contains the following travel behaviors: commuting to work (normal), picking up children from school, and other. The probability of each travel behavior is 60%, 30%, and 10%, respectively. The travel behavior with the highest probability, commuting to work (normal), is selected as the predicted travel behavior for this trip.

[0068] based on Figure 2 The technical solution shown in this application provides a travel behavior prediction method that obtains vehicle trip start data and a travel prediction probability model. The trip start data includes multiple types of subject data. The travel prediction probability model is used to represent the probability of at least one travel behavior corresponding to the subject data set. In this way, people's travel needs can be comprehensively and accurately reflected using multiple types of data. Based on the trip start data and the travel prediction probability model, travel behavior prediction results are determined. Based on this, user travel behavior can be quickly and accurately predicted using limited computing resources.

[0069] The following is a detailed description of how to construct a travel prediction probability model.

[0070] In one possible implementation, historical travel data of a vehicle is obtained; the historical travel data includes: historical trip start data and actual travel behavior data; the historical travel data includes multiple types of subject data; based on the historical trip start data, a travel behavior possibility matrix is constructed; the possibility matrix includes a possibility set of travel behaviors corresponding to the subject data set; based on the possibility set and the actual travel behavior data, a travel prediction probability model is determined.

[0071] It is understandable that various types of subject data included in the historical travel data of a vehicle can be stored in the cloud, and when the subject data is needed, it can be directly obtained from the cloud.

[0072] In one embodiment, Figure 3 As shown in FIG, a flow chart of a method for constructing a travel prediction probability model provided by this application is shown in S301-S303:

[0073] S301. Acquire historical travel data of the vehicle, where the historical travel data includes historical trip start data and actual travel behavior data; the historical travel data includes various types of subject data.

[0074] In some embodiments, the vehicle's historical trip start data includes the vehicle's starting data for a single trip, such as the vehicle's trip start time, trip start location, trip start weather, whether it was a statutory holiday, whether it was a weekday, etc. First, it is necessary to determine a complete trip of the vehicle. Specifically, based on the vehicle's speed, the time boundaries of the single trip are determined. The time boundaries include the single trip start time and the single trip end time. The single trip is determined based on the single trip start time and the single trip end time.

[0075] For example, at a certain moment, if the vehicle speed changes from zero to non-zero, and the speed remains zero for the five minutes before the change, the time at which the speed changes from zero to non-zero is recorded as the start time of the single trip. If the vehicle speed changes from zero to non-zero, and the speed remains non-zero for the five minutes before the change, the current trip is combined with the previous trip and considered a continuation of the previous trip. If the vehicle speed changes from non-zero to zero and remains zero for more than five minutes, the time at which the speed changes from non-zero to zero is recorded as the end time of the single trip. Based on the start time and end time of the single trip, a completed single trip is determined.

[0076] Next, based on the vehicle's positioning information and the aforementioned trip start time, the starting location of the trip is determined. The trip start weather is determined based on the starting location and the trip start time. Specifically, the vehicle's location at the trip start time is recorded as the trip start location, and the weather at the trip start time is recorded as the trip start weather. Heavy rain, torrential rain, hail, blowing snow, heavy snow, and snowstorms are categorized as inclement weather, while other weather conditions are categorized as other weather conditions.

[0077] The start time of a single trip is grouped according to whether it is a statutory holiday. For non-statutory holidays, it is grouped according to whether it is a working day. Monday to Friday excluding statutory holidays and working days after statutory holidays are considered working days; Saturday and Sunday excluding statutory holidays and working days after non-statutory holidays are considered non-working days.

[0078] In this way, the basic data of the vehicle's historical trip start data is classified according to different types to obtain different types of subject data.

[0079] In some embodiments, the actual travel behavior data of the vehicle includes the actual travel purpose of the vehicle.

[0080] In this embodiment of the present application, the specific location information of the vehicle can be determined based on the starting and ending locations of multiple trips of the vehicle, combined with the start and end times of a single trip of the vehicle. For example, the specific location information of the vehicle can be represented as home, work, or other.

[0081] For example, for multiple single trips, the first single trip of the day is determined based on the departure time of the single trips. The starting locations of the multiple first single trips of the day are obtained, and the location information of these trips is clustered. The location information represented by the largest number of clusters is "home".

[0082] For example, the trip with the longest interval between the end time of the previous trip and the start time of the next trip is obtained. If the interval is greater than 240 minutes, the number of trips that meet this condition and fall into the cluster range of the above cluster is counted, and the location information corresponding to the trip with the largest number is considered to be "company".

[0083] Exemplarily, the vehicle's single charging process information is obtained, and based on the battery charging mode and positioning signal, the vehicle's single charging fast / slow charging mode and charging location information are extracted to determine whether the charging location is a public charging pile or a private charging pile.

[0084] Exemplarily, the navigation data of the vehicle is obtained, and the point of interest (POI) corresponding to the navigation end position is taken as the user's navigation destination; the relationship between the navigation destination and the current actual position of the vehicle is determined. If the navigation destination and the current actual position are not in the same urban area, the navigation destination is out of town, otherwise the navigation destination is local.

[0085] S302: Construct a travel behavior possibility matrix based on historical trip start data; the possibility matrix includes a set of travel behavior possibilities corresponding to the subject data set.

[0086] In some embodiments, based on the user's daily driving needs, single trips are divided into commuting and daily life activities. Commuting activities are categorized as: commuting to work (normal), commuting to work (late), commuting home (normal), commuting home (overtime), and shopping after get off work. Daily life activities are categorized as: picking up children from school, picking up children from school, working overtime on statutory holidays, emergency trips, daily weekend trips, and going out on statutory holidays.

[0087] Figure 4 is a schematic diagram showing a possibility matrix according to an exemplary embodiment, such as Figure 4 As shown in , the possibility matrix is used to represent the possibility set of travel behaviors corresponding to different topic data sets.

[0088] The following describes how to construct a travel behavior probability matrix based on historical trip start data.

[0089] First, determine whether the date of the single trip is a working day. If the date of the single trip is a non-working day, determine the weather at the start of the trip. If it is inclement weather, the trip is considered an emergency trip.

[0090] If the weather is other, determine whether the trip's start time is a statutory holiday. If it is, determine the navigation destination. If the destination is out of town, then the trip is considered a long-distance trip on a statutory holiday. If it is not a statutory holiday and the destination is local, then the trip is considered a regular weekend trip or a statutory holiday trip.

[0091] Secondly, when the date of a single trip is a weekday, the start time of the single trip is grouped as follows:

[0092] When the starting time of a single trip is between 7:00 and 9:00 and the starting location is "home", then the travel behavior is commuting to the company (normal), picking up children from school or other.

[0093] When the starting time of a single trip is between 9:00 and 12:00 and the starting location of the trip is "home", then the travel behavior is commuting to the company (late) or other.

[0094] When the starting time of a single trip is between 12:00 and 17:00, the trip is considered a temporary trip.

[0095] If the starting time of a single trip is between 16:00 and 19:00 and the starting point is "school", then the trip is for picking up children from school or other purposes.

[0096] When the starting time of a single trip is between 17:00 and 19:00 and the starting location of the trip is "company", then the travel behavior is commuting home (normal), shopping after get off work or other.

[0097] If the starting time of a single trip is between 19:00 and 23:59 and the starting location is "company", then the travel behavior is commuting home (overtime) or other.

[0098] S303: Determine a travel prediction probability model based on the possibility set and actual travel behavior data.

[0099] In some embodiments, a possibility set is obtained, and the possibility set is used to characterize the likelihood of travel behavior corresponding to each subject data set. A travel prediction probability model is determined in combination with the actual travel behavior data of the vehicle.

[0100] Specifically, such as Figure 5 As shown in FIG, a flow chart of determining a travel prediction probability model provided by this application is provided. The determination method of the model is shown in S501-S503:

[0101] S501: Determine a possibility set corresponding to each single historical trip based on the subject data set and the possibility matrix included in each single historical trip data.

[0102] In one possible implementation, the historical travel data also includes at least one of vehicle speed, charging status, and charging mode. The charging mode indicates the type of charging station used, including public and private types. Based on at least one of the vehicle speed, charging status, and charging mode, the time boundary of a single historical trip is determined; and based on the time boundary, the historical travel data is split into multiple single historical trip data.

[0103] In some embodiments, based on the topic data sets included in the plurality of single historical travel data, a possibility set of corresponding travel behaviors in the possibility matrix under different types of topic data is obtained.

[0104] S502: Determine the actual travel behavior of each single historical trip based on the starting location and the ending location of each single historical trip included in the data of each single historical trip.

[0105] In some embodiments, the user's actual travel behavior is sorted out based on the user's single trip starting location and single trip ending location, as shown in Table 1, which is a classification table of actual travel behavior based on the single trip starting location and single trip ending location:

[0106] Table 1

[0107] Starting point of a single trip Single stroke end position Actual travel behavior Home company Commuting to work company Home Commuting home company Supermarket / shopping mall After get off work shopping Home School Pick up and drop off children at school School Home Pick up children from school Home Out of town Long-distance travel during statutory holidays

[0108] S503 : For any theme data set, based on the ratio of the number of actual travel behaviors in the possibility set corresponding to the theme data set, determine the probability of each travel behavior in the possibility set corresponding to each theme data set.

[0109] In some embodiments, for any thematic data set, based on the proportion of the number of actual travel behaviors in the possibility set corresponding to the thematic data set in the possibility set, and taking the sum of the probabilities of each travel behavior in each thematic data set as 100%, the possibility probability of each travel behavior in the possibility set corresponding to each thematic data set is determined.

[0110] For example, let's assume that the trip takes place on a weekday, the weather is clear, the trip starts at 8:00 am, and the starting point is home. The actual travel behaviors in the possibility set corresponding to this thematic dataset are commuting to the company (normal), picking up children from school, and other. The number of times these actual travel behaviors appear in the possibility set is 60, 30, and 10, respectively. Then, based on the proportion of the number of times each actual travel behavior appears in the possibility set, it is the probability of these actual travel behaviors. That is, the probability of each actual travel behavior in the possibility set corresponding to this thematic dataset is: commuting to the company (normal) 60%, picking up children from school 30%, and other 10%.

[0111] In some embodiments, a travel prediction probability model is determined based on the likelihood probability of each travel behavior under each topic data.

[0112] based on Figure 3 This technical solution constructs a travel behavior probability matrix based on historical vehicle travel data. Then, based on the set of travel behavior possibilities corresponding to the subject dataset in the probability matrix and combined with real travel behavior data, a travel prediction probability model is developed. This allows for a comprehensive and accurate travel prediction probability model to be established based on historical vehicle travel data.

[0113] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, the travel behavior prediction device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] In the embodiments of the present application, the travel behavior prediction device or electronic device can be divided into functional modules according to the above method. For example, the travel behavior prediction device or electronic device can include functional modules corresponding to the functional divisions, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0115] Figure 6FIG. 1 is a block diagram of a travel behavior prediction device according to an exemplary embodiment. Figure 6 The travel behavior prediction device includes a first acquisition unit 601, a first determination unit 602, a second acquisition unit 603, a construction unit 604, and a second determination unit 605.

[0116] The first acquisition unit 601 is used to obtain the vehicle's trip start data and travel prediction probability model; the trip start data includes multiple types of topic data; the travel prediction probability model is used to characterize the probability of at least one travel behavior corresponding to the topic data set; the topic data set is used to characterize the combination of various types of topic data.

[0117] The first determining unit 602 is configured to determine a travel behavior prediction result based on the trip start data and the travel prediction probability model.

[0118] In one possible approach, the second acquisition unit 603 is configured to acquire historical travel data for the vehicle. The historical travel data includes historical trip start data and actual travel behavior data, and the historical travel data includes multiple types of topic data. The construction unit 604 is configured to construct a travel behavior probability matrix based on the historical trip start data. The probability matrix includes a set of travel behavior possibilities corresponding to the topic dataset. The second determination unit 605 is configured to determine a travel prediction probability model based on the possibility set and the actual travel behavior data.

[0119] In one possible method, the second determination unit 605 is specifically used to split the historical travel data into multiple single historical travel data; determine the probability of each travel behavior in the possibility set corresponding to the subject data set based on each single historical travel data and the possibility matrix; and determine the travel prediction probability model based on the probability of each travel behavior in the possibility set.

[0120] In one possible manner, the second determination unit 605 is specifically used to determine the possibility set corresponding to each single historical trip based on the subject data set and the possibility matrix included in each single historical trip data; determine the actual travel behavior of each single historical trip based on the starting position and the end position of the trip included in each single historical trip data; for any subject data set, determine the probability of each travel behavior in the possibility set corresponding to each subject data set based on the ratio of the number of each actual travel behavior in the possibility set corresponding to the subject data set.

[0121] In one possible manner, the subject data includes one or more of: a trip start time, a trip start location, a trip start weather, whether it is a weekday, whether it is a holiday, and a navigation destination.

[0122] In one possible approach, the historical travel data also includes at least one of vehicle speed, charging status, and charging mode; the charging mode is used to indicate the type of charging station used for charging, which includes public and private types. The second determining unit 605 is further specifically configured to determine the time boundary of a single historical trip based on at least one of the vehicle speed, charging status, and charging mode; and to split the historical travel data into multiple single historical trip data based on the time boundary.

[0123] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0124] Figure 7 FIG. 1 is a block diagram of an electronic device in a vehicle according to an exemplary embodiment. Figure 7 As shown, the electronic devices in the vehicle include but are not limited to: a processor 701 and a memory 702 .

[0125] The memory 702 is configured to store executable instructions of the processor 701. It is understood that the processor 701 is configured to execute instructions to implement the travel behavior prediction method in the above embodiment.

[0126] It should be noted that those skilled in the art can understand that Figure 7 The electronic device structure shown in the figure does not limit the electronic device, and the electronic device may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0127] The processor 701 is the control center of the electronic device. It uses various interfaces and lines to connect the various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 702 and calling data stored in the memory 702, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly handles wireless communications. It is understood that the above-mentioned modem processor may not be integrated into the processor 701.

[0128] The memory 702 can be used to store software programs and various data. The memory 702 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and application programs required by at least one functional module (such as a determination unit, a processing unit, etc.). Furthermore, the memory 702 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0129] In an exemplary embodiment, a computer-readable storage medium including instructions is further provided, such as a memory 702 including instructions. The above instructions can be executed by a processor 701 of an electronic device to implement the travel behavior prediction method in the above embodiment.

[0130] In actual implementation, Figure 6 The functions of the first acquisition unit 601, the first determination unit 602, the second acquisition unit 603, the construction unit 604, and the second determination unit 605 can all be accomplished by Figure 7 The processor 701 in the embodiment calls the computer program stored in the memory 702. The specific execution process can be referred to the description of the method part in the above embodiment, which will not be repeated here.

[0131] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0132] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by the processor 701 of the electronic device to complete the travel behavior prediction method in the above embodiment.

[0133] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0134] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0136] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0137] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0139] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A travel behavior prediction method, characterized in that: Applied to vehicles, including: Obtaining trip start data and a travel prediction probability model for a vehicle; the trip start data includes multiple types of subject data; the travel prediction probability model is used to represent the probability of at least one travel behavior corresponding to the subject data set; the subject data set is used to represent a combination of various types of subject data; A travel behavior prediction result is determined based on the trip start data and the travel prediction probability model.

2. The method according to claim 1, characterized in that The method further comprises: Acquire historical travel data of the vehicle; the historical travel data includes: historical trip start data and actual travel behavior data; the historical travel data includes multiple types of subject data; Based on the historical trip start data, a travel behavior possibility matrix is constructed; the possibility matrix includes a set of travel behavior possibilities corresponding to the subject data set; The travel prediction probability model is determined based on the possibility set and the actual travel behavior data.

3. The method according to claim 2, characterized in that The determining of the travel prediction probability model based on the possibility set and the actual travel behavior data includes: Splitting the historical travel data into multiple single historical travel data; Determining the probability of each travel behavior in the possibility set corresponding to each subject data set based on each of the single historical travel data and the possibility matrix; The travel prediction probability model is determined based on the probability of each travel behavior in the possibility set.

4. The method according to claim 3, characterized in that The determining, based on each of the single historical travel data and the possibility matrix, the probability of each travel behavior in the possibility set corresponding to each of the subject data sets includes: Determining a possibility set corresponding to each single historical trip based on the subject data set included in each single historical trip data and the possibility matrix; Determining the actual travel behavior of each of the single historical trips based on the trip starting location and the trip ending location included in the data of each single historical trip; For any of the subject data sets, the probability of each travel behavior in the possibility set corresponding to each subject data set is determined based on the ratio of the number of times of each actual travel behavior in the possibility set corresponding to the subject data set.

5. The method according to any one of claims 1 to 4, characterized in that The subject data includes one or more of: a journey start time, a journey start location, a journey start weather, whether it is a weekday, whether it is a holiday, and a navigation destination.

6. The method according to claim 3 or 4, characterized in that The historical travel data also includes at least one of the vehicle speed, charging status and charging mode; the charging mode is used to characterize the type of charging pile used for charging; The types include public types and private types; The step of splitting the historical travel data into multiple single historical travel data includes: determining a time boundary of a single historical trip based on at least one of the vehicle speed, the charging state, and the charging mode; The historical travel data is split into multiple single historical travel data based on the time boundary.

7. A travel behavior prediction device, characterized in that: The device comprises: A first acquisition unit is configured to acquire trip start data and a travel prediction probability model for a vehicle; the trip start data includes multiple types of subject data; the travel prediction probability model is configured to represent the probability of at least one travel behavior corresponding to a subject data set; and the subject data set is configured to represent a combination of various types of subject data; The first determining unit is configured to determine a travel behavior prediction result based on the trip start data and the travel prediction probability model.

8. The device according to claim 7, characterized in that The device further comprises: A second acquisition unit is configured to acquire historical travel data of the vehicle; the historical travel data includes historical trip start data and actual travel behavior data; the historical travel data includes multiple types of subject data; A construction unit, configured to construct a travel behavior possibility matrix based on the historical trip start data; the possibility matrix includes a set of travel behavior possibilities corresponding to the subject data set; The second determining unit is used to determine the travel prediction probability model based on the possibility set and the actual travel behavior data.

9. A vehicle, characterized in that: The vehicle comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the travel behavior prediction method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method according to any one of claims 1 to 6.

Images