Vehicle commuting behavior prediction method, vehicle end controller and readable storage medium

Abstract

The invention provides a vehicle commuting behavior prediction method, a vehicle end controller and a readable storage medium, and the method comprises the steps: obtaining historical commuting place information, historical commuting path information and historical commuting behavior information, the historical commuting site information, the historical commuting path information and the historical commuting behavior information are all obtained based on historical data, provided by the controller end, of the vehicle in a workday; according to the historical commuting site information and the historical commuting path information, whether the current travel working condition of the vehicle is a commuting working condition is judged; and if yes, predicting a target commuting path of the vehicle according to the historical commuting path information, and predicting a target commuting behavior of the vehicle according to the target commuting path of the vehicle and the historical commuting behavior information. According to the invention, the historical commuting condition data of the controller end is counted, so that whether the current travel of the vehicle is the commuting condition or not can be accurately predicted, and the commuting behavior in the travel can be accurately predicted.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle commuting behavior prediction method, a vehicle-side controller and a readable storage medium. Background Art

[0002] With the acceleration of urbanization and the increase in traffic demand, the optimization of vehicle commuting conditions has become increasingly important. Traditional vehicle management systems usually rely on static data and empirical rules to predict traffic conditions and vehicle performance, but these methods are often insufficient in the face of complex and dynamic traffic environments. Accurate prediction of commuting conditions can not only improve the efficiency of traffic flow management, but also significantly improve vehicle fuel economy and reduce emissions.

[0003] At present, the mainstream technology for commuting condition prediction in the market is based on intelligent transportation system (ITS) and big data technology. Its implementation process is as follows: Figure 1 As shown in the figure, they use vehicle driving data, traffic flow information and environmental factors to collect data related to pre-analysis target tasks, convert the data into a format suitable for mining and analysis, extract feature data, and then complete the analysis and modeling through professional industry knowledge editing. Finally, through the characteristic test plan, the accuracy of the generated data mining model is evaluated, the model that passes the evaluation is applied to actual cases, and the model output results are compared and analyzed with the actual situation. Applying this closed-loop control process to commuting condition prediction can dynamically predict and optimize the vehicle's commuting condition, and achieve more accurate traffic management and resource allocation.

[0004] However, the construction of big data systems and ITS infrastructure requires high investment, and the high cost of hardware facilities and data management restricts the widespread application; moreover, signal interference or loss may occur during the data transmission process, resulting in uneven data quality, which may cause the data model to be unstable and affect the working condition prediction effect. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle commuting behavior prediction method, a vehicle-side controller and a readable storage medium. By statistically analyzing the historical commuting condition data on the controller side, it is not only possible to accurately predict whether the vehicle's current trip is a commuting condition, but also to accurately predict the commuting behavior in this trip, thereby improving the user experience.

[0006] To achieve the above object, the present invention provides a vehicle commuting behavior prediction method, comprising:

[0007] Acquire historical commuting location information, historical commuting path information, and historical commuting behavior information, wherein the historical commuting location information, historical commuting path information, and historical commuting behavior information are all obtained based on historical data of the vehicle on weekdays provided by the controller, wherein the historical commuting location information includes location information of each commuting location, the historical commuting path information includes commuting path information of each commuting location in different commuting time periods, and the historical commuting behavior information includes vehicle behavior information corresponding to each commuting path;

[0008] Determining whether the current travel condition of the vehicle is a commuting condition according to the historical commuting location information and the historical commuting route information;

[0009] If so, a target commuting route of the vehicle is predicted based on the historical commuting route information, and a target commuting behavior of the vehicle is predicted based on the target commuting route of the vehicle and the historical commuting behavior information.

[0010] Optionally, judging whether the current travel condition of the vehicle is a commuting condition according to the historical commuting location information and the historical commuting path information includes:

[0011] Determine whether the current day is a working day;

[0012] If so, determining whether the parking time of the vehicle is greater than or equal to a first preset time;

[0013] If so, determining whether the vehicle is currently located within the range of one of the commuting locations based on the current location information of the vehicle and the historical commuting location information;

[0014] If so, determining whether the current power-on time of the vehicle is within one of the commuting time periods based on the historical commuting route information;

[0015] If so, determining the total accumulated number of all commuting routes in the commuting time period corresponding to the current power-on time of the vehicle according to the historical commuting route information;

[0016] Determining whether the total accumulated number of all commuting routes in the commuting time period corresponding to the current power-on time of the vehicle is greater than a preset number;

[0017] If so, it is determined that the current travel condition of the vehicle is a commuting condition.

[0018] Optionally, the historical commuting location information is obtained through the following steps:

[0019] According to the historical data of vehicles on weekdays provided by the controller, the vehicle position that meets the preset parking point judgment conditions is used as the parking point;

[0020] Determine the commuting location according to the accumulated number of times and data update time corresponding to each of the parking points;

[0021] According to the location information of each of the commuting locations, historical commuting location information is obtained.

[0022] Optionally, the preset parking point determination conditions include: the vehicle has just been powered on, the parking time is greater than or equal to a first preset time, and the geographical location provided by the positioning system is valid.

[0023] Optionally, predicting a target commuting route of the vehicle according to the historical commuting route information includes:

[0024] Determining a current commuting location of the vehicle based on the current location of the vehicle;

[0025] Determining a current commuting time period of the vehicle according to a current power-on time of the vehicle;

[0026] Determining all commuting routes related to the current commuting location based on the historical commuting route information and the current commuting location of the vehicle;

[0027] A target commuting route of the vehicle is predicted according to the accumulated number of times of each commuting route associated with the current commuting location in the current commuting time period.

[0028] Optionally, predicting the target commuting route of the vehicle according to the accumulated number of times of each commuting route associated with the current commuting location in the current commuting time period includes:

[0029] For each commuting path related to the current commuting location, calculate the probability value corresponding to the commuting path according to the accumulated number of times the commuting path occurs in the current commuting time period and the updated weight coefficient;

[0030] The commuting route with the highest probability value is used as the target commuting route of the vehicle.

[0031] Optionally, the vehicle commuting behavior prediction method provided by the present invention further includes:

[0032] The historical commuting behavior information is updated according to the current commuting data.

[0033] Optionally, updating the historical commuting behavior information according to the current commuting data includes:

[0034] For each physical variable in the vehicle behavior information corresponding to the commuting path corresponding to the current commuting data, the updated data corresponding to the physical variable is calculated based on the historical data and current data corresponding to the physical variable, the cumulative number of times the commuting path is used in the corresponding commuting time period, and the updated weight coefficient.

[0035] Optionally, the target commuting behavior includes a target mileage, a target driving time, and a target maximum required power;

[0036] The vehicle commuting behavior prediction method provided by the present invention further includes:

[0037] If the target driving mileage is less than the preset driving mileage, the target driving duration is less than the second preset duration, and the target maximum required power is lower than the preset required power, the battery thermal management service of the vehicle is turned off.

[0038] In order to achieve the above-mentioned purpose, the present invention also provides a vehicle-side controller, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the vehicle commuting behavior prediction method described above is implemented.

[0039] In order to achieve the above-mentioned object, the present invention further provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the vehicle commuting behavior prediction method described above is implemented.

[0040] Compared with the prior art, the vehicle commuting behavior prediction method, vehicle-side controller and readable storage medium provided by the present invention have the following beneficial effects:

[0041] The vehicle commuting behavior prediction method provided by the present invention first obtains historical commuting location information, historical commuting path information and historical commuting behavior information obtained based on historical data of the vehicle on weekdays provided by the controller end, and then determines whether the current travel condition of the vehicle is a commuting condition based on the historical commuting location information and the historical commuting path information; if the current travel condition of the vehicle is a commuting condition, then predicts the target commuting path of the vehicle based on the historical commuting path information, and finally predicts the target commuting behavior of the vehicle based on the target commuting path of the vehicle and the historical commuting behavior information. Since the historical commuting location information, the historical commuting path information and the historical commuting behavior information are all obtained by statistics on the historical data of the vehicle on weekdays provided by the controller end, no additional hardware cost and maintenance cost are required, and it is easier to promote and apply. Moreover, since most of the transmission data provided by the controller end are collected through solid lines, the data quality can be guaranteed. In addition, since the amount of data on the controller end is small, data analysis and processing are relatively simple, and easier to understand and debug. In addition, the data on the controller side is more flexible, which can ensure that the final predicted target commuting behavior is more in line with the personalized driving habits of the driver of the vehicle. At the same time, the present invention can not only accurately predict whether the vehicle's current trip is a commuting condition, but also make accurate predictions on the commuting behavior during the trip, thereby improving the user experience.

[0042] Since the vehicle-side controller and the readable storage medium provided by the present invention belong to the same inventive concept as the vehicle commuting behavior prediction method provided by the present invention, the vehicle-side controller and the readable storage medium provided by the present invention at least have all the beneficial effects of the vehicle commuting behavior prediction method provided by the present invention. For details, please refer to the relevant description above, so the beneficial effects of the vehicle-side controller and the readable storage medium provided by the present invention will not be described one by one here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart for commuting traffic prediction based on intelligent transportation system and big data technology;

[0044] Figure 2 A flow chart of a vehicle commuting behavior prediction method provided by one embodiment of the present invention;

[0045] Figure 3 A flowchart for filling in a commuting location identification record form provided in one embodiment of the present invention;

[0046] Figure 4 A vehicle commuting route prediction flow chart provided in one embodiment of the present invention;

[0047] Figure 5 A schematic diagram of the block structure of a vehicle-side controller provided in accordance with one embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following is a further detailed description of the vehicle commuting behavior prediction method, vehicle-side controller and readable storage medium proposed in the present invention in combination with the accompanying drawings and specific embodiments. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose provided by the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the accompanying drawings. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention. Any structural modification, change in proportional relationship or adjustment of size, under the condition of being the same or similar to the effects that can be produced by the present invention and the purposes that can be achieved, should still fall within the scope of the technical content disclosed by the present invention.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" 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 other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The singular forms "a", "an" and "the" include plural objects, the term "or" is generally used in a sense including "and / or", the term "several" is generally used in a sense including "at least one", and the term "at least two" is generally used in a sense including "two or more". In addition, the terms "first", "second" and "third" are used for descriptive purposes only and are not to be understood as indicating or suggesting relative importance or implicitly indicating the number of the indicated technical features.

[0050] In addition, in the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0051] The core idea of ​​the present invention is to provide a vehicle commuting behavior prediction method, a vehicle-side controller and a readable storage medium. By statistically analyzing the historical commuting condition data on the controller side, it is not only possible to accurately predict whether the vehicle's current trip is a commuting condition, but also to accurately predict the commuting behavior in this trip, thereby improving the user experience.

[0052] It should be noted that the vehicle commuting behavior prediction method provided by the present invention can be applied to the vehicle-side controller provided by the present invention, and the vehicle-side controller can be applied to vehicles. The vehicles can include general motor vehicles, such as passenger vehicles including sport utility vehicles (SUVs), buses, trucks, and various commercial vehicles, and include hybrid vehicles, electric vehicles, plug-in hybrid vehicles, etc.

[0053] To realize the above idea, the present invention provides a vehicle commuting behavior prediction method, please refer to Figure 2 , which is a flow chart of a vehicle commuting behavior prediction method provided by one embodiment of the present invention. Figure 2 As shown, the vehicle commuting behavior prediction method provided by the present invention includes the following steps:

[0054] Step S100, obtaining historical commuting location information, historical commuting path information and historical commuting behavior information, wherein the historical commuting location information, historical commuting path information and historical commuting behavior information are all obtained based on the historical data of the vehicle on weekdays provided by the controller, wherein the historical commuting location information includes the location information of each commuting location, the historical commuting path information includes the commuting path information of each commuting location in different commuting time periods, and the historical commuting behavior information includes the vehicle behavior information corresponding to each commuting path.

[0055] Step S200: Determine whether the current travel condition of the vehicle is a commuting condition based on the historical commuting location information and the historical commuting route information.

[0056] If it is determined that the current travel condition of the vehicle is a commuting condition, step S300 and step S400 are executed.

[0057] Step S300: predicting a target commuting route of the vehicle based on the historical commuting route information.

[0058] Step S400: predicting a target commuting behavior of the vehicle according to the target commuting path of the vehicle and the historical commuting behavior information.

[0059] Since the historical commuting location information, the historical commuting path information, and the historical commuting behavior information are all obtained through statistics of the historical data of the vehicle provided by the controller on weekdays, there is no need for additional hardware cost and maintenance cost, and it is easier to promote and apply. Moreover, since the transmission data provided by the controller is mostly collected through solid lines, the data quality can be guaranteed. In addition, since the amount of data on the controller is small, the data analysis and processing are relatively simple, and easier to understand and debug. In addition, the data on the controller side is more flexible, which can ensure that the final predicted target commuting behavior is more in line with the personalized driving habits of the driver of this vehicle. At the same time, the present invention can not only accurately predict whether the vehicle's current trip is a commuting condition, but also make accurate predictions on the commuting behavior during this trip, thereby improving the user experience.

[0060] Specifically, the vehicle behavior information corresponding to the commuting path corresponding to the target commuting path in the historical commuting behavior information may be used as the target commuting behavior of the vehicle.

[0061] It should be noted that, as can be understood by those skilled in the art, the "commuting" referred to in this article refers to the process of commuting from the place of residence to the place of work, so it is necessary to first filter out the data belonging to the working day, that is, the data collection time must not be on weekends and holidays, that is, irregular non-working days overtime and adjustment are not considered. Further, the data collection time (year, month, day, hour, and minute) is unified into a count represented by minutes to facilitate later calculations and storage. It should be noted here that February in a leap year has 29 days. Holidays only include holidays with relatively fixed dates such as New Year's Day, Qingming Festival, May Day, and National Day. Taking into account that the adjustment dates of New Year's Day, Qingming Festival, and May Day are not fixed every year, in order to ensure the accuracy of the working day data, remove the data of all dates that may be covered by these three holidays (for example, remove the data of the two days before and after New Year's Day, January 1).

[0062] In some exemplary embodiments, the historical commuting location information is obtained by the following steps:

[0063] According to the historical data of vehicles on weekdays provided by the controller, the vehicle position that meets the preset parking point judgment conditions is used as the parking point;

[0064] Determine the commuting location according to the accumulated number of times and data update time corresponding to each of the parking points;

[0065] According to the location information of each of the commuting locations, historical commuting location information is obtained.

[0066] Specifically, according to the accumulated times and data update time corresponding to each parking point, the parking point with a larger accumulated times and a more recent data update time can be used as a commuting location.

[0067] In some exemplary embodiments, the preset parking point determination conditions include: the vehicle has just been powered on, the parking time is greater than or equal to the second preset time, and the geographical location provided by the positioning system is valid.

[0068] Therefore, by setting the preset parking point judgment condition to the vehicle just being powered on, the parking time being greater than or equal to the second preset time, and the geographical location provided by the positioning system being valid, the accuracy of the acquired historical commuting location information can be effectively guaranteed.

[0069] In some exemplary embodiments, a commuting location identification record table is used to record the historical commuting location information.

[0070] Therefore, by using a commuting location identification record table to record the historical commuting location information, it is easier to perform statistical analysis on the commuting locations.

[0071] Specifically, please refer to Table 1, which is a commuting location identification record table.

[0072] Table 1 Commute location identification record table

[0073]

[0074] As shown in Table 1, X in Table 1 represents longitude, Y represents latitude, Counter_total is the total cumulative number of times that the whole falls within the corresponding (X, Y) coordinate range. The range here represents a circle centered on the vehicle position (X, Y). The radius of the circle can be defined by the user, and any position point falling within this circle can be considered to be the same location. Time_last represents the update time, which is used for the reset strategy of subsequent data. Counter_last is used to record the daily cumulative number of times that the previous working day falls within the corresponding (X, Y) coordinate range. After it is determined to be a commuting path, the total cumulative number of the corresponding position array can be updated based on the daily cumulative number of the previous working day, that is, the corresponding Counter_total is updated to "Counter_total+Counter_last". It should be noted that, as can be understood by those skilled in the art, in order to ensure that the vehicle commuting behavior prediction method provided by the present invention can be run on a commonly used vehicle-mounted MCU (Microcontroller Unit) platform, the amount of stored data must match the chip storage space. If a data overflow error occurs, the storage capacity needs to be reduced for a specific hardware device, for example, this can be achieved by deleting the column data in Table 1 (commuting location identification record table).

[0075] Please continue to refer to Figure 3 , which is a flow chart for filling in a commuting location identification record table provided by one embodiment of the present invention. Figure 3As shown, if the vehicle position meets the preset parking point conditions, it is further determined whether there is a position array that has not been updated for a long time (i.e., the time interval between the update time and the current form filling time is greater than the preset time interval) in the formal data table area (i.e., the table area corresponding to the position array 1, position array 2, position array 3, and position array 4 in Table 2, which is used to record commuting locations). If there is a position array that has not been updated for a long time, the relevant data of the position array that has not been updated for a long time is deleted and replaced with the relevant data of the cache position array with the largest total cumulative number of times in the cache data table area (i.e., the table area corresponding to the cache position array 1, cache position array 2, cache position array 3, ... in Table 2, which is used to record temporary parking points), and the relevant data of the cache position array with the largest total cumulative number of times is deleted from the cache data table area. If there is no position array that has not been updated for a long time in the formal data table area, it is determined whether there is a position array in the formal data table area with a total cumulative number less than the total cumulative number of times in the cache data table area. If there is, the relevant data of the position array in the formal data table area with a total cumulative number less than the total cumulative number of times in the cache data table area is deleted and replaced with the relevant data of the cache position array in the cache data table area with the largest total cumulative number of times. If there is no position array in the formal data table area whose total cumulative number of times is less than the cumulative number of times in the cache data table area, then further determine whether the formal data table area is full; if the formal data table area is not full, then further determine whether the formal data table area is completely empty; if not, then further determine whether the vehicle position belongs to the position range corresponding to a certain position array in the formal data table area; if so, add 1 to the Counter_last of the corresponding position array (i.e., Counter_last+=1), and update the Time_last of the position array to this moment (i.e., Time_last=this moment); if the vehicle position does not belong to the position range corresponding to all the position arrays in the formal data table area, then fill the relevant data of the vehicle position into the empty position array in the formal data table area, and record the corresponding Counter_last as 1 (i.e., Counter_last=1), Counter_total as 0 (i.e., Counter_total=0), and Time_last as this moment (i.e., Time_last=this moment). If the official data table area is completely empty, the relevant data of the vehicle position will be filled into the position array 1 in the official data table area, and the corresponding Counter_last will be recorded as 1 (i.e. Counter_last=1), Counter_total will be recorded as 0 (i.e. Counter_total=0), and Time_last will be recorded as this moment (i.e. Time_last=this moment).If the formal data table area is full, it is further determined whether the cache data table area is full. If it is full, the relevant data of the cache position array in the cache data table area with the smallest total cumulative times or which has not been updated for a long time (i.e., the time interval between the update time and the current filling time is greater than the preset time interval) is deleted, and the relevant data of the vehicle position is filled into the cache position array. If the cache data table area is not full, it is further determined whether the cache data table area is completely empty. If so, the relevant data of the vehicle position is filled into the cache position array 1 in the cache data table area, and the corresponding Counter_last is recorded as 1 (i.e., Counter_last=1), Counter_total is recorded as 0 (i.e., Counter_total=0), and Time_last is recorded as this moment (i.e., Time_last=this moment). If the cache data table area is not completely empty, it is further determined whether the vehicle position belongs to the position range corresponding to a certain cache position array in the cache data table area. If so, the Counter_last of the corresponding cache position array is increased by 1 (i.e., Counter_last+=1), and the Time_last of the cache position array is updated to this moment (i.e., Time_last=this moment); if the vehicle position does not belong to the position range corresponding to all cache position arrays in the cache data table area, the relevant data of the vehicle position is filled into the empty cache position array in the cache data table area, and the corresponding Counter_last is recorded as 1 (i.e., Counter_last=1), Counter_total is recorded as 0 (i.e., Counter_total=0), and Time_last is recorded as this moment (i.e., Time_last=this moment).

[0076] It should be noted that, as can be understood by those skilled in the art, relatively frequent and recent parking spots in the commuting location identification record table may be used as commuting locations.

[0077] In some exemplary embodiments, a commuting route identification record table is used to record the historical commuting route information.

[0078] Therefore, by using a commuting path identification record table to record the historical commuting path information, it is easier to perform statistical analysis on the commuting path.

[0079] Specifically, please refer to Table 2, which is a commuting path identification record table.

[0080] Table 2 Commute route identification record table

[0081]

[0082] After determining the commuting location based on the commuting location identification record table shown in Table 1, the next step is to perform statistics on the paths between the two commuting locations (the commonly used paths between the various commuting locations can be identified based on the historical single-trip travel data). As shown in Table 2, commuting path 1, commuting path 2, commuting path 3, and commuting path 4 are pre-defined paths with a relatively high number of occurrences formed by connecting the commuting locations in pairs. For example, the path between commuting location 1 and commuting location 2 is defined as commuting path 1, and other paths with relatively low occurrences are recorded in other paths. It should be noted that commuting location 1→commuting location 2 and commuting location 2→commuting location 1 are both defined as commuting path 1, that is, the order of starting and ending points is not considered. The commuting time period in Table 2 represents the starting time period of the commuting path. Since the commuting at different times may be inconsistent for the same commuting location, it needs to be considered separately. Further, as shown in Table 2, each commuting path records the number of times (cumulative number) that the departure time (starting time) belongs to different commuting time periods and the time when this commuting path last appeared. If the number of times other commuting paths appear (cumulative number of times) exceeds that of a defined commuting path (commuting path 1, commuting path 2, commuting path 3 or commuting path 4), or a defined commuting path (commuting path 1, commuting path 2, commuting path 3 or commuting path 4) has not appeared for a long time, the relevant data of the defined commuting path (commuting path 1, commuting path 2, commuting path 3 or commuting path 4) will be cleared. It should be noted that, as can be understood by those skilled in the art, when the commuting location data (i.e., the relevant data of location array 1, location array 2, location array 3, location array 4) in Table 1 (commuting location identification record table) is changed, the data in Table 2 (commuting path identification record table) must also be cleared and recorded again.

[0083] In some exemplary implementations, judging whether the current travel condition of the vehicle is a commuting condition based on the historical commuting location information and the historical commuting path information includes:

[0084] Determine whether the current day is a working day;

[0085] If so, determining whether the parking time of the vehicle is greater than or equal to a first preset time;

[0086] If so, determining whether the vehicle is currently located within the range of one of the commuting locations based on the current location information of the vehicle and the historical commuting location information;

[0087] If so, determining whether the current power-on time of the vehicle is within one of the commuting time periods based on the historical commuting route information;

[0088] If so, determining the total accumulated number of all commuting routes in the commuting time period corresponding to the current power-on time of the vehicle according to the historical commuting route information;

[0089] Determining whether the total accumulated number of all commuting routes in the commuting time period corresponding to the current power-on time of the vehicle is greater than a preset number;

[0090] If so, it is determined that the current travel condition of the vehicle is a commuting condition.

[0091] Therefore, the current travel condition of the vehicle is determined to be a commuting condition only when the vehicle position is within the range of one of the commuting locations, the current power-on time of the vehicle is within one of the commuting time periods, and the total accumulated number of all commuting paths in the commuting time period corresponding to the current power-on time of the vehicle is greater than the preset number, thereby effectively ensuring the accuracy of the vehicle commuting behavior prediction method provided by the present invention.

[0092] Please continue to refer to Figure 4 , which is a vehicle commuting route prediction flow chart provided by one embodiment of the present invention. Figure 4 As shown, if the day is a non-working day, the current travel condition of the vehicle is determined to be a non-commuting condition; if the parking time of the vehicle is less than a first preset time, the current travel condition of the vehicle is determined to be a non-commuting condition; if the vehicle is not currently located within the range of one of the commuting locations, the current travel condition of the vehicle is determined to be a non-commuting condition; if the current power-on time of the vehicle is not within one of the commuting time periods, the current travel condition of the vehicle is determined to be a non-commuting condition; if the total accumulated number of all commuting paths in the commuting time period corresponding to the current power-on time of the vehicle is less than or equal to the preset number, the current travel condition of the vehicle is determined to be a non-commuting condition.

[0093] In some exemplary embodiments, predicting the target commuting route of the vehicle based on the historical commuting route information includes:

[0094] Determining a current commuting location of the vehicle based on the current location of the vehicle;

[0095] Determining a current commuting time period of the vehicle according to a current power-on time of the vehicle;

[0096] Determining all commuting routes related to the current commuting location based on the historical commuting route information and the current commuting location of the vehicle;

[0097] A target commuting route of the vehicle is predicted according to the accumulated number of times of each commuting route associated with the current commuting location in the current commuting time period.

[0098] Therefore, by predicting the target commuting path of the vehicle based on the cumulative number of commuting paths related to the current commuting location during the current commuting time period, the accuracy of the predicted target commuting path of the vehicle can be effectively guaranteed, thereby further improving the accuracy of the vehicle commuting behavior prediction method provided by the present invention.

[0099] In some exemplary embodiments, predicting the target commuting path of the vehicle according to the accumulated number of times of each commuting path associated with the current commuting location in the current commuting time period includes:

[0100] For each commuting path related to the current commuting location, calculate the probability value corresponding to the commuting path according to the accumulated number of times the commuting path occurs in the current commuting time period and the updated weight coefficient;

[0101] The commuting route with the highest probability value is used as the target commuting route of the vehicle.

[0102] Therefore, by taking the commuting path with the highest probability value corresponding to the current commuting time period among all commuting paths related to the current commuting location as the target commuting path of the vehicle, the accuracy of the predicted target commuting path of the vehicle can be further effectively guaranteed, thereby further improving the accuracy of the vehicle commuting behavior prediction method provided by the present invention.

[0103] Specifically, for each commuting path related to the current commuting location, the probability value corresponding to the commuting path can be calculated based on the following formula:

[0104]

[0105] Among them, P i represents the probability value corresponding to the i-th commuting path related to the current commuting location; w i represents the updated weight coefficient corresponding to the i-th commuting path related to the current commuting location, which is related to the time interval between the last occurrence time (last update time) and the current time. The longer the time interval, the larger the update weight coefficient w i The smaller; C i represents the cumulative number of the i-th commuting path related to the current commuting location in the current commuting time period; w j represents the updated weight coefficient corresponding to the jth commuting path related to the current commuting location, which is related to the time interval between the last occurrence time (last update time) and the current time. The longer the time interval, the larger the update weight coefficient w j The smaller; C jrepresents the cumulative number of the j-th commuting path related to the current commuting location in the current commuting time period; n represents the total number of commuting paths related to the current commuting location.

[0106] In some exemplary embodiments, the vehicle commuting behavior prediction method provided by the present invention further includes:

[0107] The historical commuting behavior information is updated according to the current commuting data.

[0108] Therefore, by updating the historical commuting behavior information according to the current commuting data, it can be effectively ensured that the target commuting behavior predicted next time is more in line with the personalized driving habits of the driver of the vehicle.

[0109] In some exemplary implementations, a commuting behavior record table is used to record the historical commuting behavior information.

[0110] Therefore, by using a commuting behavior record table to record the historical commuting behavior information, it is easier to perform statistical analysis on the commuting behavior.

[0111] Specifically, please refer to Table 3, which is a commuting behavior record table.

[0112] Table 3 Commuting behavior record

[0113]

[0114] As can be seen from Table 3, the vehicle behavior information corresponding to each commuting route includes multiple physical variables, such as mileage, battery SOC consumption (battery SOC change), driving time, battery temperature rise rate, maximum required power, driving mode ratio, etc.

[0115] It should be noted that after determining the target commuting route, the target commuting behavior of the vehicle can be predicted by looking up Table 3, that is, the data of various physical variables corresponding to the target commuting route in Table 3 are output as predicted values.

[0116] In some exemplary implementations, updating the historical commuting behavior information according to the current commuting data includes:

[0117] For each physical variable in the vehicle behavior information corresponding to the commuting path corresponding to the current commuting data, the updated data corresponding to the physical variable is calculated based on the historical data and current data corresponding to the physical variable, the cumulative number of times the commuting path is used in the corresponding commuting time period, and the updated weight coefficient.

[0118] Specifically, for each physical variable (driving mileage, battery SOC consumption, driving time, battery temperature rise rate, maximum required power, driving mode ratio, etc.), the updated data corresponding to the physical variable can be calculated according to the following formula:

[0119]

[0120] Among them, X(k) represents the historical data corresponding to the physical variable (data before update), X(k+1) represents the updated data corresponding to the physical variable, Xnew represents the current data corresponding to the physical variable, a is the update weight coefficient corresponding to the physical variable, which is related to the time interval between the last update time and the current update time. The longer the time interval, the larger the update weight coefficient, and counter represents the cumulative number of times this commuting path is in the corresponding commuting time period (the commuting time period corresponding to the current commuting data).

[0121] It should be noted that every time new data needs to be updated in Table 3, it is possible to consider calculating the variance of all relevant physical variables under the commuting path to be updated. The larger the variance, the greater the difference between the statistical values, that is, the less regular the presented data. When the variance of a physical variable is greater than the preset threshold, it can be considered that the data of this physical variable has no reference item, and the predicted value of this physical variable will no longer be output until the variance of this physical variable is less than or equal to the preset threshold again.

[0122] In some exemplary implementations, the target commuting behavior includes a target driving mileage, a target driving time, and a target maximum required power.

[0123] The vehicle commuting behavior prediction method provided by the present invention further includes:

[0124] If the target mileage is less than the preset mileage and the target maximum required power is lower than the preset required power, the battery thermal management service of the vehicle is turned off.

[0125] Therefore, by shutting down the battery thermal management service of the vehicle when the target mileage is less than the preset mileage and the target maximum required power is lower than the preset required power, energy loss caused by short-term heating and cooling can be avoided, thereby achieving energy-saving effects.

[0126] Based on the same inventive concept, the present invention also provides a vehicle-side controller, please refer to Figure 5 , which is a block diagram of a vehicle-side controller provided by an embodiment of the present invention. Figure 5As shown, the vehicle-side controller includes a processor 101 and a memory 103, and a computer program is stored in the memory 103. When the computer program is executed by the processor 101, the vehicle commuting behavior prediction method described above is implemented. Since the vehicle-side controller provided by the present invention and the vehicle commuting behavior prediction method provided by the present invention belong to the same inventive concept, the vehicle-side controller provided by the present invention at least has all the beneficial effects of the vehicle commuting behavior prediction method provided by the present invention. For details, please refer to the relevant description above, so the beneficial effects of the vehicle-side controller provided by the present invention will not be repeated here.

[0127] like Figure 5 As shown, the vehicle-side controller also includes a communication interface 102 and a communication bus 104, wherein the processor 101, the communication interface 102, and the memory 103 communicate with each other through the communication bus 104. The communication bus 104 includes but is not limited to a CAN bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface 102 is used for communication between the above-mentioned vehicle-side controller and other vehicle controllers. The communication bus 104 connects the above-mentioned vehicle-side controller and other scattered nodes such as other vehicle controllers into a closed-loop system, so that each controller can communicate and transmit data in multiple working states (parking state, charging state, starting state, running state, vehicle forward and backward state, feedback braking state, mechanical braking state, general fault state, major fault state), thereby realizing the control function of the vehicle.

[0128] The processor 101 referred to in the present invention may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 101 is the control center of the vehicle-side controller, and various interfaces and lines are used to connect various parts of the entire vehicle-side controller.

[0129] The memory 103 can be used to store the computer program, and the processor 101 implements various functions of the vehicle-side controller by running or executing the computer program stored in the memory 103 and calling the data stored in the memory 103. The memory 103 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable memory (PROM), electrically programmable memory (EPROM), electrically erasable programmable memory (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, random access memory is available in a variety of forms, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous random access memory (SDRAM), double data rate synchronous random access memory (DDRSDRAM), enhanced synchronous random access memory (ESDRAM), synchronous link (Synchlink) dynamic random access memory (SLDRAM), memory bus (Rambus) direct random access memory (RDRAM), direct memory bus dynamic random access memory (DRDRAM), and memory bus dynamic random access memory (RDRAM), etc.

[0130] The present invention also provides a readable storage medium, wherein a computer program is stored in the readable storage medium, and when the computer program is executed by a processor, the vehicle commuting behavior prediction method described above can be implemented. Since the readable storage medium provided by the present invention and the vehicle commuting behavior prediction method provided by the present invention belong to the same inventive concept, the readable storage medium provided by the present invention at least has all the beneficial effects of the vehicle commuting behavior prediction method provided by the present invention. For details, please refer to the relevant description above, so the beneficial effects of the readable storage medium provided by the present invention will not be repeated here.

[0131] Specifically, the readable storage medium provided by the present invention can adopt any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared or semiconductor, or any combination of the above. More specific examples (non-exhaustive enumeration) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer hard disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this article, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0132] Further, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0133] In summary, compared with the prior art, the vehicle commuting behavior prediction method, vehicle-side controller and readable storage medium provided by the present invention have the following beneficial effects:

[0134] The present invention first obtains the historical commuting location information, historical commuting path information and historical commuting behavior information obtained based on the historical data of the vehicle on weekdays provided by the controller end, and then determines whether the current travel condition of the vehicle is a commuting condition based on the historical commuting location information and the historical commuting path information; if the current travel condition of the vehicle is a commuting condition, then predict the target commuting path of the vehicle based on the historical commuting path information, and finally predict the target commuting behavior of the vehicle based on the target commuting path of the vehicle and the historical commuting behavior information. Since the historical commuting location information, the historical commuting path information and the historical commuting behavior information are all obtained by statistics on the historical data of the vehicle on weekdays provided by the controller end, no additional hardware cost and maintenance cost are required, and it is easier to promote and apply. Moreover, since the transmission data provided by the controller end is mostly collected through solid lines, the data quality can be guaranteed. In addition, since the amount of data on the controller end is small, the data analysis and processing are relatively simple, and it is easier to understand and debug. In addition, the data on the controller end is more flexible, which can ensure that the target commuting behavior finally predicted is more in line with the personalized driving habits of the driver of the vehicle. At the same time, the present invention can not only accurately predict whether the vehicle's current trip is a commuting condition, but also make an accurate prediction of the commuting behavior during the trip, thereby improving the user experience.

[0135] It should be noted that the computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network-including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0136] It should be noted that the devices and methods disclosed in the embodiments of this article can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of this article. In this regard, each box in the flowchart or block diagram can represent a module, a part of a program or a code, and the module, a part of a program segment or a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented by a dedicated hardware-based system for performing a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0137] It should also be noted that the above description is only a description of the preferred embodiment of the present invention, and is not any limitation on the scope of the present invention. Any changes and modifications made by a person skilled in the art in the field of the present invention based on the above disclosure are within the scope of protection of the present invention. Obviously, a person skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle commuting behavior prediction method, characterized in that: include: Obtaining historical commuting location information, historical commuting route information, and historical commuting behavior information, wherein the historical commuting location information, historical commuting route information, and historical commuting behavior information are all obtained based on historical data of the vehicle on weekdays provided by the controller, wherein the historical commuting location information includes location information of each commuting location, the historical commuting route information includes commuting route information of each commuting location in different commuting time periods, and the historical commuting behavior information includes vehicle behavior information corresponding to each commuting route; Determining whether the current travel condition of the vehicle is a commuting condition based on the historical commuting location information and the historical commuting route information; If so, a target commuting route of the vehicle is predicted based on the historical commuting route information, and a target commuting behavior of the vehicle is predicted based on the target commuting route of the vehicle and the historical commuting behavior information.

2. The vehicle commuting behavior prediction method according to claim 1, characterized in that: The determining, based on the historical commuting location information and the historical commuting route information, whether the current travel condition of the vehicle is a commuting condition includes: Determine whether the current day is a working day; If so, determining whether the parking time of the vehicle is greater than or equal to a first preset time; If so, determining whether the vehicle is currently located within the range of one of the commuting locations based on the current location information of the vehicle and the historical commuting location information; If so, determining whether the current power-on time of the vehicle is within one of the commuting time periods based on the historical commuting route information; If yes, determining the total accumulated number of all commuting routes in the commuting time period corresponding to the current power-on time of the vehicle according to the historical commuting route information; Determining whether a total accumulated number of times of all commuting routes in a commuting time period corresponding to the current power-on time of the vehicle is greater than a preset number; If so, it is determined that the current travel condition of the vehicle is a commuting condition.

3. The vehicle commuting behavior prediction method according to claim 1, characterized in that: The historical commuting location information is obtained by the following steps: Based on the historical data of vehicles on weekdays provided by the controller, the vehicle position that meets the preset parking point judgment conditions is used as the parking point; Determine the commuting location based on the accumulated number of times and data update time corresponding to each of the parking points; According to the location information of each commuting location, historical commuting location information is obtained.

4. The vehicle commuting behavior prediction method according to claim 3, characterized in that: The preset parking point determination conditions include: the vehicle has just been powered on, the parking time is greater than or equal to a first preset time, and the geographical location provided by the positioning system is valid.

5. The vehicle commuting behavior prediction method according to claim 1, characterized in that: The predicting the target commuting route of the vehicle based on the historical commuting route information includes: determining a current commuting location of the vehicle based on the current location of the vehicle; determining a current commuting time period of the vehicle according to a current power-on time of the vehicle; determining all commuting routes related to the current commuting location based on the historical commuting route information and the current commuting location of the vehicle; A target commuting route of the vehicle is predicted based on the accumulated number of times each commuting route associated with the current commuting location is used during the current commuting time period.

6. The vehicle commuting behavior prediction method according to claim 5, characterized in that: The predicting the target commuting route of the vehicle according to the accumulated number of times each commuting route associated with the current commuting location is used in the current commuting time period includes: For each commuting path associated with the current commuting location, calculate a probability value corresponding to the commuting path based on the cumulative number of times the commuting path occurs during the current commuting time period and an updated weight coefficient; The commuting route with the highest probability value is used as the target commuting route of the vehicle.

7. The vehicle commuting behavior prediction method according to claim 1, characterized in that: The method further comprises: The historical commuting behavior information is updated according to the current commuting data.

8. The vehicle commuting behavior prediction method according to claim 7, characterized in that: The updating of the historical commuting behavior information according to the current commuting data includes: For each physical variable in the vehicle behavior information corresponding to the commuting path corresponding to the current commuting data, the updated data corresponding to the physical variable is calculated based on the historical data and current data corresponding to the physical variable, the cumulative number of times the commuting path is used in the corresponding commuting time period, and the updated weight coefficient.

9. The vehicle commuting behavior prediction method according to claim 1, characterized in that: The target commuting behavior includes a target mileage, a target driving time, and a target maximum required power; The method further comprises: If the target driving mileage is less than the preset driving mileage, the target driving duration is less than the second preset duration, and the target maximum required power is lower than the preset required power, the battery thermal management service of the vehicle is turned off.

10. A vehicle-side controller, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the vehicle commuting behavior prediction method according to any one of claims 1 to 9 is implemented.

11. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle commuting behavior prediction method according to any one of claims 1 to 9 is implemented.

Images