CN111016908B

CN111016908B - Vehicle driving position determining method and device, storage medium and electronic equipment

Info

Publication number: CN111016908B
Application number: CN201911319340.XA
Authority: CN
Inventors: 杨强
Original assignee: Neusoft Corp
Current assignee: Neusoft Corp
Priority date: 2019-12-19
Filing date: 2019-12-19
Publication date: 2021-04-02
Anticipated expiration: 2039-12-19
Also published as: CN111016908A

Abstract

The disclosure relates to a vehicle driving position determining method, a vehicle driving position determining device, a storage medium and electronic equipment, and aims to solve the problem of inaccurate positioning of a vehicle positioning device in the related art. The method comprises the following steps: determining target position information of the vehicle according to first historical track information of the vehicle corresponding to a first target sampling moment, wherein the target position information comprises a position where the vehicle is to arrive at a second target sampling moment, and the second target sampling moment is a plurality of continuous sampling moments taking the next sampling moment of the first target sampling moment as a time starting point; determining whether the vehicle is in a steering state or not according to the first historical track information and the target position information; and if the vehicle is determined to be in the steering state, replacing the positions of the positioning device of the vehicle at the second target sampling moments with the positions to be reached by the vehicle at the second target sampling moments in the target position information to determine the running position of the vehicle at the second target sampling moments.

Description

Vehicle driving position determining method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of vehicles, and in particular, to a method and an apparatus for determining a driving position of a vehicle, a storage medium, and an electronic device.

Background

Currently, in the application system of the internet of vehicles, displaying the position of the vehicle in real time at the monitoring center is the most common function. This function is usually accomplished by adding a positioning device to the OBD interface of the vehicle to upload the vehicle's driving position to the monitoring center. However, the accuracy of the driving position obtained in most cases is low due to the cost and performance of the added positioning device. Since the driving position acquired by the positioning device is calculated from the previous driving position, when the vehicle turns, the inertial drift of the positioning device may cause positioning deviation, resulting in positioning error, for example, the driving position acquired by the positioning device is still on the road before turning after the vehicle turns. In addition, the driving position located by the locating device usually needs to be displayed, the locating deviation can cause sudden jump when the driving position of the vehicle is displayed, the error is very obvious, and if the number of vehicles is large, the jump of the display position can greatly influence the user experience.

Disclosure of Invention

The invention aims to provide a vehicle driving position determining method, a vehicle driving position determining device, a storage medium and electronic equipment so as to improve vehicle positioning accuracy.

In order to achieve the above object, according to a first aspect of the present disclosure, there is provided a vehicle travel position determination method including:

determining target position information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling time, wherein the first historical track information comprises a historical driving position passed by the vehicle to the first target sampling time, the target position information comprises a position to be reached by the vehicle at a second target sampling time, and the second target sampling time is a plurality of continuous sampling times taking the next sampling time of the first target sampling time as a time starting point;

determining whether the vehicle is in a steering state according to the first historical track information and the target position information;

and if the vehicle is determined to be in the steering state, replacing the positions to be reached by the vehicle at the second target sampling moments with the positions to be reached by the positioning device of the vehicle at the second target sampling moments in the target position information to determine the driving position of the vehicle at the second target sampling moments.

Optionally, the determining the target position information of the vehicle according to the first historical track information of the vehicle corresponding to the first target sampling time includes:

determining a target position determination model matched with the first historical track information from the stored plurality of position determination models;

inputting the first historical track information into the target position determination model to obtain the target position information output by the target position determination model.

Optionally, each said position determination model corresponds to a probability of occurrence of that model in a historical driving of said vehicle;

the determining a target location determination model matching the first historical trajectory information from the stored plurality of location determination models includes:

respectively determining the mean square error of each position determination model according to the first historical track information;

for each position determination model, determining the ratio of the mean square error of the position determination model to the occurrence probability of the position determination model in the historical driving of the vehicle as the model error of the position determination model;

and determining the position determination model with the minimum model error as the target position determination model.

Optionally, the plurality of location determination models are determined by:

acquiring stored second historical track information corresponding to the vehicle, wherein each second historical track information comprises a corresponding historical driving position of the vehicle in a historical driving process;

clustering the second historical track information to obtain a clustering result, wherein the clustering result comprises track categories and second historical track information under each track category;

and respectively taking each track type as a target track type, and training the long-time memory network model by using target track information to obtain a position determination model corresponding to the target track type, wherein the target track information is second historical track information under the target track type.

Optionally, the second target sampling time is a preset number of sampling times with a next sampling time of the first target sampling time as a time starting point;

the training of the long-time and short-time memory network model by using the target track information to obtain the position determination model corresponding to the target track category comprises the following steps:

and training a long-term memory network model by taking a part of the target track information as input data and taking a preset number of historical driving positions of the input data behind the target track information as output data to obtain a position determination model corresponding to the target track type.

Optionally, the determining whether the vehicle is in a steering state according to the first historical track information and the target position information includes:

determining a first driving direction of the vehicle at the first target sampling moment according to the first historical track information;

determining a second driving direction of the vehicle according to the driving position of the vehicle at a first target sampling moment and a position to be reached at a next sampling moment corresponding to the first target sampling moment in the target position information;

if the included angle between the first driving direction and the second driving direction is larger than a preset angle threshold value, determining that the vehicle is in a steering state;

and if the included angle between the first driving direction and the second driving direction is smaller than or equal to the preset angle threshold value, determining that the vehicle is not in a steering state.

Optionally, if it is determined that the vehicle is in the steering state, the method further includes:

and taking the latest sampling time in the second target sampling times as a new first target sampling time, and repeatedly executing the steps of determining the target position information of the vehicle according to the first historical track information of the vehicle corresponding to the first target sampling time, determining whether the vehicle is in a steering state according to the first historical track information and the target position information, and if the vehicle is determined to be in the steering state, replacing the position to be reached by the vehicle at each second target sampling time in the target position information with the position collected by a positioning device of the vehicle at each second target sampling time so as to determine the running position of the vehicle at each second target sampling time.

Optionally, the method further comprises:

if the vehicle is determined not to be in the steering state, determining the running position of the vehicle at the next sampling moment of the first target sampling moment according to the position information acquired by the positioning device of the vehicle; and

and taking the next sampling time of the first target sampling time as a new first target sampling time, and repeatedly executing the steps of determining the target position information of the vehicle according to the first historical track information of the vehicle corresponding to the first target sampling time, determining whether the vehicle is in a steering state according to the first historical track information and the target position information, and if the vehicle is determined to be in the steering state, replacing the position to be reached by the vehicle at each second target sampling time in the target position information with the position collected by a positioning device of the vehicle at each second target sampling time to determine the running position of the vehicle at each second target sampling time.

Optionally, the method further comprises:

determining a display position corresponding to a target driving position according to the target driving position of the vehicle, wherein the target driving position is one of the driving positions determined in the driving process of the vehicle;

generating target display information according to the sampling time corresponding to the target driving position and the display position corresponding to the target driving position;

and displaying the target display information.

According to a second aspect of the present disclosure, there is provided a vehicle travel position determination apparatus, the apparatus including:

the vehicle position detection device comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining target position information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling time, the first historical track information comprises historical driving positions passed by the vehicle to the first target sampling time, the target position information comprises positions to be reached by the vehicle at a second target sampling time, and the second target sampling time is a plurality of continuous sampling times with the next sampling time of the first target sampling time as a time starting point;

the second determining module is used for determining whether the vehicle is in a steering state or not according to the first historical track information and the target position information;

and if the vehicle is determined to be in the steering state, replacing the positions to be reached by the vehicle at the second target sampling moments with the positions to be reached by the positioning device of the vehicle at the second target sampling moments in the target position information to determine the running position of the vehicle at the second target sampling moments.

Optionally, the first determining module includes:

the first determining submodule is used for determining a target position determining model matched with the first historical track information from the stored position determining models;

and the second determining submodule is used for inputting the first historical track information into the target position determining model so as to obtain the target position information output by the target position determining model.

the first determination submodule includes:

the third determining submodule is used for respectively determining the mean square error of each position determining model according to the first historical track information;

a fourth determination submodule for determining, for each of the position determination models, a ratio of a mean square error of the position determination model to an occurrence probability of the position determination model in the historical driving of the vehicle as a model error of the position determination model;

and a fifth determining submodule for determining the position determination model with the minimum model error as the target position determination model.

Optionally, the apparatus is configured to determine a plurality of location determination models by:

the acquisition module is used for acquiring stored second historical track information corresponding to the vehicle, and each second historical track information comprises a corresponding historical driving position of the vehicle in one historical driving process;

the clustering module is used for clustering the second historical track information to obtain a clustering result, and the clustering result comprises track categories and second historical track information under each track category;

and the training module is used for respectively taking each track type as a target track type and training the long-time memory network model by using target track information to obtain a position determination model corresponding to the target track type, wherein the target track information is second historical track information under the target track type.

the training module is used for training a long-time memory network model by taking a part of the target track information as input data and taking a preset number of historical driving positions of the input data behind the target track information as output data so as to obtain a position determination model corresponding to the target track type.

Optionally, the second determining module includes:

a sixth determining submodule, configured to determine, according to the first historical trajectory information, a first traveling direction of the vehicle at the first target sampling time;

a seventh determining submodule, configured to determine a second driving direction of the vehicle according to a driving position of the vehicle at a first target sampling time and a position to be reached at a next sampling time corresponding to the first target sampling time in the target position information;

the first judgment submodule is used for determining that the vehicle is in a steering state if an included angle between the first driving direction and the second driving direction is larger than a preset angle threshold value;

and the second judgment submodule is used for determining that the vehicle is not in a steering state if an included angle between the first driving direction and the second driving direction is smaller than or equal to the preset angle threshold.

Optionally, if it is determined that the vehicle is in the turning state, the device is further configured to use a latest sampling time of the second target sampling times as a new first target sampling time, and return to the first determining module, the second determining module, and the processing module, to repeatedly execute the first historical track information corresponding to the first target sampling time according to the vehicle, determine the target position information of the vehicle, and determining whether the vehicle is in a turning state based on the first historical trajectory information and the target position information, and if the vehicle is determined to be in the steering state, replacing the positions to be reached by the vehicle at the second target sampling moments with the positions to be collected by the positioning device of the vehicle at the second target sampling moments in the target position information to determine the driving position of the vehicle at the second target sampling moments.

Optionally, the apparatus further comprises:

the third determining module is used for determining the running position of the vehicle at the next sampling time of the first target sampling time according to the position information acquired by the positioning device of the vehicle if the vehicle is determined not to be in the steering state; and

the device is further used for taking the next sampling time of the first target sampling time as a new first target sampling time, the second determining module repeatedly executes the first historical track information corresponding to the first target sampling time according to the vehicle, determines the target position information of the vehicle, determines whether the vehicle is in a steering state according to the first historical track information and the target position information, and if the vehicle is determined to be in the steering state, replaces the position to be reached by the vehicle at each second target sampling time in the target position information with the position collected by the positioning device of the vehicle at each second target sampling time so as to determine the running position of the vehicle at each second target sampling time.

Optionally, the apparatus further comprises:

the fourth determination module is used for determining a display position corresponding to the target running position according to the target running position of the vehicle, wherein the target running position is one of the running positions determined in the running process of the vehicle;

the information generating module is used for generating target display information according to the sampling time corresponding to the target driving position and the display position corresponding to the target driving position;

and the display module is used for displaying the target display information.

According to a third aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect of the present disclosure.

According to a fourth aspect of the present disclosure, there is provided an electronic device comprising:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to implement the steps of the method of the first aspect of the disclosure.

According to the technical scheme, the target position information of the vehicle is determined according to the first historical track information of the vehicle corresponding to the first target sampling time, whether the vehicle is in a steering state is determined according to the first historical track information and the target position information, and if the vehicle is determined to be in the steering state, the position to be reached by the vehicle at each second target sampling time in the target position information is used for replacing the position collected by the positioning device of the vehicle at each second target sampling time, so that the running position of the vehicle at each second target sampling time is determined. Therefore, in the vehicle running process, the position which can be reached by the vehicle subsequently is predicted based on the running position of the vehicle which can be obtained, and when the vehicle is identified to be in a steering state, the position which is obtained by prediction is used for replacing the position which is actually acquired by the vehicle positioning device so as to determine the running position of the vehicle.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows.

Drawings

The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:

FIG. 1 is a schematic view showing a road network matching method before and after correcting a driving position;

FIG. 2 is a flow chart of a vehicle driving location determination method provided according to one embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating an exemplary step of determining target location information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling time in a vehicle driving location determination method according to the present disclosure;

FIG. 4 is a block diagram of a vehicle travel position determination device provided in accordance with one embodiment of the present disclosure;

FIG. 5 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;

FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.

Currently, in the application system of the internet of vehicles, displaying the position of the vehicle in real time at the monitoring center is the most common function. This function is usually accomplished by adding a positioning device to the OBD interface of the vehicle to upload the vehicle's driving position to the monitoring center. However, since the accuracy of the driving position obtained in most cases is low due to the cost and performance of the additional positioning device, most driving positions are scattered beside the driving road, and it is necessary to perform road network matching to correct the driving position to the corresponding road to ensure the reasonableness of displaying the vehicle position.

In the related art, the correction method of road network matching calculates the vertical distance and the direction angle comparison between the driving position and each road, takes the road with the shortest vertical distance and the smallest deviation of the direction angle comparison as the matching road, and takes the vertical point between the driving position and the matching road as the corrected vehicle display position. However, the above method cannot correct the positioning deviation caused by the inertial drift of the characteristic of the positioning device when the vehicle is steered, and the display position of the steered vehicle is still on the non-steered road after the vehicle is steered after the correction, so that the display position of the vehicle suddenly jumps to the steered road in the process, which causes a display position error, and particularly when the number of monitored vehicles is large, the display position jumps of each vehicle can cause the user experience to be greatly reduced.

Fig. 1 shows the driving position before correction (solid circle) and the display position after correction (open circle), wherein the first to last rectangle of the driving time is shown by the sequence numbers from small to large, and the road is shown by the rectangle, and it can be seen that the jump in position is obvious (see the positions corresponding to the sequence numbers 8 and 9).

Therefore, the present disclosure provides a method, an apparatus, a storage medium, and an electronic device for determining a driving position of a vehicle, so as to solve the problem of inaccurate positioning of a vehicle positioning apparatus in the related art.

Fig. 2 is a flowchart of a vehicle travel position determination method provided according to an embodiment of the present disclosure. As shown in fig. 2, the method may include the following steps.

In step 21, target position information of the vehicle is determined based on first historical trajectory information of the vehicle corresponding to the first target sampling time.

During the running process of the vehicle, a positioning device on the vehicle is in an operating state, and data collection is performed periodically according to a certain time interval (for example, 1 s). In this process, the time when data acquisition is performed is the sampling time, and the sampling time described in the present embodiment can be understood by referring to the above manner.

The first historical trajectory information may include a historical travel position that the vehicle traveled to the first target sampling time. Here, the first target sampling time may be referred to as "current sampling time", and the first history track information may be referred to as "current sampling time"And the position sequence sequentially comprises historical driving positions passing by at the first target sampling time and each previous sampling time in the current driving process of the vehicle according to the time sequence. Illustratively, during the running of the vehicle, the sampling time is t in sequence₁～t_n(n is a positive integer greater than 1), if the first target sampling time is the sampling time t₁₀(preceded by a sampling time t₁～t₉) Then the first historical track information includes the vehicle at t respectively₁～t₁₀Past historical travel positions. It should be noted that the historical driving position used in the present disclosure is a driving position (i.e., a driving position corresponding to a historical sampling time) per se, and is used here for convenience of distinction.

The target location information may include a location at which the vehicle is to arrive at a second target sampling instant, wherein the second target sampling instant is a number of consecutive sampling instants starting at a time next to the first target sampling instant. The number of second target sampling instants may be set artificially, for example, to a preset number (greater than or equal to 1), that is, the second target sampling instants is a preset number of sampling instants starting from a next sampling instant of the first target sampling instants. Illustratively, during the running of the vehicle, the sampling time is t in sequence₁～t_n(n is a positive integer greater than 1), if the first target sampling time is the sampling time t₁₀Then the second target sampling instant may be t₁₁(the preset number is 1), or the second target sampling time may be t₁₁、t₁₂And t₁₃(the preset number is 3).

According to the first historical track information of the vehicle, the target position information of the vehicle is determined, namely, the position of the vehicle possibly located at the next sampling moment or at the next several sampling moments is estimated according to the historical driving position of the vehicle. When the first historical track information is used for determining the target position information of the vehicle, all the first historical track information can be used, or only a part close to the first target sampling time in the first historical track information can be used for reducing dataThe processing amount can be set according to specific requirements during practical application. For example, if the vehicle is at t in the first history track information₁～t₁₀The past historical driving position can be used at t when determining the target position information₁～t₁₀The 10 past historical driving positions (all used), or the vehicle can be used at t₆～t ₁₀5 past historical driving positions (partially used).

In step 22, it is determined whether the vehicle is in a turning state based on the first history track information and the target position information.

The current driving trend of the vehicle can be known according to the first historical track information of the vehicle which has driven, and the subsequent driving trend of the vehicle can be known according to the current driving position of the vehicle (namely, the driving position of the vehicle at the first target sampling moment) and the target position information, and the two driving trends are compared, so that whether the vehicle is in a steering state or not can be determined. If the two driving trends are relatively close, the difference between the front and the rear of the driving trends of the vehicle is not large, so that the fact that the vehicle is not in a steering state can be determined; if the difference between the two driving trends is larger, the front and back variation of the driving trend of the vehicle is larger, so that the vehicle can be determined to be in a steering state.

In step 23, if it is determined that the vehicle is in the turning state, the position to be reached by the vehicle at each second target sampling time in the target position information is used to replace the position collected by the positioning device of the vehicle at each second target sampling time, so as to determine the driving position of the vehicle at each second target sampling time.

As described above, if the vehicle is in a turning state, the data collected by the positioning device of the vehicle may have a large error, and therefore, the position to be reached by the vehicle at each second target sampling time in the target position information determined in step 11 may be used to correspond to the position collected by the positioning device of the vehicle at each second target sampling time, so as to determine the driving position of the vehicle at each second target sampling time. Wherein, the corresponding substitution means using the sampling time t corresponding to the second target in the target position information_aPosition ofIn place of the positioning means at the second target sampling instant t_aThe location of the acquisition.

In order to make those skilled in the art understand the technical solutions provided by the embodiments of the present invention, the following detailed descriptions of the corresponding steps and related concepts are provided.

In the initial situation, the vehicle has not yet had a sufficient number of historical travel positions immediately after the vehicle starts traveling, and therefore, even if the target position information is determined, there is a problem that the result is inaccurate. Therefore, in one possible case, the position acquired by the vehicle positioning device may be directly used as the travel position of the vehicle at several sampling times immediately after the vehicle starts traveling, wherein the number of several sampling times immediately after the vehicle starts traveling may be set according to an empirical value. After having enough historical driving positions, the method provided by the present disclosure is started to be executed again.

The following describes in detail the determination of the target position information of the vehicle based on the first history track information of the vehicle corresponding to the first target sampling time in step 21.

In one possible embodiment, step 21 may include the following steps, as shown in fig. 3.

In step 31, a target location determination model matching the first historical trajectory information is determined from the stored plurality of location determination models.

The plurality of position determination models are obtained in advance and stored in corresponding storage locations (for example, a database storing vehicle data), and may be directly obtained from the corresponding storage locations in actual use.

The following describes a mode of generating the position determination model in detail. In one possible embodiment, the plurality of position determination models may be determined by:

acquiring stored second historical track information corresponding to the vehicle;

clustering the second historical track information to obtain a clustering result;

and respectively taking each track category as a target track category, and training the long-time memory network model by using target track information to obtain a position determination model corresponding to the target track category.

The second history track information is obtained based on the history of the travel process of the host vehicle, and may be stored in a corresponding storage location (for example, a database storing host vehicle data). Each second historical track information includes a corresponding historical driving position of the vehicle in one historical driving process, and each second historical track information can be regarded as a sequence formed by the historical driving positions in one historical driving process according to the time sequence.

After the stored second history track information corresponding to the own vehicle is acquired, the plurality of second history track information may be clustered to obtain a clustering result. And the clustering result comprises track categories and second historical track information under each track category. For example, when clustering the second historical track information, the distance metric between the second historical track information may be based on a K-Means clustering algorithm (K-Means clustering algorithm), and a DTW (Dynamic Time Warping) distance is used as the distance metric between the second historical track information, wherein the DTW is used for measuring the similarity between different length sequences. Moreover, the way of calculating the DTW distance between data and clustering the data by using the K-Means clustering algorithm to obtain the clustering result belongs to the prior art, and is not described herein.

After the clustering result is obtained, the model can be trained respectively for each track category obtained after clustering, and second historical track information under the corresponding track category is used during training. For example, each trajectory category may be used as a target trajectory category, and the long-term and short-term memory network model may be trained by using target trajectory information to obtain a position determination model corresponding to the target trajectory category. And the target track information is second historical track information under the category of the target track. Therefore, each track category in the clustering result is sequentially used as a target track category, model training is carried out according to the target track category, and a position determination model corresponding to each track category can be trained correspondingly.

In a possible embodiment, training the long-term and short-term memory network model by using the target track information to obtain the position determination model corresponding to the target track category may include the following steps:

and training the long-time memory network model by taking a part of the target track information as input data and taking a preset number of historical driving positions of the input data behind the target track information as output data to obtain a position determination model corresponding to the target track type.

As described above, the second target sampling time may be a preset number, and thus, model training may be performed accordingly, using a preset number of historical driving positions as output data. When the model is trained, a part of the target track information is used as input data, a preset number of historical driving positions of the input data behind the target track information are used as output data, and the long-time memory network model is trained to obtain a position determination model corresponding to the target track type. For example, if the preset number is 2 and the second history track information is [ D1, D2, D3, D4, D5, D6, D7, D8, D9, D10], then [ D1, D2, D3, D4, D5] may be used as input data and [ D6, D7] may be used as output data for model training, or [ D4, D5, D6, D7, D8] may be used as input data and [ D9, D10] may be used as output data, and for selection of other training data, reference may be made here for details. And, the way of training the long-time memory network model is the prior art, and is not detailed here.

By adopting the mode, the second historical track information of the historical driving of the vehicle is clustered, and the position determination model is respectively generated according to the clustering result and aiming at each track type, so that the method has stronger pertinence and is beneficial to obtaining more accurate results when the position determination model is used.

Next, a description will be given of a case where a target position specifying model matching the first history track information is specified from among the plurality of stored position specifying models in step 31. In one possible embodiment, step 31 may include the steps of:

The mean square error reflects the degree of difference between the estimated value and the true value, and may be an expected value of the square of the difference between the estimated value of the parameter and the true value of the parameter. Therefore, from the first historical trajectory information, for each location determination model, a mean square error of the location determination model can be determined, which formula can be as follows:

wherein,

for the output result (estimated value) obtained by the position determination model for the input first historical track information, θ is the actual data (true value) corresponding to the output result in the first historical track information. When determining the mean square error of the position determination model, different parts in the first historical trajectory information can be selected as input data respectively to obtain various output results of the position determination model, the mean square error is calculated for each output result respectively, and the minimum one of the output results is used as the mean square error of the position determination model. From this, the mean square error of each position determination model can be determined.

After the mean square error of each determination model is determined, for each location determination model, the ratio of the mean square error of the location determination model to the probability of occurrence of the location determination model in the historical driving of the vehicle is determined as the model error of the location determination model. Therefore, the influence of the difference of the data quantity on the effect of the position determination model can be reduced by combining the model error obtained by the occurrence probability, so that the determined model error is more accurate.

Wherein each of the stored positions determines a probability that the model corresponds to an occurrence of the model in the historical driving of the vehicle. Referring to the determination method of the position determination model received in the above, first, the second historical trajectory information of the host vehicle is clustered, and the trajectory type and the second historical trajectory information under each trajectory type are obtained. Then, the position determination model is determined for each trajectory category, and therefore, the probability of the position determination model appearing in the historical travel of the host vehicle may be the ratio of the second historical trajectory information in the trajectory category to which the position determination model belongs to the second historical trajectory information in all the host vehicles. For example, the second history track information of all the host vehicles is divided into 3 types (A, B, C), where the number of the types a is 450, the number of the types B is 100, and the number of the types C is 50, and the probability of the occurrence of the location-determining model of the type a in the history travel of the vehicle is 450/(450+100+50) ═ 0.75, and the other similar reasons.

The size of the model error can reflect the matching degree of the position determination model and the first historical track information, and the minimum model error indicates that the position determination model can best match the historical driving position of the current driving process of the vehicle. Therefore, after the model error corresponding to each position determination model is obtained, the position determination model with the minimum model error is used as the target position determination model for subsequent data processing, so that the data processing result is closer to the current running condition of the vehicle, and the data processing result is more accurate.

In step 32, the first historical trajectory information is input to the target position determination model to obtain target position information output by the target position determination model.

By adopting the mode, the stored position determination models are utilized to determine the target position determination model with the highest matching degree with the first historical track information, and the target position information is determined through the target position determination model, so that the prediction of the position which is possibly reached by the vehicle in the following process is realized, the vehicle is closer to the current running condition of the vehicle, and the accuracy degree is higher.

In one possible embodiment, the step 12 of determining whether the vehicle is in a steering state according to the first historical track information and the target position information may include the steps of:

determining a first running direction of the vehicle at a first target sampling moment according to the first historical track information;

determining a second driving direction of the vehicle according to the driving position of the vehicle at the first target sampling time and the position to be reached at the next sampling time corresponding to the first target sampling time in the target position information;

and if the included angle between the first driving direction and the second driving direction is smaller than or equal to a preset angle threshold value, determining that the vehicle is not in a steering state.

Wherein a first direction of travel of the vehicle at the first target sampling instant can be determined from the first historical trajectory information. For example, the direction in which the travel position of the vehicle at the last sampling time of the first target sampling time points to the travel position of the vehicle at the first target sampling time may be taken as the first travel direction. For example, for each of the sampling times, a plurality of travel change directions can be obtained by obtaining a travel change direction in which the travel position of the vehicle at the previous sampling time (time t) points to the travel position of the vehicle at the next sampling time (time t + 1), and the first travel direction can be determined based on the travel change directions (for example, one direction at the intermediate position is obtained as the first travel direction based on the plurality of directions). And determining a second traveling direction of the vehicle based on the traveling position of the vehicle at the first target sampling time and a position to be reached by a next sampling time corresponding to the first target sampling time in the target position information. For example, a direction in which the travel position of the vehicle at the first target sampling timing points to the travel position of the vehicle at the next sampling timing from the first target sampling timing may be taken as the second travel direction.

The first driving direction can reflect the current driving trend of the vehicle, and the second driving direction can reflect the driving trend of the vehicle, so that the included angle between the first driving direction and the second driving direction can reflect the change degree of the driving trend of the vehicle, and the larger the included angle between the first driving direction and the second driving direction, the larger the change of the driving trend of the vehicle is, the more possible the vehicle is in a steering state. Therefore, if the included angle between the first driving direction and the second driving direction is larger than the preset angle threshold value, the vehicle is determined to be in a steering state; and if the included angle between the first driving direction and the second driving direction is smaller than or equal to a preset angle threshold value, determining that the vehicle is not in a steering state. The preset angle threshold may be set according to an empirical value, and may be, for example, within an angle interval of [15 °, 20 ° ].

In one possible embodiment, if it is determined that the vehicle is not in a turning state via step 22, the method provided by the present disclosure may further include the following steps based on the steps shown in fig. 2:

determining the running position of the vehicle at the next sampling moment of the first target sampling moment according to the position information acquired by the positioning device of the vehicle; and the number of the first and second groups,

the next sampling timing of the first target sampling timing is set as a new first target sampling timing, and step 21, step 22, and step 23 are repeatedly executed.

When the vehicle is not in a steering state, the positioning device of the vehicle is not influenced by steering, and large errors do not exist, so that the driving position of the vehicle at the next sampling moment of the first target sampling moment can be determined directly according to the position information collected by the positioning device of the vehicle. For example, the position acquired by the vehicle positioning device at the next sampling time to the first target sampling time may be directly used as the driving position of the vehicle at the next sampling time to the first target sampling time. And, since whether the vehicle is turning is unknown and the determination is continued, the next sampling time of the first target sampling time is used as a new first target sampling time, and the steps 21 to 23 are repeated, that is, whether the vehicle is in a turning state is determined based on the existing driving position, and corresponding processing is performed, and this process may continue until the vehicle stops running.

In one possible embodiment, if it is determined that the vehicle is in the turning state via step 22, the method provided by the present disclosure may further include the following steps based on the steps shown in fig. 2:

the latest sampling time of the second target sampling times is set as a new first target sampling time, and step 21, step 22, and step 23 are repeatedly performed.

After the vehicle is determined to be in the steering state, the target position information determined at the first target sampling time is used for replacing corresponding data acquired by the positioning device, and when the latest sampling time in the second target sampling time is reached, the subsequent state of the vehicle is unknown, so that the latest sampling time in the second target sampling time is used as a new first target sampling time, and the steps 21-23 are repeatedly executed, namely whether the vehicle is in the steering state is determined on the basis of the existing running position, corresponding processing is carried out, and the process can be continued until the vehicle stops running.

In one possible embodiment, the method provided by the present disclosure may further include the steps of:

determining a display position corresponding to a target running position according to the target running position of the vehicle, wherein the target running position is one of the running positions determined in the running process of the vehicle;

and displaying the target display information.

The travel position at each sampling time during the travel of the vehicle can be determined based on the content given above. According to the target driving position of the vehicle, the display position corresponding to the target driving position can be determined, wherein the target driving position is one of the driving positions determined in the driving process of the vehicle, and each driving position of the vehicle can be respectively used as the target driving position. The display position corresponding to the target driving position may refer to the correction method for road network matching given in the foregoing, that is, by calculating the perpendicular distance and the comparative direction angle from the driving position to the nearby road, the road with the shortest perpendicular distance and the smallest deviation of the direction angle is selected as the matching road, and the perpendicular point from the driving position to the matching road is used as the display position of the driving position.

Accordingly, the target display information can be generated based on the sampling time corresponding to the target travel position and the display position corresponding to the target travel position. The target display information may be used to indicate a sampling time corresponding to the target travel position and a display position corresponding to the target travel position.

After the target display information is generated, the target display information may be displayed on a corresponding visualization page. For example, a vehicle icon is displayed on the visual interface at the sampling time and the display position corresponding to the target display information.

By adopting the mode, the driving position of the determined vehicle is displayed, so that the driving track of the vehicle is visually displayed, and the situation of position jumping cannot occur during displaying due to the fact that the determined driving position of the vehicle is accurate, and user experience is improved.

Fig. 4 is a block diagram of a vehicle travel position determination apparatus provided according to an embodiment of the present disclosure. As shown in fig. 4, the apparatus 40 may include:

a first determining module 41, configured to determine target position information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling time, where the first historical track information includes a historical driving position that the vehicle has passed by when the vehicle has driven to the first target sampling time, the target position information includes a position that the vehicle will reach at a second target sampling time, and the second target sampling time is a number of consecutive sampling times with a next sampling time of the first target sampling time as a time starting point;

a second determining module 42, configured to determine whether the vehicle is in a steering state according to the first historical track information and the target position information;

and if it is determined that the vehicle is in the steering state, replacing the position, acquired by the positioning device of the vehicle, of the vehicle at each second target sampling time with a position, to be reached by the vehicle at each second target sampling time, of the target position information to determine the driving position of the vehicle at each second target sampling time.

Optionally, the first determining module 41 includes:

the first determination submodule includes:

Optionally, the apparatus 40 is configured to determine a plurality of position determination models by:

Optionally, the second determining module 42 includes:

Optionally, if it is determined that the vehicle is in the turning state, the device 40 is further configured to use the latest sampling time of the second target sampling times as a new first target sampling time, and return to the first determining module 41, the second determining module 42, and the processing module 43 to repeatedly execute the first historical track information corresponding to the first target sampling time according to the vehicle, determine the target position information of the vehicle, and determine whether the vehicle is in the turning state according to the first historical track information and the target position information, and if it is determined that the vehicle is in the turning state, replace the position to be reached by the vehicle at each second target sampling time with the position to be reached by the vehicle at each second target sampling time in the target position information, to determine the driving position of the vehicle at each of the second target sampling times.

Optionally, the apparatus 40 further comprises:

the means 40 are further arranged for taking the next one of the first target sampling instants as a new first target sampling instant, and returns to the first determining module 41, the second determining module 42 and the processing module 43, to repeatedly execute the first historical track information corresponding to the first target sampling time according to the vehicle, determine the target position information of the vehicle, and determining whether the vehicle is in a turning state based on the first historical trajectory information and the target position information, and if the vehicle is determined to be in the steering state, replacing the positions to be reached by the vehicle at the second target sampling moments with the positions to be collected by the positioning device of the vehicle at the second target sampling moments in the target position information to determine the driving position of the vehicle at the second target sampling moments.

Optionally, the apparatus 40 further comprises:

and the display module is used for displaying the target display information.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

FIG. 5 is a block diagram illustrating an electronic device in accordance with an example embodiment. As shown in fig. 5, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.

The processor 701 is configured to control the overall operation of the electronic device 700 to complete all or part of the steps of the vehicle driving position determining method. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 705 may thus include: Wi-Fi module, Bluetooth module, NFC module, etc.

In an exemplary embodiment, the electronic Device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the vehicle driving position determining method.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions which, when executed by a processor, implement the steps of the vehicle travel position determination method described above. For example, the computer readable storage medium may be the above-mentioned memory 702 including program instructions executable by the processor 701 of the electronic device 700 to perform the above-mentioned vehicle travel position determination method.

FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment. For example, the electronic device 1900 may be provided as a server. Referring to fig. 6, an electronic device 1900 includes a processor 1922, which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processor 1922 may be configured to execute the computer program to execute the vehicle travel position determination method described above.

Additionally, electronic device 1900 may also include a power component 1926 and a communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 1900. In addition, the electronic device 1900 may also include input/output (I/O) interfaces 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, etc., stored in memory 1932.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions which, when executed by a processor, implement the steps of the vehicle travel position determination method described above. For example, the computer readable storage medium may be the memory 1932 including program instructions executable by the processor 1922 of the electronic device 1900 to perform the vehicle travel position determination method described above.

In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable device, the computer program having code portions for performing the above-mentioned vehicle driving position determination method when executed by the programmable device.

The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, various possible combinations will not be separately described in this disclosure.

In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.

Claims

1. A vehicle travel position determination method, characterized by comprising:

determining target position information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling time, wherein the first historical track information comprises a historical driving position passed by the vehicle to the first target sampling time, the target position information comprises a position to be reached by the vehicle at a second target sampling time, and the second target sampling time is a preset number of continuous sampling times with a next sampling time of the first target sampling time as a time starting point;

2. The method of claim 1, wherein determining the target location information of the vehicle based on the first historical track information of the vehicle corresponding to the first target sample time comprises:

3. The method of claim 2, wherein each of said position-determining models corresponds to a probability of occurrence of that model in a historical driving of said vehicle;

4. The method of claim 2, wherein the plurality of location determination models are determined by:

5. The method of claim 4, wherein training the long-term and short-term memory network model by using the target track information to obtain the position determination model corresponding to the target track category comprises:

6. The method of claim 1, wherein determining whether the vehicle is in a steer state based on the first historical trajectory information and the target location information comprises:

7. The method of claim 1, wherein if it is determined that the vehicle is in the steering state, the method further comprises:

8. The method of claim 1, further comprising:

9. The method according to any one of claims 1-8, further comprising:

and displaying the target display information.

10. A vehicle travel position determination apparatus, characterized by comprising:

the vehicle position detection device comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining target position information of a vehicle according to first historical track information of the vehicle corresponding to a first target sampling moment, the first historical track information comprises a historical driving position passed by the vehicle to the first target sampling moment, the target position information comprises a position to be reached by the vehicle at a second target sampling moment, and the second target sampling moment is a preset number of continuous sampling moments with a next sampling moment of the first target sampling moment as a time starting point;

11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.

12. An electronic device, comprising:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 9.