CN111192452B

CN111192452B - Stroke data segmentation method and device, storage medium and electronic equipment

Info

Publication number: CN111192452B
Application number: CN201911382449.8A
Authority: CN
Inventors: 刘志伟; 徐丽丽; 苗英辉; 王宇飞; 高宏宇
Original assignee: Neusoft Corp
Current assignee: Neusoft Corp
Priority date: 2019-12-27
Filing date: 2019-12-27
Publication date: 2021-06-18
Anticipated expiration: 2039-12-27
Also published as: CN111192452A

Abstract

The disclosure relates to a stroke data segmentation method, a stroke data segmentation device, a storage medium and an electronic device, wherein the method comprises the following steps: comparing the average speed between every two adjacent data points in a target travel data set of the vehicle with a first speed threshold, and adding a status flag to each data point in the target travel data set; marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark; identifying an abnormal section which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state in each driving section; and acquiring a target travel data set marked with a driving section, a stopping section and an abnormal section as a segmentation result. The driving section and the stopping section in the vehicle travel can be determined according to the state mark of each data point, and then the abnormal section with signal loss is identified according to the characteristics of the data points, so that the efficiency and the intelligent degree of the travel data segmentation are improved.

Description

Stroke data segmentation method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of intelligent driving, and in particular, to a trip data segmentation method, device, storage medium, and electronic device.

Background

At present, mass data flood our lives, and the utilization of the data is more and more important. In the field of driving behavior analysis, a large number of data points are collected by a vehicle-mounted GPS (Global Positioning System), and research on the data points can help developers to analyze driving behaviors, and further assist in danger identification, danger early warning, danger avoidance and the like. The travel of the user is usually identified and split by data points collected by an on-board GPS (when the vehicle arrives at a location and stays for a long time, the location is considered as the end point of a travel), but the GPS raw data is rough and has many abnormal data points, including: noise data points (specifically, longitude and latitude data of different places at different moments are overlapped or crossed, and the like) and missing data points (when an automobile runs in a tunnel, a garage or a remote area without signal coverage, due to the fact that signals cannot be received, data cannot be acquired, and therefore the missing points exist in the data acquired by the data). These outlier data points tend to result in large deviations in the trip identification, such as misidentification of the trip, missed identification, and the like. In the related art, after the stroke segmentation result automatically labeled by a machine is obtained, the abnormal points are generally identified and relabeled manually, so that the implementation cost of the whole stroke data segmentation process is high, and meanwhile, the efficiency and the intelligence degree are low.

Disclosure of Invention

To overcome the problems in the related art, it is an object of the present disclosure to provide a trip data segmentation method, apparatus, storage medium, and electronic device.

In order to achieve the above object, according to a first aspect of embodiments of the present disclosure, there is provided a trip data segmentation method, including:

comparing an average speed between every two adjacent data points in a target trip data set of a vehicle to a first speed threshold in a predetermined set of target thresholds to add a status flag for each data point in the target trip data set, the target trip data set comprising a plurality of data points arranged in a chronological order, the data points consisting of a time point and a geographic location at which the vehicle is located at the time point, the status flag being one of a travel status flag and a stop status flag;

marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark;

identifying an abnormal section in each driving section, which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state, wherein the time interval between the data points at two ends of the abnormal section is larger than a first time threshold value in the target threshold value group, and the average speed of the vehicle between the data points at two ends of the abnormal section is larger than a second speed threshold value in the target threshold value group;

and acquiring the target travel data set marked with the driving section, the stopping section and the abnormal section as a first segmentation result of the target travel data set.

Optionally, before comparing the average speed between every two adjacent data points in the target trip data set of the vehicle with the first speed threshold in the predetermined set of target thresholds to add a status flag for each data point in the target trip data set, the method further comprises:

determining a first threshold value group according to an actual segmentation result of the historical travel data set of the vehicle, wherein the first threshold value group comprises a third speed threshold value, a fourth speed threshold value and a second time threshold value;

generating a preset number of second threshold value groups according to the first threshold value group;

taking the historical trip data set as the target trip data set, replacing the target threshold value set by each second threshold value set, and performing a comparison between an average speed between every two adjacent data points in the target trip data set of the vehicle and a first speed threshold value in a predetermined target threshold value set to add a state flag to each data point in the target trip data set to identify an abnormal section, which is used for representing that the vehicle is in a stop state and has abnormal signal transceiving, in each driving section so as to obtain a preset number of second section results corresponding to the historical trip data set;

and comparing each second segmentation result with the actual segmentation result to take a second threshold value group corresponding to the second segmentation result with the highest coincidence degree of the actual segmentation results as the target threshold value group.

Optionally, the comparing the average speed between every two adjacent data points in the target trip data set of the vehicle with the first speed threshold in the predetermined target threshold set to add a status flag for each data point in the target trip data set includes:

adding a stop status flag to a first data point in the target trip data set;

determining a first average speed of the vehicle between two first data points according to a time point included in each of the two first data points and geographic position information corresponding to the time point, wherein the two first data points are any two adjacent data points in the first travel data set;

if the first average speed is greater than or equal to the first speed threshold, adding a driving state mark to the latter data point of the two first data points; or,

and if the first average speed is less than the first speed threshold, adding a stop state mark for the next data point of the two first data points.

Optionally, the marking out a driving segment for representing that the vehicle is in a driving state and a stopping segment for representing that the vehicle is in a stopping state from the target travel data set according to the state mark includes:

if the state of the previous first data point in the two first data points is marked as a driving state mark and the state of the next first data point in the two first data points is marked as a stopping state mark, marking the previous first data point as a stroke end point;

if the state of the former one of the two first data points is marked as a stop state marker and the state of the latter one of the two first data points is marked as a driving state marker, marking the latter one as a stroke starting point;

determining the travel segment and the stop segment according to a trip start point and a trip end point in the target trip data set, wherein the travel segment comprises a plurality of data points between adjacent trip start points and trip end points in the target trip data set, and the stop segment comprises one or more data points between adjacent trip end points and trip start points and adjacent trip end points and trip start points in the target trip data set.

Optionally, the identifying an abnormal section, in each driving section, for indicating that the vehicle is in a stopped state and has an abnormal signal transceiving state includes:

identifying a signal missing segment in the driving segment, the signal missing segment being composed of two adjacent target data points in the driving segment, a time interval between the two target data points being greater than the first time threshold;

and determining whether the signal missing segment is the abnormal segment or not according to the second speed threshold.

Optionally, the determining, according to the second speed threshold, whether the signal missing segment is the abnormal segment includes:

determining a second average speed of the vehicle between the two target data points;

if the second average speed is smaller than the second speed threshold, marking a previous target data point in the signal missing section as a stroke end point, and marking a next target data point in the signal missing section as a stroke start point, so as to take the signal missing section as the abnormal section.

Optionally, the actual segmentation result includes: determining a first threshold value set according to an actual segmentation result of the historical travel data set by the historical travel data set marked with the travel segment, the stop segment and the abnormal segment, which is determined after manual labeling of a travel starting point and a travel ending point in a plurality of data points in the historical travel data set, and the determination comprises:

for the third speed threshold:

obtaining an average speed of the vehicle between every two data points in each stopping section in the historical trip data set to obtain a first average speed set;

obtaining an average speed of the vehicle between every two data points in each driving segment in the historical travel data set to obtain a second average speed set;

taking the median of the intersection of the first average velocity set and the second average velocity set as the third velocity threshold; and the number of the first and second groups,

for the fourth speed threshold:

acquiring the average speed of the vehicle between data points at two ends of each abnormal section in the historical travel data set to acquire a third average speed set;

taking the median of the intersection of the third average velocity set and the second average velocity set as the fourth velocity threshold; and the number of the first and second groups,

for the second time threshold:

acquiring a time interval between data points at two ends of each stay section in the historical travel data set to acquire a first time interval set;

acquiring a time interval between data points at two ends of each abnormal section in the historical travel data set to acquire a second time interval set;

and taking the minimum duration interval in the second duration interval set and the second duration interval set as the second time threshold.

Optionally, the generating a preset number of second threshold sets according to the first threshold set includes:

acquiring a plurality of fifth speed thresholds of which the difference value with the third speed threshold is smaller than a first preset difference value;

acquiring a plurality of sixth speed thresholds of which the difference value with the fourth speed threshold is smaller than a second preset difference value;

acquiring a plurality of third time thresholds of which the difference value with the second time threshold is smaller than a third preset difference value;

generating the preset number of second threshold value groups according to a third speed threshold value, a fourth speed threshold value and a second time threshold value, and the plurality of fifth speed threshold values, the plurality of sixth speed threshold values and the plurality of third time threshold values; wherein,

the second set of thresholds includes: a seventh speed threshold, an eighth speed threshold, and a fourth time threshold, where the seventh speed threshold is any one of the third speed threshold and the fifth speed thresholds, the seventh speed threshold is any one of the fourth speed threshold and the sixth speed thresholds, and the fourth time threshold is any one of the second time threshold and the third time thresholds.

According to a second aspect of the embodiments of the present disclosure, there is provided a trip data segmenting device, the device including:

a first trip marker module to compare an average speed between every two adjacent data points in a target trip data set of a vehicle to a first speed threshold of a set of predetermined target thresholds to add a status marker to each data point in the target trip data set, the target trip data set comprising a plurality of data points arranged in a chronological order, the data points consisting of a time point and a geographic location of the vehicle at the time point, the status marker being one of a travel status marker and a stop status marker;

the second travel marking module is used for marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark;

an abnormal section marking module, configured to identify an abnormal section in each driving section, which is used for indicating that the vehicle has abnormal signal transceiving and is in a stopped state, wherein a time interval between data points at two ends of the abnormal section is greater than a first time threshold in the target threshold group, and an average speed of the vehicle between the data points at two ends of the abnormal section is greater than a second speed threshold in the target threshold group;

and the first segmentation result acquisition module is used for acquiring the target travel data set marked with the driving segment, the stopping segment and the abnormal segment as a first segmentation result of the target travel data set.

Optionally, the method further includes:

a first threshold determination module for determining a first threshold set comprising a third speed threshold, a fourth speed threshold and a second time threshold according to an actual segmentation result of the historical trip data set of the vehicle;

the threshold value set generating module is used for generating a preset number of second threshold value sets according to the first threshold value set;

a second segmentation result obtaining module, configured to use the historical trip data set as the target trip data set, replace the target threshold value set by each second threshold value set, perform a comparison between an average speed between every two adjacent data points in the target trip data set of the vehicle and a first speed threshold value in a predetermined target threshold value set, add a status flag to the identification of an abnormal segment, which is used for indicating that the vehicle is in a stop state and has an abnormal signal transmission and reception state, in each driving segment, for each data point in the target trip data set, so as to obtain the preset number of second segmentation results corresponding to the historical trip data set;

and the second threshold value determining module is used for comparing each second segmentation result with the actual segmentation result so as to take a second threshold value group corresponding to the second segmentation result with the highest coincidence degree of the actual segmentation result as the target threshold value group.

Optionally, the first stroke marking module is configured to:

adding a stop status flag to a first data point in the target trip data set;

Optionally, the second stroke marking module is configured to:

Optionally, the abnormal segment marking module is configured to:

Optionally, the actual segmentation result includes: the first threshold determination module is configured to determine the historical travel data set marked with the travel segment, the stop segment, and the abnormal segment by manually labeling a travel start point and a travel end point of a plurality of data points in the historical travel data set, and is configured to:

for the third speed threshold:

for the fourth speed threshold:

for the second time threshold:

Optionally, the threshold group generating module is configured to:

According to a third aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps of the trip data segmentation method provided by the first aspect of the embodiments of the present disclosure.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to implement the steps of the trip data segmentation method provided by the first aspect of the embodiments of the present disclosure.

By the technical scheme, the method can compare the average speed between every two adjacent data points in the target travel data set of the vehicle with the first speed threshold value in the predetermined target threshold value set so as to add a state mark to each data point in the target travel data set, wherein the target travel data set comprises a plurality of data points which are arranged in time sequence, each data point consists of a time point and a geographical position of the vehicle at the time point, and each state mark is one of a driving state mark and a stopping state mark; marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark; identifying an abnormal section which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state in each driving section, wherein the time interval between the data points at two ends of the abnormal section is larger than a first time threshold value in the target threshold value group, and the average speed of the vehicle between the data points at two ends of the abnormal section is larger than a second speed threshold value in the target threshold value group; and acquiring the target travel data set marked with the driving section, the stopping section and the abnormal section as a first segmentation result of the target travel data set. The driving section and the stopping section in the vehicle travel can be determined according to the state mark of each data point, and then the abnormal section with signal loss is identified according to the characteristics of the data points, so that the efficiency and the intelligent degree of the travel data segmentation are improved.

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 flow diagram illustrating a trip data segmentation method in accordance with an exemplary embodiment;

FIG. 2 is a flow chart of another trip data segmentation method shown in accordance with the embodiment shown in FIG. 1;

FIG. 3 is a flow chart illustrating a method of tagging data points according to the embodiment shown in FIG. 2;

FIG. 4 is a flow chart illustrating a method of determining travel and dwell segments in accordance with the embodiment shown in FIG. 2;

FIG. 5 is a flow diagram illustrating a method of identifying anomalous segments in accordance with the embodiment shown in FIG. 2;

FIG. 6 is a block diagram illustrating a trip data segmentation apparatus in accordance with an exemplary embodiment;

FIG. 7 is a block diagram of another trip data segmentation apparatus shown in accordance with the embodiment of FIG. 6;

FIG. 8 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

FIG. 1 is a flow diagram illustrating a trip data segmentation method, as shown in FIG. 1, according to an exemplary embodiment, including:

step 101, comparing an average speed between every two adjacent data points in a target trip data set of a vehicle with a first speed threshold in a predetermined set of target thresholds to add a status flag for each data point in the target trip data set.

Wherein the target trip data set comprises a plurality of data points arranged in a time sequence, the data points consisting of a time point and a geographic location of the vehicle at the time point, the status flag being one of a travel status flag and a stop status flag.

For example, the target trip data set is a set of trip data of the vehicle collected within a preset time period, wherein a plurality of data points can reflect the driving state of the vehicle through a combination of time points and geographic positions. The preset time period may be, for example, a day or a week, and the geographic location may be latitude and longitude coordinates. It will be appreciated that based on the time points and geographic locations contained in two adjacent data points in the target trip data set, the average speed of the vehicle between the two data points can be determined. Specifically, the distance between two longitude and latitude coordinates of two data points may be used as the driving distance of the vehicle between the two data points, and the driving distance is preferably the actual driving distance determined according to a preset map system, not the straight distance. From the distance traveled and the time interval between two of the two data points, the average speed of the vehicle between the two data points can be determined. Thereafter, a determination can be made as to the magnitude of the average speed in relation to the first speed threshold, thereby marking either of the two data points as stopped or driving. It should be noted that, since the time interval between two data points is small (two adjacent data points with a large time interval are determined as abnormal segments in the following step 103), the labeled data point can be any one of the two data points without affecting the accuracy of the final segmentation result. However, the location of the labeled data point should be selected consistently after each determination, i.e., the labeled data point should be the previous data point of the two data points or the next data point of the two data points after each determination of the average velocity of the two adjacent data points. After step 101, all data points in the target trip data set become data points with travel or stop status markers.

And 102, marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark.

Illustratively, after step 101 above, a certain segment of the target trip data set with a status flag may be represented as, for example, "… (3A) (4B) (5B) (6B) (7A) (8A) (9A) (10A) (11A) (12A) (13B) …", where 3-13 represents the time sequence of the data points, a represents the travel status flag, and B represents the stop status flag. Thus, this data point can be divided into a stop section (4B) (5B) (6B), and a travel section Y (7A) (8A) (9A) (10A) (11A) (12A). Specifically, (3A) (4B), (6B) (7A), or (12A) (13B) may be referred to as a set of state transition points, and in the process of determining a specific start/end point of a trip, the data points of the stop state in each set of state transition points may be collectively determined as the start/end point of the trip, or the data points of the travel state in each set of state transition points may also be collectively determined as the start/end point of the trip. For example, (7A) of the travel segments Y (7A) (8A) (9A) (10A) (11A) (12A) is marked as a trip start point, and (12A) is marked as a trip end point. In this way, a plurality of data points between the end of travel and the start of travel form a stop segment, and the start of travel and the end of travel and the plurality of data points between the start of travel and the end of travel form the travel segment.

And 103, identifying abnormal sections which are used for representing that the vehicle has abnormal signal transceiving and are in a stop state in each driving section.

Wherein a time interval between data points across the abnormal segment is greater than a first time threshold in the set of target thresholds, and an average speed of the vehicle between data points across the abnormal segment is greater than a second speed threshold in the set of target thresholds.

For example, when a vehicle enters a basement or enters a remote area that cannot be covered by a signal, a situation may occur in which the vehicle cannot normally transmit and receive the signal, and in this case, data points during this period of time are missing. Since the travel segment and the stop segment are determined based on the status flag in step 102, a case where the signal missing segment is included in the travel segment may occur. In this case, if the vehicle is traveling in a remote area where the signal cannot be covered, the determination of the traveling section is still correct; if the vehicle enters the garage, the vehicle is probably in a stop state in the time period corresponding to the signal missing segment, and the judgment of the driving segment can be determined to be wrong. Therefore, in step 103, a data point indicating that the vehicle is in a stopped state and has abnormal signal transmission and reception needs to be determined from the divided driving segment (due to the signal loss, the data point generally includes only two data points before the signal loss and after the signal recovery). This segment of data point is also actually a dwell segment, but is not identified in step 102, and in order to distinguish it from the dwell segment directly identified in step 102, this segment of data point is referred to as an abnormal segment in the embodiment of the present disclosure.

And 104, acquiring the target travel data set marked with the driving section, the stopping section and the abnormal section as a first segmentation result of the target travel data set.

For example, after steps 101 to 103, some of the plurality of data points in the target course are actually identified as a course start point and a course end point, and the travel segment, the stop segment, and the abnormal segment can be directly distinguished from each other through the course start point and the course end point. It should be noted that, based on the start point and the end point of the travel, the method for distinguishing the staying section from the abnormal section is that two data points which only contain two data points (the start point of the travel is preceded by the end point of the travel and then is followed by the start point of the travel), and the time interval between the two data points is large (these conditions can be visually seen according to the actual data of the data points), the two data points are the abnormal section, and the other is the staying section. Therefore, the target trip data segment with the trip start/end point marker attached thereto can be considered as the first segmentation result. After that, the travel habits and frequent activity trajectories of the vehicle driver can be analyzed according to the segmentation result.

In summary, the present disclosure can compare an average velocity between every two adjacent data points in a target trip data set of a vehicle to a first velocity threshold in a predetermined set of target thresholds to add a status flag for each data point in the target trip data set, the target trip data set comprising a plurality of data points arranged in a time sequence, the data points consisting of a time point and a geographic location of the vehicle at the time point, the status flag being one of a travel status flag and a stop status flag; marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark; identifying an abnormal section which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state in each driving section, wherein the time interval between the data points at two ends of the abnormal section is larger than a first time threshold value in the target threshold value group, and the average speed of the vehicle between the data points at two ends of the abnormal section is larger than a second speed threshold value in the target threshold value group; and acquiring the target travel data set marked with the driving section, the stopping section and the abnormal section as a first segmentation result of the target travel data set. The driving section and the stopping section in the vehicle travel can be determined according to the state mark of each data point, and then the abnormal section with signal loss is identified according to the characteristics of the data points, so that the efficiency and the intelligent degree of the travel data segmentation are improved.

Fig. 2 is a flowchart illustrating another trip data segmentation method according to the embodiment shown in fig. 1, and as shown in fig. 2, before the step 101, the method may further include: step 105-108.

Step 105, determining a first threshold set according to the actual segmentation result of the historical travel data set of the vehicle.

Wherein the first set of thresholds includes a third speed threshold, a fourth speed threshold, and a second time threshold.

Illustratively, before the step 101, the three thresholds (i.e. the first speed threshold, the second speed threshold and the first time threshold) used in the steps 101-104 need to be determined according to the historical trip data set that has been manually marked, so as to ensure the correctness of the first segmentation result in the step 104. The steps 101-104 may be referred to as an actual application process, and the steps 105-108 are test processes for determining a target threshold set to be used by the actual application process. The actual segmentation result includes: the historical travel data set marked with the driving section, the stopping section and the abnormal section is determined by manually marking a travel starting point and a travel ending point in a plurality of data points in the historical travel data set. It should be noted that the actual segmentation result of the historical trip data set contains a plurality of data points, some of which are identified as a trip start point and a trip end point, and these manually labeled trip start/end points can be considered to be completely accurate. As with the first segmentation result of the target trip data set, the travel segment, the stop segment, and the abnormal segment can be directly identified from the data points labeled as the trip start point and the trip end point.

For example, based on the travel section, the stay section, and the abnormal section in the historical travel data set, a threshold value group (i.e., the third speed threshold value, the fourth speed threshold value, and the second time threshold value) that theoretically provides a higher accuracy for the segmentation result of the travel data may be determined. Specifically, for the third speed threshold, the step 105 may include: obtaining an average speed of the vehicle between every two data points in each stopping section in the historical travel data set to obtain a first average speed set; acquiring an average speed of the vehicle between every two data points in each driving section in the historical travel data set to acquire a second average speed set; and taking the median of the intersection of the first average speed set and the second average speed set as the third speed threshold. It should be noted that the average speed between two data points is not necessarily 0, and specifically, for example, the time interval between two data points is 2 seconds, wherein the vehicle is in the driving state in the first 0.2 seconds but the moving distance is small (for example, in the adjustment parking position), and the vehicle is in the stopping state in the second 1.8 seconds. Thus, the vehicle has both a running state and a stopped state during this period, but since the average speed is too small, the two data points are still considered to be the data points in the stop section.

For example, for the fourth speed threshold, the step 105 may comprise: acquiring the average speed of the vehicle between data points at two ends of each abnormal section in the historical travel data set so as to acquire a third average speed set; and taking the median of the intersection of the third average speed set and the second average speed set as the fourth speed threshold. And, for the second time threshold, the step 105 may comprise: acquiring a time interval between data points at two ends of each stay section in the historical travel data set to acquire a first time interval set; acquiring a time interval between data points at two ends of each abnormal section in the historical travel data set to acquire a second time interval set; and taking the minimum duration interval in the first duration interval set and the second duration interval set as the second time threshold.

And 106, generating a preset number of second threshold value sets according to the first threshold value sets.

Illustratively, as described above, this first set of thresholds is only theoretically such that the segmentation result of the trip data is of high accuracy. However, after a lot of experiments, it is confirmed that the generated first threshold set may have a certain error because the basis of the threshold generation (i.e., the stroke data) may have a noise point. In this case, it is also possible that the segmentation result has a high accuracy at a point around each of the first threshold values in the first threshold value group, or that is, at a threshold value for each of the threshold values whose difference from the threshold value is within a predetermined range. Therefore, in step 106, for each of the above threshold values, a plurality of threshold values with a difference smaller than a preset difference may be obtained, so as to generate a preset number, for example, 100, of the second threshold value sets. Specifically, this step 106 may include: acquiring a plurality of fifth speed thresholds of which the difference value with the third speed threshold is smaller than a first preset difference value; acquiring a plurality of sixth speed thresholds of which the difference value with the fourth speed threshold is smaller than a second preset difference value; acquiring a plurality of third time thresholds of which the difference value with the second time threshold is smaller than a third preset difference value; generating a preset number of second threshold value groups according to a third speed threshold value, a fourth speed threshold value and a second time threshold value, and the fifth speed threshold values, the sixth speed threshold values and the third time threshold values; wherein the second set of thresholds includes: a seventh speed threshold, an eighth speed threshold and a fourth time threshold, wherein the seventh speed threshold is any one of the third speed threshold and the fifth speed thresholds, the eighth speed threshold is any one of the fourth speed threshold and the sixth speed thresholds, and the fourth time threshold is any one of the second time threshold and the third time thresholds.

For example, it can be appreciated that for the three thresholds in the first set of thresholds, a third speed threshold, a fourth speed threshold, and a second time threshold, as well as the plurality of fifth speed thresholds, the plurality of sixth speed thresholds, and the plurality of third time thresholds, can be randomly combined. Specifically, one of the third speed threshold value and the plurality of fifth speed threshold values may be optionally selected as the speed threshold value for replacing the first speed threshold value in the target threshold value group in the following step 107. And, optionally one of the fourth speed threshold and the plurality of sixth speed thresholds may be used as the speed threshold for replacing the second speed threshold in the set of target thresholds in the following step 107. And, optionally one of the second time threshold and the plurality of third time thresholds may be used as the speed threshold for replacing the second speed threshold in the set of target thresholds in the following step 107. The above process is repeatedly executed until the number of the second threshold value sets reaches the preset number.

And 107, taking the historical travel data set as the target travel data set, replacing the target threshold set by each second threshold set, comparing the average speed between every two adjacent data points in the target travel data set of the vehicle with a first speed threshold in a predetermined target threshold set, and adding a state mark to each data point in the target travel data set to identify an abnormal section which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state, so as to obtain the preset number of second section results corresponding to the historical travel data set.

For example, after determining the preset number of second threshold value sets, the target threshold value set may be replaced by each second threshold value set, and the steps of steps 101 and 103 (performed for a preset number of times, for example, 100 times) may be performed on the historical trip data set to obtain 100 second segmentation results.

And 108, comparing each second segmentation result with the actual segmentation result, so as to take the second threshold value group corresponding to the second segmentation result with the highest coincidence degree of the actual segmentation result as the target threshold value group.

The degree of overlap may be determined by a preset recall function and precision function, for example. The recall function may include: 1. the proportion function of the number of correctly recognized strokes in all the starting points of the stroke is as follows: len1 (the number of intersections of the trip start points in the actual segmentation result and the trip start points in the second segmentation result)/len 2 (the number of trip start points in the actual segmentation result); 2. the proportional function of the number correctly identified in all the journey end points: len3 (the number of intersections of the stroke end in the actual segmentation result and the stroke end in the second segmentation result)/len 4 (the number of stroke start points in the actual segmentation result); 3. the proportional function of the number correctly identified in all trips: len5 (the number of intersections of travel, abnormal, and stop sections in the actual segmentation result and the travel, abnormal, and stop sections in the second segmentation result)/len 6 (the total number of travel, abnormal, and stop sections in the actual segmentation result). The precision function may include: 4. the proportion function of the true starting point among all the identified starting points of the journey: len1/len7 (number of travel starts in second segmentation result); 5. of all identified travel endpoints, the proportion function of the true endpoint: len3/len8 (number of travel ends in second segmentation result); 6. in all the strokes, the proportion function of the number of true strokes is as follows: len5/len9 (total number of travel, abnormal, and stay segments in the second segmentation result).

Exemplarily, the actual segmentation result and a preset number of second segmentation results are respectively substituted into the 6 functions, and then the sum of the proportional values obtained according to the 6 functions is obtained. The second segmentation result with the largest sum of the proportional values is the second segmentation result with the highest coincidence degree with the actual segmentation result, and the second threshold value set corresponding to the second segmentation result can be used as the target threshold value set in the actual calculation process.

Illustratively, the first speed threshold is used to identify the dwell segment and the second speed threshold is used to identify the anomaly segment, which, as described above, is a special dwell segment. In theory, if the second speed threshold is smaller than the first speed threshold, the data points at both ends of the abnormal section are marked as a stop state after step 101 and are identified as a stop section, and the abnormal section is not included in the driving section (i.e. all stop sections, whether special or general ones, are identified after step 102). Step 103 cannot be realized, and thus the difference of the abnormal section relative to the staying section cannot be reflected. The result obtained in step 108 also corroborates the theory that the second speed threshold value in the set of target threshold values is slightly larger than the first speed threshold value.

Fig. 3 is a flow chart illustrating a method for adding a marker to a data point according to the embodiment shown in fig. 2, wherein the step 101 may include: the following steps 1011 to 1013, or the following

steps

1011, 1012 and 1014.

At step 1011, a stop status flag is added for the first data point in the target trip data set.

Step 1012, determining a first average speed of the vehicle between the two first data points according to the time point included in each of the two first data points and the geographic position information corresponding to the time point.

The two first data points are any two adjacent data points in the first travel data set.

In step 1013, if the first average speed is greater than or equal to the first speed threshold, a driving status flag is added to the next data point of the two first data points.

In step 1014, if the first average speed is less than the first speed threshold, a stop status flag is added to the next data point of the two first data points.

For example, if the data point to which the state flag is added each time the average velocity of two adjacent data points is determined is the latter of the two data points, the first data point in the target travel data set may be directly set as the stopped state. Conversely, if the data point to which the state flag is added each time the average speed of two adjacent data points is determined is the previous data point of the two data points, the last data point in the target travel data set may be directly set to the stopped state. In this manner, the integrity of the data point status marker can be guaranteed.

Fig. 4 is a flowchart illustrating a method for determining a driving segment and a stopping segment according to the embodiment shown in fig. 2, wherein the step 102 may include:

at step 1021, if the status of the previous one of the two first data points is marked as a driving status flag and the status of the next one of the two first data points is marked as a stopping status flag, the next one of the two first data points is marked as a trip end point.

In step 1022, if the status of the previous one of the two first data points is marked as the stop status flag and the status of the next one of the two first data points is marked as the driving status flag, the previous one of the two first data points is marked as the starting point of the trip.

Still taking the above-mentioned one piece of data point "… (3A) (4B) (5B) (6B) (7A) (8A) (9A) (10A) (11A) (12A) (13B) …" with a status flag as an example, the (3A) (4B), (6B) (7A) or (12A) (13B) may be referred to as a set of status transition points, and in the process of determining the specific trip start/end point, the data point of the stop status in each set of status transition points may be determined as the trip start/end point collectively (as shown in

steps

1021 and 1022 described above), or the data point of the travel status in each set of status transition points may be determined as the trip start/end point collectively.

And 1023, determining the travel segment and the stop segment according to the travel starting point and the travel ending point in the target travel data set, wherein the travel segment comprises a plurality of data points between the adjacent travel starting point and the travel ending point in the target travel data set, and the stop segment comprises one or more data points between the adjacent travel ending point and the travel starting point and the adjacent travel ending point and the travel starting point in the target travel data set.

For example, it can be understood that, since the data points of the driving state are uniformly determined as the trip start/end points in the

above steps

1021 and 1022, the driving section includes the adjacent trip end point and the trip start point in the target trip data set and a plurality of data points between the adjacent trip end point and the trip start point, and the stopping section includes only a plurality of data points between the adjacent trip end point and the trip start point in the target trip data set. Still taking the above-mentioned one-stage data point "… (3A) (4B) (5B) (6B) (7A) (8A) (9A) (10A) (11A) (12A) (13B) (…") as an example, in the case where the data points in the stopped state are collectively determined as the stroke start/end points, the data point (4B) can be taken as the stroke end point of the stroke section X, the data point (6B) can be taken as the stroke start point of the stroke section Y, and the data point (13B) can be taken as the stroke end point of the stroke section Y, for the three sets of state transition points (3A) (4B), (6B) (7A), or (12A) (13B). In this way, a dwell segment may be determined as one or more data points (5B) between adjacent end of travel (4B) and start of travel (6B) and the adjacent end of travel (4B) and start of travel (6B) in the target travel data set, and a dwell segment (4B) (5B) (6B) may be determined. Meanwhile, the travel section Y can be determined as a plurality of data points (7A) (8A) (9A) (10A) (11A) (12A) between the adjacent travel starting point (6B) and the travel end point (13B) in the target travel data set.

Fig. 5 is a flowchart illustrating a method for identifying an abnormal segment according to the embodiment shown in fig. 2, and as shown in fig. 5, the step 103 may include:

and step 1031, identifying a signal missing segment in the driving segment.

The signal missing segment is composed of two adjacent target data points in the driving segment, and the time interval between the two target data points is greater than the first time threshold.

For example, in general, in the embodiment of the present disclosure, the system is set to collect the time information and the geographic position information of the vehicle once every preset time period within the preset time period. However, due to the complexity of the driving environment, the time interval between every two data points in the collected target travel data set is not necessarily all the preset time length, i.e., the time interval between every two data points in the target travel data set may be within an acceptable time range. However, when the time interval is greater than the acceptable time range (the first time threshold), for example, the time interval between two adjacent data points is 3 hours, it may be considered that the vehicle has a signal transceiving abnormality in the three hours, that is, the above-mentioned signal missing section exists between the two data points. It should be noted that, when determining the signal missing segment, the data point in the travel segment that has been identified as the start/end of the trip may be ignored, or the above-mentioned identification of the signal missing segment may be performed between the second data point and the second last data point of the travel segment.

Step 1032, determining whether the signal missing segment is the abnormal segment according to the second speed threshold.

For example, it can be understood that if the average speed of the vehicle in the signal missing segment is greater, it can be determined that the vehicle still keeps running in the signal missing segment; if the average speed of the vehicle in the signal missing segment is small, it can be determined that the vehicle is in a stopped state in the signal missing segment. Specifically, this step 1032 may include: determining a second average speed of the vehicle between the two target data points; if the second average speed is less than the second speed threshold, marking a previous target data point in the signal missing section as a stroke end point, and marking a next target data point in the signal missing section as a stroke start point, so as to take the signal missing section as the abnormal section.

In summary, the present disclosure can compare an average velocity between every two adjacent data points in a target trip data set of a vehicle to a first velocity threshold in a predetermined set of target thresholds to add a status flag for each data point in the target trip data set, the target trip data set comprising a plurality of data points arranged in a time sequence, the data points consisting of a time point and a geographic location of the vehicle at the time point, the status flag being one of a travel status flag and a stop status flag; marking a driving section for representing that the vehicle is in a driving state and a stopping section for representing that the vehicle is in a stopping state from the target travel data set according to the state mark; identifying an abnormal section which is used for representing that the vehicle has abnormal signal transceiving and is in a stop state in each driving section, wherein the time interval between the data points at two ends of the abnormal section is larger than a first time threshold value in the target threshold value group, and the average speed of the vehicle between the data points at two ends of the abnormal section is larger than a second speed threshold value in the target threshold value group; and acquiring the target travel data set marked with the driving section, the stopping section and the abnormal section as a first segmentation result of the target travel data set. The method has the advantages that after the accurate speed threshold and time threshold are obtained through the testing process, the state transition point of the vehicle in the travel is determined according to the state mark of each data point, the influence of the noise data point on the travel data segmentation is avoided according to the travel section and the stop section of the vehicle in the travel of the state transition point, meanwhile, the abnormal section of signal loss is identified and re-segmented according to the characteristics of the data points, and the efficiency and the intelligent degree of the travel data segmentation are improved while the accuracy of the travel data is guaranteed.

Fig. 6 is a block diagram illustrating a trip data segmentation apparatus according to an exemplary embodiment, as shown in fig. 6, the apparatus 600 including:

a first trip marking module 610 for comparing an average speed between every two adjacent data points in a target trip data set of the vehicle to a first speed threshold of a predetermined set of target thresholds to add a status mark to each data point in the target trip data set, the target trip data set comprising a plurality of data points arranged in a chronological order, the data points consisting of a time point and a geographic location of the vehicle at the time point, the status mark being one of a travel status mark and a stop status mark;

a second journey marking module 620, configured to mark, from the target journey data set, a driving segment for indicating that the vehicle is in a driving state and a stopping segment for indicating that the vehicle is in a stopping state according to the state mark;

an abnormal section marking module 630, configured to identify an abnormal section in each driving section, which is used for indicating that the vehicle has abnormal signal transceiving and is in a stopped state, wherein a time interval between data points at two ends of the abnormal section is greater than a first time threshold in the target threshold group, and an average speed of the vehicle between data points at two ends of the abnormal section is greater than a second speed threshold in the target threshold group;

a first segmentation result obtaining module 640, configured to obtain the target trip data set marked with the driving segment, the stopping segment, and the abnormal segment as a first segmentation result of the target trip data set.

Fig. 7 is a block diagram of another trip data segmentation apparatus according to the embodiment shown in fig. 6, and as shown in fig. 7, the apparatus 600 further includes:

a first threshold determination module 650 for determining a first threshold set comprising a third speed threshold, a fourth speed threshold and a second time threshold according to the actual segmentation result of the historical trip data set of the vehicle;

a threshold set generating module 660, configured to generate a preset number of second threshold sets according to the first threshold set;

a second segmentation result obtaining module 670, configured to use the historical trip data set as the target trip data set, replace the target threshold set by each second threshold set, perform a comparison between an average speed between every two adjacent data points in the target trip data set of the vehicle and a first speed threshold in a predetermined target threshold set, add a status flag to the identification of an abnormal segment that is used for indicating that the vehicle has abnormal signal transmission and reception and is in a stop state in each driving segment for each data point in the target trip data set, so as to obtain the preset number of second segmentation results corresponding to the historical trip data set;

a second threshold determining module 680, configured to compare each of the second segmentation results with the actual segmentation result, so as to use a second threshold set corresponding to the second segmentation result with the highest degree of overlap of the actual segmentation result as the target threshold set.

Optionally, the first stroke marking module 610 is configured to:

adding a stop status flag to a first data point in the target trip data set;

if the first average speed is greater than or equal to the first speed threshold, adding a driving state flag for the latter one of the two first data points; or,

and if the first average speed is lower than the first speed threshold, adding a stop state mark for the latter data point of the two first data points.

Optionally, the second stroke marking module 620 is configured to:

if the state of the previous first data point in the two first data points is marked as a stop state mark and the state of the next first data point in the two first data points is marked as a driving state mark, marking the next first data point as a stroke starting point;

the travel segment and the stop segment are determined from a trip start point and a trip end point in the target trip data set, wherein the travel segment includes a plurality of data points between adjacent trip start points and trip end points in the target trip data set, and the stop segment includes one or more data points between adjacent trip end points and trip start points and the adjacent trip end points and trip start points in the target trip data set.

Optionally, the abnormal segment marking module 630 is configured to:

identifying a signal missing segment in the driving segment, wherein the signal missing segment is composed of two adjacent target data points in the driving segment, and the time interval between the two target data points is greater than the first time threshold;

Optionally, the abnormal segment marking module 630 is configured to:

if the second average speed is less than the second speed threshold, marking a previous target data point in the signal missing section as a stroke end point, and marking a next target data point in the signal missing section as a stroke start point, so as to take the signal missing section as the abnormal section.

Optionally, the actual segmentation result includes: the first threshold determination module 650 is configured to determine the historical trip data set marked with the driving segment, the stopping segment and the abnormal segment by manually labeling a trip start point and a trip end point of a plurality of data points in the historical trip data set, and is configured to:

for the third speed threshold:

obtaining an average speed of the vehicle between every two data points in each stopping section in the historical travel data set to obtain a first average speed set;

acquiring an average speed of the vehicle between every two data points in each driving section in the historical travel data set to acquire a second average speed set;

for the fourth speed threshold:

acquiring the average speed of the vehicle between data points at two ends of each abnormal section in the historical travel data set so as to acquire a third average speed set;

for the second time threshold:

Optionally, the threshold group generating module 660 is configured to:

arranging and combining a third speed threshold, a fourth speed threshold and a second time threshold, and the fifth speed thresholds, the sixth speed thresholds and the third time thresholds to generate a second threshold group with the preset number; wherein,

the second set of thresholds includes: a seventh speed threshold, an eighth speed threshold and a fourth time threshold, wherein the seventh speed threshold is the third speed threshold and any one of the fifth speed thresholds, the seventh speed threshold is the fourth speed threshold and any one of the sixth speed thresholds, and the fourth time threshold is the second time threshold and any one of the third time thresholds.

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. 8 is a block diagram illustrating an electronic device 800 in accordance with an example embodiment. As shown in fig. 8, the electronic device 800 may include: a processor 801, a memory 802, a multimedia component 803, an input/output (I/O) interface 804, and a communications component 805.

The processor 801 is configured to control the overall operation of the electronic device 800, so as to complete all or part of the steps in the trip data segmentation method. The memory 802 is used to store various types of data to support operation at the electronic device 800, such as instructions for any application or method operating on the electronic device 800 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 802 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 803 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 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding Communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.

In an exemplary embodiment, the electronic Device 800 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 above-described trip data segmentation method.

In another exemplary embodiment, a computer readable storage medium, such as the memory 802, is also provided that includes program instructions executable by the processor 801 of the electronic device 800 to perform the trip data segmentation method described above.

Preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and other embodiments of the present disclosure may be easily conceived by those skilled in the art within the technical spirit of the present disclosure after considering the description and practicing the present disclosure, and all fall within 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. Meanwhile, any combination can be made between various different embodiments of the disclosure, and the disclosure should be regarded as the disclosure of the disclosure as long as the combination does not depart from the idea of the disclosure. The present disclosure is not limited to the precise structures that have been described above, and the scope of the present disclosure is limited only by the appended claims.

Claims

1. A trip data segmentation method, characterized in that the method comprises:

2. The method of claim 1, wherein prior to comparing the average speed between each two adjacent data points in the target trip data set of the vehicle to the first speed threshold in the predetermined set of target thresholds to add a status flag for each data point in the target trip data set, the method further comprises:

3. The method of claim 1, wherein comparing the average speed between each two adjacent data points in the target trip data set of the vehicle to a first speed threshold in a predetermined set of target thresholds to add a status flag for each data point in the target trip data set comprises:

adding a stop status flag to a first data point in the target trip data set;

determining a first average speed of the vehicle between two first data points according to a time point included in each of the two first data points and geographic position information corresponding to the time point, wherein the two first data points are any two adjacent data points in the target travel data set;

4. The method of claim 3, wherein the marking out of the target trip data set, according to the status flag, a travel segment characterizing that the vehicle is in a travel state and a stop segment characterizing that the vehicle is in a stop state comprises:

5. The method of claim 1, wherein said identifying an abnormal segment in each of said driving segments that is indicative of said vehicle having an abnormal signaling and being in a stopped state comprises:

6. The method of claim 5, wherein said determining whether the signal missing segment is the anomalous segment based on the second speed threshold comprises:

7. The method of claim 2, wherein the actual segmentation result comprises: determining a first threshold value set according to an actual segmentation result of the historical travel data set by the historical travel data set marked with the travel segment, the stop segment and the abnormal segment, which is determined after manual labeling of a travel starting point and a travel ending point in a plurality of data points in the historical travel data set, and the determination comprises:

for the third speed threshold:

for the fourth speed threshold:

for the second time threshold:

8. A trip data segmentation apparatus, characterized in that the apparatus comprises:

9. 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 7.

10. 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 7.