WO2017092418A1 - 过车记录处理方法和装置 - Google Patents

过车记录处理方法和装置 Download PDF

Info

Publication number
WO2017092418A1
WO2017092418A1 PCT/CN2016/096676 CN2016096676W WO2017092418A1 WO 2017092418 A1 WO2017092418 A1 WO 2017092418A1 CN 2016096676 W CN2016096676 W CN 2016096676W WO 2017092418 A1 WO2017092418 A1 WO 2017092418A1
Authority
WO
WIPO (PCT)
Prior art keywords
passing
bayonet
record
records
processing
Prior art date
Application number
PCT/CN2016/096676
Other languages
English (en)
French (fr)
Inventor
王龙
徐宇垚
赵世范
Original Assignee
杭州海康威视数字技术股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州海康威视数字技术股份有限公司 filed Critical 杭州海康威视数字技术股份有限公司
Priority to EP16869729.0A priority Critical patent/EP3385919B1/en
Priority to US15/780,754 priority patent/US10810870B2/en
Publication of WO2017092418A1 publication Critical patent/WO2017092418A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G07C5/085—Registering performance data using electronic data carriers
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles

Definitions

  • the present application relates to the field of data processing, and in particular to a method and apparatus for processing a passing record.
  • the vehicle is analyzed, that is, the position where the vehicle has not left for a long time after parking is analyzed.
  • the user inputs the time range to be analyzed and the specific time period, for example, the travel time period and the return time period of the day, because the specific time period of the vehicle can be arbitrarily set, and the pre-processing is added. Difficulty.
  • the user performs the foothold analysis in real time, and the processed data is the passing record of all the bayonet ports of the specified vehicle in a specific time period, and the amount of data to be processed is large and takes a long time.
  • this method counts all the bayonets that the vehicle passes during the specific time period of the time range and the number of passes corresponding to the bayonet. If the specified specific time period is not the time period of the regular travel of the vehicle, then the final statistics The result is only the statistics of the bayonet of the route.
  • the output is the collection of isolated bayonets arranged in descending order of the number of passes. Although it can reflect the bayonet that passes frequently, it will miss many conventional stops, which is not good. The area where the vehicle is located is displayed, so the result obtained by this method is not accurate and cannot achieve the purpose of the analysis.
  • the main purpose of the present application is to provide a passing record processing method and apparatus to solve the problem of inaccurate analysis of the vehicle landing point.
  • a method for processing a passing record comprising: acquiring a plurality of passing records of a preset target object within a first preset time period, wherein the passing vehicle
  • the record includes the bayonet number of the bayonet that the preset target object passes each time and the transit time when the bayonet passes; according to the plurality of passing records, the plurality of driving tracks of the preset target object are acquired; and the driving track is pre-set Processing, obtaining pre-processing results; obtaining pre-processing records satisfying the first preset condition from the pre-processing results; performing clustering processing on the pre-processing records to obtain clustering processing results; and outputting clustering processing results.
  • acquiring a plurality of passing records of the preset target object in the first preset time period including: sorting the plurality of passing records according to the passing time; and obtaining the time difference of the adjacent passing records;
  • the time difference of the neighboring vehicle records divides the plurality of passing records to obtain a dividing track, wherein the plurality of passing records are divided into the first type of passing record and the second type of passing record, and the first type of passing record is
  • the plurality of passing records extract the adjacent passing records whose time difference exceeds the second preset time, and the second type of passing records records the adjacent passing records in which the time difference does not exceed the second preset time in the plurality of passing records.
  • the first passing record in the first type of passing record is the end point of the previous dividing track.
  • the last passing record in the first type of passing record is the starting point of the next dividing track, and the dividing track includes the second type of passing record.
  • performing pre-processing on the driving trajectory to obtain a pre-processing result includes: obtaining a starting point and an ending point of each divided trajectory in the driving trajectory; and counting the number of occurrences of the starting point or the ending point in the first preset time period, wherein The number of times the start point or the end point appears in the first preset time period is the number of passes of the bayonet corresponding to the start point or the end point; and the number of the bayonet number of the bayonet corresponding to the start point or the end point and the number of passes of the bayonet are obtained, and the pre-processing result is obtained.
  • the method further includes: grouping the pre-processed records according to the same card slot number to obtain pre-processed records of the plurality of groups, where The pre-processing records of the same card slot number are divided into one group, and the plurality of card slot numbers respectively correspond to the pre-processing records of the plurality of groups; respectively, the number of passing times corresponding to the pre-processing records of the plurality of groups are respectively summed, and respectively obtained corresponding to each The total number of passes of the groups; and the mapping relationship between the plurality of bayonet numbers and the total number of passes corresponding to each group.
  • the pre-processing records are clustered to obtain a clustering processing result, which includes: clustering the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the mapping relationship, and obtaining clustering processing results. Specifically, acquiring latitude and longitude information of the bayonet of the plurality of groups; and clustering the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the latitude and longitude information of the bayonet of the plurality of groups, and obtaining a plurality of The result of clustering processing of the kind.
  • the method further includes: calculating a plurality of types of clustering processing results in each of the clustering processing results in the plurality of The weight of the clustering processing result of the kind; outputting the clustering processing result, comprising: displaying the plurality of kinds of clustering processing results in combination with weights in different regions.
  • an apparatus for processing a passing record comprising: a first acquiring unit, configured to acquire a plurality of preset target objects within a first preset time period a passing record, wherein the passing record includes a bayonet number of the bayonet that the preset target object passes each time and a transit time when the bayonet passes; the second obtaining unit is configured to obtain a preset according to the plurality of passing records a plurality of driving trajectories of the target object; a preprocessing unit configured to perform pre-processing on the driving trajectory to obtain a pre-processing result; and a third acquiring unit configured to obtain the satisfaction from the pre-processing result a pre-processing record of the first preset condition; a clustering processing unit configured to perform clustering processing on the pre-processed record to obtain a clustering processing result; and an output unit configured to output the clustering processing result.
  • the first acquiring unit of the device includes: a sorting module, configured to sort the plurality of passing records according to the passing time; and the first acquiring module is configured to: perform multiple times according to the time difference of the adjacent passing records
  • the passing record is divided to obtain the time difference of the adjacent passing record; the dividing module is used to divide the plurality of passing records to obtain the dividing track, wherein the plurality of passing records are classified into the first type of passing record and the first
  • the second type of passing record wherein the first type of passing record is an adjacent passing record in which the time difference is extracted in the plurality of passing records exceeds the second preset time, and the second type of passing record is extracted from the plurality of passing records.
  • the time difference does not exceed the adjacent passing record of the second preset time.
  • the first passing record in the first type of passing record is the end point of the previous dividing track, and the last passing record in the first type of passing record is the next one.
  • the starting point of the trajectory is divided, and the trajectory includes a second type of passing
  • the preprocessing unit of the device includes: a second acquiring module, configured to acquire a starting point and an ending point of each divided track in the driving track; and a statistics module, configured to count the starting point or the ending point in the first preset time period The number of occurrences, wherein the number of times is the number of passes of the bayonet corresponding to the start point or the end point; and the third obtaining module is configured to obtain the bayonet number and the number of passes of the bayonet corresponding to the start point or the end point, and obtain the pre-processing result.
  • the device further includes: a grouping unit, configured to group the pre-processed records according to the same card slot number after obtaining the pre-processed record that satisfies the first preset condition from the pre-processing result, to obtain multiple groups Pre-processing record, wherein the pre-processing records of the same card slot number are divided into one group, and the plurality of card slot numbers respectively correspond to the pre-processing records of the plurality of groups; the summation unit is configured to respectively correspond to the pre-processing records of the plurality of groups The number of passing times is summed to obtain the total number of passing times corresponding to each group; and the establishing unit is configured to respectively establish a mapping relationship between the plurality of card slot numbers and the total number of passing times corresponding to each group.
  • a grouping unit configured to group the pre-processed records according to the same card slot number after obtaining the pre-processed record that satisfies the first preset condition from the pre-processing result, to obtain multiple groups Pre-processing record
  • the clustering processing unit of the device is configured to perform clustering processing on the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the mapping relationship, to obtain a clustering processing result;
  • the cluster processing unit The method includes: a fourth obtaining module, configured to acquire latitude and longitude information of the bayonet of the plurality of groups; and a clustering processing module, configured to, according to the latitude and longitude information of the bayonet of the plurality of groups, the plurality of bayonet numbers and corresponding to each group The total number of passes is clustered to obtain multiple types of clustering results.
  • the device further includes: a calculating unit, configured to perform clustering processing on the pre-processed records to obtain the clustering processing result of the plurality of categories, and calculate the clustering processing result of the multiple types The weight of each of the clustering processing results in the plurality of types of clustering processing results, wherein the output unit of the apparatus is configured to display the plurality of kinds of clustering processing results in different regions in combination with the weights.
  • a calculating unit configured to perform clustering processing on the pre-processed records to obtain the clustering processing result of the plurality of categories, and calculate the clustering processing result of the multiple types The weight of each of the clustering processing results in the plurality of types of clustering processing results, wherein the output unit of the apparatus is configured to display the plurality of kinds of clustering processing results in different regions in combination with the weights.
  • the application provides an electronic device including: a housing, a processor, and a storage And a circuit board and a power supply circuit, wherein the circuit board is disposed inside a space enclosed by the casing, the processor and the memory are disposed on the circuit board; and the power circuit is configured to Each of the circuits or devices of the electronic device is powered; the memory is for storing executable program code; the processor executes the pass record processing method by running executable program code stored in the memory.
  • the present application also provides an executable program code for executing the passing record processing method at runtime.
  • the present application also provides a storage medium for storing executable program code that is executed to execute the passing record processing method.
  • a plurality of passing records of the preset target object in the first preset time period are obtained, wherein the passing record includes the bayonet number of the bayonet that the preset target object passes each time and the passing of the bayonet
  • the plurality of driving trajectories of the preset target object are obtained, and the driving trajectory is pre-processed to obtain the pre-processing result, and then the pre-supplement result is obtained from the pre-processing result.
  • the records are processed, and the pre-processed records are clustered to obtain clustering processing results, and finally the clustering processing results are output.
  • the problem of inaccurate analysis of the foothold is solved, and the accuracy of the analysis of the foothold is improved.
  • FIG. 1 is a flowchart of a method of processing a passing record according to a first embodiment of the present application
  • FIG. 2 is a flowchart of a method of processing a passing record according to a second embodiment of the present application
  • FIG. 3 is a schematic diagram of a vehicle trajectory analysis according to an embodiment of the present application.
  • FIG. 4 is a flowchart of a method of processing a passing record according to a third embodiment of the present application.
  • FIG. 5 is a schematic diagram of a landing point according to a bayonet according to an embodiment of the present application.
  • Figure 6 is a schematic diagram of a passing record processing apparatus according to a first embodiment of the present application.
  • Figure 7 is a schematic diagram of a passing record processing apparatus according to a second embodiment of the present application.
  • Figure 8 is a schematic diagram of a passing record processing apparatus according to a third embodiment of the present application.
  • Figure 9 is a schematic diagram of a passing record processing apparatus according to a fourth embodiment of the present application.
  • Figure 10 is a schematic diagram of a passing record processing apparatus according to a fifth embodiment of the present application.
  • Figure 11 is a schematic diagram of a passing record processing apparatus according to a sixth embodiment of the present application.
  • FIG. 12 is a schematic diagram of an electronic device in accordance with an embodiment of the present application.
  • the location of the vehicle within the specified time period can be analyzed according to the driving trajectory of the suspect vehicle in the bayonet system, and the location of the suspected vehicle can be analyzed.
  • Clustering The process of concentrating data in some aspects of similar data members for classification and organization. Clustering is a technique for discovering this internal structure. Clustering technology is often called unsupervised learning.
  • K-means clustering algorithm (K-means) K-means algorithm is a hard clustering algorithm. It is a representative prototype-based objective function clustering method. It is based on a certain distance from the data point to the prototype. The function uses the function to find the extremum method to get the adjustment rules of the iterative operation.
  • the K-means algorithm takes the Euclidean distance as the similarity measure, which is to find the optimal classification of the V-corresponding to a certain initial cluster center vector, so that the evaluation index J is the smallest.
  • the algorithm uses the error squared criterion function as a clustering criterion function.
  • a track refers to an ordered collection of the passing records of a license plate in a period of time. The time difference between two adjacent passing records exceeds the preset time and is divided into two tracks.
  • the embodiment of the present application provides a method for processing a passing record.
  • FIG. 1 is a flow chart of a method of processing a passing record according to a first embodiment of the present application. As shown in FIG. 1, the method for processing the passing record includes the following steps:
  • Step S102 Acquire a plurality of passing records of the preset target object in the first preset time period.
  • the vehicle that specifies the license plate analyzes the position of the vehicle during the specified time period after parking.
  • the coverage of the vehicle by the specified period of time that is, the driving trajectory of the vehicle passing through the bayonet within a specified period of time, is used to analyze the position of the vehicle staying.
  • the preset target object has different travel records through different bayonet at different time periods, wherein
  • the passing record includes the bayonet number of the bayonet that the preset target object passes each time and the transit time when the bayonet passes.
  • acquiring a plurality of passing records of the preset target object in the first preset time period wherein the passing record includes the bayonet number of the bayonet that the preset target object passes each time and the passing of the bayonet Travel time.
  • the preset target object is in the time period from 6 o'clock to 12 o'clock in the first preset time, when the passing record is 6 times, the card slot is 1, 7 when the card slot is 2, 9 is past the card slot 3, 10 hours. Pass the bayonet 5 through the bayonet 4,12.
  • the plurality of passing records After acquiring a plurality of passing records of the preset target object in the first preset time period, the plurality of passing records are sorted according to the passing time of the preset target object, and then the passing time of the preset target object is preset. Get the time difference between adjacent travel records.
  • the bayonet 2 is passed through the bayonet 1 and 7, the bayonet 1 and the bayonet 2 have a time difference of 1 hour, and at 7 o'clock, the bayonet 2, 9 passes through the bayonet 3, and the card
  • the time difference between port 2 and bayonet 3 is 2 hours
  • 9 o'clock passes the bayonet 3
  • 10 o'clock passes the bayonet 4
  • the bayonet 3 and the bayonet 4 have a time difference of 1 hour
  • 10 o'clock passes the bayonet 4
  • 12 passes the card
  • the time difference between the mouth 5 and the bayonet 4 is 2 hours.
  • the plurality of passing records are divided to obtain a dividing track.
  • the plurality of passing records may be divided by the second preset time, wherein the plurality of passing records are divided into the first type of passing record and the second type of passing record,
  • the first type of passing record records the adjacent passing records in which the time difference exceeds the second preset time in the plurality of passing records, and the second type of passing records records the time difference of the plurality of passing records not exceeding the second preset time.
  • the adjacent passing record, the first passing record in the first type of passing record is the end point of the previous dividing track, and the last passing record in the first type of passing record is the starting point of the next dividing track, and the dividing track includes The second type of passing record.
  • the first passing record is the starting point of the first dividing track, and the last passing record is the ending point of the last dividing track.
  • the second preset time is 1.5 hours, when the target object 6 is preset, the bayonet 2 is the second type of passing record when the bayonet 1 and the 7 are passed, and the bayonet 2 and the 9th pass the bayonet when the bayonet is 2 and 9 3 is the first type of passing record, 9 o'clock over the bayonet 3 and 10 when the bayonet 4 is the second type of passing record, 10 o'clock over the bayonet 4 and 12 when the bayonet 5 is the first type of passing record . Then, at 6 o'clock, the bayonet 2 is a dividing track when passing through the bayonet 1 and 7, and the bayonet 5 is another dividing track when passing the bayonet 4 and 12 through the bayonet 3 and 10.
  • the bayonet 5 is the last passing record. Therefore, at 9 o'clock, when the bayonet 3, 10 passes the bayonet 4, 12, the bayonet 5 is another dividing track.
  • a divided trajectory can be understood as a driving trajectory.
  • Step S104 Acquire a plurality of driving trajectories of the preset target object according to the plurality of passing records.
  • acquiring a plurality of passing records of the preset target object in the first preset time period After acquiring a plurality of passing records of the preset target object in the first preset time period, acquiring a plurality of driving tracks of the preset target object according to the plurality of passing records, that is, acquiring a license plate for a period of time An ordered collection of passing records sorted by time, when the difference between two adjacent passing records exceeds the pre- When the time is set, it is divided into two tracks.
  • the plurality of passing records After acquiring a plurality of passing records of the preset target object in the first preset time period, the plurality of passing records are sorted according to the passing time of the preset target object, and then the passing time of the preset target object is preset. Get the time difference between adjacent travel records.
  • the bayonet 2 is passed through the bayonet 1 and 7, the bayonet 1 and the bayonet 2 have a time difference of 1 hour, and at 7 o'clock, the bayonet 2, 9 passes through the bayonet 3, and the card
  • the time difference between port 2 and bayonet 3 is 2 hours
  • 9 o'clock passes the bayonet 3
  • 10 o'clock passes the bayonet 4
  • the bayonet 3 and the bayonet 4 have a time difference of 1 hour
  • 10 o'clock passes the bayonet 4
  • 12 passes the card
  • the time difference between the mouth 5 and the bayonet 4 is 2 hours.
  • the plurality of passing records are divided to obtain a dividing track.
  • step S106 the driving track is pre-processed to obtain a pre-processing result.
  • the landing point is a position where the preset target object does not leave after the second preset time is stopped, and after the driving trajectory of the preset target object is acquired, the driving trajectory is pre-processed.
  • Obtaining the starting point and the ending point of each divided track in the driving track, and counting the number of times that the starting point or the ending point of each divided track appears within the first preset time period, that is, counting each divided track in the first preset time The number of passes of the bayonet corresponding to the starting point or the end point.
  • the bayonet number and the number of passes of the bayonet corresponding to the starting point or the ending point of each divided track are obtained, and the pre-processing result is obtained.
  • the starting point of the dividing trajectory of the card slot 2 at 6 o'clock crossing the card slot 1 and 7 is 6 when the card slot 1 is passed, and the end point is 7
  • the card slot is 2.
  • the starting point of the dividing track of the bayonet 5 is 9 when the bayonet 3 is crossed, and when the end point is 12, the bayonet 5 is crossed.
  • the pre-processing result is 6 when the bayonet 1 is passed, the number of passing times is 1 time, and the crossing time is 7 times.
  • the number of passing times is 1 time
  • the bayonet 3 is passed at 9 o'clock, the number of passing times is 1 time
  • the crossing time is 5 at 12 o'clock, and the number of passing times is 1 time.
  • Step S108 Obtain a pre-processing record that satisfies the first preset condition from the pre-processing result.
  • the driving trajectory of the plurality of preset target objects in a plurality of preset time periods may be acquired, and the pre-processing results in the plurality of preset time periods are obtained, for example, the preset target object is acquired from January 1, 2015 to 2015.
  • the trajectory of the vehicle on June 30, obtained the pre-processing results of the preset target object from January 1, 2015 to June 30, 2015.
  • the first preset condition may be a license plate number and a start and end date.
  • the pre-processed records are grouped according to the same card slot number, and the same card slot number is a group, thereby obtaining a plurality of groups composed of different card slot numbers, and the plurality of groups respectively save the pre-corresponding to the card slot number.
  • the mapping relationship of the number of passing times is obtained by the total number of passing times corresponding to each card slot number and bayonet number. set.
  • the driving trajectory from January 1, 2015 to January 3, 2015 is: at 6 o'clock, the bayonet 1 is crossed, the number of passes is 1, and at 7 o'clock, the number of passes is 1 time, 9 o'clock over the bayonet 3, the number of passing times is 1 time, 12 o'clock crossing the bayonet 5, the number of passing times is 1; at 6 o'clock crossing the bayonet 1, the number of passing times is 2 times, 7 o'clock Passing the bayonet 2, the number of passing times is 1 time, at 9 o'clock, the bayonet 3 is crossed, the number of passing times is 3 times, the crossing time is 12 at 12 o'clock, the number of passing times is 2 times; The number of passing times is 2 times.
  • the bayonet 2 is crossed.
  • the number of passing times is 1 time.
  • the bayonet 3 is crossed.
  • the number of passing times is 3 times.
  • the number of passing passes is 5, and the number of passing times is 2 times.
  • the bayonet 1, the bayonet 2, the bayonet 3, the bayonet 4, and the bayonet 5 respectively correspond to five groups
  • the total number of passing times of the third group is all the number of passing times of the bayonet 3
  • the bayonet 1 can be obtained 5 times
  • the card Port 2 corresponds to 3 times
  • bayonet 3 corresponds to 7 times
  • bayonet 5 corresponds to 5 mappings
  • the number of passes corresponding to each bayonet number and bayonet number and the bayonet are elements of the set.
  • Step S110 performing clustering processing on the preprocessed records to obtain clustering processing results.
  • Obtaining a pre-processing record that satisfies the first preset condition from the pre-processing result, and obtaining a set of total number of passing times corresponding to each bayonet number and bayonet number, and each element in the set is similar in some aspects
  • the data members for example, the number of passes corresponding to each bayonet number and bayonet number, and the similarity of the position information between the elements of the bayonet, are classified and organized, and can be classified and organized by clustering processing to find similar structures.
  • a K-means clustering algorithm is used to implement clustering processing on pre-processed records, and the amount of data calculation after pre-processing is reduced.
  • the clustering processing of the pre-processing records includes: clustering the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the mapping relationship, first acquiring the latitude and longitude information of the bayonet of the plurality of groups, according to the plurality of groups
  • the latitude and longitude information of the bayonet is clustered by a plurality of bayonet numbers and the total number of passing times corresponding to each group to obtain a plurality of kinds of clustering processing results, for example, a plurality of kinds of clustering processing results by position Far and near to divide, the position of the bayonet with a certain degree of similarity constitutes a class, this class corresponds to a region.
  • step S112 the clustering processing result is output.
  • the output clustering processing result includes: displaying a plurality of kinds of clustering processing results combined with weights in different regions, analyzing performance of each type of clustering processing result in the overall clustering processing result, and improving real-time analysis performance.
  • the clustering processing result is displayed on the map, and a cluster corresponding to the bayonet corresponds to the set An area, which is displayed on the map in different colors according to various weights.
  • the color ranges from light to dark and can represent changes in weight from small to large.
  • a plurality of passing records of the preset target object in the first preset time period are acquired, and then multiple driving tracks of the preset target object are acquired according to the plurality of passing records, and the driving track is preset.
  • the result of the analysis of the landing point is obtained more quickly, the accuracy of the analysis of the vehicle landing point is improved, and the real-time analysis performance of the vehicle landing point is improved.
  • FIG. 2 is a flow chart of a method for processing a passing record according to a second embodiment of the present application. It should be noted that the method for processing the passing record includes analyzing the driving trajectory. As shown in FIG. 2, the method for processing the passing record includes the following steps:
  • Step S202 grouping a plurality of preset target objects.
  • the object can simultaneously analyze the driving trajectory. Obtain all the travel records of the same license plate, including the bayonet number of the bayonet that the preset target object passes each time and the transit time when the bayonet passes.
  • step S204 all the travel records of the same license plate are sorted according to the transit time.
  • the passing record includes the bayonet number of the bayonet that the preset target object passes each time and the passing time when the bayonet passes, and the plurality of passing records of the preset target object are sorted according to the passing time, for example, according to clockwise Sort the passing records sequentially.
  • step S206 the passing record is divided to obtain a divided track.
  • the trajectory idea is adopted, that is, the starting and ending point of the trajectory corresponds to the passing record of the nearest bayonet of the landing point, and the card slot number is analyzed according to the license plate of the preset target object. A mapping relationship with the number of passing times is obtained.
  • the plurality of passing records may be divided by the second preset time, wherein the plurality of passing records are divided into the first type of passing record and the second type of passing record, and the first type of passing record is multiple
  • the vehicle record records an adjacent passing record whose time difference exceeds the second preset time, and the second type of passing record records the adjacent passing record in which the time difference is not more than the second preset time in the plurality of passing records, the first type
  • the previous passing record in the passing record is the end point of the previous dividing track.
  • the last passing record in the first type of passing record is the starting point of the next dividing track, and the dividing track includes the second type of passing record.
  • the first passing record is the starting point of the first dividing track
  • the last passing record is the ending point of the last dividing track.
  • the driving trajectory of the preset target object is analyzed by dividing the passing record, and FIG. 3 is based on the present
  • a schematic diagram of the trajectory analysis of the application embodiment is shown in FIG. 3, and the trajectory of the vehicle with the brand name A8888 is analyzed.
  • the time of mouth The vehicle with the grade of A8888 passes through the bayonet 1, bayonet 2, bayonet 3, bayonet 4 and bayonet 5 within 24 hours. Calculate the time difference of Zhejiang A8888 in the adjacent passing record.
  • the previous passing record in the adjacent passing record is counted as the ending point of the previous dividing track, and the next passing record in the adjacent passing record
  • the car record counts as the starting point for the next segmentation trajectory, thus obtaining all the trajectories of the license plate.
  • the vehicle of Zhe A8888 is at 6:19, the bayonet passes 1, 7:1, and the bayonet 2, and so on.
  • the time interval of the defined trajectory is 2, there are 3 trajectories of the final day.
  • the track formed by the bayonet 1, the bayonet 2 and the bayonet 3, the track formed by the bayonet 4, the bayonet 5 and the bayonet 6, the bayonet 3, the bayonet 2 and the bayonet 1 constitute a trajectory.
  • step S208 the starting point and the ending point of each divided track of the same license plate are taken out.
  • the total number of passes at the starting point or the end point is [license plate: Zhejiang A8888, date: 20150101, [ ⁇ bayonet: 1, number of times: 2 ⁇ , ⁇ bayonet: 3, number: 2 ⁇ , ⁇ Bayonet: 4, the number of times: 1 ⁇ , ⁇ mount: 6, number of times: 1 ⁇ ], to achieve the pre-processing of the landing point.
  • S202, S204, S206 and S208 can be understood as an implementation of S106.
  • a plurality of preset target objects are grouped, all the driving records of the same license plate are sorted according to the passing time, and then the passing records are divided to obtain a dividing track, and then the starting point of each dividing track of the same license plate is taken out. And the end point, pre-processing the landing point, to achieve the analysis of the driving trajectory and the pre-processing of the landing point.
  • FIG. 4 is a flow chart of a method for processing a passing record according to a third embodiment of the present application. It should be noted that the method for processing the passing record includes an analysis of a landing point. As shown in FIG. 4, the method for processing the passing record includes the following steps:
  • Step S302 extracting a preprocessed record.
  • the user After analyzing the driving trajectory of the preset target object and pre-processing the landing point of the preset target object, the user analyzes the landing point of the target object in the first preset time period.
  • the first preset condition is set as the start and end date and the license plate number, and the distributed computing engine is used to simultaneously analyze the landing points of the plurality of preset target objects according to the first preset condition.
  • the first preset time range In the first preset time range, a preprocessed record of all dates meeting the first preset condition is found from the pre-processed result.
  • Step S304 grouping the pre-processed records according to the card slot number.
  • FIG. 5 is a schematic diagram of a landing point according to a bayonet according to an embodiment of the present application.
  • the preset target object is a vehicle with a license plate number of A8888, and the first preset time is January 1, 2015.
  • the pre-processing records of the same card slot number in the pre-processing record on June 31, 2015 are divided into one group, and the pre-processing records of multiple groups are obtained.
  • the results of the group are 1 to n groups, and the groups 1 to n are respectively Corresponding to the corresponding bayonet number, n bayonet numbers correspond to pre-processed records of groups 1 to n, respectively.
  • bayonet number After grouping according to the bayonet number, all the number of passes of the same bayonet from January 1, 2015 to June 31, 2015 are summed, and the total number of trips corresponding to each group is obtained, for example, bayonet. 1 is 260 times, bayonet 3 is 240 times, bayonet 4 is 50 times, bayonet 6 is 30 times, bayonet n is 1 time, and finally several card slot numbers are established and the total number of cars corresponding to each group is established.
  • the mapping relationship of the number of times can be obtained as a collection of [Card number, total number of passes].
  • Step S306 performing clustering processing on the pre-processed records of the group.
  • Performing clustering processing on the pre-processed records of the group includes clustering the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the mapping relationship, and combining the latitude and longitude information of the bayonet of the plurality of groups, according to the plurality of groups
  • the latitude and longitude information of the bayonet is clustered by a plurality of bayonet numbers and a total number of passing times corresponding to each group.
  • the K-means clustering algorithm is used to form a class N, thereby Obtaining a plurality of types of clustering processing results, each of which is a subset of the total number of bayonet and passing times in step S304.
  • the results of clustering processing of multiple types are divided according to the distance of the location, and the position is to some extent. Similar bayonets form a class that corresponds to an area.
  • the weights of each of the plurality of types of clustering processing results in the plurality of types of clustering processing results are calculated, and the weights of the specific types of clustering processing results in all the landing points are obtained.
  • S302, S304 and S306 can be understood as an implementation of S110.
  • step S308 the clustering processing result is displayed.
  • the clustering processing result on the map the set of the [Card number, total number of passing times] of one type of clustering is used as a region, and the results of the clustering processing of the plurality of types are combined in different regions, and according to each Class weights are displayed on the map in different colors, ranging from light to dark, and can represent changes in weight from small to large.
  • the pre-processing records are extracted, and then the pre-processing records are grouped according to the card slot number, and then the grouped pre-processing records are clustered, and finally the clustering processing results are displayed, which reduces the amount of data calculation after pre-processing, and Quickly get the analysis results of the foothold, and realize the analysis of the landing point, which improves the accuracy of the vehicle landing analysis and improves the real-time analysis performance of the vehicle landing point.
  • the embodiment of the present application further provides a passing record processing device. It should be noted that the passing record processing device of the embodiment of the present application can be used to execute the passing record processing method of the embodiment of the present application.
  • Fig. 6 is a schematic diagram of a passing record processing apparatus according to a first embodiment of the present application. As shown in FIG. 6, the apparatus includes: a first acquisition unit 10, a second acquisition unit 20, a pre-processing unit 30, a third acquisition unit 40, a cluster processing unit 50, and an output unit 60.
  • the first obtaining unit 10 is configured to acquire a plurality of passing records of the preset target object in the first preset time period, wherein the passing record includes a card slot number and a pass card of the bayonet that each preset target object passes Passing time at the mouth.
  • the second obtaining unit 20 is configured to acquire a plurality of driving trajectories of the preset target object according to the plurality of passing records. After the first obtaining unit 10 acquires the plurality of passing records of the preset target object in the first preset time period, the second obtaining unit 20 acquires the plurality of driving tracks of the preset target object according to the plurality of passing records, That is, an ordered collection of time-ordered travel records of a license plate over a period of time is obtained, and when the time difference between two adjacent travel records exceeds a preset time, it is divided into two tracks.
  • the pre-processing unit 30 is configured to perform pre-processing on the driving track to obtain a pre-processing result.
  • the landing point is a position where the preset target object does not leave after the second preset time is stopped.
  • the pre-processing unit 30 After acquiring the driving trajectory of the preset target object, the pre-processing unit 30 performs the foot-point pre-processing on the driving trajectory. Obtaining the starting point and the ending point of each divided track in the driving track, and counting the number of times that the starting point or the ending point of each divided track appears within the first preset time period, that is, counting each divided track in the first preset time The number of passes of the bayonet corresponding to the starting point or the end point. Finally, the bayonet number and the number of passes of the bayonet corresponding to the starting point or the ending point of each divided track are obtained, and the pre-processing result is obtained.
  • the third obtaining unit 40 is configured to obtain, from the pre-processing result, a pre-processing record that satisfies the first preset condition.
  • the driving trajectory of the plurality of preset target objects in the plurality of preset time periods may be acquired, and the pre-processing results in the plurality of preset time periods are obtained.
  • the pre-processed records are grouped according to the same card slot number, and the same card slot number is a group, thereby obtaining a plurality of groups composed of different card slot numbers, and the plurality of groups respectively save the pre-corresponding to the card slot number.
  • the clustering processing unit 50 is configured to perform clustering processing on the pre-processed records to obtain clustering processing results.
  • the third obtaining unit 40 obtains a pre-processing record that satisfies the first preset condition from the pre-processing result, and obtains a set consisting of the total number of passes corresponding to each card slot number and the card slot number, and each element in the set is in a certain.
  • there are similar data members for example, the number of passing times corresponding to each bayonet number and the bayonet number, and the similarity of the position information between the elements of the bayonet, which are classified and organized, and the cluster processing unit 50 performs clustering processing. Similar structures were found and classified and organized.
  • the clustering processing unit 50 employs a K-means clustering algorithm to implement clustering processing on the pre-processed records.
  • Performing clustering processing on the pre-processing records includes clustering processing the plurality of bayonet numbers and the total number of passing times corresponding to each group according to the mapping relationship, and first acquiring latitude and longitude information of the bayonet ports of the plurality of groups, according to the plurality of groups
  • the latitude and longitude information of the bayonet clusters the plurality of bayonet numbers and the total number of passing times corresponding to each group to obtain a plurality of kinds of clustering processing results, for example, the plurality of kinds of clustering processing results are in accordance with the position To divide, the bayonet positions with a certain degree of similarity form a class, which corresponds to a region.
  • the output unit 60 is configured to output a clustering processing result. After the clustering processing unit 50 performs clustering processing on the pre-processed records to obtain a plurality of types of clustering processing results, the clustering processing results of the plurality of types of clustering processing results are calculated in a plurality of types of clustering processing results. The weights in the class processing result, the output unit 60 combines the weights of the plurality of kinds of clustering processing results in different regions.
  • Fig. 7 is a schematic diagram of a passing record processing apparatus according to a second embodiment of the present application.
  • the apparatus includes: a first obtaining unit 10, a pre-processing unit 30, a second obtaining unit 20, a third obtaining unit 40, a clustering processing unit 50, and an output unit 60, wherein the first acquiring unit 10
  • the sorting module 11, the first obtaining module 12 and the dividing module 13 are included.
  • the functions of the first obtaining unit 10, the pre-processing unit 30, the second obtaining unit 20, the third obtaining unit 40, the clustering processing unit 50, and the output unit 60 in this embodiment are the same as the driving record of the second embodiment of the present application. The same in the processing device.
  • the sorting module 11 is configured to sort the plurality of passing records according to the passing time. After acquiring a plurality of passing records of the preset target object in the first preset time period, the sorting module 11 sorts the plurality of passing records according to the passing time of the preset target object.
  • the first obtaining module 12 is configured to acquire a time difference of the adjacent passing record. Specifically, the first obtaining module 12 acquires the time difference of the adjacent passing record by preset the passing time of the target object.
  • the dividing module 13 is configured to divide a plurality of passing records to obtain a dividing track. After the first acquisition module 12 presets the transit time of the target object to obtain the time difference of the adjacent passing record, the dividing module 13 divides the plurality of passing records to obtain the divided trajectory.
  • the plurality of passing records may be divided by the second preset time, wherein the plurality of passing records are divided into the first type of passing record and the second type of passing record, The first type of passing record records the adjacent passing records in which the time difference exceeds the second preset time in the plurality of passing records, and the second type of passing records records the time difference of the plurality of passing records not exceeding the second preset time.
  • the adjacent passing record, the first passing record in the first type of passing record is the end point of the previous dividing track, and the last passing record in the first type of passing record is the starting point of the next dividing track, and the dividing track includes The second type of passing record.
  • the first passing record is the starting point of the first dividing track, and the last passing record is the ending point of the last dividing track.
  • the second obtaining unit 20 includes a sorting module, the first obtaining Modules and partitioning modules.
  • Sorting module for sorting multiple passing records according to the passing time. After acquiring the plurality of passing records of the preset target object in the first preset time period, the sorting module sorts the plurality of passing records according to the passing time of the preset target object.
  • the first obtaining module is configured to acquire a time difference of the adjacent passing record. Specifically, the first acquisition module acquires the time difference of the adjacent passing record by preset the passing time of the target object.
  • the dividing module is configured to divide a plurality of passing records to obtain a dividing track. After the first acquisition module presets the transit time of the target object to obtain the time difference of the adjacent passing record, the dividing module divides the plurality of passing records to obtain a dividing track.
  • the plurality of passing records may be divided by the second preset time, wherein the plurality of passing records are divided into the first type of passing record and the second type of passing record, The first type of passing record records the adjacent passing records in which the time difference exceeds the second preset time in the plurality of passing records, and the second type of passing records records the time difference of the plurality of passing records not exceeding the second preset time.
  • the adjacent passing record, the first passing record in the first type of passing record is the end point of the previous dividing track, and the last passing record in the first type of passing record is the starting point of the next dividing track, and the dividing track includes The second type of passing record.
  • the first passing record is the starting point of the first dividing track, and the last passing record is the ending point of the last dividing track.
  • FIG. 8 is a schematic diagram of a passing record processing apparatus according to a third embodiment of the present application.
  • the apparatus includes: a first obtaining unit 10, a second obtaining unit 20, a pre-processing unit 30, a third obtaining unit 40, a clustering processing unit 50, and an output unit 60, wherein the first acquiring unit 10
  • the sequence module 11 includes a first acquisition module 12 and a partitioning module 13.
  • the pre-processing unit 30 includes a second acquisition module 31, a statistics module 32, and a third acquisition module 33.
  • the role of 13 is the same as that in the passing record processing apparatus of the second embodiment of the present application.
  • the second obtaining module 31 is configured to obtain a starting point and an ending point of each of the divided tracks in the driving track.
  • the landing point is a position where the preset target object does not leave after the second preset time is stopped, and after the driving trajectory of the preset target object is acquired, the driving trajectory is pre-processed.
  • the second acquisition module 31 acquires the start point and the end point of each of the divided tracks in the driving track.
  • the statistics module 32 is configured to count the number of occurrences of the starting point or the ending point in the first preset time period, wherein the number of times is the number of times of crossing of the bayonet corresponding to the starting point or the ending point.
  • the statistics module 32 counts the number of occurrences of the start point or the end point of each divided track in the first preset time period, that is, counts the passing of the bayonet corresponding to the start point or the end point of each divided track in the first preset time. frequency.
  • the third obtaining module 33 is configured to obtain the bayonet number and the number of passes of the bayonet corresponding to the starting point or the end point, and obtain a pre-processing result. Acquiring the start point or the end point of each divided track by the third obtaining module 33 The bayonet number of the bayonet and the number of passes to get the pre-processing results.
  • Figure 9 is a schematic diagram of a passing record processing apparatus according to a fourth embodiment of the present application.
  • the apparatus includes: a first obtaining unit 10, a pre-processing unit 30, a third obtaining unit 40, a clustering processing unit 50, and an output unit 60, further comprising: a grouping unit 70, a summing unit 80, and The unit 90 is established.
  • the functions of the first obtaining unit 10, the pre-processing unit 30, the third obtaining unit 40, the clustering processing unit 50, and the output unit 60 in this embodiment are the same as those in the passing record processing device of the first embodiment of the present application.
  • the grouping unit 70 is configured to: after obtaining the pre-processed records satisfying the first preset condition from the pre-processing result, group the pre-processed records by the same card slot number to obtain pre-processed records of the plurality of groups, wherein the same card slot number
  • the pre-processing record is divided into one group, and the plurality of card slot numbers respectively correspond to the pre-processing records of the plurality of groups.
  • the grouping unit 70 groups the pre-processed records according to the same card slot number, and the same card slot number is a group, thereby obtaining a plurality of groups composed of different card slot numbers, and the plurality of groups are separately saved.
  • the summation unit 80 is configured to respectively sum the number of passing times corresponding to the pre-processed records of the plurality of groups, and obtain the total number of passing times corresponding to the plurality of groups respectively.
  • the establishing unit 90 is configured to respectively establish a mapping relationship between the plurality of bayonet numbers and the total number of passing times corresponding to the plurality of groups.
  • the establishing unit 90 respectively establishes a mapping relationship between the plurality of bayonet numbers and the total number of passing times of each group, and obtains a set of total number of passing times corresponding to each bayonet number and the bayonet number.
  • the first obtaining unit 10 is further configured to acquire a driving trajectory of the preset target object in a plurality of preset time periods
  • the pre-processing unit 30 is further configured to perform pre-processing on the driving trajectory to obtain a plurality of preset time segments. Pretreatment results.
  • FIG. 10 is a schematic diagram of a passing record processing apparatus according to a fifth embodiment of the present application.
  • the apparatus includes: a first obtaining unit 10, a pre-processing unit 30, a third obtaining unit 40, a clustering processing unit 50, an output unit 60, a grouping unit 70, a summing unit 80, and an establishing unit 90.
  • the clustering processing unit 50 includes a fourth obtaining module 51 and a clustering processing module 52.
  • the functions of the first obtaining unit 10, the pre-processing unit 30, the third obtaining unit 40, the clustering processing unit 50, the output unit 60, the grouping unit 70, the summing unit 80 and the establishing unit 90 in this embodiment are the same as those in the present application. The same is true in the passing record processing device of the fourth embodiment.
  • the clustering processing unit 50 is specifically configured to perform clustering processing on the plurality of bayonet numbers and the total number of passing times corresponding to the plurality of groups according to the mapping relationship, to obtain a clustering processing result.
  • the fourth obtaining module 51 is configured to acquire latitude and longitude information of the bayonet of the plurality of groups.
  • the clustering processing module 52 is configured to perform clustering processing on the plurality of bayonet numbers and the total number of passing times corresponding to the plurality of groups according to the latitude and longitude information of the bayonet of the plurality of groups, to obtain a plurality of types of clustering processing results.
  • a K-means clustering algorithm is used to aggregate into N classes, thereby obtaining multiple
  • the clustering processing result of the kind for example, the results of clustering processing of multiple kinds are divided according to the distance of the position, and the bayonet positions with a certain degree of similarity form a class, and this class corresponds to one region.
  • FIG. 11 is a schematic diagram of a passing record processing apparatus according to a sixth embodiment of the present application.
  • the apparatus includes: a first obtaining unit 10, a pre-processing unit 30, a third obtaining unit 40, a clustering processing unit 50, an output unit 60, a grouping unit 70, a summing unit 80, and an establishing unit 90,
  • the device also includes a computing unit 100.
  • the clustering processing unit 50 further includes a fourth obtaining module 51 and a clustering processing module 52.
  • the role of the cluster processing module 52 is the same as that of the vehicle recording processing device of the fifth embodiment of the present application.
  • the calculating unit 100 is configured to perform clustering processing on the pre-processed records to obtain a plurality of types of clustering processing results, and calculate a plurality of types of clustering processing results in each type of clustering processing results in multiple categories.
  • the weight of the clustering process results The calculation unit 100 calculates the weights of each of the plurality of types of clustering processing results in the plurality of types of clustering processing results, and obtains the weights of the specific types of clustering processing results in all the landing points.
  • the output unit 60 is specifically configured to display the plurality of kinds of clustering processing results in different regions according to the weights.
  • the output unit 60 displays the clustering processing result on the map, and the set corresponding to the bayonet of the cluster is used as an area, and is displayed on the map in different colors according to various weights, and the color is light to deep and can represent the weight. Change from small to large.
  • the embodiment of the passing record processing device acquires a plurality of passing records of the preset target object in the first preset time period by the first obtaining unit 10, and then acquires the plurality of passing records according to the plurality of passing records by the second obtaining unit 20
  • a plurality of driving trajectories of the target object are preset, and the pre-processing unit 30 performs pre-processing on the driving trajectory to obtain a pre-processing result, and then the third obtaining unit 40 obtains a pre-supplement that satisfies the first preset condition.
  • the embodiment of the present application adopts the idea of driving trajectory to determine the footing point, and does not require the user to specify the specific travel time and the return time period, because if the specified travel time and return time period are not the regular travel time period of the preset target object, the final statistical result is only Statistics on the bayonet of the route will miss many footholds.
  • the driving track is used to obtain the starting point and the ending point of each divided track in the driving track, and the number of occurrences of the starting point or the ending point in the first preset time period is counted, and it is not necessary to analyze all the passing records of the specified license plate in the time period. Reduced the difficulty of preprocessing, and this method is suitable for distributed Pre-processing, different license plates can be processed in parallel.
  • the driving trajectory is used to determine the footing point.
  • the K-means clustering algorithm is used to cluster the landing data according to the bayonet statistics.
  • the clustering according to the K-means clustering algorithm is a group with similar positions. The area formed by the bayonet, rather than the most frequently occurring bayonet, gives the weight of the landing point in each area, and the judgment of the landing point is more accurate, and the analysis performance of the landing point is improved, so that the user experience is higher.
  • an embodiment of the present application provides an electronic device, including: a housing 110, a processor 120, a memory 130, a circuit board 140, and a power circuit 150, wherein the circuit board 140 is disposed.
  • the processor 120 and the memory 130 are disposed on the circuit board 140; the power circuit 150 is configured to supply power to various circuits or devices of the electronic device.
  • the memory 130 is configured to store executable program code; the processor 120 executes the following steps by running executable program code stored in the memory 130:
  • the passing record includes a bayonet number of the bayonet that the preset target object passes each time and a pass through the bayonet Car time
  • the clustering processing result is output.
  • a plurality of passing records of the preset target object in the first preset time period are acquired, and then multiple driving tracks of the preset target object are acquired according to the plurality of passing records.
  • the pre-processing of the driving track is performed, and the pre-processing result is obtained.
  • the pre-processing record that satisfies the first preset condition is obtained from the pre-processing result, and the pre-processing record is clustered to obtain the clustering processing result, and finally the output is gathered.
  • the class processing result reduces the amount of data calculation after preprocessing, so that the analysis result of the landing point is obtained more quickly, the accuracy of the vehicle landing point analysis is improved, and the real-time analysis performance of the vehicle landing point is further improved.
  • the electronic device exists in a variety of forms including, but not limited to:
  • Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
  • Such terminals include: smartphones (eg iPhone), multimedia Mobile phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
  • Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
  • Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
  • the server consists of a processor, a hard disk, a memory, a system bus, etc.
  • the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
  • the embodiment of the present application provides an executable program code, which is used to execute the method for processing the passing record provided by the embodiment of the present application at the time of operation, wherein the method for processing the passing record includes:
  • the passing record includes a bayonet number of the bayonet that the preset target object passes each time and a pass through the bayonet Car time
  • the clustering processing result is output.
  • a plurality of passing records of the preset target object in the first preset time period are acquired, and then multiple driving tracks of the preset target object are acquired according to the plurality of passing records, and the driving track is performed.
  • the pre-processing results are obtained, and the pre-processing records satisfying the first preset condition are obtained from the pre-processing results, the pre-processing records are clustered, the clustering processing results are obtained, and finally the clustering processing results are output.
  • the calculation amount of data after pre-processing is reduced, so that the analysis result of the landing point is obtained more quickly, the accuracy of the analysis of the vehicle landing point is improved, and the real-time analysis performance of the vehicle landing point is further improved.
  • the embodiment of the present application provides a storage medium for storing executable program code, and the executable program code is executed to execute the vehicle record processing method provided by the embodiment of the present application.
  • the vehicle record includes a bayonet number of the bayonet that the preset target object passes each time and a transit time when the bayonet passes;
  • the clustering processing result is output.
  • a plurality of passing records of the preset target object in the first preset time period are acquired, and then multiple driving tracks of the preset target object are acquired according to the plurality of passing records, and the driving track is performed.
  • the pre-processing results are obtained, and the pre-processing records satisfying the first preset condition are obtained from the pre-processing results, the pre-processing records are clustered, the clustering processing results are obtained, and finally the clustering processing results are output.
  • the calculation amount of data after pre-processing is reduced, so that the analysis result of the landing point is obtained more quickly, the accuracy of the analysis of the vehicle landing point is improved, and the real-time analysis performance of the vehicle landing point is further improved.
  • the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
  • modules or steps of the present application can be implemented by a general computing device, which can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device, such that they may be stored in a storage device by a computing device, or they may be fabricated into individual integrated circuit modules, or Multiple modules or steps are made into a single integrated circuit module. Thus, the application is not limited to any particular combination of hardware and software.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种过车记录处理方法和装置, 提高了车辆落脚点分析的准确性。该方法包括：获取预设目标对象在第一预设时间段内的多个过车记录（S102），其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；根据多个过车记录，获取预设目标对象的多条行车轨迹（S104）；对行车轨迹进行落脚点预处理，得到预处理结果（S106）；从预处理结果中获取满足第一预设条件的预处理记录（S108）；对预处理记录进行聚类处理，得到聚类处理结果；输出聚类处理结果（S110）。

Description

过车记录处理方法和装置
本申请要求于2015年12月4日提交中国专利局、申请号为201510889455.8发明名称为“过车记录处理方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理领域，具体而言，涉及一种过车记录处理方法和装置。
背景技术
为了了解车辆在指定时间段内出现的位置情况，对车辆进行落脚点分析，也即，对车辆停车以后长时间没有离开的位置情况进行分析。目前，在进行落脚点分析时，用户输入要分析的时间范围和具体的时间段，比如，一天的出行时间段和回程时间段，因为车辆的具体时间段可以随意设定，增加了预处理的难度。在大量数据的记录中，用户实时进行落脚点分析，处理的数据是指定车辆在具体时间段内所有卡口的过车记录，需要处理的数据量较大，耗费时间长。另一方面，此种方法统计指定车辆在时间范围的具体时间段内所经过的所有卡口以及卡口对应的过车次数，如果指定的具体时间段并非车辆常规出行的时间段，那么最终统计的结果只是对途径的卡口进行统计，输出的结果是按过车次数降序排列的孤立的卡口的集合，虽然可以反映出经常经过的卡口，但是会遗漏很多常规落脚点，不能很好地展示出车辆落脚点的区域，因此，此种方法得出的结果不准确，达不到落脚点分析的目的。
针对相关技术中车辆落脚点分析不准确的问题，目前尚未提出有效的解决方案。
发明内容
本申请的主要目的在于提供一种过车记录处理方法和装置，以解决车辆落脚点分析不准确问题。
为了实现上述目的，根据本申请的一个方面，提供了一种过车记录处理方法，该方法包括：获取预设目标对象在第一预设时间段内的多个过车记录，其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；根据多个过车记录，获取预设目标对象的多条行车轨迹；对行车轨迹进行落脚点预处理，得到预处理结果；从预处理结果中获取满足第一预设条件的预处理记录；对预处理记录进行聚类处理，得到聚类处理结果；以及输出聚类处理结果。
可选地，获取预设目标对象在第一预设时间段内的多个过车记录，包括：对多个过车记录按照过车时间进行排序；获取相邻过车记录的时间差；根据相邻过车记录的时间差对多个过车记录进行划分，得到划分轨迹，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。
可选地，对行车轨迹进行落脚点预处理，得到预处理结果，包括：获取行车轨迹中每条划分轨迹的起点和终点；统计起点或终点在第一预设时间段内出现的次数，其中，起点或终点在第一预设时间段内出现的次数为起点或终点对应的卡口的过车次数；以及获取起点或终点对应的卡口的卡口号和过车次数，得到预处理结果。
可选地，在从预处理结果中获取满足第一预设条件的预处理记录之后，该方法还包括：将预处理记录按照相同卡口号进行分组，得到多个组的预处理记录，其中，相同卡口号的预处理记录划分为一个组，多个卡口号分别对应于多个组的预处理记录；分别对多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数；以及分别建立多个卡口号和对应于每个组的总过车次数的映射关系。
可选地，对预处理记录进行聚类处理，得到聚类处理结果，包括：根据映射关系对多个卡口号和对应于每个组的总过车次数进行聚类处理，得到聚类处理结果，具体为：获取多个组的卡口的经纬度信息；以及根据多个组的卡口的经纬度信息对多个卡口号和对应于每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果。
可选地，在对预处理记录进行聚类处理，得到多个种类的聚类处理结果之后，该方法还包括：计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重；输出聚类处理结果，包括：将多个种类的聚类处理结果结合权重在不同的区域展示。
为了实现上述目的，根据本申请的另一方面，提供了一种过车记录处理装置，该装置包括：第一获取单元，用于获取预设目标对象在第一预设时间段内的多个过车记录，其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；第二获取单元，用于根据多个过车记录，获取预设目标对象的多条行车轨迹；预处理单元，用于对行车轨迹进行落脚点预处理，得到预处理结果；第三获取单元，用于从预处理结果中获取满足 第一预设条件的预处理记录；聚类处理单元，用于对预处理记录进行聚类处理，得到聚类处理结果；以及输出单元，用于输出聚类处理结果。
可选地，该装置的第一获取单元，包括：排序模块，用于对多个过车记录按照过车时间进行排序；第一获取模块，用于根据相邻过车记录的时间差对多个过车记录进行划分获取相邻过车记录的时间差；划分模块，用于对多个过车记录进行划分，得到划分轨迹，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，其中，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。
可选地，该装置的预处理单元，包括：第二获取模块，用于获取行车轨迹中每条划分轨迹的起点和终点；统计模块，用于统计起点或终点在第一预设时间段内出现的次数，其中，次数为起点或终点对应的卡口的过车次数；以及第三获取模块，用于获取起点或终点对应的卡口的卡口号和过车次数，得到预处理结果。
可选地，该装置还包括：分组单元，用于在从所述预处理结果中获取满足第一预设条件的预处理记录之后，将预处理记录按照相同卡口号进行分组，得到多个组的预处理记录，其中，相同卡口号的预处理记录划分为一个组，多个卡口号分别对应于多个组的预处理记录；求和单元，用于分别对多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数；以及建立单元，用于分别建立多个卡口号和对应于每个组的总过车次数的映射关系。
可选地，该装置的聚类处理单元，用于根据映射关系对多个卡口号和对应于每个组的总过车次数进行聚类处理，，得到聚类处理结果；聚类处理单元，包括：第四获取模块，用于获取多个组的卡口的经纬度信息；以及聚类处理模块，用于根据多个组的卡口的经纬度信息对多个卡口号和对应于每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果。
可选地，该装置还包括：计算单元，用于在对所述预处理记录进行聚类处理，得到所述多个种类的聚类处理结果之后，计算所述多个种类的聚类处理结果中每一类聚类处理结果在所述多个种类的聚类处理结果中的权重，其中，该装置的输出单元，用于将多个种类的聚类处理结果结合权重在不同的区域展示。
本申请的提供一种电子设备，所述电子设备包括：壳体、处理器、存储 器、电路板和电源电路，其中，所述电路板安置在所述壳体围成的空间内部，所述处理器和所述存储器设置在所述电路板上；所述电源电路，用于为所述电子设备的各个电路或器件供电；所述存储器用于存储可执行程序代码；所述处理器通过运行所述存储器中存储的可执行程序代码，以执行所述过车记录处理方法。
本申请的还提供一种可执行程序代码，所述可执行程序代码用于在运行时执行所述过车记录处理方法。
本申请的还提供一种存储介质，所述存储介质用于存储可执行程序代码，所述可执行程序代码被运行以执行所述过车记录处理方法。
通过本申请，获取预设目标对象在第一预设时间段内的多个过车记录，其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；根据多个过车记录，获取预设目标对象的多条行车轨迹，对行车轨迹进行落脚点预处理，得到预处理结果，然后从预处理结果中获取满足第一预设条件的预处理记录，再对预处理记录进行聚类处理，得到聚类处理结果，最后输出聚类处理结果。解决了落脚点分析不准确的问题，进而提高了落脚点分析的准确性。
附图说明
构成本申请的一部分的附图用来提供对本申请的理解，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请第一实施例的过车记录处理方法的流程图；
图2是根据本申请第二实施例的过车记录处理方法的流程图；
图3是根据本申请实施例的行车轨迹分析的示意图；
图4是根据本申请第三实施例的过车记录处理方法的流程图；
图5是根据本申请实施例的按照卡口统计落脚点的示意图；
图6是根据本申请第一实施例的过车记录处理装置的示意图；
图7是根据本申请第二实施例的过车记录处理装置的示意图；
图8是根据本申请第三实施例的过车记录处理装置的示意图；
图9是根据本申请第四实施例的过车记录处理装置的示意图；
图10是根据本申请第五实施例的过车记录处理装置的示意图；
图11是根据本申请第六实施例的过车记录处理装置的示意图；
图12是根据本申请实施例的电子设备的示意图。
具体实施方式
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
首先，对本实施例涉及的技术术语作如下解释：
落脚点分析：当卡口点覆盖率达到一定程度后，可根据嫌疑车辆在卡口系统中出现的行车轨迹，分析指定时间段内车辆出现位置，分析嫌疑车辆的落脚点。
聚类：将数据集中在某些方面相似的数据成员进行分类组织的过程，聚类就是一种发现这种内在结构的技术，聚类技术经常被称为无监督学习。
K均值聚类算法：(K-means)K-means算法是硬聚类算法，是典型的基于原型的目标函数聚类方法的代表，它是以数据点到原型的某种距离作为优化的目标函数，利用函数求极值的方法得到迭代运算的调整规则。K-means算法以欧式距离作为相似度测度，它是求对应某一初始聚类中心向量V最优分类，使得评价指标J最小。算法采用误差平方和准则函数作为聚类准则函数。
行车轨迹：一条轨迹指一个车牌在一段时间内的过车记录按时间排序的有序集合，相邻两条过车记录时差超过预设时间就被划分成两条轨迹。
本申请实施例提供了一种过车记录处理方法。
图1是根据本申请第一实施例的过车记录处理方法的流程图。如图1所示，该过车记录处理方法包括以下步骤：
步骤S102，获取预设目标对象在第一预设时间段内的多个过车记录。
预设目标对象在停车以后，比如，指定车牌的车辆在停车以后，对指定时间段内车辆所停留的位置情况进行分析。可选地，在卡口系统中通过指定时间段内车辆对卡口的覆盖率，也即，车辆在指定时间段内经过卡口的行车轨迹，来分析车辆停留的位置情况。
预设目标对象在不同的时间段经过不同的卡口有不同的过车记录，其中， 过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间。在获取行车轨迹之前，获取预设目标对象在第一预设时间段内的多个过车记录，其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间。比如，预设目标对象在第一预设时间为6时～12时的时间段内，过车记录为6时过卡口1，7时过卡口2，9时过卡口3，10时过卡口4，12时过卡口5。
在获取预设目标对象在第一预设时间段内的多个过车记录之后，对多个过车记录按照预设目标对象的过车时间进行排序，然后通过预设目标对象的过车时间获取相邻过车记录的时间差。
举例而言，预设目标对象6时过卡口1，7时过卡口2，卡口1与卡口2的时间差为1小时，7时过卡口2，9时过卡口3，卡口2与卡口3的时间差为2小时，9时过卡口3，10时过卡口4，卡口3与卡口4的时间差为1小时，10时过卡口4，12时过卡口5，卡口4与卡口5的时间差为2小时。
通过预设目标对象的过车时间获取相邻过车记录的时间差之后，对多个过车记录进行划分，得到划分轨迹。在本申请的一种实施方式中，可以通过第二预设时间对多个过车记录进行划分，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。第一条过车记录为第一条划分轨迹的起点，最后一条过车记录为最后一条划分轨迹的终点。
举例而言，第二预设时间为1.5小时，预设目标对象6时过卡口1与7时过卡口2为第二类过车记录，7时过卡口2与9时过卡口3为第一类过车记录，9时过卡口3与10时过卡口4为第二类过车记录，10时过卡口4与12时过卡口5为第一类过车记录。则6时过卡口1、7时过卡口2为一条划分轨迹，9时过卡口3、10时过卡口4、12时过卡口5为另一条划分轨迹。
此处，12时过卡口5为最后一条过车记录，因此，9时过卡口3、10时过卡口4、12时过卡口5为另一条划分轨迹。
这里，一条划分轨迹可以理解为一条行车轨迹。
步骤S104，根据多个过车记录，获取预设目标对象的多条行车轨迹。
在获取预设目标对象在第一预设时间段内的多个过车记录之后，根据多个过车记录获取预设目标对象的多条行车轨迹，也即，获取一个车牌在一段时间内的过车记录按时间排序的有序集合，当相邻两条过车记录时差超过预 设时间时就被划分成两条轨迹。
在获取预设目标对象在第一预设时间段内的多个过车记录之后，对多个过车记录按照预设目标对象的过车时间进行排序，然后通过预设目标对象的过车时间获取相邻过车记录的时间差。
举例而言，预设目标对象6时过卡口1，7时过卡口2，卡口1与卡口2的时间差为1小时，7时过卡口2，9时过卡口3，卡口2与卡口3的时间差为2小时，9时过卡口3，10时过卡口4，卡口3与卡口4的时间差为1小时，10时过卡口4，12时过卡口5，卡口4与卡口5的时间差为2小时。
通过预设目标对象的过车时间获取相邻过车记录的时间差之后，对多个过车记录进行划分，得到划分轨迹。
步骤S106，对行车轨迹进行落脚点预处理，得到预处理结果。
落脚点为预设目标对象停车以后在第二预设时间内没有离开的位置，在获取预设目标对象的行车轨迹之后，对行车轨迹进行落脚点预处理。获取行车轨迹中每条划分轨迹的起点和终点，统计每条划分轨迹的起点或终点在第一预设时间段内出现的次数，也即，在第一预设时间内统计每条划分轨迹的起点或终点对应的卡口的过车次数，最后，获取每条划分轨迹的起点或终点对应的卡口的卡口号和过车次数，得到预处理结果。
举例而言，在第一预设时间为6时～12时的时间段内，6时过卡口1、7时过卡口2的划分轨迹的起点为6时过卡口1，终点为7时过卡口2。9时过卡口3、10时过卡口4、12时过卡口5的划分轨迹的起点为9时过卡口3，终点为12时过卡口5。获取每条划分轨迹的起点或终点对应的卡口的卡口号和过车次数，得到的预处理结果为6时过卡口1，其过车次数为1次，7时过卡口2，其过车次数为1次，9时过卡口3，其过车次数为1次，12时过卡口5，其过车次数为1次。
步骤S108，从预处理结果中获取满足第一预设条件的预处理记录。
可以获取多个预设目标对象在多个预设时间段内的行车轨迹，获取多个预设时间段内的预处理结果，比如，获取预设目标对象在2015年1月1日～2015年6月30日中的行车轨迹，获取预设目标对象在2015年1月1日～2015年6月30日中的多个预处理结果。在从预处理结果中获取满足第一预设条件的预处理记录之后，可选地，第一预设条件可以为车牌号和起止日期。首先在多个预处理结果中，将预处理记录按照相同卡口号进行分组，相同卡口号为一个组，从而得到由不同卡口号组成的多个组，多个组分别保存与卡口号对应的预处理记录，然后分别对多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数，最后分别建立多个卡口号和对应于每个组的总过车次数的映射关系，获得每个卡口号和卡口号对应的总过车次数组成的 集合。
举例而言，2015年1月1日～2015年1月3日的行车轨迹分别为：6时过卡口1，其过车次数为1次，7时过卡口2，其过车次数为1次，9时过卡口3，其过车次数为1次，12时过卡口5，其过车次数为1次；6时过卡口1，其过车次数为2次，7时过卡口2，其过车次数为1次，9时过卡口3，其过车次数为3次，12时过卡口5，其过车次数为2次；6时过卡口1，其过车次数为2次，7时过卡口2，其过车次数为1次，9时过卡口3，其过车次数为3次，12时过卡口5，其过车次数为2次。则卡口1、卡口2、卡口3、卡口4、卡口5分别对应5个组，第一组总过车次数为卡口1的所有过车次数之和，为1+2+2＝5次，第二组总过车次数为卡口2的所有过车次数之和，为1+1+1＝3次，第三组总过车次数为卡口3的所有过车次数之和，为1+3+3＝7次，第四组总过车次数为卡口5的所有过车次数之和1+2+2＝5次，可以得到卡口1对应5次，卡口2对应3次，卡口3对应7次，卡口5对应5次的映射关系，每个卡口号和卡口号对应的过车次数以及卡口为其组成集合的元素。
步骤S110，对预处理记录进行聚类处理，得到聚类处理结果。
从预处理结果中获取满足第一预设条件的预处理记录，可以获得每个卡口号和卡口号对应的总过车次数组成的集合，集合中的各个元素之间，在某些方面有相似的数据成员，比如，各个卡口号和卡口号对应的过车次数以及卡口组成的元素之间关于位置信息的相似，将其进行分类组织，可以通过聚类处理发现相似结构将其进行分类组织在本申请的一种实施方式中，采用K均值聚类算法来实现对预处理记录的聚类处理，降低了预处理后的数据计算量。
对预处理记录进行聚类处理包括：根据映射关系对多个卡口号和对应于每个组的总过车次数进行聚类处理，首先获取多个组的卡口的经纬度信息，根据多个组的卡口的经纬度信息对多个卡口号和对应于每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果，比如，多个种类的聚类处理结果按位置的远近来划分，位置在一定程度上相近的卡口组成一个类，这个类对应于一个区域。
步骤S112，输出聚类处理结果。
在对预处理记录进行聚类处理，得到多个种类的聚类处理结果之后，计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重，其中，输出聚类处理结果包括：将多个种类的聚类处理结果结合权重在不同的区域展示，以分析每一类聚类处理结果在整体聚类处理结果中的性能，提高了实时分析性能。
可选地，在地图上展示聚类处理结果，一个聚类的卡口对应的集合作为 一个区域，并根据各类权重以不同颜色在地图上展示，颜色由浅到深，可以代表权重由小到大的变化。
值得一提的是，本申请中所述的多个可以理解为至少两个。
该实施例采用获取预设目标对象在第一预设时间段内的多个过车记录，然后根据多个过车记录，获取预设目标对象的多条行车轨迹，对行车轨迹进行落脚点预处理，得到预处理结果，再从预处理结果中获取满足第一预设条件的预处理记录，对预处理记录进行聚类处理，得到聚类处理结果，最后输出聚类处理结果，降低了预处理后的数据计算量，从而更快地得出落脚点分析结果，提高了车辆落脚点分析的准确性，提升了车辆落脚点的实时分析性能。
图2是根据本申请第二实施例的过车记录处理方法的流程图，需要说明的是，过车记录处理方法包括对行车轨迹的分析。如图2所示，该过车记录处理方法包括以下步骤：
步骤S202，对多个预设目标对象分组。
获取多个预设目标对象在第一预设时间段内的多个过车记录，按照多个预设目标对象的车牌进行分组，对其进行分布式并行计算，也即，多个预设目标对象可以同时进行行车轨迹的分析。获取同一车牌的所有过车记录，包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间。
步骤S204，按照过车时间对同一车牌的所有过车记录进行排序。
过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间，对预设目标对象的多个过车记录按照过车时间进行排序，比如，按照顺时针顺序对过车记录进行排序。
步骤S206，对过车记录进行划分，得到划分轨迹。
按照过车时间对同一车牌的所有过车记录进行排序之后，采用轨迹思路，也即，轨迹的起止点对应于落脚点最近卡口的过车记录，按预设目标对象的车牌分析出卡口号与过车次数的映射关系，得到它的轨迹集合。可以通过第二预设时间对多个过车记录进行划分，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。第一条过车记录为第一条划分轨迹的起点，最后一条过车记录为最后一条划分轨迹的终点。
通过对过车记录进行划分来分析预设目标对象的行车轨迹，图3是根据本 申请实施例的行车轨迹分析的示意图，如图3所示，对牌号为浙A8888的车辆的行车轨迹进行分析。第一预设时间段设为以12时0分开始的24小时时间段，第二预设时间设为T＝2h，其中坐标轴表示一天的时间刻度，坐标轴上方为预设目标对象经过卡口时的时间。牌号为浙A8888的车辆在24小时内经过卡口1，卡口2，卡口3，卡口4，卡口5。计算浙A8888在相邻过车记录的时间差，如果时间差超过时间T＝2h，则相邻过车记录中前一条过车记录算作上一条划分轨迹的终点，相邻过车记录中下一条过车记录算作下一条划分轨迹的起点，如此获得此车牌所有的轨迹。浙A8888的车辆6时19分过卡口1，7时1分过卡口2，以此类推，定义的划分轨迹的时间间隔为2时，则最终所在天的划分轨迹有3条，分别为卡口1、卡口2与卡口3组成的轨迹，卡口4、卡口5与卡口6组成的轨迹，卡口3、卡口2与卡口1组成的轨迹。
步骤S208，取出同一车牌每条划分轨迹的起点和终点。
取出同一车牌每条划分轨迹的起点和终点，读取卡口号和过车记录的时间，按天和卡口号统计每条行车轨迹的起点或终点的总共出现次数，也即，每条行车轨迹的起点或终点的总过车次数，如S206中统计的结果为[车牌：浙A8888，日期：20150101，[{卡口：1，次数：2}，{卡口：3，次数：2}，{卡口：4，次数：1}，{卡口：6，次数：1}]，实现了对落脚点的预处理。
上述S202、S204、S206和S208可以理解为S106的一种实现方式。
该实施例采用对多个预设目标对象分组，按照过车时间对同一车牌的所有过车记录进行排序，然后对过车记录进行划分，得到划分轨迹，再取出同一车牌每条划分轨迹的起点和终点，对落脚点进行预处理，实现了行车轨迹的分析和落脚点的预处理。
图4是根据本申请第三实施例的过车记录处理方法的流程图，需要说明的是，过车记录处理方法包括对落脚点的分析。如图4所示，该过车记录处理方法包括以下步骤：
步骤S302，提取预处理记录。
在对预设目标对象的行车轨迹进行分析和对预设目标对象的落脚点进行预处理之后，用户分析在第一预设时间段内预设目标对象的落脚点。设定第一预设条件为起止日期和车牌号，利用分布式计算引擎根据第一预设条件对多个预设目标对象的落脚点同时进行分析。在第一预设时间范围内，从预处理结果中找到符合第一预设条件的所有日期的预处理记录。
步骤S304，按照卡口号对预处理记录进行分组。
图5是根据本申请实施例的按照卡口统计落脚点的示意图，如图5所示，预设目标对象为车牌号浙A8888的车辆，将第一预设时间为2015年1月1日 ～2015年6月31日的预处理记录中相同卡口号的预处理记录划分为一个组，得到多个组的预处理记录，比如，划分组的结果为1～n组，1～n组分别对应于相应的卡口号，n个卡口号分别对应于1～n组的预处理记录。按照卡口号分组之后，分别对同一卡口在2015年1月1日～2015年6月31日内的所有过车次数求和，得到分别对应于每个组的总过车次数，比如，卡口1为260次，卡口3为240次，卡口4为50次，卡口6为30次，卡口n为1次，最后分别建立多个卡口号和对应于每个组的总过车次数的映射关系，可以得出[卡口号，过车总次数]的集合。
步骤S306，对分组的预处理记录进行聚类处理。
对分组的预处理记录进行聚类处理包括根据映射关系对多个卡口号和对应于每个组的总过车次数进行聚类处理，结合多个组的卡口的经纬度信息，根据多个组的卡口的经纬度信息对多个卡口号和对应于每个组的总过车次数进行聚类处理，在本申请的一种实施方式中，使用K均值聚类算法，聚成N类，从而得到多个种类的聚类处理结果，每类是步骤S304中卡口和过车总次数集合的子集，比如，多个种类的聚类处理结果按位置的远近来划分，位置在一定程度上相近的卡口组成一个类，这个类对应于一个区域。同时，计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重，获得具体种类的聚类处理结果在所有落脚点中的权重。
上述S302、S304和S306可以理解为S110的一种实现方式。
步骤S308，展示聚类处理结果。
在地图上展示聚类处理结果，一个种类的聚类的[卡口号，过车总次数]的集合作为一个区域，将多个种类的聚类处理结果结合权重在不同的区域展示，并根据各类权重以不同颜色在地图上展示，颜色由浅到深，可以代表权重由小到大的变化。
上述S308可以与S112实现相同的技术效果。
该实施例采用提取预处理记录，然后按照卡口号对预处理记录进行分组，再对分组的预处理记录进行聚类处理，最后展示聚类处理结果，降低了预处理后的数据计算量，更快地得出落脚点分析结果，实现了对落脚点的分析，从而提高了车辆落脚点分析的准确性，提升了车辆落脚点的实时分析性能。
需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本申请实施例还提供了一种过车记录处理装置，需要说明的是，本申请实施例的过车记录处理装置可以用于执行本申请实施例的过车记录处理方法。
图6是根据本申请第一实施例的过车记录处理装置的示意图。如图6所示，该装置包括：第一获取单元10，第二获取单元20，预处理单元30，第三获取单元40，聚类处理单元50和输出单元60。
第一获取单元10，用于获取预设目标对象在第一预设时间段内的多个过车记录，其中，过车记录包括预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间。
第二获取单元20，用于根据多个过车记录，获取预设目标对象的多条行车轨迹。在第一获取单元10获取预设目标对象在第一预设时间段内的多个过车记录之后，第二获取单元20根据多个过车记录获取预设目标对象的多条行车轨迹，也即，获取一个车牌在一段时间内的过车记录按时间排序的有序集合，当相邻两条过车记录时差超过预设时间时就被划分成两条轨迹。
预处理单元30，用于对行车轨迹进行落脚点预处理，得到预处理结果。落脚点为预设目标对象停车以后在第二预设时间内没有离开的位置，在获取预设目标对象的行车轨迹之后，预处理单元30对行车轨迹进行落脚点预处理。获取行车轨迹中每条划分轨迹的起点和终点，统计每条划分轨迹的起点或终点在第一预设时间段内出现的次数，也即，在第一预设时间内统计每条划分轨迹的起点或终点对应的卡口的过车次数，最后，获取每条划分轨迹的起点或终点对应的卡口的卡口号和过车次数，得到预处理结果。
第三获取单元40，用于从预处理结果中获取满足第一预设条件的预处理记录。可以获取多个预设目标对象在多个预设时间段内的行车轨迹，获取多个预设时间段内的预处理结果。首先在多个预处理结果中，将预处理记录按照相同卡口号进行分组，相同卡口号为一个组，从而得到由不同卡口号组成的多个组，多个组分别保存与卡口号对应的预处理记录，然后分别对多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数，最后分别建立多个卡口号和对应于每个组的总过车次数的映射关系，从而通过第三获取单元40获取满足第一预设条件的预处理记录。
聚类处理单元50，用于对预处理记录进行聚类处理，得到聚类处理结果。第三获取单元40从预处理结果中获取满足第一预设条件的预处理记录，获得每个卡口号和卡口号对应的过车总次数组成的集合，集合中的各个元素之间，在某些方面有相似的数据成员，比如，各个卡口号和卡口号对应的过车次数以及卡口组成的元素之间关于位置信息的相似，将其进行分类组织，聚类处理单元50通过聚类处理发现相似结构，并将其进行分类组织。在本申请的一种实施方式中，聚类处理单元50采用K均值聚类算法来实现对预处理记录的聚类处理。
对预处理记录进行聚类处理包括根据映射关系对多个卡口号和对应于每个组的总过车次数进行聚类处理，首先获取多个组的卡口的经纬度信息，根据多个组的卡口的经纬度信息对多个卡口号和对应于每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果，比如，多个种类的聚类处理结果按位置的远近来划分，位置在一定程度上相近的卡口组成一个类，这个类对应于一个区域。
输出单元60，用于输出聚类处理结果。在聚类处理单元50在对预处理记录进行聚类处理，得到多个种类的聚类处理结果之后，计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重，输出单元60将多个种类的聚类处理结果结合权重在不同的区域展示。
图7是根据本申请第二实施例的过车记录处理装置的示意图。如图7所示，该装置包括：第一获取单元10，预处理单元30，第二获取单元20，第三获取单元40，聚类处理单元50和输出单元60，其中，第一获取单元10包括排序模块11，第一获取模块12和划分模块13。
该实施例中的第一获取单元10，预处理单元30，第二获取单元20，第三获取单元40，聚类处理单元50和输出单元60的作用与本申请第二实施例的过车记录处理装置中的相同。
排序模块11，用于对多个过车记录按照过车时间进行排序。在获取预设目标对象在第一预设时间段内的多个过车记录之后，排序模块11对多个过车记录按照预设目标对象的过车时间进行排序。
第一获取模块12，用于获取相邻过车记录的时间差。具体而言，第一获取模块12通过预设目标对象的过车时间获取相邻过车记录的时间差。
划分模块13，用于对多个过车记录进行划分，得到划分轨迹。通过第一获取模块12预设目标对象的过车时间获取相邻过车记录的时间差之后，划分模块13对多个过车记录进行划分，得到划分轨迹。在本申请的一种实施方式中，可以通过第二预设时间对多个过车记录进行划分，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。第一条过车记录为第一条划分轨迹的起点，最后一条过车记录为最后一条划分轨迹的终点。
在本申请的一种实施方式中，第二获取单元20包括排序模块，第一获取 模块和划分模块。
排序模块，用于对多个过车记录按照过车时间进行排序。在获取预设目标对象在第一预设时间段内的多个过车记录之后，排序模块对多个过车记录按照预设目标对象的过车时间进行排序。
第一获取模块，用于获取相邻过车记录的时间差。具体而言，第一获取模块通过预设目标对象的过车时间获取相邻过车记录的时间差。
划分模块，用于对多个过车记录进行划分，得到划分轨迹。通过第一获取模块预设目标对象的过车时间获取相邻过车记录的时间差之后，划分模块对多个过车记录进行划分，得到划分轨迹。在本申请的一种实施方式中，可以通过第二预设时间对多个过车记录进行划分，其中，将多个过车记录划分为第一类过车记录和第二类过车记录，第一类过车记录为多个过车记录中提取时间差超过第二预设时间的相邻过车记录，第二类过车记录为多个过车记录中提取时间差不超过第二预设时间的相邻过车记录，第一类过车记录中前一条过车记录为上一条划分轨迹的终点，第一类过车记录中后一条过车记录为下一条划分轨迹的起点，划分轨迹包括第二类过车记录。第一条过车记录为第一条划分轨迹的起点，最后一条过车记录为最后一条划分轨迹的终点。
图8是根据本申请第三实施例的过车记录处理装置的示意图。如图8所示，该装置包括：第一获取单元10，第二获取单元20，预处理单元30，第三获取单元40，聚类处理单元50和输出单元60，其中，第一获取单元10包括排序模块11，第一获取模块12和划分模块13，预处理单元30包括：第二获取模块31，统计模块32和第三获取模块33。
该实施例中的第一获取单元10，第二获取单元20，预处理单元30，第三获取单元40，聚类处理单元50，输出单元60，排序模块11，第一获取模块12和划分模块13的作用与本申请第二实施例的过车记录处理装置中的相同。
第二获取模块31，用于获取行车轨迹中每条划分轨迹的起点和终点。落脚点为预设目标对象停车以后在第二预设时间内没有离开的位置，在获取预设目标对象的行车轨迹之后，对行车轨迹进行落脚点预处理。第二获取模块31获取行车轨迹中每条划分轨迹的起点和终点。
统计模块32，用于统计起点或终点在第一预设时间段内出现的次数，其中，次数为起点或终点对应的卡口的过车次数。统计模块32统计每条划分轨迹的起点或终点在第一预设时间段内出现的次数，也即，在第一预设时间内统计每条划分轨迹的起点或终点对应的卡口的过车次数。
第三获取模块33，用于获取起点或终点对应的卡口的卡口号和过车次数，得到预处理结果。通过第三获取模块33获取每条划分轨迹的起点或终点对应 的卡口的卡口号和过车次数来得到预处理结果。
图9是根据本申请第四实施例的过车记录处理装置的示意图。如图9所示，该装置包括：第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50和输出单元60，其中还包括：分组单元70，求和单元80和建立单元90。
该实施例中的第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50和输出单元60的作用与本申请第一实施例的过车记录处理装置中的相同。
分组单元70，用于在从预处理结果中获取满足第一预设条件的预处理记录之后，将预处理记录按相同卡口号进行分组，得到多个组的预处理记录，其中，相同卡口号的预处理记录划分为一个组，多个卡口号分别对应于多个组的预处理记录。具体而言，在多个预处理结果中，分组单元70将预处理记录按照相同卡口号进行分组，相同卡口号为一个组，从而得到由不同卡口号组成的多个组，多个组分别保存与卡口号对应的预处理记录。
求和单元80，用于分别对多个组的预处理记录对应的过车次数进行求和，得到分别对应于多个组的总过车次数。
建立单元90，用于分别建立多个卡口号和对应于多个组的总过车次数的映射关系。建立单元90分别建立多个卡口号和对应于每个组的总过车次数的映射关系，获得每个卡口号和卡口号对应的总过车次数组成的集合。
第一获取单元10还用于获取预设目标对象在多个预设时间段内的行车轨迹，预处理单元30还用于对行车轨迹进行落脚点预处理，得到多个预设时间段内的预处理结果。
图10是根据本申请第五实施例的过车记录处理装置的示意图。如图10所示，该装置包括：第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50，输出单元60，分组单元70，求和单元80和建立单元90。其中，聚类处理单元50包括：第四获取模块51和聚类处理模块52。
该实施例中的第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50，输出单元60，分组单元70，求和单元80和建立单元90的作用与本申请第四实施例的过车记录处理装置中的相同。
聚类处理单元50具体用于根据映射关系对多个卡口号和对应于多个组的总过车次数进行聚类处理，得到聚类处理结果。
这种情况下，第四获取模块51，用于获取多个组的卡口的经纬度信息。
聚类处理模块52，用于根据多个组的卡口的经纬度信息对多个卡口号和对应于多个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果。在本申请的一种实施方式中，使用K均值聚类算法，聚成N类，从而得到多个 种类的聚类处理结果，比如，多个种类的聚类处理结果按位置的远近来划分，位置在一定程度上相近的卡口组成一个类，这个类对应于一个区域。
图11是根据本申请第六实施例的过车记录处理装置的示意图。如图11所示，该装置包括：第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50，输出单元60，分组单元70，求和单元80和建立单元90，该装置还包括计算单元100。其中，聚类处理单元50还包括第四获取模块51和聚类处理模块52。
该实施例中的第一获取单元10，预处理单元30，第三获取单元40，聚类处理单元50，输出单元60，分组单元70，求和单元80，建立单元90，第四获取模块51和聚类处理模块52的作用与本申请第五实施例的过车记录处理装置中的相同。
计算单元100，用于在对所述预处理记录进行聚类处理，得到多个种类的聚类处理结果之后，计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重。计算单元100计算多个种类的聚类处理结果中每一类聚类处理结果在多个种类的聚类处理结果中的权重，获得具体种类的聚类处理结果在所有落脚点中的权重。
输出单元60具体用于将多个种类的聚类处理结果按照权重在不同的区域展示。可选地，输出单元60在地图上展示聚类处理结果，一个聚类的卡口对应的集合作为一个区域，并根据各类权重以不同颜色在地图上展示，颜色由浅到深，可以代表权重由小到大的变化。
该过车记录处理装置的实施例通过第一获取单元10获取预设目标对象在第一预设时间段内的多个过车记录，然后通过第二获取单元20根据多个过车记录，获取预设目标对象的多条行车轨迹，通过预处理单元30对行车轨迹进行落脚点预处理，得到预处理结果，再通过第三获取单元40从预处理结果中获取满足第一预设条件的预处理记录，最后通过聚类处理单元50对预处理记录进行聚类处理，得到多类聚类处理结果，最后通过输出单元60输出聚类处理结果，降低了预处理后的数据计算量，更快地得出落脚点分析结果，提高了车辆落脚点分析的准确性，提高了车辆落脚点的实时分析性能。
本申请实施例采用行车轨迹的思路确定落脚点，不需要用户指定具体出行和回程时间段，因为如果指定的出行和回程时间段并非预设目标对象常规出行时间段，那么最终统计的结果只是对途径的卡口进行统计，会遗漏很多落脚点。采用行车轨迹的方式，获取行车轨迹中每条划分轨迹的起点和终点，统计起点或终点在第一预设时间段内出现的次数，并不需要分析指定车牌在时间段内所有过车记录，降低了预处理的难度，并且这种方式适合分布式的 预处理，不同车牌可以并行处理，在真正落脚点分析时，只需要对预处理后的数据进行简单地计算，极大降低了计算量，更快地得出分析结果，提高了落脚点的实时分析性能。采用行车轨迹的思路确定落脚点，使用K均值聚类算法对按卡口统计的落脚点数据进行聚类处理，根据K均值聚类算法聚类出的分类是一组组的位置相近的多个卡口组成的区域，而不是最经常出现的卡口，并且给出了落脚点在各个区域的权重，对落脚点的判断更加准确，同时提高了落脚点的分析性能，使用户体验更高。
如图12所示，本申请实施例提供了一种电子设备，所述电子设备包括：壳体110、处理器120、存储器130、电路板140和电源电路150，其中，所述电路板140安置在所述壳体110围成的空间内部，所述处理器120和所述存储器130设置在所述电路板140上；所述电源电路150，用于为所述电子设备的各个电路或器件供电；所述存储器130用于存储可执行程序代码；所述处理器120通过运行所述存储器130中存储的可执行程序代码，以执行以下步骤：
获取预设目标对象在第一预设时间段内的多个过车记录，其中，所述过车记录包括所述预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；
根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹；
对所述行车轨迹进行落脚点预处理，得到预处理结果；
从所述预处理结果中获取满足第一预设条件的预处理记录；
对所述预处理记录进行聚类处理，得到聚类处理结果；以及
输出所述聚类处理结果。
处理器120对上述步骤的具体执行过程以及处理器120通过运行可执行程序代码来进一步执行的步骤，可以参见本申请图1-11所示实施例的描述，在此不再赘述。
由上可见，本申请实施例中，采用获取预设目标对象在第一预设时间段内的多个过车记录，然后根据多个过车记录，获取预设目标对象的多条行车轨迹，对行车轨迹进行落脚点预处理，得到预处理结果，再从预处理结果中获取满足第一预设条件的预处理记录，对预处理记录进行聚类处理，得到聚类处理结果，最后输出聚类处理结果，降低了预处理后的数据计算量，从而更快地得出落脚点分析结果，提高了车辆落脚点分析的准确性，进一步地提升了车辆落脚点的实时分析性能。
该电子设备以多种形式存在，包括但不限于：
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括：智能手机(例如iPhone)、多媒体 手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备：这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备：这类设备可以显示和播放多媒体内容。该类设备包括：音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器：提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
本申请实施例提供了一种可执行程序代码，该可执行程序代码用于在运行时执行本申请实施例提供的过车记录处理方法，其中，过车记录处理方法，包括：
获取预设目标对象在第一预设时间段内的多个过车记录，其中，所述过车记录包括所述预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；
根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹；
对所述行车轨迹进行落脚点预处理，得到预处理结果；
从所述预处理结果中获取满足第一预设条件的预处理记录；
对所述预处理记录进行聚类处理，得到聚类处理结果；以及
输出所述聚类处理结果。
本申请实施例中，采用获取预设目标对象在第一预设时间段内的多个过车记录，然后根据多个过车记录，获取预设目标对象的多条行车轨迹，对行车轨迹进行落脚点预处理，得到预处理结果，再从预处理结果中获取满足第一预设条件的预处理记录，对预处理记录进行聚类处理，得到聚类处理结果，最后输出聚类处理结果，降低了预处理后的数据计算量，从而更快地得出落脚点分析结果，提高了车辆落脚点分析的准确性，进一步地提升了车辆落脚点的实时分析性能。
本申请实施例提供了一种存储介质，用于存储可执行程序代码，该可执行程序代码被运行以执行本申请实施例提供的过车记录处理方法，其中，过车记录处理方法，包括：
获取预设目标对象在第一预设时间段内的多个过车记录，其中，所述过 车记录包括所述预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；
根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹；
对所述行车轨迹进行落脚点预处理，得到预处理结果；
从所述预处理结果中获取满足第一预设条件的预处理记录；
对所述预处理记录进行聚类处理，得到聚类处理结果；以及
输出所述聚类处理结果。
本申请实施例中，采用获取预设目标对象在第一预设时间段内的多个过车记录，然后根据多个过车记录，获取预设目标对象的多条行车轨迹，对行车轨迹进行落脚点预处理，得到预处理结果，再从预处理结果中获取满足第一预设条件的预处理记录，对预处理记录进行聚类处理，得到聚类处理结果，最后输出聚类处理结果，降低了预处理后的数据计算量，从而更快地得出落脚点分析结果，提高了车辆落脚点分析的准确性，进一步地提升了车辆落脚点的实时分析性能。
对于装置、电子设备、可执行程序代码及存储介质实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
显然，本领域的技术人员应该明白，上述的本申请的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上所述仅为本申请的优选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (15)

  1. 一种过车记录处理方法，其特征在于，包括：
    获取预设目标对象在第一预设时间段内的多个过车记录，其中，所述过车记录包括所述预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；
    根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹；
    对所述行车轨迹进行落脚点预处理，得到预处理结果；
    从所述预处理结果中获取满足第一预设条件的预处理记录；
    对所述预处理记录进行聚类处理，得到聚类处理结果；以及
    输出所述聚类处理结果。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹，包括：
    对所述多个过车记录按照过车时间进行排序；
    获取相邻过车记录的时间差；
    根据所述相邻过车记录的时间差对所述多个过车记录进行划分，得到划分轨迹，其中，将所述多个过车记录划分为第一类过车记录和第二类过车记录，其中，所述第一类过车记录为所述多个过车记录中提取时间差超过第二预设时间的相邻过车记录，所述第二类过车记录为所述多个过车记录中提取时间差不超过所述第二预设时间的相邻过车记录，
    所述第一类过车记录中前一条过车记录为上一条划分轨迹的终点，所述第一类过车记录中后一条过车记录为下一条划分轨迹的起点，所述划分轨迹包括第二类过车记录。
  3. 根据权利要求2所述的方法，其特征在于，所述对所述行车轨迹进行落脚点预处理，得到预处理结果，包括：
    获取所述行车轨迹中每条划分轨迹的起点和终点；
    统计所述起点或所述终点在所述第一预设时间段内出现的次数，其中，所述次数为所述起点或所述终点对应的卡口的过车次数；以及
    获取所述起点或所述终点对应的卡口的卡口号和过车次数，得到所述预处理结果。
  4. 根据权利要求3所述的方法，其特征在于，在所述从所述预处理结果中获取满足第一预设条件的预处理记录之后，所述方法还包括：
    将所述预处理记录按照相同卡口号进行分组，得到多个组的预处理记录，其中，相同卡口号的预处理记录划分为一个组，多个卡口号分别对应于所述多个组的预处理记录；
    分别对所述多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数；以及
    分别建立所述多个卡口号和对应于所述每个组的总过车次数的映射关系。
  5. 根据权利要求4所述的方法，其特征在于，所述对所述预处理记录进行聚类处理，得到聚类处理结果，包括：根据所述映射关系对所述多个卡口号和对应于所述每个组的总过车次数进行聚类处理，得到聚类处理结果，具体为：
    获取所述多个组的卡口的经纬度信息；以及
    根据所述多个组的卡口的经纬度信息对所述多个卡口号和对应于所述每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果。
  6. 根据权利要求5所述的方法，其特征在于，
    在所述对所述预处理记录进行聚类处理，得到所述多个种类的聚类处理结果之后，所述方法还包括：
    计算所述多个种类的聚类处理结果中每一类聚类处理结果在所述多个种类的聚类处理结果中的权重；
    所述输出所述聚类处理结果，包括：将所述多个种类的聚类处理结果结合权重在不同的区域展示。
  7. 一种过车记录处理装置，其特征在于，包括：
    第一获取单元，用于获取预设目标对象在第一预设时间段内的多个过车记录，其中，所述过车记录包括所述预设目标对象每次经过的卡口的卡口号和经过卡口时的过车时间；
    第二获取单元，用于根据所述多个过车记录，获取所述预设目标对象的多条行车轨迹；
    预处理单元，用于对所述行车轨迹进行落脚点预处理，得到预处理结果；
    第三获取单元，用于从所述预处理结果中获取满足第一预设条件的预处理记录；
    聚类处理单元，用于对所述预处理记录进行聚类处理，得到聚类处理结果；以及
    输出单元，用于输出所述聚类处理结果。
  8. 根据权利要求7所述的装置，其特征在于，所述第二获取单元，包括：
    排序模块，用于对所述多个过车记录按照过车时间进行排序；
    第一获取模块，用于获取相邻过车记录的时间差；
    划分模块，用于根据所述相邻过车记录的时间差对所述多个过车记录进 行划分对所述多个过车记录进行划分，得到划分轨迹，其中，将所述多个过车记录划分为第一类过车记录和第二类过车记录，其中，所述第一类过车记录为所述多个过车记录中提取时间差超过第二预设时间的相邻过车记录，所述第二类过车记录为所述多个过车记录中提取时间差不超过所述第二预设时间的相邻过车记录，
    所述第一类过车记录中前一条过车记录为上一条划分轨迹的终点，所述第一类过车记录中后一条过车记录为下一条划分轨迹的起点，所述划分轨迹包括第二类过车记录。
  9. 根据权利要求8所述的装置，其特征在于，所述预处理单元，包括：
    第二获取模块，用于获取所述行车轨迹中每条划分轨迹的起点和终点；
    统计模块，用于统计所述起点或所述终点在所述第一预设时间段内出现的次数，其中，所述次数为所述起点或所述终点对应的卡口的过车次数；以及
    第三获取模块，用于获取所述起点或所述终点对应的卡口的卡口号和过车次数，得到所述预处理结果。
  10. 根据权利要求9所述的装置，其特征在于，所述装置还包括：
    分组单元，用于在从所述预处理结果中获取满足第一预设条件的预处理记录之后，将所述预处理记录按照相同卡口号进行分组，得到多个组的预处理记录，其中，相同卡口号的预处理记录划分为一个组，多个卡口号分别对应于所述多个组的预处理记录；
    求和单元，用于分别对所述多个组的预处理记录对应的过车次数进行求和，得到分别对应于每个组的总过车次数；以及
    建立单元，用于分别建立所述多个卡口号和对应于所述每个组的总过车次数的映射关系。
  11. 根据权利要求10所述的装置，其特征在于，所述聚类处理单元，用于根据所述映射关系对所述多个卡口号和对应于所述每个组的总过车次数进行聚类处理，得到聚类处理结果；所述聚类处理单元，包括：
    第四获取模块，用于获取所述多个组的卡口的经纬度信息；以及
    聚类处理模块，用于根据所述多个组的卡口的经纬度信息对所述多个卡口号和对应于所述每个组的总过车次数进行聚类处理，得到多个种类的聚类处理结果。
  12. 根据权利要求11所述的装置，其特征在于，所述装置还包括：
    计算单元，用于在对所述预处理记录进行聚类处理，得到所述多个种类的聚类处理结果之后，计算所述多个种类的聚类处理结果中每一类聚类处理 结果在所述多个种类的聚类处理结果中的权重，
    其中，所述输出单元，用于将所述多个种类的聚类处理结果结合权重在不同的区域展示。
  13. 一种电子设备，其特征在于，所述电子设备包括：壳体、处理器、存储器、电路板和电源电路，其中，所述电路板安置在所述壳体围成的空间内部，所述处理器和所述存储器设置在所述电路板上；所述电源电路，用于为所述电子设备的各个电路或器件供电；所述存储器用于存储可执行程序代码；所述处理器通过运行所述存储器中存储的可执行程序代码，以执行权利要求1-6任一项所述的过车记录处理方法。
  14. 一种可执行程序代码，其特征在于，所述可执行程序代码用于在运行时执行权利要求1-6任一项所述的过车记录处理方法。
  15. 一种存储介质，其特征在于，所述存储介质用于存储可执行程序代码，所述可执行程序代码被运行以执行权利要求1-6任一项所述的过车记录处理方法。
PCT/CN2016/096676 2015-12-04 2016-08-25 过车记录处理方法和装置 WO2017092418A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP16869729.0A EP3385919B1 (en) 2015-12-04 2016-08-25 Method of processing passage record and device
US15/780,754 US10810870B2 (en) 2015-12-04 2016-08-25 Method of processing passage record and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510889455.8 2015-12-04
CN201510889455.8A CN106846538B (zh) 2015-12-04 2015-12-04 过车记录处理方法和装置

Publications (1)

Publication Number Publication Date
WO2017092418A1 true WO2017092418A1 (zh) 2017-06-08

Family

ID=58796163

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/096676 WO2017092418A1 (zh) 2015-12-04 2016-08-25 过车记录处理方法和装置

Country Status (4)

Country Link
US (1) US10810870B2 (zh)
EP (1) EP3385919B1 (zh)
CN (1) CN106846538B (zh)
WO (1) WO2017092418A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108182558A (zh) * 2017-12-04 2018-06-19 北京中交兴路信息科技有限公司 一种基于统计特征的运距计算方法及装置
CN112257589A (zh) * 2020-10-22 2021-01-22 大连交通大学 一种异常停留车辆的检测方法
CN113449217A (zh) * 2020-03-27 2021-09-28 斑马智行网络(香港)有限公司 迁移轨迹、热力图生成及网点确定的方法、设备

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018119606A1 (en) * 2016-12-26 2018-07-05 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for representing a map element and method and apparatus for locating vehicle/robot
CN109766902B (zh) * 2017-11-09 2021-03-09 杭州海康威视系统技术有限公司 对同区域的车辆聚类的方法、装置和设备
CN108615359B (zh) * 2018-05-04 2020-05-08 山东合天智汇信息技术有限公司 一种车辆落脚点分析方法和装置
EP3807836A4 (en) * 2018-06-15 2022-01-26 Bayerische Motoren Werke Aktiengesellschaft INCREMENTAL POINT CLOUD SEGMENTATION
CN108875835B (zh) * 2018-06-26 2021-06-22 北京旷视科技有限公司 对象落脚点确定方法、装置、电子设备和计算机可读介质
CN109471907B (zh) * 2018-11-15 2022-04-29 刘长山 一种基于卡口数据的行车规律分析系统和方法
CN109741227B (zh) * 2019-01-07 2020-12-08 巩志远 一种基于最近邻算法预测人房一致性处理方法及系统
CN109932702B (zh) * 2019-04-03 2021-07-30 森思泰克河北科技有限公司 道闸控制方法及道闸雷达
CN110838232A (zh) * 2019-09-27 2020-02-25 浙江工业大学 基于过车电警数据的单一车辆od获取方法
CN111369791B (zh) * 2019-10-18 2021-04-27 杭州海康威视系统技术有限公司 落脚点确定方法、装置、电子设备及存储介质
CN111540202B (zh) * 2020-04-23 2021-07-30 杭州海康威视系统技术有限公司 一种相似卡口确定方法、装置、电子设备及可读存储介质
CN112201047B (zh) * 2020-10-10 2022-02-18 武汉中科通达高新技术股份有限公司 一种基于Flink框架的嫌疑车辆落脚点分析方法及装置
CN112181986A (zh) * 2020-10-10 2021-01-05 武汉中科通达高新技术股份有限公司 一种基于Flink框架的数据分析方法及装置
CN112733047B (zh) * 2020-11-05 2022-10-28 浙江大华技术股份有限公司 车辆落脚点生成方法、装置、设备及计算机存储介质
CN112885101B (zh) * 2021-03-30 2022-06-14 浙江大华技术股份有限公司 确定异常设备的方法、装置、存储介质及电子装置
CN113779171B (zh) * 2021-09-26 2024-09-17 浙江大华技术股份有限公司 对象落脚点的确定方法、装置、存储介质及电子装置
CN117935531A (zh) * 2023-12-05 2024-04-26 中睿信数字技术有限公司 一种基于多源交通数据的落脚点分析方法以及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003042770A (ja) * 2001-07-31 2003-02-13 Kopisu:Kk 送迎バス位置情報配信システム
CN103325245A (zh) * 2013-06-25 2013-09-25 中国科学院信息工程研究所 一种黑名单车辆的时空行驶轨迹预测方法
CN104715612A (zh) * 2013-12-12 2015-06-17 南京中兴力维软件有限公司 基于行车轨迹匹配实现的嫌疑车辆跟踪方法及装置
CN104750800A (zh) * 2014-11-13 2015-07-01 安徽四创电子股份有限公司 一种基于出行时间特征的机动车聚类方法
CN104933870A (zh) * 2015-05-21 2015-09-23 中兴软创科技股份有限公司 基于车辆行为分析的车辆套牌识别方法与装置
CN104952273A (zh) * 2015-07-17 2015-09-30 东方网力科技股份有限公司 针对车辆行为的告警方法、装置及系统

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100547625C (zh) * 2008-01-31 2009-10-07 浙江工业大学 一种城市交通中的典型行驶路线分析方法
CN101930668B (zh) * 2009-04-29 2012-08-22 上海电器科学研究所（集团）有限公司 车牌识别的道路交通od信息采集系统的处理方法
CN102044163B (zh) * 2011-01-18 2013-08-07 北京世纪高通科技有限公司 一种提供路况信息的方法、装置及系统
CN102629297B (zh) 2012-03-06 2016-01-06 北京建筑工程学院 一种基于行程识别的出行者活动规律分析方法
JP5914249B2 (ja) * 2012-08-10 2016-05-11 クラリオン株式会社 経路計算システム、ナビゲーション装置および経路計算方法
US9224293B2 (en) * 2013-03-16 2015-12-29 Donald Warren Taylor Apparatus and system for monitoring and managing traffic flow
JP6293458B2 (ja) 2013-11-15 2018-03-14 株式会社日立製作所 プローブ情報管理装置、プローブ情報管理システムおよびプローブ情報管理方法
CN104318327A (zh) * 2014-10-17 2015-01-28 北京邮电大学 一种车辆轨迹预测分析方法
CN104318766B (zh) * 2014-10-22 2016-06-08 北京建筑大学 一种公交gps轨迹数据的路网匹配方法
CN104966129A (zh) * 2015-06-08 2015-10-07 浙江大学 一种车辆运行轨迹的分离方法
CN104952248B (zh) * 2015-06-08 2017-09-12 浙江大学 一种基于欧氏空间的车辆汇聚预测方法
JP6768557B2 (ja) * 2017-02-27 2020-10-14 パナソニックｉ−ＰＲＯセンシングソリューションズ株式会社 監視カメラシステム及び監視方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003042770A (ja) * 2001-07-31 2003-02-13 Kopisu:Kk 送迎バス位置情報配信システム
CN103325245A (zh) * 2013-06-25 2013-09-25 中国科学院信息工程研究所 一种黑名单车辆的时空行驶轨迹预测方法
CN104715612A (zh) * 2013-12-12 2015-06-17 南京中兴力维软件有限公司 基于行车轨迹匹配实现的嫌疑车辆跟踪方法及装置
CN104750800A (zh) * 2014-11-13 2015-07-01 安徽四创电子股份有限公司 一种基于出行时间特征的机动车聚类方法
CN104933870A (zh) * 2015-05-21 2015-09-23 中兴软创科技股份有限公司 基于车辆行为分析的车辆套牌识别方法与装置
CN104952273A (zh) * 2015-07-17 2015-09-30 东方网力科技股份有限公司 针对车辆行为的告警方法、装置及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3385919A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108182558A (zh) * 2017-12-04 2018-06-19 北京中交兴路信息科技有限公司 一种基于统计特征的运距计算方法及装置
CN113449217A (zh) * 2020-03-27 2021-09-28 斑马智行网络(香港)有限公司 迁移轨迹、热力图生成及网点确定的方法、设备
CN112257589A (zh) * 2020-10-22 2021-01-22 大连交通大学 一种异常停留车辆的检测方法
CN112257589B (zh) * 2020-10-22 2024-03-05 大连交通大学 一种异常停留车辆的检测方法

Also Published As

Publication number Publication date
EP3385919A1 (en) 2018-10-10
CN106846538B (zh) 2019-12-03
US10810870B2 (en) 2020-10-20
EP3385919B1 (en) 2024-03-27
EP3385919A4 (en) 2019-10-09
US20180357891A1 (en) 2018-12-13
CN106846538A (zh) 2017-06-13

Similar Documents

Publication Publication Date Title
WO2017092418A1 (zh) 过车记录处理方法和装置
Zheng et al. Diagnosing New York city's noises with ubiquitous data
Ye et al. Coupled-view based ranking optimization for person re-identification
CN107766883A (zh) 一种基于加权决策树的优化随机森林分类方法及系统
CN109118119A (zh) 风控模型生成方法及装置
CN111028016A (zh) 销量数据预测方法、装置以及相关设备
CN105069534A (zh) 客户流失预测方法以及装置
Li et al. A supervised clustering and classification algorithm for mining data with mixed variables
CN110334111A (zh) 一种多维轨迹分析方法及装置
CN109740479A (zh) 一种车辆重识别方法、装置、设备及可读存储介质
CN103226584B (zh) 形状描述符的构建方法及基于该描述符的图像检索方法
CN108171976A (zh) 基于在途数据的车辆用途识别方法
CN107784046B (zh) Poi信息处理方法和装置
CN110163631A (zh) 客户精准服务方法、装置、计算机设备及存储介质
CN111709382A (zh) 人体轨迹处理方法、装置、计算机存储介质以及电子设备
CN115545103A (zh) 异常数据识别、标签识别方法和异常数据识别装置
CN116188956A (zh) 一种深度伪造人脸图像检测的方法及相关设备
CN105844204A (zh) 人体行为识别方法和装置
CN116263735A (zh) 神经网络的鲁棒性评估方法、装置、设备及存储介质
CN109447112A (zh) 一种人像聚类方法、电子设备和存储介质
CN103678709B (zh) 一种基于时序数据的推荐系统攻击检测方法
CN110766938B (zh) 路网拓扑结构的构建方法、装置、计算机设备及存储介质
CN112015937A (zh) 一种图片地理定位方法及系统
Rousseeuw et al. Monitoring system of phytoplankton blooms by using unsupervised classifier and time modeling
Dutta et al. Inferencing transportation mode using unsupervised deep learning approach exploiting GPS point-level characteristics

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16869729

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016869729

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2016869729

Country of ref document: EP

Effective date: 20180704