CN113190769B - Communication characteristic data determining method, device, electronic equipment and storage medium - Google Patents

Communication characteristic data determining method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113190769B
CN113190769B CN202110501129.0A CN202110501129A CN113190769B CN 113190769 B CN113190769 B CN 113190769B CN 202110501129 A CN202110501129 A CN 202110501129A CN 113190769 B CN113190769 B CN 113190769B
Authority
CN
China
Prior art keywords
commute
user
data
determining
position data
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202110501129.0A
Other languages
Chinese (zh)
Other versions
CN113190769A (en
Inventor
王建光
秦思娴
项雯怡
阚长城
闫浩强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
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 Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110501129.0A priority Critical patent/CN113190769B/en
Publication of CN113190769A publication Critical patent/CN113190769A/en
Application granted granted Critical
Publication of CN113190769B publication Critical patent/CN113190769B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3438—Rendez-vous, i.e. searching a destination where several users can meet, and the routes to this destination for these users; Ride sharing, i.e. searching a route such that at least two users can share a vehicle for at least part of the route
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
    • 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
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses a method, a device, electronic equipment and a storage medium for determining commute characteristic data, relates to the field of data processing, and particularly relates to big data, automatic driving, intelligent transportation and the like. The specific implementation scheme is as follows: extracting the position data of the user from the position service data of the user and the acquisition time of each position data; and determining the commute characteristic data of the user according to the position data of the user and the acquisition time of each position data. The embodiment of the application can improve the collection efficiency of the commute data and reduce the collection cost of the commute data.

Description

Communication characteristic data determining method, device, electronic equipment and storage medium
Technical Field
The application relates to the field of data processing, in particular to big data, automatic driving, intelligent traffic and the like, and particularly relates to a method and device for determining commute characteristic data, electronic equipment and a storage medium.
Background
The travel rule of people is an important subject of urban planning and traffic planning research.
The commute (refers to the travel of a person going from home to work or the travel of a person going from work to home) is taken as the most important resident travel type, and can be used for researching the time-space distribution of urban commute flow and the space-time distribution in a road network, so that a reference is provided for urban traffic planning.
Disclosure of Invention
The application provides a method, a device, electronic equipment and a storage medium for determining commute characteristic data.
According to an aspect of the present application, there is provided a commute feature data determination method comprising:
extracting the position data of the user from the position service data of the user and the acquisition time of each position data;
and determining the commute characteristic data of the user according to the position data of the user and the acquisition time of each position data.
According to another aspect of the present application, there is provided a commute feature data determining apparatus comprising:
the commute position data determining module is used for extracting the position data of the user from the position service data of the user and the acquisition time of each position data;
and the commute characteristic data determining module is used for determining the commute characteristic data of the user according to the position data of the user and the acquisition time of each position data.
According to another aspect of the present application, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of commute feature data determination of any of the embodiments of the application.
According to another aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the commute feature data determining method according to any of the embodiments of the present application.
According to another aspect of the application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the commute feature data determination method of any of the embodiments of the application.
The embodiment of the application can improve the collection efficiency of the commute data and reduce the collection cost of the commute data.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
The drawings are included to provide a better understanding of the present application and are not to be construed as limiting the application. Wherein:
FIG. 1 is a schematic illustration of a method of commute feature data determination in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram of a method of commute feature data determination, according to an embodiment of the application;
FIG. 3 is a schematic diagram of a method of commute feature data determination, according to an embodiment of the application;
FIG. 4 is a schematic diagram of a method of commute feature data determination, according to an embodiment of the application;
FIG. 5 is a schematic illustration of a curved road segment according to an embodiment of the application;
fig. 6 is a schematic view of a straight road segment according to an embodiment of the application;
FIG. 7 is a schematic diagram of a candidate grid set according to an embodiment of the application;
FIG. 8 is a schematic diagram of road commute pressure for an inward commute mode, according to an embodiment of the application;
FIG. 9 is a schematic diagram of road commute pressure for a reverse commute mode, according to an embodiment of the application;
FIG. 10 is a schematic diagram of road commute pressure for one side commute mode, according to an embodiment of the application;
FIG. 11 is a schematic diagram of road commute pressure for an internal commute mode, according to an embodiment of the application;
FIG. 12 is a block diagram of a commute feature data determination device according to an embodiment of the present application;
fig. 13 is a block diagram of an electronic device for implementing the commute feature data determination method of an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of a commute feature data determining method according to an embodiment of the present application, which may be applied to a case of extracting location data from location service data of a user and determining a commute feature of the user. The method of the embodiment can be executed by a commute characteristic data determining device, the device can be realized in a software and/or hardware mode, and the device is specifically configured in an electronic device with certain data operation capability, and the electronic device can be a client device, a mobile phone, a tablet personal computer, a vehicle-mounted terminal, a desktop computer and the like, or can be server-side equipment.
S101, extracting the position data of the user from the position service data of the user and the acquisition time of each position data.
The location service data of the user may refer to data associated with geographical location information acquired by the user using a location based service (Location Based Service, LBS). The location service data may include: the positioning data of the user at a certain moment, namely the user position data and the acquisition time of the position data. In general, the location service data of a user is obtained by requesting location service from a location server by using a client under the authorization of the user, so that the location server obtains the location data of the user, records the current time, and determines the acquisition time. The location data may refer to geographic location information of the user. The acquisition time of the location data may refer to the time when the user is in the location data. The location data of the user and the acquisition time of the location data are used to determine that the user is at the geographic location represented by the location data at the acquisition time.
S102, determining the commute characteristic data of the user according to the position data of the user and the acquisition time of each position data.
The user commute feature data is used to describe the user's commute travel behavior. The statistics of a large amount of user commute characteristic data can determine the distribution situation of the people flow in the city in space and time, so that a reference is provided for the traffic planning of the city. Specifically, according to the acquisition time of the position data of the same user, the position data in the commute time period can be counted, and according to the position data in the commute time period, the user commute characteristic data can be extracted.
Optionally, the commute feature data includes at least one of: a commute start end point, a commute start time, and a commute path.
The commuting behavior may include a behavior of going from home to work and/or a behavior of going from work to home. A commute start and end point may refer to a start and/or end point of a commute behavior. Illustratively, the commuting behavior is a behavior from home to work, and the commuting start endpoint includes: home-initiated and/or work-site (e.g., company, factory, or unit, etc.). The commuting behavior is the behavior of going home from work, and the commuting starting and ending point comprises: starting at the work site and/or ending at home.
The commute start time may refer to the departure time of the commute. Illustratively, the commute behavior is a behavior from home to work, and the commute start time includes: the time the user left home. The commuting behavior is the behavior of going home from work, and the commuting starting time comprises: the time the user left from the work site.
A commute path may refer to route-related data of a commute behavior. The commute path may include at least one of: commute route, commute mode, commute time and commute distance, etc. A commute route may refer to a road through which a user commutes. Commute mode may refer to a mode of traffic for commute behavior, for example, including at least one of: walking, riding, driving, public transportation, subway and the like. Commute time may refer to the time spent on the commute, i.e., the duration from the start of the commute to the end of the commute. The commute distance may refer to the length of the commute route.
By configuring the commute feature data as at least one of a commute start-end point, a commute start time, a commute path of the user, and the like, the richness of the commute feature data can be increased, and at the same time, the commute feature can be extracted from the multi-dimensions, accurately describing the commute behavior of the user.
In the existing travel-related data collection method, the traditional questionnaire survey is used for collecting, the number of travel samples collected is small, a large amount of economic cost and labor cost are consumed, the timeliness of data updating is poor (the data updating is only carried out once every few years), the phenomenon of reporting omission and reporting of personal travel is also caused, and fewer people in recent years are willing to cooperate with the questionnaire survey; through wearing GPS equipment for volunteers to collect, though the real travel process can be restored more truly, fewer travel samples can be collected by the method, and the method is also bad in the aspects of execution cost, data frequency and the like. The method and the device acquire the position data and the acquisition time according to the position service data provided by the user authorization, so that the commute characteristics are determined, real-time position data of a large number of users can be quickly collected in real time and counted, the real travel process can be truly restored, a large number of user position data can be quickly collected, meanwhile, the user does not need to additionally execute operation, the labor cost is reduced, the user uses the position service every day or even every moment, the position service data are provided, and the acquisition instantaneity of the position service data is greatly improved, so that the instantaneity of the position data is improved.
According to the technical scheme, the position data of the user and the acquisition time of each position data are extracted from the position service data of the user, and the user commute characteristic data are determined, so that a large amount of user trip data can be quickly collected, the collection efficiency of the trip data is improved, the labor cost and the economic cost for collecting the trip data are reduced, the trip data can be updated in real time, the instantaneity of the trip data is improved, and the commute characteristics of the user can be accurately and quickly determined.
Fig. 2 is a flowchart of another method for determining commute feature data according to an embodiment of the present application, further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. Determining the commute feature data of the user according to the position data of the user and the acquisition time of each position data, wherein the commute feature data comprises the following specific steps: aggregating the position data of the user to form at least one position cluster; counting the number of the position data belonging to a specified time period in the position cluster according to the acquisition time of the position data for each position cluster, wherein the specified time period comprises a working time period and/or a rest time period; and obtaining the land type of each position cluster, and determining the commute starting and ending point of the user according to the statistical result of each position cluster.
S201, extracting the position data of the user and the acquisition time of each position data from the position service data of the user.
The same or similar features may be referred to the foregoing description.
S202, aggregating the position data of the user to form at least one position cluster.
Aggregating the location data may refer to classifying the location data according to the geographic location represented by the location data. One location cluster represents a collection of a plurality of location data that are closely located. The location clusters are used to group location data suspected of being in the same geographic location into a set to determine the geographic location that the user is typically located in, and thus the user's home and work place.
For example, a clustering algorithm may be used to aggregate the location data to form at least one location cluster. By way of example, the clustering algorithm may be a partition-based algorithm, a Density-based algorithm, a mesh-based algorithm, a graph theory-based algorithm, or the like, in particular a K-means algorithm (K-means), a noise-based application spatial clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN), a statistical information mesh algorithm (STatistical INformation Grid, STING), or a minimum spanning tree (Minimum Spanning Tree, MST), or the like. Optionally, the position data is aggregated by adopting a spatial density clustering algorithm DBSCAN to form at least one position cluster.
S203, counting the number of the position data belonging to a specified time period in the position cluster according to the acquisition time of the position data for each position cluster, wherein the specified time period comprises a working time period and/or a rest time period.
The specified time period is used to distinguish between the working time and the rest time of the user. The working period may refer to a period in which a user processes a work at a work place, and the rest period may refer to a period in which the user does not work at home. Illustratively, the working period is 10:00-18:00 of the working day, and the rest period is 20:00-07:00 of the working day. If the user is a shift worker, a free worker, or the like, the working period and the rest period are different from the above example, for example, the working period of the shift worker is 20:00 to 07:00 on the working day, and the rest period is 10:00 to 18:00 on the working day. Can be specifically set according to the specific situation.
The number of the position data belonging to the specified time period in the position cluster is counted, and the number of the position data in the working time period and/or the number of the position data in the rest time period can be counted in the position cluster. Typically, the same geographic location is frequently located during the working period, indicating that the geographic location is a work site; frequent in the same geographic location during the rest period indicates that the geographic location is home, where frequent in the same geographic location may mean that the number of location data representing the same geographic location is large. Accordingly, by counting the number of location data within a specified period of time, location data of the work site and/or home can be determined.
S204, obtaining the land type of each position cluster, and determining the commute starting and ending point of the user according to the statistical result of each position cluster.
The type of land may refer to the type of building at the geographic location. By way of example, the land type may include a residential type or a work type, wherein the work type may include: industrial type, commercial type, scientific type, etc. The location data of the living type may refer to a geographical location where a building suitable for human living is located, among others. Industrial type location data may refer to the geographic location of a building in which a human performs an industrial activity. The business type location data may refer to the geographic location of a building in which a human performs a business. The scientific type of location data may refer to the geographical location of a building where a human performs a scientific activity. In addition, the work type also includes an agricultural type or an administrative office type, etc., and can be specifically set as required.
The usage type of a location cluster may refer to a usage type of a geographic location at a cluster center of the location cluster. The cluster center of the position cluster may be calculated, or the position data closest to the average value may be determined as the cluster center, and in addition, the logical center (such as the center of gravity) of the shape of the cluster distribution may be calculated to obtain the cluster center, which may be determined as needed. In general, information such as a building name and a tag is labeled for each geographical location in map data, and the tag information generally includes the use of the building, so that the type of land used for each geographical location can be determined. The type of the land can be used for acquiring label information at the geographic position corresponding to the cluster center in the map data.
Determining the user's commute start point may refer to determining the user's commute start point and the user's commute end point. And selecting the position data in the position cluster from the position clusters with the largest number in the statistics results in the rest time period and the land type being the living type, and determining the position data as the home. And selecting the position data in the position cluster from the position clusters with the largest number in the statistics results in the working time period and the position cluster with the land type as the working type, and determining the position data as the working place. Wherein, the position data corresponding to the cluster center in the position cluster can be selected and determined as a home or a work place. In a commute from home to work site, the home is taken as a commute start point and the work site is taken as a commute end point. In the commuting from the work place to the home, the work place is taken as a commuting start point, and the home is taken as a commuting end point.
Optionally, determining the target position data in the position cluster with the largest number in the statistics result in the rest time period and the land type being the living type as the home of the user; in the position clusters except the position cluster where the target position data are located, the number of the statistical results in the working time period is the largest, and the target position data are determined as the working place of the user in the position cluster with the working type; the user's home and work place is determined as the user's commute origin. Wherein, in the position cluster that the quantity is the biggest in the statistics result in the rest time period, and the land type is living type, the target position data, confirm as user's family, include: detecting the land type of the position cluster with the largest number in the statistical result in the rest time period; and removing the position cluster if the land type of the position cluster with the largest number in the statistical result in the rest time period is the non-resident type, detecting the land type of the position cluster with the largest number in the statistical result in the rest time period until the position cluster with the largest number in the statistical result in the rest time period is screened out, wherein the land type is the resident type, and determining the target position data in the position cluster as a family. The method for determining the target position data in the position cluster with the largest number in the statistical results in the working time period and the land type being the working type as the working place of the user comprises the following steps: detecting the land type of the position cluster with the largest number in the statistical result in the working time period; and removing the position cluster if the position cluster with the largest number in the statistical result in the working time period is of a non-working type, detecting the position cluster with the largest number in the statistical result in the rest position clusters until the position cluster with the largest number in the statistical result in the working time period is screened out, wherein the position cluster with the largest number in the statistical result in the working time period is of the working type, and determining the target position data in the position cluster as the working place.
In a specific example, LBS location data is collected for a user for all its last 3 months, and spatially close location points are clustered into a location cluster by using a spatial density clustering algorithm (e.g., DBSCAN), so as to obtain a plurality of location clusters, where each location cluster represents an activity of the user, and the activity should include the user's home and work place. For each location cluster of the user, the number of location data N1 and the number of location data N2 occurring at 10:00-18:00 and 20:00-07:00 are counted respectively. And checking the land type of the position cluster with the largest N2 value, if the position cluster is the living type, determining the position data of the position cluster as the geographic position of the user home, otherwise, checking the land attribute of the position cluster with the second largest N2 value (and the like) until the geographic position of the user home is found. Removing the position cluster representing the home, checking the land type of the position cluster with the largest N1 value, if the position cluster is the type representing the work place such as the industrial type or the commercial type, determining the position of the position cluster as the geographic position of the user work place, otherwise checking the land type of the position cluster with the second largest N1 value (and the like) until the geographic position of the user work place is found.
In addition, if the land type of all the position clusters is a non-working type and/or a living type, determining a commuting starting end point of the user according to the statistical result of each position cluster; if the number of the position data included in the position cluster where the determined home is located is smaller than the set number threshold value, and/or the number of the position data included in the position cluster where the determined work place is located is smaller than the set number threshold value, determining the commuting start and end points of the user according to the statistical result of each position cluster.
Illustratively, if all of the user's location clusters do not match the type of usage corresponding to the home or work place, indicating that the location data is insufficient to determine the user's home and work place, the user is not treated as a commute sample. If the determined "home location cluster" where the home is located and "workplace location cluster" where the workplace is located contain fewer than m location points, indicating that the location data is insufficient to determine the user's home and workplace, the user is not taken as a commute sample. m is a preset number threshold. By not taking the user as a commute sample, a collection of candidate commute samples may be screened, with both the start and end of the commute for these samples being determined, improving the representativeness of the commute samples.
According to the technical scheme, position data are aggregated to form position clusters according to the space positions, the number of the position data associated with the working time period and/or the rest time period in each position cluster is counted, the home and the working place of a user are determined according to the land type of each position cluster, the long-term geographic position of the user in the appointed time period can be accurately counted, the home and the working place can be accurately determined, the commute starting point and the commute ending point of the user are determined, the starting point and the ending point of the commute behavior are determined through analysis of the time dimension and the space dimension, and the detection accuracy of the commute starting point and the ending point is improved.
Fig. 3 is a flowchart of another method for determining commute feature data according to an embodiment of the present application, further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. Determining the commute feature data of the user according to the position data of the user and the acquisition time of each position data, wherein the commute feature data comprises the following specific steps: determining commute position data within a commute time period according to the acquisition time of the position data; counting the space distance between each commute position data and the commute starting and ending point; screening out at least one commute departure location data according to the spatial distance between each commute location data and the commute departure point; and determining the commute starting time of the user according to the acquisition time of the commute departure position data.
S301, extracting the position data of the user and the acquisition time of each position data from the position service data of the user.
The same or similar features may be referred to the foregoing description.
S302, determining the commute position data in the commute time period according to the acquisition time of the position data.
A commute time period may refer to a collection of times that a user has occurred a commute. Illustratively, the commute time period is a time period from home to work site for the user, such as work day 5:00-11:00, or a time period from work site to home for the user, such as work day 17:00-20:00. The commute location data is the location data of the acquisition time within the commute time period. Wherein the commute location data may be categorized according to commute behavior. For example, the commute location data may be divided into commute location data from home to work site; and/or commute location data from work site to home.
S303, counting the space distance between each commute position data and the commute starting and ending point.
The commute origin and destination may be determined with reference to the foregoing description. The spatial distance between the commute position data and the commute start and end points may refer to the spatial distance between the commute position data and the commute start and/or end points. In an embodiment of the present application, the commute feature data comprises a commute start time, and the corresponding spatial distance between the commute position data and a commute start end point, in particular, the spatial distance between the commute position data and the commute start point. Wherein the spatial distance may refer to a distance between a geographical location represented by the commute location data and two points of the commute origin. The spatial distance can be determined by the latitude and longitude of the geographical position represented by the commute position data and the latitude and longitude of the commute start point, and the calculated linear distance. For commuting from home to work, i.e. to work, the start point of the commuting is home; for commuting from work place to home, i.e. off duty, the start of the commuting is the work place.
S304, screening out at least one commute departure position data according to the space distance between each commute position data and the commute departure point.
The commute departure location data may refer to commute location data representing a departure location of a commute activity. The commute departure location data is used as a commute departure location to determine a commute start time. And screening out at least one commute departure position data according to the space distance and the distance threshold. Specifically, among the commute position data, the commute position data having a spatial distance greater than the distance threshold value is selected and determined as the commute departure position data. The distance threshold may be set as desired, for example, 20 meters. In fact, the user is at the start of the commute for a long time before actually traveling, and the collection time of the collected commute position data is not the actual start time of the commute of the user in the aforesaid time period. When a certain distance exists between the user and the commute starting point, the user is indicated to leave the commute starting point and start to the destination, so that the commute position data at this time can be determined as the commute starting position data.
S305, determining the commute starting time of the user according to the acquisition time of the commute starting position data.
The user's commute start time may refer to a start time of the user's commute behavior and may include a start time from home to work site and/or a start time from work site to home. The commute departure position data of the same commute can be sequenced according to the acquisition time and the sequence time of the same day, and the acquisition time of the commute departure position data of the first sequence of the same commute in the same day is determined as the commute starting time of the same commute in the same day. The commute start time of the same commute every day over a period of time (e.g., 3 months) is counted, and the expected value is calculated and determined as the commute start time of the user's commute.
Optionally, the commute departure location data is classified according to the date of the collection time (usually the working day) and the geographic location corresponding to the commute departure location data, the date of the commute departure location data in the same class is the same, the commute behavior is the same, for example, the commute behavior is the same as the commute departure location data, the commute start points are the same as the commute start points, for example, the commute start points are the home or the working place. In each class, the acquisition time of the commute departure position data with the forefront time sequence is determined as the corresponding commute starting time of the class. And calculating an expected value according to the commute starting time corresponding to a plurality of classes of the same commute behavior in a preset statistical time period, and determining the expected value as the commute starting time of the user. The expected value can be calculated according to a calculation formula of the expected value of the n-too-distribution.
In a specific example, for a user, a first location point is found that is spatially more than d away from home during 5:00-11:00 each weekday. The distribution of the time generated by such location points during all working days of the user over 3 months on the time axis is analyzed, and in fact, the distribution curve is similar to a normal distribution, and the expected value of the distribution is selected as the departure time of the user from work, i.e. the start time of the user's commute from home to working place. Where d is the distance threshold.
For a user, on each workday, find the first location point during 17:00-20:00 that is spatially farther than d from the workplace. And analyzing the distribution of the time generated by the position points in all working days of the user in 3 months on a time axis, wherein the distribution curve is similar to the distribution of the front, and selecting the expected value of the distribution as the departure time of the user going home from work. I.e. the start time of the user's commute from the work place to home.
According to the technical scheme, the commute position data are screened out according to the acquisition time, the commute departure position data are screened out according to the position between the commute departure position data and the commute start position data, the commute start time of the user is finally determined according to the acquisition time of the commute departure position data, the departure geographic position and the departure time of the user in the commute time period can be accurately counted, the start time of the commute behavior is determined through analysis from the time dimension and the space dimension, and the detection accuracy of the commute start time is improved.
Fig. 4 is a flowchart of another method for determining commute feature data according to an embodiment of the present application, further optimized and expanded based on the above technical solution, and may be combined with the above various alternative embodiments. Determining the commute feature data of the user according to the position data of the user and the acquisition time of each position data, wherein the commute feature data comprises the following specific steps: determining a commute starting end point and a commute starting time according to the position data of the user and the acquisition time of each position data; determining a commute starting and ending point as a path starting and ending point; determining a plurality of planned paths according to the commute starting time and the path starting and ending points; and screening the commute path of the user from each planned path according to the position data of the user.
S401, extracting the position data of the user from the position service data of the user and the acquisition time of each position data.
The same or similar features may be referred to the foregoing description.
S402, determining a commute starting end point and a commute starting time according to the position data of the user and the acquisition time of each position data.
The commute start end point and the commute start time may be determined with reference to the foregoing description.
S403, determining the commute starting and ending point as the path starting and ending point.
For each commute action, determining a commute start point as a path start point; the commute end point is determined as the path end point.
S404, determining a plurality of planning paths according to the commute starting time and the path starting and ending points.
The commute start time is determined as the path start time. At least two commute modes are selected, and a planned path is determined. The starting time and the starting and ending points of the paths of different planning paths are the same, and the commuting modes of the different planning paths are different. Illustratively, the commute mode may include driving, public transportation, subway, riding or walking, and the like. Wherein, a path planning algorithm can be adopted to consider the historical road condition of the start time of the commute to give the shortest path between the start point and the end point of the commute to travel in a specific traffic mode. The historical road conditions may be determined according to the flow of pedestrians, vehicles, etc. on each road during the historical period. In practice, the planned path is determined, and at the same time, the commute mode, the commute time consumption, the commute distance, etc. of the planned path are also determined. By way of example, the path planning algorithm may be a graph search method, a fast search random tree algorithm (Rapidly-exploring Random Tree, RRT), a manual potential field method, an obstacle avoidance algorithm (Bug), or an incremental heuristic algorithm, etc. The planned path comprises a plurality of path points, the planned path is formed by connecting the plurality of path points, and the sparse road sections in the planned path can be subjected to difference value, so that the linear distance between each two adjacent path points in each planned path is larger than the interval threshold value.
S405, screening the commute paths of the user from the planned paths according to the position data of the user.
Different commuting modes are used for determining different planning paths, and screening the commuting paths of the user can be used for screening out which commuting mode the user selects for commuting and carrying out the actual path for commuting in the commuting mode. According to the position data of the user, the travel route of the user can be determined, the most similar planning path is searched in the planning paths, and the most similar planning path is determined as the commuting path of the user.
Optionally, the selecting the commute path of the user from the planned paths according to the position data of the user includes: gridding each planning path to obtain a candidate grid set corresponding to each planning path; forming a real grid set according to the position data of the user; and determining a candidate grid set matched with the real grid set in each candidate grid set, and determining a corresponding planning path as a commute path of the user.
The candidate mesh set may refer to a set of mesh formations obtained by gridding the planned path. The meshing process may refer to mapping path points included in the planned path to grids in a map grid network to facilitate normalization of different planned paths. And carrying out gridding processing on each planning path, and mapping the planning paths into a map grid network to obtain a candidate grid set of the planning paths in the map grid network, wherein the map grid network can also be called a map grid network, and the map grid network can be formed by gridding a map according to preset intervals. The real grid set may refer to a set of grid formations resulting from the mapping of location data into a map grid network. Wherein, a plurality of position data or a plurality of path points can be mapped to the same grid, and the side length of the grid is the interval threshold value of the interpolation. Alternatively, mapping to the same grid does not repeat the recording, i.e. the formed grid set does not include a repeating grid. In fact, the different planned paths include different numbers of straight line segments and curved line segments, resulting in a large number of path points, and it is difficult for the different planned paths to match the user's position data with a uniform rule. Each planning path is gridded, the planning paths can be normalized into a grid set under the same map grid network, position data can be matched according to a unified rule, and the commute paths can be accurately obtained. In addition, a plurality of path points can be mapped into the same grid, so that the data volume of each path point participating in the matching detection can be reduced, and the efficiency of the matching detection is improved.
The candidate grid set matching the real grid set is used to determine the commute path, i.e. to determine the actual path of the user, and may refer to the candidate grid set most similar to the real grid set.
The same gridding processing is carried out on the planned path and the position data, so that the data can be accurately unified into standard data for comparison, the screening accuracy of the candidate grid set is improved, the detection accuracy of the commute path is improved, redundant data can be reduced, and the path matching detection efficiency is improved.
Optionally, the determining, in each candidate grid set, a candidate grid set matched with the real grid set includes: calculating the intersection of each candidate grid set and the real grid set; calculating the ratio of the number of grids of each intersection to the number of grids of the candidate grid set of the intersection; and determining a planning path corresponding to the candidate grid set with the largest ratio as the commute path of the user.
The intersection is used to determine the same mesh in the candidate set of meshes as in the real set of meshes. The ratio is used to determine the proportion of the same grid to the candidate grid set. The number of meshes included in the intersection is counted, and the number of meshes included in the candidate mesh set used to calculate the intersection is counted. The ratio of the number of meshes of each intersection to the number of meshes of the candidate mesh set for which the intersection is calculated is the ratio of the number of meshes of the mesh included in the intersection to the number of meshes of the candidate mesh set for which the intersection is calculated for each intersection. In general, the larger the ratio is, the more grids of the candidate grid set and the real grid set overlap, and the fewer non-overlapping grids in the candidate grid set are, so that the candidate grid set with the largest ratio can be determined as the candidate grid set most similar to the real grid set, and the corresponding planning path can be determined as the commute path of the user.
The candidate grid set most similar to the actual grid set can be accurately determined by calculating the intersection of the candidate grid set and the actual grid set and the grid quantity ratio of the intersection to the candidate grid set, so that the commuting path of the user is determined, the actual path of the commuting of the user is inquired, the detection accuracy of the commuting path is improved, in addition, the detection process of the commuting path can be simplified and the detection efficiency is improved by calculating the intersection and the ratio.
In a specific example, for each user, a path planning module is called by taking a commute starting point (home or work place) as a path starting point, a commute ending point (work place or home) as a path ending point, a commute starting time as a condition, and various commute modes as policy parameters, a path searching algorithm adopting path planning can consider the historical road condition of the commute starting time to give the shortest path between the path starting point and the path ending point, which goes out in a specific commute mode, so as to obtain a plurality of planning paths, and each planning path corresponds to the determined commute mode, the commute time consumption, the commute distance and the commute path.
Each commute path of the user is spatially interpolated. Commuting paths are described by waypoints, which are denser for curved road segments (as in fig. 5); for a straight road segment, the path points of the straight road segment are sparse (as in fig. 6), and for a road segment with sparse path points, that is, a road segment with a linear distance between adjacent path points greater than f, a plurality of points need to be inserted between the two road segments, so that the linear distance between the adjacent points is less than f, where f is an interval threshold, and f is 5 meters as an example.
And gridding the path point sequence of the candidate path after interpolation, wherein the grid side length is f, and a grid sequence is generated. As in fig. 7, the dashed dots represent the path points resulting from interpolation. The main purpose of gridding is two-way: the geographic space can be divided into standard units, so that subsequent calculation of path matching and the like is facilitated; multiple path points belonging to the same grid are aggregated into one grid, so that the calculation amount of participation in operation is reduced. Thus, a plurality of meshed candidate paths from the path starting point to the path ending point of the user are obtained, and each meshed candidate path has a determined commuting mode, commuting time consumption, commuting distance and the like.
Representing all position data generated by the user in 3 months by using a gridding result to obtain a real grid set U, wherein the number of grids in the U is size (U); in the last step, each gridding candidate path corresponds to a candidate grid set Ri (i=1, 2,3 and …) respectively, and corresponds to the grid number size (Ri). The number size (U.U.Ri) of the grid in the intersection of U and Ri is calculated. The ratio r=size (U n Ri)/size (Ri) is defined as the matching rate, the larger the ratio r is, the more matching of the observable user location data with the candidate grid set Ri is indicated. Selecting a planning path corresponding to the candidate grid set Ri with the maximum r as an actual path for the user to commute, and determining a commute mode, commute time consumption and commute distance; if there are multiple sets of biggest and equal candidate grids, the planned path with the shortest time consumption is selected as the actual path for the user commute.
Optionally, the commute feature data determining method further includes: acquiring a commute user set in a road network; and determining the commute pressure of each road in the road network according to the commute characteristic data of each user in the commute user set.
The road network may refer to a network formed by a plurality of roads to be detected. A commute user collection may refer to a collection formed by users of the pathway road network of a commute path. The commute feature data of each user in the commute user set can be obtained through the commute feature data determining method. Commute pressure is used to describe the flow size of pedestrians and vehicles, etc. passing through a road network. The commute pressure may be determined based on the number of users of the pathway road network over a specified period of time. And the number of users of the pathway road network within a specified time period may be determined based on the commute feature data of each user in the set of commute users. For example, the commute pressure may be equal to the number of users of the pathway road network over a specified period of time, or the commute pressure may be equal to the ratio of the number of users of the pathway road network over a specified period of time to the length of the road, and further, the commute pressure may be determined in other situations, as may be desired.
The method comprises the steps of calculating the number of users of any road in a road network in a specified time period according to the commute characteristic data of each user in a commute user set. The user who approaches a certain road in a specified time period may refer to a user who determines the actual commute time of the user according to the start time of the commute and the time consumption of the commute path, and the actual commute time of the user is completely overlapped with or partially overlapped with the specified time period, and the commute path is completely overlapped with or partially overlapped with the road. The users of the route may be counted as one user of the route in the route road network for a specified period of time. Or the weight of the user can be determined according to the overlapping time period between the commute time and the specified time period and the overlapping length of the commute path and the road, and the user is counted as the number of users with the weight of the road in the road network in the specified time period, wherein the weight is a value between 0 and 1. The calculation mode of the number of users can be determined according to the needs. The commute pressure can be calculated for each road in the road network, or the commute pressure of the road network can be counted by integrating the roads.
In a specific example, by using the method for determining the commute feature data provided by the embodiment of the present application, the commute features of a large number of commute users are obtained, including a commute start and end point, a commute start time, a commute mode, a commute time consuming and a commute path, and note that the commute path is represented by a detailed route path point in the path planning result, so that the commute path can be corresponding to a specific road section in the road network. As shown in fig. 8-11, the result of the commute pressure analysis (thicker line, higher road commute pressure) on the road in 4 commute modes (inward commute, reverse commute, lateral commute, internal commute, etc.) for a certain city using the commute feature data of the mass samples. The different commute modes correspond to the commute behavior of different areas to areas, and the commute behavior of the internal commute mode is exemplified by the commute behavior from the commute start point in the urban area to the commute end point in the urban area; the commuting behavior of the inward commuting mode refers to the commuting behavior from the commuting start point in the urban area to the commuting end point in the urban area; the commuting behavior of the reverse commuting mode refers to the commuting behavior from the commuting start point in the urban area to the commuting end point in the urban area; the commuting behavior of the lateral commuting mode refers to the commuting behavior from the commuting start point in the off-city area to the commuting end point in the off-city area.
The commuting pressure of each road in the road network is determined by acquiring the commuting user set in the road network and according to the commuting characteristic data of each user, the commuting pressure can be counted according to a real large number of user commuting data, the detection accuracy of the commuting pressure is improved, the commuting data acquired at low cost are counted, and the detection cost of the commuting pressure can be reduced.
According to the technical scheme, the plurality of planning paths are determined according to the start time and the start and end points of the commute, and the commute paths are screened out from the plurality of planning paths according to the position data of the user, so that the paths which are most in line with the actual commute conditions of the user can be accurately detected based on the real positions of the user, and the detection accuracy of the commute paths is improved.
Fig. 12 is a block diagram of a commute feature data determining apparatus in an embodiment of the present application, which is applicable to a case where position data is extracted from position service data of a user and a commute feature of the user is determined, according to an embodiment of the present application. The device is realized by software and/or hardware, and is specifically configured in the electronic equipment with certain data operation capability.
A commute feature data determining apparatus 500 as shown in fig. 12, comprising: a commute location data determination module 501 and a commute feature data determination module 502; wherein,,
A commute location data determining module 501, configured to extract location data of a user from location service data of the user, and a collection time of each of the location data;
the commute feature data determining module 502 is configured to determine the commute feature data of the user according to the location data of the user and the acquisition time of each location data.
According to the technical scheme, the position data of the user and the acquisition time of each position data are extracted from the position service data of the user, and the user commute characteristic data are determined, so that a large amount of user trip data can be quickly collected, the collection efficiency of the trip data is improved, the labor cost and the economic cost for collecting the trip data are reduced, the trip data can be updated in real time, the instantaneity of the trip data is improved, and the commute characteristics of the user can be accurately and quickly determined.
Further, the commute feature data comprises at least one of: a commute start end point, a commute start time, and a commute path.
Further, the commute feature data determination module 502 includes: a position aggregation unit, configured to aggregate position data of the user to form at least one position cluster; the time-sharing statistics unit is used for counting the number of the position data belonging to a specified time period in the position cluster according to the acquisition time of the position data for each position cluster, wherein the specified time period comprises a working time period and a rest time period; and the commuting starting and ending point determining unit is used for acquiring the land type of each position cluster and determining the commuting starting and ending point of the user according to the statistical result of each position cluster.
Further, the commute feature data determination module 502 includes: a commute position data determining unit for determining commute position data within a commute time period based on the acquisition time of the position data; a start point distance determining unit for counting a spatial distance between each of the commute position data and a commute start point; a start point position data determining unit, configured to screen out at least one commute start position data according to a spatial distance between each commute position data and the commute start end point; the commute starting time determining unit is used for determining the commute starting time of the user according to the acquisition time of the commute starting position data.
Further, the commute feature data determination module 502 includes: a commute start end point and start time determining unit configured to determine a commute start end point and a commute start time according to the position data of the user and the acquisition time of each of the position data; a path start and end point determining unit configured to determine a commute start and end point as a path start and end point; a planned path determining unit configured to determine a plurality of planned paths according to the commute start time and the path start and end points; and the commuting path determining unit is used for screening the commuting paths of the users from the planning paths according to the position data of the users.
Further, the commute path determining unit includes: a candidate grid set determining subunit, configured to perform gridding processing on each planned path to obtain a candidate grid set corresponding to each planned path; a real grid set determining subunit, configured to form a real grid set according to the location data of the user; and the grid set matching subunit is used for determining a candidate grid set matched with the real grid set in each candidate grid set and determining a corresponding planning path as the commute path of the user.
Further, the grid set matching subunit includes: an intersection calculating subunit, configured to calculate an intersection of each candidate grid set and the real grid set; a grid number comparison subunit, configured to calculate a ratio of the number of grids of each intersection to the number of grids of the candidate grid set for calculating the intersection; and the planning path screening subunit is used for determining the planning path corresponding to the candidate grid set with the largest ratio as the commute path of the user.
Further, the commute feature data determining device further includes: the commute user set acquisition module is used for acquiring a commute user set in the road network; and the road commute pressure determining module is used for determining the commute pressure of each road in the road network according to the commute characteristic data of each user in the commute user set.
The object detection device can execute the method for determining the commute characteristic data provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing the method for determining the commute characteristic data.
According to embodiments of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.
Fig. 13 shows a schematic block diagram of an example electronic device 600 that may be used to implement an embodiment of the application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 13, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, such as the commute feature data determination method. For example, in some embodiments, the commute feature data determination method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the commute feature data determination method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the commute feature data determination method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present application may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution disclosed in the present application can be achieved, and are not limited herein. In the technical scheme of the application, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.

Claims (14)

1. A commute feature data determination method, comprising:
extracting the position data of the user from the position service data of the user and the acquisition time of each position data;
determining the commute characteristic data of the user according to the position data of the user and the acquisition time of each position data;
Wherein, the determining the commute feature data of the user according to the position data of the user and the collection time of each position data comprises:
determining a commute starting end point and a commute starting time according to the position data of the user and the acquisition time of each position data;
determining a commute starting and ending point as a path starting and ending point;
determining a plurality of planned paths according to the commute starting time and the path starting and ending points;
screening the commute path of the user from each planned path according to the position data of the user;
wherein the step of screening the commute path of the user from each planned path according to the position data of the user comprises the following steps:
gridding each planning path to obtain a candidate grid set corresponding to each planning path; the meshing processing refers to mapping path points included in the planned paths into grids in a map grid network, and is used for normalizing different planned paths; the candidate grid set is a set formed by grids obtained by gridding the planning path;
forming a real grid set according to the position data of the user; wherein the real grid set is a set formed by the grids obtained by mapping the position data into the map grid network;
And determining a candidate grid set matched with the real grid set in each candidate grid set, and determining a corresponding planning path as a commute path of the user.
2. The method of claim 1, wherein the commute feature data comprises at least one of: a commute start end point, a commute start time, and a commute path.
3. The method of claim 1, wherein the determining the user's commute feature data based on the user's location data and the time of acquisition of each of the location data comprises:
aggregating the position data of the user to form at least one position cluster;
counting the number of the position data belonging to a specified time period in each position cluster according to the acquisition time of the position data, wherein the specified time period comprises a working time period and/or a rest time period;
and obtaining the land type of each position cluster, and determining the commute starting and ending point of the user according to the statistical result of each position cluster.
4. The method of claim 1, wherein the determining the user's commute feature data based on the user's location data and the time of acquisition of each of the location data comprises:
Determining commute position data within a commute time period according to the acquisition time of the position data;
counting the space distance between each commute position data and the commute starting and ending point;
screening out at least one commute departure location data according to the spatial distance between each commute location data and the commute departure point;
and determining the commute starting time of the user according to the acquisition time of the commute departure position data.
5. The method of claim 1, wherein said determining, among the candidate grid sets, a candidate grid set that matches the real grid set comprises:
calculating the intersection of each candidate grid set and the real grid set;
calculating the ratio of the number of grids of each intersection to the number of grids of the candidate grid set of the intersection;
and determining a planning path corresponding to the candidate grid set with the largest ratio as the commute path of the user.
6. The method of claim 1, further comprising:
acquiring a commute user set in a road network;
and determining the commute pressure of each road in the road network according to the commute characteristic data of each user in the commute user set.
7. A commute feature data determining apparatus comprising:
the commute position data determining module is used for extracting the position data of the user from the position service data of the user and the acquisition time of each position data;
the commute feature data determining module is used for determining the commute feature data of the user according to the position data of the user and the acquisition time of each position data;
wherein the commute feature data determination module comprises:
a commute start end point and start time determining unit configured to determine a commute start end point and a commute start time according to the position data of the user and the acquisition time of each of the position data;
a path start and end point determining unit configured to determine a commute start and end point as a path start and end point;
a planned path determining unit configured to determine a plurality of planned paths according to the commute start time and the path start and end points;
the commute path determining unit is used for screening the commute path of the user from the planning paths according to the position data of the user;
wherein the commute path determination unit includes:
a candidate grid set determining subunit, configured to perform gridding processing on each planned path to obtain a candidate grid set corresponding to each planned path; the meshing processing refers to mapping path points included in the planned paths into grids in a map grid network, and is used for normalizing different planned paths; the candidate grid set is a set formed by grids obtained by gridding the planning path;
A real grid set determining subunit, configured to form a real grid set according to the location data of the user; wherein the real grid set is a set formed by the grids obtained by mapping the position data into the map grid network;
and the grid set matching subunit is used for determining a candidate grid set matched with the real grid set in each candidate grid set and determining a corresponding planning path as the commute path of the user.
8. The apparatus of claim 7, wherein the commute feature data comprises at least one of: a commute start end point, a commute start time, and a commute path.
9. The apparatus of claim 7, wherein the commute feature data determination module comprises:
a position aggregation unit, configured to aggregate position data of the user to form at least one position cluster;
the time-sharing statistics unit is used for counting the number of the position data belonging to a specified time period in the position cluster according to the acquisition time of the position data for each position cluster, wherein the specified time period comprises a working time period and a rest time period;
And the commuting starting and ending point determining unit is used for acquiring the land type of each position cluster and determining the commuting starting and ending point of the user according to the statistical result of each position cluster.
10. The apparatus of claim 7, wherein the commute feature data determination module comprises:
a commute position data determining unit for determining commute position data within a commute time period based on the acquisition time of the position data;
a start point distance determining unit for counting a spatial distance between each of the commute position data and a commute start point;
a start point position data determining unit, configured to screen out at least one commute start position data according to a spatial distance between each commute position data and the commute start end point;
the commute starting time determining unit is used for determining the commute starting time of the user according to the acquisition time of the commute starting position data.
11. The apparatus of claim 7, wherein the grid set matching subunit comprises:
an intersection calculating subunit, configured to calculate an intersection of each candidate grid set and the real grid set;
a grid number comparison subunit, configured to calculate a ratio of the number of grids of each intersection to the number of grids of the candidate grid set for calculating the intersection;
And the planning path screening subunit is used for determining the planning path corresponding to the candidate grid set with the largest ratio as the commute path of the user.
12. The apparatus of claim 7, further comprising:
the commute user set acquisition module is used for acquiring a commute user set in the road network;
and the road commute pressure determining module is used for determining the commute pressure of each road in the road network according to the commute characteristic data of each user in the commute user set.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the commute feature data determination method of any one of claims 1-6.
14. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the commute feature data determination method according to any one of claims 1-6.
CN202110501129.0A 2021-05-08 2021-05-08 Communication characteristic data determining method, device, electronic equipment and storage medium Active CN113190769B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110501129.0A CN113190769B (en) 2021-05-08 2021-05-08 Communication characteristic data determining method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110501129.0A CN113190769B (en) 2021-05-08 2021-05-08 Communication characteristic data determining method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113190769A CN113190769A (en) 2021-07-30
CN113190769B true CN113190769B (en) 2023-09-19

Family

ID=76984457

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110501129.0A Active CN113190769B (en) 2021-05-08 2021-05-08 Communication characteristic data determining method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113190769B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105674995A (en) * 2015-12-31 2016-06-15 百度在线网络技术（北京）有限公司 Method for acquiring commuting route based on user's travel locus, and apparatus thereof
CN105894358A (en) * 2016-03-31 2016-08-24 百度在线网络技术（北京）有限公司 Commuting order identification method and device
CN106403925A (en) * 2016-08-31 2017-02-15 河南理工大学 Space network construction and path planning method for indoor and underground space navigation
CN106931974A (en) * 2017-03-29 2017-07-07 清华大学 The method that personal Commuting Distance is calculated based on mobile terminal GPS location data record
WO2017133627A1 (en) * 2016-02-03 2017-08-10 中兴通讯股份有限公司 User commuter track management method, device and system
CN108848463A (en) * 2018-06-29 2018-11-20 百度在线网络技术（北京）有限公司 Commute route determination method and apparatus
CN111121796A (en) * 2018-10-30 2020-05-08 北京嘀嘀无限科技发展有限公司 Commuting route planning method and device and computer equipment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105466435B (en) * 2014-08-22 2020-07-10 中兴通讯股份有限公司 Route planning method and device of navigation system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105674995A (en) * 2015-12-31 2016-06-15 百度在线网络技术（北京）有限公司 Method for acquiring commuting route based on user's travel locus, and apparatus thereof
WO2017133627A1 (en) * 2016-02-03 2017-08-10 中兴通讯股份有限公司 User commuter track management method, device and system
CN107038168A (en) * 2016-02-03 2017-08-11 中兴通讯股份有限公司 A kind of user's commuting track management method, apparatus and system
CN105894358A (en) * 2016-03-31 2016-08-24 百度在线网络技术（北京）有限公司 Commuting order identification method and device
CN106403925A (en) * 2016-08-31 2017-02-15 河南理工大学 Space network construction and path planning method for indoor and underground space navigation
CN106931974A (en) * 2017-03-29 2017-07-07 清华大学 The method that personal Commuting Distance is calculated based on mobile terminal GPS location data record
CN108848463A (en) * 2018-06-29 2018-11-20 百度在线网络技术（北京）有限公司 Commute route determination method and apparatus
CN111121796A (en) * 2018-10-30 2020-05-08 北京嘀嘀无限科技发展有限公司 Commuting route planning method and device and computer equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Estimating Common Pedestrian Routes through Indoor Path Networks Using Position Traces;Thor S. Prentow 等;2014 IEEE 15th International Conference on Mobile Data Management;全文 *
基于互联网位置数据的通勤特征挖掘技术;阚长城;闫浩强;项雯怡;万涛;付凌峰;;城市交通(第05期);全文 *
规则网格数字高程模型中基于距离与坡度的路径规划算法;张润莲;张鑫;张楚芸;奚玉昂;;计算机应用(第11期);全文 *

Also Published As

Publication number Publication date
CN113190769A (en) 2021-07-30

Similar Documents

Publication Publication Date Title
Yuan et al. Driving with knowledge from the physical world
Zheng et al. Detecting collective anomalies from multiple spatio-temporal datasets across different domains
CN106971547B (en) A kind of Short-time Traffic Flow Forecasting Methods considering temporal correlation
CN108734955B (en) Method and device for predicting road condition state
Tang et al. A network Kernel Density Estimation for linear features in space–time analysis of big trace data
CN109360421B (en) Traffic information prediction method and device based on machine learning and electronic terminal
CN106931974A (en) The method that personal Commuting Distance is calculated based on mobile terminal GPS location data record
CN114428828A (en) Method and device for digging new road based on driving track and electronic equipment
CN118171035B (en) Method and device for early warning of people stream heating power, electronic equipment and storage medium
CN114758495A (en) Traffic signal lamp adjusting method and device and electronic equipment
CN114596709A (en) Data processing method, device, equipment and storage medium
CN113435403B (en) Road network missing road detection method, device, electronic equipment and storage medium
CN111159583A (en) User behavior analysis method, device, equipment and storage medium
CN116824868B (en) Method, device, equipment and medium for identifying illegal parking points and predicting congestion of vehicles
CN116703132B (en) Management method and device for dynamic scheduling of shared vehicles and computer equipment
CN111047107B (en) Road traffic time prediction method, device, electronic equipment and storage medium
CN113344277A (en) Prediction model training method, state updating method, device, equipment and medium
CN117351431A (en) Crowd gathering point identification method, device, equipment and storage medium
CN113190769B (en) Communication characteristic data determining method, device, electronic equipment and storage medium
CN111008730B (en) Crowd concentration prediction model construction method and device based on urban space structure
CN112966192A (en) Region address naming method and device, electronic equipment and readable storage medium
CN112541021B (en) Route evaluation method, scenic spot tour estimated time length calculation method and device
CN112836626B (en) Accident determining method and device, model training method and device and electronic equipment
CN115330067A (en) Traffic congestion prediction method and device, electronic equipment and storage medium
CN115206102A (en) Method, apparatus, electronic device, and medium for determining traffic path

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant