CN117098071A - Travel identification method, device, equipment and storage medium - Google Patents
Travel identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117098071A CN117098071A CN202311323438.9A CN202311323438A CN117098071A CN 117098071 A CN117098071 A CN 117098071A CN 202311323438 A CN202311323438 A CN 202311323438A CN 117098071 A CN117098071 A CN 117098071A
- Authority
- CN
- China
- Prior art keywords
- state
- data
- user
- point
- resident
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000011664 signaling Effects 0.000 claims description 77
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 abstract description 7
- 230000009466 transformation Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 16
- 230000007704 transition Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000002776 aggregation Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a travel identification method, a travel identification device, travel identification equipment and a travel identification storage medium, and belongs to the technical field of communication. The invention obtains the position service data of the user; carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user; extracting the resident points according to the state data to obtain target resident point data; and connecting the target residence point data to obtain a travel chain of the user so as to identify the user in travel, abstracting the track of the user into a state transformation relation through a preset state machine model, so that the states of the user are aggregated, a reliable travel chain of the user is extracted, and the applicability and the accuracy of the travel identification of the user are improved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a trip identification method, apparatus, device, and storage medium.
Background
At present, a travel rule mining, traffic state prediction and urban space-time trend evolution analysis can be realized by extracting a user travel chain so as to identify the user travel, a series of problems can be effectively relieved, and the method has important significance for service urban traffic planning and management.
The trip identification method aims at the problems of fixed scenes and large analysis granularity. The lack of system analysis for the travel segments of users between cities and regions focuses on the positioning judgment of the OD (starting) endpoints on both sides. The existing extraction technology for the travel sections between OD is mainly a simple data statistics method, has relatively poor applicability and is not accurate in identification.
Disclosure of Invention
The invention mainly aims to provide a travel identification method, a travel identification device, travel identification equipment and a storage medium, and aims to solve the technical problems that travel identification applicability is poor and the travel identification is not accurate enough in the prior art.
In order to achieve the above object, the present invention provides a travel identification method, which includes the following steps:
acquiring position service data of a user;
carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user;
extracting the resident points according to the state data to obtain target resident point data;
and connecting the target residence point data to obtain a travel chain of the user so as to identify the travel of the user.
Optionally, the abstracting the location service data through a preset state machine model to obtain state data of the user includes:
Obtaining an initial position point, a current time position point and a last time position point according to the position service data;
abstracting each position point in the position service data into a resident state, a pseudo-mobile state and a mobile state through a preset state machine model, and setting the state of an initial position point in the position service data into the resident state;
calculating the position distance between the current time position point and the last time position point;
comparing the position distance with a preset distance threshold value to obtain a comparison result;
and determining the state of the position point at the current moment according to the comparison result and the state of each position point to obtain the state data of the user in each time period.
Optionally, the determining the state of the location point at the current moment according to the comparison result and the state of each location point, to obtain the state data of the user in each time period includes:
acquiring the state of the position point at the previous moment according to the state of each position point;
when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the resident state;
when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the last moment is a pseudo-moving state, determining that the states at the last moment and the current moment are resident states;
And summarizing the state of the last moment and the state of the current moment to obtain the state data of the user in each time period.
Optionally, after the obtaining the state of the position point at the last moment according to the state of each position point, the method further includes:
when the comparison result shows that the position distance is larger than or equal to the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the moving state;
and when the comparison result shows that the position distance is larger than or equal to the preset distance threshold value and the state of the position point at the last moment is the pseudo-moving state, determining that the state at the last moment is the moving state and the state at the current moment is the pseudo-moving state.
Optionally, the extracting the dwell point according to the state data to obtain target dwell point data includes:
obtaining the resident state quantity and the duration data of the resident segments of the user based on the state data;
obtaining a time threshold of the user at the residence point according to the residence state quantity and the duration data;
obtaining a target time difference of the user residing at the same position according to the position service data;
Comparing the target time difference with the time threshold;
when the target time difference is smaller than the time threshold, setting the resident point as a short-time trip point, and eliminating the resident point from the position service data;
and clustering corresponding resident points when the target time difference is greater than or equal to the time threshold value to obtain target resident point data.
Optionally, the connecting the target residence point data to obtain a travel chain of the user so as to identify the travel of the user includes:
acquiring the starting time and the ending time of the target residence point data;
and connecting residence points in the target residence point data according to the starting time and the ending time in time sequence to obtain a travel chain of the user so as to identify the travel of the user.
Optionally, the acquiring the location service data of the user includes:
acquiring signaling data;
grouping the signaling data with hour granularity and day granularity to obtain grouped signaling data;
evaluating the number of the grouped signaling data, and eliminating the signaling data with the number of the signaling data smaller than a preset number threshold value to obtain target signaling data;
And taking initial data in the target signaling data as initial records of the tracks of the users, traversing the target signaling data, generating track data of a plurality of users, and obtaining the position service data of the users.
In addition, in order to achieve the above object, the present invention also provides a travel identification device, including:
the acquisition module is used for acquiring the position service data of the user;
the processing module is used for carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user;
the extraction module is used for extracting the resident points according to the state data to obtain target resident point data;
and the connection module is used for connecting the target residence point data to obtain a travel chain of the user.
In addition, to achieve the above object, the present invention also proposes a travel identification device including: the system comprises a memory, a processor and a travel identification program stored on the memory and capable of running on the processor, wherein the travel identification program is configured to realize the steps of the travel identification method.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a travel identification program which, when executed by a processor, implements the steps of the travel identification method as described above.
The invention obtains the position service data of the user; carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user; extracting the resident points according to the state data to obtain target resident point data; and connecting the target residence point data to obtain a travel chain of the user so as to identify the user in travel, abstracting the track of the user into a state transformation relation through a preset state machine model, so that the states of the user are aggregated, a reliable travel chain of the user is extracted, and the applicability and the accuracy of the travel identification of the user are improved.
Drawings
Fig. 1 is a schematic structural diagram of a trip identification device of a hardware running environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of the trip identification method of the present invention;
FIG. 3 is a flow chart of a second embodiment of the trip identification method of the present invention;
FIG. 4 is a schematic diagram illustrating a relationship between a preset state machine model and a state transition route according to an embodiment of the trip identification method of the present invention;
FIG. 5 is a flowchart of a third embodiment of the trip identification method of the present invention;
FIG. 6 is a flowchart of a travel identification method according to a fourth embodiment of the present invention;
FIG. 7 is a flowchart of a trip identification method according to a fifth embodiment of the present invention;
FIGS. 8 a-8 d are diagrams illustrating space-time trajectories of users according to an embodiment of the trip identification method of the present invention;
FIG. 9 is a schematic diagram of a trace before extraction of a travel chain of a user according to an embodiment of the travel identification method of the present invention;
FIG. 10 is a schematic diagram of a trace of a user after travel chain extraction according to an embodiment of the travel identification method of the present invention;
FIG. 11 is a flowchart of a travel identification method according to a sixth embodiment of the present invention;
FIG. 12 is a diagram illustrating acquiring signaling data according to an embodiment of the trip identification method of the present invention;
fig. 13 is a schematic diagram illustrating preprocessing of signaling data in an embodiment of the trip identification method of the present invention;
fig. 14 is a block diagram showing the construction of a first embodiment of the travel identification apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a trip identification device of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the trip identification apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the trip identification device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a travel identification program may be included in the memory 1005 as one type of storage medium.
In the trip identification device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the trip identification device of the present invention may be provided in the trip identification device, and the trip identification device invokes the trip identification program stored in the memory 1005 through the processor 1001 and executes the trip identification method provided by the embodiment of the present invention.
The embodiment of the invention provides a travel identification method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the travel identification method.
In this embodiment, the travel identification method includes the following steps:
step S10: and acquiring the position service data of the user.
It should be noted that, the execution body of the present embodiment may be a trip identification device, or may be other devices that may implement the same or similar functions, which is not limited in this embodiment, and the trip identification device is described as an example in this embodiment.
It should be noted that, the location service data of the user is LBS (Location Based Services, location-based service) data of the user, and the location service data of the user may be obtained by directly obtaining the location service data of the user, or by obtaining signaling data of the user and preprocessing the signaling data, which is not limited in this embodiment.
Step S20: and carrying out abstraction processing on the position service data through a preset state machine model to obtain state data of a user.
In a specific implementation, after the location service data of the user is obtained, the location service data can be subjected to related processing, so that trip data of the user and the like can be extracted, and the preset state machine model can be a model which is established in advance and is used for carrying out abstract processing on the location service data.
Therefore, before abstracting the location service data or before proceeding the trip identification, a preset state machine model may be established, where the preset state machine model is a wireless signaling data state machine SFSM (Signaling Finite State Machine) model, and the preset state machine model mainly includes the following 4 states: (1) as-is: refers to the current state. (2) condition: also referred to as an "event," when a condition is met, an action is triggered, or a state transition is performed. (3) action: and (5) executing actions after the conditions are met. After the action is executed, the method can be shifted to a new state or still maintain the original state. The action is not necessary, and when the condition is satisfied, the new state may be directly shifted to without executing any action. (4) inferior state: and a new state to which the condition is to be moved after being satisfied. "minor" is relative to "active" and, once activated, transitions to a new "active".
In this embodiment, the preset state machine model may be created by a state machine concept under the Spring framework, by modifying the pon file, adding Maven/gradle dependencies, thereby defining a state enumeration including two states with a distance smaller than a threshold and a distance greater than the threshold, defining event enumeration, and triggering state transitions by the occurrence of events including stay, pseudo-move and move, and configuring the state machine, and turning on the state machine functions by annotating. The configuration class typically inherits the EnumStateMachineConfigurationrAdapter class and rewrites some of the configuration methods to configure the initial state of the state machine and the association of events with state transitions, thereby building a preset state machine model.
In a specific implementation, the preset state machine model may abstract the location service data, so as to abstract the action state of the user into a plurality of states, thereby obtaining the state data of the user.
Step S30: and extracting the resident points according to the state data to obtain target resident point data.
In a specific implementation, after the state data is obtained, the state data can be subjected to state transition, so that the resident point is extracted from the state data to obtain the target resident point data.
Step S40: and connecting the target residence point data to obtain a travel chain of the user so as to identify the travel of the user.
After the target resident point data is obtained, all resident points in the target resident point data can be connected according to a certain connection rule, so that a complete travel chain of the user on the same day can be formed, and travel of the user can be identified through the travel chain of the user, for example, positions wanted by the user or areas passed by the user are identified.
The embodiment obtains the position service data of the user; carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user; extracting the resident points according to the state data to obtain target resident point data; and connecting the target residence point data to obtain a travel chain of the user so as to identify the user in travel, abstracting the track of the user into a state transformation relation through a preset state machine model, so that the states of the user are aggregated, a reliable travel chain of the user is extracted, and the applicability and the accuracy of the travel identification of the user are improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a trip identification method according to a second embodiment of the present invention.
Based on the above first embodiment, the step S20 of the trip identification method of this embodiment specifically includes:
step S201: and obtaining an initial position point, a current time position point and a last time position point according to the position service data.
It should be noted that, the obtained location service data of the user may be used as input data of a preset state machine model, and an initial location point of each user going out is defined as a "stay (S)" state, so that the location service data may be analyzed first to obtain an initial location point, a current location point at the moment, and a location point at the last moment.
The position point at the previous moment can be changed continuously according to the change of the position point at the current moment, and the position of the position point at the current moment is changed continuously according to the position of the user, so that the position point at the current moment and the position point at the previous moment can be obtained continuously, and a plurality of position point data can be obtained.
Step S202: abstracting each position point in the position service data into a resident state, a pseudo-mobile state and a mobile state through a preset state machine model, and setting the state of an initial position point in the position service data into the resident state.
FIG. 4 is a diagram showing the relationship between a preset state machine model and a state transition path by setting a transition function in advance And determining the state of each-day position point data record through threshold judgment of a transfer function, and after the state is determined, forming resident segments through aggregation of resident points, and finally connecting all the resident segments to form a complete travel chain of a user, wherein in fig. 4, S is a resident state, T is a pseudo-mobile state, and M is a mobile state. Based on the preset state machine model, defining the distance between adjacent points as a conversion functionAnd sets the distance conversion threshold to +.>The time conversion threshold is +.>And satisfies the following formula 1:
(1)
In formula 1, whereinTotal number of records for location services->For the space-time distance function between the position service data record and the initial point, the travel chain extraction is mainly divided into three steps of track point state identification, resident point aggregation and travel chain connection according to the state transition route of fig. 4.
Step S203: and calculating the position distance between the current time position point and the last time position point.
It should be appreciated that the location distance between the current time location point and the last time location point may be calculated by traversing all location points in the location services data。
Step S204: and comparing the position distance with a preset distance threshold value to obtain a comparison result.
It should be understood that the preset distance threshold may be set in advance, for example, 3m, 5m, etc., and the comparison result may be obtained by comparing the position distance with the preset distance threshold. The comparison result may be that the position distance is greater than a preset distance threshold, the position distance is less than a preset distance threshold, and the position distance is equal to the preset distance threshold.
Step S205: and determining the state of the position point at the current moment according to the comparison result and the state of each position point to obtain the state data of the user in each time period.
In a specific implementation, different comparison results and states of the location points can represent different states of the location points at the current moment, for example, the location distance is greater than or equal to a preset distance threshold, the states of the location points at the current moment are defined to be moving states, and the like, so that the states of the location points at the current moment can be determined according to the different comparison results and the states of the location points, and state data of a user in each time period can be obtained, wherein the state data can comprise a moving state, a resident state and a pseudo-moving state. The pseudo-movement state is that only the resident position is shifted, but the actual user does not substantially move.
According to the embodiment, an initial position point, a current moment position point and a last moment position point are obtained according to the position service data; abstracting each position point in the position service data into a resident state, a pseudo-mobile state and a mobile state through a preset state machine model, and setting the state of an initial position point in the position service data into the resident state; calculating the position distance between the current time position point and the last time position point; comparing the position distance with a preset distance threshold value to obtain a comparison result; and determining the state of the position point at the current moment according to the comparison result and the state of each position point to obtain the state data of the user in each time period, so that different positions of the user in different time periods are abstracted into specific states, the change condition of the user is recognized more rapidly, and the efficiency and accuracy of extracting the travel chain of the user are improved.
Referring to fig. 5, fig. 5 is a flowchart of a third embodiment of the trip identification method of the present invention.
Based on the first and second embodiments, the trip identification method of this embodiment specifically includes the following step S205:
step S2051: and acquiring the state of the position point at the last moment according to the state of each position point.
It should be noted that, for example, when the current time is t2, the state of the t1 position point at the previous time may be obtained, for example, when the t1 position point at the previous time is the initial position point, the state of the position point at the previous time is the stay state, and the state of the position point at the next time may be obtained continuously according to the state of the initial position point, so as to continuously obtain the state of the position point at the current time.
In a specific implementation, after the state of the position point at the previous moment is obtained, a comparison result, for example, the state of the position point at the previous moment is the state of the initial position point, namely the stay state, and when the comparison result is that the position distance is greater than or equal to the preset distance threshold value, the position is proved to be possibly changed greatly at the moment, so that the state at the current moment can be further confirmed according to the state of the position point at the previous moment, and when the state of the position point at the previous moment is the stay state, the state at the current moment is determined to be the moving state;
It should be understood that if the position distance is equal to or greater than the preset distance threshold, it is proved that the position may be changed greatly at this time, so that the state at the current time can be further confirmed according to the state of the position point at the previous time, and when the state of the position point at the previous time is "stay (S)", the state at the current time is determined to be "moving (M)", that is, a moving state.
In a specific implementation, the state at the previous moment may be a pseudo-moving state, so when the comparison result is that the position distance is greater than or equal to the preset distance threshold, and the state of the position point at the previous moment is the pseudo-moving state, the state at the previous moment is determined to be the moving state, and the state at the current moment is the pseudo-moving state.
If the position distance is equal to or greater than the preset distance threshold, and the state of the position point at the previous time is the "pseudo-moving state (T)", it is determined that the state at the previous time is the "moving (M)" state, and the state at the current time is the "pseudo-moving (T)" state.
Step S2052: and when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the resident state.
It should be understood that if the comparison result is that the position distance is smaller than the preset distance threshold, it is proved that the position point at the previous time may not be significantly changed from the position point at the current time, further judgment needs to be performed in combination with the state of the position point at the previous time, and if the state of the position point at the previous time is the stay state, it can be determined that the current time is not moved, so that the state at the current time is the stay (S) state.
Step S2053: and when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the last moment is a pseudo-moving state, determining that the states at the last moment and the current moment are resident states.
If the comparison result shows that the position distance is smaller than the preset distance threshold, it is proved that the position point at the previous time may not be significantly changed from the position point at the current time, and when the state of the position point at the previous time is further confirmed to be in the pseudo-moving state, it is determined that the states at the previous time and the current time are both in the "stay (S)" state, and only the stay position is shifted.
Step S2054: and summarizing the state of the last moment and the state of the current moment to obtain the state data of the user in each time period.
The above steps S2051 to S2053 may be repeated continuously to obtain the state at the previous time and the state at the current time, so that all the states are collected to obtain the state data of the user in each time period.
According to the embodiment, the state of the position point at the last moment is obtained according to the state of each position point; when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the resident state; when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the last moment is a pseudo-moving state, determining that the states at the last moment and the current moment are resident states; and summarizing the state of the last moment and the state of the current moment to obtain state data of a user in each time period, thereby rapidly determining whether the current moment moves or not through the distance between the position point of the last moment and the position point of the current moment, further accurately determining the state of the position point of the current moment according to the state of the position point of the last moment, and further obtaining the states of all the position points, and facilitating the follow-up extraction of a travel chain.
Referring to fig. 6, fig. 6 is a flowchart of a travel identification method according to a fourth embodiment of the present invention.
Based on the above first embodiment, the step S30 of the trip identification method of this embodiment specifically includes:
step S301: and obtaining the resident state quantity and the duration data of the resident segments of the user based on the state data.
It should be noted that, all residence states in the state data may be determined according to the state data, and the number of residence states and the duration data of the user residence segment may be counted, where the duration data of the user residence segment may be the sum of durations of the user residence segment. The residence time of the user at the position point corresponding to each residence state can be counted to obtain the time sum.
Step S302: and obtaining the time threshold value of the user at the residence point according to the residence state quantity and the duration data.
It can be understood that, after obtaining the number of residence states and the long data, the time threshold of the user at the residence point can be calculated, and the following formula 2 is specifically calculated:
(2)
In the above-mentioned formula 2,for the time threshold of the user at the dwell point, < ->For the number of resident states>Duration data for the user resident segment.
Step S303: and obtaining the target time difference of the user residing in the same position according to the position service data.
It should be noted that, the maximum time difference of the users residing in the same location may be calculated according to the location service data, the target time difference is the maximum time difference, for example, the time difference of a plurality of users continuously residing in the same location may be counted, and the time difference may be filtered to obtain the maximum time difference。
Step S304: the target time difference is compared to the time threshold.
In an implementation, the maximum time difference can be obtained byAnd time threshold->A comparison is made so that it can be determined whether the corresponding dwell point is available or not based on the comparison result.
Step S305: and when the target time difference is smaller than the time threshold, setting the resident point as a short-time trip point, and eliminating the resident point from the position service data.
It will be appreciated that if the target time differenceLess than a time threshold->And judging the corresponding resident point as a short-time trip point, and eliminating the resident point from the position service data.
Step S306: and clustering corresponding resident points when the target time difference is greater than or equal to the time threshold value to obtain target resident point data.
When the target time difference isGreater than or equal to the time threshold->If the corresponding dwell point is determined to be the useful dwell point, the target time difference can be set to +. >Greater than or equal to the time threshold->And carrying out cluster analysis on all corresponding resident points, so as to obtain all resident point data meeting the requirements, namely target resident point data.
The embodiment obtains the resident state quantity and the duration data of the resident segments of the user based on the state data; obtaining a time threshold of the user at the residence point according to the residence state quantity and the duration data; obtaining a target time difference of the user residing at the same position according to the position service data; comparing the target time difference with the time threshold; when the target time difference is smaller than the time threshold, setting the resident point as a short-time trip point, and eliminating the resident point from the position service data; when the target time difference is greater than or equal to the time threshold, clustering corresponding resident points to obtain target resident point data, and extracting resident points which can form a travel chain of the user from all the position service data, so that the travel chain of the user can be extracted conveniently and rapidly.
Referring to fig. 7, fig. 7 is a flowchart of a trip identification method according to a fifth embodiment of the present invention.
Based on the above-mentioned first embodiment, the step S40 of the trip identification method of this embodiment specifically includes:
Step S401: and acquiring the starting time and the ending time of the target residence point data.
After the target resident point data are clustered, the starting time in the target resident point data is the arrival time of the last trip, and the ending time is the departure time of the trip, so that the starting time and the ending time of the target resident point data can be obtained.
Step S402: and connecting residence points in the target residence point data according to the starting time and the ending time in time sequence to obtain a travel chain of the user so as to identify the travel of the user.
Through connecting the resident points in the target resident point data according to the time sequence, a complete trip chain of the user on the same day is formed, and the user trip is conveniently identified or corresponding service is provided.
Based on the travel chain extraction, in this embodiment, the User can work in the new area of the south Beijing city in daytime and live in the Jiang Ning area of the south Beijing city in evening by counting the authorized position data of the User. Firstly, the acquired signaling data of the user is preprocessed, and the processed signaling is analyzed according to a space-time function, as shown in fig. 8 a-8 d, and fig. 8 a-8 d are space-time trace diagrams of the user, as shown in fig. 8 a. The commute range of the user 25km can be seen from the figure. According to the SFSM state machine model, we traverse the user' S location service data, where M mobile states total 110 records and S resident states total 252 resident records. As shown in table 1 below, table 1 is a status table of users. On the basis, time aggregation is carried out according to a time threshold value, and 36 effective travel chains are obtained in total. Fig. 8b shows the state of the output of the preset state machine model, and it can be seen from the figure that the resident state of the user is hidden in the "scrambled" location service data, and the change condition of the data can be identified by the transfer function of the state machine, so as to map to the state of the user. The mobile state, the park state, is shown in fig. 8 c. In fig. 8d, the time threshold is considered for the travel chain after aggregation, and the curve at this time is more similar to the "noise removal" and filtering of the original data.
TABLE 1
As shown in fig. 9 and 10, fig. 9 is a schematic diagram of a track before the extraction of the travel chain of the user, and fig. 10 is a schematic diagram of a track after the extraction of the travel chain of the user, before the track of the position data of the user extracts the travel chain, the random clutter phenomenon is serious, and the identification and track judgment of the travel mode of the user can be greatly affected. And the track of the extracted travel chain reflects the activity route of the user more clearly and is segmented and partitioned. From the aspect of matching readiness, the travel chain of the user almost completely coincides with the actual track.
The embodiment obtains the starting time and the ending time of the target residence point data; and connecting residence points in the target residence point data according to the starting time and the ending time in time sequence to obtain a travel chain of the user so as to identify the travel of the user and improve the reliability of extraction of the travel chain of the user.
Referring to fig. 11, fig. 11 is a flowchart of a travel identification method according to a sixth embodiment of the present invention.
Based on the above first embodiment, the step S10 of the trip identification method of this embodiment specifically includes:
step S101: signaling data is acquired.
It should be noted that the signaling data may be mobile phone signaling data, computer signaling data, etc., and may also include wireless signaling data of other scenes, which is not limited in this embodiment. For example, the signaling data is mobile phone signaling data, as shown in fig. 12, and fig. 12 is a schematic diagram of acquiring signaling data, where a total amount of MME (Mobility Management Entity ) signaling s= { msisdn, cell, begin_time, end_time, & gt, is first acquired and matched with analysis area engineering parameter data G to acquire cell longitude and latitude information. In the actual production process, the signaling big data calculation frame is built based on Hadoop/Spark and other technologies, and the acquisition of the signaling needs to interact with Kafka and other message queue components. The core network device, such as MME producer, sends the raw data directly to the brooker as partition leader. As a consumer of Kafka, the way to acquire signaling works is to issue an "acquire" request to the partition's brooker.
Step S102: and grouping the signaling data with the hour granularity and the day granularity to obtain grouped signaling data.
In the process of generating the mobile phone signaling data, due to the influence of various factors such as a base station, environment, electromagnetic interference and the like, a small amount of invalid data, table tennis data, drift data and other abnormal data can be generated, so that a necessary data cleaning step is needed.
Therefore, the signaling data can be preprocessed, and the method specifically comprises the steps of grouping the signaling data with the hour granularity and the day granularity, wherein the grouping with the hour granularity can be polymerized and de-duplicated according to different base stations, filtering out the abnormal data with part empty, and labeling the data (longitude and latitude, user attribution city province, grid where the user is located and the like). The day granularity packets may be grouped according to different users, thereby obtaining groups of grouped signaling data.
Step S103: and evaluating the number of the grouped signaling data, and eliminating the signaling data with the number of the signaling data smaller than a preset number threshold value to obtain target signaling data.
In specific implementation, the data which does not meet the number requirements can be removed by setting a screening rule, so that the number of the grouped signaling data can be evaluated, the preset number threshold value can be 2, the data with the number of the data in the group being smaller than 2 can be removed for other number values, and the target signaling data is obtained, and the number of the target signaling data is the data which meets the number requirements.
Step S104: and taking initial data in the target signaling data as initial records of the tracks of the users, traversing the target signaling data, generating track data of a plurality of users, and obtaining the position service data of the users.
In a specific implementation, the first data in each group can be used as the initial record of the user track by sorting the target signaling data according to the time sequence, all the data in the target signaling data are traversed and compared with the initial record of the track, and if the data are changed with the base station record of the previous data, a user track record (starting point i and end point j) is generated; if the data is the same as the base station record of the previous data, continuing to judge the time difference, and if the time difference exceeds a set time threshold, generating one piece of track data (a starting point i and an ending point j), so as to obtain track data of a plurality of users until all the data are compared, and taking all the track data of the users as the position service data of the users.
As shown in fig. 13, fig. 13 is a schematic diagram of preprocessing signaling data, by acquiring MME signaling data, aggregating, de-duplicating, filtering anomalies, labeling the data by hour granularity and day granularity, grouping, discarding the data less than 2, sorting target signaling data, traversing the target signaling data, and comparing with the initial trace records respectively. If the base station record of the data and the previous data is changed, a user track record is generated, so that a plurality of pieces of user track data are obtained, and user LBS data are output.
The embodiment obtains signaling data; grouping the signaling data with hour granularity and day granularity to obtain grouped signaling data; evaluating the number of the grouped signaling data, and eliminating the signaling data with the number of the signaling data smaller than a preset number threshold value to obtain target signaling data; and taking initial data in the target signaling data as initial records of the tracks of the users, traversing the target signaling data, generating track data of a plurality of users, obtaining position service data of the users, realizing more refined granularity extraction, and improving the accuracy of the data.
Referring to fig. 14, fig. 14 is a block diagram showing the construction of a first embodiment of the travel identification apparatus according to the present invention.
As shown in fig. 14, the trip identification device provided by the embodiment of the present invention includes:
an acquisition module 10, configured to acquire location service data of a user.
And the processing module 20 is configured to abstract the location service data through a preset state machine model to obtain state data of the user.
And the extracting module 30 is used for extracting the resident points according to the state data to obtain target resident point data.
And the connection module 40 is used for connecting the target residence point data to obtain a travel chain of the user.
The embodiment obtains the position service data of the user; carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user; extracting the resident points according to the state data to obtain target resident point data; and connecting the target residence point data to obtain a travel chain of the user so as to identify the user in travel, abstracting the track of the user into a state transformation relation through a preset state machine model, so that the states of the user are aggregated, a reliable travel chain of the user is extracted, and the applicability and the accuracy of the travel identification of the user are improved.
In an embodiment, the processing module 20 is further configured to obtain an initial location point, a current location point and a last location point according to the location service data; abstracting each position point in the position service data into a resident state, a pseudo-mobile state and a mobile state through a preset state machine model, and setting the state of an initial position point in the position service data into the resident state; calculating the position distance between the current time position point and the last time position point; comparing the position distance with a preset distance threshold value to obtain a comparison result; and determining the state of the position point at the current moment according to the comparison result and the state of each position point to obtain the state data of the user in each time period.
In an embodiment, the processing module 20 is further configured to obtain a state of the location point at the previous time according to the state of each location point; when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the resident state; when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the last moment is a pseudo-moving state, determining that the states at the last moment and the current moment are resident states; and summarizing the state of the last moment and the state of the current moment to obtain the state data of the user in each time period.
In an embodiment, the processing module 20 is further configured to determine that the state at the current time is a moving state when the comparison result indicates that the location distance is greater than or equal to the preset distance threshold and the state of the location point at the previous time is a resident state; and when the comparison result shows that the position distance is larger than or equal to the preset distance threshold value and the state of the position point at the last moment is the pseudo-moving state, determining that the state at the last moment is the moving state and the state at the current moment is the pseudo-moving state.
In an embodiment, the extracting module 30 is further configured to obtain the number of residence states and duration data of the user residence segment based on the state data; obtaining a time threshold of the user at the residence point according to the residence state quantity and the duration data; obtaining a target time difference of the user residing at the same position according to the position service data; comparing the target time difference with the time threshold; when the target time difference is smaller than the time threshold, setting the resident point as a short-time trip point, and eliminating the resident point from the position service data; and clustering corresponding resident points when the target time difference is greater than or equal to the time threshold value to obtain target resident point data.
In an embodiment, the connection module 40 is further configured to obtain a start time and an end time of the target residence point data; and connecting residence points in the target residence point data according to the starting time and the ending time in time sequence to obtain a travel chain of the user so as to identify the travel of the user.
In an embodiment, the obtaining module 10 is further configured to obtain signaling data; grouping the signaling data with hour granularity and day granularity to obtain grouped signaling data; evaluating the number of the grouped signaling data, and eliminating the signaling data with the number of the signaling data smaller than a preset number threshold value to obtain target signaling data; and taking initial data in the target signaling data as initial records of the tracks of the users, traversing the target signaling data, generating track data of a plurality of users, and obtaining the position service data of the users.
In addition, to achieve the above object, the present invention also proposes a travel identification device including: the system comprises a memory, a processor and a travel identification program stored on the memory and capable of running on the processor, wherein the travel identification program is configured to realize the steps of the travel identification method.
The travel identification device adopts all the technical schemes of all the embodiments, so that the travel identification device has at least all the beneficial effects brought by the technical schemes of the embodiments, and is not described in detail herein.
In addition, the embodiment of the invention also provides a storage medium, wherein a travel identification program is stored on the storage medium, and the travel identification program realizes the steps of the travel identification method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the trip identification method provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The travel identification method is characterized by comprising the following steps of:
Acquiring position service data of a user;
carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user;
extracting the resident points according to the state data to obtain target resident point data;
and connecting the target residence point data to obtain a travel chain of the user so as to identify the travel of the user.
2. The trip identification method of claim 1, wherein the abstracting the location service data through a preset state machine model to obtain the state data of the user comprises:
obtaining an initial position point, a current time position point and a last time position point according to the position service data;
abstracting each position point in the position service data into a resident state, a pseudo-mobile state and a mobile state through a preset state machine model, and setting the state of an initial position point in the position service data into the resident state;
calculating the position distance between the current time position point and the last time position point;
comparing the position distance with a preset distance threshold value to obtain a comparison result;
and determining the state of the position point at the current moment according to the comparison result and the state of each position point to obtain the state data of the user in each time period.
3. The trip identification method of claim 2, wherein the determining the state of the current time location point according to the comparison result and the state of each location point to obtain the state data of the user in each time period comprises:
acquiring the state of the position point at the previous moment according to the state of each position point;
when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the resident state;
when the comparison result shows that the position distance is smaller than the preset distance threshold value and the state of the position point at the last moment is a pseudo-moving state, determining that the states at the last moment and the current moment are resident states;
and summarizing the state of the last moment and the state of the current moment to obtain the state data of the user in each time period.
4. The trip identification method of claim 3, wherein after the state of the last time location point is obtained according to the state of each location point, further comprising:
when the comparison result shows that the position distance is larger than or equal to the preset distance threshold value and the state of the position point at the previous moment is the resident state, determining that the state at the current moment is the moving state;
And when the comparison result shows that the position distance is larger than or equal to the preset distance threshold value and the state of the position point at the last moment is the pseudo-moving state, determining that the state at the last moment is the moving state and the state at the current moment is the pseudo-moving state.
5. The trip identification method of claim 1, wherein the extracting the stay point according to the state data to obtain the target stay point data comprises:
obtaining the resident state quantity and the duration data of the resident segments of the user based on the state data;
obtaining a time threshold of the user at the residence point according to the residence state quantity and the duration data;
obtaining a target time difference of the user residing at the same position according to the position service data;
comparing the target time difference with the time threshold;
when the target time difference is smaller than the time threshold, setting the resident point as a short-time trip point, and eliminating the resident point from the position service data;
and clustering corresponding resident points when the target time difference is greater than or equal to the time threshold value to obtain target resident point data.
6. The trip identification method of claim 1, wherein the step of connecting the target residence data to obtain a trip chain of the user to perform trip identification on the user comprises the steps of:
Acquiring the starting time and the ending time of the target residence point data;
and connecting residence points in the target residence point data according to the starting time and the ending time in time sequence to obtain a travel chain of the user so as to identify the travel of the user.
7. The trip identification method of any one of claims 1 to 6, wherein the acquiring location service data of the user includes:
acquiring signaling data;
grouping the signaling data with hour granularity and day granularity to obtain grouped signaling data;
evaluating the number of the grouped signaling data, and eliminating the signaling data with the number of the signaling data smaller than a preset number threshold value to obtain target signaling data;
and taking initial data in the target signaling data as initial records of the tracks of the users, traversing the target signaling data, generating track data of a plurality of users, and obtaining the position service data of the users.
8. A travel identification device, characterized in that the travel identification device comprises:
the acquisition module is used for acquiring the position service data of the user;
the processing module is used for carrying out abstract processing on the position service data through a preset state machine model to obtain state data of a user;
The extraction module is used for extracting the resident points according to the state data to obtain target resident point data;
and the connection module is used for connecting the target residence point data to obtain a travel chain of the user.
9. A travel identification device, characterized in that the travel identification device comprises: a memory, a processor, and a travel identification program stored on the memory and executable on the processor, the travel identification program configured to implement the travel identification method of any one of claims 1 to 7.
10. A storage medium, wherein a travel identification program is stored on the storage medium, which when executed by a processor implements the travel identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311323438.9A CN117098071A (en) | 2023-10-13 | 2023-10-13 | Travel identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311323438.9A CN117098071A (en) | 2023-10-13 | 2023-10-13 | Travel identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117098071A true CN117098071A (en) | 2023-11-21 |
Family
ID=88775662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311323438.9A Pending CN117098071A (en) | 2023-10-13 | 2023-10-13 | Travel identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117098071A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582948A (en) * | 2020-05-25 | 2020-08-25 | 北京航空航天大学 | Individual behavior analysis method based on mobile phone signaling data and POI (Point of interest) |
| CN112822639A (en) * | 2020-12-18 | 2021-05-18 | 河北师范大学 | Method for demarcating airport abdominal area of passengers entering and exiting port based on mobile phone signaling |
| CN115643528A (en) * | 2022-10-24 | 2023-01-24 | 东南大学 | Mobile phone signaling data-based traveler activity-trip chain reconstruction method |
-
2023
- 2023-10-13 CN CN202311323438.9A patent/CN117098071A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582948A (en) * | 2020-05-25 | 2020-08-25 | 北京航空航天大学 | Individual behavior analysis method based on mobile phone signaling data and POI (Point of interest) |
| CN112822639A (en) * | 2020-12-18 | 2021-05-18 | 河北师范大学 | Method for demarcating airport abdominal area of passengers entering and exiting port based on mobile phone signaling |
| CN115643528A (en) * | 2022-10-24 | 2023-01-24 | 东南大学 | Mobile phone signaling data-based traveler activity-trip chain reconstruction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107547633B (en) | User constant standing point processing method and device and storage medium | |
| Qiao et al. | A mobility analytical framework for big mobile data in densely populated area | |
| Xu et al. | Understanding mobile traffic patterns of large scale cellular towers in urban environment | |
| WO2017133627A1 (en) | User commuter track management method, device and system | |
| CN103116696B (en) | Personnel based on the mobile phone location data of sparse sampling reside place recognition methods | |
| Gidófalvi et al. | When and where next: Individual mobility prediction | |
| Asgari et al. | A survey on human mobility and its applications | |
| Fiadino et al. | Steps towards the extraction of vehicular mobility patterns from 3G signaling data | |
| CN111209261A (en) | User travel track extraction method and system based on signaling big data | |
| CN111212383B (en) | Method, device, server and medium for determining number of regional permanent population | |
| CN112543419B (en) | User trajectory prediction method and device based on density clustering | |
| CN104462193A (en) | Vehicle movement trajectory searching system and method based on time-space matching | |
| CN109885636B (en) | User portrait drawing method and server | |
| CN110933662B (en) | Space-time adjoint relation analysis method and system based on data mining | |
| CN109634998A (en) | A kind of traffic journey characteristic analysis platform based on mobile phone signaling big data | |
| Yao et al. | Understanding human activity and urban mobility patterns from massive cellphone data: Platform design and applications | |
| CN112770265A (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
| CN113111271A (en) | Travel OD data sample expansion method and device, computer equipment and storage medium | |
| CN112364907A (en) | Method, system, server and storage medium for general investigation of frequent station of user to be tested | |
| Li et al. | Mobile user location prediction based on user classification and markov model | |
| Chen et al. | A travel mode identification framework based on cellular signaling data | |
| CN106201841A (en) | The statistical method of a kind of application program service data and device | |
| Klimek et al. | Towards a better understanding and behavior recognition of inhabitants in smart cities. A public transport case | |
| CN117098071A (en) | Travel identification method, device, equipment and storage medium | |
| CN104778355A (en) | Trajectory outlier detection method based on wide-area distributed traffic system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20231121 |