CN108875032B - Region type determination method and device - Google Patents

Region type determination method and device Download PDF

Info

Publication number
CN108875032B
CN108875032B CN201810661463.0A CN201810661463A CN108875032B CN 108875032 B CN108875032 B CN 108875032B CN 201810661463 A CN201810661463 A CN 201810661463A CN 108875032 B CN108875032 B CN 108875032B
Authority
CN
China
Prior art keywords
city
partition
user
urban
base station
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
CN201810661463.0A
Other languages
Chinese (zh)
Other versions
CN108875032A (en
Inventor
杨子清
刘燕驰
李梓赫
周熠晨
谭昶
昌玮
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.)
Iflytek Information Technology Co Ltd
Original Assignee
Iflytek Information 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 Iflytek Information Technology Co Ltd filed Critical Iflytek Information Technology Co Ltd
Priority to CN201810661463.0A priority Critical patent/CN108875032B/en
Publication of CN108875032A publication Critical patent/CN108875032A/en
Application granted granted Critical
Publication of CN108875032B publication Critical patent/CN108875032B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Navigation (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The embodiment of the invention provides a method and a device for determining a region type, and belongs to the technical field of computer application. The method comprises the following steps: acquiring a departure matrix and an arrival matrix corresponding to each city partition; and inputting the specified parameters into a preset model, and determining a preset type corresponding to each city partition based on an output result of the preset model. According to the embodiment of the invention, the starting matrix and the arrival matrix corresponding to each city partition are obtained, the designated parameters are input into the preset model, and the preset type corresponding to each city partition is determined based on the output result of the preset model. The area type corresponding to the city subarea can be automatically determined based on the movement data of the user among different city subareas, so that the determination result is more accurate. In addition, because the time dimension is introduced when the area type corresponding to the urban subarea is determined, namely the area type corresponding to the urban subarea in different time periods can be determined for the same urban subarea, and the method is more suitable for practical application scenes.

Description

Region type determination method and device
Technical Field
The embodiment of the invention relates to the technical field of computer application, in particular to a method and a device for determining a region type.
Background
In recent years, cities have become larger and larger, and in some application scenarios, the types of different partitions in urban areas need to be determined. For example, urban areas are divided by function, and the area types may include residential areas, business areas, industrial areas, and the like. In the related art, when determining the area type of the urban subarea, the interest points in each urban subarea, such as stores, schools, companies, etc., are usually determined, and then the area type of each urban subarea is determined manually according to the interest points in each urban subarea. Because the determination is performed manually, the determination result is not accurate enough.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method and an apparatus for determining a region type, which overcome the above problems or at least partially solve the above problems.
According to a first aspect of the embodiments of the present invention, there is provided a region type determining method, including:
the method comprises the steps of inputting specified parameters into a preset model by obtaining a departure matrix and an arrival matrix corresponding to each city partition, and determining a preset type corresponding to each city partition based on an output result of the preset model. The area type corresponding to the city subarea can be automatically determined based on the movement data of the user among different city subareas, so that the determination result is more accurate. In addition, because the time dimension is introduced when the area type corresponding to the urban subarea is determined, namely the area type corresponding to the urban subarea in different time periods can be determined for the same urban subarea, and the method is more suitable for practical application scenes.
According to the method provided by the embodiment of the invention, the starting matrix and the arrival matrix corresponding to each city partition are obtained, the designated parameters are input into the preset model, and the preset type corresponding to each city partition is determined based on the output result of the preset model. The area type corresponding to the city subarea can be automatically determined based on the movement data of the user among different city subareas, so that the determination result is more accurate. In addition, because the time dimension is introduced when the area type corresponding to the urban subarea is determined, namely the area type corresponding to the urban subarea in different time periods can be determined for the same urban subarea, and the method is more suitable for practical application scenes.
According to a second aspect of embodiments of the present invention, there is provided an area type determination apparatus, including:
the acquisition module is used for acquiring a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to any urban subarea comprises the moving frequency of all users moving from any urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to any urban subarea comprises the moving frequency of all users moving from each other urban subarea to any urban subarea in the preset time period, and other urban subareas are urban subareas except any urban subarea in the urban area;
the first determining module is used for inputting the specified parameters into the preset model and determining the preset type corresponding to each city partition based on the output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the region type determination method provided by any of the various possible implementations of the first aspect.
According to a fourth aspect of the present invention, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for region type determination provided by any one of the various possible implementations of the first aspect.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of embodiments of the invention.
Drawings
Fig. 1 is a schematic flowchart of a method for determining a region type according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for determining a region type according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of the invention for covering a Thiessen polygon in a city partition;
fig. 4 is a flowchart illustrating a method for determining a region type according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a trip sequence according to an embodiment of the present invention;
fig. 6 is a flowchart illustrating a method for determining a region type according to an embodiment of the present invention;
fig. 7 is a block diagram of an area type determination apparatus according to an embodiment of the present invention;
fig. 8 is a block diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the drawings and examples. The following examples are intended to illustrate the examples of the present invention, but are not intended to limit the scope of the examples of the present invention.
In recent years, with the increasing urban scale, urban problems, such as traffic jam and air pollution, become more and more obvious. Therefore, a solution for solving the above problems needs to be constructed from the perspective of large data mining and analysis. For different urban partitions in an urban area, determining the area type of the urban partition has important significance for constructing a scheme for solving the problems. When determining the area type of the urban subarea, the area type of each urban subarea is generally determined according to the angle of the functional area, such as a residential area, a business area, an industrial area, and the like. In the related art, when determining the area type of the urban subarea, the interest points in each urban subarea, such as stores, schools, companies, etc., are usually determined, and then the area type of each urban subarea is determined manually according to the interest points in each urban subarea. Because the determination is performed manually, the determination result is not accurate enough. In addition, after the area type of the urban subarea is determined manually, the area type of each urban subarea is not changed basically, but the functions carried by the urban subareas may change along with the change of time, such as the change along with the advance of urban construction or the change along with the movement of people stream, so that the area type determined manually cannot reflect the change of the area type in the time dimension.
In view of the above situation, an embodiment of the present invention provides a method for determining a region type. The method is suitable for the division scene of any city functional area to determine the area types of different city subareas in the angle of the functional area. The execution subject of the method may be a preset processing device, such as a server or a terminal, which is not specifically limited in this embodiment of the present invention. Specifically, the method comprises the following steps:
101. and acquiring a departure matrix and an arrival matrix corresponding to each city partition.
Prior to execution 101, an urban area may be partitioned into a plurality of urban partitions. Specifically, the urban area may be divided into a plurality of urban partitions according to the road network data, which is not specifically limited in the embodiment of the present invention. In 101, for any city partition within a city block, the departure matrix corresponding to the city partition may have two dimensions of rows and columns. The rows of the departure matrix may refer to other city partitions to which the user moves after departing from the city partition, and the columns of the departure matrix may refer to different preset time periods. The departure matrix may include a moving frequency of all users moving from the city partition to each of the other city partitions within a preset time period, and each element in the departure matrix represents a moving frequency of all users moving from the city partition to each of the other city partitions within a certain preset time period, which is not specifically limited in the embodiment of the present invention. Wherein, the other city subareas refer to city subareas except the city subarea in the city area.
For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. For city partition a, a corresponds to 3 rows of departure matrix, that is, city partition B, C and D, respectively. The number of columns of the departure matrix corresponding to a is 3, that is, the departure matrix corresponds to the three different time periods. For the element in the 1 st row and 1 st column in the departure matrix, the element indicates the frequency of movement of all users from a to B starting at 8 am to 9 am.
It should be noted that, in an actual implementation process, for convenience of subsequent statistics, the preset time period may also be normalized to an integer time point in units of hours. For example, for any user, if the user moves from point a to point B at 8 am 40 (i.e., within 8 am to 9 am), the time of the user from point a may be regulated to 8 am or to 9 am in units of hours, which is not particularly limited in the embodiment of the present invention. In this case, the columns of the departure matrix corresponding to a indicate different integer time points. In addition, the preset time period mentioned in the embodiments and the following embodiments of the present invention may be a weekend time period, besides a working day time period, and may also be a afternoon time period or an evening time period, besides a morning time period, which is not specifically limited in this respect in the embodiments of the present invention.
Similarly, for any city partition in a city region, the arrival matrix corresponding to the city partition may also have two dimensions of rows and columns. Where a row of the arrival matrix may refer to which other city zone the user moved to that city zone, and a column of the arrival matrix may refer to a different preset time period. The arrival matrix may include a moving frequency of all users moving from each other civic partition to the civic partition within a preset time period, and each element in the arrival matrix represents a moving frequency of all users moving from some other civic partition to the civic partition within a certain preset time period, which is not specifically limited by the embodiment of the present invention.
For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. For city partition a, a corresponds to 3 rows of the arrival matrix, i.e., city partition B, C and D, respectively. The number of columns of the arrival matrix corresponding to a is 3, that is, the arrival matrix corresponds to the three different time periods. For the row 1, column 1 element in the arrival matrix, the meaning of this element is that all users start from B and move to the frequency of a in the period of 8 am to 9 am.
Similarly, in order to facilitate subsequent statistics in the actual implementation process, the preset time period may also be normalized to an integer time point according to the unit of hour. For example, for any user, if the user starts from B and moves to a at 8 am 40 (i.e., within 8 am to 9 am), the time when the user arrives at a may be regulated to 8 am or 9 am in units of hours, which is not specifically limited in the embodiment of the present invention. At this time, the columns of the arrival matrix corresponding to a refer to different integer time points.
In addition, in 101, when the departure matrix and the arrival matrix corresponding to each city partition are obtained, the departure matrix and the arrival matrix may be obtained based on location data uploaded by a user within a preset time period, which is not specifically limited in the embodiment of the present invention. For example, a user usually starts a positioning function when using a mobile terminal, so that a departure matrix and an arrival matrix corresponding to each city partition can be obtained according to location data uploaded by the mobile terminal.
102. Inputting the designated parameters into a preset model, and determining a preset type corresponding to each urban partition based on an output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition.
For any city partition, if the city partition is regarded as a document, and each element in the departure matrix and the arrival matrix corresponding to the city partition is regarded as a word in the document, the problem of determining the area type of the city partition can be converted into the problem of determining the document theme.
For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. If the city partition A is considered as a document, each element in the departure matrix and the arrival matrix corresponding to A can be considered as a word in the document. For the row 1, column 1 element in the arrival matrix, the meaning of this element is that all users start from B and move to the frequency of a in the period of 8 am to 9 am. That is, for the element in line 1 and column 1, the element represents a moving relationship in a time period, the moving relationship can be regarded as a word in the document, and the frequency of the word appearing in the document is also the moving frequency.
As can be seen from the above principles, the problem of determining the area type of a city partition can be translated into a problem of determining the subject matter of a document. That is, for any document in a series of documents, the probability distribution of the document for each topic may be determined first, so that the probability value of the document for each topic may be determined, and the topic with the highest probability value is taken as the topic corresponding to the document. Correspondingly, in the embodiment of the invention, for any city partition, the probability distribution of the city partition as each preset type can be output through the preset model, so that the preset type with the maximum probability value can be determined and used as the preset type corresponding to the city partition.
Based on the above description, in 102, the type of the preset model may be a document theme generation model, such as an LDA (Latent Dirichlet Allocation) model, and the like, which is not specifically limited in the embodiment of the present invention. The designated parameters input by the preset model during use at least comprise the total number of the preset types, the departure matrix and the arrival matrix corresponding to each city partition. The preset type total is also the predetermined area type total. For example, if the area type of each city zone is determined in accordance with the angle of the functional zone, the predetermined area types may be residential areas, business areas, industrial areas, and school areas. At this time, the predetermined total number of types of regions is 4. And inputting the specified parameters into a preset model, and outputting the probability distribution of each city partition as each region type. For example, for any city partition, if the probability value of outputting the city partition as a residential district through the preset model is 0.25, the probability value as a business district is 0.35, the probability value as an industrial district is 0.3, and the probability value as a school district is 0.1. Therefore, the area type with the highest probability value, i.e., the commercial district, can be used as the area type of the city partition. After determining the region type for each city partition, the city partitions with the same region type may be clustered.
It should be noted that, in the embodiment of the present invention, the number of the preset time periods may be one or multiple, and the embodiment of the present invention is not particularly limited to this. If the number of the preset time periods related to the embodiment of the present invention is multiple, the departure matrices and the arrival matrices of the multiple time periods may be input to the preset model subsequently, that is, the departure matrices and the arrival matrices of the multiple time periods are fitted to obtain the area types of the city partitions in the overall time period corresponding to the multiple time periods.
According to the method provided by the embodiment of the invention, the starting matrix and the arrival matrix corresponding to each city partition are obtained, the designated parameters are input into the preset model, and the preset type corresponding to each city partition is determined based on the output result of the preset model. The area type corresponding to the city subarea can be automatically determined based on the movement data of the user among different city subareas, so that the determination result is more accurate. In addition, because the time dimension is introduced when the area type corresponding to the urban subarea is determined, namely the area type corresponding to the urban subarea in different time periods can be determined for the same urban subarea, and the method is more suitable for practical application scenes.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the departure matrix corresponding to each city partition, and includes but is not limited to: for any city partition, acquiring a user departure matrix corresponding to each user; for any user in all users, the user departure matrix corresponding to any user comprises the moving frequency of any user moving from any city partition to each other city partition within a preset time period; and overlapping the user departure matrix corresponding to each user to obtain the departure matrix corresponding to any city partition.
As can be seen from the definition of the departure matrix corresponding to the city partition in the above embodiment, for any city partition, the departure matrix corresponding to the city partition includes the moving frequency of all users moving from the city partition to each of the other city partitions within the preset time period. In an actual implementation process, the user departure matrix corresponding to each user may be obtained first, and the user departure matrices corresponding to each user are superimposed, so that the departure matrix corresponding to the city partition may be obtained. It should be noted that, the user departure matrix corresponding to each user is superimposed, and elements at the same position in the departure matrix of each user are mainly superimposed, so that elements at the same position in the departure matrix corresponding to the city partition can be obtained.
For any user, the user departure matrix corresponding to the user can also have two dimensions of rows and columns. The rows of the user departure matrix may refer to other city partitions to which the user moves after departing from the city partition, and the columns of the user departure matrix may refer to different preset time periods. The user departure matrix may include a moving frequency of the user moving from the city partition to each of the other city partitions within a preset time period, and each element in the user departure matrix represents a moving frequency of the user moving from the city partition to each of the other city partitions within a certain preset time period. Through the process, the departure matrix corresponding to each city partition can be finally obtained.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the arrival matrix corresponding to each city partition, which includes but is not limited to: for any city partition, acquiring a user arrival matrix corresponding to each user; for any user in all users, the user arrival matrix corresponding to any user comprises the moving frequency of any user moving from each other city partition to any city partition within a preset time period; and superposing the user arrival matrix corresponding to each user to obtain the arrival matrix corresponding to any city partition.
As can be seen from the definition of the arrival matrix corresponding to the city partition in the above embodiment, for any city partition, the arrival matrix corresponding to the city partition includes the moving frequency to which all users move from each other city partition to the city partition within the preset time period. In the actual implementation process, the user arrival matrix corresponding to each user can be obtained first, and the user arrival matrices corresponding to each user are superposed to obtain the arrival matrix corresponding to the city partition. It should be noted that the user arrival matrix corresponding to each user is superimposed, and the elements at the same position in the arrival matrix of each user are mainly superimposed, so that the elements at the same position in the arrival matrix corresponding to the city partition can be obtained.
For any user, the user arrival matrix corresponding to the user may also have two dimensions of rows and columns. Wherein, a row of the user arrival matrix may refer to which other city partition the user moves to, and a column of the user arrival matrix may refer to a different preset time period. The user arrival matrix may include a moving frequency of the user moving from each other city partition to the city partition within a preset time period, and each element in the user arrival matrix represents a moving frequency of the user moving from a certain other city partition to the city partition within a certain preset time period, which is not specifically limited in the embodiment of the present invention. Through the above process, the arrival matrix corresponding to each city partition can be finally obtained.
As can be seen from the above embodiments, the elements in the user departure matrix and the user arrival matrix represent a moving relationship in a time period. For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. If the city partition of the user departure matrix corresponding to the user, which is taken as the departure place, is a, the element in the 1 st row and the 1 st column in the user departure matrix means that the user departs from a and moves to the movement frequency of B in the time period from 8 am to 9 am, that is, the element in the 1 st row and the 1 st column in the 1 st row represents a movement relationship from a to B.
Based on the above description and the content of the above embodiments, in an actual implementation process, the user departure matrix corresponding to each user may be obtained based on the above movement relationship. Accordingly, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the user departure matrix corresponding to each user, and includes but is not limited to: for any user, determining a travel sequence meeting a first preset condition from all travel sequences of the user within a preset time period; the first preset condition is that any city partition is taken as a starting place and other city partitions are taken as destinations, and each travel sequence corresponds to a moving frequency; and determining a user departure matrix corresponding to any user according to the travel sequence meeting the first preset condition.
All travel sequences of the user in the preset time period may be obtained based on the location data uploaded by the user in the preset time period, which is not specifically limited in the embodiment of the present invention. For example, the user uploaded location data at 8 am 40 and location data at 9 am. If it is determined that the user moves in the period based on the position data uploaded at the two time points, a corresponding travel sequence can be constructed from the position data uploaded twice. Wherein, the trip sequence can be represented by the following form:
((k，start_time)，(k',end_time)，wi)
where k denotes a city partition as a departure place, and k' denotes a city partition as a destination. start _ time represents the time from the departure, end _ time represents the time to the destination, wiRepresenting the corresponding moving frequency of the trip sequence.
Take the city partitions in the urban area as A, B, C and D, respectively, and the preset time periods as 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively, as an example. For any user, all travel sequences of the user within 8 to 9 am refer to a travel sequence from any city partition within 8 to 9 am (i.e. start _ time within 8 to 9 am), and a travel sequence to reach any city partition within 8 to 9 am (i.e. end _ time within 8 to 9 am). If the city partition as the departure place is a, the departure sequence meeting the first preset condition is a trip sequence in which k takes the value of a in the trip sequence expression, that is, a trip sequence issued from a within 8 to 9 am.
According to the above, the trip sequence may determine a moving relationship between city partitions in a time period, and the trip sequence also corresponds to a moving frequency. Therefore, the user departure matrix corresponding to the user can be determined based on the travel sequence. For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. If the city partition a is taken as a starting point, the travel sequences meeting the first preset condition can be classified into the following types:
(1) starting from A and moving to B in 8 to 9 am;
(2) starting from A within 9 to 10 am, and moving to a travel sequence of B;
(3) starting from A and moving to B in 10 to 11 am;
(4) starting from A and moving to C in 8 to 9 am;
(5) starting from A and moving to C in 9 to 10 am;
(6) a travel sequence starting from A and moving to C within 10 to 11 am;
(7) a travel sequence from A to D within 8 to 9 am;
(8) a travel sequence from A to D within 9 to 10 am;
(9) a travel sequence from a, moving to D, within 10 to 11 am.
Each travel sequence corresponds to a moving frequency. It should be noted that, in practical implementation, the number of each of the above travel sequences may be more than one. For example, the user moves from A to B from 8 to 9 am, then from B to A from 8 to 9 am, and finally from A to B from 8 to 9 am. At this time, two travel sequences will appear starting from a and moving to B from 8 am to 9 am. For this situation, the moving frequencies corresponding to the two trip sequences may be added and combined into one trip sequence.
As can be seen from the above description of the embodiment, if the departure place is the city partition a, the rows of the departure matrix of the user may refer to other city partitions to which the user moves after the departure from a, and the columns of the departure matrix of the user may refer to different preset time periods. And determining the user departure matrix corresponding to the user according to the trip sequence meeting the first preset condition by combining the definition of the user departure matrix and the description about the trip sequence. It should be noted that, if the departure place is other city partitions, the trip sequence meeting the first preset condition corresponding to each user may also be determined according to the above process, and then the user departure matrix of each user is determined, which is not described herein again. Through the process, the user departure matrix corresponding to each user can be obtained under the condition that different city partitions are taken as departure places.
Based on the above description and the content of the above embodiments, in an actual implementation process, the user arrival matrix corresponding to each user may be obtained based on the above movement relationship. Accordingly, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the user arrival matrix corresponding to each user, including but not limited to: for any user, determining a travel sequence meeting a second preset condition from all travel sequences of the user within a preset time period; the second preset condition is that other city partitions are taken as departure places and any city partition is taken as a destination, and each travel sequence corresponds to a moving frequency; and determining a user arrival matrix corresponding to any user according to the travel sequence meeting the second preset condition.
Wherein, for the explanation of all travel sequences of the user in the preset time period, and the specific form of the travel sequence, reference is made to the description in the above embodiment,
take the city partitions in the urban area as A, B, C and D, respectively, and the preset time periods as 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively, as an example. For any user, all travel sequences of the user within 8 to 9 am refer to a travel sequence from any city partition within 8 to 9 am (i.e. start _ time within 8 to 9 am), and a travel sequence to reach any city partition within 8 to 9 am (i.e. end _ time within 8 to 9 am). If the city partition as the destination is a, the travel sequence satisfying the second preset condition is the travel sequence in which k' takes the value of a in the travel sequence expression, that is, the travel sequence reaching a within 8 to 9 am.
According to the above, the trip sequence may determine a moving relationship between city partitions in a time period, and the trip sequence also corresponds to a moving frequency. Therefore, the user arrival matrix corresponding to the user can be determined based on the travel sequence. For example, the city partitions in the urban area are A, B, C and D, respectively, and the predetermined time periods are 8 am to 9 am, 9 am to 10 am, and 10 am to 11 am of the working day, respectively. If the urban partition a is taken as a destination, the travel sequences meeting the second preset condition can be classified into the following types:
(1) starting from B, moving to A travel sequence from 8 am to 9 am;
(2) starting from B, moving to A travel sequence from 9 am to 10 am;
(3) starting from B, moving to A travel sequence within 10 to 11 am;
(4) starting from C, moving to A travel sequence from 8 am to 9 am;
(5) starting from C, moving to the travel sequence of A within 9 to 10 am;
(6) starting from C, moving to A travel sequence from 10 to 11 pm;
(7) starting from D, moving to the travel sequence of A in 8 to 9 am;
(8) starting from D, moving to the travel sequence of A within 9 to 10 am;
(9) starting at D, move to A's travel sequence from 10 AM to 11 AM.
Each travel sequence corresponds to a moving frequency. It should be noted that, in practical implementation, the number of each of the above travel sequences may be more than one. For example, the user starts from B and moves to a from 8 to 9 am, then starts from a and moves to B from 8 to 9 am, and finally starts from B and moves to a from 8 to 9 am. At this time, two travel sequences will appear starting from B and moving to a from 8 am to 9 am. For this situation, the moving frequencies corresponding to the two trip sequences may be added and combined into one trip sequence.
As can be seen from the above description of the embodiment, if the destination is city partition a, the row of the user arrival matrix may refer to which other city partition the user starts to move to a, and the column of the user departure matrix may refer to different preset time periods. And determining the user arrival matrix corresponding to the user according to the travel sequence meeting the second preset condition by combining the definition of the user arrival matrix and the description about the travel sequence. It should be noted that, if the destination is other urban partitions, the trip sequence meeting the second preset condition corresponding to each user may also be determined according to the above process, and then the user departure matrix of each user is determined, which is not described herein again. Through the process, the user arrival matrix corresponding to each user can be finally obtained under the condition that different city partitions are used as destinations.
In a practical application scenario, a mobile terminal used by a user typically generates signaling data. The signaling data mainly includes a base station identifier for communicating with the mobile terminal and a generation time of the signaling data. Therefore, as the positions of the base stations are determined, a user may move from an area covered by one base station to an area covered by another base station, and the area covered by the base station overlaps with a city partition, so that a sequence formed by the signaling data can reflect the moving track of the user. Based on the above description and the content of the above embodiments, as an optional embodiment, for any user, before determining a travel sequence satisfying a first preset condition from all travel sequences of the user within a preset time period, or before determining a travel sequence satisfying a second preset condition from all travel sequences of the user within the preset time period, all travel sequences of the user within the preset time period may also be determined.
Accordingly, the embodiment of the present invention provides a method for determining all travel sequences of a user within a preset time period, including but not limited to: for any user, all travel sequences of any user in a preset time period are determined based on the urban subarea corresponding to each base station in the urban area and the base station moving sequence of the user in the preset time period.
As can be seen from the above, the area covered by the base station may partially overlap with the urban partition, so that for any base station, the urban partition overlapping with the coverage area of the base station may be used as the urban partition corresponding to the base station. In addition, the base station movement sequence may be determined by signaling data generated by the mobile terminal, such as by sequencing the signaling data to generate the base station movement sequence. The base station moving sequence may include at least a user identifier of the user, a base station identifier as a departure place, a signaling data generation time corresponding to the base station as the departure place, a base station identifier as a destination, and a signaling data generation time corresponding to the base station as the destination. Wherein, the user identification corresponds to a user using the mobile terminal. For example, the base station movement sequence may be expressed as follows:
(user_id,(cell_id0,time0),(cell_id1,time1))
wherein, user _ id is user identification, cell _ id0Cell _ id as base station identification of departure place1Time for base station identification as destination0Generating time, for signalling data corresponding to the base station as the origin1The time is generated for the signaling data corresponding to the destination base station. Wherein, (cell _ id)0,time0) Is the signaling data corresponding to the base station as the starting place, (cell _ id)1,time1) Is signaling data corresponding to the base station as the destination.
The base station moving sequence can reflect the moving track of the user between the base stations, and the corresponding relation exists between the base stations and the urban subarea, so that the base station moving sequence can be mapped into the trip sequence according to the corresponding relation between the base stations and the urban subarea.
According to the method provided by the embodiment of the invention, for any user, all travel sequences of any user in a preset time period are determined based on the urban subarea corresponding to each base station in the urban area and the base station moving sequence of any user in the preset time period. The signaling data can reflect the movement track of the user, so that the trip sequence of the user is determined by combining the base station movement sequence determined by the signaling data, the signaling data can be fully mined and utilized, and the accuracy of the subsequent determination of the urban subarea type can be improved.
Based on the content of the foregoing embodiment, as an optional embodiment, before determining all trip sequences of any user in a preset time period based on a city partition corresponding to each base station in an urban area and a base station moving sequence of any user in the preset time period, the city partition corresponding to each base station may also be determined. Referring to fig. 2, the embodiment of the present invention does not specifically limit the manner of determining the city partition corresponding to each base station, including but not limited to:
201. and determining a Thiessen polygon corresponding to each base station in the urban area, wherein each Thiessen polygon comprises one base station.
In 201, if an urban area is considered as a spatial plane, each base station in the urban area can be considered as a point on the spatial plane. Based on the Thiessen polygon mapping method, the spatial plane may be divided into a plurality of Thiessen polygons. Wherein each Thiessen polygon contains a base station. The Thiessen polygon is a subdivision of a spatial plane, and is characterized in that any position in the polygon is closest to a sampling point (namely a base station) of the polygon and is far away from the sampling point in an adjacent polygon, and each polygon contains only one sampling point.
202. And determining the city partition covering each Thiessen polygon, and taking the city partition covering each Thiessen polygon as the city partition corresponding to each base station.
Since the urban area is also regarded as a spatial plane and is obtained by dividing the urban area according to the road network data, the overlapping part of the Thiessen polygon and the urban area exists. As shown in fig. 3, the hexagon located in the middle of fig. 3 is a tesson polygon 1 in the space plane, and the rectangle in the dotted line portion of fig. 3 is a city partition. As can be seen from fig. 3, 3 dashed rectangles in fig. 3 can just cover the thiessen polygon, so that the 3 city partitions are the city partitions covering the thiessen polygon 1. Correspondingly, for the base station corresponding to the thiessen multiple variant 1, the above 3 city partitions are the city partitions corresponding to the base station.
The method provided by the embodiment of the invention determines the Thiessen polygon corresponding to each base station in the urban area. And determining the city partition covering each Thiessen polygon, and taking the city partition covering each Thiessen polygon as the city partition corresponding to each base station. The urban subareas covering the Thiessen polygons are the urban subareas closest to the base station in the Thiessen polygons, and the urban subareas covering the Thiessen polygons are used as the urban subareas corresponding to the departure place and the destination of the user, so that the accuracy in predicting the travel sequence can be improved, and the accuracy in subsequently determining the types of the urban subareas can be improved.
As can be seen from the above description of the embodiments, the signaling data reflects the coverage of which base station the user is located at different time points, and the base station movement sequence can be generated by the signaling data. The signaling data are sequenced according to the generation time, and for any two adjacent signaling data after sequencing, it is not necessarily ensured that the user is just in a moving state in the time period corresponding to the two adjacent signaling data. In the embodiment of the present invention, the trip sequences of the users need to be determined according to the base station moving sequence generated by the signaling data, and each trip sequence represents a section of moving relationship between the urban partitions, that is, the users are always in a moving state, so that for the base station moving sequence generated based on the signaling data, it is necessary to ensure that the users are in a moving state within a time period corresponding to the base station moving sequence. In view of the above requirement, for any user, the embodiment of the present invention further provides a method for determining a base station moving sequence of the user within a preset time period. Referring to fig. 4, including but not limited to:
401. sequencing each signaling data of the user in sequence according to the generation time of each signaling data to obtain a base station trip sequence of the user in a preset time period.
Specifically, the obtained base station travel sequence may be represented as follows:
(user_id,(cell_id0,time0),(cell_id1,time1)...)
wherein, the user _ id is the user identifier (cell _ id) of the user0,time0) And(cell_id1,time1) Are all signaling data. cell _ id0And cell _ id1Are all base station identities. time0Is signaling data (cell _ id)0,time0) Time of generation of1Is signaling data (cell _ id)1,time1) The time of generation of (c). The following ellipses represent other signaling data in the base station trip sequence. It should be noted that, the base station trip sequence in the preset time period in 401 means that the generation time of each signaling data in the base station trip sequence is within the preset time period.
402. Selecting a subsequence meeting a third preset condition from the base station trip sequence, and taking the subsequence as a base station moving sequence of any user in a preset time period; the third preset condition is that the difference between the generation moments corresponding to any two adjacent signaling data is smaller than a first preset threshold value and the user moving speed is within a preset range.
For the convenience of understanding, any two adjacent signaling data are (cell _ id)0,time0) And (cell _ id)1,time1) For example, the process of 402 is explained. Wherein, (cell _ id)0,time0) And (cell _ id)1,time1) The corresponding difference between the times of generation is (time)1-time0). Since which base station can be determined based on the base station identity, and the base station location is predetermined, the slave base station cell _ id0To cell _ id1The user moving speed can be calculated according to the distance difference between the two base stations and the difference between the generation moments.
After the user moving speed is calculated, it may be determined whether a difference between the user moving speed and the generation time satisfies a third preset condition. The first preset threshold in the third preset condition may be 1 hour, and the preset range may be between 2 kilometers per hour and 150 kilometers per hour, which is not specifically limited in the embodiment of the present invention. If the third preset condition is satisfied, the user is really the base station cell _ id0Move to base station cell _ id1That is, it can be considered as the cell _ id of the base station0And base station cell _ id1Are continuous in between.
After the above process is performed, the base station cell _ id can be determined according to the same method1And base station cell _ id2Whether or not there is continuity between. If the first and second preset conditions are satisfied, the base station cell _ id can be determined0Base station cell _ id1And base station cell _ id2The three are continuous. If the base station cell _ id is judged2And base station cell _ id3If the sequences are not consecutive, a first subsequence satisfying a third preset condition may be selected from the base station trip sequences, and the subsequence may be represented as follows:
(user_id,(cell_id0,time0),(cell_id1,time1),(cell_id2,time2))
wherein, the user _ id is the user identifier of the user. For the sub-sequence, it can be understood that the user is represented by the base station cell _ id0Starts to move to the base station cell _ id2The position of (3) is stopped. Thus, cell _ id0Cell _ id as base station identification of departure place2Is identified for the base station as the destination.
After the first subsequence meeting the third preset condition is selected from the base station trip sequences, the base station cell _ id is judged2And base station cell _ id3Are not continuous, the base station cell _ id can be set3The base station identification is taken as the starting place, and the base station cell _ id in the base station trip sequence is continuously judged3And base station cell _ id4And if the data is continuous, traversing each signaling data in the base station trip sequence one by one according to the process until all the signaling data are traversed. By executing the above process, a plurality of subsequences meeting the third preset condition can be finally selected from the base station trip sequence, so that the plurality of subsequences meeting the third preset condition can be used as the base station moving sequence of the user in the preset time period.
In the method provided by the embodiment of the invention, for any user, the base station trip sequence of the user in a preset time period is obtained by sequencing each signaling data of the user according to the generation time of each signaling data. And selecting a subsequence meeting a third preset condition from the base station trip sequence, and taking the subsequence as a base station moving sequence of any user in a preset time period. The subsequence of the user in the moving state can be selected from the base station trip sequence and used as the base station moving sequence, so that the user in the moving state in the time period corresponding to the base station moving sequence can be ensured, and the accuracy of the trip sequence can be improved when the trip sequence is determined based on the base station moving sequence subsequently.
Based on the content of the foregoing embodiment, as an optional embodiment, for any user, the embodiment of the present invention does not specifically limit the manner of determining all travel sequences of the user in a preset time period based on the urban partition corresponding to each base station in the urban area and the base station movement sequence of any user in the preset time period, including but not limited to: randomly combining the first city partition and the second city partition to obtain all travel sequences of any user in a preset time period; the first city subarea is a city subarea corresponding to a base station which is taken as a starting place in a base station moving sequence, and the second city subarea is a city subarea corresponding to a base station which is taken as a destination in any base station moving sequence.
As can be seen from the above description of the embodiments, the base station moving sequence includes the base station identifier as the departure point and the base station identifier as the destination point. And each base station corresponds to a Thiessen polygon, and for the Thiessen polygon corresponding to any base station, the city partition corresponding to the base station refers to the city partition covering the Thiessen multi-deformation. As shown in fig. 3, there are 3 city divisions corresponding to the thiessen polygon 1. Since there may be a plurality of city partitions corresponding to the thiessen polygon, when determining the travel sequence based on the base station movement sequence, even if the base station as the departure place and the base station as the destination are uniquely determined, the city partition as the departure place and the city partition as the destination cannot be uniquely determined.
For the convenience of understanding the process of obtaining the travel sequence by any combination, taking the thiessen polygon corresponding to the base station as the departure place in the base station movement sequence as TPi, the thiessen polygon corresponding to the base station as the destination in the base station movement sequence as TPj, the city partitions corresponding to the thiessen polygon TPi as R1 and R2, and the city partition corresponding to the thiessen polygon Tpj as R3 and R4 as examples, the process of any combination can refer to fig. 5. As shown in fig. 5, the travel sequences may be (R1, R3), (R1, R4), (R2, R3), and (R2, R4), respectively. Where R1 and R2 are city partitions as departure points, and R3 and R4 are city partitions as destination points.
As can be seen from the above embodiments, each row sequence corresponds to a moving frequency. After all travel sequences of any user in a preset time period are determined based on city partitions corresponding to each base station in an urban area and base station movement sequences of any user in the preset time period, the movement frequency corresponding to each travel sequence can be calculated. Accordingly, based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention further provides a method for calculating a moving frequency corresponding to a travel sequence, including but not limited to: for any travel sequence, calculating a first area ratio between a first part of Thiessen polygons and a first urban subarea, calculating a second area ratio between a second part of Thiessen polygons and a second urban subarea, and taking the product of the first area ratio and the second area ratio as the movement frequency corresponding to the travel sequence; the first city partition is a city partition which is taken as a starting place in the travel sequence, and the second city partition is a city partition which is taken as a destination in the travel sequence; the first part of Thiessen polygons are part of Thiessen polygons contained in the first city partition, and the second part of Thiessen polygons are part of Thiessen polygons contained in the second city partition.
For the sake of easy understanding, the above-mentioned process of calculating the shift frequency is described with reference to fig. 5, taking the row sequence as (R1, R3) as an example. In the first city partition, i.e. the city partition R1, the first part of the thieson polygon, i.e. the partial region of the thieson polygon Tpi, is located within R1, thereby calculating a first area ratio between the partial region of the thieson polygon Tpi and the city partition R1. Similarly, a second area ratio between the partial region of the thiessen polygon Tpj and the city partition R3 may be calculated, and the product of the first area ratio and the second area ratio may be used as the moving frequency corresponding to the row sequence (R1, R3).
It should be noted that the value of the shift frequency calculated by the above procedure is less than 1. The moving frequency corresponding to the trip sequence calculated in the embodiment of the present invention is not obtained by actually counting the trip frequency of the user, that is, is not really representing the actual occurrence frequency of the moving relationship corresponding to the trip sequence, but rather emphasizing on representing the possibility that the corresponding moving relationship of each trip sequence actually occurs in the determined multiple trip sequences.
In addition, it should be noted that, as can be seen from the content of the foregoing embodiment, when determining the preset type corresponding to each city partition, the problem of determining the area type of the city partition needs to be converted into the problem of determining the document theme. The city partition can be regarded as a document, the movement relation corresponding to each trip sequence can be regarded as a word in the document, and the movement frequency corresponding to the trip sequence can be regarded as the frequency of the word appearing in the document. Based on the above description, since the frequency of the occurrence of the words is an integer under the conventional understanding, in order to facilitate processing of the data, after the moving frequency smaller than 1 is obtained through the above calculation, the moving frequency corresponding to each row sequence may also be converted into an integer in a unified manner in the embodiment of the present invention, which is not specifically limited in the embodiment of the present invention. For example, the conversion may be directly multiplying the shift frequency by 100 and rounding.
Based on the content of the above embodiment, as an optional embodiment, the specified parameters further include a feature vector corresponding to each city partition; and determining the feature vector corresponding to each city partition by the interest points in each city partition. The format of the point of interest may be (a point of interest name, a point of interest location, a point of interest category), and the point of interest category may be divided according to functions, such as being divided into a scenic spot, a store, a school, a company, a residential area, and the like, which is not limited in this embodiment of the present invention.
It should be noted that, as can be seen from the above embodiments, the city partition can be regarded as a document. In the embodiment of the present invention, the feature vector corresponding to the city partition may be regarded as document meta-information, such as the author of the document or the publication year of the document. In the above embodiment, if the preset model is the LDA model, the document meta-information is not introduced in the document theme determination process, so that the final determination result is not accurate enough. In the embodiment of the present invention, the specific parameters further include a feature vector corresponding to each city partition. Accordingly, the preset model related to the above embodiment may also be a DMR (Dirichlet-multinomial Regression) model. The feature vector corresponding to each city partition is introduced into the designated parameters to determine the preset type of each city partition by combining the interest points in the city partitions, so that the determination result is more accurate.
Based on the content of the foregoing embodiment, as an optional embodiment, if the specified parameter further includes a feature vector corresponding to each city partition, before the specified parameter is input to the preset model, the feature vector corresponding to each city partition may also be determined. Accordingly, the embodiment of the present invention does not specifically limit the manner of determining the feature vector corresponding to each city partition, including but not limited to: and determining a feature vector corresponding to each urban partition based on the number of the interest points of each type in each urban partition and the area of each urban partition.
For any city partition, the feature vector corresponding to the city partition may be directly constituted by the number of each type of interest point in the city partition and the area of the city partition, and may be specifically expressed as follows:
fi＝(pfi1,pfi2,...,pfiC,Area(i))
wherein f isiAnd partitioning the feature vector corresponding to the ith city. pfi1Is the number of the first type of interest points in the ith city partition, pfi2The number of interest points of the second type in the ith city partition, … …, pficThe class C in the ith city partition is addedThe number of interesting points, area (i), is the ratio of the area corresponding to the ith city partition to the minimum area in all city partitions.
Based on the content of the foregoing embodiment, as an alternative embodiment, the embodiment of the present invention does not specifically limit the manner of determining the feature vector corresponding to each city partition based on the number of each type of interest point in each city partition and the area of each city partition. Referring to fig. 6, including but not limited to:
601. and determining an initial feature vector corresponding to each urban partition based on the number of the interest points of each type in each urban partition and the area of each urban partition.
Specifically, based on the number of each type of interest points in each city partition and the area of each city partition, the candidate feature vector corresponding to each city partition may be determined first. The candidate feature vector may be represented as follows:
fi＝(pfi1,pfi2,...,pfiC,Area(i))
wherein f isiAnd partitioning the candidate feature vector corresponding to the ith city. pfi1Is the number of the first type of interest points in the ith city partition, pfi2The number of interest points of the second type in the ith city partition, … …, pficArea (i) is the ratio of the area corresponding to the ith city partition to the minimum area in all the city partitions.
After the candidate feature vector corresponding to each city partition is obtained, the candidate feature vector corresponding to each city partition can be converted into a TF-IDF (term-Inverse text Frequency index) vector corresponding to each city partition, that is, an initial feature vector. Wherein, the TF-IDF vector corresponding to each city partition can be represented as follows:
TFIDFi＝(tfidfi1,tfidfi2,...,tfidfic,Area(i))
wherein, TFIDFiCorresponding TFIDF direction for the ith city partitionAmount of the compound (A). tfidfi1Tfidf is the importance of the first type of interest points in the ith city zonei2… …, tfidf, as the importance of the second type of interest points in the ith city partitionicArea (i) is the ratio of the area corresponding to the ith city partition to the minimum area in all the city partitions.
Importance tfidf to the jth class of interest points in the ith city partitionijSpecifically, the following can be referred to:
Figure BDA0001706864930000231
wherein tfidfijThe importance degree of the j-th interest point in the ith city partition, pfijThe number of j-th interest points in the ith city partition is, M is the total number of city partitions, and count (j) is the number of city partitions containing j-th interest points in all city partitions.
602. Splicing the initial eigenvectors corresponding to each city partition to obtain first matrixes corresponding to all the city partitions, and performing singular value decomposition on the first matrixes to obtain second matrixes; the second matrix is composed of the characteristic vectors corresponding to each city partition.
After the initial feature vector corresponding to each city partition is obtained, the initial feature vectors corresponding to each city partition, that is, the TF-IDF vectors corresponding to each city partition, may be spliced, so as to obtain a first matrix of M x (C +1) dimension. By decomposing the first matrix using an SVD (Singular Value Decomposition) matrix, a second matrix X ═ F (X) of M × F can be obtained1,...xM)T. Wherein x isiAnd representing the feature vector corresponding to the ith city partition.
As can be seen from the above description of the embodiments, the output of the preset model is the probability distribution of each city partition as each preset type. Based on the content of the foregoing embodiment, as an alternative embodiment, the specified parameter may further include a weight corresponding to the feature vector. Accordingly, the process of inputting the specified parameters into the preset model to obtain the output result is not specifically limited in the embodiments of the present invention, including but not limited to: inputting the designated parameters into a preset model, outputting the probability distribution between each city partition and each preset type, adjusting the weight corresponding to the feature vector corresponding to each city partition based on a gradient descent method, inputting the adjusted weight corresponding to each city partition and the designated parameters into the preset model again, outputting the probability distribution between each city partition and each preset type again, and repeating the weight adjustment process and the preset model input and output process until the output probability distribution between each city partition and each preset type tends to be stable. Through the process, the output result of the preset model can be more accurate.
According to the method provided by the embodiment of the invention, the initial characteristic vector corresponding to each city partition is determined based on the number of each type of interest points in each city partition and the area of each city partition. And splicing the initial characteristic vectors corresponding to each city partition to obtain first matrixes corresponding to all the city partitions, and performing singular value decomposition on the first matrixes to obtain second matrixes. The feature vector corresponding to each city partition can be introduced into the designated parameters to determine the preset type of each city partition by combining the interest points in the city partitions, so that the determination result is more accurate.
It is considered that if the urban subareas are too small, the number of urban subareas is relatively large, and the statistical result is too dispersed and not significant enough. For this situation, based on the content of the foregoing embodiment, as an optional embodiment, before obtaining the departure matrix and the arrival matrix corresponding to each city partition, the city partitions may also be merged. Accordingly, the embodiment of the present invention does not specifically limit the manner of merging the city partitions, including but not limited to: if the urban subareas with the areas smaller than the second preset threshold exist in the urban subarea set, merging the urban subareas in the urban subarea set until the area of each urban subarea in the urban subarea set is larger than the second preset threshold; the urban subarea set comprises a plurality of urban subareas obtained by dividing urban areas based on road network data.
The plurality of city partitions obtained after the road network data are divided can be merged in a pairwise merging mode, for example, the city partition with the smallest area and the city partition with the second smallest area are selected from all the city partitions for merging each time until the area of each city partition in the city partition set is larger than a second preset threshold.
In the method provided by the embodiment of the invention, the urban partitions with the area smaller than the second preset threshold value exist in the urban partition set, and the urban partitions in the urban partition set are merged until the area of each urban partition in the urban partition set is larger than the second preset threshold value. Because the urban partitions with smaller areas in all the urban partitions can be merged, the subsequent statistical result is more obvious and more targeted.
Consider that the connections between city partitions with common edges are more compact among all city partitions, and the connections are more compact the longer the common edges are. Based on the principle and the content of the foregoing embodiment, as an optional embodiment, regarding a manner in which the city partitions in the city partition set are merged until the area of each city partition in the city partition set is greater than the second preset threshold, the embodiment of the present invention is not particularly limited to this, and includes but is not limited to: selecting a third city partition meeting a third preset condition from the city partition set, selecting a fourth city partition meeting a fourth preset condition from the city partition set, merging the third city partition and the fourth city partition to obtain a city partition set again, and repeatedly executing the selecting and merging processes until the area of each city partition in the city partition set is larger than a second preset threshold; the third preset condition is that the area is minimum and is smaller than a second preset threshold, and the fourth preset condition is that the public side length between the third preset condition and the third preset condition is that the public side length is longest and is adjacent to the third city subarea.
Specifically, the second preset threshold a may be selected firstthAnd all the city partitions in the city partition set are partitionedSorting according to the area from large to small, and specifically recording as:
Figure BDA0001706864930000252
from
Figure BDA0001706864930000253
Selecting the city partition b with the smallest areaiIf the city partition biIs larger than a second preset threshold value and a second preset threshold value AthThen the selection and combination process is finished. If the city is partitioned into biIs smaller than a second preset threshold value and a second preset threshold value AthThen from
Figure BDA0001706864930000254
To the city partition biAdjacent city partition bijAnd calculate city partition biAnd city partition bijThe ratio of the perimeter to the common side length can be specifically referred to by the following formula:
Figure BDA0001706864930000251
wherein lcijFor city division biAnd city partition bijCommon side length between, lpiFor city division biPerimeter of (lp)ijFor city division bijPerimeter of priijIs a city zone biAnd city partition bijThe ratio of the perimeter to the common side length. Note that priijThe larger the value of (b), the more the city partition b is indicatediAnd city partition bijThe longer the common edge in between.
Accordingly, the maximum pri may be selectedijCorresponding city partition bijAnd divide the city into zones biAnd city partition bijAnd merging. Repeating the selection and combination process until the area of each urban subarea in the urban subarea set is larger than a second preset areaThreshold value Ath。
The method provided by the embodiment of the invention selects the third city partition meeting the third preset condition from the city partition set, selects the fourth city partition meeting the fourth preset condition from the city partition set, merges the third city partition and the fourth city partition to obtain the city partition set again, and repeatedly executes the selecting and merging process until the area of each city partition in the city partition set is larger than the second preset threshold. Because the urban partitions with smaller areas in all the urban partitions can be merged, the subsequent statistical result is more obvious and more targeted.
It should be noted that, all the above-mentioned alternative embodiments may be combined arbitrarily to form alternative embodiments of the present invention, and are not described in detail herein.
Based on the content of the foregoing embodiments, an embodiment of the present invention provides an area type determination device, where the area type determination device is configured to execute the area type determination method provided in the foregoing method embodiment. Referring to fig. 7, the apparatus includes:
an obtaining module 701, configured to obtain a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to any urban subarea comprises the moving frequency of all users moving from any urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to any urban subarea comprises the moving frequency of all users moving from each other urban subarea to any urban subarea in the preset time period, and other urban subareas are urban subareas except any urban subarea in the urban area;
a first determining module 702, configured to input a specified parameter into a preset model, and determine a preset type corresponding to each city partition based on an output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition.
As an alternative embodiment, the obtaining module 701 includes:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a user departure matrix corresponding to each user for any city partition; for any user in all users, the user departure matrix corresponding to any user comprises the moving frequency of any user moving from any city partition to each other city partition within a preset time period;
and the first superposition unit is used for superposing the user departure matrix corresponding to each user to obtain the departure matrix corresponding to any city partition.
As an alternative embodiment, the obtaining module 701 includes:
the second acquisition unit is used for acquiring a user arrival matrix corresponding to each user for any city partition; for any user in all users, the user arrival matrix corresponding to any user comprises the moving frequency of any user moving from each other city partition to any city partition within a preset time period;
and the second superposition unit is used for superposing the user arrival matrix corresponding to each user to obtain the arrival matrix corresponding to any city partition.
As an optional embodiment, the first obtaining unit is configured to, for any user, determine a travel sequence that meets a first preset condition from all travel sequences of the user within a preset time period; the first preset condition is that any city partition is taken as a starting place and other city partitions are taken as destinations, and each travel sequence corresponds to a moving frequency; and determining a user departure matrix corresponding to any user according to the travel sequence meeting the first preset condition.
As an optional embodiment, the second obtaining unit is configured to, for any user, determine a travel sequence that meets a second preset condition from all travel sequences of the user within a preset time period; the second preset condition is that other city partitions are taken as departure places and any city partition is taken as a destination, and each travel sequence corresponds to a moving frequency; and determining a user arrival matrix corresponding to any user according to the travel sequence meeting the second preset condition.
As an alternative embodiment, the apparatus further comprises:
and the second determining module is used for determining all travel sequences of any user in a preset time period based on the urban subarea corresponding to each base station in the urban area and the base station moving sequence of any user in the preset time period.
As an alternative embodiment, the apparatus further comprises:
the third determining module is used for determining a Thiessen polygon corresponding to each base station in the urban area, and each Thiessen polygon comprises one base station;
and the fourth determining module is used for determining the city partition covering each Thiessen polygon and taking the city partition covering each Thiessen polygon as the city partition corresponding to each base station.
As an alternative embodiment, the apparatus further comprises:
the sequencing module is used for sequencing each signaling data of any user according to the generation time of each signaling data for any user to obtain a base station trip sequence of any user in a preset time period;
the selecting module is used for selecting a subsequence meeting a third preset condition from the base station trip sequence, and taking the subsequence as a base station moving sequence of any user in a preset time period; the third preset condition is that the difference between the generation moments corresponding to any two adjacent signaling data is smaller than a first preset threshold value and the user moving speed is within a preset range.
As an optional embodiment, the second determining module is configured to arbitrarily combine the first-class urban partition and the second-class urban partition to obtain all travel sequences of any user within a preset time period; the first city subarea is a city subarea corresponding to a base station which is taken as a starting place in a base station moving sequence, and the second city subarea is a city subarea corresponding to a base station which is taken as a destination in any base station moving sequence.
As an alternative embodiment, the apparatus further comprises:
the calculating module is used for calculating a first area ratio between a first part of Thiessen polygons and a first urban subarea, calculating a second area ratio between a second part of Thiessen polygons and a second urban subarea, and taking the product of the first area ratio and the second area ratio as the moving frequency corresponding to any travel sequence;
the first city partition is a city partition which is taken as a starting place in any one trip sequence, and the second city partition is a city partition which is taken as a destination in any one trip sequence; the first part of Thiessen polygons are part of Thiessen polygons contained in the first city partition, and the second part of Thiessen polygons are part of Thiessen polygons contained in the second city partition.
As an optional embodiment, the specified parameters further include a feature vector corresponding to each city partition; and determining the feature vector corresponding to each city partition by the interest points in each city partition.
As an alternative embodiment, the apparatus further comprises:
and the fifth determining module is used for determining the characteristic vector corresponding to each city partition based on the number of the interest points of each type in each city partition and the area of each city partition.
As an optional embodiment, the fifth determining module is configured to determine, based on the number of each type of interest point in each city partition and the area of each city partition, an initial feature vector corresponding to each city partition; splicing the initial eigenvectors corresponding to each city partition to obtain first matrixes corresponding to all the city partitions, and performing singular value decomposition on the first matrixes to obtain second matrixes; the second matrix is composed of the characteristic vectors corresponding to each city partition.
As an alternative embodiment, the apparatus further comprises:
the merging module is used for merging the urban partitions in the urban partition set when the urban partitions with the areas smaller than a second preset threshold exist in the urban partition set until the areas of all the urban partitions in the urban partition set are larger than the second preset threshold; the urban subarea set comprises a plurality of urban subareas obtained by dividing urban areas based on road network data.
As an optional embodiment, the merging module is configured to select a third city partition meeting a third preset condition from the city partition set, select a fourth city partition meeting a fourth preset condition from the city partition set, merge the third city partition and the fourth city partition, obtain the city partition set again, and repeatedly execute the selecting and merging processes until the area of each city partition in the city partition set is greater than a second preset threshold; the third preset condition is that the area is minimum and is smaller than a second preset threshold, and the fourth preset condition is that the public side length between the third preset condition and the third preset condition is that the public side length is longest and is adjacent to the third city subarea.
According to the device provided by the embodiment of the invention, the specified parameters are input into the preset model by acquiring the departure matrix and the arrival matrix corresponding to each city partition, and the preset type corresponding to each city partition is determined based on the output result of the preset model. The area type corresponding to the city subarea can be automatically determined based on the movement data of the user among different city subareas, so that the determination result is more accurate. In addition, because the time dimension is introduced when the area type corresponding to the urban subarea is determined, namely the area type corresponding to the urban subarea in different time periods can be determined for the same urban subarea, and the method is more suitable for practical application scenes.
Secondly, for any user, all travel sequences of any user in a preset time period are determined based on the urban subarea corresponding to each base station in the urban area and the base station moving sequence of any user in the preset time period. The signaling data can reflect the movement track of the user, so that the trip sequence of the user is determined by combining the base station movement sequence determined by the signaling data, the signaling data can be fully mined and utilized, and the accuracy of the subsequent determination of the urban subarea type can be improved.
Thirdly, determining the Thiessen polygon corresponding to each base station in the urban area. And determining the city partition covering each Thiessen polygon, and taking the city partition covering each Thiessen polygon as the city partition corresponding to each base station. The urban subareas covering the Thiessen polygons are the urban subareas closest to the base station in the Thiessen polygons, and the urban subareas covering the Thiessen polygons are used as the urban subareas corresponding to the departure place and the destination of the user, so that the accuracy in predicting the travel sequence can be improved, and the accuracy in subsequently determining the types of the urban subareas can be improved.
And then, for any user, sequencing each signaling data of the user according to the generation time of each signaling data to obtain a base station trip sequence of the user in a preset time period. And selecting a subsequence meeting a third preset condition from the base station trip sequence, and taking the subsequence as a base station moving sequence of any user in a preset time period. The subsequence of the user in the moving state can be selected from the base station trip sequence and used as the base station moving sequence, so that the user in the moving state in the time period corresponding to the base station moving sequence can be ensured, and the accuracy of the trip sequence can be improved when the trip sequence is determined based on the base station moving sequence subsequently.
In addition, an initial feature vector corresponding to each city partition is determined based on the number of each type of interest point in each city partition and the area of each city partition. And splicing the initial characteristic vectors corresponding to each city partition to obtain first matrixes corresponding to all the city partitions, and performing singular value decomposition on the first matrixes to obtain second matrixes. The feature vector corresponding to each city partition can be introduced into the designated parameters to determine the preset type of each city partition by combining the interest points in the city partitions, so that the determination result is more accurate.
And finally, combining the urban partitions in the urban partition set until the area of each urban partition in the urban partition set is larger than a second preset threshold value by the fact that the urban partitions with the areas smaller than the second preset threshold value exist in the urban partition set. Because the urban partitions with smaller areas in all the urban partitions can be merged, the subsequent statistical result is more obvious and more targeted.
The embodiment of the invention provides electronic equipment. Referring to fig. 8, the apparatus includes: a processor (processor)801, a memory (memory)802, and a bus 803;
the processor 801 and the memory 802 communicate with each other via a bus 803; the processor 801 is configured to call program instructions in the memory 802 to execute the region type determination method provided by the above embodiments, for example, including: acquiring a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to any urban subarea comprises the moving frequency of all users moving from any urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to any urban subarea comprises the moving frequency of all users moving from each other urban subarea to any urban subarea in the preset time period, and other urban subareas are urban subareas except any urban subarea in the urban area; inputting the designated parameters into a preset model, and determining a preset type corresponding to each urban partition based on an output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition.
An embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions cause a computer to execute the area type determination method provided in the foregoing embodiment, for example, the method includes: acquiring a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to any urban subarea comprises the moving frequency of all users moving from any urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to any urban subarea comprises the moving frequency of all users moving from each other urban subarea to any urban subarea in the preset time period, and other urban subareas are urban subareas except any urban subarea in the urban area; inputting the designated parameters into a preset model, and determining a preset type corresponding to each urban partition based on an output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the electronic device and the like are merely illustrative, and units illustrated as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the various embodiments or some parts of the methods of the embodiments.
Finally, the method of the present application is only a preferred embodiment and is not intended to limit the scope of the embodiments of the present invention. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims (16)

1. A method for determining a region type, comprising:
acquiring a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to the urban subarea comprises the moving frequency of all users moving from the urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to the urban subarea comprises the moving frequency of all users moving from the urban subarea to the urban subarea in the preset time period, and the other urban subareas are urban subareas except the urban subarea; any element in the departure matrix corresponding to any one city partition represents the moving frequency of the city partition moving to other corresponding city partitions within a corresponding preset time period; any element in the arrival matrix corresponding to any one city partition represents the moving frequency of moving from other corresponding city partitions to any one city partition in a corresponding preset time period;
inputting specified parameters into a preset model, and determining a preset type corresponding to each city partition based on an output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition;
before the obtaining of the departure matrix and the arrival matrix corresponding to each city partition, the method further includes:
for any user in all users, determining all travel sequences of the user in the preset time period based on the urban subarea corresponding to each base station in the urban area and the base station moving sequence of the user in the preset time period;
the base station moving sequence is determined based on signaling data generated by a mobile terminal, and the base station moving sequence at least comprises a user identification of any user, a base station identification as a starting place, a signaling data generation time corresponding to the base station as the starting place, a base station identification as a destination and a signaling data generation time corresponding to the base station as the destination.
2. The method of claim 1, wherein the obtaining the departure matrix corresponding to each city partition comprises:
for any city partition, acquiring a user departure matrix corresponding to each user; for any user in all the users, the user departure matrix corresponding to the user comprises the moving frequency of the user moving from the city partition to each other city partition within the preset time period;
and overlapping the user departure matrix corresponding to each user to obtain the departure matrix corresponding to any city partition.
3. The method of claim 1, wherein obtaining the arrival matrix corresponding to each city partition comprises:
for any city partition, acquiring a user arrival matrix corresponding to each user; for any user in all the users, the user arrival matrix corresponding to the user comprises the moving frequency of the user moving from each other urban subarea to the urban subarea in the preset time period;
and superposing the user arrival matrix corresponding to each user to obtain the arrival matrix corresponding to any city partition.
4. The method of claim 2, wherein the obtaining the user departure matrix corresponding to each user comprises:
for any user, determining a travel sequence meeting a first preset condition from all travel sequences of the user in the preset time period; the first preset condition is that each travel sequence corresponds to a moving frequency by taking any one city partition as a starting place and taking other city partitions as destinations;
and determining a user departure matrix corresponding to any user according to the travel sequence meeting the first preset condition.
5. The method of claim 3, wherein the obtaining the user arrival matrix corresponding to each user comprises:
for any user, determining a travel sequence meeting a second preset condition from all travel sequences of the user in the preset time period; the second preset condition is that the other city partitions are taken as departure places and any one of the city partitions is taken as a destination, and each travel sequence corresponds to a moving frequency;
and determining a user arrival matrix corresponding to any user according to the travel sequence meeting the second preset condition.
6. The method of claim 1, wherein the determining, based on the urban partition corresponding to each base station in the urban area and the base station movement sequence of the any user in the preset time period, all the travel sequences of the any user in the preset time period before, further comprises:
determining a Thiessen polygon corresponding to each base station in the urban area, wherein each Thiessen polygon comprises one base station;
and determining the city partition covering each Thiessen polygon, and taking the city partition covering each Thiessen polygon as the city partition corresponding to each base station.
7. The method of claim 1, wherein the determining, based on the urban partition corresponding to each base station in the urban area and the base station movement sequence of the any user in the preset time period, all the travel sequences of the any user in the preset time period before, further comprises:
for any user, sequencing each signaling data of any user in sequence according to the generation time of each signaling data to obtain a base station trip sequence of any user in the preset time period;
selecting a subsequence meeting a third preset condition from the base station trip sequence, and taking the subsequence as a base station moving sequence of any user in the preset time period;
the third preset condition is that the difference between the generation moments corresponding to any two adjacent signaling data is smaller than a first preset threshold value and the user moving speed is within a preset range.
8. The method of claim 1, wherein the determining all travel sequences of the any user in the preset time period based on the city partition corresponding to each base station in the urban area and the base station movement sequence of the any user in the preset time period comprises:
randomly combining the first city partition and the second city partition to obtain all travel sequences of any user in the preset time period; the first city partition is a city partition corresponding to a base station serving as a starting place in the base station moving sequence, and the second city partition is a city partition corresponding to a base station serving as a destination in the base station moving sequence.
9. The method according to claim 6, wherein after determining all travel sequences of any user within the preset time period based on the city partition corresponding to each base station within the urban area and the base station movement sequence of any user within the preset time period, the method further comprises:
for any row sequence, calculating a first area ratio between a first part of Thiessen polygons and a first urban subarea, calculating a second area ratio between a second part of Thiessen polygons and a second urban subarea, and taking the product of the first area ratio and the second area ratio as the moving frequency corresponding to the any row sequence;
the first city partition is a city partition which is taken as a starting place in any one travel sequence, and the second city partition is a city partition which is taken as a destination in any one travel sequence; the first partial Thiessen polygon is a partial Thiessen polygon contained in the first city zone, and the second partial Thiessen polygon is a partial Thiessen polygon contained in the second city zone.
10. The method of claim 1, wherein the specified parameters further comprise a feature vector corresponding to each city partition; and determining the feature vector corresponding to each city partition by the interest points in each city partition.
11. The method of claim 10, wherein before inputting the specified parameters into the preset model, further comprising:
and determining a feature vector corresponding to each urban partition based on the number of the interest points of each type in each urban partition and the area of each urban partition.
12. The method of claim 1, wherein before obtaining the departure matrix and the arrival matrix corresponding to each city partition, further comprising:
if the urban partitions with the areas smaller than a second preset threshold exist in the urban partition set, merging the urban partitions in the urban partition set until the area of each urban partition in the urban partition set is larger than the second preset threshold;
the urban subarea set comprises a plurality of urban subareas obtained by dividing the urban area based on road network data.
13. The method of claim 12, wherein the merging the civic partitions in the set of civic partitions until the area of each civic partition in the set of civic partitions is greater than the second preset threshold comprises:
selecting a third city partition meeting a third preset condition from the city partition set, selecting a fourth city partition meeting a fourth preset condition from the city partition set, merging the third city partition and the fourth city partition to obtain the city partition set again, and repeatedly executing the selecting and merging processes until the area of each city partition in the city partition set is larger than a second preset threshold;
the third preset condition is that the area is minimum and is smaller than the second preset threshold, and the fourth preset condition is that the public side length between the third preset condition and the third city partition is longest and is adjacent to the third city partition.
14. An area type determination apparatus, comprising:
the acquisition module is used for acquiring a departure matrix and an arrival matrix corresponding to each city partition; the urban subareas are obtained by dividing urban areas; for any urban subarea in the urban area, the departure matrix corresponding to the urban subarea comprises the moving frequency of all users moving from the urban subarea to each other urban subarea in a preset time period, the arrival matrix corresponding to the urban subarea comprises the moving frequency of all users moving from the urban subarea to the urban subarea in the preset time period, and the other urban subareas are urban subareas except the urban subarea; any element in the departure matrix corresponding to any one city partition represents the moving frequency of the city partition moving to other corresponding city partitions within a corresponding preset time period; any element in the arrival matrix corresponding to any one city partition represents the moving frequency of moving from other corresponding city partitions to any one city partition in a corresponding preset time period;
the first determination module is used for inputting the designated parameters into a preset model and determining the preset type corresponding to each city partition based on the output result of the preset model; the designated parameters at least comprise a preset type total number, a departure matrix and an arrival matrix corresponding to each city partition;
the device further comprises:
a second determining module, configured to determine, for any user of the all users, all trip sequences of the any user in the preset time period based on a city partition corresponding to each base station in the urban area and a base station moving sequence of the any user in the preset time period;
the base station moving sequence is determined based on signaling data generated by a mobile terminal, and the base station moving sequence at least comprises a user identification of any user, a base station identification as a starting place, a signaling data generation time corresponding to the base station as the starting place, a base station identification as a destination and a signaling data generation time corresponding to the base station as the destination.
15. An electronic device, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 13.
16. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 13.
CN201810661463.0A 2018-06-25 2018-06-25 Region type determination method and device Active CN108875032B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810661463.0A CN108875032B (en) 2018-06-25 2018-06-25 Region type determination method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810661463.0A CN108875032B (en) 2018-06-25 2018-06-25 Region type determination method and device

Publications (2)

Publication Number Publication Date
CN108875032A CN108875032A (en) 2018-11-23
CN108875032B true CN108875032B (en) 2022-02-25

Family

ID=64294663

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810661463.0A Active CN108875032B (en) 2018-06-25 2018-06-25 Region type determination method and device

Country Status (1)

Country Link
CN (1) CN108875032B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110442662B (en) * 2019-07-08 2022-05-20 清华大学 Method for determining user attribute information and information push method
CN110866156B (en) * 2019-11-26 2022-05-17 北京明略软件系统有限公司 Method, device, equipment and medium for identifying functional park based on social data
CN111738624B (en) * 2020-07-20 2020-11-13 武大吉奥信息技术有限公司 Region division method and system for solving supply and demand relation balance

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996068A (en) * 2014-05-08 2014-08-20 百度在线网络技术（北京）有限公司 Statistical method and device for passenger flow distribution
CN106681996A (en) * 2015-11-05 2017-05-17 腾讯科技（深圳）有限公司 Method and device for determining interest areas and interest points within geographical scope
CN106991142A (en) * 2017-03-22 2017-07-28 湖州师范学院 A kind of method that urban function region is recognized based on wechat data and interest point data

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011142225A1 (en) * 2010-05-12 2011-11-17 日本電気株式会社 Feature-point detection system, feature-point detection method, and program

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996068A (en) * 2014-05-08 2014-08-20 百度在线网络技术（北京）有限公司 Statistical method and device for passenger flow distribution
CN106681996A (en) * 2015-11-05 2017-05-17 腾讯科技（深圳）有限公司 Method and device for determining interest areas and interest points within geographical scope
CN106991142A (en) * 2017-03-22 2017-07-28 湖州师范学院 A kind of method that urban function region is recognized based on wechat data and interest point data

Also Published As

Publication number Publication date
CN108875032A (en) 2018-11-23

Similar Documents

Publication Publication Date Title
Gurumurthy et al. Analyzing the dynamic ride-sharing potential for shared autonomous vehicle fleets using cellphone data from Orlando, Florida
Hwang et al. An effective taxi recommender system based on a spatio-temporal factor analysis model
Offenhuber et al. Decoding the city: Urbanism in the age of big data
Ben-Akiva et al. Discrete choice methods and their applications to short term travel decisions
Ghaemi et al. A visual segmentation method for temporal smart card data
Conway et al. Accounting for uncertainty and variation in accessibility metrics for public transport sketch planning
US20140089036A1 (en) Dynamic city zoning for understanding passenger travel demand
CN111612122B (en) Real-time demand prediction method and device and electronic equipment
CN108875032B (en) Region type determination method and device
Goetz et al. OpenStreetMap in 3D–detailed insights on the current situation in Germany
JP7175783B2 (en) Program, device and method for estimating stay area population in predetermined area
Montero et al. Fusing mobile phone data with other data sources to generate input OD matrices for transport models
CN107861957B (en) Data analysis method and device
Sim et al. Great cities look small
Tan et al. Development of an inexact fuzzy robust programming model for integrated evacuation management under uncertainty
WO2020086336A1 (en) Space utilization measurement and modeling using artificial intelligence
Cvijovic et al. Conditional transit signal priority for connected transit vehicles
Zhang et al. An optimization model for guiding pedestrian–vehicle mixed flows during an emergency evacuation
Horn et al. QZTool—automatically generated origin-destination matrices from cell phone trajectories
Tiwari et al. Information enrichment for tourist spot recommender system using location aware crowdsourcing
EP3192061B1 (en) Measuring and diagnosing noise in urban environment
Raghothama et al. Analytics on public transport delays with spatial big data
Moreira-Matias et al. An online recommendation system for the taxi stand choice problem (Poster)
Pelekis et al. Simulating our LifeSteps by example
Robbennolt et al. Microsimulation study evaluating the benefits of cyclic and non-cyclic max-pressure control of signalized intersections

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