Disclosure of Invention
In order to solve the above prior art problems, the invention provides a method, a device and a storage medium for generating an individual travel chain, which have the following technical scheme:
an individual travel chain generation method, comprising:
Acquiring multi-source data information about a target city from a plurality of sources;
Sample expansion is carried out on the multi-source data information to generate an individual commute data set, wherein the individual commute data set comprises the commute data of a plurality of individuals in a target city, and the commute data of one individual at least comprises the commute mode and the commute information of the individual, and the commute information comprises the commute starting point information, the commute end point information, the departure time information and the arrival time information;
Constructing a multi-mode traffic network of the target city according to the subset of the commuting modes in the individual commuting data set;
carrying out traffic simulation on the individual commute data set in a multi-mode traffic network to generate an individual travel chain, wherein the method specifically comprises the following steps of:
Acquiring a commute mode of at least one individual in a target city, and a traffic network corresponding to the commute mode;
Acquiring the commute information of the individual;
Carrying out traffic simulation on the individual commute information on a multi-mode traffic network to obtain a path with the shortest time consumption as the individual commute path;
And generating an individual trip chain corresponding to the individual according to the individual commute data set and the commute path.
In one embodiment, the multi-source data information includes at least cell phone signaling data, traffic swipe data, resident survey data, and census data; and/or
The commuting modes at least comprise a track commuting mode, a bus commuting mode, a driving commuting mode and a walking commuting mode.
In one embodiment, sample expansion is performed according to multi-source data information to generate an individual commute data set, comprising:
determining commute information according to the mobile phone signaling data;
sample expansion is carried out on the multi-source data information and the commute information, and track commute data corresponding to the track commute mode is generated;
sample expansion is carried out on the multi-source data information and the commute information, and bus commute data corresponding to a public traffic mode is generated;
Judging whether the individual is a non-public traffic individual according to the track commute data corresponding to the track commute mode and the bus commute data corresponding to the bus commute mode, if so, determining that the individual is a driving commute individual or a non-driving commute individual according to the commute information and resident investigation data;
if the individual is a driving commute individual, driving commute data corresponding to the driving commute mode is generated according to the commute information; or (b)
If the individual is a non-driving commute individual, generating walking commute data corresponding to the walking commute mode according to the commute information.
In one embodiment, determining the commute information from the handset signaling data includes:
acquiring at least one individual track point set of a target city according to mobile phone signaling data, wherein the track point set comprises a plurality of track points and residence time corresponding to each track point;
calculating the distance and the stay time between each group of adjacent track points in the track point set to obtain the distance between the adjacent track points and the stay time of the adjacent track points;
comparing the distance between adjacent track points with a preset distance, comparing the stay time of the adjacent track points with a preset duration, and taking the corresponding adjacent track points as stay positions if the distance between the adjacent track points is smaller than the preset distance and the stay time of the adjacent track points is longer than the preset duration;
Obtaining a stay position sequence of at least one individual in the target city according to the stay positions, wherein the stay position sequence comprises a plurality of stay positions and corresponding stay times;
The commute information is determined from the sequence of stay locations.
In one embodiment, sample spreading is performed on the multi-source data information and the commute information, and generating the track commute data corresponding to the track commute mode includes:
Judging whether at least one individual in the target city is a track commuting individual according to the traffic card swiping data, wherein the track commuting individual comprises a whole-course track commuting individual or a track bus transfer commuting individual;
If the traffic card is a rail commute individual, determining a commute station corresponding to the individual according to traffic card swiping data;
Counting a first trip amount between a starting point and a destination according to a commuting station of the track commuting individual;
Counting a second trip amount between the starting point and the end point according to the traffic card swiping data;
Calculating the ratio of the second trip amount to the first trip amount to obtain a first sample expansion coefficient;
And carrying out sample expansion on the track commute individuals according to the first sample expansion coefficient, and generating track commute data corresponding to the track commute mode by combining the commute information.
In one embodiment, sample expansion is performed on multi-source data information and commute information, and generating bus commute data corresponding to a public traffic mode includes:
Judging whether at least one individual in the target city is a public traffic commute individual according to the mobile phone signaling data, the traffic card swiping data, the resident investigation data and the population census data, wherein the public traffic commute individual comprises a public traffic commute individual, a rail public traffic transfer commute individual and a transfer public traffic commute individual;
if the public traffic service individuals are public traffic service individuals, passenger flows of the public traffic lines corresponding to the individuals are calculated according to traffic card swiping data:
Wherein,For the number of the first public traffic service individuals, p is the second sample expansion coefficient,/>For the number of rail transit commuting individuals,/>For the number of transfer traffic service individuals, the second sample spreading coefficient is:
And (3) carrying out sample expansion on the bus commuting individuals, the rail bus transfer commuting individuals and the transfer public traffic commuting individuals according to the second sample expansion coefficient, and generating bus commuting data corresponding to the public traffic commuting mode by combining the commuting information.
In one embodiment, the resident survey data includes a car trip proportion;
determining that the individual is a driving commute individual or a non-driving commute individual based on the commute information and resident survey data comprises:
calculating a commute distance of at least one non-public traffic commute individual based on the commute information;
Determining a commute distance segment in which at least one non-public communication commute individual is located according to the commute distance;
Calculating driving commute individuals with segmented commute distances according to the travel proportion of the car;
and removing the driving commuter from the non-public traffic commuter to obtain the non-driving commuter.
In one embodiment, if the individual is a non-driving commute individual, walking commute data corresponding to the walking commute mode is generated based on the commute information:
screening out individuals with the commuting distance smaller than a preset distance from the non-driving commuting individuals to obtain walking commuting individuals;
And generating walking commute data corresponding to the walking commute mode according to the walking commute individuals and the commute information.
An individual travel chain generation device, comprising:
the acquisition module is used for acquiring multi-source data information of the target city from a plurality of sources;
The sample spreading module is used for spreading the multi-source data information to generate an individual commute data set, wherein the individual commute data set comprises the commute data of a plurality of individuals in a target city, and the commute data of one individual at least comprises the commute mode and the commute information of the individual, and the commute information comprises the commute starting point information, the commute end point information, the departure time information and the arrival time information;
The network construction module is used for constructing a multi-mode traffic network of the target city according to the commute mode subsets in the individual commute data sets;
The trip chain generation module is used for carrying out traffic simulation on the individual commute data set in the multi-mode traffic network to generate an individual trip chain, and comprises the following steps: acquiring a commute mode of at least one individual in a target city, and a traffic network corresponding to the commute mode; acquiring the commute information of the individual; carrying out traffic simulation on the individual commute information on a multi-mode traffic network to obtain a path with the shortest time consumption as the individual commute path; and generating an individual trip chain corresponding to the individual according to the individual commute data set and the commute path.
A computer readable storage medium having a computer program stored therein, the computer program when executed by a processor implementing the individual travel chain generation method of any one of the above.
The method has the advantages that the individual commute data sets comprising the commute modes and the commute information of a plurality of individuals in the target city are generated by sample expansion according to the multi-source data information of the target city, the multi-mode traffic network of the target city is constructed based on the commute modes, the individual commute data sets are subjected to traffic simulation in the multi-mode traffic network to obtain time-consuming shortest paths as the commute paths of the individuals, so that individual travel chains are generated according to the individual commute data and the commute paths, the individual travel chain reduction applied to the whole urban traffic scene is realized, and meanwhile, compared with the statistical sample expansion errors according to the mobile phone signaling data, the statistical sample expansion based on the multi-source data information is smaller, and the accuracy and the reliability of the individual travel chains are improved.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Fig. 1 shows a flowchart of an individual travel chain generation method according to an embodiment of the present application. As shown in fig. 1, the individual travel chain generation method may include:
s101, multi-source data information about a target city is acquired from a plurality of sources.
The multi-source data information of the target city is various big data related to the target city. It can be understood that the target city is a city object for generating an individual travel chain according to the embodiment of the present application.
It will be appreciated that data received from clients, such as RFID data, sensor data, user behavior data, social network interaction data, and various types of structured, semi-structured, and unstructured mass data within a target city, may be received via multiple databases or storage systems.
S102, sample expansion is carried out according to the multi-source data information, and an individual commute data set is generated.
The individual commute data set comprises the commute data of a plurality of individuals in a target city, wherein the commute data of one individual at least comprises the commute mode and the commute information of the individual, and the commute information comprises the commute starting point information, the commute ending point information, the departure time information and the arrival time information.
It can be understood that in the existing individual travel chain generation method based on mobile phone signaling data, when the individual travel chain is restored, the travel track including the track among the starting point, the route site, the end point and at least one point is identified according to the mobile phone signaling data, so that the individual travel chain is restored. However, the individual travel chain generation method based on the mobile phone signaling data needs to clean the mobile phone signaling data identified by a plurality of base stations, and requires higher-precision mobile phone signaling data, so that the data processing difficulty at transfer sites of a plurality of lines is higher; meanwhile, the individual travel chain generation method needs to segment travel tracks of corresponding passes of travelers, a connection mode of the travelers is obtained through recognition, and bus/subway matching in the individual travel chain generated when bus/subway departure intervals are relatively close can be problematic. Therefore, the error is large when the statistical sample expansion is performed according to the mobile phone signaling data, so that the individual trip chain recovery result is unreliable. Based on the above, in the embodiment of the application, the statistical sample expansion is performed according to the multi-source data information of the target city acquired in the step S101, and compared with the statistical sample expansion error according to the mobile phone signaling data, the statistical sample expansion error is smaller, so that the accuracy and the reliability of the individual trip chain are improved.
Optionally, in some embodiments, when generating the commute mode and the commute information of the plurality of individuals in the target city by sample spreading according to the multi-source data information, the living individual is first determined in at least one individual in the target city, and then the commute mode and the commute information of the at least one living individual are generated by sample spreading according to the multi-source data information. Alternatively, an individual whose stay number exceeds a preset number of days in the target city within a preset time range is considered a surviving individual, such as an individual whose stay number exceeds 21 days in the target city within one month is considered a surviving individual.
Optionally, in some embodiments, the multi-source data information includes at least cell phone signaling data, traffic swipe data, resident survey data, and census data, and the commuting mode includes at least a track commuting mode, a bus commuting mode, a driving commuting mode, and a walking commuting mode. Step S102, when sample expansion is performed according to multi-source data information to generate an individual commute data set, needs to identify at least one individual commute mode of a target city, and then generates individual commute data corresponding to the at least one commute mode respectively, and specifically comprises the following steps S1021-S1027:
step S1021, determining commute information according to the mobile phone signaling data.
It will be appreciated that the handset signalling data is communication data between the handset user and the communications base station. When the mobile phone of the mobile phone user is started and the service of the operator is started, mobile phone signaling data are generated. In the process of using the mobile phone, the mobile phone can be in communication relation with a nearby communication base station, and the position of the communication base station reflects the position of the user because the position of the communication base station is fixed and known, namely the field of the mobile phone signaling data always has time and position information. According to the embodiment of the application, at least one individual track point of a target city is obtained according to time and position information in mobile phone signaling data, and a commute starting point and a commute ending point as well as corresponding departure time and arrival time are identified from each track point.
Optionally, in some embodiments, step S1021 specifically includes:
1) Acquiring at least one individual track point set of a target city according to mobile phone signaling data, wherein the track point set comprises a plurality of track points and residence time corresponding to each track point;
2) Calculating the distance and the stay time between each group of adjacent track points in the track point set to obtain the distance between the adjacent track points and the stay time of the adjacent track points;
3) Comparing the distance between adjacent track points with a preset distance, comparing the stay time of the adjacent track points with a preset duration, and taking the corresponding adjacent track points as stay positions if the distance between the adjacent track points is smaller than the preset distance and the stay time of the adjacent track points is longer than the preset duration;
4) Obtaining a stay position sequence of at least one individual in the target city according to the stay positions, wherein the stay position sequence comprises a plurality of stay positions and corresponding stay times;
5) The commute information is determined from the sequence of stay locations.
Optionally, the preset distance is 500m, and the preset time period is 30min. In some embodiments of the present application, the distance between each group of adjacent track points in the track point set is less than 500m, and the adjacent track points with the total stay time longer than 30min are used as stay positions, so as to obtain at least one individual stay position sequence of the target city.
Alternatively, in some embodiments, two dwell positions are combined if the time interval between the two dwell positions is less than a predetermined time (e.g., 30 minutes) and the distance is less than a predetermined distance (e.g., 500 m).
It can be understood that at least one dwell position in the dwell position sequence generated by the embodiment of the application is the position of the communication base station.
Specifically, in the step of determining the commute information from the sequence of stay positions, it is necessary to identify a commute start point and a commute end point from at least one stay position of the sequence of stay positions and determine the commute information in combination with the corresponding departure time and arrival time.
Optionally, in some embodiments, the home period and the working day period are preset, the stay position with the largest occurrence number of the at least one individual in the home period is taken as a commute starting point of the corresponding individual, and the stay position with the largest occurrence number of the at least one individual in the working day period is taken as a commute end point of the corresponding individual, so that the commute information is determined by combining the time information corresponding to the commute starting point and the time information corresponding to the commute end point.
Optionally, in some embodiments, the home period and the working day working period are preset, the stay position with the largest occurrence number of at least one individual in the home period is taken as the commuting start point of the corresponding individual, the stay position with the largest occurrence number of at least one individual in the working day working period is taken as the candidate commuting end point of the corresponding individual, and if the total stay time of the individual in the preset range (such as 500 m) of the candidate commuting end point exceeds the preset working time (such as 3 h), the working day of the individual is counted. If the number of days of the working day of the individual exceeds a preset number of days (e.g., 3 days) within a week, the candidate commute endpoint is determined as a commute endpoint, and the commute information is determined in combination with the commute start point, the time information corresponding to the commute start point, and the time information corresponding to the commute endpoint.
Optionally, in some embodiments, the preset household period is 21:00 to 7:00 the next day, and the preset workday working period is 9:00-17:00 from monday to friday.
Optionally, in some embodiments, the primary activity area of the at least one individual is obtained from a sequence of stay locations of the at least one individual, and the at least one individual's home period and work day work period are preset according to the primary activity area. It will be appreciated that when at least one individual is provided with the same home period and work day work period, the individual's commute information for a portion of the particular work mode (e.g., a diurnal reverse work mode, a work mode without a stationary job, etc.) cannot be accurately identified. For this reason, some embodiments of the present application acquire a main activity area of at least one individual according to the stay location sequence, and preset a home period and a working day working period of at least one individual according to the main activity area, thereby improving the accuracy and reliability of the determined commute information.
Step S1022, sample expansion is carried out according to the multi-source data information and the commute information, and track commute data corresponding to the track commute mode is generated.
Specifically, firstly, track commuting individuals are screened out from a plurality of individuals in a target city according to multi-source data information, then, the track commuting individuals are subjected to statistics sample expansion based on the multi-source data information, and track commuting data corresponding to a track commuting mode are generated by combining the commuting information.
Optionally, in some embodiments, step S1022 specifically includes:
1) And determining a track commuting individual according to the mobile phone signaling data, wherein the track commuting individual comprises a whole-course track commuting individual and a track bus transfer commuting individual.
It is understood that the whole-course rail commuting individual is an individual which performs commuting through a rail in the whole course, and the rail bus transfer commuting individual is an individual which performs commuting through a rail transfer bus or a bus transfer rail, namely, a bus path is included in the commuting path of the rail bus transfer commuting individual.
Optionally, in some embodiments, a dwell position sequence is determined from the handset signaling data (the same step as the step of determining the dwell position sequence of step S1021), and then an individual commute simulation trajectory is generated from the dwell position sequence; extracting an individual track commuting track according to the individual commuting simulation track and the base station information corresponding to the track station; if the track in the preset early peak time period (such as 6:00-10:00) exists in the track commute track of the individual, counting the track commute day of the individual as the day; if the number of days of the individual's orbital commute day exceeds a preset number of days, e.g., the number of days of the individual's orbital commute day exceeds 11 days in a month, then the individual is considered an orbital commute individual.
2) A commute site of the rail commute individual is determined from the commute information.
Wherein the commute site includes a departure site and an arrival site. It will be appreciated that the commute information includes commute start point information from which a departure station can be determined and commute end point information from which an arrival station can be determined.
3) And counting the first travel amount between the starting point and the end point according to the commuting stations of the rail commuting individuals.
4) And counting a second trip amount between the starting point and the end point according to the traffic card swiping data.
5) And calculating the ratio of the second trip amount to the first trip amount to obtain a first sample expansion coefficient.
6) And carrying out sample expansion on the track commute individuals according to the first sample expansion coefficient, and generating track individual commute data corresponding to the track commute mode by combining the commute information.
It is noted that when the rail commuter is subjected to sample expansion according to the first sample expansion coefficient, the whole-course rail commuter and the rail bus transfer commuter are subjected to sample expansion by adopting the first sample expansion coefficient.
Step S1023, sample expansion is carried out according to the multi-source data information and the commute information, and bus commute data corresponding to the public traffic mode is generated.
Specifically, public traffic service individuals are screened out from a plurality of individuals in a target city according to multi-source data information, then statistical sample expansion is carried out on the public traffic service individuals based on the multi-source data information, and public traffic service data corresponding to the public traffic service mode is generated by combining the traffic service information.
Optionally, in some embodiments, step S1023 specifically includes:
1) And determining public traffic service individuals according to the mobile phone signaling data, the resident investigation data and the population census data, wherein the public traffic service individuals comprise primary public traffic service individuals, rail public traffic transfer service individuals and transfer public traffic service individuals.
It can be understood that a public transportation service individual is an individual taking only one bus on one commuting path, and a rail bus transfer commuting individual is an individual taking rail transfer bus on one commuting path, and a transfer public transportation service individual is an individual taking bus transfer bus on one commuting path.
2) And counting the passenger flow of the bus line according to the traffic card swiping data.
It is understood that the bus line passenger flow is equal to the number of all the individuals taking buses, and the number of the individuals taking buses comprises three parts of the number of one public traffic service individuals, the number of transfer public traffic service individuals and the number of rail bus transfer commute individuals. Namely bus line passenger flow:
Wherein,For the number of individuals on a public transportation service/>For the second sample expansion coefficient,/>For the number of rail transit commuting individuals,/>To transfer the number of public traffic service individuals.
3) And calculating according to the bus line passenger flow, the bus commuter, the rail bus transfer commuter and the transfer public traffic commuter to obtain a second sample expansion coefficient.
It will be appreciated that the second sample expansion coefficient:
4) And (3) carrying out sample expansion on the bus commuting individuals, the rail bus transfer commuting individuals and the transfer public traffic commuting individuals according to the second sample expansion coefficient, and generating bus commuting data corresponding to the public traffic commuting mode by combining the commuting information.
Step S1024, judging whether the individual is a non-public traffic individual according to the track commute data corresponding to the track commute mode and the bus commute data corresponding to the bus commute mode;
It will be appreciated that the non-public traffic commute individuals may be obtained by removing the track commute individuals and the bus commute individuals from the plurality of individuals within the target city.
Step S1025, determining that the individual is a driving commuter or a non-driving commuter according to the commuter information and resident investigation data.
It will be appreciated that non-public traffic commutes include driving commutes and non-driving commutes, and that driving commutes may be determined based on resident survey data.
Optionally, in some embodiments, the resident survey data includes a car trip ratio, and step S1025 includes:
1) A commute distance of at least one non-public communication commute individual is calculated from the commute information.
2) A commute distance segment at which at least one non-public commute individual is located is determined based on the commute distance.
Optionally, the commute distance segments include four segments of 0-1km, 1-2km, 2-3km, and > 3 km.
3) And calculating driving commute individuals with segmented commute distances according to the car trip proportion.
4) And removing the driving commuter from the non-public traffic commuter to obtain the non-driving commuter.
And step S1026, generating driving commute data corresponding to the driving commute mode according to the driving commute individuals and the commute information.
It can be understood that, according to the driving commute individuals obtained in step S1025, driving commute data corresponding to the driving commute mode can be generated by combining the commute information of at least one driving commute individual.
Step S1027, generating walking commute data corresponding to the walking commute mode according to the non-driving commute individuals and the commute information.
Wherein the non-driving commuter is not necessarily all the walking commuter. Therefore, according to the embodiment of the application, the walking commute individuals in the non-driving commute individuals are screened out according to the commute distance, and then the walking commute data corresponding to the walking commute mode can be generated according to the walking commute individuals and the corresponding commute information.
Optionally, in some embodiments, step S1027 specifically includes:
1) Screening out individuals with the commuting distance smaller than a preset distance from the non-driving commuting individuals to obtain walking commuting individuals;
2) And generating walking commute data corresponding to the walking commute mode according to the walking commute individuals and the commute information.
Optionally, the preset distance is 2km.
S103, constructing a multi-mode traffic network of the target city according to the subset of the commuting modes in the individual commuting data set.
Wherein the multi-mode traffic network comprises a traffic network corresponding to the commute mode. Optionally, the commuting mode includes a track commuting mode, a bus commuting mode, a driving commuting mode, and a walking commuting mode, and the multi-mode traffic network includes a track network, a bus network, a driving network, and a walking network.
Optionally, in some embodiments, when the multimode traffic network of the target city is constructed, a mutual influence relationship (network sharing) exists between the public traffic network and the driving network, the public traffic network and the track network do not influence each other (network sharing), as shown in fig. 2, since the public traffic network and the car run on the road traffic network, the public traffic network and the car mutually influence each other and share the network traffic, the two track traffic networks are relatively independent, and do not share the network traffic with the public traffic network and the driving network. Based on individual travel demands of different modes, multi-mode traffic distribution is carried out, and the road traffic distributed by the car is assumed to influence the road running speed, so that the running time of the bus is further influenced, and when the overall traffic flow reaches a user equilibrium mode or the maximum iteration number, the multi-mode traffic distribution algorithm stops.
S104, carrying out traffic simulation on the individual commute data set in the multi-mode traffic network to generate an individual travel chain.
The method comprises the steps of obtaining a commuting mode of at least one individual in a target city, and obtaining a traffic network corresponding to the commuting mode; acquiring the commute information of the individual; carrying out traffic simulation on the individual commute information on a multi-mode traffic network to obtain a path with the shortest time consumption as the individual commute path; and generating an individual trip chain corresponding to the individual according to the individual commute data set and the commute path.
Optionally, in some embodiments, referring to fig. 2, traffic simulation is performed on the multi-mode traffic network according to the individual commute data, if the individual commute mode is a driving commute mode, the interaction relationship between the driving network and the public transportation network is considered, the distribution of the commute path is performed in combination with the driving network and the road running speed, and the commute path is output after the traffic simulation converges; if the individual commuting mode is a public traffic commuting mode (a public traffic commuting mode and a track commuting mode), the corresponding public traffic network (a public traffic network or a track network) is combined to distribute the commuting paths, wherein the public traffic commuting mode also needs to consider the mutual influence relationship between a driving network and the public traffic network, the public traffic network and the road running speed are combined to distribute the commuting paths, and the traffic simulation converges and then the commuting paths are output.
Optionally, in some embodiments, the navigation map based API simulates a time-consuming shortest path on the target traffic network as the commute path of at least one individual of the target city according to the commute start point, the commute end point, the departure time, and the arrival time, respectively.
Optionally, in some embodiments, based on an iterative balanced allocation (MSA) algorithm, simulating on the target traffic network a time-consuming shortest path as a commute path for at least one individual of the target city according to the commute start point, the commute end point, the departure time and the arrival time, comprising in particular the steps of:
1) The preset iteration times are ns, and traffic volumes corresponding to the individual commute data are equally divided into ns;
2) In the iterative process n, distributing each traffic to a candidate time-consuming shortest path in a corresponding target traffic network;
3) In the iteration process n, after traffic distribution is completed, acquiring traffic distribution conditions of the multi-mode traffic network, loading traffic according to the traffic distribution conditions, acquiring running time of each road section of the multi-mode traffic network and delay of intersections, and updating impedance of each road section;
4) In the iterative process n+1, distributing each traffic volume to a candidate time-consuming shortest path in a corresponding target traffic network according to the updated impedance of each road section of the multi-mode traffic network again, acquiring traffic volume distribution conditions of the multi-mode traffic network after completing traffic volume distribution, loading traffic flow according to the traffic volume distribution conditions, acquiring running time and intersection delay of each road section of the multi-mode traffic network, and updating the impedance of each road section;
5) And (3) iterating circularly until the iteration times reach the maximum iteration times ns, and at the moment, completing path distribution of all traffic volumes to obtain at least one individual commute path of the target city.
Optionally, in some embodiments, after the individual travel chain of the target city is generated in step S104, the individual travel chain is checked by using the traffic card swiping data, parameters of the multi-mode traffic network are adjusted according to the check result, and traffic simulation is performed on the multi-mode traffic network according to the individual commute data to generate the individual travel chain, so that accuracy and reliability of the individual travel chain are further improved.
In summary, in the steps S101 to S104 of the embodiment of the present application, the sample is expanded according to the multi-source data information of the target city, the individual commute data set including the commute mode and the commute information of a plurality of individuals in the target city is generated, the multi-mode traffic network of the target city is constructed based on the commute mode, and the individual commute data set is subjected to traffic simulation in the multi-mode traffic network to obtain the shortest time-consuming path as the commute path of each individual, so that the individual travel chain is generated according to the individual commute data and the commute path, the individual travel chain reduction applied to the whole urban traffic scene is realized, and meanwhile, compared with the statistical sample expansion error according to the mobile phone signaling data, the statistical sample expansion based on the multi-source data information is smaller, and the accuracy and reliability of the individual travel chain are improved.
Fig. 3 shows a block diagram of the structure of the individual travel chain generation device according to the embodiment of the present application. As shown in fig. 3, the apparatus may include:
An acquisition module 301, configured to acquire multi-source data information of a target city from multiple sources;
The sample spreading module 302 is configured to perform sample spreading on the multi-source data information to generate an individual commute data set, where the individual commute data set includes commute data of a plurality of individuals in the target city, and the commute data of one individual includes at least a commute mode and commute information of the individual, and the commute information includes commute start point information, commute end point information, departure time information and arrival time information;
A network construction module 303, configured to construct a multi-mode traffic network of the target city according to the subset of commute modes in the individual commute data set;
The trip chain generation module 304 is configured to perform traffic simulation on the individual commute data set in the multi-mode traffic network, and generate an individual trip chain, which includes: acquiring a commute mode of at least one individual in a target city, and a traffic network corresponding to the commute mode; acquiring the commute information of the individual; carrying out traffic simulation on the individual commute information on a multi-mode traffic network to obtain a path with the shortest time consumption as the individual commute path; and generating an individual trip chain corresponding to the individual according to the individual commute data set and the commute path.
The functions of each module in each device of the embodiments of the present invention may be referred to the corresponding descriptions in the above methods, which are not described herein.
Fig. 4 shows a block diagram of the structure of an individual travel chain generation device according to an embodiment of the present invention. As shown in fig. 4, the individual travel chain generation apparatus includes: memory 410 and processor 420, memory 410 stores a computer program executable on processor 420. The processor 420, when executing the computer program, implements the individual travel chain generation method in the above-described embodiment. The number of memories 410 and processors 420 may be one or more.
The individual travel chain generation device further includes:
And the communication interface 430 is used for communicating with external equipment and carrying out data interaction transmission.
If the memory 410, the processor 420, and the communication interface 430 are implemented independently, the memory 410, the processor 420, and the communication interface 430 may be connected to each other and communicate with each other through buses. The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, peripheral interconnect (Peripheral ComponentInterconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 410, the processor 420, and the communication interface 430 are integrated on a chip, the memory 410, the processor 420, and the communication interface 430 may communicate with each other through internal interfaces.
The embodiment of the application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the method provided in the embodiment of the application.
The embodiment of the application also provides a chip, which comprises a processor and is used for calling the instructions stored in the memory from the memory and running the instructions stored in the memory, so that the communication equipment provided with the chip executes the method provided by the embodiment of the application.
The embodiment of the application also provides a chip, which comprises: the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method provided by the application embodiment.
It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processor, digital signal processor (DIGITAL SIGNAL processing, DSP), application Specific Integrated Circuit (ASIC), field programmable gate array (fieldprogrammablegate array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an advanced reduced instruction set machine (ADVANCED RISC MACHINES, ARM) architecture.
Further, optionally, the memory may include a read-only memory and a random access memory, and may further include a nonvolatile random access memory. The memory may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may include a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM), an electrically erasable programmable EPROM (EEPROM), or a flash memory, among others. Volatile memory can include random access memory (random access memory, RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available. For example, static random access memory (STATIC RAM, SRAM), dynamic random access memory (dynamic random access memory, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (double DATA DATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DR RAM).
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. Computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method description in a flowchart or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a substantially simultaneous manner or in an opposite order from that shown or discussed, including in accordance with the functions that are involved.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the methods of the embodiments described above may be performed by a program that, when executed, comprises one or a combination of the steps of the method embodiments, instructs the associated hardware to perform the method.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that various changes and substitutions are possible within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.