CN113723979A

CN113723979A - Commuting preference analysis method, mining method, device, equipment and medium

Info

Publication number: CN113723979A
Application number: CN202010455182.7A
Authority: CN
Inventors: 闫浩强; 阚长城; 项雯怡; 江畅; 王建光
Original assignee: Baidu Online Network Technology Beijing Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd
Priority date: 2020-05-26
Filing date: 2020-05-26
Publication date: 2021-11-30

Abstract

The embodiment of the application discloses a commuting preference analysis method, a mining method, a device, equipment and a medium, and relates to a big data technology. The commuting preference analysis method comprises the following steps: determining sample users according to a commute mode; determining multi-type travel characteristics of sample users; the multi-type travel characteristics are used for representing the commuting characteristics of the sample user from different angles; and determining an incidence relation between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, wherein the incidence relation is used for mining the commuting preference of the user to be processed. The embodiment of the application can improve accuracy and reliability of user commuting preference mining and improve applicability of a commuting mining scheme.

Description

Commuting preference analysis method, mining method, device, equipment and medium

Technical Field

The embodiment of the application relates to a computer technology, in particular to a big data technology, and particularly relates to a commuting preference analysis method, a commuting preference mining method, a commuting preference analysis device, a commuting preference mining device and a commuting preference analysis medium.

Background

At present, regarding determining the commuting mode of residents, the main adopted modes include: based on a questionnaire mode in a certain area range, a mode based on signaling big data, a GPS positioning mode based on sampling users and the like, the statistical result of the commuting mode is inaccurate due to the factors of limited data quantity, limited user groups covered by data, low data precision and the like.

In addition, in the existing scheme, the commuting mode of the user is determined based on fixed number data, generally, a user track is determined according to continuous positioning data, the user travel speed is calculated by combining the user travel time, and then the commuting mode of the user is analyzed according to the characteristic of the travel speed. The scheme is only suitable for continuous positioning scenes, so that the applicable scenes are relatively limited.

Disclosure of Invention

The embodiment of the application discloses a commute preference analysis method, a commute preference mining device and a commute preference mining medium, so that accuracy and reliability of the commute preference mining of a user are improved, and applicability of a commute mining scheme is improved.

In a first aspect, an embodiment of the present application discloses a commute preference analysis method, including:

determining sample users according to a commute mode;

determining multi-type travel characteristics of the sample user; the multi-type travel features are used for representing the commuting characteristics of the sample user from different angles;

and determining an incidence relation between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, wherein the incidence relation is used for mining the commuting preference of the user to be processed.

In a second aspect, an embodiment of the present application further discloses a commuting preference mining method, where the commuting preference mining method is implemented based on an association relationship between a determined commuting manner and multi-type travel features of a user in any one of the commuting preference analysis methods disclosed in the embodiments of the present application, and the commuting preference mining method includes:

determining multi-type travel characteristics of a user to be processed; the multi-type travel characteristics are used for representing the commuting characteristics of the user to be processed from different angles;

and predicting the commuting mode of the user to be processed by utilizing the incidence relation between the commuting mode and the multi-type travel characteristics of the user to be processed.

In a third aspect, an embodiment of the present application further discloses a commute preference analysis apparatus, including:

the user determination module is used for determining sample users according to the commute mode;

the characteristic determining module is used for determining the multi-type travel characteristics of the sample user; the multi-type travel features are used for representing the commuting characteristics of the sample user from different angles;

and the relation determining module is used for determining the incidence relation between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, and the incidence relation is used for mining the commuting preference of the user to be processed.

In a fourth aspect, an embodiment of the present application further discloses a commute preference mining device, including:

the characteristic determining module is used for determining the multi-type travel characteristics of the user to be processed; the multi-type travel characteristics are used for representing the commuting characteristics of the user to be processed from different angles;

and the commuting prediction module is used for predicting the commuting mode of the user to be processed by utilizing the incidence relation between the commuting mode and the multi-type travel characteristics of the user to be processed.

In a fifth aspect, an embodiment of the present application further discloses an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a commute preference analysis method as in any one of the embodiments of the present application or a commute preference mining method as in any one of the embodiments of the present application.

In a sixth aspect, embodiments of the present application further disclose a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the commute preference analysis method or the commute preference mining method as described in any of the embodiments of the present application.

According to the technical scheme of the embodiment of the application, the incidence relation between each commuting mode and the multi-type travel characteristics of the user is obtained by collecting the sample user and determining the multi-type travel characteristics of the sample user so as to be used for excavating the commuting preference of the user to be processed, the problems that the accuracy of the existing commuting mode statistical scheme is low and the scheme application scene is limited are solved, the accuracy and the reliability of the excavation of the commuting preference of the user are improved, and the application scope of the commuting excavation scheme is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

FIG. 1 is a flow chart of a method of commute preference analysis as disclosed in an embodiment of the present application;

FIG. 2 is a flow chart of another method of commute preference analysis as disclosed in an embodiment of the present application;

FIG. 3 is a block diagram of a method for analyzing commute preference according to an embodiment of the present disclosure;

FIG. 4 is a flow chart of a commute preference mining method disclosed in accordance with an embodiment of the present application;

fig. 5 is a schematic structural diagram of a commute preference analysis apparatus according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a commute preference mining apparatus according to an embodiment of the present disclosure;

fig. 7 is a block diagram of an electronic device disclosed according to an embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a flowchart of a commute preference analysis method disclosed in an embodiment of the present application, which may be applied to a scenario of commute mode analysis or mining. The commuting preference analysis method disclosed by the embodiment of the application can be executed by a commuting preference analysis device, and the device can be realized by adopting software and/or hardware and can be integrated on any electronic equipment with computing capability.

As shown in fig. 1, a commuting preference analysis method disclosed in an embodiment of the present application may include:

s101, determining a sample user according to a commute mode.

For example, the embodiment of the present application may automatically classify and determine sample users according to different commuting manners by mining positioning type data (or internet travel data) of internet users, for example, an existing commuting manner may include at least one of public transportation, driving, riding, and walking, and a sample user corresponding to each commuting manner may be determined separately. The internet positioning type data or the internet trip data refer to any data which can be used for distinguishing the commuting modes of the user, such as user positioning coordinates, wireless network information connected with the user, driving marking data uploaded to a navigation server by the user, user navigation data, recording data of public transportation taken by the user, riding recording data of the user and the like. Public transportation includes buses and subways, and therefore, commuting modes can also be specifically detailed to include buses, subways, driving, riding and walking.

By utilizing the internet positioning type data or the internet trip data, the sample users of different commuting modes are determined, and compared with the situation that the sample users are determined according to geographic region sampling, user groups in different regions can be better covered, the sample data volume can be greatly improved, a foundation is laid for obtaining accurate commuting analysis results subsequently, the sample data acquisition cost can also be reduced, and further the cost of commuting preference analysis and commuting preference mining is reduced.

S102, determining multi-type travel characteristics of a sample user; wherein, the multi-type trip characteristics are used for characterizing the commuting characteristics of the sample user from different angles.

The multi-type travel characteristics of each sample user can represent the commuting characteristics of the sample user from different angles, namely, the selection tendency of the sample user to the travel mode is described from different dimensions, and the multi-type travel characteristics of the sample user can be obtained based on user behaviors and user information in a preset statistical period, wherein the preset statistical period can be determined in units of days or months. For example, the multi-type travel features of each sample user may include at least two of the following types: location features, public transportation distribution features on the way of commutes (or referred to as public transportation convenience features), user profile features, and terminal behavior features. The positioning characteristics refer to data of any positioning type related to the sample user and determined based on any available positioning mode; the public transportation distribution characteristics in the commute mean data related to the deployment situation of public transportation facilities between the residence and the working places of sample users; the user image characteristics refer to data which can reflect personal information such as sample user identity, interests and the like; the terminal behavior characteristics refer to behavior data generated by using the user terminal in the commute of the sample user.

For example, if the location characteristics of a sample user indicate that the user is in a remote suburb by analyzing the multi-type travel characteristics of the sample user, the sample user has a greater probability of commuting to select driving; or the public traffic distribution characteristics in the commuting process show that the public traffic distribution in the commuting process is dense or the distribution quantity is large, so that the probability that the sample user commutes to select to take the public traffic is high; or the user portrait characteristics show that the sample user is a high-income user, so that the probability that the sample user commutes to select to drive is higher; or the terminal behavior characteristics show that the frequency of using the user terminal by the sample user in the commuting period is higher, so that the probability of selecting to take the public transportation in the commuting of the sample user is higher.

As a preferred example, the multi-type travel features of each sample user may include at least: positioning characteristics and public traffic distribution characteristics in the commute; wherein the public transportation distribution characteristics on the commute may include at least one of: the distribution number of the public transportation stations which are a preset distance away from the residence and the working place of the sample user, the minimum distance of the public transportation stations from the residence and the working place of the sample user, and the like. For example, how close to the sample user is the closest to the home and the company, respectively, how many bus stations and subway stations are near the sample user home and the company, respectively, and the like.

The distribution number of the public transportation stations which are away from the residence and the working place of the sample user by the preset distance is larger, and/or the minimum distance between the public transportation station and the residence and the working place of the sample user is shorter, so that the public transportation of the surrounding environment is convenient to commute for the sample user, and the probability of selecting the public transportation by the sample user is relatively larger. The value of the preset distance can be flexibly set aiming at the residence and the working place, and the embodiment of the application is not specifically limited.

Optionally, the positioning feature may comprise at least one of: the system comprises characteristics such as commuting distance, residence location coordinates, workplace location coordinates, number of locations within a preset range of a public transportation station on the way of commuting, location speed and the like, for example, the number of locations near a subway station on the way of sample user commuting, the number of locations near a bus station. The commuting distance can be a trip distance with the most frequent occurrence times in a user commuting time period in a preset statistical period, or an average commuting distance in the preset statistical period, and the length of the commuting distance influences the selection of a sample user on a commuting mode; the residence location coordinates or the working location coordinates can be used for measuring whether the residence and the working location of the sample user belong to a remote suburb, an alarm area, a scientific and technological park or the like, the selection of the sample user on the commuting mode is different for different types of areas, and the determination of the commuting distance also needs to know the residence location coordinates and the working location coordinates; the preset range of the public transportation station in the commute process can be flexibly set, the smaller the preset range is, the closer the sample user is positioned to the public transportation station is, and the greater the positioning number in the preset range of the public transportation station in the commute process is, the greater the probability that the sample user takes the public transportation is further explained. The positioning speed may include a maximum speed, a minimum speed, a median of the speeds, and the like of the sample user during the commute period, and may be a speed corresponding to a complete commute trajectory or a speed corresponding to a partial commute trajectory. The fine-grained positioning features can be used for detailed analysis of track behaviors of the sample user on the way of commuting, and further used for accurately analyzing travel selection of the sample user.

It should be noted that, in the embodiment of the present application, as part of features in the multi-type travel features of the sample user, the positioning coordinates, the speed, and the like participate in analyzing the commuting behavior of the sample user together with other types of features, and compared with a scheme for analyzing the commuting behavior of the user based on the user speed, the embodiment of the present application may effectively balance the defect that the commuting analysis or the mining result is inaccurate due to inaccurate speed determination, and may extend the accurate and effective commuting analysis or mining scheme to be applied to a non-continuous positioning scene, because continuous positioning is a precondition for ensuring that an accurate positioning speed is obtained. Especially, in a scene of commuting analysis or mining based on internet data, positioning data in the internet data is usually discretized and discontinuous data, which cannot ensure that an accurate travel speed of a user can be always obtained, and further, based on the existing thought, the user commuting behavior can not be accurately and reliably obtained based on speed analysis, and by adopting the technical scheme of the embodiment of the application, the defect can be overcome.

Optionally, the terminal behavior characteristics of the sample user may include a navigation operation behavior of the sample user for the commute mode, for example, in a commute period, a click behavior of the sample user on a navigation application, a selection and viewing behavior of a navigation route for a specific commute mode, a road condition query behavior, a navigation map or route amplification behavior, and the like. By analyzing these navigation operation behaviors of the sample user, the travel selection of the sample user can be assisted and analyzed in combination with the travel characteristics. Of course, the terminal behavior characteristics of the sample user may also include the operation behavior of the user on other applications except the navigation application, and if the sample user operates the other applications more frequently, it may be stated that the sample user has a lower probability of driving from the perspective of safe driving.

Alternatively, the user representation characteristics of the sample user may include characteristics of gender, age, asset condition, education level, consumption level, and income level. The characteristics can describe the characteristics of each sample user in detail, and the commuting behavior of the sample user is analyzed in a side-aided mode by combining the travel characteristics.

S103, determining an incidence relation between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, wherein the incidence relation is used for mining the commuting preference of the user to be processed.

Specifically, for sample users with different commuting modes, differences exist among the multi-type travel features, and therefore, after the commuting mode and the multi-type travel features of each sample user are determined, regularity between each commuting mode and the multi-type travel features of the sample users can be analyzed by using any available data analysis algorithm to serve as an association relation between the commuting mode and the multi-type travel features, the association relation can be a linear relation or a non-linear relation, for example, a weight factor of each type feature in the multi-type travel features of the sample users is analyzed in each commuting mode. The available data analysis algorithms include, but are not limited to, algorithms such as decision trees, random forests, Support Vector Machines (SVMs), bayes, and the like, and specifically, the algorithms may be selected according to actual needs.

Illustratively, determining the association relationship between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user includes:

the method comprises the steps of taking a commuting mode of a sample user as output of model training, taking multi-type travel characteristics of the sample user as input of the model training, training to obtain a commuting classification model, namely representing an incidence relation between the commuting mode and the multi-type travel characteristics by using the commuting classification model, and predicting commuting preference of a user to be processed by using the commuting classification model. As an example, the commute classification model may be implemented based on an xgboost model (a set of machine learning systems with extensible lifting trees), so that the commute classification model has high accuracy and recall.

According to the technical scheme of the embodiment of the application, the incidence relation between each commuting mode and the multi-type travel characteristics of the user is obtained by collecting the sample user and determining the multi-type travel characteristics of the sample user for excavating the commuting preference of the user to be processed, the multi-type travel characteristics can represent the commuting characteristics of the sample user from different angles, the method is different from the prior art which only considers the characteristic of one dimension of the positioning speed of the user, the effect of refining and analyzing the commuting behavior of the sample user from multiple characteristic dimensions is realized, the accuracy of the incidence relation between the determined commuting mode and the multi-type travel characteristics of the user is ensured, the problems of lower accuracy and more limited scheme application scene in the conventional commuting mode statistical scheme are solved, the accuracy and the reliability of subsequent user commuting preference excavation are improved, and the commuting excavation quality is improved, and the applicability of the commute excavation scheme is improved.

On the basis of the above technical solution, optionally, different types of travel characteristics of the sample user may be determined in the following manner:

in an exemplary aspect, determining the distribution characteristics of public transportation on the commute of the sample user includes:

determining a commuting area in a map according to the residence location coordinates and the working location coordinates of the sample user;

determining public transportation interest points in the commuting area by using the map data;

and determining the public traffic distribution characteristics of the sample user in the commuting process according to the public traffic interest point information.

By using the map data in determining the public transportation distribution characteristics of the sample user, the convenience of characteristic determination and the determination efficiency are improved.

Exemplary two, determining a location feature of a sample user, includes:

and acquiring a positioning log generated by a sample user terminal in the commuting period, and determining the positioning characteristics of the sample user by analyzing the positioning log.

Exemplary three, determining the terminal behavior characteristics of the sample user includes:

and acquiring a behavior log generated by the terminal when the sample user uses the terminal in the commuting period, and determining the terminal behavior characteristics of the sample user by analyzing the behavior log. For example, a navigation behavior log (or referred to as a map application log) generated in the user terminal is obtained, and a navigation operation behavior of the sample user for the commute mode is determined by analyzing the navigation behavior log.

Exemplary four, determining a user profile feature of a sample user, comprising:

by accounting for user information, portrait characteristics of the user are constructed, including but not limited to gender, age, asset condition, education level, consumption level, income level, and the like.

Fig. 2 is a flowchart of another commuting preference analysis method disclosed in an embodiment of the present application, which is further optimized and expanded based on the above technical solution, and can be combined with the above various optional embodiments. As shown in fig. 2, the method may include:

s201, determining a sample user adopting the commuting mode by utilizing internet trip data and based on a preset user statistical mode of the commuting mode; wherein the commuting mode comprises at least one of: public transportation, driving, riding, and walking.

In the embodiment of the application, different sample user statistical modes are adopted for different commuting modes respectively, the sample users corresponding to each commuting mode are determined in a classified mode by utilizing internet trip data, and a piece of high-quality sample data can be provided for subsequent commuting analysis. Specifically, by utilizing the internet trip data, the sample users corresponding to different commuting modes are determined, and compared with the situation that the sample users are determined according to geographic region sampling, user groups in different regions can be better covered, the sample data volume can be greatly improved, a foundation is laid for obtaining accurate commuting analysis results subsequently, the sample data acquisition cost can also be reduced, and then the commuting analysis and mining cost is reduced.

After obtaining sample users corresponding to different commuting modes, the embodiment of the present application may further include: detecting whether repetition exists among sample users corresponding to different commuting modes, for example, if a certain sample user is classified into a sample user corresponding to riding and a sample user corresponding to walking, the sample user belongs to a repeated sample user; if the repetition exists, the selection probability of the repeated sample user to different commuting modes can be determined by combining with the multi-class travel characteristics of the user, and the sample user is classified into the commuting mode type with higher selection probability, so that the duplicate removal processing for the sample user is realized, and the sample quality is improved. Of course, the priorities between the commuting modes may be preset, and the repeated sample users may be preferentially classified into the types of commuting modes with higher priorities.

S202, determining multi-type travel characteristics of the sample user; wherein, the multi-type trip characteristics are used for characterizing the commuting characteristics of the sample user from different angles.

S203, determining an incidence relation between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, wherein the incidence relation is used for mining the commuting preference of the user to be processed.

On the basis of the above technical solution, optionally, the sample users who travel in different commuting modes can be determined in the following mode:

in an exemplary embodiment, determining a sample user using a mass transit travel method includes:

determining the time length of different candidate user terminals connected with a wireless network on public transport, the travel distance of the connected wireless network and the signal intensity of the connected wireless network in the commuting period from the internet travel data;

and determining the sample user adopting the public transportation travel mode according to the determined time length, the travel distance and the signal intensity.

Specifically, among the candidate users, the user whose time length that the terminal is connected to the wireless network on the public transportation is greater than the time threshold, whose travel distance is greater than the travel distance threshold, and whose signal strength of the connected wireless network is less than the signal strength threshold may be determined as the sample user adopting the public transportation travel mode. The value of the signal intensity is a positive value, and the smaller the value is, the closer the user is to the network signal source is, the better the network quality is; the time threshold, the travel distance threshold, and the signal strength threshold may be adaptively set, and the embodiment of the present application is not particularly limited.

For example, a candidate user whose wifi is connected to the bus by the terminal for more than 5 minutes, whose traveling distance exceeds 1km, and whose wifi signal strength is less than 70dBm can be determined as a sample user who takes the bus for traveling; similarly, a candidate user whose terminal is connected with wifi on the subway for more than 5 minutes, whose traveling distance is more than 1km, and whose connected wifi signal strength is less than 70dBm can be determined as a sample user who takes the subway for traveling.

Example two, determining a sample user that employs a driving travel style includes:

acquiring driving marking data reported by different candidate users and/or map navigation operation behaviors of the different candidate users in a commuting period from internet trip data;

and determining a sample user adopting a driving travel mode according to the driving marking data and/or the map navigation operation behavior.

Specifically, a sample user who drives a vehicle for traveling can be screened out according to driving marking data reported by a candidate user, wherein the driving marking data refers to the driving behavior reported by the candidate user through a user terminal when the candidate user selects driving for traveling; whether a candidate user adopts a driving navigation mode can be determined by analyzing map navigation operation behaviors, and if so, the candidate user is determined as a sample user for driving travel; furthermore, the driving marking data reported by the candidate user and the map navigation operation behavior of the candidate user can be comprehensively analyzed, whether the candidate user belongs to a user who drives a vehicle for travel or not is determined, and therefore the accuracy of the sample user classification determination is improved. If the result of determining the commuting mode of the candidate user is inconsistent according to the driving annotation data reported by the candidate user and the map navigation operation behavior of the candidate user, the commuting mode determined by the map navigation operation behavior is preferably used as the main mode, for example, if the candidate user is determined not to adopt the driving navigation mode by analyzing the map navigation operation behavior, even if the driving annotation data of the candidate user is obtained currently, the candidate user is determined not to belong to a sample user who drives a vehicle, because the driving annotation data uploaded by the candidate user may have a subjective false behavior, and the commuting result obtained by analyzing the map navigation operation behavior of the candidate user is more objective and accurate.

Exemplary three, determining a sample user adopting a cycling trip approach includes:

determining the use conditions of different candidate users on the shared bicycle in the commuting period from the internet trip data;

and determining the sample user adopting the riding and traveling mode according to the use condition of the shared bicycle.

The service conditions of the candidate users for the shared bicycle can include the scanning unlocking times and locking times of the candidate users for the shared bicycle in the commuting period, the positioning number in the fixed parking area of the shared bicycle and other information, the service frequency of the candidate users for the shared bicycle can be obtained through analysis according to the information, and whether the candidate users belong to a sample user who rides and goes out is further determined. The information such as the number of scanning unlocking times, the number of locking times, the number of positioning in the fixed parking area of the shared bicycle and the like can be acquired by analyzing the shared bicycle use log and the positioning log generated in the user terminal.

Specifically, if at least one factor of the number of times that the candidate user scans and unlocks the shared bicycle, the number of times that the candidate user locks, and the number of positions in the fixed parking area of the shared bicycle in the commuting period is greater than a corresponding threshold value, it is determined that the candidate user has a high frequency of using the shared bicycle, and the candidate user belongs to a sample user who is traveling by bike, otherwise, the candidate user does not belong to the sample user.

Fourth, determining a sample user in a walking mode comprises:

acquiring residence location coordinates and working location coordinates of different candidate users from internet trip data, and calculating the distance between the residence and the working locations;

and determining the sample user adopting the walking travel mode according to the relationship between the calculated distance and the distance threshold value. Specifically, if the distance between the residence and the workplace of the candidate user is less than the distance threshold, the candidate user is considered to belong to the sample user who walks on foot. The distance threshold may be flexible, for example, 1 km.

According to the technical scheme of the embodiment of the application, the sample users corresponding to different commuting modes are determined by utilizing internet trip data and based on preset user statistical modes of different commuting modes, so that the effect of efficiently, flexibly and inexpensively acquiring high-quality sample data is realized, and a data basis is laid for the subsequent accurate analysis of the incidence relation between the commuting modes and the multi-type trip characteristics of the users; because the characteristics of the multi-type trip of the user can represent the commuting characteristics of the sample user from different angles, the method is different from the characteristic that only the dimension of the positioning speed of the user is considered in the prior art, the effect of refining and analyzing the commuting behavior of the sample user from multiple characteristic dimensions is realized, the accuracy of the incidence relation between the determined commuting mode and the characteristics of the multi-type trip of the user is ensured, the problems of lower accuracy and more limited scheme application scene in the existing commuting mode statistical scheme are solved, the accuracy and reliability of mining of the subsequent commuting mode of the user are improved, and the applicability of the commuting mining scheme is improved.

Illustratively, compared with the existing commuting behavior analysis scheme, the advantages of the embodiment of the application are as follows:

1) compared with a scheme of analyzing the public commuting behavior based on the questionnaire, the embodiment of the application can spend less cost and obtain a large amount of sample data by means of the Internet trip data, and can cover the user groups in any national region range and perform the public commuting analysis in any regional dimension.

2) Compared with a scheme for analyzing the public commuting behavior based on signaling big data, the related positioning data in the embodiment of the application can be obtained based on a Global Positioning System (GPS), the positioning precision is higher than the precision of positioning depending on mobile communication (the precision of positioning depending on mobile communication is about 200 meters), the GPS positioning precision can reach about 10 meters, for example, the commuting distance and the positioning coordinate can be more accurately determined, which is beneficial to ensuring the accuracy of commuting analysis results, and the higher the precision of the positioning coordinate of the user is, the more beneficial to realizing the commuting behavior analysis of the fine granularity of a geographic area, for example, the commuting behaviors of users in different industrial parks and different residential area ranges are analyzed.

3) Compared with the method for analyzing the public commuting behavior based on the continuous GPS positioning result of the sampling user, the method for analyzing the public commuting behavior based on the sampling user can cover the whole quantity of users without difference by means of the Internet trip data, is not limited to a part of user groups, and is beneficial to analyzing the commuting behavior patterns of the public in a follow-up large-scale mode, for example, the difference of the commuting behavior of the user between different cities can be conveniently and transversely compared, and the difference of the commuting behavior of the user between different areas of the same city can be longitudinally compared.

Fig. 3 is a schematic structural diagram of a commute preference analysis method disclosed in an embodiment of the present application, and specifically, an example is a commute classification model obtained through training to represent a correlation between a commute mode and a multi-type travel characteristic of a user, and an embodiment of the present application is exemplarily described and should not be construed as a specific limitation to the embodiment of the present application. As shown in fig. 3, sample extraction is performed by collecting user annotation data of an internet user for different commuting modes, driving data of a navigation map user, positioning logs in a user terminal, and the like, so as to obtain sample users for different commuting modes; constructing various travel characteristics of a sample user by utilizing a user portrait, a map application log, a positioning log and the like in a user terminal; then based on a machine learning thought, a commuting classification model is trained by using commuting modes and multi-type travel characteristics of sample users, the model can be evaluated and adjusted by using a test set in a model training process to obtain a final commuting classification model, wherein, exemplarily, the proportions of the sample users who drive, transit, subway, ride and walk can be divided according to a certain proportion, such as the proportion of 15:10:10:5:2, in the model training process; in the model application stage, the multi-type travel characteristics of the user to be processed can be extracted based on the commuting data of the user to be processed, and then the commuting preference of the user to be processed is predicted by utilizing a commuting classification model; furthermore, regional statistics and analysis can be performed according to the residence or the working place aiming at a large number of users to be processed, so that the commuting preference of the masses in different regions can be evaluated.

Fig. 4 is a flowchart of a commute preference mining method disclosed in an embodiment of the present application, which may be applied to a scenario of commute mode mining for a user to be processed. The commuting preference mining method disclosed by the embodiment of the application can be executed by a commuting preference mining device, and the device can be realized by adopting software and/or hardware and can be integrated on any electronic equipment with computing capability.

The method for mining the commuting preference is based on the method for analyzing the commuting preference arbitrarily disclosed by the embodiment of the application, and the determined association relation between the commuting mode and the multi-type travel characteristics of the user is realized. As to how the association relationship between the commuting mode and the multi-type travel characteristics of the user is determined, reference may be made to the explanation in the above technical solution.

As shown in fig. 4, the commuting preference mining method disclosed in the embodiment of the present application may include:

s401, determining multi-type travel characteristics of a user to be processed; the multi-type travel characteristics are used for representing the commuting characteristics of the user to be processed from different angles.

S402, forecasting the commuting mode of the user to be processed by utilizing the incidence relation between the commuting mode and the multi-type travel characteristics of the user to be processed.

The multi-type travel characteristics of each user to be processed can represent the commuting characteristics of the user to be processed from different angles, namely the selection tendency of the user to be processed on the travel mode is described from different dimensions, the multi-type travel characteristics of the user to be processed can be obtained based on user behaviors and user information in a preset statistical period, and the preset statistical period can be determined in units of days or months. For example, the multi-type travel features of each user to be processed may include at least two types: location features, public transportation distribution features on the way of commutes (or referred to as public transportation convenience features), user profile features, and terminal behavior features. The positioning characteristics refer to data of any positioning type related to the user to be processed and determined based on any available positioning mode; the public transportation distribution characteristics in the commute mean data related to the deployment situation of public transportation facilities between the residence and the working place of the user to be processed; the user portrait characteristics refer to data which can reflect personal information such as the identity, interest and the like of a user to be processed; the terminal behavior characteristics refer to behavior data generated when the user terminal is used by the user to be processed in the commute.

As a preferred example, the multi-type travel characteristics of each user to be processed at least comprise a positioning characteristic and a public transportation distribution characteristic in the commute; wherein the public transportation distribution characteristics on the commute may include at least one of: the distribution number of public transportation stations which are a preset distance away from the residence and the workplace of the user to be processed, the minimum distance between the public transportation stations and the residence and the workplace of the user to be processed, and the like. Further, the positioning feature may comprise at least one of: the location system comprises a commuting distance, a residence location coordinate, a workplace location coordinate, the number of locations within a preset range of public transportation stations on the way of the commute, a location speed and the like.

Optionally, the terminal behavior characteristics of the user to be processed may include a navigation operation behavior of the user to be processed for the commute mode, for example, in a commute period, a click behavior of the user to be processed on a navigation application, a selection and viewing behavior of a navigation route for a specific commute mode, a road condition query behavior, a navigation map or route amplification behavior, and the like. By analyzing the navigation operation behaviors of the user to be processed, the commute preference of the user to be processed can be analyzed in an auxiliary mode by combining the travel characteristics. Of course, the terminal behavior characteristics of the user to be processed may also include the operation behavior of the user on other applications besides the navigation application.

Optionally, the user representation characteristics of the user to be processed may include characteristics of gender, age, asset condition, education level, consumption level, and income level. The characteristics can describe the characteristics of each user to be processed in detail, and the commuting behavior of the user to be processed is analyzed in a side-aided mode by combining the travel characteristics.

It should be noted that how to determine the multi-type travel features of the user to be processed belongs to the same determination logic as how to determine the multi-type travel features of the sample user in the foregoing technical solution, and reference may be made to the explanation in the foregoing technical solution for details that are not explained here.

On the basis of the above technical solution, optionally, different types of travel characteristics of each user to be processed may be determined in the following manner:

according to an exemplary embodiment, the determining the distribution characteristics of public transportation on the commute of the user to be processed includes:

determining a commuting area in a map according to the residence location coordinates and the working location coordinates of the user to be processed;

and determining the public traffic distribution characteristics of the user to be processed on the commuting way according to the public traffic interest point information.

Exemplary two, determining the location characteristics of the user to be processed includes:

and acquiring a positioning log generated by the user terminal to be processed in the commuting period, and determining the positioning characteristics of the user to be processed by analyzing the positioning log.

Exemplary three, determining the terminal behavior characteristics of the user to be processed includes:

the method comprises the steps of obtaining a behavior log generated by a user to be processed in the process of using the terminal in the commuting period, and determining the terminal behavior characteristics of the user to be processed by analyzing the behavior log. For example, a navigation behavior log (or referred to as a map application log) generated in the user terminal is obtained, and a navigation operation behavior of the user to be processed for the commute mode is determined by analyzing the navigation behavior log.

Fourth, determining a user profile characteristic of the user to be processed includes:

According to the technical scheme of the embodiment of the application, through confirming the multi-type trip characteristics of the user to be processed, the incidence relation between each commuting mode and the multi-type trip characteristics of the user is combined, the commuting preference of the user to be processed is excavated, the commuting characteristics of the user to be processed can be represented from different angles due to the multi-type trip characteristics, the characteristics of the dimension of the positioning speed of the user are generally considered in the prior art, the effect of refining and analyzing the commuting preference of the user to be processed from multiple feature dimensions is realized, the problems that the accuracy is low in the existing commuting mode statistical scheme and the scheme is applicable to a limited scene are solved, the accuracy and the reliability of the excavation of the commuting preference of the user are improved, the commuting excavation quality is improved, and the applicability of the commuting excavation scheme is improved.

Fig. 5 is a schematic structural diagram of a commute preference analysis apparatus disclosed according to an embodiment of the present application, which may be applied to a scene of commute mode analysis or mining. The commute preference analyzing apparatus may be implemented in software and/or hardware and may be integrated on any electronic device having computing capabilities.

As shown in fig. 5, the commute preference analyzing apparatus 500 disclosed in the embodiment of the present application may include a user determining module 501, a feature determining module 502, and a relationship determining module 503, wherein:

a user determining module 501, configured to determine a sample user according to a commute manner;

a feature determination module 502, configured to determine multi-type travel features of a sample user; the multi-type travel characteristics are used for representing the commuting characteristics of the sample user from different angles;

the relationship determining module 503 is configured to determine an association relationship between the commuting mode and the multi-type travel characteristics according to the commuting mode of the sample user and the multi-type travel characteristics of the sample user, where the association relationship is used to mine the commuting preference of the user to be processed.

Optionally, the multi-type travel characteristics at least include a positioning characteristic and a public traffic distribution characteristic in the commute;

the public transportation distribution characteristics on the commute include at least one of: the distribution number of the public transportation sites which are a preset distance from the residence and the workplace of the sample user, and the minimum distance of the public transportation sites from the residence and the workplace of the sample user.

Optionally, the positioning feature comprises at least one of: commuting distance, residence location coordinates, workplace location coordinates, number of locations within a preset range of a public transportation site on the way of the commute, and location speed.

Optionally, the multi-type travel features further include user portrait features and terminal behavior features.

Optionally, the feature determination module 502 may include at least two of:

the public traffic distribution characteristic determining unit is used for determining public traffic distribution characteristics of the sample user in the commuting process;

the positioning feature determining unit is used for determining the positioning features of the sample users;

a user portrait feature determination unit to determine user portrait features of a sample user;

the terminal behavior characteristic determining unit is used for determining the terminal behavior characteristics of the sample user;

wherein, the public traffic distribution characteristic determining unit includes:

the commuting area determining subunit is used for determining a commuting area in the map according to the residence location coordinates and the working location coordinates of the sample user;

the interest point determining subunit is used for determining public transportation interest points in the commuting area by utilizing the map data;

and the characteristic determining subunit is used for determining the public traffic distribution characteristics of the sample user in the commuting process according to the public traffic interest point information.

Optionally, the terminal behavior characteristics of the sample user include a navigation operation behavior of the sample user for the commute mode.

Optionally, the user determining module 501 is specifically configured to:

determining a sample user adopting the commuting mode by utilizing internet trip data and based on a preset user statistical mode of the commuting mode; wherein the commuting mode comprises at least one of: public transportation, driving, riding, and walking.

Optionally, the user determining module 501 may include a first determining unit, configured to determine a sample user adopting a public transportation travel mode; the first determination unit may include:

the public transport data determining subunit is used for determining the time length of different candidate user terminals connected with a wireless network on public transport, the travel distance of the connected wireless network and the signal intensity of the connected wireless network in the commuting period from the internet travel data;

and the public transport trip user determination subunit is used for determining the sample user adopting the public transport trip mode according to the determined time length, the trip distance and the signal intensity.

Optionally, the user determining module 501 may further include a second determining unit, configured to determine the sample user adopting the driving travel mode, where the second determining unit may include:

the driving data acquisition subunit is used for acquiring driving marking data reported by different candidate users and/or map navigation operation behaviors of the different candidate users in a commuting period from internet trip data;

and the driving travel user determining subunit is used for determining the sample user adopting the driving travel mode according to the driving marking data and/or the map navigation operation behavior.

Optionally, the user determining module 501 may further include a third determining unit, configured to determine the sample user in the cycling trip manner, where the third determining unit may include:

the riding data determining subunit is used for determining the use conditions of different candidate users on the shared bicycle in the commuting period from the Internet trip data;

and the riding trip user determination subunit is used for determining the sample user adopting the riding trip mode according to the use condition of the shared bicycle.

Optionally, the user determining module 501 may further include a fourth determining unit, configured to determine the sample user in the walking trip manner, where the fourth determining unit may include:

the distance determining subunit is used for acquiring residence location coordinates and working location coordinates of different candidate users from the internet trip data, and calculating the distance between the residence and the working locations;

and the walking trip user determination subunit is used for determining the sample user adopting the walking trip mode according to the relationship between the calculated distance and the distance threshold value.

In the above technical solution, the terms such as "first" to "fourth" and the like related to the first to fourth determination units are used for naming distinction without any sequence limitation.

The commuting preference analysis device 500 disclosed in the embodiment of the present application can execute any commuting preference analysis method disclosed in the embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method. Reference may be made to the description of any method embodiment of the present application for details not explicitly described in the apparatus embodiments of the present application.

Fig. 6 is a schematic structural diagram of a commute preference mining device disclosed according to an embodiment of the present application, which may be applied to a scene mined in a commute manner for a user to be processed. The commute preference mining apparatus may be implemented in software and/or hardware and may be integrated on any electronic device having computing capabilities.

As shown in fig. 6, the commute preference mining apparatus 600 disclosed in the embodiment of the present application may include a feature determination module 601 and a commute prediction module 602, where:

the characteristic determining module 601 is configured to determine multi-type travel characteristics of a user to be processed; the multi-type travel characteristics are used for representing the commuting characteristics of the user to be processed from different angles;

the commute prediction module 602 is configured to predict a commute mode of the user to be processed by using an association relationship between the commute mode and the multi-type travel characteristics of the user to be processed.

the public transportation distribution characteristics on the commute include at least one of: the distribution number of the public transportation stations which are a preset distance away from the residence and the workplace of the user to be processed, and the minimum distance of the public transportation stations from the residence and the workplace of the user to be processed.

Optionally, the feature determining module 601 may include at least two of the following:

the public traffic distribution characteristic determining unit is used for determining public traffic distribution characteristics of the user to be processed in the commuting process;

the positioning feature determining unit is used for determining the positioning feature of the user to be processed;

the user portrait characteristic determining unit is used for determining user portrait characteristics of a user to be processed;

the terminal behavior characteristic determining unit is used for determining the terminal behavior characteristics of the user to be processed;

the commuting area determining subunit is used for determining a commuting area in the map according to the residence location coordinates and the working location coordinates of the user to be processed;

and the characteristic determining subunit is used for determining the public traffic distribution characteristics of the user to be processed in the commuting process according to the public traffic interest point information.

Optionally, the terminal behavior feature of the user to be processed includes a navigation operation behavior of the user to be processed for the commute mode.

The commuting preference mining device 600 disclosed in the embodiment of the present application can execute any commuting preference mining method disclosed in the embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method. Reference may be made to the description of any method embodiment of the present application for details not explicitly described in the apparatus embodiments of the present application.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

As shown in fig. 7, fig. 7 is a block diagram of an electronic device for implementing a commute preference analysis method or a commute preference mining method in an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of embodiments of the present application described and/or claimed herein.

As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display Graphical information for a Graphical User Interface (GUI) on an external input/output device, such as a display device coupled to the Interface. In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations, e.g., as a server array, a group of blade servers, or a multi-processor system. In fig. 7, one processor 701 is taken as an example.

The memory 702 is a non-transitory computer readable storage medium provided by the embodiments of the present application. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform a commute preference analysis method or a commute preference mining method provided by embodiments of the present application. A non-transitory computer-readable storage medium of an embodiment of the present application stores computer instructions for causing a computer to perform a commute preference analysis method or a commute preference mining method provided by an embodiment of the present application.

The memory 702 is a non-transitory computer readable storage medium, and may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the commute preference analysis method or the commute preference mining method in the embodiments of the present application, for example, the user determination module 501, the feature determination module 502, and the relationship determination module 503 shown in fig. 5, or the feature determination module 601 and the commute prediction module 602 shown in fig. 6. The processor 701 executes various functional applications and data processing of the electronic device, i.e., implementing the commuting preference analysis method or the commuting preference mining method in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 702.

The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 702 may optionally include a memory remotely disposed with respect to the processor 701, and these remote memories may be connected via a network to an electronic device for implementing the commute preference analysis method or the commute preference mining method in this embodiment. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device for implementing the commuting preference analysis method or the commuting preference mining method in the embodiment of the present application may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.

The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of an electronic apparatus for implementing the commute preference analysis method or the commute preference mining method in the present embodiment, such as an input device of a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output device 704 may include a display apparatus, an auxiliary lighting device such as a Light Emitting Diode (LED), a tactile feedback device, and the like; the tactile feedback device is, for example, a vibration motor or the like. The Display device may include, but is not limited to, a Liquid Crystal Display (LCD), an LED Display, and a plasma Display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, Integrated circuitry, Application Specific Integrated Circuits (ASICs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs, also known as programs, software applications, or code, include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or Device for providing machine instructions and/or data to a Programmable processor, such as a magnetic disk, optical disk, memory, Programmable Logic Device (PLD), including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device for displaying information to a user, for example, a Cathode Ray Tube (CRT) or an LCD monitor; and a keyboard and a pointing device, such as a mouse or a trackball, by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front-end component, e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical scheme of the embodiment of the application, the incidence relation between the commuting mode and the multi-type travel characteristics of the user is obtained by collecting the sample user and determining the multi-type travel characteristics of the sample user, the incidence relation can be used for excavating the commuting preference of the user to be processed, the problems that the accuracy of the existing commuting mode statistical scheme is low and the scheme application scene is limited are solved, the accuracy and the reliability of the excavation of the commuting mode of the follow-up user are improved, and the application scope of the commuting excavation scheme is improved.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A commute preference analysis method, comprising:

determining sample users according to a commute mode;

2. The method of claim 1, wherein the multi-type travel features include at least location features and on-commute mass transit distribution features;

the on-commute public transportation distribution characteristics include at least one of: a distribution number of public transportation sites that are a preset distance from the sample user's residence and place of work, and a minimum distance of the public transportation sites from the sample user's residence and place of work.

3. The method of claim 2, wherein the locating features comprise at least one of: commuting distance, residence location coordinates, workplace location coordinates, number of locations within a preset range of a public transportation site on the way of the commute, and location speed.

4. The method of claim 2, wherein the multi-type travel features further comprise user portrait features and terminal behavior features.

5. The method of claim 2, wherein determining the sample user's commuting en-route public transportation distribution characteristics comprises:

determining a commuting area in a map according to the sample user residence location coordinates and the work location coordinates;

determining public transportation interest points in the commuting area using map data;

6. The method of claim 4, wherein the terminal behavior characteristics comprise navigational operational behavior of the sample user with respect to the commute mode.

7. The method of claim 1, wherein said determining sample users in a commute manner comprises:

determining a sample user adopting the commuting mode based on a preset user statistical mode of the commuting mode by utilizing internet trip data;

wherein the commuting mode comprises at least one of: public transportation, driving, riding, and walking.

8. The method of claim 7, wherein determining sample users for mass transit travel comprises:

determining the time length of different candidate user terminals connected with a wireless network on public transport, the travel distance of the wireless network and the signal strength of the connected wireless network in the commuting period from the internet travel data;

9. The method of claim 7, wherein determining sample users for driving travel comprises:

acquiring driving marking data reported by different candidate users and/or map navigation operation behaviors of the different candidate users in a commuting period from the internet trip data;

and determining the sample user adopting the driving travel mode according to the driving marking data and/or the map navigation operation behavior.

10. The method of claim 7, wherein determining a sample user in a cycling trip comprises:

and determining the sample user adopting the riding travel mode according to the use condition of the shared bicycle.

11. The method of claim 7, wherein determining the sample users in a walking mode comprises:

acquiring residence location coordinates and working location coordinates of different candidate users from the internet trip data, and calculating the distance between the residence and the working locations;

and determining the sample user adopting the walking travel mode according to the relationship between the calculated distance and the distance threshold value.

12. A commuting preference mining method, based on the association relationship between the determined commuting mode and the multi-type travel features of the user in the commuting preference analysis method according to any one of claims 1 to 11, the commuting preference mining method comprising:

13. The method of claim 12, wherein the multi-type travel characteristics include at least location characteristics and on-commute mass transit distribution characteristics;

the on-commute public transportation distribution characteristics include at least one of: the distribution number of public transportation stations which are a preset distance away from the residence and the working place of the user to be processed, and the minimum distance from the public transportation stations to the residence and the working place of the user to be processed.

14. The method of claim 13, wherein the locating features comprise at least one of: commuting distance, residence location coordinates, workplace location coordinates, number of locations within a preset range of a public transportation site on the way of the commute, and location speed.

15. The method of claim 13, wherein the multi-type travel features further comprise user portrait features and terminal behavior features.

16. The method of claim 13, wherein determining the distribution of public traffic on the commute of the pending user comprises:

determining a commuting area in a map according to the residence location coordinate and the working location coordinate of the user to be processed;

17. The method of claim 15, wherein the terminal behavior characteristics comprise a navigation operation behavior of the pending user with respect to the commute mode.

18. A commute preference analysis apparatus, comprising:

19. A commute preference mining apparatus, comprising:

20. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the commute preference analysis method of any one of claims 1-11 or to perform the commute preference mining method of any one of claims 12-17.

21. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the commute preference analysis method of any one of claims 1-11 or the commute preference mining method of any one of claims 12-17.