Method, system, medium, and program product for attributing user outbound travel trajectory

Abstract

The present application provides a method and system for attributing a user's exit travel trajectory, a computer-readable storage medium, and a computer program product, which determine the number of times the user exits each gate of a subway station gate group based on the user's itinerary and gate information, and use this as a basis to determine the user's exit gate, and correspond the user's exit travel trajectory to the exit gate to which it belongs, thereby solving the technical problem of being unable to achieve positioning during subway travel and thus obtaining the user's exit travel trajectory, and avoiding the limitation of the existing implementation that requires determining the subway exit based on buried points.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a method and system for attributing a user's outbound travel trajectory, a computer-readable storage medium, and a computer program product. Background Art

[0002] When users travel, whether they are at a subway station or in the tunnels between subway stations, it is difficult for them to obtain their own positioning in order to meet the needs of terminal applications.

[0003] The geographical location of the terminal application when exiting the subway station is often determined through GPS (Global Positioning SystemGlobal Positioning System) positioning. However, due to the poor GPS signal in the subway or even the inability to receive GPS signals, it is difficult for the terminal application to determine the geographical location through GPS signals when exiting the subway station.

[0004] In addition, in addition to being limited by the lack of GPS signals or very poor GPS signals in the subway, obtaining positioning through terminal applications is also due to reasons such as the rejection of location permission. It is impossible to locate the user's travel trajectory out of the station through the terminal application to determine the exit to which the user belongs. Summary of the invention

[0005] One purpose of this application is to solve the technical problem of being unable to achieve positioning during subway travel and thus obtain the user's travel trajectory when leaving the station, so as to accurately correspond the user's travel trajectory when leaving the station to the exit.

[0006] According to one aspect of an embodiment of the present application, a method for attributing a user's outbound travel trajectory is disclosed, the method comprising:

[0007] Get the number of times a user exits each gate at a subway station gate group;

[0008] Predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate group at the subway station and the user portrait, the exit being an exit accessible from the gate group;

[0009] According to the exit to which the user belongs, the travel trajectory of the user is matched to the exit to which the user belongs;

[0010] The users passing through the exit are aggregated through the travel trajectory and user portrait, and the aggregated users are assigned a location mapped by the exit.

[0011] According to one aspect of an embodiment of the present application, obtaining the number of times a user exits each gate of a gate group at a subway station includes:

[0012] Acquire the itinerary data of the user, wherein the itinerary data at least describes the exit stations and exit gates involved in the generated user itinerary of the user;

[0013] For the user's travel data, the number of times the user exits each gate of the subway station gate group is obtained from the gate information according to the user's exit station and exit gate.

[0014] According to one aspect of an embodiment of the present application, predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate of a subway station gate group and the user portrait includes:

[0015] Predicting the number of exits of the user at each gate on the subway station gate group and the user portrait, obtaining the probability of the user's exit direction, the exit direction corresponding to at least one of the exits;

[0016] The exit gate to which the user belongs is determined according to the probability of the user's exit direction.

[0017] According to one aspect of an embodiment of the present application, before predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate group of the subway station gate and the user portrait, the method further includes:

[0018] Determine whether the number of times the user exits the subway station gate is less than a set threshold. If so, jump to execute the prediction of the user's exit direction.

[0019] According to one aspect of the embodiment of the present application, the method further includes:

[0020] If the number of times the user exits the subway station gate is not less than a set threshold, the exit to which the user belongs is determined by performing historical exit bias statistics.

[0021] According to one aspect of an embodiment of the present application, determining the exit to which the user belongs by performing historical exit bias statistics includes:

[0022] Determine the gate that the user prefers in the gate group according to the distribution statistics of the number of times the user exits the station at each gate group at the subway station;

[0023] According to the location of the gate, the exit located on the same side is determined as the exit to which the user belongs.

[0024] According to one aspect of an embodiment of the present application, after aggregating users passing through the exit through the travel trajectory and user portrait, the method further includes:

[0025] For the location corresponding to the exit, the user profile of the aggregated user is assigned to the location for use in the delivery control at the location, and the location includes a media location and a store location.

[0026] According to one aspect of an embodiment of the present application, the present application discloses an attribution system for a user's outbound travel trajectory, the system comprising a memory, a processor, and a computer program stored on the memory, the processor executing the computer program to implement the steps of any of the methods described above.

[0027] According to one aspect of an embodiment of the present application, the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of any of the methods described above when executed by a processor.

[0028] According to one aspect of an embodiment of the present application, the present application discloses a computer program product, including a computer program, wherein the computer program is executed by a processor to implement the steps of any of the methods described above.

[0029] The embodiments of the present application implement attribution of the user's outbound travel trajectory and can accurately correspond the outbound travel trajectory to the exit gate, no longer limited by the signal problem of GPS positioning and the problem of obtaining location authority. Specifically, the number of exit times of the user at each gate of the subway station gate group is first obtained, and then the user's belonging exit gate is predicted according to the distribution of the user's exit times at each gate of the subway station gate group and the user portrait. The exit gate is the exit that the user can pass through from the gate group. According to the exit gate to which the user belongs, the user's travel trajectory is mapped to the belonging exit gate, and finally, the users who pass through the exit are aggregated through the travel trajectory and user portrait, and then the aggregated users are assigned the location mapped by the exit gate. The whole process does not require GPS positioning, and since the location is not acquired, there is no need to obtain location authority, thereby accurately corresponding the user's outbound travel trajectory to the exit gate.

[0030] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0031] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0033] Figure 1 A flow chart of a method for attributing a user's outbound travel trajectory according to an embodiment of the present application is shown.

[0034] Figure 2 is based on Figure 1 A flowchart of a method for describing the steps of obtaining the number of times a user exits each gate of a subway station gate group is shown in the corresponding embodiment.

[0035] Figure 3 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of predicting the exit gate to which the user belongs based on the distribution of the number of times the user exits each gate group at the subway station and the user portrait.

[0036] Figure 4 According to one embodiment, a flow chart of a method for determining an exit step of a user attribute by executing historical exit bias statistics is shown.

[0037] Figure 5 It is a schematic diagram of a subway station scene according to an embodiment.

[0038] Figure 6 is a data flow diagram according to an embodiment. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present application will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0040] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present application. However, those skilled in the art will appreciate that the technical solution of the present application may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring the present application and making the various aspects of the present application obscure.

[0041] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0042] Terminal applications usually locate their current location through GPS positioning after obtaining the location permission of the app (Application).

[0043] That is to say, the realization of accurate positioning in the existing implementation relies on two conditions, namely: obtaining the location permission of the app and the stability of the GPS signal.

[0044] Once the app's location permission is denied, or the GPS signal is poor or even nonexistent, the current location cannot be determined.

[0045] As a result, this will make it difficult to track and locate the user's exit travel trajectory, whether the user is traveling in the station hall or in the tunnel section between stations, due to the above two conditions. Also, since positioning cannot be performed, the user's exit gate is unknown, and thus the user's itinerary cannot be mapped to the exit gate.

[0046] In view of the inability to achieve positioning during subway travel, an embodiment of the present application provides a method for attributing the user's exit travel trajectory, which does not rely on GPS signals or require location permissions, and can determine the user's exit point in a compliant and imperceptible manner.

[0047] See also Figure 1 , Figure 1 A flow chart of a method for attributing a user's outbound travel trajectory according to an embodiment of the present application is shown. The present application embodiment provides a method for attributing a user's outbound travel trajectory, the method comprising:

[0048] Step S110, obtaining the number of times the user exits each gate of the subway station gate group;

[0049] Step S120, predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate group at the subway station and the user portrait, where the exit is the exit accessible from the gate group;

[0050] Step S130, mapping the user's travel trajectory to the exit to which the user belongs according to the exit to which the user belongs;

[0051] Step S140, users passing through the exit are aggregated through travel trajectories and user portraits, and the aggregated users are assigned a location mapped to the exit.

[0052] These steps are described in detail below.

[0053] Without the need for GPS positioning based on location permissions in subway station halls and tunnel sections between stations, the exit belonging to the user can be obtained, and the user's itinerary and travel trajectory generated by the subway trip can be accurately mapped to this exit, which greatly solves the problem of being unable to obtain location during subway travel, especially obtaining the subway exit, and can realize terminal application functions accurately and quickly based on location during subway travel.

[0054] This application is aimed at users exiting the station and infers their travel trajectory, so as to accurately and quickly determine the user's exit. Therefore, the position in the direction corresponding to this exit will be the position requested by the terminal application to realize its own functions for the user.

[0055] In step S110, the attribution process of the exit travel trajectory is performed for the subway station where the user exits the station in the user's itinerary, so that the user who travels on the subway can correspond to the accurate exit on his travel trajectory.

[0056] During the execution of step S110, the number of exits of each gate on the exit gate group at the subway station where the user exits is obtained, that is, the number of exits of the user at each gate of the exit gate group in the subway station.

[0057] The number of times a user exits the station at each gate is obtained by counting the OriginDestination (OD) data of the user. For example, the OD data of the user indicates the user trip generated when the user enters and exits the station from the gate, as well as the exit station and exit gate involved in the generated user trip.

[0058] For each user trip generated by the user, it can be known that the user exits from a certain gate at a certain station. Therefore, by counting all the user trips of the user, the number of exits from each gate at a station can be determined.

[0059] On this basis, combined with the existing gate information, we determine the gate group of each gate to be counted, as well as the line and city where the gate group is located. Ultimately, the user will obtain complete information on the number of exits from each gate in the subway station gate group.

[0060] In an exemplary embodiment, the travel data exists in the form of a user travel table. Each user travel generated when the user enters or exits the station through the gate is stored in the constructed user travel table.

[0061] Among them, the field information in the user's itinerary includes: date, itinerary identification (trip id), user identification (user id), city identification (city id), line number, entry time, entry station code, entry gate code, exit time, exit station code and exit gate code, etc., which are not listed one by one here.

[0062] In an exemplary embodiment, gate information is collected based on site design to indicate the location of each gate. The gate information exists in the form of a gate information table, and the field information in the table includes: gate code, city identification, line number, site code, gate group number in the station, gate station number, and device type.

[0063] By counting the travel data and matching the travel data with the gate information, we can determine the number of times a user exits a gate and the location of the gate, especially the gate group where the gate is located, so as to ultimately determine the number of times a user exits each gate in the subway station gate group.

[0064] Through the execution of step S110, the gates used by the subway user to exit the station through the gate group at each station are recorded and counted, so as to match the exit gate to the travel trajectory of the user at this station.

[0065] See also Figure 2 , Figure 2 is based on Figure 1 A flowchart of a method for describing the steps of obtaining the number of times a user exits each gate of a subway station gate group is shown in the corresponding embodiment.

[0066] The step S110 of obtaining the number of times a user exits each gate of a subway station gate group provided in the embodiment of the present application includes:

[0067] Step S111, obtaining the user's itinerary data, where the itinerary data at least describes the exit stations and exit gates involved in the user's itinerary;

[0068] Step S112, for the user's travel data, the number of times the user exits each gate of the subway station gate group from the gate information is obtained according to the user's exit station and exit gate.

[0069] These two steps are described in detail below.

[0070] The travel data of each user is obtained. For example, the travel data is the user travel table referred to above. The user travel and the exit gate code in the user travel are obtained from the user travel table.

[0071] For the statistics of the number of times a user exits a station at a gate, the number of times the user exits the station at the corresponding gate is counted according to the exit gate code of each user's trip, and the gate group to which the gate belongs is determined based on the gate information, so as to finally obtain the number of times the user exits the station at each gate in the gate group of the subway station.

[0072] Exemplarily, the gate information is the gate information table mentioned above. For each subway station, each gate group in the station and each gate on the gate group are collected to build a relational database to obtain the gate information table.

[0073] To further explain, the gate information table represents the location of the gate, and the gate code it contains indicates the unique code of the gate in the city. For example, the gate code can be composed of the site code, equipment type and equipment number, and the equipment number is the serial number within the gate station in the gate information table.

[0074] For example, if the site code is 0253, the device type is 01, and the device number is 07, then the gate number is 02530107.

[0075] As mentioned above, in addition to the gate code, the fields in the gate information table also include city identification, line serial number, station code, gate group serial number within the station, gate station serial number and equipment type.

[0076] The city ID is used to uniquely identify the city. In other words, each city has a unique city ID. The station code is used to uniquely identify the station in the city, so that each subway station has a unique code in the city. The gate group serial number in the station is used to identify each group of gates in the station. For example, if there are 4 rows of gates in the station, they correspond to serial numbers 1-4 respectively. The gate station serial number is the equipment number. For example, if there are 10 gates in the station, the equipment number can be a serial number 1-10.

[0077] Based on the gate information table and the user itinerary table, the number of exits of the user at each gate of the subway station gate group is obtained, and the number of exits describes the user's exit behavior. For users who have a user itinerary while traveling on the subway, the number of exits of the exit gate on the subway station gate group corresponding to the destination station in their user itinerary is obtained through the execution of step S110, and then the user itinerary of the user to the corresponding subway station is accurately matched to the exit based on this data, so as to realize the exit location of the user during the exit passage process.

[0078] Step S110 obtains the number of exits of the user at each gate group at a subway station. In the execution of step S120, the distribution of the number of exits and the corresponding user portrait are used to predict the exit gate to which the user belongs, so as to determine the most likely exit gate for the user's user itinerary.

[0079] In step S120, the user portrait is used to describe the user status of the user, which may be composed of constructed user tags. Exemplarily, the user portrait exists in the form of a user tag table, which includes a user ID and several user IDs corresponding to the user ID.

[0080] The user ID will uniquely identify the user. User tags include but are not limited to gender, age, life stage, occupation, total number of rides in the past 7 / 14 / 30 / 90 days, total ride duration in the past 7 / 14 / 30 / 90 days, average entry time for the first user trip on a weekday in the past 7 / 14 / 30 / 90 days, average exit time for the most recent trip on a weekday in the past 7 / 14 / 30 / 90 days, average commuting distance per trip in the past 7 / 14 / 30 / 90 days, total number of rides, high-frequency stops, total number of commercial benefits received, total number of commercial benefits write-offs, total amount of commercial benefits write-offs, average customer order value for commercial benefits write-offs, total number of travel benefits received, number of each card voucher, and frequency of card use.

[0081] The distribution of the number of times a user exits each gate in a subway station gate group describes the number of times a single user exits gate 1 in the gate group, the number of times a single user exits gate 2 in the gate group, and so on, at gate n_zj in the gate group (n_zj is the number of gates in the entire gate group).

[0082] The distribution of the number of times a user exits each gate at a subway station and the user portrait are used as the user's features to predict the exit gate to which the user belongs.

[0083] It should be understood that for a user, the number of exits at a single set of gates within a certain time range, such as a single month, may be low, and is affected by multiple factors such as actual conditions. Therefore, the distribution of the number of exits at each gate group at a subway station and the user portrait are used as the characteristics of the user, which provides a data basis for predicting the exit to which the user belongs, and also improves the richness and scalability of the features, which is conducive to achieving accurate predictions based on existing data.

[0084] It should be noted that the exit port predicted by the user is an exit port corresponding to the gate group, and is an exit port through which the user can exit from the gate group.

[0085] One gate group corresponds to at least one exit, and the exit that a user is most likely to pass through after exiting from a gate on this gate group is the predicted exit to which the user belongs.

[0086] The prediction of the exit to which the user belongs can be achieved by obtaining the probability of the user belonging to each exit through a pre-trained classification model, and then the exit to which the user belongs is finally determined by the probability.

[0087] Exemplarily, the pre-trained model can be a binary classification model, which is characterized by the distribution of the number of times users exit each gate at a subway station gate group and the user portrait. Under this feature, the corresponding direction value of the feature is marked according to the direction of the user after exiting the station, and each direction value uniquely corresponds to an exit that can be accessed from the gate group.

[0088] For example, if the user in the feature mapping passes to the left after exiting the gate group, the marked direction value is 0; correspondingly, if the user in the feature mapping passes to the right after exiting the gate group, the marked direction value is 1.

[0089] Based on this, construct a training data set , where each training data set In a single record in It is the feature of this record, which is used to describe the user status of the corresponding user.

[0090] Specifically, It includes the distribution of the number of times users exit each gate at a subway station at a certain time and the user portrait, and the user portrait can be represented by multiple user tags. Is a user i In the gate unit j Features, Is a user i of m dimensional feature map m dimensional real number space.

[0091] For example, =[Date (YYYYMM), User User tag 1, user User tag 2, ..., user User tags ,user In the gate unit j The number of exits from gate 1 and the number of users In the gate unit j The number of exits from gate 2, ..., user In the gate unit j Gate machine The date (YYYYMM) represents the month, such as 202312, which means December 2023. The date feature indicates the time range corresponding to other features. Refers to the user No. User tags, i.e. Represents the number of users, Representative User The number of gates facing when exiting a subway station, Represents the number of user tags, It is the direction value of the feature annotation in a single record of the corresponding training dataset. Representative User Given the corresponding features (especially the actual number of exits), the direction of the final exit traffic.

[0092] That is, in a single record of the training data set is the direction value of the annotation. For example, the user In the gate unit j Turn left after exiting the station. , if you go right, then .

[0093] By training the model with the constructed training data set, a model is obtained that can accurately predict the exit to which the user belongs, providing the user with accurate judgment of the exit affiliation. There is no need to obtain the location, that is, it is no longer restricted by GPS positioning and the acquisition of location permissions.

[0094] Furthermore, the training for exit prediction will be conducted for gate groups corresponding to only one exit. A training data set is constructed for the gate group corresponding to the only exit, and features are constructed based on all records related to the gate group, and direction values ​​are annotated for the constructed features based on the unique direction of the gate group.

[0095] Specifically, the number of times the user exits each gate of the gate group in the subway station is obtained through the travel data and the gate information, that is, the user's gate group exit data of user-subway station-gate group-gate-exit number is obtained, which can be in a tabular form, that is, a table maintained according to fields such as user, subway station, gate group, gate, and exit number, and the user gate group exit data corresponding only to the only exit is obtained therefrom, and the number of times the user exits each gate of the gate group in the subway station is obtained from the user gate group exit data corresponding only to the only exit, and the feature is constructed based on this.

[0096] In addition, the corresponding user portraits will be extracted for feature construction, and the constructed features will be labeled with directional values ​​to finally form a training data set.

[0097] The constructed training data set shields the influence of other exits and only considers the prediction of the user's exit in the feature dimension, so that the subsequent predictions will not be affected by other factors, which will greatly improve the accuracy and reliability of the prediction.

[0098] Exemplarily, a gate group entrance and exit distance relationship will also be constructed. The gate group entrance and exit distance relationship is used to indicate the distance of each gate of the gate group in a site relative to the exits in each direction. Therefore, after predicting the most likely direction of the user after exiting the gate, it can be directly mapped to the closest exit based on the gate group entrance and exit distance relationship. This exit is the exit to which the predicted user belongs.

[0099] As mentioned above, the model trained by constructing the obtained training data set can be a binary classification model, and thus, the obtained binary classification model will be used to predict the exit to which the user belongs. Specifically, the binary classification model is used to predict the most likely direction of the user after exiting the gate group based on the number of exits of the user at each gate group on the subway station and the user portrait, and the exit mapped by the direction is used as the exit to which the user belongs.

[0100] To further illustrate, a prediction data set is constructed based on the number of times a user exits each gate at a subway station gate group and the user profile. , where, unlike the training data set, the prediction data set is not limited to the gate group corresponding to the only exit; in other words, it will not distinguish whether the gate group corresponds to the only exit, and all the user's data will be used to construct the prediction data set, and then the exit to which the user belongs will be predicted based on the features of the constructed prediction data set.

[0101] Prediction Dataset In each record Indicates users whose exit port has not yet been determined i In the gate unit j The feature, as mentioned above, describes the user in terms of content i In the gate unit j The number of exits and user tags of each gate, the list of features included and similar.

[0102] Specifically, to obtain the applicable two-classification model , first construct t The problem loss function during round iteration is:

[0103]

[0104] in, It is ij The record is in t The predicted value of the round iteration, For the t A tree, , q Representation Tree The structure, w For Trees The weights of the leaves in To indicate the i The weight of a leaf, It's about trees The regular term of the complexity of At the point Making a second-order approximation we get:

[0105]

[0106] in, ;

[0107]

[0108] So far, the optimal solution to the problem is:

[0109]

[0110] Among them, q is a tree with a fixed structure, γ and λ are the first-order and second-order regularization coefficients respectively.

[0111] The optimal solution of each round based on the training data set can be iteratively converged to obtain a binary classification model .

[0112] Based on the obtained binary classification model , the prediction data set Each record of Use two classification models one by one Implement predictions and get users i In the gate unit j The characteristics of the gate are biased towards one direction, that is, they belong to the gate unit. j The probability of the corresponding exit .

[0113] For example, if the gate unit j Corresponding to two exits. In other words, the gate unit j Post-exit users i There are two directions, each direction corresponds to an exit, then the probability of leaning towards the other direction, that is, belonging to the other exit, is 1- .

[0114] In addition, if the gate unit j There are more than two exits in one direction, that is, the exit in this direction is not unique, then the binary classification model is used to predict the user i In the gate unit j When exiting the station and heading towards a direction with more than two exits, the user will be determined based on the traffic of each exit. i The exit that is most likely to be passed by, which is the user i The exit gate to which you belong.

[0115] Specifically, each exit in one direction has its own flow, which can be sensed by the passenger flow counter set at the exit. The flow ratio of each exit is determined by the flow corresponding to each exit, and then the user is determined according to the flow ratio. i The exit gate to which you belong.

[0116] Further explanation, for determining the user based on the flow of each exit i The exit with a high probability is a random number determined by the proportion of the user. i The execution process of attribution. The ratio refers to the traffic proportion of each exit.

[0117] When predicting the user through the binary classification model i In the gate unit j After exiting the station, if there are multiple exits in the exit direction, the traffic proportion of each exit and the user will be calculated. i The random number taken determines the user i The exit gate to which you belong.

[0118] For multiple exits in the outbound direction, the random number ranges mapped to each are constructed according to the traffic proportion of each exit. For example, there are three exits in the same outbound direction, and the traffic proportions of each of these three exits are 0.3, 0.2, and 0.5 respectively. Thus, the random number range mapped to each exit is constructed, that is, the random number range constructed for the first exit with a traffic proportion of 0.3 is [0, 0.3), the random number range constructed for the second exit with a traffic proportion of 0.2 is [0.3, 0.3 + 0.2), and the random number range constructed for the third exit with a traffic proportion of 0.5 is [0.3 + 0.2, 0.3 + 0.2 + 0.5).

[0119] For users i Take a random number between 0 and 1, and determine the amount that belongs to the user based on the random number range into which the random number falls. i If the random number falls within the range [0,0.3), the user itinerary of user i corresponds to the first exit; if the random number falls within the range [0.3,0.3+0.2), the user i Belongs to the second exit; if the random number falls within the random number range [0.3+0.2,0.3+0.2+0.5), then the user i Belongs to the third exit.

[0120] See also Figure 3 , Figure 3 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of predicting the exit gate to which the user belongs based on the distribution of the number of times the user exits each gate group at the subway station and the user portrait.

[0121] The step S120 provided in the embodiment of the present application of predicting the exit gate to which the user belongs based on the distribution of the number of exits of the user at each gate group of the subway station and the user portrait includes:

[0122] Step S121, obtaining the probability of the user's exit direction based on the number of exits of the user at each gate on the subway station gate group and the prediction of the user portrait;

[0123] Step S122, determining the exit gate to which the user belongs according to the probability of the user's exit direction.

[0124] These two steps are described in detail below.

[0125] During the execution of step S121, features are constructed based on the number of times the user exits each gate at the gate group at the subway station and the user labels contained in the user portrait, and predictions are made through a pre-trained model, such as the binary classification model mentioned above, to obtain the probability of each exit direction after the user exits the gate group at the designated subway station.

[0126] There are more than one direction that a user can go out of a gate unit. For example, in many cases, a user will have one or two exit directions after exiting a gate unit, and each exit direction has an accessible exit.

[0127] After obtaining the probability of the user's exit direction, the user's travel direction after exiting the gate unit can be determined based on this probability, that is, the exit direction corresponding to the high probability.

[0128] The exit in the exit direction corresponding to the high probability is determined. In an exemplary embodiment, when there is only one exit in the exit direction corresponding to the high probability, the exit closest to the exit direction is determined based on the distance relationship between the exit and entrance of the gate group obtained in the exit direction corresponding to the high probability, and this exit is used as the exit to which the user belongs.

[0129] In another exemplary embodiment, there are more than two exits in the exit direction corresponding to the high probability. For example, the import and export channels in this exit direction are further branched into more than two exits. At this time, the exit to which the user belongs will be determined from the two or more exits based on the traffic proportion of each exit and the obtained random number.

[0130] As a result, there is no need to obtain the user's location, that is, there is no need to obtain location permission and then perform GPS positioning. The user's itinerary and user trajectory can also be accurately matched to the predicted exit, thereby accurately inferring the user's trajectory after exiting the station.

[0131] In another embodiment of the present application, before the step S120 of predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate group of the subway station and the user portrait, the attribution method of the user's exit travel trajectory provided by the present application further includes the following steps:

[0132] Determine whether the number of exits of the user at each gate of the subway station gate group is less than the set threshold. If it is less than the set threshold, jump to step S120, i.e., predict the user's exit direction;

[0133] If the number of times a user exits the subway station through each gate of the gate group is not less than the set threshold, the exit gate to which the user belongs is determined by performing historical exit gate bias statistics.

[0134] Specifically, it should be noted first that if a user frequently exits a station from a gate group, it means that the gate corresponding to the gate group in an exit direction is preferred by the user. For such users, the exit direction to which they belong will no longer be predicted. The exit to which the user belongs can be determined only through the bias statistics of the historical exit gates, thereby reducing the computational complexity and improving execution efficiency.

[0135] The number of times a user exits a subway station gate group is used to determine whether the user exits the current subway station gate group more frequently. The number of times a user exits a subway station gate group can be obtained based on the user's travel data and gate information, and further, can be obtained from the user's gate group exit data constructed by the travel data and gate information. Of course, it is not limited to this, and can also be obtained by counting the exit data of each gate of the user's subway station gate group, which is not limited here.

[0136] Exemplarily, the set threshold may be 5. That is to say, if a user exits a gate group at a subway station no less than 5 times within a set time range, it means that an exit direction corresponding to the gate group and an exit gate in the exit direction are both consistent with the user's exit passage, thereby determining that the exit gate is the user's frequently used exit gate.

[0137] To further explain, for the number of exits not less than the set threshold, the gate machine preferred by the user will be respectively counted, that is, according to the distribution of the number of exits of the user in the gate machine group, the user prefers the left half or the right half of the gate machine group. Regardless of the left half or the right half of the gate machine, it corresponds to an exit direction. The exit direction that the user will pass through after exiting the station can be determined by the gate machine to which the user prefers, and then the exit in the exit direction is the exit to which the user belongs.

[0138] At this point, it should be added that if the number of gates in a gate group is an odd number, the middle gate will belong to both the left and right half groups of gates. Therefore, for users exiting the station at the middle gate, it will be counted as the number of times the user exits the station at the left half group of gates and the number of times the user exits the station at the right half group of gates.

[0139] If the number of times a user exits a subway station gate is less than the set threshold, it means that neither the subway station nor the gate is frequently used by users. Therefore, it is necessary to construct features based on richer data, that is, the distribution of the number of times users exit each gate at the subway station gate and the user portrait as mentioned above, and then implement predictions through the pre-built model.

[0140] See also Figure 4 , Figure 4 According to one embodiment, a flow chart of a method for determining an exit step of a user attribute by executing historical exit bias statistics is shown.

[0141] The steps of determining the exit port of a user attribute by performing historical exit port bias statistics provided in the embodiment of the present application include:

[0142] Step S301, determining the gate that the user prefers in the gate group according to the distribution statistics of the number of times the user exits the station at each gate group in the subway station;

[0143] Step S302: The gate position determines that the exit on the same side is the exit to which the user belongs.

[0144] For a gate group, statistics are performed on the distribution of the number of exits of a user at each gate in the gate group to determine whether the user prefers to exit at the left half of the gates in the gate group or the right half.

[0145] According to the statistical determination of the user's preference at the gate group, the exit direction and exit gate can be determined, and then the exit gate on the same side is the user's frequently used exit gate. This exit gate is used as the user's belonging exit gate, and the user's itinerary and travel trajectory are matched with this exit gate.

[0146] Therefore, after the user's exit is determined, the user's travel trajectory is mapped to the exit according to the user's exit through the execution of step S130, and the user's itinerary in the subway travel will also be mapped to this exit.

[0147] In other words, for the exit corresponding to the travel trajectory, on the one hand, we can know which users have passed through this exit, and then match these users with the positions at this exit, that is, determine which users correspond to the positions at this exit, and match the user portraits of these users with the positions at this exit, such as media locations, shop locations, etc.

[0148] On the other hand, the exit corresponding to the travel trajectory provides the tracked travel trajectory within the station, breaking out of the restricted GPS positioning and the required location permissions, and can also obtain the user's in-station trajectory, enhancing the in-station tracking performance.

[0149] As the user's travel trajectory out of the station and the exit that can be matched in the user's itinerary, step S140 is executed to aggregate the users at the location at the exit, thereby assigning the aggregated users to the location at the exit.

[0150] The user aggregation referred to is to determine the corresponding user group for the location at the exit, and to describe and characterize the aggregated user group through the user profiles of the aggregated users.

[0151] The travel trajectory is mapped to the corresponding exit so that the corresponding user trip can be mapped to the exit, and then the user who generated the user trip is also mapped to the exit, so that the users corresponding to the same exit are aggregated.

[0152] The location mapped by the exit refers to the location on the exit. For example, in terms of location type, the location includes but is not limited to the media location, the store location, etc.; in terms of geographical location, the location mapped by the exit is any location in the direction of the exit, such as the location inside the station in the direction of the exit, the exit passage in the direction of the exit, and the location outside the station exiting from the exit.

[0153] In terms of data, users exist in the form of user portraits and their travel trajectories. Therefore, user aggregation is achieved in the form of travel trajectories and user portraits, so that the user portraits corresponding to the aggregated users are assigned to the locations mapped by the exits, so as to accurately locate and describe the user characteristics of the location through the assigned user portraits. For example, the user portraits of the aggregated users are assigned to the media locations to construct the corresponding media portraits.

[0154] Based on this, in one embodiment of the present application, after executing step S140, the attribution method of the user's outbound travel trajectory provided by the present application further includes:

[0155] For the location corresponding to the exit, the user profile of the aggregated user is assigned to the location for use in the delivery control at the location, which includes the media location and the store location.

[0156] The delivery control at a position refers to the control of the content delivered at the position. The content referred to includes media content and commodities. Based on the user profile of the aggregated user, the content delivered at the position and the delivery frequency are controlled.

[0157] In another exemplary embodiment, for the user exit travel trajectory attribution method provided in this application, a sliding time window is set, for example, the sliding time window is set to 30 days. The sliding time window is used to control the number of exits of the user at each gate of the subway station gate group, and even the acquisition of the user portrait, so as to ensure the validity of the obtained data, thereby enhancing the accuracy of the location corresponding to the user's itinerary.

[0158] Correspondingly, the user's travel data and gate information are also updated with the addition of the user's travel and the change of the gate position. The travel data and gate information are controlled by the sliding time window to obtain the number of exits of the user at each gate of the subway station gate group.

[0159] In an exemplary embodiment, a distance factor is also set, and the distance factor is used to measure the distance between the elevator facilities from the platform to the station hall and the gate position.

[0160] That is, for the gate machine where the user has exited the subway station, it is determined whether the distance between the elevator facility and the gate machine position exceeds the distance factor. If it exceeds the distance factor, the exit to which the user belongs is determined through the execution process.

[0161] If the distance between the elevator facility and the gate does not exceed the set distance factor, the user is determined to have chosen the gate closest to the elevator facility to exit, and the exit at the same location as the gate is the user's exit.

[0162] In this way, the user's exit behavior can be screened, thereby shielding the impact of the distance between the elevator facilities and the gate.

[0163] The following is a specific example to illustrate the attribution process of the user's outbound travel trajectory as described above.

[0164] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram of a subway station scene according to an embodiment. Figure 5 In the subway station scene shown, four gate groups divide the gate area for the subway station hall. Users going from the platform to the station hall will exit the station through a gate group and pass through an exit.

[0165] For example, in the gate groups numbered 1 to 6, the corresponding exits are Exit A and Exit B, that is, for exiting users, the left half of the group corresponds to Exit A and the right half of the group corresponds to Exit B.

[0166] Take a user exiting the station at a gate group numbered 1 to 6 as an example. Figure 6 , Figure 6 is a data flow diagram according to an embodiment. Figure 5 The gate group shown is composed of gates No. 1 to 6. Based on the user itinerary table and gate information table, the user gate group exit data is obtained, that is, the user gate group code table under the user code exit. The user gate group code table indicates the number of code swiping times of each gate of each gate group at a certain subway station in the past n days. Figure 5 The number of times marked on gates 1 to 6.

[0167] The number of times this gate machine scans the code is the number of times the aforementioned user has exited the station at each gate machine in the subway station gate machine group.

[0168] Through the gate groups numbered 1 to 6, the user's exit is locked to Exit A and Exit B, excluding Exit C and Exit D.

[0169] According to the number of gate code swiping times, it is determined that the number of times the user has exited the subway station gate group is 29, which is greater than the set threshold of 5. The historical exit bias statistics are then performed according to the number of gate code swiping times corresponding to each gate, and the exit to which the user belongs is then determined. Specifically, the number of gate code swiping times for gates 1-3 are 10, 8, and 7 respectively, and the number of gates 4-6 are 3, 0, and 1 respectively. The user prefers the gates 1-3. Therefore, Exit A, which is preferred by the gates 1-3, is the user's common exit at the subway station.

[0170] If the number of times the user exits the subway station gate is less than the set threshold, Figure 6 The data flow shown is to construct a prediction data set and hand it over to the binary classification model for prediction. The binary classification model is trained by the constructed training data set, that is, the binary classification model training record table.

[0171] Through the exemplary embodiments described above, the limitations and shortcomings of obtaining user location information based on app tracking to determine the exit to which they belong are avoided; specifically, there is no need to obtain location permissions and be restricted by GPS signals, nor will it affect the exposure and implementation of front-end services, and there will be no situation where the proportion of users covered by location acquisition is far lower than expected, thereby achieving a high population coverage rate.

[0172] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0173] In an exemplary embodiment of the present application, a computer program medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the method described in the above method embodiment.

[0174] According to one embodiment of the present application, a program product for implementing the method in the above method embodiment is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0175] The program product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0176] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0177] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0178] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0179] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0180] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0181] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0182] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for attributing a user's outbound travel trajectory, characterized in that: The method comprises: For users who have a user trip while traveling by subway, the number of times the user exits each gate at a gate group at a subway station is obtained, where the subway station is the destination station in the user's trip; Predict the most likely direction of the user after exiting from the gate group based on the distribution of the number of exits of the user at each gate group at the subway station and the user portrait, and use the exit mapped by the direction as the exit to which the user belongs, which is the exit through which the user exits from the gate group; According to the exit to which the user belongs, the travel trajectory of the user is matched to the exit to which the user belongs; Aggregate users passing through the exit through the travel trajectory and user portrait, and assign the aggregated users a location mapped to the exit, where the location is the location requested by the terminal application for the user to realize its own function; Wherein, the prediction is realized by a pre-trained classification model, and the training data set of the classification model is constructed for the gate group corresponding to the only exit.

2. The method according to claim 1, characterized in that The method of obtaining the number of times a user exits each gate at a subway station gate group includes: Acquire the itinerary data of the user, wherein the itinerary data at least describes the exit stations and exit gates involved in the generated user itinerary of the user; For the user's travel data, the number of times the user exits each gate of the subway station gate group is obtained from the gate information according to the user's exit station and exit gate.

3. The method according to claim 2, characterized in that The method predicts the most likely direction of the user after exiting from the gate group according to the distribution of the number of exits of the user at each gate group at the subway station and the user portrait, and uses the exit mapped by the direction as the exit to which the user belongs, including: Predicting the number of exits of the user at each gate on the subway station gate group and the user portrait, obtaining the probability of the user's exit direction, the exit direction corresponding to at least one of the exits; The exit gate to which the user belongs is determined according to the probability of the user's exit direction.

4. The method according to claim 1, characterized in that: Before predicting the exit to which the user belongs based on the distribution of the number of exits of the user at each gate group of the subway station and the user portrait, the method further includes: Determine whether the number of times the user exits the subway station gate is less than a set threshold. If so, jump to execute the prediction of the user's exit direction.

5. The method according to claim 4, characterized in that The method further comprises: If the number of times the user exits the subway station gate is not less than a set threshold, the exit to which the user belongs is determined by performing historical exit bias statistics.

6. The method according to claim 5, characterized in that The method of determining the exit port to which the user belongs by performing historical exit port bias statistics includes: Determine the gate that the user prefers in the gate group according to the distribution statistics of the number of times the user exits the station at each gate group at the subway station; According to the location of the gate, the exit located on the same side is determined as the exit to which the user belongs.

7. The method according to claim 1, characterized in that After aggregating the users passing through the exit through the travel trajectory and user portrait, the method further includes: For the location corresponding to the exit, the user profile of the aggregated user is assigned to the location for use in the delivery control at the location, and the location includes a media location and a store location.

8. A system for attributing user outbound travel trajectories, the system comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed by a processor to implement the steps of the method according to any one of claims 1 to 7.

Images