A method, device, equipment and medium for transferring target users in a target area

Abstract

The present application relates to the field of user data processing and communication technology, and in particular to a method, device, equipment and medium for transferring target users in a target area, the method comprising: collecting an initial activity data set corresponding to each target user in the target area according to a preset time period; inputting the initial activity data set corresponding to each target user into a target probability prediction model, and obtaining the user transfer probability of each preset activity location predicted by the target probability prediction model; determining the number of user transfers at each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location; scheduling a number of preset vehicles according to the number of user transfers at each preset activity location and the status information of each preset vehicle obtained in real time, so as to realize the transfer of target users in the target area. The present invention can reasonably allocate vehicles and realize the rapid transfer of users.

Description

Technical Field

[0001] The present invention relates to the field of user data processing and communication technology, and in particular to a method, device, equipment and medium for transferring a target user within a target area. Background Art

[0002] When the activity area is large and the distance between each activity location is far, for example, the distance between each sub-attraction in a scenic area is far, in order to save users' time and energy, vehicles are needed to pick up tourists from one activity location and send them to the next activity location. However, it is currently impossible to know the number of tourists to be transferred from each activity location. How to predict the number of people to be transferred from each activity location and achieve reasonable allocation of vehicles is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, equipment and medium for transferring target users in a target area, so as to obtain the number of users transferred to each activity location and realize the reasonable allocation of vehicles.

[0004] According to a first aspect of the present invention, a method for transferring a target user within a target area is provided, comprising the following steps:

[0005] According to a preset time period, an initial activity data set corresponding to each target user among a plurality of target users in a target area is collected; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0006] The initial activity data set corresponding to each target user is input into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0007] The number of user transfers to each preset activity location is determined according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0008] According to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, a plurality of preset vehicles are dispatched to realize the transfer of target users in the target area.

[0009] Furthermore, the target probability prediction model is trained through the following steps:

[0010] A historical activity data set corresponding to each target historical user in a historical time period of the target area is obtained; the historical activity data set corresponding to the target historical user includes time points when the target historical user enters and leaves each historical activity location corresponding to the target historical user.

[0011] According to a preset time period, a historical activity data set corresponding to each key user at the target collection time is obtained from the historical activity data set corresponding to each target historical user; the key user is a target historical user who has entered any preset activity location before the target collection time.

[0012] If the target collection time is in the first preset time period, the historical activity data set corresponding to each key user is input into the preset probability prediction model for training to obtain a first probability prediction model.

[0013] If the target collection time is in the second preset time period, the historical activity data set corresponding to each key user is input into the preset probability prediction model for training to obtain a second probability prediction model.

[0014] Furthermore, the target probability prediction model is determined through the following steps:

[0015] When the time point at which each target user enters the first initial activity location corresponding to himself is within the first preset time period, the first probability prediction model is determined as the target probability prediction model.

[0016] When the time point at which the target user enters the first initial activity location corresponding to the target user is within the second preset time period, the second probability prediction model is determined as the target probability prediction model.

[0017] Further, according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location, determining the number of user transfers to each preset activity location includes the following steps:

[0018] According to the time point when each target user enters each initial activity location corresponding to himself, the current activity trajectory corresponding to each target user is obtained; the current activity trajectory corresponding to the target user is a trajectory composed of several initial activity locations where he has been active in order of activity.

[0019] According to the initial activity data set corresponding to each target user, a number of intermediate users are obtained; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set.

[0020] According to the last initial activity location in the current activity track corresponding to each intermediate user, the number of target users at each preset activity location at the current collection time is obtained.

[0021] The number of user transfers at each preset activity location is determined according to the number of target users at each preset activity location at the current collection moment and the user transfer probability at each preset activity location.

[0022] Furthermore, according to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, scheduling a plurality of preset vehicles includes the following steps:

[0023] According to the status information of each preset vehicle acquired in real time, a plurality of intermediate vehicles are acquired; the status information of the preset vehicle includes the position information and idle information of the preset vehicle; the intermediate vehicle is any preset vehicle in an idle state.

[0024] According to the number of users transferred to each preset activity location, a number of intermediate vehicles are allocated in proportion, so that a number of preset vehicles are dispatched according to the obtained number of intermediate vehicles allocated to each preset activity location.

[0025] Furthermore, according to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, scheduling a plurality of preset vehicles includes the following steps:

[0026] Obtain the time point at which the target user of each preset activity location enters the preset activity location at the current collection time.

[0027] According to the sequence of time points at which the target users enter the preset activity location, the target users transferred by the previous users are all determined as transferred users in the corresponding preset activity location.

[0028] The current activity track corresponding to each transferred user is obtained; the current activity track corresponding to the transferred user is a track formed by arranging several initial activity locations where the user has been active in the order of activity.

[0029] The current activity track corresponding to each transferred user is compared with a plurality of pre-stored historical activity tracks to determine the next preferred activity location of each transferred user.

[0030] According to the next preferred activity location of each transferred user, a number of intermediate vehicles are dispatched; the intermediate vehicle is any preset vehicle in an idle state.

[0031] According to a second aspect of the present invention, a device for transferring a target user in a target area is provided, the device comprising:

[0032] The collection module is used to collect an initial activity data set corresponding to each target user among a plurality of target users in a target area according to a preset time period; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0033] The first acquisition module is used to input the initial activity data set corresponding to each target user into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0034] The first determining module is used to determine the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0035] The first scheduling module is used to schedule a plurality of preset vehicles according to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, so as to realize the transfer of target users in the target area.

[0036] Furthermore, the device also includes a model training module, and the model training module includes:

[0037] The second acquisition module is used to acquire a historical activity data set corresponding to each target historical user within a historical time period of the target area; the historical activity data set corresponding to the target historical user includes time points when the target historical user enters and leaves each historical activity location corresponding to the target historical user.

[0038] The third acquisition module is used to acquire the historical activity data set corresponding to each key user at the target collection time from the historical activity data set corresponding to each target historical user according to a preset time period; the key user is a target historical user who has entered any preset activity location before the target collection time.

[0039] The first training module is used to input the historical activity data set corresponding to each key user into a preset probability prediction model for training if the target collection time is in a first preset time period to obtain a first probability prediction model.

[0040] The second training module is used to input the historical activity data set corresponding to each key user into the preset probability prediction model for training if the target collection time is in the second preset time period to obtain a second probability prediction model.

[0041] Furthermore, the first acquisition module includes:

[0042] The second determination module is used to determine the first probability prediction model as the target probability prediction model when the time point when each target user enters the first initial activity location corresponding to himself is in the first preset time period.

[0043] The third determination module is used to determine the second probability prediction model as the target probability prediction model when the time point at which the target user enters the first initial activity location corresponding to himself is in the second preset time period.

[0044] Furthermore, the first determining module includes:

[0045] The fourth acquisition module is used to acquire the current activity trajectory corresponding to each target user according to the time point when each target user enters each initial activity location corresponding to himself; the current activity trajectory corresponding to the target user is a trajectory composed of several initial activity locations where he has been active in order of activity.

[0046] The fifth acquisition module is used to acquire a number of intermediate users according to the initial activity data set corresponding to each target user; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set.

[0047] The sixth acquisition module is used to acquire the number of target users at each preset activity location at the current collection time according to the last initial activity location in the current activity track corresponding to each intermediate user.

[0048] The fourth determination module is used to determine the number of user transfers at each preset activity location according to the number of target users at each preset activity location and the user transfer probability at each preset activity location at the current collection moment.

[0049] Furthermore, the first scheduling module includes:

[0050] The seventh acquisition module is used to acquire a number of intermediate vehicles based on the status information of each preset vehicle acquired in real time; the status information of the preset vehicle includes the location information and idle information of the preset vehicle; the intermediate vehicle is any preset vehicle in an idle state.

[0051] The allocation module is used to allocate a number of intermediate vehicles in proportion according to the number of user transfers at each preset activity location, so as to dispatch a number of preset vehicles according to the obtained number of intermediate vehicles allocated to each preset activity location.

[0052] Furthermore, the first scheduling module includes:

[0053] The eighth acquisition module is used to acquire the time point at which the target user of each preset activity location enters the preset activity location at the current collection time.

[0054] The fifth determining module is used to determine the target users transferred by the previous user as the transferred users in the corresponding preset activity location according to the order of the time points when the target users enter the preset activity location.

[0055] The ninth acquisition module is used to acquire the current activity track corresponding to each transferred user; the current activity track corresponding to the transferred user is a track composed of several initial activity locations where the user has been active in an order of activity.

[0056] The sixth determination module is used to compare the current activity track corresponding to each transferred user with a plurality of pre-stored historical activity tracks to determine the next preferred activity location of each transferred user.

[0057] The second scheduling module is used to schedule a number of intermediate vehicles according to the next preferred activity location of each transferred user; the intermediate vehicle is any preset vehicle in an idle state.

[0058] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for transferring a target user within a target area when executing the computer program.

[0059] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for transferring a target user within a target area is implemented.

[0060] Compared with the prior art, the present invention has at least the following beneficial effects:

[0061] The present invention collects the initial activity data set of each target user in the target area every period, that is, the activity locations that each target user has entered at the current collection time, as well as the time points of entering and leaving each activity location before the current collection time, and then inputs the initial activity data set into the target probability prediction model, so as to obtain the user transfer probability of each preset activity location, and then combine the number of target users at each preset activity location to calculate the number of user transfers at each preset activity location, and also predict the next preferred activity location of each target user according to the historical activity trajectory, and then reasonably allocate the number of vehicles to each preset activity location according to the position information and idle status information of each preset vehicle obtained in real time, so as to improve the transfer efficiency of the target users in the target area and save the physical strength and time of the target users. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 A flow chart of a method for transferring a target user within a target area provided in Embodiment 1 of the present invention;

[0064] Figure 2 A flowchart of the steps of training a target probability prediction model provided in the first embodiment of the present invention;

[0065] Figure 3 A flowchart of the steps of determining a target historical user provided in the first embodiment of the present invention;

[0066] Figure 4 A flowchart of the steps of determining a target probability prediction model provided in the first embodiment of the present invention;

[0067] Figure 5 A flowchart of step S300 provided in the first embodiment of the present invention;

[0068] Figure 6 A flowchart of step S400 provided in the first embodiment of the present invention;

[0069] Figure 7 A flowchart of the steps of determining an intermediate vehicle provided in the first embodiment of the present invention;

[0070] Figure 8 Another flow chart of step S400 provided in the first embodiment of the present invention;

[0071] Fig. 9 A schematic diagram of a device for transferring a target user within a target area provided in the first embodiment of the present invention;

[0072] Fig.10 A schematic diagram of a model training module provided in Embodiment 2 of the present invention;

[0073] Fig.11 A schematic diagram of the module 200 provided in the second embodiment of the present invention;

[0074] Fig.12 A schematic diagram of the module 300 provided in the second embodiment of the present invention;

[0075] Fig.13 A schematic diagram of the module 400 provided in the second embodiment of the present invention;

[0076] Fig.14 Another schematic diagram of the module 400 provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0078] Embodiment 1

[0079] like Figure 1 As shown, this embodiment 1 provides a method for transferring a target user in a target area, including the following steps:

[0080] S100, collecting an initial activity data set corresponding to each target user among a plurality of target users in a target area according to a preset time period; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0081] Specifically, the initial activity data set corresponding to the i-th target user is C i ={C i1 , C i2 , ..., C ip , ..., C iq(i)}, C ip ={C ip1 , C ip2 , C ip3}, where C ip1 is the time point when the i-th target user enters the corresponding p-th initial activity location, C ip2 is the time point when the i-th target user leaves the corresponding p-th initial activity location, C ip3 is the active time of the i-th target user in its corresponding p-th initial activity location, i=1, 2, ..., m, m is the number of target users in the target area at the current collection time, p=1, 2, ..., q(i), q(i) is the number of preset activity locations where the i-th target user has been active before the current collection time; it can be understood that when obtaining target user data, only the target user data existing at the current collection time can be obtained. When C iq(i)When it is the location where the i-th target user is currently active, the time point at which the target user leaves the activity location is empty.

[0082] Optionally, the initial activity data set also includes but is not limited to the time, season, age, and average daily steps of the target user entering the target area, so as to obtain the impact of different seasons and different user physical fitness on the user transfer probability, so as to fine-tune the prediction results of the target probability prediction model; for example, when users are generally younger and have better physical fitness, after a certain period of activity, the user's transfer probability will be greater than the predicted result.

[0083] Specifically, the initial activity data set is obtained through video surveillance of the scenic spot, WiFi in the target area connected to the target user's device, or an APP authorized by the target user, which will not be described in detail here.

[0084] S200, inputting the initial activity data set corresponding to each target user into a target probability prediction model, and obtaining the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0085] Preferably, the target probability prediction model is trained by the following steps: Figure 2 As shown:

[0086] S001, obtaining a historical activity data set corresponding to each target historical user in a historical time period of a target area; the historical activity data set corresponding to the target historical user includes time points when the target historical user enters and leaves each historical activity location corresponding to the target historical user.

[0087] Preferably, in S001, the target historical user is determined by the following steps: Figure 3 As shown:

[0088] S0011, obtaining a historical activity data set corresponding to each initial historical user within a historical time period of a target area; the historical activity data set corresponding to the initial historical user includes time points at which the initial historical user enters and leaves each historical activity location corresponding to the initial historical user.

[0089] Specifically, the initial historical user refers to any historical user in the historical time period of the target area.

[0090] S0012, acquiring an initial activity track corresponding to each initial historical user according to the historical activity data set corresponding to each initial historical user.

[0091] Specifically, the initial activity track corresponding to the initial historical user is a list of several activity locations where the user has been active arranged in the order of activities.

[0092] S0013, performing deduplication processing on a number of initial activity trajectories corresponding to a number of historical visitors, and obtaining a list of intermediate activity trajectories.

[0093] Specifically, the intermediate activity trajectory list is B={B1, B2, ..., B e , ..., B f}, where B e is the e-th intermediate activity trajectory, e=1, 2, ..., f, f is the number of intermediate activity trajectories, and the intermediate activity trajectory is any initial activity trajectory obtained after deduplication processing of several initial activity trajectories.

[0094] S0014, acquiring a number of key activity trajectories from the intermediate activity trajectory list according to the initial historical user quantity corresponding to each intermediate activity trajectory in the intermediate activity trajectory list and a preset ratio threshold.

[0095] Specifically, when L e / ∑ f k=1 L k ≥λ, B e Determined as the key activity trajectory, where L e For B e The corresponding initial number of historical users, L k is the initial number of historical users corresponding to the kth intermediate activity trajectory, and λ is a preset ratio threshold, for example, λ is 0.1.

[0096] S0015, determining the initial historical user corresponding to each key activity track as the target historical user.

[0097] As mentioned above, since the order of activity locations for each user is different, there will be several activity routes. In the training process, only the commonly used routes need to be used as a feature to filter out routes with very few people, such as users who only visit one location and leave due to special circumstances. By screening key activity trajectories, the data is cleaned and preprocessed to make the training results of the model more reasonable.

[0098] S002, according to a preset time period, obtaining a historical activity data set corresponding to each key user at the target collection time from the historical activity data set corresponding to each target historical user; the key user is a target historical user who has entered any preset activity location before the target collection time.

[0099] S003: If the target collection time is in a first preset time period, the historical activity data set corresponding to each key user is input into a preset probability prediction model for training to obtain a first probability prediction model.

[0100] Optionally, the first time period is a time period between 8:00am-12:00am.

[0101] Specifically, the user transfer probability output by the preset probability prediction model is compared with the actual user transfer probability, and the parameters of the preset probability prediction model are corrected until the error between the user transfer probability output by the preset probability prediction model and the actual user transfer probability meets the preset threshold, so as to obtain the first probability prediction model.

[0102] S004, if the target collection time is in the second preset time period, the historical activity data set corresponding to each key user is input into the preset probability prediction model for training to obtain a second probability prediction model; the training process of the second probability prediction model and the training process of the first probability prediction model are not repeated here.

[0103] Optionally, the second time period is a time period between 12:00am-17:00am.

[0104] As mentioned above, due to the different times of entering the target area, the activity duration will be different. For example, the activity duration at each activity location and the number of activity locations for users who are active for one day and half a day are quite different. Therefore, different activity data sets are obtained according to the time periods of different times of entering the target area to train the subsequent prediction models separately and improve the prediction accuracy.

[0105] Specifically, in S200, the target probability prediction model is determined through the following steps: Figure 4 As shown:

[0106] S201, when the time point at which each target user enters the first initial activity location corresponding to himself is in a first preset time period, the first probability prediction model is determined as the target probability prediction model.

[0107] S202: When the time point at which the target user enters the first initial activity location corresponding to the target user is in the second preset time period, the second probability prediction model is determined as the target probability prediction model.

[0108] As described above, by training different prediction models according to the time when the user enters the target area and the corresponding activity data, the corresponding prediction model can be selected according to the time when the user enters the target area in subsequent predictions, thereby improving the accuracy of the prediction results.

[0109] S300, determining the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0110] Specifically, step S300 also includes the following steps: Figure 5 As shown:

[0111] S301, according to the time point when each target user enters each initial activity location corresponding to itself, obtain the current activity trajectory corresponding to each target user; the current activity trajectory corresponding to the target user is a trajectory composed of several initial activity locations where the target user has been active in order of activity.

[0112] S302, acquiring a number of intermediate users according to the initial activity data set corresponding to each target user; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set.

[0113] S303, according to the last initial activity location in the current activity track corresponding to each intermediate user, the number of target users at each preset activity location at the current collection time is obtained.

[0114] S304: Determine the number of users who have transferred to each preset activity location according to the number of target users at each preset activity location at the current collection time and the user transfer probability of each preset activity location.

[0115] Specifically, the preset activity location list is A={A1, A2, ..., A j , ..., A n}, A j is the jth preset activity location in the target area, j=1, 2, ..., n, and n is the number of preset activity locations in the target area.

[0116] Specifically, A j The corresponding number of user transfers S j Meet the following conditions:

[0117] S j =Z j ×ζ j , where Z j A is the current collection time j The corresponding number of target users, ζ j A j The corresponding user transfer probability.

[0118] As described above, the number of target users at each preset activity location is obtained based on the current activity trajectory corresponding to each target user, and the number of users that need to be transferred is calculated based on the user transfer probability of the preset activity location, which is conducive to the reasonable allocation of vehicles according to the number of users, and then to the efficient transfer of users.

[0119] S400, scheduling a plurality of preset vehicles according to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, so as to realize the transfer of target users in the target area.

[0120] Optionally, step S400 includes the following steps: Figure 6 As shown:

[0121] S401, acquiring a number of intermediate vehicles based on the status information of each preset vehicle acquired in real time; the status information of the preset vehicle includes the location information and idle information of the preset vehicle; the intermediate vehicle is any preset vehicle in an idle state.

[0122] Specifically, the location information of the preset vehicle is the location of the preset vehicle obtained in real time, which can be understood as: installing a GPS positioning system for each preset vehicle, and obtaining the location of each scenic spot vehicle in real time according to the GPS positioning system.

[0123] Preferably, in step S401, the intermediate vehicle is determined by the following steps: Figure 7 As shown:

[0124] S4011, obtaining the passenger capacity information of each preset vehicle; the passenger capacity information of the preset vehicle includes the maximum passenger capacity and the current passenger capacity of the preset vehicle.

[0125] S4012, when the position information and passenger information of the preset vehicle meet the preset conditions, determine that the preset vehicle is the middle vehicle.

[0126] Specifically, the preset vehicle location information and passenger information meet the preset conditions:

[0127] (D1 / D0)×θ1+(G1 / G0)×θ2≤δ, where D1 is the driving distance of the preset vehicle from the nearest preset activity location, D0 is the preset distance, G1 is the current passenger capacity of the preset vehicle, G0 is the maximum passenger capacity of the preset vehicle, θ1 is the preset distance weight, and θ2 is the preset passenger weight.

[0128] It should be noted that the driving distance of the preset vehicle from the nearest preset activity location is obtained based on the current position of the preset vehicle. The current number of passengers of the preset vehicle can be obtained through in-vehicle monitoring, infrared sensors installed at the door, or card swiping. The preset vehicle here is the same preset vehicle. When the position information and passenger information of the preset vehicle meet the preset conditions, the preset vehicle is determined to be the intermediate vehicle.

[0129] As mentioned above, by obtaining the passenger information, location information and idle status information of each preset vehicle, several intermediate vehicles can be calculated, which increases the rationality of the use of nearby vehicles and increases the utilization rate of vehicles, thereby realizing the rapid transfer of several target users and saving the target users' physical strength and time.

[0130] S402, allocating a number of intermediate vehicles in proportion to the number of users transferred to each preset activity location, so as to dispatch a number of preset vehicles according to the obtained number of intermediate vehicles allocated to each preset activity location.

[0131] Optionally, step S400 includes the following steps: Figure 8 As shown:

[0132] S410, obtaining the time point at which the target user of each preset activity location at the current collection time enters the preset activity location.

[0133] S420: According to the sequence of time points at which the target users enter the preset activity location, determine the target users who have been transferred by the previous user as transfer users in the corresponding preset activity location.

[0134] S430, obtaining a current activity track corresponding to each transferred user; the current activity track corresponding to the transferred user is a track formed by arranging several initial activity locations of the transferred user in an activity sequence.

[0135] S440, comparing the current activity track corresponding to each transferred user with a plurality of pre-stored historical activity tracks to determine the next preferred activity location of each transferred user.

[0136] For better understanding, the following example is used to illustrate: if the list of current activity tracks corresponding to the transferred user is H={H1, H2, ..., H α , ..., H β}, the list of several pre-stored historical activity trajectories containing H is H 0 ={H1,H2,……,H α , ..., H β , H β+1 , ..., H β+γ}, then H β+1 Determine the next preferred activity location for the transferred user.

[0137] S450, dispatching a number of intermediate vehicles according to the next preferred activity location of each transferred user; the intermediate vehicle is any preset vehicle in an idle state; those skilled in the art can know that any method in the prior art for realizing vehicle dispatch according to the number of people and location information falls within the protection scope of the present invention and will not be repeated here.

[0138] As mentioned above, by predicting the number of users transferring to each preset activity location, the total number of people who need to take the vehicle can be known, and based on the number and location information of the intermediate vehicles, a reasonable number of vehicles can be provided for each preset activity location, thereby achieving reasonable scheduling of vehicles and solving the problem of long waiting time for target users.

[0139] This embodiment collects the initial activity data set of each target user in the target area every period, that is, the activity locations that each target user has entered at the current collection time, as well as the time points of entering and leaving each activity location before the current collection time, and then inputs the initial activity data set into the target probability prediction model, so as to obtain the user transfer probability of each preset activity location, and then combine the number of target users at each preset activity location to calculate the number of user transfers at each preset activity location, and also predict the next preferred activity location of each target user based on the historical activity trajectory, and then reasonably allocate the number of vehicles to each preset activity location based on the location information and idle status information of each preset vehicle obtained in real time, so as to improve the transfer efficiency of target users in the target area and save the target users' physical strength and time.

[0140] Embodiment 2

[0141] like Fig. 9 As shown, this embodiment 2 provides a device for transferring a target user in a target area, including:

[0142] The collection module 100 is used to collect an initial activity data set corresponding to each target user among a plurality of target users in a target area according to a preset time period; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0143] Specifically, the initial activity data set corresponding to the i-th target user is C i ={C i1 , C i2 , ..., C ip , ..., C iq(i)}, C ip ={C ip1 , C ip2 , C ip3}, where C ip1 is the time point when the i-th target user enters the corresponding p-th initial activity location, C ip2 is the time point when the i-th target user leaves the corresponding p-th initial activity location, Cip3 is the active time of the i-th target user in its corresponding p-th initial activity location, i=1, 2, ..., m, m is the number of target users in the target area at the current collection time, p=1, 2, ..., q(i), q(i) is the number of preset activity locations where the i-th target user has been active before the current collection time; it can be understood that when obtaining target user data, only the target user data existing at the current collection time can be obtained. When C iq(i) When it is the location where the i-th target user is currently active, the time point at which the target user leaves the activity location is empty.

[0144] Optionally, the initial activity data set also includes but is not limited to the time, season, age, and average daily steps of the target user entering the target area, so as to obtain the impact of different seasons and different user physical fitness on the user transfer probability, so as to fine-tune the prediction results of the target probability prediction model; for example, when users are generally younger and have better physical fitness, after a certain period of activity, the user's transfer probability will be greater than the predicted result.

[0145] Specifically, the initial activity data set is obtained through video surveillance of the scenic spot, WiFi in the target area connected to the target user's device, or an APP authorized by the target user, which will not be described in detail here.

[0146] The first acquisition module 200 is used to input the initial activity data set corresponding to each target user into the target probability prediction model, and obtain the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0147] Preferably, the device also includes a model training module, such as Fig.10 As shown, the model training module includes:

[0148] The second acquisition module 001 is used to acquire a historical activity data set corresponding to each target historical user within a historical time period of a target area; the historical activity data set corresponding to the target historical user includes the time points when the target historical user enters and leaves each historical activity location corresponding to the target historical user.

[0149] Preferably, the second acquisition module is further used to determine the target historical user through the following steps:

[0150] S0011, obtaining a historical activity data set corresponding to each initial historical user within a historical time period of a target area; the historical activity data set corresponding to the initial historical user includes time points at which the initial historical user enters and leaves each historical activity location corresponding to the initial historical user.

[0151] Specifically, the initial historical user refers to any historical user in the historical time period of the target area.

[0152] S0012, acquiring an initial activity track corresponding to each initial historical user according to the historical activity data set corresponding to each initial historical user.

[0153] Specifically, the initial activity track corresponding to the initial historical user is a list of several activity locations where the user has been active arranged in the order of activities.

[0154] S0013, performing deduplication processing on a number of initial activity trajectories corresponding to a number of historical visitors, and obtaining a list of intermediate activity trajectories.

[0155] Specifically, the intermediate activity trajectory list is B={B1, B2, ..., B e , ..., B f}, where B e is the e-th intermediate activity trajectory, e=1, 2, ..., f, f is the number of intermediate activity trajectories, and the intermediate activity trajectory is any initial activity trajectory obtained after deduplication processing of several initial activity trajectories.

[0156] S0014, acquiring a number of key activity trajectories from the intermediate activity trajectory list according to the initial historical user quantity corresponding to each intermediate activity trajectory in the intermediate activity trajectory list and a preset ratio threshold.

[0157] Specifically, when L e / ∑ f k=1 L k ≥λ, B e Determined as the key activity trajectory, where L e For B e The corresponding initial number of historical users, L k is the initial number of historical users corresponding to the kth intermediate activity trajectory, and λ is a preset ratio threshold, for example, λ is 0.1.

[0158] S0015, determining the initial historical user corresponding to each key activity track as the target historical user.

[0159] As mentioned above, since the order of activity locations for each user is different, there will be several activity routes. In the training process, only the commonly used routes need to be used as a feature to filter out routes with very few people, such as users who only visit one location and leave due to special circumstances. By screening key activity trajectories, the data is cleaned and preprocessed to make the training results of the model more reasonable.

[0160] The third acquisition module 002 is used to acquire the historical activity data set corresponding to each key user at the target collection time from the historical activity data set corresponding to each target historical user according to a preset time period; the key user is the target historical user who has entered any preset activity location before the target collection time.

[0161] The first training module 003 is used to input the historical activity data set corresponding to each key user into a preset probability prediction model for training if the target collection time is in a first preset time period to obtain a first probability prediction model.

[0162] Optionally, the first time period is a time period between 8:00am-12:00am.

[0163] Specifically, the user transfer probability output by the preset probability prediction model is compared with the actual user transfer probability, and the parameters of the preset probability prediction model are corrected until the error between the user transfer probability output by the preset probability prediction model and the actual user transfer probability meets the preset threshold, so as to obtain the first probability prediction model.

[0164] The second training module 004 is used to input the historical activity data set corresponding to each key user into the preset probability prediction model for training if the target collection time is in the second preset time period to obtain a second probability prediction model; the training process of the second probability prediction model and the training process of the first probability prediction model are not repeated here.

[0165] Optionally, the second time period is a time period between 12:00am-17:00am.

[0166] As mentioned above, due to the different times of entering the target area, the activity duration will be different. For example, the activity duration at each activity location and the number of activity locations for users who are active for one day and half a day are quite different. Therefore, different activity data sets are obtained according to the time periods of different times of entering the target area to train the subsequent prediction models separately and improve the prediction accuracy.

[0167] Specifically, Fig.11 As shown, the first acquisition module 200 includes:

[0168] The second determination module 201 is used to determine the first probability prediction model as the target probability prediction model when the time point when each target user enters the first initial activity location corresponding to himself is in the first preset time period.

[0169] The third determination module 202 is used to determine the second probability prediction model as the target probability prediction model when the time point at which the target user enters the first initial activity location corresponding to himself is in the second preset time period.

[0170] As described above, by training different prediction models according to the time when the user enters the target area and the corresponding activity data, the corresponding prediction model can be selected according to the time when the user enters the target area in subsequent predictions, thereby improving the accuracy of the prediction results.

[0171] The first determination module 300 is used to determine the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0172] Specifically, Fig.12 As shown, the first determining module 300 includes:

[0173] The fourth acquisition module 301 is used to acquire the current activity trajectory corresponding to each target user according to the time point when each target user enters each initial activity location corresponding to himself; the current activity trajectory corresponding to the target user is a trajectory composed of several initial activity locations where he has been active in order of activity.

[0174] The fifth acquisition module 302 is used to acquire a number of intermediate users according to the initial activity data set corresponding to each target user; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set.

[0175] The sixth acquisition module 303 is used to acquire the number of target users at each preset activity location at the current collection time according to the last initial activity location in the current activity track corresponding to each intermediate user.

[0176] The fourth determination module 304 is used to determine the number of user transfers at each preset activity location according to the number of target users at each preset activity location and the user transfer probability at each preset activity location at the current collection time.

[0177] Specifically, the preset activity location list is A={A1, A2, ..., A j , ..., A n}, A j is the jth preset activity location in the target area, j=1, 2, ..., n, and n is the number of preset activity locations in the target area.

[0178] Specifically, A j The corresponding number of user transfers S j Meet the following conditions:

[0179] S j =Z j ×ζ j , where Z jA is the current collection time j The corresponding number of target users, ζ j A j The corresponding user transfer probability.

[0180] As described above, the number of target users at each preset activity location is obtained based on the current activity trajectory corresponding to each target user, and the number of users that need to be transferred is calculated based on the user transfer probability of the preset activity location, which is conducive to the reasonable allocation of vehicles according to the number of users, and then to the efficient transfer of users.

[0181] The first scheduling module 400 is used to schedule a plurality of preset vehicles according to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, so as to realize the transfer of target users in the target area.

[0182] Optional, such as Fig.13 As shown, the first scheduling module 400 includes:

[0183] The seventh acquisition module 401 is used to acquire a number of intermediate vehicles based on the status information of each preset vehicle acquired in real time; the status information of the preset vehicle includes the location information and idle information of the preset vehicle; the intermediate vehicle is any preset vehicle in an idle state.

[0184] Specifically, the location information of the preset vehicle is the location of the preset vehicle obtained in real time, which can be understood as: installing a GPS positioning system for each preset vehicle, and obtaining the location of each scenic spot vehicle in real time according to the GPS positioning system.

[0185] Preferably, the seventh acquisition module is further used to determine the intermediate vehicle through the following steps:

[0186] S4011, obtaining the passenger capacity information of each preset vehicle; the passenger capacity information of the preset vehicle includes the maximum passenger capacity and the current passenger capacity of the preset vehicle.

[0187] S4012, when the position information and passenger information of the preset vehicle meet the preset conditions, determine that the preset vehicle is the middle vehicle.

[0188] Specifically, the preset vehicle location information and passenger information meet the preset conditions:

[0189] (D1 / D0)×θ1+(G1 / G0)×θ2≤δ, where D1 is the driving distance of the preset vehicle from the nearest preset activity location, D0 is the preset distance, G1 is the current passenger capacity of the preset vehicle, G0 is the maximum passenger capacity of the preset vehicle, θ1 is the preset distance weight, and θ2 is the preset passenger weight.

[0190] It should be noted that the driving distance of the preset vehicle from the nearest preset activity location is obtained based on the current position of the preset vehicle. The current number of passengers of the preset vehicle can be obtained through in-vehicle monitoring, infrared sensors installed at the door, or card swiping. The preset vehicle here is the same preset vehicle. When the position information and passenger information of the preset vehicle meet the preset conditions, the preset vehicle is determined to be the intermediate vehicle.

[0191] As mentioned above, by obtaining the passenger information, location information and idle status information of each preset vehicle, several intermediate vehicles can be calculated, which increases the rationality of the use of nearby vehicles and increases the utilization rate of vehicles, thereby realizing the rapid transfer of several target users and saving the target users' physical strength and time.

[0192] The allocation module 402 is used to allocate a number of intermediate vehicles in proportion according to the number of user transfers at each preset activity location, so as to dispatch a number of preset vehicles according to the obtained number of intermediate vehicles allocated to each preset activity location.

[0193] Optional, such as Fig.14 As shown, the first scheduling module 400 includes:

[0194] The eighth acquisition module 410 is used to acquire the time point at which the target user at each preset activity location enters the preset activity location at the current collection moment.

[0195] The fifth determining module 420 is used to determine the target users transferred by the first user as the transferred users in the corresponding preset activity location according to the order of the time points at which the target users enter the preset activity location.

[0196] The ninth acquisition module 430 is used to acquire the current activity track corresponding to each transferred user; the current activity track corresponding to the transferred user is a track composed of several initial activity locations where the user has been active in an order of activity.

[0197] The sixth determination module 440 is used to compare the current activity track corresponding to each transferred user with a plurality of pre-stored historical activity tracks to determine the next preferred activity location of each transferred user.

[0198] For better understanding, the following example is used to illustrate: if the list of current activity tracks corresponding to the transferred user is H={H1, H2, ..., H α , ..., H β}, the list of several pre-stored historical activity trajectories containing H is H 0 ={H1,H2,……,H α , ..., H β , H β+1 , ..., Hβ+γ}, then H β+1 Determine the next preferred activity location for the transferred user.

[0199] The second scheduling module 450 is used to schedule a number of intermediate vehicles according to the next preferred activity location of each transferred user; the intermediate vehicle is any preset vehicle in an idle state; those skilled in the art can know that any method in the prior art for realizing vehicle scheduling based on the number of people and location information falls within the protection scope of the present invention and will not be repeated here.

[0200] As mentioned above, by predicting the number of users transferring to each preset activity location, the total number of people who need to take the vehicle can be known, and based on the number and location information of the intermediate vehicles, a reasonable number of vehicles can be provided for each preset activity location, thereby achieving reasonable scheduling of vehicles and solving the problem of long waiting time for target users.

[0201] This embodiment collects the initial activity data set of each target user in the target area every period, that is, the activity locations that each target user has entered at the current collection time, as well as the time points of entering and leaving each activity location before the current collection time, and then inputs the initial activity data set into the target probability prediction model, so as to obtain the user transfer probability of each preset activity location, and then combine the number of target users at each preset activity location to calculate the number of user transfers at each preset activity location, and also predict the next preferred activity location of each target user based on the historical activity trajectory, and then reasonably allocate the number of vehicles to each preset activity location based on the location information and idle status information of each preset vehicle obtained in real time, so as to improve the transfer efficiency of target users in the target area and save the target users' physical strength and time.

[0202] Embodiment 3

[0203] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0204] According to a preset time period, an initial activity data set corresponding to each target user among a plurality of target users in a target area is collected; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0205] The initial activity data set corresponding to each target user is input into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0206] The number of user transfers to each preset activity location is determined according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0207] According to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, a plurality of preset vehicles are dispatched to realize the transfer of target users in the target area.

[0208] Embodiment 4

[0209] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0210] According to a preset time period, an initial activity data set corresponding to each target user among a plurality of target users in a target area is collected; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area.

[0211] The initial activity data set corresponding to each target user is input into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model.

[0212] The number of user transfers to each preset activity location is determined according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location.

[0213] According to the number of users transferred to each preset activity location and the status information of each preset vehicle obtained in real time, a plurality of preset vehicles are dispatched to realize the transfer of target users in the target area.

[0214] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0215] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0216] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for transferring a target user in a target area, characterized in that: The following steps are involved: According to a preset time period, an initial activity data set corresponding to each target user among a plurality of target users in a target area is collected; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active among the plurality of preset activity locations in the target area; The initial activity data set corresponding to each target user is input into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model; wherein the target probability prediction model is determined by the following steps: obtaining the historical activity data set corresponding to each target historical user in the historical time period of the target area; the historical activity data set corresponding to the target historical user includes the time points when the target historical user enters and leaves each historical activity location corresponding to itself; according to the preset time period, obtaining the historical activity data set corresponding to each key user at the target collection time from the historical activity data set corresponding to each target historical user; the key user is the target user who has entered any preset activity location before the target collection time. Target historical users; if the target collection time is in the first preset time period, the historical activity data set corresponding to each key user is input into the preset probability prediction model for training to obtain a first probability prediction model; if the target collection time is in the second preset time period, the historical activity data set corresponding to each key user is input into the preset probability prediction model for training to obtain a second probability prediction model; and when the time point at which each target user enters the first initial activity location corresponding to itself is in the first preset time period, the first probability prediction model is determined as the target probability prediction model, and when the time point at which a target user enters the first initial activity location corresponding to itself is in the second preset time period, the second probability prediction model is determined as the target probability prediction model; Determining the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location; According to the number of user transfers at each preset activity location and the status information of each preset vehicle obtained in real time, a number of preset vehicles are dispatched to achieve the transfer of target users in the target area; the following steps are included: according to the status information of each preset vehicle obtained in real time, a number of intermediate vehicles are obtained; the status information of the preset vehicles includes the location information and idle information of the preset vehicles; the intermediate vehicle is any preset vehicle in an idle state; according to the number of user transfers at each preset activity location, a number of intermediate vehicles are allocated in proportion, so that a number of preset vehicles are dispatched according to the number of intermediate vehicles allocated to each preset activity location obtained.

2. The method for transferring a target user within a target area according to claim 1, characterized in that: Determining the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location includes the following steps: According to the time point when each target user enters each initial activity location corresponding to the target user, the current activity trajectory corresponding to each target user is obtained; the current activity trajectory corresponding to the target user is a trajectory formed by arranging several initial activity locations where the target user has been active in accordance with the activity sequence; According to the initial activity data set corresponding to each target user, a number of intermediate users are obtained; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set; According to the last initial activity location in the current activity track corresponding to each intermediate user, the number of target users at each preset activity location at the current collection time is obtained; The number of user transfers at each preset activity location is determined according to the number of target users at each preset activity location at the current collection moment and the user transfer probability at each preset activity location.

3. The method for transferring a target user within a target area according to claim 1, characterized in that: According to the number of user transfers at each preset activity location and the status information of each preset vehicle obtained in real time, scheduling a plurality of preset vehicles includes the following steps: Obtain the time point at which the target user of each preset activity location enters the preset activity location at the current collection time; According to the order of the time points at which the target users enter the preset activity location, the target users transferred by the previous users are all determined as the transferred users in the corresponding preset activity location; Obtaining a current activity track corresponding to each transferred user; the current activity track corresponding to the transferred user is a track formed by arranging a number of initial activity locations where the user has been active in accordance with the activity sequence; Compare the current activity track corresponding to each transferred user with a number of pre-stored historical activity tracks to determine the next preferred activity location of each transferred user; According to the next preferred activity location of each transferred user, a number of intermediate vehicles are dispatched; the intermediate vehicle is any preset vehicle in an idle state.

4. A device for transferring a target user in a target area, characterized in that: The device comprises: A collection module is used to collect an initial activity data set corresponding to each target user among a plurality of target users in a target area according to a preset time period; the target area includes a plurality of preset activity locations and a plurality of preset vehicles, and the initial activity data set includes time points at which the target user enters and leaves each initial activity location corresponding to the target user; the initial activity location is any location where the corresponding target user has been active in the plurality of preset activity locations in the target area; The first acquisition module is used to input the initial activity data set corresponding to each target user into the target probability prediction model to obtain the user transfer probability of each preset activity location predicted by the target probability prediction model; the device also includes a model training module, which includes: a second acquisition module, used to obtain the historical activity data set corresponding to each target historical user in the historical time period of the target area; the historical activity data set corresponding to the target historical user includes the time points when the target historical user enters and leaves each historical activity location corresponding to itself; a third acquisition module is used to obtain the historical activity data set corresponding to each key user at the target collection time from the historical activity data set corresponding to each target historical user according to a preset time period; the key user is a target historical user who has entered any preset activity location before the target collection time; the first A training module, for inputting the historical activity data set corresponding to each key user into the preset probability prediction model for training if the target collection moment is in the first preset time period, so as to obtain a first probability prediction model; a second training module, for inputting the historical activity data set corresponding to each key user into the preset probability prediction model for training if the target collection moment is in the second preset time period, so as to obtain a second probability prediction model; the first acquisition module includes: a second determination module, for determining the first probability prediction model as the target probability prediction model when the time point at which each target user enters the first initial activity location corresponding to itself is in the first preset time period; a third determination module, for determining the second probability prediction model as the target probability prediction model when the time point at which a target user enters the first initial activity location corresponding to itself is in the second preset time period; A first determination module is used to determine the number of user transfers to each preset activity location according to the initial activity data set corresponding to each target user and the user transfer probability of each preset activity location; The first scheduling module is used to schedule a number of preset vehicles according to the number of user transfers at each preset activity location and the status information of each preset vehicle obtained in real time, so as to realize the transfer of target users in the target area; the first scheduling module includes: a seventh acquisition module, used to acquire a number of intermediate vehicles according to the status information of each preset vehicle obtained in real time; the status information of the preset vehicles includes the location information and idle information of the preset vehicles; the intermediate vehicle is any preset vehicle in an idle state; an allocation module is used to allocate a number of intermediate vehicles in proportion according to the number of user transfers at each preset activity location, so as to schedule a number of preset vehicles according to the acquired number of intermediate vehicles allocated to each preset activity location.

5. The device for transferring target users in a target area according to claim 4, characterized in that: The first determining module comprises: A fourth acquisition module is used to acquire the current activity trajectory corresponding to each target user according to the time point when each target user enters each initial activity location corresponding to the target user; the current activity trajectory corresponding to the target user is a trajectory formed by arranging the initial activity locations where the target user has been active in accordance with the activity sequence; A fifth acquisition module is used to acquire a number of intermediate users according to the initial activity data set corresponding to each target user; the intermediate user is any target user whose time point of leaving the last initial activity location in the corresponding current activity track is not found in the initial activity data set; A sixth acquisition module, used to acquire the number of target users at each preset activity location at the current collection time according to the last initial activity location in the current activity track corresponding to each intermediate user; The fourth determination module is used to determine the number of user transfers at each preset activity location according to the number of target users at each preset activity location and the user transfer probability at each preset activity location at the current collection moment.

6. The device for transferring a target user in a target area according to claim 4, characterized in that: The first scheduling module includes: An eighth acquisition module is used to acquire the time point at which the target user of each preset activity location enters the preset activity location at the current collection time; A fifth determination module is used to determine the target users of the previous user transfer number as the transfer users in the corresponding preset activity location according to the order of the time points when the target users enter the preset activity location; A ninth acquisition module is used to acquire a current activity track corresponding to each transferred user; the current activity track corresponding to the transferred user is a track formed by arranging a number of initial activity locations where the user has been active in accordance with the activity sequence; A sixth determination module, used to compare the current activity track corresponding to each transferred user with a plurality of pre-stored historical activity tracks, and determine the next preferred activity location of each transferred user; The second scheduling module is used to schedule a number of intermediate vehicles according to the next preferred activity location of each transferred user; the intermediate vehicle is any preset vehicle in an idle state.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for transferring a target user within a target area as claimed in any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for transferring a target user within a target area as claimed in any one of claims 1 to 3 is implemented.

Images