CN108764951B - User similarity obtaining method and device, equipment and storage medium - Google Patents

Abstract

The invention discloses a method, device, device and storage medium for obtaining user similarity based on user movement trajectory. The method for obtaining user similarity based on a user movement track includes: obtaining a first user movement track and a second user movement track; wherein the first user movement track includes at least one first moment information; the second user movement track includes at least one piece of first moment information; The movement track contains at least one second moment information; according to each of the first moment information and each of the second moment information, a time similarity is obtained; according to the first user movement track, the second user movement The trajectory and the time similarity are used to obtain the user similarity between the first user and the second user. By adopting the present invention, the accuracy of the obtained user similarity can be improved.

Description

User similarity acquisition method and device, device, and storage medium

technical field

The present invention relates to the field of computer technology, and in particular, to a method and apparatus, device, and storage medium for obtaining user similarity.

Background technique

In the operation process of a telecommunication operator, when the communication number used by a certain user changes, it is often necessary to merge the relevant records of the old and new numbers of the user. Then, how to identify whether two numbers belong to the same user, that is, how to judge whether a new user and an old user are the same user, has become a core technical problem in the telecommunication operation process.

In the prior art, it is usually determined whether the two users are the same user by calculating the similarity between the two users. Specifically, whenever a new network user is detected, the user similarity between all the old network users in the communication network and the new network user is automatically calculated, and it is detected that the calculated user similarity is greater than When the user similarity of the preset threshold is reached, it is considered that there is an old network user similar to the new network user in the communication network, so it is determined that the new network user is a re-entry user; then, it is determined that the old network user with the largest user similarity is the same as the new network user. The new network user is the same user, and the related records corresponding to the two are merged. The existing methods for calculating the user similarity between the new network user and the old network user are usually obtained by calculating the similarity of the user's communication records.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a method, apparatus, device, and storage medium for obtaining a user similarity, which can improve the accuracy of the obtained user similarity.

A method for obtaining user similarity based on a user's movement trajectory provided by an embodiment of the present invention specifically includes:

obtaining a first user movement track and a second user movement track; wherein, the first user movement track includes at least one first moment information; the second user movement track includes at least one second moment information;

obtaining a temporal similarity according to each of the first moment information and each of the second moment information;

The user similarity between the first user and the second user is obtained according to the first user movement trajectory, the second user movement trajectory and the time similarity.

Further, the first user movement track includes at least one first track point; the second user movement track includes at least one second track point; each of the first time information is associated with each of the first The track points have a one-to-one correspondence; each of the second moment information has a one-to-one correspondence with each of the second track points.

Further, the obtaining the temporal similarity according to each of the first moment information and each of the second moment information specifically includes:

计算获得所述时间相似度COL；其中，u表示所述第一用户；v表示所述第二用户；n(u)为所述第一用户移动轨迹中的第一轨迹点的总个数；n(v)为所述第二用户移动轨迹中的第二轨迹点的总个数；ΔT为预设的时间精度；L_i(u)表示所述第一用户移动轨迹中的第i个第一轨迹点；L_j(v)表示所述第二用户移动轨迹中的第j个第二轨迹点；δ(L_i(u),L_j(v))为所述第一用户移动轨迹中的第i个第一轨迹点与所述第二用户移动轨迹中的第j个第二轨迹点的重合度。The model is calculated according to each of the first time information T _i (u), each of the second time information T _j (v) and a preset time similarity

Calculate and obtain the temporal similarity COL; wherein, u represents the first user; v represents the second user; n(u) is the total number of first trajectory points in the movement trajectory of the first user; n(v) is the total number of second trajectory points in the second user's movement trajectory; ΔT is the preset time precision; Li (u) represents the _i -th point in the first user's movement trajectory A trajectory point; L _j (v) represents the j-th second trajectory point in the second user movement trajectory; δ(L _i (u), L _j (v)) is the first user movement trajectory in the The degree of coincidence between the i-th first trajectory point of and the j-th second trajectory point in the second user movement trajectory.

Further, the obtaining the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory and the time similarity, specifically includes:

计算获得轨迹相似度D_LCSS；其中，LCSS(u,v)表示所述第一用户移动轨迹与所述第二用户移动轨迹之间的最长公共子序列；len_u表示所述第一用户移动轨迹中的第一轨迹点的总个数；len_v表示所述第二用户移动轨迹中的第二轨迹点的总个数；The model is calculated according to the similarity of the first user movement trajectory, the second user movement trajectory and a preset trajectory

Calculate and obtain the track similarity D _LCSS ; wherein, LCSS(u, v) represents the longest common subsequence between the first user's movement track and the second user's movement track; len _u represents the first user's movement the total number of first trajectory points in the trajectory; len _v represents the total number of second trajectory points in the second user movement trajectory;

The user similarity is obtained according to the trajectory similarity D _LCSS and the temporal similarity.

Further, obtaining the user similarity according to the trajectory similarity D _LCSS and the temporal similarity specifically includes:

According to the trajectory similarity D _LCSS , the temporal similarity COL and the user similarity calculation model sim(u,v)=D _LCSS *COL, the user similarity sim(u,v) is obtained by calculation.

Further, the first time information is the time information when the first user arrives at the corresponding first trajectory point; the second time information is the time information when the second user arrives at the corresponding second trajectory point.

Further, after obtaining the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory and the time similarity, the method further includes:

judging whether the user similarity is greater than a preset threshold;

If so, determine that the first user and the second user are the same user;

If not, it is determined that the first user and the second user are not the same user.

Correspondingly, the embodiment of the present invention also provides a user similarity obtaining device based on the user movement trajectory, which specifically includes:

a user movement track obtaining module, configured to obtain a first user movement track and a second user movement track; wherein, the first user movement track includes at least one first moment information; the second user movement track includes at least one second time information;

a time similarity obtaining module, configured to obtain a time similarity according to each of the first moment information and each of the second moment information; and,

The user similarity obtaining module is configured to obtain the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory and the time similarity.

An embodiment of the present invention further provides a device, which specifically includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor implements the above when executing the computer program The method for obtaining user similarity based on user movement trajectory.

Embodiments of the present invention further provide a computer-readable storage medium, which specifically includes a stored computer program, wherein, when the computer program runs, the device on which the computer-readable storage medium is located is controlled to execute the above-described movement based on the user's movement trajectory. The method for obtaining user similarity.

Implementing the embodiment of the present invention has the following beneficial effects:

In the method, device, device, and storage medium for obtaining user similarity provided by the embodiments of the present invention, the similarity between the first user and the second user is obtained by calculating the similarity between the movement trajectory of the first user and the movement trajectory of the second user. User similarity, so that the calculated user similarity is highly consistent with the actual situation. In addition, by introducing temporal similarity in the process of calculating user similarity, the basis for obtaining user similarity can be diversified, thereby increasing the number of users obtained. Similarity accuracy.

Description of drawings

1 is a schematic flowchart of a preferred embodiment of a method for obtaining user similarity based on user movement trajectory provided by the present invention;

2 is a schematic structural diagram of a preferred embodiment of a device for obtaining user similarity based on user movement trajectory provided by the present invention;

FIG. 3 is a schematic structural diagram of a preferred embodiment of the device provided by the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

As shown in FIG. 1, it is a schematic flowchart of a preferred embodiment of the method for obtaining user similarity based on user movement trajectory provided by the present invention, including steps S11 to S13, and the details are as follows:

S11: Obtain a first user movement track and a second user movement track; wherein the first user movement track includes at least one piece of first moment information; and the second user movement track includes at least one second moment information.

It should be noted that the embodiments of the present invention are executed by the system. Wherein, the system may be a system in a telecommunication operator's server.

Telecom operators set up several base stations in various places, and the system obtains the user's user movement trajectory by obtaining the user's communication data. Specifically, the system monitors the first user in real time, obtains communication data such as WeChat, SMS, QQ, etc. of the first user, and analyzes these communication data to determine the base stations that the first user passes through during this period, and analyzes these base stations. Recording is performed to obtain the movement track of the first user. Similarly, the movement trajectory of the second user can be obtained.

Further, the first user movement track includes at least one first track point; the second user movement track includes at least one second track point; each of the first time information is associated with each of the first The track points have a one-to-one correspondence; each of the second moment information has a one-to-one correspondence with each of the second track points.

More preferably, the first time information is the time information when the first user arrives at the corresponding first trajectory point; the second time information is the time information when the second user arrives at the corresponding second trajectory point.

It should be noted that, in this embodiment, whenever it is detected that the first user moves to the vicinity of a base station, the base station is recorded as a track point, and the time information when the first user arrives at the base station is recorded at the same time. The above-mentioned first user movement trajectory can be obtained from the base stations that the user passes through within the preset time period and the time information of each base station arrival. Similarly, the above-mentioned second user movement trajectory can be obtained.

S12: Obtain a temporal similarity according to each of the first time information and each of the second time information.

It should be noted that, according to each first moment information and each second moment information, the similarity in time between the first user and the second user (that is, the first user and the second user appear in the same time period) are obtained. possibility of being in the same geographic location) to obtain the above-mentioned temporal similarity.

S13: Obtain the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory, and the time similarity.

It should be noted that, in this embodiment, the similarity between the movement trajectory of the first user and the movement trajectory of the second user is calculated by combining the temporal similarity, so as to obtain the user similarity between the first user and the second user .

In this embodiment, the user similarity between the first user and the second user is obtained by calculating the similarity between the first user's movement trajectory and the second user's movement trajectory, so that the calculated user similarity is consistent with the actual situation. In addition, by introducing the temporal similarity in the process of calculating the user similarity, the basis for obtaining the user similarity can be diversified, thereby improving the accuracy of the obtained user similarity.

In another preferred embodiment, the above step S12 further includes step S1201, which is as follows:

计算获得所述时间相似度COL；其中，u表示所述第一用户；v表示所述第二用户；n(u)为所述第一用户移动轨迹中的第一轨迹点的总个数；n(v)为所述第二用户移动轨迹中的第二轨迹点的总个数；ΔT为预设的时间精度；L_i(u)表示所述第一用户移动轨迹中的第i个第一轨迹点；L_j(v)表示所述第二用户移动轨迹中的第j个第二轨迹点；δ(L_i(u),L_j(v))为所述第一用户移动轨迹中的第i个第一轨迹点与所述第二用户移动轨迹中的第j个第二轨迹点的重合度。S1201: Calculate a model according to each of the first time information T _i (u), each of the second time information T _j (v) and a preset time similarity

Calculate and obtain the temporal similarity COL; wherein, u represents the first user; v represents the second user; n(u) is the total number of first trajectory points in the movement trajectory of the first user; n(v) is the total number of second trajectory points in the second user's movement trajectory; ΔT is the preset time precision; Li (u) represents the _i -th point in the first user's movement trajectory A trajectory point; L _j (v) represents the j-th second trajectory point in the second user movement trajectory; δ(L _i (u), L _j (v)) is the first user movement trajectory in the The degree of coincidence between the i-th first trajectory point of and the j-th second trajectory point in the second user movement trajectory.

It should be noted that, more preferably, the value of ΔT is set to 1 hour. When the i-th first trajectory point in the first user's movement trajectory coincides with the j-th second trajectory point in the second user's movement trajectory, δ(L _i (u), L _j (v))=1, otherwise , δ(L _i (u), L _j (v))=0.

In yet another preferred embodiment, the above step S13 further includes steps S1301 to S1302, which are as follows:

计算获得轨迹相似度D_LCSS；其中，LCSS(u,v)表示所述第一用户移动轨迹与所述第二用户移动轨迹之间的最长公共子序列；len_u表示所述第一用户移动轨迹中的第一轨迹点的总个数；len_v表示所述第二用户移动轨迹中的第二轨迹点的总个数。S1301: Calculate a model according to the first user movement trajectory, the second user movement trajectory, and a preset trajectory similarity

Calculate and obtain the track similarity D _LCSS ; wherein, LCSS(u, v) represents the longest common subsequence between the first user's movement track and the second user's movement track; len _u represents the first user's movement The total number of first track points in the track; len _v represents the total number of second track points in the second user movement track.

其中，u_i表示上述第一用户移动轨迹中的第i个第一轨迹点；v_j表示上述第二用户移动轨迹中的第j个第二轨迹点；γ为预设的相似性阈值；dist(u_i,v_j)为第一用户移动轨迹与第二用户移动轨迹之间的欧氏距离。It should be noted,

Wherein, _ui represents the i-th first trajectory point in the above-mentioned first user movement trajectory; vj represents the _j -th second trajectory point in the above-mentioned second user movement trajectory; γ is a preset similarity threshold; dist (u _i , v _j ) is the Euclidean distance between the movement trajectory of the first user and the movement trajectory of the second user.

S1302: Obtain the user similarity according to the trajectory similarity D _LCSS and the temporal similarity.

Further, the above step S1302 further includes step S1302_1, which is as follows:

S1302_1: Calculate and obtain the user similarity sim(u,v) according to the trajectory similarity D _LCSS , the temporal similarity COL and the user similarity calculation model sim(u,v)=D _LCSS *COL.

In yet another preferred embodiment, after the above step S13, steps S14 to S16 are further included, as follows:

S14: Determine whether the user similarity is greater than a preset threshold, if so, skip to S15, and if not, skip to S16.

S15: Determine that the first user and the second user are the same user.

S16: Determine that the first user and the second user are not the same user.

It should be noted that, in this embodiment, the similarity between the first user and the second user is determined by calculating the similarity between the movement trajectory of the first user and the movement trajectory of the second user. In , it is judged whether the user who newly joins the network is a user who has re-entered the network. For example, suppose a user A used the number 159******** before, and deactivated the number after using it for 2 months. After 2 months, a user B activated the number on the same telecom operator. A new number 186********. At this time, the telecom operator analyzes the communication data of user A and user B to obtain the user movement trajectory of user A and the user movement trajectory of user B respectively, and then calculates the user movement trajectory of user A by calculating the user movement trajectory of user A. The similarity between the user movement trajectory and the user B, so as to obtain the user similarity between the user A and the user B, if the user similarity is greater than a preset threshold, it can be considered that the user A and the user If the user B is the same person, it is determined that the user B is a re-entry user; if the similarity of the user is less than or equal to a preset threshold, it is considered that the user A and the user B are not the same person, and the user B is determined to be the same person. For new users. In this embodiment, since the accuracy of the user similarity obtained according to the above embodiment is high, the accuracy of the judgment on the re-entering users can be improved.

It should be further noted that the above step numbers are only used to indicate different steps, and do not limit the execution order of the steps.

The method for obtaining the user similarity based on the user's movement trajectory provided by the embodiment of the present invention obtains the user similarity between the first user and the second user by calculating the similarity between the first user's movement trajectory and the second user's movement trajectory In addition, by introducing the temporal similarity in the process of calculating the user similarity, the basis for obtaining the user similarity can be diversified, thereby improving the obtained user similarity accuracy.

Correspondingly, the present invention also provides an apparatus for obtaining user similarity based on user movement trajectory, which can implement all the processes of the method for obtaining user similarity based on user movement trajectory in the above embodiments.

As shown in FIG. 2, it is a schematic structural diagram of a preferred embodiment of an apparatus for obtaining user similarity based on user movement trajectory provided by the present invention, and the details are as follows:

The user movement track obtaining module 21 is configured to obtain a first user movement track and a second user movement track; wherein, the first user movement track includes at least one first moment information; the second user movement track includes at least one piece of first moment information; a second moment message;

a time similarity obtaining module 22, configured to obtain a time similarity according to each of the first moment information and each of the second moment information; and,

The user similarity obtaining module 23 is configured to obtain the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory and the time similarity.

Further, the first user movement track includes at least one first track point; the second user movement track includes at least one second track point; each of the first time information is associated with each of the first The track points have a one-to-one correspondence; each of the second moment information has a one-to-one correspondence with each of the second track points.

Further, the temporal similarity obtaining module specifically includes:

计算获得所述时间相似度COL；其中，u表示所述第一用户；v表示所述第二用户；n(u)为所述第一用户移动轨迹中的第一轨迹点的总个数；n(v)为所述第二用户移动轨迹中的第二轨迹点的总个数；ΔT为预设的时间精度；L_i(u)表示所述第一用户移动轨迹中的第i个第一轨迹点；L_j(v)表示所述第二用户移动轨迹中的第j个第二轨迹点；δ(L_i(u),L_j(v))为所述第一用户移动轨迹中的第i个第一轨迹点与所述第二用户移动轨迹中的第j个第二轨迹点的重合度。A time similarity calculation unit, configured to calculate a model according to each of the first time information T _i (u), each of the second time information T _j (v) and a preset time similarity

Calculate and obtain the temporal similarity COL; wherein, u represents the first user; v represents the second user; n(u) is the total number of first trajectory points in the movement trajectory of the first user; n(v) is the total number of second trajectory points in the second user's movement trajectory; ΔT is the preset time precision; Li (u) represents the _i -th point in the first user's movement trajectory A trajectory point; L _j (v) represents the j-th second trajectory point in the second user movement trajectory; δ(L _i (u), L _j (v)) is the first user movement trajectory in the The degree of coincidence between the i-th first trajectory point of and the j-th second trajectory point in the second user movement trajectory.

Further, the user similarity obtaining module specifically includes:

计算获得轨迹相似度D_LCSS；其中，LCSS(u,v)表示所述第一用户移动轨迹与所述第二用户移动轨迹之间的最长公共子序列；len_u表示所述第一用户移动轨迹中的第一轨迹点的总个数；len_v表示所述第二用户移动轨迹中的第二轨迹点的总个数；以及，A trajectory similarity calculation unit, configured to calculate a model according to the first user movement trajectory, the second user movement trajectory and a preset trajectory similarity

Calculate and obtain the track similarity D _LCSS ; wherein, LCSS(u, v) represents the longest common subsequence between the first user's movement track and the second user's movement track; len _u represents the first user's movement the total number of first trajectory points in the trajectory; len _v represents the total number of second trajectory points in the second user movement trajectory; and,

A user similarity calculation unit, configured to obtain the user similarity according to the trajectory similarity D _LCSS and the temporal similarity.

Further, the user similarity calculation unit specifically includes;

A user similarity calculation subunit, configured to calculate and obtain the user similarity sim according to the trajectory similarity D _LCSS , the temporal similarity COL and the user similarity calculation model sim(u,v)=D _LCSS *COL (u, v).

Further, the first time information is the time information when the first user arrives at the corresponding first trajectory point; the second time information is the time information when the second user arrives at the corresponding second trajectory point.

Further, the device for obtaining the user similarity based on the user's movement trajectory further includes:

a user similarity judging module for judging whether the user similarity is greater than a preset threshold; and,

a first processing module, configured to determine that the first user and the second user are the same user when it is determined that the user similarity is greater than a preset threshold; or,

A second processing module, configured to determine that the first user and the second user are not the same user when it is determined that the user similarity is not greater than a preset threshold.

The apparatus for obtaining the user similarity based on the user movement trajectory provided by the embodiment of the present invention obtains the user similarity between the first user and the second user by calculating the similarity between the movement trajectory of the first user and the movement trajectory of the second user In addition, by introducing the temporal similarity in the process of calculating the user similarity, the basis for obtaining the user similarity can be diversified, thereby improving the obtained user similarity accuracy.

The present invention also provides a device.

As shown in FIG. 3 , it is a schematic structural diagram of a preferred embodiment of the device provided by the present invention, including a processor 31 , a memory 32 and a computer stored in the memory 32 and configured to be executed by the processor 31 A program, when the processor 31 executes the computer program, the method for obtaining a user similarity based on a user movement trajectory described in any of the above embodiments is implemented.

It should be noted that FIG. 3 only takes the connection of a memory and a processor in the device as an example for illustration, and in some specific embodiments, the device may also include multiple memories and/or multiple processors , the specific number and connection method can be set and adjusted according to the actual situation.

The device provided by the embodiment of the present invention obtains the user similarity between the first user and the second user by calculating the similarity between the movement trajectory of the first user and the movement trajectory of the second user, so that the user similarity obtained by calculation The degree of conformity with the actual situation is high. In addition, by introducing the temporal similarity in the process of calculating the user similarity, the basis for obtaining the user similarity can be diversified, thereby improving the accuracy of the obtained user similarity.

The present invention also provides a computer-readable storage medium, including a stored computer program, wherein, when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the user-based user-based method described in any of the above embodiments. A method for obtaining user similarity of moving trajectories.

It should be noted that, in the present invention, all or part of the processes in the methods of the above embodiments can also be implemented by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be further noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer-readable The medium excludes electrical carrier signals and telecommunication signals.

The computer-readable storage medium provided by the embodiment of the present invention obtains the user similarity between the first user and the second user by calculating the similarity between the movement trajectory of the first user and the movement trajectory of the second user, so that the calculation obtains In addition, by introducing the temporal similarity in the process of calculating the user similarity, the basis for obtaining the user similarity can be diversified, thereby improving the accuracy of the obtained user similarity.

The above are the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can also be made, and these improvements and modifications are also regarded as protection scope of the present invention.

Claims (8)

1. A user similarity obtaining method based on a user movement track is characterized by comprising the following steps:

obtaining a first user movement track and a second user movement track; the first user movement track comprises at least one piece of first time information; the second user movement track comprises at least one piece of second time information; the first user moving track comprises at least one first track point; the second user moving track comprises at least one second track point; each piece of first time information and each piece of first track point have one-to-one correspondence; each piece of second time information and each piece of second track point have one-to-one correspondence;

obtaining time similarity according to each piece of first time information and each piece of second time information;

according to the first user movement track, the second user movement track and the time similarity, obtaining the user similarity between the first user and the second user;

wherein, the obtaining the time similarity according to each piece of the first time information and each piece of the second time information specifically includes:

according to each first time information T_i(u) each of the second time information T_j(v) And a preset time similarity calculation model

Calculating to obtain the time similarity COL; wherein u represents the first user; v represents the second user; n (u) is the total number of first track points in the first user movement track; n (v) is the total number of second track points in the second user moving track; Δ T is a preset time precision; l is_i(u) representing an ith first track point in the first user movement track; l is_j(v) Representing a jth second track point in the second user movement track; delta (L)_i(u),L_j(v) Is the coincidence degree of the ith first track point in the first user moving track and the jth second track point in the second user moving track.

2. The method for obtaining user similarity based on user movement trajectory according to claim 1, wherein obtaining the user similarity between the first user and the second user according to the first user movement trajectory, the second user movement trajectory and the time similarity specifically includes:

calculating a model according to the first user movement track, the second user movement track and the preset track similarity

Calculating to obtain the track similarity D_LCSS(ii) a Wherein LCSS (u, v) represents the longest common subsequence between the first user movement trajectory and the second user movement trajectory; len (a)_uRepresenting the total number of first track points in the first user moving track; len (a)_vRepresenting the total number of second track points in the second user moving track;

according to the track similarity D_LCSSAnd obtaining the user similarity according to the time similarity.

3. The method as claimed in claim 2, wherein the user similarity obtaining method based on the user movement track is characterized in that the user similarity obtaining method is based on the track similarity D_LCSSAnd the time similarity, obtaining the user similarity, specifically comprising:

according to the track similarity D_LCSSThe time similarity COL and a user similarity calculation model sim (u, v) ═ D_LCSSCOL, calculating to obtain the user similarity sim (u, v).

4. The user similarity obtaining method based on the user moving track according to any one of claims 1 to 3, wherein the first time information is time information when the first user arrives at the corresponding first track point; and the second time information is the time information when the second user arrives at the corresponding second track point.

5. The method as claimed in claim 1, wherein after obtaining the user similarity between the first user and the second user according to the first user movement track, the second user movement track and the time similarity, the method further comprises:

judging whether the user similarity is greater than a preset threshold value or not;

if yes, the first user and the second user are judged to be the same user;

if not, determining that the first user and the second user are not the same user.

6. A user similarity obtaining apparatus based on a user movement trajectory, comprising:

the user movement track obtaining module is used for obtaining a first user movement track and a second user movement track; the first user movement track comprises at least one piece of first time information; the second user movement track comprises at least one piece of second time information;

a time similarity obtaining module, configured to obtain a time similarity according to each piece of the first time information and each piece of the second time information;

the time similarity obtaining module specifically includes:

a time similarity calculation unit for calculating a time similarity according to each of the first time information T_i(u) each of the second time information T_j(v) And a preset time similarity calculation model

Calculating to obtain the time similarity COL; wherein u represents the first user; v represents the second user; n (u) is the total number of first track points in the first user movement track; n (v) is the total number of second track points in the second user moving track; Δ T is a preset time precision; l is_i(u) representing an ith first track point in the first user movement track; l is_j(v) Representing a jth second track point in the second user movement track; delta (L)_i(u),L_j(v) The coincidence degree of the ith first track point in the first user moving track and the jth second track point in the second user moving track is obtained;

and the number of the first and second groups,

and the user similarity obtaining module is used for obtaining the user similarity between the first user and the second user according to the first user movement track, the second user movement track and the time similarity.

7. An apparatus comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the user similarity obtaining method based on a user movement trajectory according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium is controlled to execute the method for obtaining user similarity based on user movement trajectory according to any one of claims 1 to 5.

Images