CN113888600A

CN113888600A - Trajectory determination method and apparatus, electronic device and computer-readable storage medium

Info

Publication number: CN113888600A
Application number: CN202111234121.9A
Authority: CN
Inventors: 叶建云; 陈闯; 侯敏
Original assignee: Zhejiang Shangtang Technology Development Co Ltd
Current assignee: Zhejiang Shangtang Technology Development Co Ltd
Priority date: 2021-10-22
Filing date: 2021-10-22
Publication date: 2022-01-04

Abstract

The embodiment of the disclosure discloses a track determination method, a track determination device, track determination equipment and a computer-readable storage medium. The method comprises the following steps: acquiring track data to be matched, wherein the track data to be matched comprises: at least one image trajectory data of the target object and at least one device trajectory data of the device; determining characteristic parameters of each pair of track data; each pair of trace data includes: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined. By the method and the device, the accuracy of the obtained track can be improved.

Description

Trajectory determination method and apparatus, electronic device and computer-readable storage medium

Technical Field

The present disclosure relates to terminal technologies, and in particular, to a trajectory determination method and apparatus, an electronic device, and a computer-readable storage medium.

Background

In some investigation and analysis, the track information of the portrait can be obtained through intelligent analysis of the collected video images and portrait track convergence, and the track information of the mobile phone is obtained through the base station information of the mobile phone, so that the complete track of the person is determined according to the track information of the portrait and the track information of the mobile phone. However, the accuracy of the complete track of the person determined by adopting the track information of the portrait and the track information of the mobile phone in the related technology is low, which is not beneficial to the development of investigation and analysis.

Disclosure of Invention

The embodiment of the disclosure provides a track determination method, a track determination device, an electronic device and a computer-readable storage medium, which can improve the accuracy of an obtained track.

The technical scheme of the embodiment of the disclosure is realized as follows:

the embodiment of the disclosure provides a track determination method, which includes: acquiring track data to be matched, wherein the track data to be matched comprises: at least one image trajectory data of the target object and at least one device trajectory data of the device; determining characteristic parameters of each pair of track data; each pair of track data comprises: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined.

An embodiment of the present disclosure provides a trajectory determination device, including: the device comprises an acquisition unit, a matching unit and a matching unit, wherein the acquisition unit is used for acquiring track data to be matched, and the track data to be matched comprises: at least one image trajectory data of the target object and at least one device trajectory data of the device; the determining unit is used for determining the characteristic parameters of each pair of track data; each pair of track data comprises: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined.

An embodiment of the present disclosure provides an electronic device, including: a memory for storing an executable computer program; and the processor is used for combining the display screen to realize the track determination method when executing the executable computer program stored in the memory.

The embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program for causing a processor to execute the above-mentioned trajectory determination method.

According to the track determining method, the track determining device, the track determining equipment and the computer readable storage medium, the characteristic parameters of each pair of track data are determined by acquiring the track data to be matched, wherein the track data to be matched comprises at least one piece of image track data of a target object and at least one piece of equipment track data of the equipment; each pair of trace data includes: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between the any piece of image track data and the any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined. In the technical scheme, the mobile phone data for matching is not mobile phone data obtained after screening the image track, and the characteristic parameters for measuring the matching degree of the image track data and the equipment track data are adopted to match the image track data and the equipment track data, so that on one hand, the accuracy of a subsequently obtained matching result can be improved because the mobile phone data for matching is more comprehensive, and on the other hand, the accuracy of the obtained matching result can be improved because the characteristic parameters for measuring the matching degree are adopted; thereby, the accuracy of the obtained trajectory of the target object can be improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

Fig. 1 is an alternative flow chart of a trajectory determination method provided in the embodiment of the present disclosure;

fig. 2 is an alternative flow chart of a trajectory determination method provided by the embodiment of the present disclosure;

fig. 3 is an alternative flow chart of a trajectory determination method provided by the embodiment of the present disclosure;

fig. 4 is an alternative flow chart of a trajectory determination method provided by the embodiment of the present disclosure;

fig. 5 is an alternative flow chart of a trajectory determination method provided by the embodiment of the present disclosure;

fig. 6 is an alternative flow chart of a trajectory determination method provided by the embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of a trajectory determination device provided in an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

For the purpose of making the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be described in further detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present disclosure, and all other embodiments obtained by a person of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present disclosure.

The embodiment of the disclosure provides a track determination method, a track determination device, track determination equipment and a computer-readable storage medium, which can improve the accuracy of an obtained track. The track determination method provided by the embodiment of the disclosure is applied to electronic equipment. An exemplary application of the electronic device provided by the embodiment of the present disclosure is described below, and the electronic device provided by the embodiment of the present disclosure may be implemented as various types of user terminals (hereinafter, referred to as terminals) such as AR glasses, a notebook computer, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, and a portable game device), and may also be implemented as a server.

Fig. 1 is an alternative flowchart of a trajectory determination method provided in an embodiment of the present disclosure, which will be described with reference to the steps shown in fig. 1.

S101, acquiring track data to be matched, wherein the track data to be matched comprises: at least one image trace data of the target object and at least one device trace data of the device.

In the embodiment of the disclosure, the electronic device may obtain at least one piece of image trajectory data of the target object and at least one piece of device trajectory data of the device, and use the obtained at least one piece of image trajectory data and the obtained at least one piece of device trajectory data as trajectory data to be matched, so as to match the obtained at least one piece of image trajectory data and the obtained at least one piece of device trajectory data by using a subsequent method.

In the embodiment of the present disclosure, the at least one piece of image trajectory data of the target object may be at least one piece of image trajectory data corresponding to different target objects; for example, in the case where the target object is an actual person, the at least one piece of image trajectory data of the target object may be at least one piece of image trajectory data corresponding to a different actual person. In the embodiment of the present disclosure, the trajectory data of the device may be trajectory data of a mobile device held by the target object, for example, in a case where the target object is a real person, at least one piece of device trajectory data may be at least one piece of trajectory data of a mobile device held by a different real person, for example, a mobile phone, a tablet computer, and the like.

In the embodiment of the present disclosure, one piece of image trajectory data may include at least one position point at which the image is acquired, and at least one time point (hereinafter referred to as a first time point) corresponding to the at least one position point (hereinafter referred to as a first position point); a piece of device trajectory data may contain at least one location point (hereinafter referred to as a second location point) at which the device is acquired, and at least one time point (hereinafter referred to as a second time point) corresponding to the at least one location point. For example, in the case where the target object is a real person and the device is a mobile phone of the real person, one piece of image trajectory data may be a position point when an image of the real person is captured by the camera and a time point of the capture. In some embodiments of the present disclosure, a piece of device trajectory data may be a position point acquired from a base station to which the mobile phone is connected and a corresponding acquisition time point.

In the embodiment of the present disclosure, the at least one piece of image trajectory data and the at least one piece of device trajectory data may be image trajectory data of a target object acquired in a certain area for a certain period of time, and device trajectory data. For example, the image track data of a person collected in a certain city in one month, and the device track data of a mobile phone may be used.

In the embodiment of the present disclosure, the location point may be represented by longitude and latitude, or may be represented by other manners, which is not limited in the embodiment of the present disclosure; and, the time point may be represented by world time, and may also be represented by other manners, which is not limited by the embodiment of the present disclosure.

In the disclosed embodiment, the electronic device may directly obtain, from the other device, at least one piece of image trajectory data and at least one piece of device trajectory data that have been generated by the other device; in some embodiments, the electronic device may also generate at least one image trajectory data and at least one device trajectory data based on the raw acquisition data. For example, in a case that the target object is a real person and the device is a mobile phone, the electronic device may perform person identification and person extraction based on a person bayonet of a certain region in a preset time period and an image acquired by video monitoring, and classify the image by using a video image clustering technology to form corresponding person track clustering data, so as to obtain at least one piece of image track data in the region in the time period according to the person track clustering data, wherein each piece of image track data corresponds to one person, the persons corresponding to different pieces of image track data are different, and each piece of image track data may include: at least one first location point and corresponding at least one first time point (first trajectory data), an identification (e.g., an identification number), and characteristic information, and the characteristic information includes at least one of age, gender, and clothing characteristics. And the electronic device may further obtain desensitized mobile phone track information in the area in the time period from a mobile phone operator, and obtain at least one piece of device track data in the area in the time period according to the mobile phone track information, where each piece of device track data may include an identifier of the device (for example, a mobile phone number after desensitization), at least one second location point, and at least one corresponding second time point (second track data).

In some embodiments, the identity may be obtained by: after the image is captured, the captured image may be compared with a standard image (e.g., an image on a valid document (an identification card, a residence permit, etc.)) in a preset image library, so as to determine a standard image corresponding to each captured image, and an identifier to which the standard image belongs is used as an identifier of the corresponding captured image.

S102, determining characteristic parameters of each pair of track data; each pair of trace data includes: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data.

In the embodiment of the disclosure, for any piece of image track data and any piece of device track data, the electronic device may use the two pieces of image track data as a pair of track data, and determine the characteristic parameter for characterizing the matching degree between the two pieces of track data, so that the matched image track data and device track data may be determined subsequently through the characteristic parameter.

In the embodiment of the disclosure, each pair of track data may correspond to at least one feature parameter, so that the matching degree of the pair of track parameters can be measured from one aspect or multiple aspects.

In an embodiment of the present disclosure, the characteristic parameter includes at least one of: the method comprises the following steps of total matching times, total matching time, average matching times of a preset time period, average matching distance of the preset time period, average matching duration of the preset time period, maximum matching distance interval and maximum matching time interval.

S103, determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters.

In the embodiment of the disclosure, the electronic device may determine all matched pair of trajectory data from the trajectory data to be matched based on the characteristic parameter corresponding to each pair of trajectory data, so as to obtain at least one pair of matched trajectory data.

For example, the trajectory data to be matched includes: in the case of one piece of image trajectory data t1, one piece of image trajectory data t2, one piece of device trajectory data s1, and one piece of device trajectory data s2, the electronic device may determine a feature parameter between t1 and s1, a feature parameter between t1 and s2, a feature parameter between t2 and s1, and a feature parameter between t2 and s2, and determine all matching trajectory data from the 4 pairs of trajectory data according to the corresponding feature parameters; for example, t1 and s2 are determined as a pair of matched trajectory data, and t2 and s1 are determined as a pair of matched trajectory data.

In some embodiments, the electronic device may select one or more pairs of trajectory data with the largest corresponding characteristic parameter as the obtained at least one pair of matched trajectory data; in other embodiments, the electronic device may also select each pair of trajectory data whose corresponding characteristic parameter is greater than or equal to the preset parameter threshold, so as to obtain at least one pair of matched trajectory data.

And S104, determining the track of the corresponding target object for each pair of matched track data.

In the embodiment of the present disclosure, in the case that the electronic device obtains all the matched trajectory data, for each pair of matched trajectory data, the trajectory of the target object corresponding to the pair of matched trajectory data may be determined according to the pair of matched trajectory data.

In some embodiments, for each pair of matched trajectory data, the electronic device may compare one image trajectory data of the pair of matched trajectory data with a position point of one device trajectory data, determine all different position points, and sort all the different position points according to corresponding time points, thereby obtaining a complete trajectory of the target object corresponding to the image trajectory data of the pair of matched trajectory data.

In some embodiments, S102 may be implemented by S1021-S1023, which will be described in conjunction with fig. 2.

S1021, determining the distance interval between each first position point and each second position point to obtain at least one distance interval, and determining the time interval between each first time point and each second time point to obtain at least one time interval; each pair of trace data includes: any piece of image track data and any piece of equipment track data; the image track data includes: at least one first location point and a corresponding at least one first time point; the any piece of equipment trajectory data comprises: at least one second location point and a corresponding at least one second point in time.

S1022, determining matching parameters based on the at least one distance interval and the at least one time interval.

In the embodiment of the disclosure, for any pair of track data (i.e., one piece of image track data and one piece of device track data), the electronic device may determine a distance interval between each first position point and each second position point, and determine a time interval between each first time point and each second time point, thereby obtaining at least one distance interval and at least one time interval, and determine a matching parameter corresponding to the pair of track data according to the obtained at least one distance interval and the obtained at least one time interval.

In some embodiments, for any pair of track data, the electronic device may determine, according to the calculated distance interval and time interval, which first location points and second location points match, and which first time points and second time points match, to obtain a matching location and a matching time of the any pair of track data, and use the matching location and the matching time as matching parameters of the any pair of track data.

In some embodiments, S1022 described above can be implemented by S201-S204, which will be described by taking fig. 3 as an example.

S201, analyzing the relationship between any distance interval and a preset distance range and analyzing the relationship between the corresponding time interval and a preset time range for any distance interval and the time interval corresponding to the distance interval.

The preset distance range and the preset time range can be set according to actual needs, and the embodiment of the disclosure does not limit the preset distance range and the preset time range; for example, the preset distance range may be 1 km, and the preset time range may be 15 minutes.

S202, under the condition that any distance interval belongs to a preset distance range and the corresponding time interval belongs to a preset time range, determining the position points of the pair of track data corresponding to any distance interval, and matching the position points with the time points corresponding to the corresponding time interval.

For any one of the obtained at least one distance interval and one of the obtained at least one time interval corresponding to the any one distance interval, the electronic device may determine whether the distance interval belongs to a preset distance range, and determine whether the time interval belongs to a preset time range, and in a case that the distance interval belongs to the preset distance range and the time interval belongs to the preset time range, determine that the any pair of trajectory data matches at the any position point and matches at the corresponding time point, and take the any position point as a matching position of the any pair of trajectory data, and take the corresponding time point as a matching time of the any pair of trajectory data.

S203, under the condition that at least one distance interval and at least one time interval are analyzed, at least one matching position of each pair of track data and at least one matching time corresponding to the at least one matching position are obtained.

And S204, obtaining a matching parameter according to the at least one matching position and the at least one matching time.

In some embodiments, the electronic device may obtain at least one matching position and at least one matching time corresponding to the arbitrary pair of trajectory data after analyzing the at least one distance interval and the at least one time interval corresponding to the arbitrary pair of trajectory data by using the method of S201-S202 described above, and may use the obtained at least one matching position and the obtained at least one matching time as matching parameters of the arbitrary pair of trajectory data; therefore, the matching parameters of each pair of track data are obtained.

In some embodiments, the above S204 may also be implemented by S2041-S2043:

s2041, in at least one matching position and at least one matching time, when there are at least two identical matching positions and a maximum time interval between at least two matching times corresponding to the at least two identical matching positions is smaller than a preset interval, determining a maximum matching time of the at least two matching times, and determining a maximum matching position corresponding to the maximum matching time of the at least two identical matching positions.

The electronic device may determine whether the same location point exists in the obtained at least one matching location, and in a case where it is determined that the same location point exists, may determine whether a maximum time interval among time intervals between time points corresponding to the same location point is smaller than a preset interval, and in a case where the maximum time interval is smaller than the preset interval, determine a maximum time point among the corresponding time points, and determine a location point corresponding to the maximum time point from among the same location points as a maximum location.

In the embodiment of the present disclosure, the at least two identical matching position points may be at least two position points with completely identical positions, or may be at least two position points whose distance between the two position points is smaller than a preset distance threshold, which is not limited in the embodiment of the present disclosure; the preset time interval may be set according to actual needs, for example, may be 15 minutes, and this is not limited in this disclosure.

S2042, discarding the matching time except the maximum matching time in the at least two matching times, and discarding the matching position except the maximum matching position in the at least two identical matching positions, to obtain at least one updated matching time and at least one updated matching position.

The electronic device may discard the matching positions except the maximum matching position in the same matching positions under the condition that the maximum matching time and the maximum matching position are obtained, correspondingly discard the maximum matching time in the matching times corresponding to the same matching positions, take the maximum matching position and other different matching positions as at least one updated matching position, and take the maximum matching time and the matching time corresponding to other different matching positions as at least one updated matching time.

S2043, obtaining a matching parameter according to the updated at least one matching position and the updated at least one matching time.

The electronic device can directly use the updated at least one matching position and the updated at least one matching time as the matching parameters of the arbitrary pair of trajectory data.

For the following descriptions of S2041 to S2043, at least one matching position is: position point 1, position point 2, position point 3, position point 4, and position point 5; at least one matching time is: time point 1, time point 2, time point 3, time point 4, and time point 5, and location point 1 corresponds to time point 1, location point 2 corresponds to time point 2, location point 3 corresponds to time point 3, location point 4 corresponds to time point 4, and location point 5 corresponds to time point 5, and in the case where it is determined therefrom that location point 1, location point 2, and location point 3 belong to the same matching location point, the electronic apparatus can determine interval j1 between time point 1 and time point 2, interval j2 between time point 2 and time point 3, and interval j3 between time point 1 and time point 3, and determine whether the largest interval between j1, j2, and j3 is smaller than a preset interval, and in the case where the largest interval is smaller than the preset interval, select the largest interval (the largest matching time) among time point 1, time point 2, and time point 3, for example, time point 2, and the position point 2 corresponding to time point 2 is taken as the maximum matching position; and discarding the position point 1 and the position point 3, and discarding the time point 1 and the time point 3, and taking the position point 2, the position point 4 and the position point 5 as at least one updated matching position, and taking the time point 2, the time point 4 and the time point 5 as at least one updated matching time.

Through the above S2041 to S2043, repeated position points and time points can be removed, interference factors for determining at least one pair of matched trajectory data are reduced, and the amount of data required to be calculated is reduced, so that the efficiency and accuracy in determining at least one pair of matched trajectory data can be improved. For example, when a certain mobile phone is connected to a certain base station for a long time, the base station may acquire a location point of the mobile phone at intervals to keep a heartbeat with the mobile phone, so as to obtain a plurality of same location points and corresponding time points of the mobile phone, and the above-mentioned S2041 to S2043 may remove the repeated location points and time points.

The following proceeds to the explanation of S1023 in fig. 2: s1023, determining characteristic parameters of each pair of track data based on the matching parameters; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data.

When determining the matching parameters of the arbitrary pair of trajectory data, the electronic device may determine the characteristic parameters of the arbitrary pair of trajectory data based on the matching parameters.

Here, in a case where at least one matching position and at least one corresponding matching time of the arbitrary pair of trajectory data are determined, the electronic device may determine at least one of a total matching number of times, a total matching time, an average matching number of times of a preset time period, an average matching distance of the preset time period, an average matching time of the preset time period, a maximum matching distance interval, and a maximum matching time interval of the arbitrary pair of trajectory data, thereby obtaining the characteristic parameters of the arbitrary pair of trajectory data.

In some embodiments, the characteristic parameters include: total matching times; the above S1023 may be implemented by S11:

and S11, counting the total number of the at least one matching position or the at least one matching time corresponding to each pair of track data for the characteristic parameters of each pair of track data, and taking the total number as the total matching times of the pair of track data.

For any pair of track data, the electronic device may count the total number of the at least one matching position or the at least one matching time when obtaining the at least one matching position and the at least one matching time, and use the counted total number as the total matching times of the any pair of track data. For example, for any pair of trajectory data, in a case where 8 matching positions and 8 corresponding matching times are determined, the electronic device may determine that the total matching number of times of the any pair of trajectory data is 8.

In some embodiments, in the case where the number of the obtained matching positions and the number of the matching times are not the same, the number of the obtained matching positions may be taken as the total number of matching times.

In some embodiments, in the case that at least one matching position is obtained, the electronic device may first determine whether the same matching position exists in the at least one matching position, and in the case that the same matching position exists, regard the same matching position as one matching position, so that the counted number of matching positions is more accurate, and the obtained total number of times of matching is more accurate.

Here, for any piece of image track data and any piece of equipment track data, if the total matching times between them is larger, the probability of representing their matching is higher, so the accuracy of each pair of determined matching track data can be improved by using the total matching times as a characteristic parameter for measuring the matching degree between them.

In some embodiments, the characteristic parameters include: total matching time; s1023 may also be implemented by S21:

and S21, for the characteristic parameters of each pair of track data, determining the total number of unit matching time according to at least one matching time corresponding to the pair of track data, and taking the total number of unit matching time as the total matching time of the pair of track data.

In the embodiment of the disclosure, for any pair of track data, the electronic device may determine unit matching time according to at least one matching time, determine the total amount of the unit matching time, and use the total amount as the total matching time of the any pair of track data. For example, in the case that each matching time includes year, month, and day, the day may be taken as the unit matching time, so that the number of different days corresponding to at least one matching time may be counted to obtain the total matching time of the arbitrary pair of trajectory data.

For example, for any pair of trajectory data, 4 matching times are obtained, respectively: xx years 2 month 1 No. 14: 00 o, xx year No. 2 month No. 1: 15: 26. xx years 2 month 3 # 6: 00 o, xx year No. 2 month No. 4: 15: 00, it can be determined that the track data of any pair are matched in numbers 1, 3 and 4, and the total matching time of the track data of any pair is 3.

In some embodiments of the present disclosure, since the trajectory data to be matched is data within a preset time period, the electronic device may further determine the unit matching time according to the preset time period corresponding to the trajectory data to be matched, for example, when the preset time period is one month, a day may be used as the unit matching time, and when the preset time period is one day, 1 hour may be used as the unit matching time. In other embodiments, the unit matching time may also be determined in other manners, which is not limited in the embodiments of the disclosure.

Here, for any piece of image track data and any piece of equipment track data, if the total matching time between them is longer, the probability of representing their matching is higher, so the accuracy of each pair of determined matching track data can be improved by using the total matching time as a characteristic parameter for measuring the matching degree between them.

In some embodiments, the characteristic parameters include: average matching times of a preset time period; the above S1023 can also be realized by S31-S32:

s31, determining a fourth number of matching time in each unit matching time according to at least one matching time corresponding to each pair of track data for the characteristic parameters of each pair of track data; the preset time period includes at least one unit matching time.

The preset number of unit matching time constitutes a preset time period; for example, in the case that the preset time period is 1 day and the unit matching time is hours, the preset time period includes 12 unit matching times; for another example, if the preset time period is 7 days and the unit matching time is days, the preset time period includes 7 unit matching times.

For any pair of track data, the electronic device may count the number of matching times in each unit matching time according to the obtained at least one matching time corresponding to the any pair of track data, to obtain a fourth number. Continuing with the above example, in the case where the unit matching time is day, it can be determined that there are two matching times for No. 1, and 1 matching time for No. 3 and No. 4, and thus the fourth numbers can be determined to be 2, 1, and 1, respectively.

And S32, determining a fourth number of first average values in a preset time period, and taking the first average values as the average matching times of the preset time period of the pair of track data.

Under the condition that the fourth quantities corresponding to all the unit matching times are obtained, the electronic equipment can calculate the average value of the obtained fourth quantities, so that the average matching times of any pair of track data in the preset time period can be obtained. Continuing with the above example, in the case that the preset time period is 7 days, and the fourth quantity corresponding to number 1 is 2, and the fourth quantity corresponding to each of numbers 3 and 4 is 1, the first average value of the fourth quantity in 7 days may be determined to be (2+1+ 1)/7.

Here, for any piece of image track data and any piece of equipment track data, if the average matching times between them in the preset time period is more, the probability of representing their matching is higher, so the accuracy of each pair of determined matching track data can be improved by using the average matching times in the preset time period as a characteristic parameter for measuring the matching degree between them.

In some embodiments, the characteristic parameters include: matching average distance of a preset time period; the above S1023 can also be realized by S41-S43:

s41, determining a matching position corresponding to the matching time in each unit matching time according to at least one matching position corresponding to each pair of track data according to the characteristic parameters of each pair of track data; the preset time period includes at least one unit matching time.

S42, determining the distance between every two different matching positions for the matching position corresponding to the matching time in each unit matching time to obtain at least one distance, and determining a second average value between the at least one distance.

And S43, determining a third average value of the obtained second average values, and taking the third average value as the matching average distance of the pair of track data in the preset time period.

For at least one matching position corresponding to any pair of track data, the electronic device may determine a matching position corresponding to the matching time within each unit matching time, calculate a distance between every two different matching positions under the condition that the corresponding matching position within each unit matching time is obtained, calculate a second average value of the obtained distances, finally calculate a third average value of the second average value within a preset time period, and use the obtained third average value as the matching average distance of the preset time period of the any pair of track data.

For example, for any pair of trajectory data, 5 matching times are obtained within 7 days, respectively: xx years 2 month 1 No. 14: 00 o, xx year No. 2 month No. 1 15: 26. xx years 2 month 1 No. 16: 26. xx years 2 month 3 # 6: 00 o, xx year No. 2 month No. 3 15: 00, the 5 matching positions corresponding to the 5 matching times one by one are respectively: position point 1, position point 2, position point 3, position point 4, and position point 5, and these 5 position points are all different position points, and then the matching position on day # 1 is: position point 1, position point 2, and position point 3; the matching positions on the day of No. 3 are: position point 4 and position point 5. The electronic device can calculate the distance 11 between the position point 1 and the position point 2, calculate the distance 22 between the position point 2 and the position point 3, calculate the distance 33 between the position point 1 and the position point 3, and take (distance 11+ distance 22+ distance 33)/3 as a second average value corresponding to the day of 1; and the electronic device may use the distance 44 between location 4 and location 5 as a second average value for the day # 3; finally, ((distance 11+ distance 22+ distance 33)/3+ distance 44)/7 was taken as the matching average distance of the arbitrary pair of trajectory data over 7 days.

In some embodiments, two different location points may refer to a distance between two location points that is not less than a preset distance value, for example, 500 meters or 1 kilometer, etc.

Here, for any piece of image trajectory data and any piece of device trajectory data, if the average distance between matching positions between them is larger, the probability of representing their matching is higher, so the accuracy of each pair of determined matching trajectory data can be improved by using the matching average distance of the preset time period as a characteristic parameter for measuring the matching degree between them.

In some embodiments, the characteristic parameters include: presetting the matching average time length of a time period; the above S1023 can also be realized by S51-53:

s51, determining the matching time in each unit matching time according to at least one matching time corresponding to each pair of track data for the characteristic parameters of each pair of track data; the preset time period includes at least one unit matching time.

And S52, determining the interval between every two different matching times for the matching time in each unit matching time to obtain at least one interval, and determining a fourth average value between the at least one interval.

And S53, determining a fifth average value of the obtained fourth average values, and taking the fifth average value as the matching average duration of the preset time period of the pair of track data.

For at least one matching time corresponding to any pair of track data, the electronic device may determine the matching time in each unit matching time, calculate a time interval between every two different matching times under the condition that the matching time in each unit matching time is obtained, calculate a fourth average value of the obtained time interval, finally calculate a fifth average value of the fourth average value in a preset time period, and use the obtained fifth average value as the matching average duration of the preset time period of any pair of track data.

For example, continuing with the above example for any pair of trajectory data, the electronic device may calculate 14 No. 2/month 1: 00 and xx year, month 2, No. 1 15: the time interval between 26 was 1 hour 26 minutes, 2 months No. 1 14: 00 o and 2 month No. 1 16: the time interval between 26 was 2 hours 26 minutes, 2 months No. 1 15: 26 and 16 from month 2 and No. 1: the time interval between 26 was 1 hour, and (1 hour 26 minutes +2 hours 26 minutes +1 hour)/3 was taken as the fourth average value for the day No. 2 month 1; and, the electronic device may convert month 2, No. 3, No. 6: 00 o and 2 month No. 3 15: the time interval between 00 is 9 hours, which is taken as the fourth average value corresponding to the day of month 2 and 3; finally, ((1 hour 26 minutes +2 hours 26 minutes +1 hour)/3 +9 hours)/7, was taken as the average length of time that the trace data of any pair matched over 7 days.

In some embodiments, two different matching times may mean that the time interval between the two matching times is not less than a preset time value, for example, 15 minutes or 10 minutes, etc.

Here, for any piece of image track data and any piece of equipment track data, if the average value of the time intervals between the matching times of any piece of image track data and any piece of equipment track data is larger, the possibility of representing the matching of any piece of image track data and any piece of equipment track data is higher, so that the accuracy of each pair of determined matching track data can be improved by adopting the matching average time length of the preset time period as a characteristic parameter for measuring the matching degree between the image track data and the equipment track data.

In some embodiments, the characteristic parameters include: a maximum matching distance interval; the above S1023 may also be realized by S61-62:

and S61, determining the distance between every two different matching positions according to at least one matching position corresponding to each pair of track data according to the characteristic parameters of each pair of track data to obtain at least one distance.

And S62, determining the maximum distance from at least one distance, and taking the maximum distance as the maximum matching distance interval of the pair of track data.

For at least one matching position corresponding to any pair of track data, the electronic device may determine a distance between every two different matching positions, and after obtaining all the distances, select a maximum distance as a maximum matching distance interval of the any pair of track data.

Here, for any piece of image track data and any piece of equipment track data, if the maximum distance interval between the matching positions between them is larger, the probability of representing their matching is higher, so that the accuracy of each pair of determined matching track data can be improved by using the maximum matching distance interval as a characteristic parameter for measuring the matching degree between them.

In some embodiments, the characteristic parameters include: a maximum matching time interval; the above S1023 may also be realized by S71-72:

and S71, determining the interval between every two different matching times according to at least one matching time corresponding to each pair of track data for the characteristic parameters of each pair of track data to obtain at least one interval.

And S72, determining the maximum interval from the at least one interval, and taking the maximum interval as the maximum matching time interval of each pair of track data.

For at least one matching time corresponding to any pair of track data, the electronic device may determine a time interval between every two different matching times, and select a maximum time interval as a maximum matching time interval of the any pair of track data after obtaining all the time intervals.

Here, for any piece of image track data and any piece of device track data, if the maximum time interval between the matching times of them is larger, the probability of representing their matching is higher, so that the accuracy of each pair of determined matching track data can be improved by using the maximum matching time interval as a characteristic parameter for measuring the matching degree between them.

In some embodiments, S103 may be implemented by S1031 to S1033, which is described below with reference to fig. 4 as an example.

And S1031, determining a mapping value corresponding to each characteristic parameter of each pair of track data for each pair of track data.

S1032, acquiring a weight value corresponding to each characteristic parameter; the weight value is obtained by training at least one preset pair of matched track data through a deep neural network.

For any pair of track data, under the condition that at least one characteristic parameter exists in any pair of track data, the electronic device can determine a mapping value corresponding to each characteristic parameter of any pair of track data, and obtain a weight value corresponding to each characteristic parameter, wherein the weight value is obtained by training at least one preset pair of matched track data through a deep neural network. For example, in the case where there are 7 kinds of characteristic parameters in any pair of trajectory data, the electronic device may determine 7 mapping values and 7 weight values corresponding to the 7 mapping values one to one.

In the embodiment of the present disclosure, the mapping value corresponding to each characteristic parameter of any pair of track data may be determined according to the value of the characteristic parameter of any pair of track data, the mapping value may be a score value within a preset score range, and the size of the score value is proportional to the size of the value of the characteristic parameter.

The preset fraction range can be set according to actual needs, and the embodiment of the disclosure does not limit the range; for example, the preset fraction value may be 1-10.

Here, the electronic device may obtain at least one pair of matching trajectory data (positive samples) in advance, for example, 1000 pairs of matching trajectory data may be obtained in advance, an initial weight value is set for each feature parameter, all the initial weight values are input into the deep neural network after the matching relationship in the at least one pair of matching trajectory data obtained in advance is disturbed, and a matching result output by the deep neural network (that is, trajectory data of each pair considered to be matched by the deep neural network) is obtained; and comparing the matching result with at least one pair of matched track data acquired in advance, determining a loss value according to the comparison result, adjusting the input initial weight value according to the determined loss value to obtain an updated weight value, continuously inputting the updated weight value and the at least one pair of matched track data with the disordered matching relation into the deep neural network, and repeating the steps until the updated weight value obtained at the last time is used as the weight value obtained by training under the condition that the determined loss value is smaller than the preset loss value.

Exemplary, the characteristic parameters include: under the conditions of the total matching times, the total matching time, the average matching times of the preset time period, the matching average distance of the preset time period, the matching average duration of the preset time period, the maximum matching distance interval and the maximum matching time interval, the weight value corresponding to the total matching times may be 0.7, the weight value corresponding to the total matching time may be 0.4, the weight value corresponding to the average matching times of the preset time period may be 0.5, the weight value corresponding to the matching average distance of the preset time period may be 0.9, the weight value corresponding to the matching average duration of the preset time period may be 0.7, the weight value corresponding to the maximum matching distance interval may be 0.8, and the weight value corresponding to the maximum matching time interval may be 0.6.

In some embodiments, S1031 may be implemented by S301-S302:

s301, for any image track data contained in the pair of track data, determining each characteristic parameter between the any image track data and at least one piece of equipment track data, and correspondingly obtaining at least one value of each characteristic parameter; and each value corresponds to any one of the image trace data and one of the device trace data.

For a piece of image trajectory data (any piece of image trajectory data) included in any pair of trajectory data, the electronic device may determine each feature parameter between the any piece of image trajectory data and each piece of device trajectory data in the to-be-matched trajectory data, so that in a case where at least one piece of device trajectory data is included in the to-be-matched trajectory data, at least one value of each feature parameter may be obtained correspondingly, and each value of the at least one value corresponds to the any piece of image trajectory data and one piece of device trajectory data, and represents a value of the feature parameter between the any piece of image trajectory data and the piece of device trajectory data. For example, in the case that there are 5 pieces of device trajectory data in the trajectory data to be matched, 5 values corresponding to each feature parameter may be obtained for any piece of image trajectory data, and each value corresponds to any piece of image trajectory data and one piece of device trajectory data.

S302, according to the magnitude relation between at least one value, corresponding mapping values are matched for each value, and according to the mapping values corresponding to any piece of equipment track data contained in the pair of track data, the mapping values corresponding to each characteristic parameter of the pair of track data are obtained.

The electronic device may determine a mapping value corresponding to each of the at least one value according to a magnitude relationship between the at least one value when obtaining the at least one value corresponding to each of the characteristic parameters, and obtain a mapping value corresponding to each of the characteristic parameters of the arbitrary pair of trajectory data according to a mapping value corresponding to one piece of device trajectory data included in the arbitrary pair of trajectory data. For example, in the case of 7 kinds of feature parameters, 7 mapping values corresponding to the 7 kinds of feature parameters of the arbitrary pair of trajectory data may be obtained, and each mapping value corresponds to one kind of feature parameter.

In some embodiments, for at least one value corresponding to each characteristic parameter, the electronic device may sort the at least one value from large to small, assign a score to the value of the first 10 from 10 to 1, and assign a score of 0 to the value of the tenth and the tenth, so that the score value corresponding to the first value is 10, the score value corresponding to the second value is 9, and decrease sequentially; thereby obtaining at least one fractional value corresponding to the at least one value. It should be noted that the fractional values given above are only exemplary, and the embodiments of the present disclosure do not limit this.

And S1033, determining at least one pair of matched track data from the track data to be matched based on the mapping value and the weight value.

The electronic device can determine all matched track data from the track data to be matched according to the mapping value corresponding to each characteristic parameter of each pair of track data and the weight value corresponding to each characteristic parameter, so that at least one pair of matched track data is obtained.

In the embodiment of the disclosure, on the basis of the mapping value, the determination of the matched trajectory data is further performed by using the weight value trained by the deep neural network, so that whether the characteristic parameter is important or not can be accurately distinguished, the determined matched trajectory data is more accurate, and the accuracy of the determined trajectory of the target object corresponding to each pair of matched trajectory data is finally further improved.

In some embodiments, the electronic device may also determine all matched trajectory data from the trajectory data to be matched directly according to the mapping value when obtaining the mapping value corresponding to each characteristic parameter, so as to obtain at least one pair of matched trajectory data; this can improve the determination efficiency.

In some embodiments, the above-mentioned S1033 may pass through S401-S404, which will be described below by taking fig. 5 as an example.

S401, determining a product value between a mapping value corresponding to each characteristic parameter of the pair of track data and a weight value corresponding to each characteristic parameter, and obtaining product values with the same number as the mapping values.

For any pair of track data, the electronic device may calculate a product value between a mapping value and a weight value corresponding to each characteristic parameter, so as to obtain M product values, under the condition that M mapping values corresponding to M kinds of characteristic parameters are obtained and M weight values corresponding to M kinds of characteristic parameters are obtained.

S402, taking the sum of the product values as a matching value of the pair of track data, and obtaining at least one matching value corresponding to each piece of image track data and at least one piece of equipment track data in the track data to be matched in the mode.

For any pair of track data, the electronic device may calculate a sum of the obtained product values, and use the obtained sum as a matching value of the any pair of track data, so that, for each piece of image track data in the to-be-matched track data, a matching value between the each piece of image track data and all pieces of device track data in the to-be-matched track data may be obtained in this way, so as to obtain at least one matching value, and each matching value represents an overall matching degree between the piece of image track data and a corresponding piece of device track data.

For example, in the case where there are 7 kinds of feature parameters, the matching value Kmp can be expressed by the following equation (1) for any pair of trajectory data:

Kmp＝a×A+b×B+c×C+d×D+e×E+f×F+g×G (1)

wherein, a to G represent 7 kinds of characteristic parameters, and a to G represent 7 weight values corresponding to the 7 kinds of characteristic parameters one by one.

And S403, regarding each piece of image track data, taking the equipment track data corresponding to the first target matching value in at least one matching value as the equipment track data matched with each piece of image track data to obtain a pair of matched track data.

S404, obtaining at least one pair of matching data under the condition that the equipment track data matched with the at least one piece of image track data is determined.

For any piece of image track data in the track data to be matched, the electronic equipment can select a matching value from at least one obtained matching value as a first target matching value, and uses one piece of equipment track data corresponding to the first target matching value as one piece of equipment track data matched with the any piece of image track data, so that the any piece of image track data and the one piece of equipment track data can be used as a pair of matched track data; and under the condition that the equipment track data matched with all the image track data in the track data to be matched is determined, at least one pair of matched data can be obtained.

In the embodiment of the present disclosure, the higher the matching value of a pair of trajectory data is, the higher the total matching degree of the pair of trajectory data is.

In the embodiment of the present disclosure, the first target matching value may be a maximum matching value among the obtained at least one matching value; thereby making the determined device trajectory data more closely match the image trajectory data.

In some embodiments, S403 may be implemented by S4031-S4033:

s4031, selecting a first number of second target matching values from at least one matching value corresponding to each piece of image track data, and correspondingly obtaining a second number of second target matching values for at least one piece of image track data; the second number is greater than the first number.

For any piece of image track data in the track data to be matched, the electronic device may select a first number of second target matching values that satisfy a condition from the corresponding at least one matching value, so that for at least one piece of image track data included in the track data to be matched, a second number of second target matching values may be obtained, and the second number is a product between the first number and the number of the at least one piece of image track data included in the track data to be matched.

In some embodiments, the electronic device may rank the at least one matching value and select a first number of second target matching values therefrom based on the ranking result. Exemplarily, the electronic device may sort the at least one matching value from large to small, and take the top ten matching values as 10 second target matching values; thus, in the case that the trajectory data to be matched includes 5 pieces of image trajectory data, 50 second target matching values can be obtained.

S4032, in the case that there are at least two second target matching values corresponding to the same device trajectory data in the second number of second target matching values, discarding the at least two second target matching values to obtain an updated second target matching value of each image trajectory data.

The electronic device may analyze whether two or more second target matching values in the second target matching values correspond to the same device trajectory data under the condition that a second number of second target matching values are obtained, and may discard the two or more second target matching values under the condition that the two or more second target matching values correspond to the same device trajectory data, so that a third number of second target matching values of the arbitrary piece of image trajectory data in the trajectory data to be matched may be obtained, where the third number is smaller than the second number. For example, continuing with the above example, after obtaining 50 second target matching values, in a case that it is determined that 3 second matching values correspond to the same piece of device trajectory data, the electronic device may discard the 3 second matching values, so as to obtain 47 second target matching values.

S4033, for each piece of image trajectory data, determining a first target matching value from the third number of second target matching values, and using the device trajectory data corresponding to the first target matching value as the device trajectory data matched with each piece of image trajectory data to obtain a pair of matched trajectory data.

Under the condition that a third number of second matching values are obtained, the electronic device can select one matching value from the third number of second target matching values as a first target matching value, and use one piece of device track data corresponding to the first target matching value as one piece of device track data matched with any one piece of image track data, so that any one piece of image track data and the one piece of device track data can be used as a pair of matched track data; and under the condition that the equipment track data matched with all the image track data in the track data to be matched is determined, at least one pair of matched data can be obtained.

The following example is continued for the above-described matching deduplication method. For example, when the device is a mobile phone, each piece of device trajectory data includes a mobile phone number, the mobile phone numbers corresponding to any two pieces of device trajectory data are different, and a target object corresponding to each piece of image trajectory data is a real person, when 10 second target matching values corresponding to each piece of device trajectory data in 5 pieces of device trajectory data are obtained for any one piece of image trajectory data in the to-be-matched trajectory data, that is, 50 second target matching values are obtained in total, and 3 second target matching values in the 50 second target matching values correspond to the same piece of device trajectory data B, the overall matching degree between the mobile phone number corresponding to the piece of device trajectory data B and the 3 pieces of image trajectory data is high, but generally one mobile phone number is matched with one real person, which indicates that the possibility that the mobile phone number is matched with each real person in three different real persons corresponding to the 3 pieces of image trajectory data is high If the number of the second target matching values is small, the 3 second matching values can be removed from the second target matching values corresponding to the 3 pieces of image track data; this may make the remaining second target match values more accurate.

By adopting the matching duplication elimination method, the device track data repeatedly corresponding to different image track data can be eliminated, and the interference in determining the first target matching value is reduced, so that the obtained candidate matching value for the first target matching value is more accurate, and the accuracy of the determined first target matching value is improved.

Fig. 6 is a flowchart of an exemplary trajectory determination method provided by an embodiment of the present disclosure. As shown in fig. 6, at least one pair of matched trajectory data is obtained in advance as a positive sample, the positive sample and a preset weight value are trained by using a deep neural network to obtain a trained weight value, meanwhile, trajectory data to be matched is obtained, a characteristic parameter between each pair of trajectory data in the trajectory data to be matched is determined, a mapping value corresponding to a value of each characteristic parameter is determined according to the obtained value of the characteristic parameter, a matching value between each pair of trajectory data is determined by using the mapping value and the trained weight value, and all matched trajectory data are determined from all pairs of trajectory data according to the size of the matching value, so that at least one pair of matched trajectory data is obtained.

The present disclosure further provides a trajectory determination apparatus, and fig. 7 is a schematic structural diagram of the trajectory determination apparatus provided in the embodiment of the present disclosure; as shown in fig. 7, the trajectory determination device 1 includes: an obtaining unit 10, configured to obtain trajectory data to be matched, where the trajectory data to be matched includes: at least one image trajectory data of the target object and at least one device trajectory data of the device; a determining unit 20, configured to determine a characteristic parameter of each pair of trajectory data; each pair of track data comprises: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined.

In some embodiments of the present disclosure, the any piece of image trajectory data includes: at least one first location point and a corresponding at least one first time point; the any piece of device trajectory data includes: at least one second location point and a corresponding at least one second time point; the determining unit 20 is further configured to determine a distance interval between each first location point and each second location point to obtain at least one distance interval, and determine a time interval between each first time point and each second time point to obtain at least one time interval; determining matching parameters based on the at least one distance interval and the at least one time interval; determining the feature parameters of each pair of trajectory data based on the matching parameters.

In some embodiments of the present disclosure, the characteristic parameter includes at least one of: the method comprises the following steps of total matching times, total matching time, average matching times of a preset time period, average matching distance of the preset time period, average matching duration of the preset time period, maximum matching distance interval and maximum matching time interval.

In some embodiments of the present disclosure, the characteristic parameter is at least one characteristic parameter; the determining unit 20 is further configured to determine a mapping value corresponding to each feature parameter of each pair of trajectory data; acquiring a weight value corresponding to each characteristic parameter; the weight values are obtained by training at least one preset pair of matched track data through a deep neural network; and determining at least one pair of matched track data from the track data to be matched based on the mapping value and the weight value.

In some embodiments of the present disclosure, the determining unit 20 is further configured to determine, for the any piece of image trajectory data, each feature parameter between the any piece of image trajectory data and the at least one piece of device trajectory data, and obtain at least one value of each feature parameter correspondingly; and each value corresponds to any one of the image trajectory data and one of the device trajectory data; and according to the magnitude relation among the at least one value, corresponding mapping values are matched for each value, and according to the mapping values corresponding to any piece of equipment track data, the mapping values corresponding to each characteristic parameter of each pair of track data are obtained.

In some embodiments of the present disclosure, the determining unit 20 is further configured to determine a product value between a mapping value corresponding to each feature parameter of each pair of track data and a weight value corresponding to each feature parameter, so as to obtain product values with the same number as the mapping values; taking the sum of the product values as a matching value of each pair of track data, and obtaining at least one matching value corresponding to each image track data and at least one piece of equipment track data in the track data to be matched in this way; for each piece of image track data, taking the equipment track data corresponding to the first target matching value in the at least one matching value as the equipment track data matched with each piece of image track data to obtain a pair of matched track data; and obtaining the at least one pair of matching data under the condition that the equipment track data matched with the at least one piece of image track data is determined.

In some embodiments of the present disclosure, the determining unit 20 is further configured to select a first number of second target matching values from the at least one matching value corresponding to each piece of image track data, and obtain a second number of second target matching values for the at least one piece of image track data; the second number is greater than the first number; under the condition that at least two second target matching values in the second number of second target matching values correspond to the same equipment track data, discarding the at least two second target matching values to obtain a third number of second target matching values of each piece of image track data; and for each piece of image track data, determining the first target matching value from the third number of second target matching values, and taking the equipment track data corresponding to the first target matching value as the equipment track data matched with each piece of image track data to obtain the pair of matched track data.

In some embodiments of the present disclosure, the determining unit 20 is further configured to, for any distance interval and a time interval corresponding to the any distance interval, analyze an affiliation between the any distance interval and a preset distance range, and analyze an affiliation between the corresponding time interval and a preset time range; under the condition that any one distance interval belongs to a preset distance range and the corresponding time interval belongs to a preset time range, determining the position point of each pair of track data corresponding to the any one distance interval and matching the position points with the time points corresponding to the corresponding time intervals; under the condition that the at least one distance interval and the at least one time interval are analyzed, obtaining at least one matching position of each pair of track data and at least one matching time corresponding to the at least one matching position; and obtaining the matching parameters according to the at least one matching position and the at least one matching time.

In some embodiments of the present disclosure, the determining unit 20 is further configured to, in a case that there are at least two identical matching locations in the at least one matching location and the at least one matching time, and a maximum time interval between at least two matching times corresponding to the at least two identical matching locations is smaller than a preset interval, determine a maximum matching time in the at least two matching times, and determine a maximum matching location corresponding to the maximum matching time in the at least two identical matching locations; discarding the matching time except the maximum matching time in the at least two matching times, and discarding the matching position except the maximum matching position in the at least two same matching positions to obtain at least one updated matching time and at least one updated matching position; and obtaining the matching parameters according to the updated at least one matching position and the updated at least one matching time.

In some embodiments of the present disclosure, the characteristic parameters include: total matching times; the determining unit 20 is further configured to count a total number of the at least one matching position or the at least one matching time corresponding to each pair of track data, and use the total number as the total matching times of each pair of track data.

In some embodiments of the present disclosure, the characteristic parameters include: total matching time; the determining unit 20 is further configured to determine, according to the at least one matching time corresponding to each pair of track data, a total number of unit matching times, and use the total number of unit matching times as the total matching time of each pair of track data.

In some embodiments of the present disclosure, the characteristic parameters include: average matching times of a preset time period; the determining unit 20 is further configured to determine a fourth number of matching times in each unit matching time according to the at least one matching time corresponding to each pair of trajectory data; the preset time period comprises at least one unit matching time; and determining the first average value of the fourth quantity in the preset time period, and taking the first average value as the average matching times of the preset time period of each pair of track data.

In some embodiments of the present disclosure, the characteristic parameters include: matching average distance of a preset time period; the determining unit 20 is further configured to determine, according to the at least one matching position corresponding to each pair of track data, a matching position corresponding to a matching time within each unit matching time; the preset time period comprises at least one unit matching time; for the matching position corresponding to the matching time in each unit matching time, determining the distance between every two different matching positions to obtain at least one distance, and determining a second average value between the at least one distance; and determining a third average value of the obtained second average value in the preset time period, and taking the third average value as the matching average distance of each pair of track data in the preset time period.

In some embodiments of the present disclosure, the characteristic parameters include: presetting the matching average time length of a time period; the determining unit 20 is further configured to determine a matching time within each unit matching time according to the at least one matching time corresponding to each pair of track data; the preset time period comprises at least one unit matching time; for the matching time in each unit matching time, determining the time interval between every two different matching times to obtain at least one time interval, and determining a fourth average value between the at least one time interval; and determining a fifth average value of the obtained fourth average values, and taking the fifth average value as the matching average duration of the preset time period of each pair of track data.

In some embodiments of the present disclosure, the characteristic parameters include: a maximum matching distance interval; the determining unit 20 is further configured to determine a distance between each two different matching positions according to the at least one matching position corresponding to each pair of track data, so as to obtain at least one distance; determining a maximum distance from the at least one distance, and using the maximum distance as the maximum matching distance interval of each pair of trajectory data.

In some embodiments of the present disclosure, the characteristic parameters include: a maximum matching time interval; the determining unit 20 is further configured to determine a time interval between every two different matching times according to the at least one matching time corresponding to each pair of trajectory data, so as to obtain at least one time interval; determining a maximum time interval from the at least one time interval, and using the maximum time interval as the maximum matching time interval of each pair of trace data.

In some embodiments of the present disclosure, the target object comprises: a real character; the image track data comprises: at least one of identification and characteristic information of a real person, and first trajectory data of the real person; the feature information includes at least one of: age, gender, clothing characteristics; the any piece of device trajectory data includes: an identification of a device and second trajectory data for the identification; the determining unit 20 is further configured to determine, for each pair of matched trajectory data, a match between the device identifier and at least one of the identity identifier and the feature information corresponding to the pair of matched trajectory data; and determining the track of the real person according to the first track data and the second track data.

An embodiment of the present disclosure further provides an electronic device, and fig. 8 is a schematic structural diagram of the electronic device provided in the embodiment of the present disclosure, as shown in fig. 8, including: a memory 21 and a processor 22, wherein the memory 21 and the processor 22 are connected by a communication bus 23; a memory 21 for storing an executable computer program; the processor 22 is configured to implement the method provided by the embodiment of the present disclosure, for example, the trajectory determination method provided by the embodiment of the present disclosure, when the executable computer program stored in the memory 21 is executed.

The present disclosure provides a computer-readable storage medium, which stores a computer program for causing the processor 22 to execute a method provided by the present disclosure, for example, a trajectory determination method provided by the present disclosure.

In some embodiments of the present disclosure, the storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

In some embodiments of the disclosure, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts, or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.

In summary, according to the technical implementation scheme, the mobile phone data for matching is not mobile phone data obtained after image track screening, and the characteristic parameters for measuring the matching degree of the image track data and the equipment track data are adopted to match the image track data and the equipment track data, so that on one hand, the accuracy of a subsequently obtained matching result can be improved due to the fact that the mobile phone data for matching is more comprehensive, and on the other hand, the accuracy of the obtained matching result can be improved due to the fact that the characteristic parameters for measuring the matching degree are adopted; thereby, the accuracy of the obtained trajectory of the target object can be improved.

The above description is only an example of the present disclosure, and is not intended to limit the scope of the present disclosure. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present disclosure are included in the protection scope of the present disclosure.

Claims

1. A trajectory determination method, comprising:

acquiring track data to be matched, wherein the track data to be matched comprises: at least one image trajectory data of the target object and at least one device trajectory data of the device;

determining characteristic parameters of each pair of track data; each pair of track data comprises: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data;

determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters;

for each pair of matched trajectory data, a trajectory of the corresponding target object is determined.

2. The method of claim 1, wherein the any piece of image trace data comprises: at least one first location point and a corresponding at least one first time point; the any piece of device trajectory data includes: at least one second location point and a corresponding at least one second time point; the determining the characteristic parameters of each pair of track data comprises the following steps:

determining a distance interval between each first position point and each second position point to obtain at least one distance interval, and determining a time interval between each first time point and each second time point to obtain at least one time interval;

determining matching parameters based on the at least one distance interval and the at least one time interval;

determining the feature parameters of each pair of trajectory data based on the matching parameters.

3. The method according to claim 1 or 2, wherein the characteristic parameters comprise at least one of:

the method comprises the following steps of total matching times, total matching time, average matching times of a preset time period, average matching distance of the preset time period, average matching duration of the preset time period, maximum matching distance interval and maximum matching time interval.

4. The method according to any one of claims 1 to 3, wherein the characteristic parameter is at least one characteristic parameter; the determining at least one pair of matched trajectory data from the trajectory data to be matched based on the characteristic parameters includes:

determining a mapping value corresponding to each characteristic parameter of each pair of track data;

acquiring a weight value corresponding to each characteristic parameter; the weight values are obtained by training at least one preset pair of matched track data through a deep neural network;

and determining at least one pair of matched track data from the track data to be matched based on the mapping value and the weight value.

5. The method of claim 4, wherein determining the mapping value corresponding to each feature parameter of each pair of trace data comprises:

for any piece of image track data, determining each characteristic parameter between any piece of image track data and at least one piece of equipment track data, and correspondingly obtaining at least one value of each characteristic parameter; and each value corresponds to any one of the image trajectory data and one of the device trajectory data;

and according to the magnitude relation among the at least one value, corresponding mapping values are matched for each value, and according to the mapping values corresponding to any piece of equipment track data, the mapping values corresponding to each characteristic parameter of each pair of track data are obtained.

6. The method according to claim 4 or 5, wherein the determining at least one pair of matching trajectory data from the trajectory data to be matched based on the mapping value and the weight value comprises:

determining a mapping value corresponding to each characteristic parameter of each pair of track data, and obtaining a product value with the same number as the mapping values by the product value between the mapping value corresponding to each characteristic parameter and the weight value corresponding to each characteristic parameter;

taking the sum of the product values as a matching value of each pair of track data, and obtaining at least one matching value corresponding to each image track data and at least one piece of equipment track data in the track data to be matched in this way;

for each piece of image track data, taking the equipment track data corresponding to the first target matching value in the at least one matching value as the equipment track data matched with each piece of image track data to obtain a pair of matched track data;

and obtaining the at least one pair of matching data under the condition that the equipment track data matched with the at least one piece of image track data is determined.

7. The method according to claim 6, wherein for each piece of image track data, taking device track data corresponding to a first target matching value in the at least one matching value as device track data matched with each piece of image track data to obtain a pair of matched track data, includes:

selecting a first number of second target matching values from the at least one matching value corresponding to each piece of image track data, and correspondingly obtaining a second number of second target matching values for the at least one piece of image track data; the second number is greater than the first number;

under the condition that at least two second target matching values in the second number of second target matching values correspond to the same equipment track data, discarding the at least two second target matching values to obtain a third number of second target matching values of each piece of image track data;

and for each piece of image track data, determining the first target matching value from the third number of second target matching values, and taking the equipment track data corresponding to the first target matching value as the equipment track data matched with each piece of image track data to obtain the pair of matched track data.

8. The method of claim 2, wherein determining the matching parameters based on the at least one distance interval and the at least one time interval comprises:

for any distance interval and a time interval corresponding to the distance interval, analyzing the relationship between the distance interval and a preset distance range, and analyzing the relationship between the corresponding time interval and a preset time range;

under the condition that any one distance interval belongs to a preset distance range and the corresponding time interval belongs to a preset time range, determining the position point of each pair of track data corresponding to the any one distance interval and matching the position points with the time points corresponding to the corresponding time intervals;

under the condition that the at least one distance interval and the at least one time interval are analyzed, obtaining at least one matching position of each pair of track data and at least one matching time corresponding to the at least one matching position;

and obtaining the matching parameters according to the at least one matching position and the at least one matching time.

9. The method of claim 8, wherein the deriving the matching parameters according to the at least one matching location and the at least one matching time comprises:

determining the maximum matching time in the at least two matching times and determining the maximum matching position corresponding to the maximum matching time in the at least two identical matching positions when at least two identical matching positions exist in the at least one matching position and the at least one matching time and the maximum time interval between the at least two matching times corresponding to the at least two identical matching positions is smaller than a preset interval;

discarding the matching time except the maximum matching time in the at least two matching times, and discarding the matching position except the maximum matching position in the at least two same matching positions to obtain at least one updated matching time and at least one updated matching position;

and obtaining the matching parameters according to the updated at least one matching position and the updated at least one matching time.

10. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of total matching times, the determining the feature parameters of each pair of trajectory data based on the matching parameters includes:

and counting the total number of the at least one matching position or the at least one matching time corresponding to each pair of track data, and taking the total number as the total matching times of each pair of track data.

11. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of total matching time, the determining the feature parameters of each pair of trajectory data based on the matching parameters includes:

and determining the total number of unit matching time according to the at least one matching time corresponding to each pair of track data, and taking the total number of unit matching time as the total matching time of each pair of track data.

12. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of an average matching number of a preset time period, the determining the feature parameter of each pair of trajectory data based on the matching parameter includes:

determining a fourth number of matching times in each unit matching time according to the at least one matching time corresponding to each pair of track data; the preset time period comprises at least one unit matching time;

and determining the first average value of the fourth quantity in the preset time period, and taking the first average value as the average matching times of the preset time period of each pair of track data.

13. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of a matching average distance of a preset time period, the determining the feature parameters of each pair of trajectory data based on the matching parameters includes:

determining a matching position corresponding to the matching time in each unit matching time according to the at least one matching position corresponding to each pair of track data; the preset time period comprises at least one unit matching time;

for the matching position corresponding to the matching time in each unit matching time, determining the distance between every two different matching positions to obtain at least one distance, and determining a second average value between the at least one distance;

and determining a third average value of the obtained second average value in the preset time period, and taking the third average value as the matching average distance of each pair of track data in the preset time period.

14. The method according to claim 8 or 9, wherein the characteristic parameters comprise: under the condition of a matching average duration of a preset time period, the determining the characteristic parameter of each pair of trajectory data based on the matching parameter includes:

determining the matching time in each unit matching time according to the at least one matching time corresponding to each pair of track data; the preset time period comprises at least one unit matching time;

for the matching time in each unit matching time, determining the interval between every two different matching times to obtain at least one interval, and determining a fourth average value between the at least one interval;

and determining a fifth average value of the obtained fourth average values, and taking the fifth average value as the matching average duration of the preset time period of each pair of track data.

15. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of a maximum matching distance interval, the determining the feature parameters of each pair of trajectory data based on the matching parameters includes:

determining the distance between every two different matching positions according to the at least one matching position corresponding to each pair of track data to obtain at least one distance;

determining a maximum distance from the at least one distance, and using the maximum distance as the maximum matching distance interval of each pair of trajectory data.

16. The method according to claim 8 or 9, wherein the characteristic parameters comprise: in the case of a maximum matching time interval, the determining the feature parameters of each pair of trajectory data based on the matching parameters includes:

determining an interval between every two different matching times according to the at least one matching time corresponding to each pair of track data to obtain at least one interval;

determining a maximum interval from the at least one time interval, and using the maximum interval as the maximum matching time interval of each pair of trace data.

17. The method of claim 1, wherein the target object comprises: a real character; the image track data comprises: at least one of identification and characteristic information of a real person, and first trajectory data of the real person; the feature information includes at least one of: age, gender, clothing characteristics; the any piece of device trajectory data includes: an identification of a device and second trajectory data for the identification; for each pair of matched trajectory data, determining a trajectory of a corresponding target object, comprising:

for each pair of matched track data, determining matching between the device identifier and at least one of the identity identifier and the feature information corresponding to each pair of matched track data;

and determining the track of the real person according to the first track data and the second track data.

18. A trajectory determination device, comprising:

the device comprises an acquisition unit, a matching unit and a matching unit, wherein the acquisition unit is used for acquiring track data to be matched, and the track data to be matched comprises: at least one image trajectory data of the target object and at least one device trajectory data of the device;

the determining unit is used for determining the characteristic parameters of each pair of track data; each pair of track data comprises: any piece of image track data and any piece of equipment track data; the characteristic parameters are used for representing the matching degree between any piece of image track data and any piece of equipment track data; determining at least one pair of matched track data from the track data to be matched based on the characteristic parameters; for each pair of matched trajectory data, a trajectory of the corresponding target object is determined.

19. An electronic device, comprising:

a memory for storing an executable computer program;

a processor for implementing the method of any one of claims 1 to 17 when executing an executable computer program stored in the memory.

20. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 17.