WO2023098339A1

WO2023098339A1 - Data processing method and apparatus, device, storage medium and program product

Info

Publication number: WO2023098339A1
Application number: PCT/CN2022/127065
Authority: WO
Inventors: 张丹丹; 赵海川; 王长春
Original assignee: 上海商汤智能科技有限公司
Priority date: 2021-12-03
Filing date: 2022-10-24
Publication date: 2023-06-08
Also published as: CN114185964A

Abstract

Disclosed in embodiments of the present disclosure are a data processing method and apparatus, a device, a storage medium and a program product. The method comprises: obtaining a first track point set of each first object in at least two first objects, wherein the at least two first objects have the same or related attributes, and each first track point set comprises at least one track point; performing space-time collision on track points in the first track point set of the at least two first objects to obtain at least one space-time overlapping area; determining at least one second object other than the at least two first objects appearing in the at least one space-time overlapping area, and a second track point set of each second object in the at least one space-time overlapping area; and for each second object, under the condition that the number of the track points in the second track point set of the second object exceeds a track point number threshold, determining that the second object has an association relationship with the at least two first objects.

Description

Data processing method, device, device, storage medium and program product

Cross References to Related Applications

This disclosure is based on the Chinese patent application with the application number 202111467662.6, the application date is December 03, 2021, and the application name is "data processing method, device, equipment, storage medium and program product", and requires the priority of the Chinese patent application Right, the entire content of this Chinese patent application is hereby incorporated into this disclosure as a reference.

technical field

The present disclosure relates to but not limited to the technical field of computer vision, and in particular relates to a data processing method, device, equipment, storage medium and program product.

Background technique

Spatio-temporal data has the characteristics of large scale, wide temporal and regional distribution, and can potentially contain trajectory information of a large number of objects. However, the data analysis system in the related art cannot effectively mine the potential trajectory information in the massive spatio-temporal data, etc., so the value of these data cannot be fully utilized.

Contents of the invention

In view of this, the embodiments of the present disclosure provide a data processing method, device, device, storage medium, and program product.

The technical scheme of the embodiment of the present disclosure is realized in this way:

An embodiment of the present disclosure provides a data processing method, the method including:

Obtain a first track point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first track point sets including at least one track point;

performing space-time collision on track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

determining at least one second object other than the at least two first objects occurring within the at least one spatio-temporal overlapping region, and the second object of each of the second objects within the at least one spatio-temporal overlapping region set of track points;

For each of the second objects, when the number of trajectory points in the second trajectory point set of the second object exceeds the threshold of the number of trajectory points, determine that the second object and the at least two first objects There is an association.

An embodiment of the present disclosure provides a data processing device, and the device includes:

The acquiring part is configured to acquire a first trajectory point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the The first track point set includes at least one track point;

The collision part is configured to perform space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

The first determining part is configured to determine at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and each of the second objects in the at least a second set of trajectory points within a spatio-temporal overlapping region;

The second determining part is configured to, for each of the second objects, determine that the second object is related to There is an association relationship between the at least two first objects.

An embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements some or all of the steps in the above method when executing the program.

An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, part or all of the steps in the above method are implemented.

An embodiment of the present disclosure provides a computer program, including computer readable codes, when the computer readable codes are run in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method .

An embodiment of the present disclosure provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, a part or part of the above-mentioned method is implemented. All steps.

In the embodiment of the present disclosure, by analyzing the trajectory information of at least two first objects with the same or related attributes, at least one space-time overlapping area is obtained, and the at least two first objects appearing in the at least one space-time overlapping area are analyzed. Analyze the trajectory information of at least one second object other than the first object to obtain a second object that is associated with at least two first objects, thereby improving the ability to analyze trajectory information, and then making full use of the trajectory information In addition, it can make the resources invested in the acquisition of massive trajectory information be used more effectively.

Description of drawings

FIG. 1 is a schematic diagram of the implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of the implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of an implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of an implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of an implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 6A is a schematic diagram of an implementation flow of a data processing method provided by an embodiment of the present disclosure;

FIG. 6B is a schematic diagram of a trajectory analysis interface provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of the composition and structure of a data processing device provided by an embodiment of the present disclosure;

FIG. 8 is a schematic diagram of a hardware entity of a computer device provided by an embodiment of the present disclosure.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be further elaborated below in conjunction with the accompanying drawings and embodiments, and the described embodiments should not be regarded as limiting the present disclosure. All other embodiments obtained under the premise of no creative work belong to the protection scope of the present disclosure. In the following description, references to "some embodiments" describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or a different subset of all possible embodiments, and Can be combined with each other without conflict. The term "first/second/third" involved in the following description is only to distinguish similar objects, and does not represent a specific order for objects. It is understandable that "first/second/third" is allowed The specific order or sequence of events may be interchanged such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terms used herein are for the purpose of describing the present disclosure only, and are not intended to limit the present disclosure.

An embodiment of the present disclosure provides a data processing method, which can be executed by a processor of a computer device. Among them, computer equipment refers to servers, notebook computers, tablet computers, desktop computers, smart TVs, set-top boxes, mobile devices (such as mobile phones, portable video players, personal digital assistants, dedicated messaging devices, portable game devices), etc. Devices with data processing capabilities. Fig. 1 is a schematic flow diagram of a data processing method provided by an embodiment of the present disclosure. As shown in Fig. 1, the method includes the following steps S101 to S104:

Step S101, obtaining a first trajectory point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first trajectory points The point set includes at least one trajectory point.

Here, each of the at least two first objects may be any suitable movable object for which track information can be collected, such as a person, an animal, a vehicle, an object, etc., which is not limited here. In some implementations, the at least two first objects may be at least two of the first object set preset by the user.

The first track point set of each first object may include at least one track point of the first object. Each track point of an object may be recorded information of the object appearing at a specific space at a specific time. During implementation, the record information of each first object appearing in different spaces at different times can be collected by any suitable means such as image collection or positioning information collection, so as to obtain at least one trajectory point of each first object, and then obtain A first track point set for each first object. In some implementations, the collected track points of each first object may be directly acquired to obtain the first set of track points of each first object. In other embodiments, the collected track points of each object can be stored first, and then the track of each first object in at least two first objects can be obtained by querying from the stored track point data of a large number of objects point collection.

The attributes of an object can include object types, such as people, cats, dogs, vehicles, objects, etc., and can also include object identity attributes, such as the identity of the object, the identity type of the object, and the identity label of the object. limited.

At least two first objects may have the same attributes, or may have different but related attributes. Identical attributes may include, but are not limited to, identical object types, identical object identity attributes, and the like. Related attributes can include related object types, such as people and vehicles, people and cats, dogs and vehicles, etc., and can also include related object identity attributes, such as the identity of the person and the identity of the person's pet cat, the person's The identity mark and the identity mark of the person's vehicle may also include related identity types, such as a preset first identity type and a preset second identity type. During implementation, it may be determined whether there is correlation between different attributes according to actual conditions, which is not limited here.

Step S102, performing space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area.

Here, the spatiotemporal overlapping area is an area where the trajectories of at least two first objects overlap in time and space. Each spatio-temporal overlapping area may indicate that at least two first objects appear once in the same or similar space-time area, that is, the trajectories of at least two first objects intersect or are similar once in space-time. Performing space-time collision on track points in track point sets of at least two first objects refers to colliding at least one track point in track point sets of at least two first objects with another track point in space-time At least one track point in the track point set of the first object is matched. At least one space-time overlapping region between the two first objects can be obtained by performing space-time collision on track points in the set of track points of at least two first objects. During implementation, any suitable manner may be used to perform spatio-temporal collision on the track points in the track point sets of at least two first objects to obtain at least one spatio-temporal overlapping area, which is not limited in this embodiment of the present disclosure.

Step S103, determining at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping region, and each of the second objects in the at least one spatio-temporal overlapping region The second track point set of .

Here, the second object may be any suitable movable object that appears in at least one spatio-temporal overlapping region except the first object and whose track information can be collected, which is not limited here. For example, the second object may be a person, an animal, a vehicle, an object, etc. that appear in at least one space-time overlapping region and walk with the first object. During implementation, those skilled in the art may determine at least one second object appearing in at least one space-time overlapping region and the second trajectory point of each second object in at least one space-time overlapping region in an appropriate manner according to the actual situation set, which is not limited in the embodiments of the present disclosure.

In some implementations, at least one overlapping track point in the at least one space-time overlapping area can be obtained, and the object to which each overlapping track point belongs is counted to obtain at least one object appearing in the at least one space-time overlapping area ; Determining an object other than the first object in the at least one object as a second object; adding the track point of each second object in the at least one overlapping track point to the second track point set of the second object.

In some implementations, at least one object appearing in the at least one spatio-temporal overlapping area may be acquired, and an object in the at least one object other than the first object is determined as a second object; by acquiring each second object in The at least one trajectory point in the at least one spatio-temporal overlapping area obtains a second trajectory point set of each second object.

Step S104, for each second object, when the number of track points in the second track point set of the second object exceeds a threshold number of track points, determine that the second object is related to the at least two The first object has an association relationship.

Here, the association relationship may be any suitable relationship that characterizes the association between the second object and at least two first objects, and may include but not limited to the behavioral association relationship between the second object and at least two first objects, in Relationships on attributes, etc.

The track point number threshold can be preset or default. During implementation, an appropriate threshold for the number of track points may be determined according to an actual association relationship, which is not limited here. Each track point in the second set of track points of the second object can represent that the second object has appeared once in at least one spatio-temporal overlapping region, and the number of track points in the second set of track points can represent that the second object appears in at least one space-time overlapping region. The number of occurrences in a spatio-temporal overlapping region. In a case where the number of track points in the second set of track points of the second object exceeds the threshold number of track points, it may be determined that there is an association relationship between the second object and at least two first objects.

In some embodiments, the association relationship between the second object and the at least two first objects may include a behavioral association relationship between the second object and the at least two first objects. Behavioral associations may include behaviors such as meeting, traveling together, handing over objects, and feeding between the second object and the first object. For example, in the case where the first object is a first person and the second object is a second person, the association between the second object and at least two first objects may be between the second person and at least two first persons Perform meeting behavior, peer behavior or non-real-time object handover behavior, etc.; when the first object is the first person and the second object is a vehicle, the association relationship between the second object and at least two first objects can be at least Two first persons drive the vehicle; when the first object is the first person and the second object is a cat, the association relationship between the second object and at least two first objects can be that at least two first persons and Cat walks. During implementation, those skilled in the art may determine an appropriate behavioral relationship according to actual conditions, which is not limited here.

In some embodiments, the association relationship between the second object and the at least two first objects may include an association relationship between the second object and the at least two first objects in terms of attributes. The association relationship on attributes may include that the second object has potential associations on attributes with at least two first objects. For example, the second object may be an object potentially having the same or related object type, object identity attribute, etc. as any one of the at least two first objects. During implementation, the correlation on appropriate attributes may be determined according to actual conditions, which is not limited here.

In some embodiments, when the number of track points in the second set of track points of the second object in the above step S104 exceeds the threshold number of track points, it is determined that the second object and the at least two A first object has an association relationship, which may include the following steps S111 to S112:

Step S111 , if the number of track points in the second track point set of the second object exceeds the threshold number of track points, determine a target space-time overlapping area matched by each track point in the second track point set.

Here, each track point in the second set of track points of the second object can represent that the second object appears once in at least one space-time overlapping area, and the space-time overlapping area where each track point is located is the track point matching The target spatio-temporal overlapping region. During implementation, those skilled in the art may determine the target spatio-temporal overlapping region matched by each track point in the second set of track points in an appropriate manner according to the actual situation, which is not limited here.

In some implementations, each trajectory point can correspond to a time region and a space region, and by determining the time region and space region of each trajectory point in the space-time overlapping region, the target space-time overlapping region matched by each trajectory point can be determined .

Step S112, when the number of target spatio-temporal overlapping areas matched by the track points in the second set of track points exceeds a first overlap quantity threshold, determine that the second object has an association relationship with the at least two first objects .

Here, the first overlap quantity threshold may be preset or default. During implementation, an appropriate first overlapping quantity threshold may be determined according to an actual association relationship, which is not limited here.

In the above embodiment, when the number of track points in the second track point set of the second object exceeds the threshold number of track points, determine the target spatio-temporal overlapping area matched by each track point in the second track point set, and When the number of target spatio-temporal overlapping areas matched by the track points in the second set of track points exceeds a first overlap quantity threshold, it is determined that the second object has an association relationship with at least two first objects. In this way, the second object that appears in the spatio-temporal overlapping region that exceeds the first overlap quantity threshold can be determined as having an association relationship with at least two first objects, thereby improving the identification of the second object that has an association relationship with at least two first objects. The accuracy of the two objects can further improve the analysis ability of trajectory information.

An embodiment of the present disclosure provides a data processing method, which can be executed by a processor of a computer device. As shown in Figure 2, the method includes the following steps S201 to S205:

Step S201, obtaining a first track point set of each of the at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first track points The point set includes at least one trajectory point.

Step S202, performing space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area.

Here, the above steps S201 to S202 respectively correspond to the steps S101 to S102 in the foregoing embodiments, and for implementation, reference may be made to the implementation manners of the foregoing steps S101 to S102.

Step S203, when the number of the spatio-temporal overlapping regions exceeds a second overlapping number threshold, determine that there is a preset association behavior between the at least two first objects.

Here, the second overlap quantity threshold may be preset or default. During implementation, an appropriate second overlapping quantity threshold may be determined according to an actual association relationship, which is not limited here.

Preset associated behaviors may include preset behaviors such as meeting, traveling together, object handover, feeding, etc. between two first objects, such as the preset meeting behavior between two people, the preset person driving the preset The behavior of the vehicle, the behavior of the preset person walking with the preset cat, the behavior of the preset vehicle carrying the preset item, the behavior of non-real-time object handover between the preset two people, etc.; it can also include Behaviors such as meeting, gathering, walking, and object handover between at least two types of first objects with different attributes among at least two first objects, such as having a preset first identity type and a preset second identity type The meeting behavior between two types of first objects, the walking behavior of two types of first objects, people and vehicles, the handover behavior between couriers and recipients or senders, and the feeding between people and cats or dogs behavior etc. During implementation, those skilled in the art may determine a suitable first object and a suitable preset association behavior according to actual conditions, which are not limited here.

Step S204, in the case that there is a preset association behavior between the at least two first objects, determine at least one first object other than the at least two first objects that appears in the at least one spatio-temporal overlapping region Two objects, and a set of second trajectory points of each second object in the at least one spatio-temporal overlapping region.

Step S205, for each second object, if the number of track points in the second set of track points of the second object exceeds a threshold number of track points, determine that the second object is related to the at least two The first object has an association relationship.

Here, the above steps S204 to S205 respectively correspond to the steps S103 to S104 in the foregoing embodiments, and for implementation, reference may be made to the implementation manners of the foregoing steps S103 to S104.

In the embodiment of the present disclosure, when the number of spatio-temporal overlapping regions exceeds the second overlapping number threshold, it is determined that there is a preset association behavior between at least two first objects, and there is a preset association behavior between at least two first objects. In the case of an association behavior, the second object that has an association relationship with at least two first objects is identified, so that the accuracy of the identified second object that has an association relationship with at least two first objects can be improved, and then the Further improve the ability to analyze trajectory information.

In some embodiments, the at least two first objects include at least one first sub-object with a first attribute and at least one second sub-object with a second attribute, and the preset association behavior includes the first Object aggregation behavior between the child object and the second child object. The above step S203 may include:

Step S211, when the number of the spatiotemporal overlapping regions exceeds a second overlapping quantity threshold, respectively determine the number of first sub-objects and the number of second sub-objects appearing in the at least one spatiotemporal overlapping region.

Here, the first attribute and the second attribute may be any suitable same or related attributes.

The second overlap quantity threshold may be preset or default. During implementation, an appropriate second overlapping quantity threshold may be determined according to actual conditions, which is not limited here.

The object aggregation behavior refers to the aggregation behavior between two types of first objects with the first attribute and the second attribute, that is, the aggregation behavior between the first sub-objects and the second sub-objects.

Step S212, when the number of the first sub-object is greater than the first object quantity threshold and the second sub-object is greater than the second object quantity threshold, it is determined that the first sub-object and the second sub-object exist Object aggregation behavior between two child objects.

Here, both the first object quantity threshold and the second object quantity threshold can be preset or default. The first object quantity threshold and the second object quantity threshold may be the same or different. During implementation, the appropriate first object quantity threshold and the second object quantity threshold may be determined according to actual conditions, which are not limited here.

In the above embodiment, when there is an object aggregation behavior between the first sub-object and the second sub-object, the second object that has an association relationship with at least two first objects that have the object aggregation behavior can be identified, so that The ability to analyze trajectory information can be further improved.

An embodiment of the present disclosure provides a data processing method, which can be executed by a processor of a computer device. As shown in Figure 3, the method includes the following steps S301 to S305:

Step S301, obtaining a first track point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first track points The point set includes at least one track point; each track point has a time stamp.

Here, the time identifier of each track point may correspond to a time point or a time range or the like. During implementation, those skilled in the art may select an appropriate time identifier according to actual conditions, which is not limited here. For example, each track point may have a time identifier representing the time point at which the object to which the track point belongs appears at the corresponding spatial position. For another example, each track point may have a time identifier that characterizes the time range in which the object to which the track point belongs stays at the corresponding spatial position.

Step S302, spatially matching the trajectory points in the first trajectory point set of the at least two first objects to obtain at least one spatial overlapping region and at least two spatial overlapping regions in each spatial overlapping region track point.

Here, each spatial overlapping region may indicate that at least two first objects appear once at the same or similar spatial positions, that is, the trajectories of at least two first objects intersect or are similar in space once, wherein , each spatial overlapping region may correspond to at least one trajectory point of each of the at least two first objects, and each trajectory point corresponding to each spatial overlapping region may be a spatially overlapping trajectory point within the spatial overlapping region. By spatially matching each trajectory point in the first trajectory point set of one of the at least two first objects with each trajectory point in the first trajectory point set of the other first object, it is possible to The spatial overlapping area between the two first objects is obtained, and then at least one spatial overlapping area between the at least two first objects and at least two spatial overlapping track points in each spatial overlapping area can be obtained.

During implementation, any suitable method may be used to spatially match the track points in the first set of track points of at least two first objects to obtain at least one spatial overlapping area and at least two in each spatial overlapping area. The spatially overlapping track points are not limited in this embodiment of the present disclosure. For example, each first object in at least two first objects can have a spatial identifier, and each spatial identifier can represent a spatial position, and the first track point set of one first object in at least two first objects can be Each trajectory point in is compared with each trajectory point in the first trajectory point set of another first object, and two trajectories are determined when the spatial identifiers of the two trajectory points correspond to the same or similar spatial positions The points are matched in space, so that a spatial overlapping region corresponding to the two trajectory points can be obtained, and the two trajectory points are the spatially overlapping trajectory points in the spatial overlapping region.

Step S303, for each of the spatial overlapping areas, in the case that at least two spatial overlapping track points in the spatial overlapping area satisfy the preset time condition in time, based on the Time marking, determining a time overlapping area, and determining a spatio-temporal overlapping area based on the spatial overlapping area and the temporal overlapping area.

Here, the spatial overlapping region indicates that two first objects appear at the same or similar spatial positions, and the two first objects may or may not appear simultaneously, that is, the spatial overlapping region At least two spatially overlapping track points may or may not be correlated in time. Since the space-time overlapping area indicates that two first objects appeared in the same or similar space-time, therefore, at least two space-overlapping trajectory points in the space-time overlapping area satisfy the preset time condition in time , for the spatial overlapping area, determine a time overlapping area, and determine a space-time overlapping area based on the space overlapping area and the time overlapping area, wherein the at least two spatially overlapping trajectory points can be used as overlapping in the space-time overlapping area track point.

The preset time conditions may include, but are not limited to, that the time interval between two spatially overlapping trajectory points is less than a preset time interval threshold, and the duration of two spatially overlapping trajectory points staying together at the same or similar spatial position is longer than the preset time interval. duration threshold, etc. For example, each spatially overlapping track point can have a time mark representing the time point at which the object to which the track point belongs appears at the corresponding spatial position, and two spatially overlapping track points can be determined based on the time marks of the two spatially overlapping track points In terms of time interval, if the interval is smaller than a preset time interval threshold, it may be determined that at least two spatially overlapping track points in the spatially overlapping region satisfy a preset time condition in time. As another example, each spatially overlapping trajectory point can have a time identifier that characterizes the time range of the object to which the spatially overlapping trajectory point belongs stays at the corresponding spatial position, and the time range corresponding to the time identifier of the two spatially overlapping trajectory points can be The intersection between determines the length of time that two spatially overlapping trajectory points stay together at the same or similar spatial position. If the length of time is greater than the preset duration threshold, at least two spatially overlapping The track point satisfies a preset time condition in time.

The temporal overlapping region corresponding to each spatial overlapping region may be determined based on the time identifier of each spatial overlapping trajectory point within the spatial overlapping region. During implementation, a time overlapping area may be determined based on the time identifier of each spatially overlapping track point in the space overlapping area in an appropriate manner according to the actual situation, which is not limited here. For example, the time zone and/or time point corresponding to the time identifier of each spatially overlapping track point can be combined to obtain the time overlap zone; the time zone and/or corresponding to the time marker of each spatially overlapping track point can also be determined A minimum time value and a maximum time value in a time point, and a time region between the minimum time value and the maximum time value is determined as a time overlap region.

Step S304, determining at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping region, and each of the second objects in the at least one spatio-temporal overlapping region The second track point set of .

Step S305, for each second object, if the number of track points in the second set of track points of the second object exceeds a threshold number of track points, determine that the second object is related to the at least two The first object has an association relationship.

Here, the above steps S304 to S305 respectively correspond to the steps S103 to S104 in the foregoing embodiments, and for implementation, reference may be made to the implementation manners of the foregoing steps S103 to S104.

In some embodiments, a map including at least one spatial overlapping region may be displayed on the trajectory analysis interface, and at least one spatial overlapping trajectory point in the spatial overlapping region is displayed in each spatial overlapping region in the map, and each Each track point of a second object associated with the at least two first objects within the spatial overlapping area.

In the embodiment of the present disclosure, the trajectory points in the first trajectory point set of at least two first objects are spatially matched to obtain at least one spatial overlapping region and at least two spatially overlapping trajectories in each spatial overlapping region point, for each spatial overlapping area, when at least two spatially overlapping trajectory points in the spatial overlapping area meet the preset time condition in time, based on the time identifier of each spatially overlapping trajectory point, determine a time an overlapping area, and determine a spatio-temporal overlapping area based on the spatial overlapping area and the temporal overlapping area. This enables fast and accurate determination of at least one spatio-temporal overlap region.

In some embodiments, the at least two first objects include at least one first sub-object with a first attribute and at least one second sub-object with a second attribute, the first attribute being the same as the second attribute or Correlation, each track point has a spatial identifier. The above step S302 may include the following steps S311 to S313:

Step S311, determining each track point in the set of track points of each first sub-object with the first attribute as a track point to be matched.

The spatial identifier of each track point corresponds to a spatial location, which may be a location point or a location area, which is not limited here.

Step S312, from the set of track points of each second sub-object with the second attribute, determine a target track point that matches the spatial identifier of at least one track point to be matched.

Here, the situation that the spatial identifiers of two trajectory points match may include but not limited to that the spatial locations corresponding to the spatial identifiers of the two trajectory points are the same location point, the spatial locations corresponding to the spatial identifiers of the two trajectory points belong to the same location area, or two The distance between the spatial positions corresponding to the spatial identifiers of the trajectory points is less than one or more of the set distance thresholds and the like. During implementation, any suitable manner may be used to determine whether the spatial identifiers of two track points match according to actual conditions, which is not limited here.

Step S313, for each target track point, based on the spatial identification of the target track point and the spatial identification of at least one track point to be matched corresponding to the target track point, determine at least one spatial overlapping area, and combine the Both the target track point and the at least one to-be-matched track point are determined as spatially overlapping track points in the spatially overlapping area.

Here, for each target track point, the target track point and the track point to be matched corresponding to the target track point may correspond to a spatial overlapping area. During implementation, each target track point and the spatial overlapping area corresponding to the track point to be matched corresponding to the target track point may be determined in any suitable manner according to the actual situation, which is not limited here. For example, for a group of target track points matched by space identification and at least one track point to be matched, the space region and/or space point corresponding to the space identification of the target track point can be used, and the space identification of each track point to be matched corresponds to The union of the spatial region and/or spatial point is determined as the spatial overlapping region; the spatial region and/or spatial point corresponding to the spatial identification of the target trajectory point, and the corresponding spatial identification of each trajectory point to be matched Intersections between spatial regions and/or spatial points are determined as spatial overlapping regions.

In some embodiments, it is also possible to deduplicate or aggregate the determined at least one spatio-temporal overlapping region to obtain the final at least one spatio-temporal overlapping region. For example, multiple spatio-temporal overlapping regions that are adjacent in time or space can be aggregated into a spatio-temporal overlapping region, or multiple spatio-temporal overlapping regions that are the same in time or space can be deduplicated to obtain a spatio-temporal overlapping region.

In some embodiments, when at least two spatially overlapping trajectory points in the spatially overlapping area described in the above step S303 meet the preset time condition in time, based on each of the spatially overlapping trajectory points The time stamps, identifying a temporal overlap region, may include:

Step S321, based on the time marks of at least two spatially overlapping trajectory points in the spatially overlapping region, determine the time interval between every two spatially overlapping trajectory points.

Here, in some implementations, the time identifier of each spatially overlapping track point may correspond to a time point, and the time interval between two spatially overlapping track points may be the time point corresponding to the time markers of these two spatially overlapping track points difference. In some implementations, the time identifier of each spatially overlapping track point may correspond to a time range, and the time interval between two spatially overlapping track points may be between the time ranges corresponding to the time markers of the two spatially overlapping track points interval. During implementation, those skilled in the art may determine the time interval between every two spatially overlapping trajectory points in each spatially overlapping area in an appropriate manner according to actual conditions, which is not limited here.

Step S322, in the case where the minimum time interval between spatially overlapping track points belonging to different objects in the spatially overlapping area is less than the overlapping time threshold, based on the time identifier of each of the spatially overlapping track points, determine a temporally overlapping area .

Here, for each spatial overlapping region, the time identifier of each spatially overlapping trajectory point in the spatial overlapping region can be determined, based on the time identifier of each spatially overlapping trajectory point, it can be determined The minimum time interval is the minimum time interval between spatially overlapping trajectory points belonging to different objects. If the minimum time interval is less than the overlapping time threshold, it can be based on each The time stamps of the spatially overlapping trajectory points define a temporally overlapping region.

The overlap time threshold can be preset or default. During implementation, an appropriate overlapping time threshold may be determined according to actual conditions, which is not limited here.

In some embodiments, if there is a preset association behavior between at least two first objects, an appropriate overlapping time threshold may be determined according to the preset association behavior between the at least two first objects. For example, for preset association behaviors that require real-time interaction (such as meeting, peering, real-time object handover behavior, real-time animal feeding behavior, etc.), a smaller overlapping time threshold can be set, such as two for preset association behaviors. In the case of a meeting behavior between preset objects, two objects need to appear at the same or similar spatial position at the same time, and a small overlapping time threshold can be set, such as 5 seconds, 10 seconds, 15 seconds, etc. As another example, for preset association behaviors that do not require real-time interaction (such as non-real-time object handover behavior, non-real-time animal feeding behavior, etc.), a larger overlapping time threshold can be set, such as two preset association behaviors. In the case of non-real-time object handover behavior between objects, two objects may appear at the same or similar spatial positions at the same time, or they may not appear at the same or similar spatial positions at the same time, and a larger overlap time can be set Threshold value, such as 12 hours, 1 day, 3 days, etc.

In the above-mentioned embodiments, the time overlapping area between at least one spatially overlapping track point in each spatially overlapping area can be accurately determined, and then at least one first time point that appears at the same or similar spatial position at adjacent times can be accurately determined. The spatio-temporal overlapping area between one object further improves the accuracy of identifying the association relationship between the second object and at least two first objects.

In some embodiments, when each trajectory point is determined based on the collected image data, the spatial identification includes at least one of the following: the identification of the image acquisition device that collects the image data corresponding to the trajectory point, the acquisition trajectory The attribution area of the image acquisition device of the image data corresponding to the point; the time identifier includes at least one of the following: the acquisition date of the image data corresponding to the trajectory point, and the acquisition time of the image data corresponding to the trajectory point. Here, the image data may be image data including a part of the object captured by the image acquisition device, or may be image data including the entire object. For example, for a person, the image data can be a face image or a human body image collected by a camera; for a vehicle, the image data can be a license plate image or a vehicle image collected by a camera, etc. The image acquisition device may include but not limited to one or more of a color camera, an infrared camera, a grayscale camera, a video camera, and the like. Each image acquisition device may have a unique identifier or correspond to an attribution area.

In the above-mentioned embodiment, the trajectory points of at least two first objects and the second object can be determined based on a large amount of image data collected by image acquisition devices arranged at different spatial positions, so that the obtained trajectory points can be improved in terms of time and space. The coverage rate can further improve the accuracy of identifying the association relationship between the second object and at least two first objects.

In some embodiments, in the case where each track point is determined based on the collected positioning data, the spatial identification includes the attribution area of the positioning position corresponding to the track point; the time identification includes at least one of the following: track The collection date of the positioning data corresponding to the point, and the collection time of the positioning data corresponding to the track point. Here, in some implementations, the positioning data may include the positioning position of the object collected using any suitable positioning system. During implementation, the positioning system used may include but not limited to one or more of the Global Positioning System (Global Positioning System, GPS), Beidou satellite navigation system, Galileo satellite navigation system, and global navigation satellite system. In some implementations, the snapshots or features of the object can be collected by image capture devices installed in different spatial regions, and the data structures of the snapshots and features can include point information corresponding to the identification of the image capture device. The point information identified by the image acquisition device may include longitude and latitude information, area codes, etc. of the spatial position corresponding to the snapshot or the snapshot feature. In this way, based on the point information corresponding to the image acquisition device identification in the snapshot image of the object or the data structure of the snapshot feature, the positioning position of the object can be determined, so that the positioning of the object can be realized and the positioning data of the object can be obtained.

In the above-mentioned embodiment, the trajectory points of at least two first objects and the second object can be determined based on a large amount of positioning data collected by the positioning system, so that the coverage rate of the obtained trajectory points in time and space can be further improved, and further can be further improved. The accuracy rate of identifying the association relationship between the second object and at least two first objects.

An embodiment of the present disclosure provides a data processing method, which can be executed by a processor of a computer device. As shown in Figure 4, the method includes the following steps S401 to S405:

Step S401, based on at least one attribute, determine the at least two first objects from a set of candidate objects; wherein each of the first objects has any attribute in the at least one attribute.

Here, the set of candidate objects may be any suitable set containing at least two objects. At least one attribute includes one attribute or two or more related attributes, which may be preset or defaulted by the system, which is not limited here. At least two first objects determined from the candidate object set respectively have any attribute of the at least one attribute, that is, at least two first objects determined from the candidate object set have the same or related attributes. During implementation, those skilled in the art may determine at least two first objects from the candidate object set in an appropriate manner according to actual conditions, which is not limited here. For example, each object in the candidate object set can have an attribute identifier, and each attribute identifier can represent an attribute, and by comparing the attribute identifier of each object with each attribute in the at least one attribute, It is determined whether the object is a first object having any of the at least one attribute.

Step S402, based on the set space-time range, obtain the first track point set of each of the at least two first objects; wherein, in the first track point set of each of the first objects At least one trajectory point of the first object within the space-time range is included.

Here, the spatio-temporal range may include a temporal range or a spatial range. The time range may be a preset fixed range, or a range dynamically set by the system based on the current time, which is not limited here. For example, the pre-set time range may be from June 1, 2021 to June 3, 2021. As another example, assuming that the current time is 10:30 on June 5, 2021, the set time range can be the time range of the last 3 days determined by the system based on the current time, that is, 10:30 on June 2, 2021 Minutes until 10:30 on June 5, 2021. During implementation, the value precision of the time range may be accurate to any one of month, day, hour, minute, second, etc. according to actual conditions. The spatial range may be a preset fixed range, or a range dynamically set by the system based on the current spatial position, which is not limited here. For example, the preset spatial range may be one or more preset fixed spatial regions. As another example, assuming that the current spatial position is the current positioning address of the system, the set spatial range can be the spatial area where the positioning address is located, or a spatial range within a preset distance range near the positioning address, such as the positioning The spatial range within 500 meters, 3 kilometers or 5 kilometers near the address.

Based on the set time range and space range, at least one trajectory point of each of the at least two first objects within the time-space range can be determined, so that a first set of trajectory points for each first object can be obtained. During implementation, at least one trajectory point of each of the at least two first objects within the space-time range can be obtained by querying the database or pulling data from the cloud or other services, and obtaining each A first track point set of the first object, which is not limited here.

Step S403, performing space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area.

Step S404, determining at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and each of the second objects in the at least one spatio-temporal overlapping area The second track point set of .

Step S405, for each second object, if the number of track points in the second set of track points of the second object exceeds the threshold number of track points, determine the relationship between the second object and the at least two The first object has an association relationship.

Here, the above step S403 to step S405 correspond to the above step S102 to step S104, and the implementation manner of the above step S102 to step S104 can be referred to for implementation.

In the embodiment of the present disclosure, based on at least one attribute, at least two first objects are determined from the set of candidate objects, wherein each first object has any attribute in the at least one attribute; and based on the set space-time range , acquiring a set of track points of each of the at least two first objects; wherein, the set of track points of each first object includes at least one track point of the first object within the space-time range. In this way, the trajectory information of at least two first objects with the same or related attributes within the set space-time range can be obtained simply and quickly, so that the distance between the at least two first objects within the space-time range can be identified. The second object that has an association relationship.

In some embodiments, the above step S402 may include:

Step S411, slice the space-time range to obtain multiple space-time slices;

Here, each space-time slice may include a specific time interval and a specific spatial region. In some implementations, the space-time range can be equally sliced in the time dimension and/or space dimension, for example, using a set time step to divide the space-time range into multiple space-time slices of equal duration in the time dimension, or The space-time range is divided into a plurality of space-time slices with equal space areas in the space dimension by using a set space step. In some implementations, the spatio-temporal range can be unequally sliced to obtain multiple spatio-temporal slices with different time lengths and/or different spatial areas. During implementation, those skilled in the art may use an appropriate manner to segment the space-time range according to actual conditions, which is not limited here.

Step S412, in a distributed manner, obtain at least one trajectory point of each of the first objects in each of the at least two first objects in each of the space-time slices in parallel, and obtain A first set of track points of the object.

Here, at least one trajectory point of each first object in each space-time slice of the at least two first objects may be obtained by executing multiple distributed tasks in parallel.

During implementation, at least one distributed task for acquiring trajectory points can be determined in any suitable manner according to the actual situation. By executing each distributed task, it is possible to obtain at least two first objects in each At least one trajectory point in a space-time slice, and then a set of trajectory points of each first object in the at least two first objects can be obtained. Each distributed task can be executed based on any suitable distributed data processing engine such as Spark or Flink. Each distributed task can acquire at least one trajectory point of each first object in a space-time slice of at least two first objects, or can only acquire at least one trajectory point of a first object in a space-time slice, where Not limited.

In the above embodiment, the space-time range is segmented to obtain multiple space-time slices, and at least one trajectory of each first object in each space-time slice of at least two first objects is obtained in parallel in a distributed manner points to obtain a track point set of each of the at least two first objects. In this way, in a distributed manner, the efficiency of obtaining the trajectory point set of each first object in the at least two first objects can be further improved, and the tracking of the first object that has an association relationship with the at least two first objects can be further improved. The efficiency of two-object recognition.

An embodiment of the present disclosure provides a data processing method, which can be executed by a processor of a computer device. As shown in Figure 5, the method includes the following steps S501 to S506:

Step S501, obtaining a first track point set of each of the first objects in at least two first objects; the at least two first objects have the same or related attributes, and each of the first track point sets Include at least one track point;

Step S502, performing space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

Step S503, determining at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and each of the second objects in the at least one spatio-temporal overlapping area The second track point set of ;

Step S504, for each second object, if the number of track points in the second set of track points of the second object exceeds a threshold number of track points, determine that the second object is related to the at least two The first object has an association relationship.

Here, the above-mentioned steps S501 to S504 correspond to the above-mentioned steps S101 to S104 respectively, and for implementation, reference may be made to the implementation manners of the above-mentioned steps S101 to S104.

Step S505, for each second object, when it is determined that there is an association relationship between the second object and the at least two first objects, based on the second track point set of the second object The number of track points determines the level of association between the second object and the at least two first objects.

Here, the association level may be any suitable level information that characterizes the degree of association between the second object and at least two first objects. During implementation, the association level between the second object and at least two first objects may be determined in an appropriate manner according to actual conditions, which is not limited here.

In some implementations, the corresponding relationship between the number of appropriate track points and the association level can be determined in advance according to the actual application scenario, so that the number of track points in the second set of track points of the second object can be determined. The level of association between the corresponding second object and at least two first objects.

Step S506, generating and sending prompt information based on the association level between each of the second objects and the at least two first objects.

Here, in some implementation manners, for each second object, based on the level of association between the second object and at least two first objects, a piece of prompt information may be generated and sent. Wherein, the prompt information may include any suitable information for prompting the association relationship between the second object and at least two first objects, which is not limited here.

In some implementations, based on the association level between each second object and at least two first objects, a piece of prompt information may be generated and sent. Wherein, the prompt information may include any suitable information for prompting the relationship between each second object and at least two first objects, which is not limited here.

In the embodiment of the present disclosure, in the case that there is an association relationship between the second object and at least two objects, the corresponding association level may be determined according to the number of track points in the second track point set of the second object, and based on The association level sends prompt information to remind the association relationship.

The following describes the application of the data processing method provided by the embodiments of the present disclosure in actual scenarios, taking the scenario of identifying a second object that has an association relationship with two preset types of first objects based on trajectory information as an example.

An embodiment of the present disclosure provides a data processing method, which can help analyze and compare the preset two types of first objects by counting the image data of the preset two types of first objects collected by cameras installed at different spatial locations within a preset time range. A second object that has an association relationship between one object. The method is executed by a computer device. As shown in FIG. 6A, the method includes the following steps S601 to S604:

Step S601, performing space-time collision on track points in a first set of track points of at least two first objects to obtain at least one space-time overlapping area.

Here, the preset two types of first objects may include preset first types of first objects and second types of first objects, wherein the first type and the second type may be configurable. The at least two first objects may include at least one first object of the first type and at least one first object of the second type after identification. For the temporal-spatial matching of the trajectory points of the identified first type of first object and the second type of first object, at least one spatio-temporal overlap between at least one first object and at least one first object can be determined area.

In some implementations, each trajectory point of the at least two first objects within a preset time range may be acquired, so as to obtain a first set of trajectory points of the at least two first objects. The preset time range may be configurable. For example, the preset time range may be a time period before the current time, and the default preset time range is within one month before the current time.

In some implementations, within n seconds, two first objects whose image data is captured by the same camera can be considered to appear at the same time, that is, there is a space-time overlapping region between the two first objects, where n is a set positive An integer, which may correspond to the overlap time threshold in the foregoing embodiments. The overlap time threshold may be configurable, and the default overlap time threshold may be 10 seconds.

For example, the first object of the first type includes object A, object B, and object C, the first object of the second type includes object D, object E, and object F, and each track point of object A is used as a track point to be matched, Compare each track point to be matched with each track point of object D, object E, and object F, and find out that the capture device ID corresponding to each track point of object A is the same and the capture time interval is within the overlapping time threshold target track points, and the first object to which each target track point belongs, and so on, to find target track points that match at least one track point to be matched in object B and object C respectively, wherein each group of matching The trajectory points to be matched and the target trajectory points can correspond to a space-time overlapping region; in addition, the total number of space-time overlapping regions can also be counted, and the total number of first objects corresponding to all the trajectory points to be matched and the target trajectory points that match each other; for example : The trajectory point a1 of object A matches the trajectory point d3 of object D, the trajectory point a2 of object A matches the trajectory point e5 of object E, the trajectory point b3 of object B matches the trajectory point e3 of object E, and the trajectory point of object C The point c4 matches the trajectory point f6 of the object F, so that a space-time overlap can be determined based on the trajectory point a1 and the trajectory point d3, the trajectory point a2 and the trajectory point e5, the trajectory point b3 and the trajectory point e3, and the trajectory point c4 and the trajectory point f6 area, and the total number of spatio-temporal overlapping areas is 4, and the first object corresponding to all the track points to be matched and the target track point includes object A, object D, object E, object B, object C, and object F, that is, the corresponding The total number of first objects is 6.

In some implementations, multiple warning levels can be set in advance for the number of spatiotemporal overlapping regions, and if the number of collided spatiotemporal overlapping regions matches the target warning level, an early warning prompt corresponding to the target warning level is output. For example, the warning level can include primary warning, intermediate warning and advanced warning. Among them, the warning levels of primary warning, medium warning and advanced warning increase in turn. Each warning level corresponds to a configurable quantity threshold. By default, the primary warning can be corresponding to Set the number threshold of 100, set the number threshold corresponding to the intermediate warning to 1000, and set the number threshold corresponding to the advanced warning to 5000. When the number of space-time overlapping areas in the collision is greater than or equal to 100 and less than 1000, you can Determine the early warning level of the target as primary warning; if the number of space-time overlapping areas produced by the collision is greater than or equal to 1000 and less than 5000, the early warning level of the target can be determined as intermediate warning; when the number of space-time overlapping areas produced by the collision is greater than or equal to 5000 In the case of , it can be determined that the target warning level is advanced warning.

Step S602, when the number of spatio-temporal overlapping regions between the at least two first objects exceeds a second overlapping number threshold, determine that meeting behavior occurs between at least two first objects of two preset types of first objects.

Step S603, in the case that the at least two first objects meet, determine at least one second object other than the at least two first objects appearing in at least one spatio-temporal overlapping area, and each second object A second track point set of the object in the at least one spatio-temporal overlapping region.

Step S604, for each second object, if the number of track points in the second track point set of the second object exceeds the threshold number of track points, determine that the second object is associated with the at least two first objects relation.

In some embodiments, the total number of space-time overlapping areas, the total number of overlapping trajectory points in each space-time overlapping area, and the first object to which each overlapping trajectory point belongs can be counted; based on the object identity of each first object, the deduplication The subsequent first object list and the number of first objects in the first object list; counting the number of overlapping trajectory points corresponding to each object in the first object list.

In some embodiments, the total number of objects of the first type of first objects, the total number of objects of the second type of first objects, and the trajectory of each type of first objects within a preset time range can be displayed on the trajectory analysis interface The number of points, the number of first objects appearing within the at least one spatiotemporal overlapping region, the number of overlapping trajectory points within the at least one spatiotemporal overlapping region, and each overlapping trajectory point.

In some embodiments, as shown in FIG. 6B , a map 610 including at least one spatio-temporal overlapping region 611 can be displayed on the trajectory analysis interface 600, and each spatio-temporal overlapping region 611 in the map can be displayed within the spatio-temporal overlapping region. At least one overlapping trajectory point 621 of , and each trajectory point 622 of each second object associated with at least two first objects within the spatial overlapping area.

In the embodiment of the present disclosure, by counting the image data of the preset two types of first objects collected by the cameras set at different spatial positions within the preset time range, it can help to analyze the relationship between the preset two types of first objects. There is a second object with an association relationship, so as to support the effective use of trajectory information.

FIG. 7 is a schematic diagram of the composition and structure of a data processing device provided by an embodiment of the present disclosure. As shown in FIG. 7 , the data processing device 700 includes: an acquisition part 710 , a collision part 720 , a first determination part 730 and a second determination part 740 ,in:

The obtaining part 710 is configured to obtain a first trajectory point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first objects The first track point set includes at least one track point;

The collision part 720 is configured to perform space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

The first determining part 730 is configured to determine at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and each of the second objects in the a second set of trajectory points within at least one spatio-temporal overlapping region;

The second determining part 740 is configured to, for each of the second objects, determine the second object when the number of track points in the second set of track points of the second object exceeds the threshold of the number of track points There is an association relationship with the at least two first objects.

In some embodiments, the second determining part is further configured to: determine the second track point when the number of track points in the second set of track points of the second object exceeds a threshold number of track points The target spatio-temporal overlapping area matched by each track point in the set; when the number of the target space-time overlapping area matched by the track point in the second set of track points exceeds the first overlap quantity threshold, determine that the second object and the set There is an association relationship between the at least two first objects.

In some embodiments, the apparatus further includes: a third determining part configured to determine that there is an existence between the at least two first objects when the number of the spatio-temporal overlapping regions exceeds a second overlapping number threshold Preset association behavior; the first determining part is further configured to: in the case that there is a preset association behavior between the at least two first objects, determine all but at least one second object other than the at least two first objects, and a second trajectory point set of each second object within the at least one space-time overlapping region.

In some embodiments, the at least two first objects include at least one first sub-object with a first attribute and at least one second sub-object with a second attribute, and the preset association behavior includes the first The object aggregation behavior between the sub-object and the second sub-object; the third determining part is further configured to: when the number of the spatio-temporal overlapping regions exceeds a second overlapping number threshold, respectively determine the The number of first sub-objects and the number of second sub-objects appearing in at least one spatio-temporal overlapping region; the number of the first sub-objects is greater than the first object number threshold, and the number of the second sub-objects is greater than the second In the case of the object number threshold, it is determined that there is an object aggregation behavior between the first sub-object and the second sub-object.

In some embodiments, each of the trajectory points has a time stamp; the collision part is further configured to: spatially perform Matching, obtaining at least one spatial overlapping region and at least two spatial overlapping trajectory points in each of the spatial overlapping regions; for each of the spatial overlapping regions, at least two spatial overlapping trajectory points in the spatial overlapping region In the case that the preset time condition is satisfied in time, based on the time mark of each of the spatially overlapping trajectory points, a temporal overlapping region is determined, and a temporal-spatial overlapping region is determined based on the spatial overlapping region and the temporal overlapping region .

In some embodiments, the at least two first objects include at least one first sub-object with a first attribute and at least one second sub-object with a second attribute, the first attribute being the same as the second attribute or Correlation, each of the track points has a spatial identifier; the collision part is further configured to: determine each track point in the set of track points of each of the first sub-objects with the first attribute to be matched track point; from the track point set of each second sub-object with the second attribute, determine a target track point that matches the spatial identifier of at least one track point to be matched; for each target track point , based on the spatial identification of the target track point and the spatial identification of at least one track point to be matched corresponding to the target track point, determine at least one spatial overlapping area, and combine the target track point and the at least one track point to be matched The trajectory points are all determined as spatially overlapping trajectory points within the spatially overlapping region.

In some embodiments, the collision part is further configured to: determine the time interval between every two spatially overlapping trajectory points based on the time identification of at least two spatially overlapping trajectory points in the spatially overlapping region; If the minimum time interval between spatially overlapping trajectory points belonging to different objects in the spatially overlapping region is less than an overlapping time threshold, a temporally overlapping region is determined based on the time identifier of each spatially overlapping trajectory point.

In some embodiments, when each trajectory point is determined based on the collected image data, the spatial identification includes at least one of the following: the identification of the image acquisition device that collects the image data corresponding to the trajectory point, the acquisition trajectory The attribution area of the image acquisition device of the image data corresponding to the point; the time identifier includes at least one of the following: the acquisition date of the image data corresponding to the trajectory point, and the acquisition time of the image data corresponding to the trajectory point.

In some embodiments, in the case where each track point is determined based on the collected positioning data, the spatial identification includes the attribution area of the positioning position corresponding to the track point; the time identification includes at least one of the following: track The collection date of the positioning data corresponding to the point, and the collection time of the positioning data corresponding to the track point.

In some embodiments, the acquisition part is further configured to: determine the at least two first objects from the set of candidate objects based on at least one attribute; wherein each of the first objects has the at least one any one of the attributes; based on the set space-time range, obtain the first set of trajectory points of each of the first objects in the at least two first objects; wherein, the first track point set of each of the first objects A track point set includes at least one track point of the first object within the space-time range.

In some embodiments, the apparatus further includes: a fourth determining part configured to, for each of the second objects, determine that there is an association relationship between the second object and the at least two first objects In the case of , based on the number of track points in the second track point set of the second object, determine the association level between the second object and the at least two first objects; the sending part is configured to be based on For each level of association between the second object and the at least two first objects, prompt information is generated and sent.

The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiments of the present disclosure, please refer to the description of the method embodiments of the present disclosure for understanding.

It should be noted that, in the embodiments of the present disclosure and other embodiments, a "part" may be a part of a circuit, a part of a processor, a part of a program or software, etc., of course, it may also be a unit, and it may also be a module or a non-module of.

In the embodiment of the present disclosure, if the above-mentioned data processing method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the embodiments of the present disclosure or the part that contributes to the related technology can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk. As such, embodiments of the present disclosure are not limited to any specific combination of hardware and software.

An embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the above method when executing the program.

An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented. The computer readable storage medium may be transitory or non-transitory.

An embodiment of the present disclosure provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, a part or part of the above-mentioned method is implemented. All steps. The computer program product can be realized by hardware, software or a combination thereof. In some embodiments, the computer program product is embodied as a computer storage medium, and in other embodiments, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.

It should be pointed out here that: the above descriptions of the storage medium, computer program product, and device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to those of the method embodiments. For technical details not disclosed in the storage medium, computer program product, and device embodiments of the present disclosure, please refer to the description of the method embodiments of the present disclosure for understanding.

It should be noted that FIG. 8 is a schematic diagram of a hardware entity of a computer device in an embodiment of the present disclosure. As shown in FIG. 8, the hardware entity of the computer device 800 includes: a processor 801, a communication interface 802, and a memory 803, wherein: The processor 801 usually controls the overall operation of the computer device 800; the communication interface 802 can enable the computer device to communicate with other terminals or servers through the network; the memory 803 is configured to store instructions and applications executable by the processor 801, and can also cache 801 and the data to be processed or processed by each module in the computer device 800 (for example, image data, audio data, voice communication data and video communication data), can be passed through flash memory (FLASH) or random access memory (Random Access Memory, RAM) accomplish. Data transmission may be performed between the processor 801 , the communication interface 802 and the memory 803 through the bus 804 .

It should be understood that reference throughout the specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic related to the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present disclosure, the sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, rather than by the embodiments of the present disclosure. The implementation process constitutes any limitation. The serial numbers of the above-mentioned embodiments of the present disclosure are for description only, and do not represent the advantages and disadvantages of the embodiments.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms of.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may be used as a single unit, or two or more units may be integrated into one unit; the above-mentioned integration The unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

Those of ordinary skill in the art can understand that all or part of the steps to realize the above method embodiments can be completed by hardware related to program instructions, and the aforementioned programs can be stored in computer-readable storage media. When the program is executed, the execution includes: The steps of the foregoing method embodiments; and the foregoing storage media include: removable storage devices, read-only memory (Read Only Memory, ROM), magnetic disks or optical disks and other media that can store program codes.

Alternatively, if the above-mentioned integrated units of the present disclosure are realized in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present disclosure or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes various media capable of storing program codes such as removable storage devices, ROMs, magnetic disks or optical disks.

The above is only the embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope of the present disclosure, and should within the protection scope of the present disclosure.

Industrial Applicability

The embodiment of the present disclosure discloses a data processing method, device, device, storage medium, and program product, wherein the method includes: obtaining a first track point set of each first object in at least two first objects; at least two The first objects have the same or related attributes, and each first track point set includes at least one track point; the track points in the first track point set of at least two first objects are subjected to space-time collision to obtain at least one Spatio-temporal overlapping regions; determining at least one second object other than at least two first objects appearing in at least one spatio-temporal overlapping region, and a second trajectory point set of each second object in at least one spatio-temporal overlapping region; For each second object, if the number of track points in the second set of track points of the second object exceeds the threshold number of track points, it is determined that the second object has an association relationship with at least two first objects. According to the embodiment of the present disclosure, it is possible to determine the second object that has an association relationship with at least two first objects that have the same or related attributes, so that the ability to analyze the trajectory information can be improved, and the value in the trajectory information can be more fully utilized. , and can make more effective use of the resources invested in the acquisition of massive trajectory information.

Claims

A data processing method, the method comprising:

Obtain a first track point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the first track point sets including at least one track point;

performing space-time collision on track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

determining at least one second object other than the at least two first objects occurring within the at least one spatio-temporal overlapping region, and the second object of each of the second objects within the at least one spatio-temporal overlapping region set of track points;

For each of the second objects, when the number of trajectory points in the second trajectory point set of the second object exceeds the threshold of the number of trajectory points, determine that the second object and the at least two first objects There is an association.
The method according to claim 1, wherein when the number of track points in the second set of track points of the second object exceeds a threshold number of track points, it is determined that the second object and the at least two There is an associated relationship with the first object, including:

When the number of track points in the second set of track points of the second object exceeds a threshold number of track points, determine a target space-time overlapping area matched by each track point in the second set of track points;

In a case where the number of target spatio-temporal overlapping regions matched by track points in the second set of track points exceeds a first overlap quantity threshold, it is determined that the second object has an association relationship with the at least two first objects.
The method according to claim 1 or 2, said method further comprising:

When the number of the spatio-temporal overlapping regions exceeds a second overlapping number threshold, it is determined that there is a preset association behavior between the at least two first objects;

The determining of at least one second object other than the at least two first objects occurring within the at least one spatio-temporal overlapping region, and each of the second objects within the at least one spatio-temporal overlapping region The second trajectory point set includes:

In the case that there is a preset association behavior between the at least two first objects, determining at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and a set of second trajectory points of each second object within the at least one spatio-temporal overlapping region.
The method according to claim 3, wherein the at least two first objects include at least one first sub-object with a first attribute and at least one second sub-object with a second attribute, and the preset association behavior including an object aggregation behavior between the first sub-object and the second sub-object;

The determining that there is a preset association behavior between the at least two first objects when the number of the spatio-temporal overlapping regions exceeds a second overlapping number threshold includes:

When the number of the spatiotemporal overlapping regions exceeds a second overlapping quantity threshold, determining the number of first sub-objects and the number of second sub-objects appearing in the at least one spatiotemporal overlapping region;

In a case where the number of the first sub-object is greater than a first object number threshold and the number of the second sub-object is greater than a second object number threshold, determining that the first sub-object and the second sub-object exist Object aggregation behavior between.
The method according to any one of claims 1 to 4, wherein each said trajectory point has a time stamp;

The performing space-time collision on the trajectory points in the first trajectory point set of the at least two first objects to obtain at least one space-time overlapping area includes:

spatially matching the trajectory points in the first trajectory point set of the at least two first objects to obtain at least one spatially overlapping region and at least two spatially overlapping trajectory points in each of the spatially overlapping regions;

For each of the spatially overlapping areas, when at least two spatially overlapping trajectory points in the spatially overlapping area satisfy a preset time condition in time, based on the time identifier of each of the spatially overlapping trajectory points, A temporal overlapping area is determined, and a spatio-temporal overlapping area is determined based on the spatial overlapping area and the temporal overlapping area.
The method according to claim 5, wherein said at least two first objects comprise at least one first sub-object having a first attribute and at least one second sub-object having a second attribute, said first attribute being identical to The second attributes are the same or related, and each of the track points has a spatial identifier;

The trajectory points in the first trajectory point set of the at least two first objects are spatially matched to obtain at least one spatial overlapping area and at least two spatially overlapping trajectories in each of the spatial overlapping areas points, including:

determining each track point in the set of track points of each first sub-object with the first attribute as a track point to be matched;

From the set of track points of each second sub-object with the second attribute, determine a target track point that matches the spatial identifier of at least one track point to be matched;

For each target track point, based on the spatial identification of the target track point and the spatial identification of at least one track point to be matched corresponding to the target track point, determine at least one spatial overlapping area, and set the target track point Both the point and the at least one track point to be matched are determined as spatially overlapping track points in the spatially overlapping area.
The method according to claim 6, wherein, when the at least two spatially overlapping trajectory points in the spatially overlapping area satisfy a preset time condition in time, based on each of the spatially overlapping trajectory points The time stamp, determine a time overlap area, including:

Determining a time interval between every two spatially overlapping trajectory points based on the time stamps of at least two spatially overlapping trajectory points within the spatially overlapping region;

In a case where the minimum time interval between spatially overlapping track points belonging to different objects within the spatially overlapping area is less than an overlapping time threshold, a temporally overlapping area is determined based on the time stamp of each of the spatially overlapping track points.
The method according to claim 7, wherein,

In the case where each track point is determined based on the collected image data, the spatial identification includes at least one of the following: the identification of the image acquisition device that collects the image data corresponding to the track point, the image data corresponding to the collected track point The belonging area of the image acquisition device; the time identifier includes at least one of the following: the acquisition date of the image data corresponding to the trajectory point, and the acquisition time of the image data corresponding to the trajectory point;

In the case where each track point is determined based on the collected positioning data, the spatial identification includes the attribution area of the positioning position corresponding to the track point; the time identification includes at least one of the following: the positioning data corresponding to the track point The collection date and the collection time of the positioning data corresponding to the track point.
The method according to any one of claims 1 to 8, wherein said acquiring the first track point set of each of the at least two first objects comprises:

Determining the at least two first objects from a set of candidate objects based on at least one attribute; wherein each of the first objects has any one of the at least one attribute;

Based on the set space-time range, obtain the first track point set of each of the at least two first objects; wherein, the first track point set of each of the first objects includes the At least one trajectory point of the first object within the space-time range.
The method according to any one of claims 1 to 9, further comprising:

For each of the second objects, when it is determined that there is an association relationship between the second object and the at least two first objects, based on the track points in the second track point set of the second object quantity, determining a level of association between the second object and the at least two first objects;

Based on the association level between each of the second objects and the at least two first objects, prompt information is generated and sent.
A data processing device, comprising:

The acquiring part is configured to acquire a first trajectory point set of each of the first objects in at least two first objects; wherein, the at least two first objects have the same or related attributes, and each of the The first track point set includes at least one track point;

The collision part is configured to perform space-time collision on the track points in the first set of track points of the at least two first objects to obtain at least one space-time overlapping area;

The first determining part is configured to determine at least one second object other than the at least two first objects appearing in the at least one spatio-temporal overlapping area, and each of the second objects in the at least a second set of trajectory points within a spatio-temporal overlapping region;

The second determining part is configured to, for each of the second objects, determine that the second object is related to There is an association relationship between the at least two first objects.
A computer device, comprising a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the method of any one of claims 1 to 10 when executing the program .
A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method of any one of claims 1 to 10 are implemented.
A computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, it realizes any one of claims 1 to 10 steps in the method.