A trajectory reduction method and system based on face, vehicle and mobile phone information

Abstract

The present invention belongs to the technical field of trajectory integration, and provides a trajectory reduction method and system based on face, vehicle and mobile phone information. According to the point relationship and trajectory time relationship of trajectory points in a face trajectory list, a vehicle trajectory list and a mobile phone trajectory list, the weight value of one item among face, vehicle and mobile phone and the other two items is calculated; then, the trajectory lists of the same entity and different entity types are sorted according to the weight value, and reduction is performed on this basis, so that the trajectories of the face, vehicle and mobile phone can form a trajectory list, and the trajectory list has integrity and rationality. The trajectory list formed after reduction can form a correct trajectory according to a normal lifestyle of a person.

Description

Technical Field

[0001] The present invention belongs to the technical field of trajectory integration, and in particular relates to a trajectory reduction method and system based on face, vehicle and mobile phone information. Background Art

[0002] When integrating pedestrian trajectories, the existing technology still integrates the trajectories of each entity separately. For example, the face trajectory can only query the trajectory of the face.

[0003] The inventors found that a person may take a vehicle or walk alone in a day, and the International Mobile Subscriber Identity (IMSI) and International Mobile Equipment Identity (IMEI) of his / her mobile phone may also be collected; the prior art does not have an effective method to reduce the multiple and multiple trajectories of faces, vehicles and mobile phones collected by various types of front-end devices, and cannot form the entire trajectory according to the person's life form. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a trajectory reduction method and system based on face, vehicle and mobile phone information. The present invention can form a trajectory list of face, vehicle and mobile phone trajectories, and the trajectory list is complete and reasonable; it can form a correct trajectory according to a person's normal lifestyle.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a trajectory reduction method based on face, vehicle and mobile phone information, comprising:

[0007] Obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data;

[0008] Based on the acquired pedestrian face data, vehicle data and mobile phone data, a face track list, a vehicle track list and a mobile phone track list are determined respectively;

[0009] According to the positional relationship and time relationship of the track points in the face track list, vehicle track list and mobile phone track list; calculate the weight value of one item among face, vehicle and mobile phone and the other two items;

[0010] Determine whether the two trajectory lists belong to the same entity relationship based on the weight value; if they belong to the same entity relationship, sort the entities based on the weight value; if they do not belong to the same entity relationship, sort the trajectory lists of different entity types based on the mean value of all entities of the entity type;

[0011] Perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

[0012] Furthermore, the acquired facial data, vehicle data of the vehicle being ridden, and mobile phone data include at least the identification number of the collection device when acquiring the information, the collection timestamp, the type of entity being collected, the identification number of the entity, and the location where the collection was conducted.

[0013] Furthermore, the face trajectory list, vehicle trajectory list and mobile phone trajectory list at least include the entity's identity number, collection time and the identity number of the collection device.

[0014] Furthermore, one of the face, vehicle and mobile phone is determined as the central entity, and the number of collisions between other entities and the central entity in space and time is calculated as the weight value.

[0015] Furthermore, the latest time and the earliest time of the two entity trajectories are first calculated, and the latest timestamp of the earliest time and the earliest timestamp of the latest time of the two entities are selected; within the range of these two timestamps, the entity trajectory with the larger weight is retained.

[0016] Furthermore, the trajectory lists within the same entity relationship are first reduced, and then the trajectory lists between different entity relationships are reduced; under the same entity type, entities with larger weights are reduced first, and the trajectory lists with larger average weights generated by different entity types are reduced first.

[0017] Furthermore, if the time interval between two tracks in a track list is greater than a preset time, the track list is split into two lists, and so on and so forth, into multiple lists.

[0018] In a second aspect, the present invention further provides a trajectory reduction system based on face, vehicle and mobile phone information, comprising:

[0019] The data collection module is configured to: obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data;

[0020] The trajectory list determination module is configured to: determine a face trajectory list, a vehicle trajectory list, and a mobile phone trajectory list respectively according to the acquired pedestrian face data, vehicle data, and mobile phone data;

[0021] The weight value calculation module is configured to: calculate the weight value of one of the face, vehicle and mobile phone items and the other two items according to the position relationship and track time relationship of the track points in the face track list, the vehicle track list and the mobile phone track list;

[0022] The judgment processing module is configured to: judge whether two trajectory lists belong to the same entity relationship according to the weight value; if they belong to the same entity relationship, sort the entities according to the weight value; if they do not belong to the same entity relationship, sort the trajectory lists between different entity types according to the average value of all entities of the entity type;

[0023] The reduction module is configured to perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

[0024] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the trajectory reduction method based on face, vehicle and mobile phone information described in the first aspect.

[0025] In a fourth aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the trajectory reduction method based on face, vehicle, and mobile phone information described in the first aspect are implemented.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention calculates the weight value of one of the face, vehicle and mobile phone and the other two items according to the point relationship and trajectory time relationship of the trajectory points in the face trajectory list, the vehicle trajectory list and the mobile phone trajectory list; then sorts the trajectory lists of the same entity and different entity types according to the weight value, and performs reduction on this basis, so that the trajectories of the face, vehicle and mobile phone can form a trajectory list, and the trajectory list has integrity and rationality. The trajectory list formed after reduction can form a correct trajectory according to the normal lifestyle of people. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0029] Figure 1 This is a flow chart of Embodiment 1 of the present invention;

[0030] Figure 2 This is an example diagram of reduction rules according to Embodiment 1 of the present invention;

[0031] Figure 3 This is an example of the reduction order of Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0034] Glossary:

[0035] Timestamp is data generated using digital signature technology. The object of the signature includes original file information, signature parameters, signature time and other information.

[0036] Reduction refers to data reduction, which means to reduce the amount of data to the maximum extent possible while keeping the original appearance of the data as much as possible; in the present invention, reduction means integrating or simplifying multiple trajectories corresponding to faces, vehicles and mobile phones into an overall trajectory.

[0037] Embodiment 1:

[0038] As described in the background technology, the prior art does not have an effective method to reduce the multiple and multiple trajectories of faces, vehicles and mobile phones collected by various types of front-end devices; or after reduction, a complete trajectory chain cannot be formed, and within a certain time range, the trajectory points are spatially disordered; or the final trajectory has no temporal and spatial correlation. In order to overcome the above problems, this embodiment provides a trajectory reduction method based on face, vehicle and mobile phone information, including:

[0039] Obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data;

[0040] Based on the acquired pedestrian face data, vehicle data and mobile phone data, a face track list, a vehicle track list and a mobile phone track list are determined respectively;

[0041] According to the positional relationship and time relationship of the track points in the face track list, vehicle track list and mobile phone track list; calculate the weight value of one item among face, vehicle and mobile phone and the other two items;

[0042] Determine whether the two trajectory lists belong to the same entity relationship based on the weight value; if they belong to the same entity relationship, sort the entities based on the weight value; if they do not belong to the same entity relationship, sort the trajectory lists of different entity types based on the mean value of all entities of the entity type;

[0043] Perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

[0044] In this embodiment, according to the positional relationship and trajectory time relationship of the trajectory points in the face trajectory list, the vehicle trajectory list and the mobile phone trajectory list, the weight value of one item among the face, vehicle and mobile phone and the other two items is calculated, and the temporal and spatial associations are added; then, the trajectory lists of the same entity and different entity types are sorted according to the weight value, and reduction is performed on this basis, so that the trajectories of the face, vehicle and mobile phone can form a trajectory list, and the trajectory list is complete and reasonable. The trajectory list formed after reduction can form a correct trajectory according to the normal lifestyle of the person.

[0045] In this embodiment, when acquiring face data, vehicle data of the vehicle being taken, and mobile phone data, each front-end needs to collect data. The collected data includes but is not limited to the identity document (ID) of the collection device, the collection timestamp, the entity type collected, the ID of the entity type, and the point where the collection is located. The corresponding data collected by the front-end collection device can be stored in the corresponding database. Since the devices and device types for capturing or collecting the three entities of face, vehicle, and mobile phone are different, two spatial relationship point tables are used in this embodiment, specifically titled {"vehicle collection device ID": ["mobile phone collection device ID"]} and {"face collection device ID": ["mobile phone collection device ID"]}, and different collection devices at the same location are mapped to prove that these devices are spatially associated.

[0046] Determine one of the face, vehicle and mobile phone as the central entity. When querying, first, the program inputs the central entity to be queried and the other two entity types. The input entity attributes include but are not limited to the entity ID, etc.; then query the corresponding database for each entity to obtain a track list, each of which contains the collection device ID, collection time and entity ID, etc.

[0047] Calculate the weight of each entity except the central entity with the central entity; the specific calculation method can be: if the space in the trajectory point has a relationship in the point table and the appearance time is no more than the preset time before and after the generation time of a certain trajectory point in the central entity, it proves that the two entities have a relationship, and its weight value is increased by one. In this embodiment, the preset time can be five minutes, and in other embodiments, the preset time can be set according to actual conditions. Calculate the number of collisions between other entities and the central entity in space and time, which is what we call the weight value. Spatial collision refers to whether the acquisition device ID is mapped in the point table, and temporal collision refers to the appearance of other entities and the central entity within 5 minutes.

[0048] Determine whether the entities to which the two trajectory lists belong are the same entity relationship. If they are the same entity relationship, sort the entities in descending order according to the weight value; if they are not the same entity relationship, sort the trajectory lists between different entity types according to the mean of all entities of the entity type, and the weight value of the central entity is the largest; then perform reduction analysis on the trajectory lists of each pair, if the trajectory of entity 1 is empty, the result is the trajectory of entity 2, and vice versa; if the trajectories overlap in time, select the entity trajectory list of the time overlap part with a larger weight; continue to reduce until all entities have been reduced, and the result obtained at this time is the final reduction result.

[0049] When performing trajectory reduction, first, perform trajectory list reduction in the same entity relationship, and then perform trajectory list reduction between different entity relationships; specifically, in Rule 1: first calculate the latest time and earliest time of the two entity trajectories, select the later timestamp of the earliest time and the earlier timestamp of the latest time of the two entities, in this embodiment, the later timestamp and the earlier timestamp can be the latest timestamp and the earliest timestamp; within the range of these two timestamps, although both entities have trajectories, the entity trajectory with a larger weight should be retained; there is no overlap of trajectories in other time ranges, so the trajectory should be retained. In Rule 2: first, the entity trajectory list in the same entity type is reduced, and then the trajectory reduction between different entities is performed. In Rule 3: under the same entity type, the entity with a larger weight is reduced first; different entity types should be reduced first according to the trajectory list with a larger average weight generated by the entity type. In rule 4, if the time interval between two trajectories in a trajectory list is greater than the preset time, which can be one hour, the trajectory list is split into two lists, and so on, it can be split into multiple lists; in this way, while not sacrificing the trajectories of entities with high weights, the trajectory lists of entities with lower weights and no overlapping time ranges are also added.

[0050] Embodiment 2:

[0051] This embodiment provides a trajectory reduction system based on face, vehicle and mobile phone information, including:

[0052] The data collection module is configured to: obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data;

[0053] The trajectory list determination module is configured to: determine a face trajectory list, a vehicle trajectory list, and a mobile phone trajectory list respectively according to the acquired pedestrian face data, vehicle data, and mobile phone data;

[0054] The weight value calculation module is configured to: calculate the weight value of one of the face, vehicle and mobile phone items and the other two items according to the position relationship and track time relationship of the track points in the face track list, the vehicle track list and the mobile phone track list;

[0055] The judgment processing module is configured to: judge whether two trajectory lists belong to the same entity relationship according to the weight value; if they belong to the same entity relationship, sort the entities according to the weight value; if they do not belong to the same entity relationship, sort the trajectory lists between different entity types according to the average value of all entities of the entity type;

[0056] The reduction module is configured to perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

[0057] The working method of the system is the same as the trajectory reduction method based on face, vehicle and mobile phone information in Example 1, and will not be repeated here.

[0058] Embodiment 3:

[0059] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the trajectory reduction method based on face, vehicle and mobile phone information described in Example 1 are implemented.

[0060] Embodiment 4:

[0061] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the trajectory reduction method based on face, vehicle, and mobile phone information described in Example 1 are implemented.

[0062] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A trajectory reduction method based on face, vehicle and mobile phone information, characterized in that: include: Obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data; Based on the acquired pedestrian face data, vehicle data and mobile phone data, a face track list, a vehicle track list and a mobile phone track list are determined respectively; According to the position relationship and track time relationship of the track points in the face track list, vehicle track list and mobile phone track list; Calculate the weight of one of the face, vehicle and mobile phone items relative to the other two items; Determine whether the two trajectory lists belong to the same entity relationship based on the weight value; if they belong to the same entity relationship, sort the entities based on the weight value; if they do not belong to the same entity relationship, sort the trajectory lists of different entity types based on the mean value of all entities of the entity type; First, the trajectory lists in the same entity relationship are reduced, and then the trajectory lists between different entity relationships are reduced; under the same entity type, entities with larger weights are reduced first, and different entity types are reduced first according to the trajectory lists with larger average weights generated by the entity types; If they are not the same entity relationship, the trajectory lists of different entity types are sorted according to the mean of all entities of the entity type, and the weight value of the central entity is the largest; then the trajectory lists are reduced and analyzed two by two, and if the trajectory of entity 1 is empty, the result is the trajectory of entity 2; if the trajectories overlap in time, the entity trajectory list of the time overlap part with a larger weight is selected; Perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

2. A trajectory reduction method based on face, vehicle and mobile phone information as claimed in claim 1, characterized in that: The acquired facial data, vehicle data of the vehicle being ridden, and mobile phone data shall at least include the identification number of the collection device when acquiring the information, the collection timestamp, the type of entity being collected, the identification number of the entity, and the location where the collection took place.

3. A trajectory reduction method based on face, vehicle and mobile phone information as claimed in claim 2, characterized in that: The face track list, vehicle track list and mobile phone track list at least include the entity's identity number, collection time and the identity number of the collection device.

4. The trajectory reduction method based on face, vehicle and mobile phone information as claimed in claim 1, characterized in that: Determine one of the face, vehicle and mobile phone as the central entity, and calculate the number of collisions between other entities and the central entity in space and time as the weight value.

5. The trajectory reduction method based on face, vehicle and mobile phone information as claimed in claim 1, characterized in that: First, calculate the latest and earliest times of the two entity trajectories, and select the latest timestamp of the earliest time and the earliest timestamp of the latest time of the two entities; Within the range of these two timestamps, the entity trajectory with the larger weight is retained.

6. A trajectory reduction method based on face, vehicle and mobile phone information as claimed in claim 1, characterized in that: If the time interval between two tracks in a track list is greater than a preset time, the track list is split into two lists, and so on and so forth.

7. A trajectory reduction system based on face, vehicle and mobile phone information, characterized in that: include: The data collection module is configured to: obtain facial data of pedestrians, vehicle data of passengers, and mobile phone data; The trajectory list determination module is configured to: determine a face trajectory list, a vehicle trajectory list, and a mobile phone trajectory list respectively according to the acquired pedestrian face data, vehicle data, and mobile phone data; The weight value calculation module is configured to: calculate the position relationship and the time relationship of the track points in the face track list, the vehicle track list and the mobile phone track list; Calculate the weight of one of the face, vehicle and mobile phone items relative to the other two items; The judgment processing module is configured to: judge whether two trajectory lists belong to the same entity relationship according to the weight value; if they belong to the same entity relationship, sort the entities according to the weight value; if they do not belong to the same entity relationship, sort the trajectory lists between different entity types according to the average value of all entities of the entity type; First, the trajectory lists in the same entity relationship are reduced, and then the trajectory lists between different entity relationships are reduced; under the same entity type, entities with larger weights are reduced first, and different entity types are reduced first according to the trajectory lists with larger average weights generated by the entity types; If they are not the same entity relationship, the trajectory lists of different entity types are sorted according to the mean of all entities of the entity type, and the weight value of the central entity is the largest; then the trajectory lists are reduced and analyzed two by two, and if the trajectory of entity 1 is empty, the result is the trajectory of entity 2; if the trajectories overlap in time, the entity trajectory list of the time overlap part with a larger weight is selected; The reduction module is configured to perform pairwise trajectory list reduction analysis and reduction on the sorted trajectory lists.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the trajectory reduction method based on face, vehicle and mobile phone information as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the trajectory reduction method based on face, vehicle and mobile phone information as described in any one of claims 1-6 are implemented.

Images