Method and apparatus for determining binding relationship, storage medium and electronic device

Abstract

Embodiments of the present application provide a method and device for determining a binding relationship, a storage medium and an electronic device. The method comprises: obtaining first trajectory information of a first MAC address and second trajectory information of a first portrait, wherein the first trajectory information comprises acquisition time of the first MAC address acquired by a group of MAC acquisition devices, position information or identification information of the group of MAC acquisition devices, and the second trajectory information comprises shooting time of the first portrait shot by a group of shooting devices, position information or identification information of the group of shooting devices; determining whether the first MAC address and the first portrait have a time and space accompanying relationship according to the first trajectory information and the second trajectory information; and establishing a binding relationship between the first MAC address and the first portrait in a case where it is determined that the first MAC address and the first portrait have a time and space accompanying relationship. Through the present application, the problem of low efficiency in determining the binding relationship between the MAC address and the portrait in the related art is solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and more specifically, to a method, apparatus, storage medium, and electronic device for determining a binding relationship. Background Technology

[0002] In the field of surveillance, a large amount of video image data, including facial images, vehicle data, and MAC addresses, has been accumulated through the initial construction of video equipment. However, MAC data suffers from data silos; individual MAC information cannot be linked to individuals, resulting in a significant but limited improvement in efficiency for criminal investigations and surveillance despite the investment in MAC acquisition and storage equipment. The most direct and effective way to enhance the utilization value of MAC data is to link MAC addresses to personnel identification information. Compared to other acquisition devices, MAC acquisition devices have advantages such as a wider acquisition range and less susceptibility to interference from light and obstructions. Linking MAC addresses to personal identification can greatly assist in criminal investigations and surveillance.

[0003] The most basic method of binding MAC addresses to personnel identity information is through registration and maintenance. However, this method suffers from high maintenance costs, incomplete registration, and various external factors such as changes in MAC device users leading to information lag and incomplete coverage. Related technologies have low efficiency in determining the binding relationship between MAC addresses and personnel (or facial images). Therefore, in current scenarios, a highly efficient, low-latency, and high-confidence method for binding MAC addresses to facial images is a pressing issue that needs to be addressed.

[0004] There is currently no effective solution to the problem of low efficiency in determining the binding relationship between MAC addresses and human images in related technologies. Summary of the Invention

[0005] This invention provides a method, apparatus, storage medium, and electronic device for determining binding relationships, in order to at least solve the problem of low efficiency in determining the binding relationship between MAC addresses and human images in related technologies.

[0006] According to an embodiment of the present invention, a method for determining a binding relationship is provided, comprising: acquiring first trajectory information of a first MAC address and second trajectory information of a first portrait, wherein the first trajectory information includes the acquisition time of the first MAC address acquired by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first portrait captured by a group of shooting devices and the location information or identification information of the group of shooting devices; determining whether there is a temporal and spatial accompaniment relationship between the first MAC address and the first portrait based on the first trajectory information and the second trajectory information; and establishing a binding relationship between the first MAC address and the first portrait if it is determined that there is a temporal and spatial accompaniment relationship between the first MAC address and the first portrait.

[0007] In an exemplary embodiment, determining whether the first MAC address and the first portrait have a temporal and spatial relationship based on the first trajectory information and the second trajectory information includes: searching for a pair of devices that match in time and space among the set of MAC acquisition devices and the set of shooting devices based on the first trajectory information and the second trajectory information to obtain a target search result, wherein each device pair includes a MAC acquisition device and a shooting device, and a device pair that matches in time and space means that the distance between the MAC acquisition device and the shooting device in the device pair is less than or equal to a preset distance threshold, and the time interval between the acquisition time of the first MAC address by the MAC acquisition device in the device pair and the shooting time of the first portrait by the shooting device in the device pair is less than or equal to a first preset time threshold; and determining whether the first MAC address and the first portrait have a temporal and spatial relationship based on the target search result.

[0008] In an exemplary embodiment, the step of searching for a time- and space-matching device pair among the group of MAC acquisition devices and the group of shooting devices based on the first trajectory information and the second trajectory information includes: when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the location information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first image captured by the group of shooting devices and the location information of the group of shooting devices, determining the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first image captured by the j-th shooting device, and... Based on the location information of the i-th MAC acquisition device and the j-th shooting device, the current distance between the i-th MAC acquisition device and the j-th shooting device is determined. The group of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2 ≤ i ≤ N. The group of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2 ≤ j ≤ M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space.

[0009] In an exemplary embodiment, the step of searching for a time- and space-matching device pair among the group of MAC acquisition devices and the group of shooting devices based on the first trajectory information and the second trajectory information includes: when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first image captured by the group of shooting devices and the identification information of the group of shooting devices, determining the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first image captured by the j-th shooting device, and determining whether the current time interval is less than or equal to the first MAC acquisition device and the second trajectory information. A preset time threshold is set. Based on the identification information of the i-th MAC acquisition device and the j-th shooting device, it is determined whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. The set of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2≤i≤N. The set of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2≤j≤M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space.

[0010] In an exemplary embodiment, determining whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold based on the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device includes: searching in a pre-established binding relationship set whether the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device have a binding relationship, wherein the binding relationship set includes the binding relationship between the identification information of MAC acquisition devices in the MAC acquisition device set and the identification information of shooting devices in the shooting device set, the binding relationship in the binding relationship set indicates that the distance between the MAC acquisition device and the shooting device corresponding to the binding relationship is less than or equal to the preset distance threshold, the MAC acquisition device set includes the group of MAC acquisition devices, and the shooting device set includes the group of shooting devices; if a binding relationship is found between the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device, determining that the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold.

[0011] In an exemplary embodiment, determining whether the first MAC address and the first image have a temporal and spatial relationship based on the target search result includes: determining that the first MAC address and the first image have a temporal and spatial relationship when the target search result indicates that the number of device pairs that match in time and space is greater than or equal to a preset number threshold; or determining that the first MAC address and the first image have a temporal and spatial relationship when the target search result indicates that both a first proportion and a second proportion are greater than or equal to a preset proportion threshold, wherein the first proportion is the ratio between the number of device pairs that match in time and space and the number of MAC acquisition devices in the group of MAC acquisition devices, and the second proportion is the ratio between the number of device pairs that match in time and space and the number of shooting devices in the group of shooting devices.

[0012] In an exemplary embodiment, after establishing the binding relationship between the first MAC address and the first image, the method further includes: merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, wherein each record item in the combined trajectory information includes the acquisition time of the first MAC address acquired by a MAC acquisition device and the location information or identification information of the MAC acquisition device, or includes the shooting time of the first image captured by a shooting device and the location information or identification information of the shooting device; and determining that the binding relationship between the first MAC address and the first image passes the verification when it is determined that every two adjacent record items in the combined trajectory information meet the predetermined speed condition.

[0013] In an exemplary embodiment, after merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, the method further includes: obtaining adjacent first record items and second record items in the combined trajectory information, wherein the first record item corresponds to a first device, a first time parameter, and a first position parameter, and the second record item corresponds to a second device, a second time parameter, and a second position parameter; determining the time interval between moving from the first device to the second device based on the first time parameter and the second time parameter; determining the distance between the first device and the second device based on the first position parameter and the second position parameter; determining the moving speed from the first device to the second device as equal to the ratio of the distance to the time interval; determining that adjacent first record items and second record items do not meet the predetermined speed condition if the moving speed is greater than a predetermined speed threshold; and determining that adjacent first record items and second record items do not meet the predetermined speed condition if the moving speed is less than or equal to the predetermined speed threshold. Under a predetermined speed threshold, adjacent first and second record items are determined to satisfy the predetermined speed condition; wherein, the first device is a first MAC acquisition device, the first time parameter is the acquisition time when the first MAC acquisition device acquires the first MAC address, and the first location parameter is the location information or identification information of the first MAC acquisition device; or, the first device is a first shooting device, the first time parameter is the shooting time when the first shooting device captures the first image, and the first location parameter is the location information or identification information of the first shooting device; wherein, the second device is a second MAC acquisition device, the second time parameter is the acquisition time when the second MAC acquisition device acquires the first MAC address, and the second location parameter is the location information or identification information of the second MAC acquisition device; or, the second device is a second shooting device, the second time parameter is the shooting time when the second shooting device captures the first image, and the second location parameter is the location information or identification information of the second shooting device.

[0014] In an exemplary embodiment, determining whether the first MAC address and the first portrait have a temporal and spatial relationship based on the first trajectory information and the second trajectory information includes: dividing the first trajectory information into P first sub-trajectory information according to the different time segments to which the acquisition time corresponding to each record item in the first trajectory information belongs, wherein each of the P first sub-trajectory information corresponds to a different time segment, and P is a positive integer greater than or equal to 2; dividing the second trajectory information into Q second sub-trajectory information according to the different time segments to which the shooting time corresponding to each record item in the second trajectory information belongs, wherein each of the Q second sub-trajectory information... The second sub-trajectory information corresponds to different time segments, where Q is a positive integer greater than or equal to 2. Among the P first sub-trajectory information and the Q second sub-trajectory information, pairs of sub-trajectory information corresponding to the same time segment are searched, resulting in M ​​pairs of sub-trajectory information corresponding to M time segments. Each sub-trajectory information pair includes first and second sub-trajectory information corresponding to the same time segment, where M is less than or equal to P and less than or equal to Q. If M is greater than or equal to a preset threshold, and based on the M sub-trajectory information pairs, it is determined that the first MAC address and the first portrait have a temporal and spatial association relationship in the M time segments, then the temporal and spatial association relationship between the first MAC address and the first portrait is established.

[0015] In an exemplary embodiment, obtaining the first trajectory information of the first MAC address and the second trajectory information of the first portrait includes: obtaining first record information in a target MAC acquisition device, wherein each record item in the first record information is used to represent the corresponding MAC address acquired by the target MAC acquisition device in a set of acquisition times, the first record information includes a first target record item, the first target record item includes the first MAC address and the target acquisition time when the target MAC acquisition device acquired the first MAC address; obtaining second record information in a target shooting device, wherein each record item in the second record information is used to represent the corresponding portrait captured by the target shooting device in a set of shooting times, the second record information includes a second target record item, the second target record item includes the first portrait and the target shooting time when the target shooting device captured the first portrait, the distance between the target shooting device and the target MAC acquisition device is less than or equal to a second preset distance threshold; and obtaining the first trajectory information and the second trajectory information when it is determined that the time interval between the target acquisition time and the target shooting time is less than or equal to a second preset time threshold.

[0016] According to another embodiment of the present invention, a device for determining a binding relationship is also provided, comprising: a first acquisition module, configured to acquire first trajectory information of a first MAC address and second trajectory information of a first portrait, wherein the first trajectory information includes the acquisition time of the first MAC address acquired by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first portrait captured by a group of shooting devices and the location information or identification information of the group of shooting devices; a first determination module, configured to determine whether there is a temporal and spatial accompaniment relationship between the first MAC address and the first portrait based on the first trajectory information and the second trajectory information; and an establishment module, configured to establish a binding relationship between the first MAC address and the first portrait when it is determined that there is a temporal and spatial accompaniment relationship between the first MAC address and the first portrait.

[0017] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0018] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0019] This invention obtains first trajectory information of a first MAC address and second trajectory information of a first portrait image. The first trajectory information includes the acquisition time of the first MAC address by a set of MAC acquisition devices and the location or identification information of the MAC acquisition devices. The second trajectory information includes the capture time of the first portrait image by a set of capturing devices and the location or identification information of the capturing devices. Based on the first and second trajectory information, it is determined whether there is a temporal and spatial relationship between the first MAC address and the first portrait image. When a temporal and spatial relationship is determined, a binding relationship between the first MAC address and the first portrait image is established. In other words, when a temporal and spatial relationship between the first MAC address and the first portrait image is determined based on the first and second trajectory information, the purpose of establishing a binding relationship between the first MAC address and the first portrait image can be achieved. This avoids the low efficiency problem caused by the registration and maintenance method used in related technologies for binding MAC addresses and portrait images. Therefore, it solves the problem of low efficiency in determining the binding relationship between MAC addresses and portrait images in related technologies, and achieves the effect of improving the efficiency of determining the binding relationship between MAC addresses and portrait images. Attached Figure Description

[0020] Figure 1 This is a mobile terminal hardware structure block diagram of the binding relationship determination method according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart of a method for determining a binding relationship according to an embodiment of the present invention;

[0022] Figure 3 This is a flowchart illustrating the process of binding personnel to MAC addresses according to an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the time-related calculation according to a specific embodiment of the present invention;

[0024] Figure 5 This is an example diagram of trajectory merging according to a specific embodiment of the present invention;

[0025] Figure 6 This is an example diagram of speed conversion according to a specific embodiment of the present invention;

[0026] Figure 7 This is a structural block diagram of a binding relationship determination device according to an embodiment of the present invention. Detailed Implementation

[0027] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0029] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a mobile terminal hardware structure block diagram of the binding relationship determination method according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the binding relationship determination method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0032] This embodiment provides a method for determining binding relationships. Figure 2 This is a flowchart of a method for determining binding relationships according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0033] Step S202: Obtain first trajectory information of the first MAC address and second trajectory information of the first portrait. The first trajectory information includes the acquisition time of the first MAC address by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices. The second trajectory information includes the shooting time of the first portrait captured by a group of shooting devices and the location information or identification information of the group of shooting devices.

[0034] Step S204: Based on the first trajectory information and the second trajectory information, determine whether there is a temporal and spatial relationship between the first MAC address and the first portrait.

[0035] Step S206: If it is determined that the first MAC address and the first image have a temporal and spatial relationship, a binding relationship is established between the first MAC address and the first image.

[0036] Through the above steps, by acquiring the first trajectory information of the first MAC address and the second trajectory information of the first portrait, the first trajectory information includes the acquisition time of the first MAC address by a set of MAC acquisition devices and the location or identification information of a set of MAC acquisition devices. The second trajectory information includes the capture time of the first portrait by a set of capturing devices and the location or identification information of a set of capturing devices. Based on the first and second trajectory information, it is determined whether there is a temporal and spatial relationship between the first MAC address and the first portrait. When it is determined that there is a temporal and spatial relationship between the first MAC address and the first portrait, a binding relationship between the first MAC address and the first portrait can be established. That is, when it is determined that there is a temporal and spatial relationship between the first MAC address and the first portrait based on the first and second trajectory information, the purpose of establishing a binding relationship between the first MAC address and the first portrait can be achieved. This avoids the problem of low efficiency caused by binding MAC addresses and portraits through registration and maintenance in related technologies. Therefore, it solves the problem of low efficiency in determining the binding relationship between MAC addresses and portraits in related technologies, and achieves the effect of improving the efficiency of determining the binding relationship between MAC addresses and portraits.

[0037] The entity performing the above steps can be a terminal or a server, such as a data analysis server, but is not limited to these.

[0038] In the above embodiments, the server obtains first trajectory information of the first MAC address and second trajectory information of the first portrait. The first trajectory information includes the collection time of the first MAC address by a set of MAC acquisition devices and the location or identification information of a set of MAC acquisition devices. The second trajectory information includes the shooting time of the first portrait captured by a set of shooting devices and the location or identification information of a set of shooting devices. The first MAC address corresponds to the MAC address of a terminal T (such as a mobile phone or iPad) collected by the MAC acquisition devices. The first trajectory information is a combination of information collected by multiple MAC acquisition devices at different times during the movement of terminal T. Similarly... The first image corresponds to the image of a person (e.g., Zhang San) captured by a shooting device (such as a camera or webcam). The second trajectory information is a combination of information captured by multiple shooting devices at different times during Zhang San's movement. In practical applications, the data collected by the aforementioned set of MAC acquisition devices and the set of shooting devices can be intelligently structured and parsed into data in a specified format. For example, each piece of information in the first trajectory information may include the MAC acquisition device of the first MAC address, the acquisition time, and the first MAC address acquired. The information about the MAC acquisition device may be the identifier (or device number) of the MAC acquisition device, or MA C. Location information of the acquisition device (such as the latitude and longitude of the device's location). Each piece of information in the second trajectory information mentioned above may include the capturing device of the first human image, the acquisition time, and the captured first human image. Information about the capturing device may be the identification (or device number) of the capturing device, or the location information of the capturing device (such as the latitude and longitude of the device's location). The first human image information may be a person identification (such as ID0001) or human image file number obtained from the video image captured by the capturing device. In practical applications, the location corresponding to each device can also be determined based on the identification of each device. Based on the first trajectory information and the second trajectory information, the first MAC address and the first... Whether there is a temporal and spatial relationship between the portrait and the first image is determined by considering the acquisition time and location information of the acquisition device included in each piece of the first trajectory information, and the shooting time and location information of the shooting device included in each piece of the second trajectory information. When it is determined that there is a temporal and spatial relationship between the first MAC address and the first image, a binding relationship between the first MAC address and the first image is established. In other words, the binding relationship between the first MAC address and the first image is determined, or it is preliminarily determined that the user of the terminal corresponding to the first MAC address may be the person corresponding to the first image.That is, when it is determined that the first MAC address and the first portrait have a temporal and spatial relationship based on the first trajectory information and the second trajectory information, the purpose of establishing a binding relationship between the first MAC address and the first portrait can be achieved. This avoids the problem of low efficiency caused by binding MAC addresses and portraits through registration and maintenance in related technologies. Therefore, it solves the problem of low efficiency in determining the binding relationship between MAC addresses and portraits in related technologies and achieves the effect of improving the efficiency of determining the binding relationship between MAC addresses and portraits.

[0039] In an optional embodiment, determining whether the first MAC address and the first image have a temporal and spatial relationship based on the first trajectory information and the second trajectory information includes: searching for time- and spatially matching device pairs among the set of MAC acquisition devices and the set of shooting devices based on the first trajectory information and the second trajectory information to obtain a target search result, wherein each device pair includes a MAC acquisition device and a shooting device, and a time- and spatially matching device pair means that the distance between the MAC acquisition device and the shooting device in the device pair is less than or equal to a preset distance threshold, and the time interval between the acquisition time of the first MAC address by the MAC acquisition device in the device pair and the shooting time of the first image by the shooting device in the device pair is less than or equal to a first preset time threshold; and determining whether the first MAC address and the first image have a temporal and spatial relationship based on the target search result.In this embodiment, a time-space matching device pair is searched among a set of MAC acquisition devices and a set of imaging devices. A time-space matching device pair means that the distance between the MAC acquisition device and the imaging device in the device pair is less than or equal to a preset distance threshold (e.g., 10m, 15m, or others), and the time interval between the acquisition time of the first MAC address by the MAC acquisition device in the device pair and the capture time of the first human image by the imaging device in the device pair is less than or equal to a first preset time threshold (e.g., 10s, 20s, or others). Each device pair consists of one MAC acquisition device and one imaging device, or in other words, each... In a device pair, the MAC acquisition device and the imaging device form a binding relationship. In practical applications, one MAC acquisition device can be bound to one or more imaging devices. For example, MAC acquisition device MAC1 can be bound to imaging device C1, and can also be bound to imaging device C2 simultaneously. Of course, one imaging device can also be bound to one or more MAC acquisition devices. Typically, when the distance between the MAC acquisition device and the imaging device is less than a predetermined threshold (e.g., 10m), the MAC acquisition device and the imaging device are bound together. Establishing the binding relationship between the MAC acquisition device and the imaging device facilitates subsequent MAC-based... The system uses the trajectory information of the address and the trajectory information of the person to determine the binding relationship between the MAC address and the person. Then, based on the above search results, it determines whether there is a temporal and spatial relationship between the first MAC address and the first image. For example, in a set of MAC acquisition devices and a set of shooting devices, no matching device pair is found in time and space. For example, the distance between the MAC acquisition devices involved in the first trajectory information and the shooting devices involved in the second trajectory information is very far. In this case, it is unlikely that the first MAC address and the first image will form a binding relationship, that is, the user of the terminal corresponding to the first MAC address is unlikely to be the person corresponding to the first image. If the number of time-space matching device pairs found in a set of MAC acquisition devices and a set of shooting devices is greater than or equal to a predetermined number (such as 2 pairs, 3 pairs, or others), it can be determined that the first MAC address and the first portrait have a time-space relationship. Alternatively, if the ratio of the number of time-space matching device pairs found to the number of a set of MAC acquisition devices is greater than or equal to a first predetermined ratio threshold, and / or if the ratio of the number of time-space matching device pairs found to the number of a set of shooting devices is greater than or equal to a second predetermined ratio threshold, it can be determined that the first MAC address and the first portrait have a time-space relationship.In this embodiment, by searching among a set of MAC acquisition devices and a set of shooting devices to see if there are any matching device pairs in time and space, the purpose of determining whether there is a temporal and spatial relationship between the first MAC address and the first portrait is achieved based on the search results.

[0040] In an optional embodiment, the step of searching for a temporally and spatially matching device pair among the group of MAC acquisition devices and the group of shooting devices based on the first trajectory information and the second trajectory information includes: when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the location information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first image captured by the group of shooting devices and the location information of the group of shooting devices, determining the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first image captured by the j-th shooting device, and... Based on the location information of the i-th MAC acquisition device and the j-th shooting device, the current distance between the i-th MAC acquisition device and the j-th shooting device is determined. The group of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2 ≤ i ≤ N. The group of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2 ≤ j ≤ M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space. In this embodiment, based on the acquisition time of the first MAC address acquired by each MAC acquisition device included in the first trajectory information and the location information of each MAC acquisition device, and the capture time of the first portrait captured by each shooting device included in the second trajectory information and the location information of each shooting device, it is determined whether any MAC acquisition device and any shooting device are a device pair that matches in time and space. Taking the i-th MAC acquisition device and the j-th shooting device as an example, for instance, the acquisition time of the first MAC address acquired by the i-th MAC acquisition device is t. i The shooting time t when the j-th shooting device captures the first portrait j The time interval between the two (referring to the MAC acquisition device and the imaging device) can be determined to be |t. i -t jFurthermore, the distance between the i-th MAC acquisition device and the j-th shooting device can be determined based on their location information. For example, the location information could be the latitude and longitude of the devices, allowing calculation of the Euclidean distance between them. Then, if the distance is less than or equal to a preset distance threshold (e.g., 10m, 15m, or others) and the time interval is less than or equal to a first preset time threshold (e.g., 10s, 20s, or others), the i-th MAC acquisition device and the j-th shooting device can be identified as a temporally and spatially matched device pair. This embodiment achieves the goal of determining whether any MAC acquisition device and any shooting device are temporally and spatially matched device pairs based on the device acquisition time and device location information contained in the first and second trajectory information.

[0041] In an optional embodiment, the step of searching for a time- and space-matching device pair among the group of MAC acquisition devices and the group of shooting devices based on the first trajectory information and the second trajectory information includes: when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first image captured by the group of shooting devices and the identification information of the group of shooting devices, determining the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first image captured by the j-th shooting device, and determining whether the current time interval is less than or equal to the first MAC acquisition device and the second trajectory information. A preset time threshold is set. Based on the identification information of the i-th MAC acquisition device and the j-th shooting device, it is determined whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. The set of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2≤i≤N. The set of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2≤j≤M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space. In this embodiment, based on the acquisition time of the first MAC address acquired by each MAC acquisition device included in the first trajectory information and the identification information of each MAC acquisition device, and the capture time of the first portrait captured by each shooting device included in the second trajectory information and the identification information of each shooting device, it is determined whether any MAC acquisition device and any shooting device are a device pair that matches in time and space. Taking the i-th MAC acquisition device and the j-th shooting device as an example, for instance, the acquisition time of the first MAC address acquired by the i-th MAC acquisition device is t. i The shooting time t when the j-th shooting device captures the first portrait j The time interval between the two (referring to the MAC acquisition device and the imaging device) can be determined to be |t. i -t jThe system determines whether the time interval between the two devices is less than or equal to a first preset time threshold. It can also determine whether the distance between the two devices is less than or equal to a preset distance threshold based on the identification information of the i-th MAC acquisition device and the j-th shooting device. For example, MAC acquisition devices and shooting devices with a distance less than or equal to a preset distance threshold (e.g., 10m) are bound in advance. Typically, a binding relationship is established between the identifiers of the two devices. That is, in the aforementioned group of MAC acquisition devices and group of shooting devices, multiple binding relationships between the identifiers of MAC acquisition devices and the identifiers of shooting devices may have been established in advance. Thus, the distance between the two devices can be determined using the identification information of the i-th MAC acquisition device and the j-th shooting device. Then, when the distance between the two devices is determined to be less than or equal to the preset distance threshold (e.g., 10m, 15m, or others) based on the identifier information, and the time interval between the two devices is less than or equal to the first preset time threshold (e.g., 10s, 20s, or others), the i-th MAC acquisition device and the j-th shooting device can be identified as a device pair that matches in time and space. This embodiment achieves the goal of determining whether any MAC acquisition device and any shooting device are a device pair that are matched in time and space based on the device acquisition time and device identification information contained in the first trajectory information and the second trajectory information.

[0042] In an optional embodiment, determining whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold based on the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device includes: searching in a pre-established binding relationship set whether the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device have a binding relationship, wherein the binding relationship set includes the binding relationship between the identification information of MAC acquisition devices in the MAC acquisition device set and the identification information of shooting devices in the shooting device set, the binding relationship in the binding relationship set indicates that the distance between the MAC acquisition device and the shooting device corresponding to the binding relationship is less than or equal to the preset distance threshold, the MAC acquisition device set includes the group of MAC acquisition devices, and the shooting device set includes the group of shooting devices; if a binding relationship is found between the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device, then determining that the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. In this embodiment, the aforementioned binding relationship set contains one or more sets of correspondences between the identification information of MAC acquisition devices and the identification information of shooting devices. Each set of MAC acquisition device identification information and shooting device identification information has a binding relationship, meaning the distance between the two devices is less than or equal to a preset distance threshold. Thus, when a binding relationship is found between the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device in the binding relationship set, it can be determined that the distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. Through this embodiment, by pre-establishing a binding relationship set between the identification information of MAC acquisition devices and the identification information of shooting devices, it is possible to determine whether the distance between a MAC acquisition device represented by any MAC acquisition device identification information and a shooting device represented by any shooting device identification information is less than or equal to the preset distance threshold.

[0043] In an optional embodiment, determining whether the first MAC address and the first image have a temporal and spatial relationship based on the target search result includes: determining that the first MAC address and the first image have a temporal and spatial relationship when the target search result indicates that the number of device pairs that match in time and space is greater than or equal to a preset number threshold; or determining that the first MAC address and the first image have a temporal and spatial relationship when the target search result indicates that both a first proportion and a second proportion are greater than or equal to a preset proportion threshold, wherein the first proportion is the ratio between the number of device pairs that match in time and space and the number of MAC acquisition devices in the group of MAC acquisition devices, and the second proportion is the ratio between the number of device pairs that match in time and space and the number of shooting devices in the group of shooting devices. Optionally, when the target search result indicates that the number of time-space matching device pairs found in a set of MAC acquisition devices and a set of shooting devices is greater than or equal to a predetermined number (e.g., 2 pairs, 3 pairs, or others), it can be determined that the first MAC address and the first portrait have a temporal and spatial relationship. Alternatively, when the ratio of the number of time-space matching device pairs found to the number of a set of MAC acquisition devices is greater than or equal to a first predetermined ratio threshold (e.g., 20%, 50%, or others), and / or when the ratio of the number of time-space matching device pairs found to the number of a set of shooting devices is greater than or equal to a second predetermined ratio threshold (e.g., 30%, 50%, or others), it is determined that the first MAC address and the first portrait have a temporal and spatial relationship. Through this embodiment, the purpose of further determining whether the first MAC address and the first portrait have a temporal and spatial relationship is based on the number of matching device pairs indicated by the target search result is achieved.

[0044] In an optional embodiment, after establishing the binding relationship between the first MAC address and the first image, the method further includes: merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information. Each record item in the combined trajectory information includes the acquisition time of the first MAC address acquired by a MAC acquisition device and the location information or identification information of the MAC acquisition device, or includes the shooting time of the first image captured by a shooting device and the location information or identification information of the shooting device. If it is determined that every two adjacent record items in the combined trajectory information meet a predetermined speed condition, the binding relationship between the first MAC address and the first image is verified. In this embodiment, when establishing the binding relationship between the first MAC address and the first portrait, there may be an incorrect binding relationship, that is, the person indicated by the first portrait is not the terminal corresponding to the first MAC address. Therefore, after establishing the binding relationship between the first MAC address and the first portrait, the binding relationship between the two can be verified. For example, the first trajectory information and the second trajectory information can be merged, and each record item in the merged trajectory information can be sorted according to the order of collection time and shooting time to obtain combined trajectory information. Then, it can be determined whether each pair of adjacent record items in the combined trajectory information meets the predetermined speed condition, thereby achieving the purpose of verifying the binding relationship between the first MAC address and the first portrait, and achieving the effect of improving the accuracy of determining the binding relationship between the MAC address and the portrait.

[0045] In an optional embodiment, after merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, the method further includes: obtaining adjacent first record items and second record items in the combined trajectory information, wherein the first record item corresponds to a first device, a first time parameter, and a first position parameter, and the second record item corresponds to a second device, a second time parameter, and a second position parameter; determining the time interval between moving from the first device to the second device based on the first time parameter and the second time parameter; determining the distance between the first device and the second device based on the first position parameter and the second position parameter; determining the moving speed from the first device to the second device as equal to the ratio of the distance to the time interval; determining that adjacent first record items and second record items do not meet the predetermined speed condition if the moving speed is greater than a predetermined speed threshold; and determining that adjacent first record items and second record items do not meet the predetermined speed condition if the moving speed is less than or equal to the predetermined speed threshold. Under a predetermined speed threshold, adjacent first and second record items are determined to satisfy the predetermined speed condition; wherein, the first device is a first MAC acquisition device, the first time parameter is the acquisition time when the first MAC acquisition device acquires the first MAC address, and the first location parameter is the location information or identification information of the first MAC acquisition device; or, the first device is a first shooting device, the first time parameter is the shooting time when the first shooting device captures the first image, and the first location parameter is the location information or identification information of the first shooting device; wherein, the second device is a second MAC acquisition device, the second time parameter is the acquisition time when the second MAC acquisition device acquires the first MAC address, and the second location parameter is the location information or identification information of the second MAC acquisition device; or, the second device is a second shooting device, the second time parameter is the shooting time when the second shooting device captures the first image, and the second location parameter is the location information or identification information of the second shooting device.In this embodiment, by acquiring two adjacent record items, such as a first record item and a second record item, and based on the time and location parameters recorded in each record item, the time (or time difference) for the terminal represented by the first MAC address or the person represented by the first image to move from the first device corresponding to the first record item to the second device corresponding to the second record item can be calculated. The distance between the first and second devices can also be calculated, and thus the movement speed from the first device to the second device can be calculated. When the movement speed is determined to be greater than a predetermined speed threshold (e.g., 200 km / h), it is determined that the predetermined speed condition is not met between the two adjacent record items. In this case, the previously determined binding relationship between the first MAC address and the first image can be corrected; for example, the binding relationship can be deleted. When the movement speed is determined to be less than or equal to the predetermined speed threshold, it is determined that the predetermined speed condition is met between the two adjacent record items. Through this embodiment, by performing speed verification on the merged trajectory, the accuracy of determining the binding relationship between the MAC address and the image can be further improved.

[0046] In an optional embodiment, determining whether the first MAC address and the first portrait have a temporal and spatial relationship based on the first trajectory information and the second trajectory information includes: dividing the first trajectory information into P first sub-trajectory information according to the different time segments to which the acquisition time corresponding to each record item in the first trajectory information belongs, wherein each of the P first sub-trajectory information corresponds to a different time segment, and P is a positive integer greater than or equal to 2; dividing the second trajectory information into Q second sub-trajectory information according to the different time segments to which the shooting time corresponding to each record item in the second trajectory information belongs, wherein each of the Q second sub-trajectory information... The second sub-trajectory information corresponds to different time segments, where Q is a positive integer greater than or equal to 2. Among the P first sub-trajectory information and the Q second sub-trajectory information, pairs of sub-trajectory information corresponding to the same time segment are searched, resulting in M ​​pairs of sub-trajectory information corresponding to M time segments. Each sub-trajectory information pair includes first and second sub-trajectory information corresponding to the same time segment, where M is less than or equal to P and less than or equal to Q. If M is greater than or equal to a preset threshold, and based on the M sub-trajectory information pairs, it is determined that the first MAC address and the first portrait have a temporal and spatial association relationship in the M time segments, then the temporal and spatial association relationship between the first MAC address and the first portrait is established. In this embodiment, the first trajectory information is divided into P first sub-trajectory information according to different time segments, or in other words, the original trajectory of the first MAC address is divided into multiple sub-trajectory segments according to time segments. Similarly, the second trajectory information is divided into Q second sub-trajectory information according to different time segments. Then, the sub-trajectory information pairs corresponding to the same time segment are searched. For example, in a certain time segment, there are sub-trajectory information in both the first trajectory information and the second trajectory information. Assuming there are sub-trajectory information pairs in a total of M time segments, when M is greater than or equal to a preset threshold, and the first MAC address and the first portrait have a temporal and spatial accompaniment relationship in the M time segments, it can be determined that the first MAC address and the first portrait have a temporal and spatial accompaniment relationship.

[0047] In an optional embodiment, obtaining the first trajectory information of the first MAC address and the second trajectory information of the first portrait includes: obtaining first record information in a target MAC acquisition device, wherein each record item in the first record information is used to represent the corresponding MAC address acquired by the target MAC acquisition device in a set of acquisition times, the first record information includes a first target record item, the first target record item includes the first MAC address and the target acquisition time when the target MAC acquisition device acquired the first MAC address; obtaining second record information in a target shooting device, wherein each record item in the second record information is used to represent the corresponding portrait captured by the target shooting device in a set of shooting times, the second record information includes a second target record item, the second target record item includes the first portrait and the target shooting time when the target shooting device captured the first portrait, the distance between the target shooting device and the target MAC acquisition device is less than or equal to a second preset distance threshold; and obtaining the first trajectory information and the second trajectory information when it is determined that the time interval between the target acquisition time and the target shooting time is less than or equal to a second preset time threshold.In this embodiment, firstly, first recording information from the target MAC acquisition device and second recording information from the target shooting device can be obtained. The distance between the target MAC acquisition device and the target shooting device is less than or equal to a second preset distance threshold, or the target MAC acquisition device and the target shooting device are bound together. Based on the target acquisition time corresponding to the first target recording item included in the first recording information and the target shooting time corresponding to the second target recording item included in the second recording information, when the time interval between the target acquisition time and the target shooting time is determined to be less than or equal to a second preset time threshold, first trajectory information and second trajectory information are obtained. In this embodiment, when acquiring… Before obtaining the first and second trajectory information, a pair of bound devices is first used. For example, a MAC acquisition device MAC1 and a shooting device C1 are bound together. Recorded information from each device in this pair is then acquired, such as the first and second recorded information mentioned above. This recorded information can be all information collected by the devices within a day (or one hour, or other time period). For example, if the recorded information is from one hour (e.g., 10:00-11:00), MAC1 might record 200 pieces of information, while C1 might record 100 pieces. The information recorded by each device is then sorted chronologically, and the corresponding information from the first recorded information is then... The acquisition time of each MAC address is compared with the shooting time of each corresponding portrait in the second recording information. Only when the time difference between the acquisition time and the shooting time is less than or equal to a second preset time threshold (e.g., 10 seconds) is the trajectory information of the corresponding MAC address and portrait obtained. For example, if the time difference between the acquisition time of the first MAC address and the shooting time of the first portrait is less than 10 seconds, then the first trajectory information corresponding to the first MAC address and the second trajectory information corresponding to the first portrait are obtained. However, if the time difference between the acquisition time of the second MAC address and the shooting time of the second portrait is 5 minutes (exceeding the aforementioned second preset time threshold), then no further acquisition is required. The trajectory information corresponding to the second MAC address and the trajectory information corresponding to the second portrait are obtained to determine the temporal and spatial accompaniment relationship. That is, in practical applications, the MAC addresses (such as the first MAC address) and personnel (such as the first portrait) that may have an accompaniment relationship can be found by first using the recorded information in the device pair with a binding relationship (such as the MAC acquisition device MAC1 and the shooting device C1 mentioned above). Then, their trajectory information is obtained to further determine whether there is a temporal and spatial accompaniment relationship. For MAC addresses (such as the second MAC address) and personnel (such as the second portrait) that cannot have an accompaniment relationship, it is not necessary to obtain their trajectory information for comparison.This embodiment reduces the number of comparisons, avoiding the problem of excessive comparisons caused by comparing all possible MAC addresses with all facial images one by one in the prior art. Especially for big data applications, the methods in related technologies have the problem of high performance consumption on the device.

[0048] In practical applications, after acquiring the first and second record information, assume the first record information contains 200 pieces of information (each piece of information records the collected MAC address and collection time), and the second record information contains 100 pieces of information (each piece of information records the captured image and collection time). Of course, in practice, the same MAC address may be collected multiple times by the same MAC acquisition device; that is, the same MAC address may correspond to multiple pieces of information. Similarly, the same person may be captured multiple times by the same camera. For ease of illustration, here we assume the 200 pieces of information in the first record information... Given 200 different MAC addresses, and 100 entries in the second record information corresponding to 100 different individuals, in the initial determination of whether there might be a correlation between these 100 individuals and the 200 MAC addresses, related technologies employ a pairwise comparison method. This requires comparing the capture time for each individual with the capture time for each MAC address, resulting in a large workload and significant strain on equipment performance. Optionally, this embodiment sorts the record items in the second record information according to chronological order. For example, each record item corresponds to a capture time, resulting in a total of 100 time entries t. [0] ~t

[99] (First time set), and sort the record items in the first record information according to the chronological order. For example, each record item corresponds to a collection time, and there are a total of 200 times t. [0] '~t

[199] '(Second time set), in the process of determining whether there is a possible association between the above 100 people and 200 MAC addresses, for a certain shooting time (e.g., t) in the second record information. [K] Find the record with time t from the 200 times corresponding to the first record information. [K] The time difference is less than or equal to one or more acquisition times of a preset time threshold (e.g., 10s), and it is assumed that t is determined in the second time set. [L] 'and t [K] The time difference is greater than the preset time threshold, and t [L+1] 'and t [K] If the time difference is less than or equal to a preset time threshold, then when the first time set t... [K]After comparing with the second time set, when performing the next round of comparison, the time set t in the first time set will be compared again. [K+1] When comparing with the second time set, it is not necessary to compare from the first element of the second time set; comparison can be performed from t. [L+1] The comparisons are performed sequentially in chronological order, which greatly reduces the number of comparisons and improves the efficiency of the comparison process, thus improving the efficiency of determining the binding relationship between MAC addresses and facial images.

[0049] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. The present invention will be specifically described below with reference to the embodiments.

[0050] Currently, with the advancement of intelligent security, numerous video surveillance points of various types are being built in various social and public security fields, generating a large amount of image data and parsed structured data every day. This invention's embodiments combine the collected facial image data and the MAC information of the terminal device with basic device information for mining and analysis, constructing a MAC ID mapping.

[0051] The facial image data includes attributes such as: acquisition device ID, master file ID, acquisition time, and device number; the terminal device's MAC data includes attributes such as: terminal device MAC address, acquisition device number, acquisition device name, acquisition time, and device ID; basic device information includes device number, device name, device type, and device latitude and longitude. The core idea of ​​this invention is to establish a companion relationship based on the trajectory of the mobile terminal's MAC address and the human's behavioral trajectory. Competency matching is performed between the human's trajectory and the MAC address trajectory (optimized for computational stability and performance). Deduplication is performed on the companion details to form the first relationship. Then, related trajectories are associated through this first relationship and the trajectories are merged. The distance between two devices at adjacent time points is calculated, converted into speed, and error correction is performed using the speed data to finally generate the second relationship.

[0052] This patent requires structured facial image and MAC trajectory data as prerequisites. The facial image data consists of structured data containing redundant personal identification information and device latitude and longitude coordinates, as shown in Table 1.

[0053] Human trajectory data:

[0054] Table 1. Human Image Trajectory Information

[0055] Device number Image file number Document Types ID number Name Collection time 1 00001 Resident ID Card 330128****011892774 Zhang San 1629276297000 1 00001 Resident ID Card 330128****011892774 Zhang San 1629276297000 1 00002 Ordinary passport E0000**** Li Si 1629276293000

[0056] MAC data requires the latitude and longitude of redundant acquisition devices, and needs to be verified for authenticity and signal strength. For example, MAC trajectory data is shown in Table 2.

[0057] MAC trajectory data:

[0058] Table 2 MAC Trajectory Information Table

[0059] Device number MAC address Collection time 2 B0-**-**-**-**-69 1629276297000 2 B0-**-**-**-**-69 1629276297000 2 B0-**-**-**-**-69 1629276293000

[0060] Equipment information is shown in Table 3.

[0061] Table 3 Equipment Information Table

[0062] Device number Equipment type Regional longitude Regional latitude 1 people 110.289124 39.287544 2 Mac 121.485451 31.226562

[0063] The main objective of this invention is to mine ID-mapping from structured human and MAC-related trajectory data. By automatically extracting correlations from massive amounts of trajectory data using a computer, it enables the binding of MAC addresses of suspicious individuals, thereby increasing the utilization value of MAC trajectory data. Furthermore, compared to facial recognition devices with their narrow acquisition range and limitations imposed by external factors such as lighting and obstruction, MAC devices offer a wider acquisition range and are less affected by factors like lighting and obstruction, providing a feasible supplementary solution for real-time personnel location tracking.

[0064] Figure 3 This is a flowchart illustrating the process of binding personnel to MAC addresses according to an embodiment of the present invention. The specific process is as follows:

[0065] Step S302: Obtain video structured data

[0066] Image data acquired by the acquisition device cannot be used directly. It needs to undergo intelligent structured parsing to be parsed into a specified data format before it can be used for the specified time range.

[0067] The database contains structured data, including facial image data, facial profile identity information, and terminal MAC data. Basic location information of the collected devices is used to prepare for subsequent model construction.

[0068] Optionally, in practical applications, redundant identity information can be combined to identify key personnel.

[0069] Step S304: Data Preprocessing

[0070] The incoming data contains a large amount of dirty and interfering data, requiring data integration and filtering. To improve the effectiveness of the overall calculation results, the following data preprocessing steps are performed on the MAC data.

[0071] The second-lowest bit (LSb) of the most significant byte (MSB) of a MAC address indicates whether the MAC address is global or local, i.e., the U / L (Universal / Local) bit. A value of 0 indicates a global address. This bit is 0 for all OUI (Original / Local) values. The first-lowest bit (LSb) of the most significant byte (MSB) of a MAC address indicates whether the MAC address is unicast or multicast. 0 indicates unicast. This invention focuses on unicast MAC addresses for analysis.

[0072] Step S306: Bind device relationship

[0073] Binding relationships between devices are established based on the Euclidean distance between the person and the MAC acquisition device being less than a threshold.

[0074] Let the latitude and longitude of the two devices be (x1, y1) and (x2, y2) respectively, the radius of the Earth be R, and the final arc distance be D. The calculation formula is as follows:

[0075]

[0076]

[0077]

[0078] D=R·arccos(2sinα·sinγ+cosα·cosβ·cosγ)

[0079] Step S308: Obtain peer details in a bidirectional loop according to time accompaniment.

[0080] The trajectories are grouped by device, and then further grouped by time within each group. Assuming a grouping interval of 4 hours and a time-related threshold of 1 minute, the time groups for a day are: [0:00-4:00], [3:59-8:00], [7:59-12:00], [11:59-16:00], [15:59-20:00], and [19:59-0:00 the next day]. This grouping mode reduces the sorting cost of grouping within each group. Although there is a 1-minute overlap between adjacent groups involving duplicate calculations, the stability and performance in the subsequent sorting step are improved.

[0081] Time-dependent calculations are performed on the trajectories corresponding to the two bound devices. The calculation involves double loops and double exits, significantly reducing the number of pairwise comparisons. Figure 4 As shown, Figure 4 This is a flowchart illustrating the time-related calculation according to a specific embodiment of the present invention, as follows:

[0082] S402, the trajectory of device A is sorted by time. For example, device A is a camera device (or MAC acquisition device). The acquisition data of device A within a certain time period (such as 1 day, 1 hour, or other duration) is obtained. The acquisition data within this time period includes multiple people. Of course, the acquisition data includes the shooting time when each person is captured.

[0083] S404, define the set index x = 0; for example, if device A collects a total of 100 data points within a certain time period, that is, the data set of device A contains a total of 100 data points, then the index x ranges from 0 to 99; in practical applications, each data point has a recorded collection time (or shooting time);

[0084] S406, determine if x is out of bounds;

[0085] S408, if it is determined that x has not crossed the boundary, obtain the trajectory where the index x is located; for example, obtain the collected data corresponding to the index x;

[0086] If it is determined in step S406 that x has exceeded the limit (for example, x has exceeded 99), the process ends directly, meaning that all data in the data set of device A has been compared.

[0087] S410, the trajectory of device B is sorted by time. For example, device B is a MAC acquisition device (or camera device). Acquire the acquisition data of device B within a certain time period (such as 1 day, 1 hour, or other duration). The acquisition data within this time period includes multiple MAC addresses. Of course, the acquisition data includes the acquisition time when each MAC address is acquired.

[0088] S412, define the set index y = 0, and define the set index y1 = 0; for example, if device B collects a total of 200 data points within a certain time period, that is, the data set of device B contains a total of 200 data points, then the index y ranges from 0 to 199, and the index y1 ranges from 0 to 199; in practical applications, each data point has a recorded collection time (or shooting time);

[0089] S414, determine if y is out of bounds;

[0090] S416, if it is determined that y has not exceeded the boundary, obtain the trajectory where the index y is located; obtain the collected data corresponding to the index y;

[0091] S418, compare the data collection time corresponding to index x with the data collection time corresponding to index y;

[0092] It should be noted that the above steps S410-S416 can also be performed simultaneously with S402-S408, or step S410 can be performed before S402.

[0093] S420, when the trajectory time of device A is greater than that of device B and exceeds the time difference threshold, it does not constitute an association. For example, if the time difference threshold is 1 minute (or 5 seconds, or other time difference values), and the acquisition time (or shooting time, such as 10:05) of the data corresponding to index x is greater than the acquisition time of the data corresponding to index y (such as 10:02), the time difference between the two is 3 minutes, which exceeds the time difference threshold (such as 1 minute as mentioned above). In this case, it can be determined that the data corresponding to index x and the data corresponding to index y do not constitute an association relationship.

[0094] S422, the index y1 of device B = y1+1; that is, take the acquisition time of the next data from the data set of device B, and proceed to step S426.

[0095] S424, when the time difference between the trajectory of device A and the trajectory of device B is within a threshold (such as 1 minute as mentioned above), they are considered to be associated. For example, if the data collection time corresponding to index x is 10:05, and the data collection time corresponding to index y is within the range of [10:04, 10:06], that is, when the time difference between the trajectory of device A and the trajectory of device B is within the threshold, it can be preliminarily determined that the data corresponding to index x and the data corresponding to index y are associated; and proceed to step S426, and execute step S428.

[0096] Step S424 is equivalent to initially determining the personnel corresponding to index x (e.g., P). x ) and the MAC address corresponding to the index y (e.g., MAC address) y This constitutes a symbiotic relationship, or a spatiotemporal symbiotic relationship, i.e., MAC. y The user of the corresponding terminal is likely person P. x ;

[0097] S426, the index y of device B is y + 1; that is, take the acquisition time of the next data from the data set of device B, and then return to step S414 for judgment;

[0098] S428, add the first relation data; that is, if it is determined that the data corresponding to index x and the data corresponding to index y form a companion relationship, then the first relation between the data corresponding to index x and the data corresponding to index y is established.

[0099] S430, when it is determined in step S414 above that y has exceeded the limit (for example, y has exceeded 199), step S430 is entered to determine that the data corresponding to index x and the data corresponding to index y do not constitute a pair. At this time, the first loop is reset, that is, the index in the data set of device A is reset.

[0100] It should also be noted that when, based on the comparison results in step S418 above, it is determined that the trajectory time of device A is less than that of device B and exceeds the time difference threshold, step S430 is also entered, that is, it is determined that there is no accompanying relationship and the first loop is reset; for example, if the acquisition time (or shooting time, such as 10:05) of the data corresponding to index x is less than the acquisition time of the data corresponding to index y (such as 10:10), and the time difference between the two is 5 minutes, which exceeds the time difference threshold (such as 1 minute above), then it can be determined that the data corresponding to index x and the data corresponding to index y do not constitute an accompanying relationship;

[0101] S432, the index x of device A = x + 1; that is, take the acquisition time corresponding to the next data from the data set of device A, and return to step S406;

[0102] S434, the index y of device B is y1; that is, take the data corresponding to the index y1 from the data set of device B, and then continue to return to step S414 for judgment;

[0103] To explain step S434, for example, in the previous loop, when comparing the acquisition time of the data corresponding to index x = s with the acquisition time of the data in the data set of device B, it is determined that index y1 = t (here referring to the value of y1 after executing y1 = y1 + 1, such as 20). That is, the acquisition time of the data in the data set of device B with indices between 0 and y1 is earlier than the acquisition time of the data corresponding to index x = s in the data set of device A, and the difference between the acquisition time of the data corresponding to index x = s and the acquisition time of the data corresponding to index y1 = t is greater than the time difference threshold (such as 1 minute as mentioned above). If the difference between the data collection time of the data and the data collection time corresponding to the index y1=t+1 is less than or equal to the time difference threshold, then in the next loop comparison (i.e. x=s+1), that is, when comparing the data collection time of the data corresponding to the index x=s+1 with the data collection time of the data in the data set of device B, it is not necessary to start from the beginning. That is, it is not necessary to start the comparison from the data collection time corresponding to the data with the index y=0 in the data set of device B. Instead, it can start from y=y1=t (as in 20 above), that is, start from the index y=t and compare the data collection time of the corresponding data with the data collection time corresponding to the index x=s+1 respectively.

[0104] In this embodiment, the method performs a double loop within the set of trajectory A and trajectory B, and the starting point of the second loop is variable instead of starting from the beginning, which greatly reduces the number of comparisons and improves the efficiency of the comparison at this point.

[0105] It should be noted that in the process of binding personnel to MAC addresses, there are many shooting devices (i.e., personnel collection devices) and MAC collection devices involved. Among them, there may be multiple pairs of shooting devices and MAC collection devices that form a binding relationship. For example, according to the above step S306, a binding relationship can be established between the two types of devices. In this way, for multiple pairs of devices with binding relationships, the data corresponding to the personnel and MAC addresses that meet the first relationship can be initially determined by the methods in steps S402 to S434 above.

[0106] S310: Deduplication process to obtain the first relation

[0107] The first set of relationship data is obtained through step S308. In practical applications, the correspondence between personnel and MAC addresses can be initially determined through multiple sets of device pairs with binding relationships. For example, device A and device B are a pair, and device A' and device B' are also a pair. If personnel P is initially determined from multiple pairs of device pairs... x With MAC address y If a pairing relationship exists, then deduplication can be performed, meaning that only the P derived from one set of device pairs needs to be considered. x With MAC y To obtain the first relationship, you only need to consider the accompanying relationship.

[0108] In steps S308-S310 above, the first relationship is calculated using time association.

[0109] Step S312: Trajectory Merging

[0110] Step S308 retrieves accompanying details. These details are then used to obtain the trajectories of the person and the MAC address across all devices. The trajectories are then merged. Figure 5 As shown, Figure 5 This is an example diagram of trajectory merging according to a specific embodiment of the present invention, such as... Figure 5 The system merges the "Zhang San" and "B0-**-**-**-**-50" trajectories collected by different devices (including camera devices and MAC acquisition devices); sorts the merged trajectories by time, and calculates speed by converting adjacent distances, i.e., converting speed (such as the movement speed of a person or MAC) to the distance between two adjacent points in the trajectory. For example, it calculates the time difference between adjacent time points and the Euclidean distance between devices at adjacent time points to obtain the speed. Figure 6 This is an example diagram of speed conversion according to a specific embodiment of the present invention. Figure 6 The table below shows the conversion of MAC or human movement speed.

[0111] Step S314: Calculate the second relation

[0112] The trajectories merged in step S312 are grouped according to the same relationship, sorted by time within each group, and the time difference is calculated based on adjacent time points. Euclidean distance is calculated from adjacent time points to determine the speed. If the speed exceeds a threshold, the first relationship is deemed invalid and the track is discarded. For example, based on... Figure 6 The calculated speed, when it is determined that the speed exceeds the threshold (such as 200km / h), can be judged that the first relationship is not valid, such as the first relationship between "Zhang San" and "B0-**-**-**-**-50" mentioned above is not valid.

[0113] In the above embodiments, the introduction of a segmentation method based on time periods plus a time difference threshold increases the sorting cost of trajectories under the same bound device and improves the stability of the calculation. At the same time, a double loop is introduced, and the index is initialized at the beginning of the second loop, which improves the efficiency of time-related calculation. In addition, the adjacent velocities of the fused trajectories are calculated by merging trajectories, and the relationship of the fusion is verified twice.

[0114] Through the above embodiments, person and MAC data are bound by device physical distance and collection time. The result data is normalized by person profile, MAC terminal, and time and space dimensions to infer the user's identity information from the MAC. This embodiment proposes a non-mobile device determination standard to avoid interference when processing peers. This embodiment also proposes a method for determining peer standards for different data sources. This embodiment determines a binding relationship through spatiotemporal accompaniment, optimizes the algorithm to improve stability and efficiency, and performs velocity-based verification after merging trajectories to improve the accuracy of relationship determination.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0116] This embodiment also provides a device for determining the binding relationship. Figure 7 This is a structural block diagram of a binding relationship determination device according to an embodiment of the present invention, such as... Figure 7 As shown, the device includes:

[0117] The first acquisition module 702 is used to acquire first trajectory information of a first MAC address and second trajectory information of a first portrait. The first trajectory information includes the acquisition time of the first MAC address acquired by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices. The second trajectory information includes the shooting time of the first portrait captured by a group of shooting devices and the location information or identification information of the group of shooting devices.

[0118] The first determining module 704 is used to determine whether there is a temporal and spatial relationship between the first MAC address and the first portrait based on the first trajectory information and the second trajectory information.

[0119] The module 706 is used to establish a binding relationship between the first MAC address and the first image when it is determined that the first MAC address and the first image have a temporal and spatial relationship.

[0120] In an optional embodiment, the first determining module 704 includes: a first searching submodule, configured to search for a pair of devices that match in time and space among the group of MAC acquisition devices and the group of shooting devices based on the first trajectory information and the second trajectory information, to obtain a target search result, wherein each device pair includes a MAC acquisition device and a shooting device, and a pair of devices that match in time and space means that the distance between the MAC acquisition device and the shooting device in the device pair is less than or equal to a preset distance threshold, and the time interval between the acquisition time of the first MAC address acquired by the MAC acquisition device in the device pair and the shooting time of the first image captured by the shooting device in the device pair is less than or equal to a first preset time threshold; the first determining submodule is configured to determine whether there is a temporal and spatial relationship between the first MAC address and the first image based on the target search result.

[0121] In an optional embodiment, the above-mentioned search submodule includes: a first determining unit, configured to, when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the location information of the group of MAC acquisition devices, and the second trajectory information includes the capture time of the first image captured by the group of shooting devices and the location information of the group of shooting devices, determine the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the capture time of the first image captured by the j-th shooting device, and ... based on the location information of the i-th MAC acquisition device and the location information of the j-th shooting device. The location information of the camera devices is used to determine the current distance between the i-th MAC acquisition device and the j-th shooting device. The group of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2 ≤ i ≤ N. The group of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2 ≤ j ≤ M. The second determining unit is used to determine the i-th MAC acquisition device and the j-th shooting device as the found device pair that matches in time and space when the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold.

[0122] In an optional embodiment, the above-mentioned search submodule includes: a third determining unit, configured to, when the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first image captured by the group of shooting devices and the identification information of the group of shooting devices, determine the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first image captured by the j-th shooting device, and determine whether the current time interval is less than or equal to the first preset time threshold; a fourth determining unit, configured to, based on the i-th MAC acquisition device The identification information and the identification information of the j-th shooting device are used to determine whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. The set of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2 ≤ i ≤ N. The set of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2 ≤ j ≤ M. The fifth determining unit is used to determine the i-th MAC acquisition device and the j-th shooting device as the found device pair that matches in time and space when the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold.

[0123] In an optional embodiment, the fourth determining unit includes: a searching subunit, configured to search in a pre-established binding relationship set whether the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device have a binding relationship, wherein the binding relationship set includes the binding relationship between the identification information of MAC acquisition devices in the MAC acquisition device set and the identification information of shooting devices in the shooting device set, the binding relationship in the binding relationship set indicates that the distance between the MAC acquisition device and the shooting device corresponding to the binding relationship is less than or equal to the preset distance threshold, the MAC acquisition device set includes the group of MAC acquisition devices, and the shooting device set includes the group of shooting devices; and a determining subunit, configured to determine that the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold when the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device are found to have a binding relationship.

[0124] In an optional embodiment, the first determining submodule includes: a sixth determining unit, configured to determine that the first MAC address and the first image have a temporal and spatial association when the target search result indicates that the number of time-space matching device pairs found is greater than or equal to a preset number threshold; or a seventh determining unit, configured to determine that the first MAC address and the first image have a temporal and spatial association when the target search result indicates that both a first proportion and a second proportion are greater than or equal to a preset proportion threshold, wherein the first proportion is the ratio between the number of time-space matching device pairs found and the number of MAC acquisition devices in the group of MAC acquisition devices, and the second proportion is the ratio between the number of time-space matching device pairs found and the number of shooting devices in the group of shooting devices.

[0125] In an optional embodiment, the above apparatus further includes: a merging module, configured to merge the first trajectory information and the second trajectory information after establishing the binding relationship between the first MAC address and the first image, and sort each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, wherein each record item in the combined trajectory information includes the acquisition time of the first MAC address acquired by a MAC acquisition device and the location information or identification information of the MAC acquisition device, or includes the shooting time of the first image captured by a shooting device and the location information or identification information of the shooting device; and a second determining module, configured to determine that the binding relationship between the first MAC address and the first image passes the verification when it is determined that every two adjacent record items in the combined trajectory information meet a predetermined speed condition.

[0126] In an optional embodiment, the above apparatus further includes: a second acquisition module, configured to, after merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, acquire adjacent first record items and second record items in the combined trajectory information, wherein the first record item corresponds to a first device, a first time parameter, and a first position parameter, and the second record item corresponds to a second device, a second time parameter, and a second position parameter; a third determination module, configured to determine the time interval between moving from the first device to the second device based on the first time parameter and the second time parameter; a fourth determination module, configured to determine the distance between the first device and the second device based on the first position parameter and the second position parameter; a fifth determination module, configured to determine the moving speed from the first device to the second device as equal to the ratio of the distance to the time interval; and a sixth determination module, configured to determine that, if the moving speed is greater than a predetermined speed threshold, adjacent first record items and second record items do not meet the predetermined speed threshold. The predetermined speed condition is described; if the moving speed is less than or equal to the predetermined speed threshold, adjacent first and second record items are determined to satisfy the predetermined speed condition; wherein, the first device is a first MAC acquisition device, the first time parameter is the acquisition time when the first MAC acquisition device acquires the first MAC address, and the first position parameter is the position information or identification information of the first MAC acquisition device; or, the first device is a first shooting device, the first time parameter is the shooting time when the first shooting device captures the first image, and the first position parameter is the position information or identification information of the first shooting device; wherein, the second device is a second MAC acquisition device, the second time parameter is the acquisition time when the second MAC acquisition device acquires the first MAC address, and the second position parameter is the position information or identification information of the second MAC acquisition device; or, the second device is a second shooting device, the second time parameter is the shooting time when the second shooting device captures the first image, and the second position parameter is the position information or identification information of the second shooting device.

[0127] In an optional embodiment, the first determining module 704 includes: a first dividing submodule, configured to divide the first trajectory information into P first sub-trajectory information according to the different time segments to which the acquisition time corresponding to each record item in the first trajectory information belongs, wherein each of the P first sub-trajectory information corresponds to a different time segment, and P is a positive integer greater than or equal to 2; and a second dividing submodule, configured to divide the second trajectory information into Q second sub-trajectory information according to the different time segments to which the shooting time corresponding to each record item in the second trajectory information belongs, wherein each of the Q second sub-trajectory information corresponds to a different time segment, and Q is a positive integer greater than or equal to 2. A positive integer greater than or equal to 2; a second search submodule, used to search for pairs of sub-trajectory information corresponding to the same time segment among the P first sub-trajectory information and the Q second sub-trajectory information, to obtain a total of M pairs of sub-trajectory information corresponding to M time segments, wherein each pair of sub-trajectory information includes first sub-trajectory information and second sub-trajectory information corresponding to the same time segment, M is less than or equal to P and less than or equal to Q; a second determination submodule, used to determine that the first MAC address and the first image have a temporal and spatial accompaniment relationship when M is greater than or equal to a preset threshold and the first MAC address and the first image are determined to have a temporal and spatial accompaniment relationship according to the M pairs of sub-trajectory information.

[0128] In an optional embodiment, the first acquisition module 702 includes: a first acquisition submodule, configured to acquire first recording information from a target MAC acquisition device, wherein each record item in the first recording information represents a corresponding MAC address acquired by the target MAC acquisition device during a set of acquisition times, the first recording information includes a first target record item, the first target record item including the first MAC address and the target acquisition time of the first MAC address acquired by the target MAC acquisition device; a second acquisition submodule, configured to acquire second recording information from a target shooting device, wherein each record item in the second recording information represents a corresponding portrait captured by the target shooting device during a set of shooting times, the second recording information includes a second target record item, the second target record item including the first portrait and the target shooting time of the first portrait captured by the target shooting device, and the distance between the target shooting device and the target MAC acquisition device is less than or equal to a second preset distance threshold; and a third acquisition submodule, configured to acquire the first trajectory information and the second trajectory information when it is determined that the time interval between the target acquisition time and the target shooting time is less than or equal to a second preset time threshold.

[0129] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0130] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0131] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0132] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0133] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0134] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0135] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0136] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining a binding relationship, characterized in that, include: The system acquires first trajectory information of a first MAC address and second trajectory information of a first human image. The first trajectory information includes the acquisition time of the first MAC address acquired by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices. The second trajectory information includes the shooting time of the first human image captured by a group of shooting devices and the location information or identification information of the group of shooting devices. Based on the first trajectory information and the second trajectory information, determine whether there is a temporal and spatial relationship between the first MAC address and the first portrait; If it is determined that the first MAC address and the first image have a temporal and spatial relationship, a binding relationship between the first MAC address and the first image is established. The method further includes, after establishing the binding relationship between the first MAC address and the first image, merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the order of the acquisition time and the shooting time to obtain combined trajectory information. Each record item in the combined trajectory information includes the acquisition time of the first MAC address acquired by a MAC acquisition device and the location information or identification information of the MAC acquisition device, or the shooting time of the first image captured by a shooting device and the location information or identification information of the shooting device. If it is determined that every two adjacent record items in the combined trajectory information meet the predetermined speed condition, the binding relationship between the first MAC address and the first image is verified.

2. The method according to claim 1, characterized in that, The step of determining whether there is a temporal and spatial correlation between the first MAC address and the first image based on the first trajectory information and the second trajectory information includes: Based on the first trajectory information and the second trajectory information, a device pair that matches in time and space is searched in the group of MAC acquisition devices and the group of shooting devices to obtain the target search result. Each device pair includes a MAC acquisition device and a shooting device. A device pair that matches in time and space means that the distance between the MAC acquisition device and the shooting device in the device pair is less than or equal to a preset distance threshold, and the time interval between the acquisition time of the first MAC address by the MAC acquisition device in the device pair and the shooting time of the first portrait by the shooting device in the device pair is less than or equal to a first preset time threshold. Based on the target search results, determine whether there is a temporal and spatial relationship between the first MAC address and the first portrait.

3. The method according to claim 2, characterized in that, The step of searching for a matching device pair in time and space among the set of MAC acquisition devices and the set of shooting devices based on the first trajectory information and the second trajectory information includes: Given that the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the location information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first portrait captured by the group of shooting devices and the location information of the group of shooting devices, the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first portrait captured by the j-th shooting device is determined, and the current distance between the i-th MAC acquisition device and the j-th shooting device is determined based on the location information of the i-th MAC acquisition device and the location information of the j-th shooting device. The group of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2 ≤ i ≤ N; the group of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2 ≤ j ≤ M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space.

4. The method according to claim 2, characterized in that, The step of searching for a matching device pair in time and space among the set of MAC acquisition devices and the set of shooting devices based on the first trajectory information and the second trajectory information includes: When the first trajectory information includes the acquisition time of the first MAC address acquired by the group of MAC acquisition devices and the identification information of the group of MAC acquisition devices, and the second trajectory information includes the shooting time of the first portrait captured by the group of shooting devices and the identification information of the group of shooting devices, the current time interval between the acquisition time of the first MAC address acquired by the i-th MAC acquisition device and the shooting time of the first portrait captured by the j-th shooting device is determined, and it is determined whether the current time interval is less than or equal to the first preset time threshold. Based on the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device, determine whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold. The group of MAC acquisition devices includes N MAC acquisition devices, where N is a positive integer greater than or equal to 2, and 2≤i≤N. The group of shooting devices includes M shooting devices, where M is a positive integer greater than or equal to 2, and 2≤j≤M. If the current distance is less than or equal to the preset distance threshold and the current time interval is less than or equal to the first preset time threshold, the i-th MAC acquisition device and the j-th shooting device are identified as the found device pair that matches in time and space.

5. The method according to claim 4, characterized in that, The step of determining whether the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold based on the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device includes: In a pre-established set of binding relationships, it is searched to determine whether the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device have a binding relationship. The binding relationship set includes the binding relationship between the identification information of MAC acquisition devices in the MAC acquisition device set and the identification information of shooting devices in the shooting device set. The binding relationship in the binding relationship set indicates that the distance between the MAC acquisition device and the shooting device corresponding to the binding relationship is less than or equal to the preset distance threshold. The MAC acquisition device set includes the group of MAC acquisition devices, and the shooting device set includes the group of shooting devices. If a binding relationship is found between the identification information of the i-th MAC acquisition device and the identification information of the j-th shooting device, it is determined that the current distance between the i-th MAC acquisition device and the j-th shooting device is less than or equal to the preset distance threshold.

6. The method according to claim 2, characterized in that, The step of determining whether there is a temporal and spatial correlation between the first MAC address and the first image based on the target search result includes: If the target search result indicates that the number of device pairs that match in time and space is greater than or equal to a preset threshold, it is determined that the first MAC address and the first image have a temporal and spatial correlation; or If the target search result indicates that both the first proportion and the second proportion are greater than or equal to a preset proportion threshold, it is determined that the first MAC address and the first image have a temporal and spatial relationship. The first proportion is the ratio between the number of time-space matching device pairs found and the number of MAC acquisition devices in the group of MAC acquisition devices, and the second proportion is the ratio between the number of time-space matching device pairs found and the number of shooting devices in the group of shooting devices.

7. The method according to claim 1, characterized in that, After merging the first trajectory information and the second trajectory information, and sorting each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, the method further includes: In the combined trajectory information, adjacent first and second record items are obtained, wherein the first record item corresponds to the first device, the first time parameter, and the first position parameter, and the second record item corresponds to the second device, the second time parameter, and the second position parameter; Based on the first time parameter and the second time parameter, determine the duration of the movement from the first device to the second device; The distance between the first device and the second device is determined based on the first position parameter and the second position parameter; The moving speed from the first device to the second device is determined to be equal to the ratio of the distance to the duration. If the moving speed is greater than a predetermined speed threshold, it is determined that the adjacent first record item and the second record item do not meet the predetermined speed condition; if the moving speed is less than or equal to the predetermined speed threshold, it is determined that the adjacent first record item and the second record item meet the predetermined speed condition. Wherein, the first device is a first MAC acquisition device, the first time parameter is the acquisition time when the first MAC acquisition device acquires the first MAC address, and the first location parameter is the location information or identification information of the first MAC acquisition device; or, the first device is a first shooting device, the first time parameter is the shooting time when the first shooting device captures the first human image, and the first location parameter is the location information or identification information of the first shooting device; Wherein, the second device is a second MAC acquisition device, the second time parameter is the acquisition time when the second MAC acquisition device acquires the first MAC address, and the second location parameter is the location information or identification information of the second MAC acquisition device; or, the second device is a second shooting device, the second time parameter is the shooting time when the second shooting device captures the first image, and the second location parameter is the location information or identification information of the second shooting device.

8. The method according to claim 1, characterized in that, The step of determining whether there is a temporal and spatial correlation between the first MAC address and the first image based on the first trajectory information and the second trajectory information includes: According to the different time segments to which the collection time belongs for each record item in the first trajectory information, the first trajectory information is divided into P first sub-trajectory information, wherein each of the P first sub-trajectory information corresponds to a different time segment, and P is a positive integer greater than or equal to 2. According to the different time segments to which the shooting time belongs to each record item in the second trajectory information, the second trajectory information is divided into Q second sub-trajectory information, wherein each of the Q second sub-trajectory information corresponds to a different time segment, and Q is a positive integer greater than or equal to 2; Search for pairs of sub-trajectory information corresponding to the same time segment among the P first sub-trajectory information and the Q second sub-trajectory information, and obtain a total of M pairs of sub-trajectory information corresponding to M time segments. Each pair of sub-trajectory information includes first sub-trajectory information and second sub-trajectory information corresponding to the same time segment, where M is less than or equal to P and less than or equal to Q. If M is greater than or equal to a preset threshold, and the M sub-trajectory information indicates that the first MAC address and the first portrait have a temporal and spatial relationship in the M time periods, then the first MAC address and the first portrait have a temporal and spatial relationship.

9. The method according to any one of claims 1 to 8, characterized in that, The acquisition of the first trajectory information of the first MAC address and the second trajectory information of the first portrait includes: Obtain first record information from the target MAC acquisition device, wherein each record item in the first record information is used to represent the corresponding MAC address acquired by the target MAC acquisition device in a set of acquisition times, the first record information includes a first target record item, the first target record item includes the first MAC address and the target acquisition time when the target MAC acquisition device acquired the first MAC address; Acquire second recording information from the target shooting device, wherein each recording item in the second recording information is used to represent the corresponding human image captured by the target shooting device in a set of shooting times, the second recording information includes a second target recording item, the second target recording item includes the first human image and the target shooting time when the target shooting device captured the first human image, and the distance between the target shooting device and the target MAC acquisition device is less than or equal to a second preset distance threshold. If the time interval between the target acquisition time and the target shooting time is less than or equal to a second preset time threshold, the first trajectory information and the second trajectory information are acquired.

10. A device for determining a binding relationship, characterized in that, include: The first acquisition module is used to acquire first trajectory information of a first MAC address and second trajectory information of a first portrait. The first trajectory information includes the acquisition time of the first MAC address acquired by a group of MAC acquisition devices and the location information or identification information of the group of MAC acquisition devices. The second trajectory information includes the shooting time of the first portrait captured by a group of shooting devices and the location information or identification information of the group of shooting devices. The first determining module is used to determine whether there is a temporal and spatial relationship between the first MAC address and the first portrait based on the first trajectory information and the second trajectory information. A module is established to establish a binding relationship between the first MAC address and the first image when it is determined that the first MAC address and the first image have a temporal and spatial relationship. The device further includes: a merging module, configured to merge the first trajectory information and the second trajectory information after establishing the binding relationship between the first MAC address and the first image, and sort each record item in the merged trajectory information according to the chronological order of the acquisition time and the shooting time to obtain combined trajectory information, wherein each record item in the combined trajectory information includes the acquisition time of the first MAC address acquired by a MAC acquisition device and the location information or identification information of the MAC acquisition device, or includes the shooting time of the first image captured by a shooting device and the location information or identification information of the shooting device; and a second determining module, configured to determine that the binding relationship between the first MAC address and the first image passes the verification when it is determined that every two adjacent record items in the combined trajectory information meet the predetermined speed condition.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 9.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 9.

Images