Information association method, electronic device, and storage medium

Abstract

The application discloses an information association method, an electronic device and a computer readable storage medium. The method comprises the following steps: determining a target human body in a to-be-processed image, the to-be-processed image being an image collected by a target number taking machine at a target time; determining whether the target human body implements a number taking behavior on the target number taking machine based on the action of the target human body; and in response to the target human body implementing the number taking behavior on the target number taking machine, associating the target human body with number taking information generated by the target number taking machine within an association time period at the target time. Through the above method, the human body (number taking personnel) corresponding to the number taking information can be determined, the management of the number taking personnel in the subsequent queuing process is facilitated, and the service quality and efficiency for a single number taking personnel are improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an information association method, electronic device, and computer-readable storage medium. Background Technology

[0002] In service establishments such as banks, hospitals, and commercial shops, visitors are often arranged to take a number and queue according to the order of the number. Then, the calling system calls each visitor in order of their number to provide services to each visitor.

[0003] While this queuing system maintains order, the experience for individual visitors remains poor. For example, if a visitor fails to respond due to various factors (such as not hearing the notification, leaving the service area, etc.), and the queuing system waits for a period without response, it will notify the next visitor. Consequently, the first visitor cannot receive service according to their assigned number. Therefore, to improve service quality and efficiency, a method for managing those queuing for numbers is urgently needed. Summary of the Invention

[0004] This application provides an information association method, an electronic device, and a computer-readable storage medium that enable the management of people taking numbers during the queuing process.

[0005] To address the aforementioned technical problems, this application provides a technical solution: an information association method. This method includes: identifying a target human body in an image to be processed, wherein the image to be processed is an image captured at a target time for an area associated with a target ticket dispenser; determining whether the target human body is performing a ticket-taking action at the target ticket dispenser based on the target human body's actions; and, in response to the target human body performing a ticket-taking action at the target ticket dispenser, associating the ticket-taking information generated by the target human body and the target ticket dispenser within the associated time period at the target time.

[0006] To solve the above-mentioned technical problems, another technical solution adopted in this application is: to provide an electronic device, which includes a processor and a memory connected to the processor, wherein the memory stores program instructions; the processor is used to execute the program instructions stored in the memory to implement the above-mentioned method.

[0007] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a computer-readable storage medium storing program instructions that, when executed, can implement the above-mentioned method.

[0008] Through the above method, this application acquires an image to be processed; identifies the target human body in the image; determines whether the target human body is taking a number at the target ticket dispenser based on the target human body's actions; and, in response to the target human body taking a number at the target ticket dispenser, associates the ticket information generated by the target human body and the target ticket dispenser within the associated time period at the target time. Thus, this application acquires an image to be processed from the application location, analyzes the image, and associates the human body of the person taking a number with their ticket information based on the analysis results. Therefore, based on the association, the person taking a number corresponding to the ticket information can be clearly identified, facilitating the management of people taking numbers during subsequent queuing processes and improving the service quality and efficiency for individual people taking numbers. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating an embodiment of the information association method of this application;

[0010] Figure 2 This is a flowchart illustrating another embodiment of the information association method of this application;

[0011] Figure 3 yes Figure 2 A detailed flowchart of the S21 process;

[0012] Figure 4 This is a schematic diagram of the first video frame;

[0013] Figure 5 This is a schematic diagram of the second video frame;

[0014] Figure 6 This is a flowchart illustrating a specific example of the information association method.

[0015] Figure 7 This is another schematic diagram of the first video frame;

[0016] Figure 8 This is a schematic diagram of the structure of an embodiment of the electronic device of this application;

[0017] Figure 9 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0019] The terms "first," "second," and "third" used in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments without conflict.

[0021] Before introducing the information association method provided in this application, let's briefly introduce the overall technical approach:

[0022] The application site is equipped with a target ticket dispenser, which provides a user interface. When a target visitor needs to obtain a ticket at the application site, they can do so through the user interface on the target ticket dispenser, which then generates a ticket number in response.

[0023] The application site is equipped with cameras, which can be fisheye cameras or other types. Compared to other cameras, fisheye cameras have a wider field of view, are easier to install, and have lower deployment costs. The camera's field of view covers the area associated with the target ticket dispenser. This area includes the area where the ticket dispenser is located and the surrounding area of ​​the side of the ticket dispenser with its user interface. Alternatively, the area associated with the ticket dispenser may include the surrounding area of ​​the side of the ticket dispenser with its user interface. In the former case, the image to be processed includes both the target human body and the ticket dispenser; in the latter case, the image to be processed includes the target human body but not the ticket dispenser. The camera's installation angle allows for monitoring of ticket dispensing behavior within the area associated with the ticket dispenser, thereby establishing a link between ticket dispensing information and the target human body.

[0024] The information association method provided in this application is described in detail below:

[0025] Figure 1 This is a flowchart illustrating one embodiment of the information association method of this application. It should be noted that if substantially the same result is achieved, this embodiment does not necessarily reflect that outcome. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, this embodiment may include:

[0026] S11: Identify the target human body in the image to be processed.

[0027] The image to be processed is an image captured at the target time for the area associated with the target ticket dispenser.

[0028] A camera can be used to acquire video streams of the area associated with the target ticket dispenser. The image to be processed can be a video frame from a historical moment in the video stream, or the most recent video frame, i.e., the current frame. In this step, the video stream can be continuously acquired via the camera during the monitoring period. Alternatively, the video stream can be continuously acquired via the camera when the target ticket dispenser receives an operation command from the user interface. It's understood that when a visitor needs to obtain a ticket, they will operate the ticket dispenser using buttons, touch, or other methods. Upon receiving the operation command, the ticket dispenser indicates that the visitor has started obtaining a ticket, and then informs the camera, "A visitor has started obtaining a ticket," and the camera begins acquiring video data. This saves computing resources.

[0029] The camera's perspective allows observation of the positional relationship between the target person and the ticket dispenser, as well as the target person's movements. In other words, the image acquired from the camera's perspective can be used to determine the positional relationship between the target person and the ticket dispenser, and to determine the target person's movements. For example, the camera can be installed at the top of the application area to capture images of the target person and the ticket dispenser from a top-down perspective. Alternatively, the camera can be installed to the side of the target person and the ticket dispenser to capture images from a left-to-right or right-to-left perspective.

[0030] The target human body can be identified through object detection (including but not limited to the SSD YOLO algorithm) or object segmentation. Specifically, object detection can be performed on the image to obtain bounding boxes indicating the location of the target human body, and the region corresponding to these bounding boxes can be considered the target human body. Alternatively, object segmentation can be performed on the image to obtain the pixels that belong to the target human body, and the region consisting of these pixels can be considered the target human body.

[0031] S12: Determine whether the target human body is taking a number at the target ticket machine based on the target human body's actions.

[0032] For a target human to take a number at the target ticket machine, conditions 1 and 2 must be met. Condition 1 is that the positional relationship between the target human and the target ticket machine meets the preset positional requirements (i.e., the target human is close to the target ticket machine). Condition 2 is that the target human's action meets the preset action requirements (i.e., the target human's action is a ticket taking action).

[0033] There is no specific order in which conditions 1 and 2 are evaluated. That is, conditions 1 and 2 can be evaluated simultaneously. Alternatively, conditions 1 can be evaluated first, and if condition 1 is satisfied, then condition 2 can be evaluated. Or, conditions 2 can be evaluated first, and if condition 2 is satisfied, then condition 1 can be evaluated.

[0034] In some embodiments, in addition to satisfying conditions 1 and 2, the target person's act of taking a number at the ticket dispenser also needs to satisfy condition 3. Condition 3 is that the target ticket dispenser generates ticket information within a first preset time period after conditions 1 and 2 are satisfied. This first preset time period can be set according to the normal time required for ticket taking. Therefore, the probability that subsequent ticket information associated with the target person is generated by the target person taking a number at the target ticket dispenser can be increased.

[0035] If the target person takes a number at the target ticket machine, then execute S13; otherwise, execute S14.

[0036] S13: Associate the queuing information generated by the target human body and the target queuing machine within the associated time period at the target time.

[0037] The associated time period may include a time period from the target time to a second preset duration after the target time. Alternatively, the associated time period may include a time period of a first preset duration after conditions 1 and 2 are satisfied. Specifically, if condition 1 is judged first and then condition 2 is judged, the associated time period may include a time period of a first preset duration after conditions 2 are satisfied; if condition 2 is judged first and then condition 1 is judged, the associated time period may include a time period of a first preset duration after conditions 1 are satisfied.

[0038] If S12 involves determining whether condition 3 is met, this step can directly associate the target human body with the number retrieval information. If S12 does not involve determining whether condition 3 is met, this step can first determine whether condition 3 is met, and if so, associate the target human body with the number retrieval information.

[0039] The queuing information may include the number, as well as the queuing time, the name of the person to whom the target person belongs, their level (such as ordinary person, VIP person, VVIP person), the type of service required, the assigned service window, and other service-related information.

[0040] The information included in the queuing system depends on the type of venue. In venues where visitor identity is not involved, such as bubble tea shops, the queuing information includes the number, the time of queuing, and the type and quantity of service requested (the type and quantity of drinks ordered). In venues where visitor identity is involved, such as banks and hospitals, the queuing information includes the number, the time of queuing, the name of the person queuing, the person's rank, and the assigned service window.

[0041] S14: Do not associate.

[0042] Through the implementation of this embodiment, this application acquires the image to be processed in the application location, analyzes the image, and associates the person taking a number with their number information based on the analysis results. Therefore, based on the association, the person taking a number corresponding to the number information can be clearly identified, facilitating the management of people taking numbers during the subsequent queuing process and improving the service quality and efficiency for individual people taking numbers.

[0043] Figure 2 This is a flowchart illustrating another embodiment of the information association method of this application. It should be noted that if substantially the same result is achieved, this embodiment does not necessarily reflect that outcome. Figure 2 The illustrated process sequence is limited. This embodiment is a further extension of S12, first determining whether condition 1 is satisfied, and then determining whether condition 2 is satisfied if condition 1 is satisfied. For example... Figure 2 As shown, this embodiment may include:

[0044] S21: Determine whether the positional relationship between the target human body and the target ticket dispenser meets the preset positional requirements (condition 1).

[0045] The target ticket dispenser is located in a fixed position at the application site. It can be pre-calibrated, thus the target ticket dispenser is known in this step. Alternatively, the target ticket dispenser can be obtained by performing target detection or segmentation on the image to be processed (applicable when the image to be processed includes the target ticket dispenser).

[0046] Based on the overlap between the overall or partial key points of the target human body and the target ticket dispenser, it can be determined whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements. The partial key points can be the key points of the parts of the target human body that may come into contact with the target ticket dispenser (such as the arms or legs) when the target human body performs the ticket dispensing action.

[0047] Taking the image to be processed, including the target ticket dispenser, as an example, in conjunction with the reference... Figure 3 S21 may include the following sub-steps:

[0048] S211: Perform key point detection on the target human body.

[0049] Keypoint detection algorithms include, but are not limited to, OpenPose and AlphaPose.

[0050] S212: Based on the distribution information of each detected key point in the image area of ​​the ticket dispenser, determine whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements.

[0051] The image area of ​​the ticket dispenser is the image area corresponding to the target ticket dispenser in the image to be processed.

[0052] It can determine the total number of detected key points; and determine the number of sub-key points distributed in the image area of ​​the ticket dispenser among the detected key points; and determine that the positional relationship meets the positional requirements if the ratio of the sub-key points to the total key points is greater than or equal to a preset ratio threshold.

[0053] If the positional relationship meets the positional requirements, then execute S22; otherwise, execute S25.

[0054] S22: Acquire the target human body's movements.

[0055] The target body's movements involve parts of the body related to the act of taking a number, such as the head and arms. Accordingly, the target body's movements can include head movements and arm movements.

[0056] In some embodiments, a deep learning network can be used to classify the target human body to obtain its movements. For example, the target human body can be classified to obtain its arm movements and head movements.

[0057] In some embodiments, key points of the target human body can be acquired, and the target human body's actions can be determined based on these key points. If key points have already been acquired in S21, they can be reused here without being acquired again.

[0058] This can be achieved by calculating the angles of relevant body parts based on key points of the target human body, and determining the target human body's movement based on these angles. For example, if the target human body's movement involves the head, and the key points are associated with the head and torso, the forward tilt angle of the head can be calculated based on the key points of the head and the torso (the part between the neck and hips), and the head movement can be determined based on this forward tilt angle. If the forward tilt angle is greater than a threshold, the head movement is determined to be a forward tilt. Similarly, if the target human body's movement involves the arm, and the key points are associated with the arm, the angle of upward bending of the arm can be determined based on the key points of the arm, and the arm movement is determined based on this upward bending angle. If the upward bending angle of the arm is greater than a threshold, the arm movement is determined to be an arm raise. Alternatively, a curve can be fitted to the target human body's body parts related to the number taking process based on the key points, and the target human body's movement can be determined based on this curve. For example, based on the key points of the arm, a curve of the arm can be fitted, and the arm curve can be matched with a preset arm raise curve. If the matching degree is greater than a threshold, the arm movement is determined to be an arm raise.

[0059] S23: Determine whether the target human body's movement meets the preset movement requirements (condition 2).

[0060] In some embodiments, the preset action requirements may include whether the target human body's action is a preset action (a number-taking action, such as raising an arm or tilting the head forward). In this case, if the arm action is raising an arm, then the arm action meets the preset action requirements. If the head action is tilting the head forward, then the head action meets the preset action requirements.

[0061] In some embodiments, considering that the target human's action is a number-taking action, which may not be caused by the number-taking behavior, to improve the accuracy of the judgment result, the preset action requirement may also include that the duration of the preset action is greater than a time threshold. The duration of the preset action can be measured by the number of subsequent video frames in which the preset action exists. Subsequent video frames are video frames that are after the image to be processed and adjacent to the image to be processed. The more subsequent video frames in which the preset action exists, the longer the duration of the preset action. For example, if the target human's action is an arm movement, it is determined whether the arm movement is raising the arm and whether the raising time is greater than a preset time threshold. If so, the target human's action is determined to meet the action requirement. Alternatively, if the target human's action is a head movement, and the head movement is tilting the head forward and the tilting time is greater than a preset time threshold, the target human's action is determined to meet the action requirement.

[0062] If the target human's movement meets the action requirements, then execute S24; otherwise, execute S25.

[0063] S24: It is determined that the target human body has performed the act of taking a number on the target number-taking machine.

[0064] In some embodiments, if the target person's action meets the action requirements, it can be directly determined that the target person performed a ticket-taking action at the target ticket-taking machine. In this case, before associating the target person with the ticket-taking information, it is necessary to first determine whether the target ticket-taking machine generated ticket-taking information within a first preset time period after the target person performed the ticket-taking action (condition 3). Only if ticket-taking information is generated can the target person be associated with the ticket-taking information. If no ticket-taking information is generated, it means that the ticket-taking action was misjudged, or that although the target person performed the ticket-taking action, the ticket-taking was not completed normally.

[0065] In some embodiments, within a first preset time period after determining that the target human's action meets the action requirements, it is determined whether the target ticket dispenser has generated ticket dispensing information; if ticket dispensing information has been generated, it is determined that the target human has performed the ticket dispensing action on the target ticket dispenser; otherwise, it is determined that no ticket dispensing action has been performed. In this case, it is not necessary to determine whether ticket dispensing information has been generated (condition 3), and the association between the target human and ticket dispensing information can be directly established.

[0066] S25: It is determined that the target person did not take a number.

[0067] The following two examples illustrate in detail the process of establishing a connection between a target human body and its identification number information.

[0068] Example 1: The ticket dispenser receives an operation command from the user interface and sends a ticket dispensing signal to the camera; in response to the ticket dispensing signal, the camera acquires an image to be processed; the target human body and the target ticket dispenser in the image to be processed are identified; it is determined whether the target human body is close to the target ticket dispenser and whether the target human body's action is a preset action; if so, it is determined that the target human body is performing a ticket dispensing action at the target ticket dispenser; it is determined whether the target ticket dispenser generates ticket dispensing information within a first preset time period after the target human body performs the ticket dispensing action; if ticket dispensing information is generated, the target human body is associated with the ticket dispensing information.

[0069] Example 2: Use a camera to acquire an image to be processed; identify the target human body and the target ticket dispenser in the image to be processed; determine whether the target human body is close to the target ticket dispenser and whether the target human body's action is a preset action; if so, determine whether the target ticket dispenser generates ticket information within the first preset time period after the target human body performs the ticket dispensing action; if ticket dispensing information is generated, associate the target human body with the ticket dispensing information.

[0070] Furthermore, based on any of the above embodiments, after establishing a link between the target human body and the ticket information, the relationship between the target human body and the ticket information can be visualized to further strengthen the management of each person taking a ticket during the queuing process, improve service efficiency, and facilitate people taking tickets to understand their queuing status in a timely manner. Specifically, this can be done as follows:

[0071] The image to be processed includes the first video frame from a video stream captured for the area associated with the target ticket dispenser. Hereinafter, video frames following the first video frame in the video stream will be referred to as second video frames.

[0072] In some embodiments, the target human body can be tracked in the second video frame of the video stream (achieved through algorithms such as Kalman filtering prediction), and queuing description information can be added to the target human body in the second video frame based on the associated queuing information. The queuing description information may include queuing information and waiting information. The waiting information may include the waiting time, the number of people waiting ahead, the estimated service time, location, stationary time, movement time, etc., and the waiting time is the difference between the capture time of the second video frame and the queuing time.

[0073] The following combination Figures 4-5 An example is given of adding descriptive information about the target human body in the second video frame. Figure 4 This is a schematic diagram of the first video frame. Figure 5 This is a schematic diagram of the second video frame. (For example...) Figures 4-5As shown, the tags for target human 1 in the first video frame include the ID of target human 1, and the tags for target human 1 in the second video frame include the ID, level, service type, and waiting time of target human 1.

[0074] In some embodiments, a second video frame containing added queuing description information can be pushed to a terminal associated with the target queuing machine. The type of terminal associated with the target queuing machine may depend on whether the queuing description information involves the privacy of the person taking the queuing ticket. If it involves the identity information of the person taking the queuing ticket, the terminal associated with the target queuing machine may be limited to the user terminal of the person taking the queuing ticket or the work terminal of the staff. If it does not involve the identity information of the person taking the queuing ticket, the terminal associated with the target queuing machine may also be other terminals installed in the application area for a reminder function (such as a lobby display screen). For example, the queuing description information may include pushing a second video frame containing the added queuing description information to the work terminal of the staff member corresponding to the service window. Furthermore, it can be displayed in a designated area of ​​the work terminal, allowing the staff member to promptly understand the status of the people queuing for queuing tickets. Alternatively, the queuing description information may include the service window, the number of people waiting ahead of that service window, and the estimated service time, and the second video frame containing the added queuing description information may be pushed to the lobby display screen.

[0075] In some embodiments, the information of the person who took a number and their corresponding description can be directly pushed to an authorized terminal. For example, the information of the person who took a number, their waiting time, the service window, the number of people waiting ahead of them at the service window, and the estimated service time can be displayed in a table on the lobby display screen.

[0076] In some embodiments, the target human body can be tracked in the second video frame to determine its positional relationship with the queuing system; in response to the target human body exceeding the queuing system's notification range, queuing notification information is pushed to the target human body's user terminal. Thus, even if the person taking a number exceeds the queuing system's notification range, they can be notified promptly, allowing them to stay informed about their queuing status in real time.

[0077] The following combination Figures 6-7 The information association method provided in this application will be described in detail with an example.

[0078] Example 3: Figure 6 This is a flowchart illustrating a specific example of the information association method, such as... Figure 6 As shown, the specific process is as follows:

[0079] 1) After acquiring the first video frame using a fisheye camera, perform human detection on the first video frame to obtain the target human body.

[0080] 2) Perform key point detection on the target human body to obtain the key points of the target human body.

[0081] 3) Perform motion recognition on the target human body based on key points. That is, determine whether the positional relationship between the target human body and the target ticket dispensing machine meets the positional requirements, and whether the target human body's motion meets the motion requirements based on key points; if so, associate the target human body with the target ticket dispensing machine.

[0082] Please refer to the example of the first video frame. Figure 7 ,like Figure 7 As shown, the first video frame includes three human figures (including target human figure 2) and target ticket dispenser 3. After the above process, the ticket dispensing information generated by target human figure 2 and target ticket dispenser 3 is associated.

[0083] 4) Track the target human body in the second video frame.

[0084] 5) Based on the tracking results, perform information statistics on the target human body to obtain the target human body's waiting information.

[0085] 6) Information Output. Based on the queuing and waiting information, descriptive information about the queuing process is added to the target person in the first video frame and then displayed. Staff can then provide assistance to those queuing based on the displayed information. For example, bank staff can intervene in advance for those waiting long or communicate with those handling complex transactions to encourage them to wait. This improves service quality.

[0086] Figure 8 This is a schematic diagram of the structure of an embodiment of the electronic device of this application. Figure 8 As shown, the electronic device includes a processor 21 and a memory 22 coupled to the processor 21.

[0087] The memory 22 stores program instructions for implementing the methods of any of the above embodiments; the processor 21 executes the program instructions stored in the memory 22 to implement the steps of the above method embodiments. The processor 21 may also be referred to as a CPU (Central Processing Unit). The processor 21 may be an integrated circuit chip with signal processing capabilities. The processor 21 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor may be a microprocessor or any conventional processor.

[0088] Figure 9 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application. Figure 9As shown, the computer-readable storage medium 30 of this application embodiment stores program instructions 31, which, when executed, implement the methods provided in the above embodiments of this application. The program instructions 31 can form a program file and be stored in the computer-readable storage medium 30 in the form of a software product, so that a computer device (which may be a personal computer, server, or network device, etc.) or processor can execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned computer-readable storage medium 30 includes various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or terminal devices such as computers, servers, mobile phones, and tablets.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0090] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An information association method, characterized in that, include: Identify the target human body in the image to be processed, wherein the image to be processed is an image captured at a specific time in the area associated with the target ticket dispenser; Determine whether the target human body meets the queuing conditions. The queuing conditions include that the positional relationship between the target human body and the target queuing machine meets the preset positional requirements and that the action of the target human body meets the preset action requirements. The positional requirements include that the overlap relationship between the key points of the target human body and the target queuing machine meets the preset overlap relationship. The action requirements include that the head action is determined to be tilting the head forward and the arm action is raising the arm based on the key points of the target human body. In response to the fulfillment of the queuing condition, it is determined that the target human body performs the queuing behavior on the target queuing machine, and the queuing information generated by the target human body and the target queuing machine within the associated time period at the target time is associated.

2. The method according to claim 1, characterized in that, The determination of whether the target human body meets the number selection criteria includes: Determine whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements; In response to the positional relationship satisfying the positional requirement, the action of the target human body is acquired; Determine whether the target human body's movement meets the movement requirements; In response to the target human body's action satisfying the action requirement, it is determined that the target human body meets the number selection condition.

3. The method according to claim 2, characterized in that, The image to be processed also includes the target ticket dispenser. Determining whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements includes: Key point detection is performed on the target human body; Based on the distribution information of each detected key point in the image area of ​​the ticket dispenser, it is determined whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements. The image area of ​​the ticket dispenser is the image area corresponding to the target ticket dispenser in the image to be processed.

4. The method according to claim 3, characterized in that, The step of determining whether the positional relationship between the target human body and the target ticket dispenser meets the positional requirements based on the distribution information of each detected key point in the image area of ​​the ticket dispenser includes: Determine the total number of the detected key points; and determine the number of sub-key points distributed in the image area of ​​the ticket dispenser among each detected key point; In response to the ratio of the number of sub-quantities to the total number being greater than or equal to a preset ratio threshold, it is determined that the positional relationship satisfies the positional requirement.

5. The method according to claim 3, characterized in that, The key point is associated with the arm of the target human body, and the action of the target human body is obtained in response to the positional relationship satisfying the positional requirement, including: The arm movements of the target human body are determined based on the key points mentioned above; The step of determining whether the target human body's action meets preset action requirements includes: Determine whether the arm movement is an arm raising, and whether the raising time is greater than or equal to a preset time threshold; In response to the arm movement being an arm raised and the raising time being greater than or equal to the time threshold, it is determined that the movement of the target human body meets the movement requirement.

6. The method according to any one of claims 2-5, characterized in that, The associated time period includes a first preset duration after the moment when the target human body's action is determined to meet the action requirements.

7. The method according to any one of claims 1-5, characterized in that, The associated time period includes a time period from the target time to a second preset duration after the target time.

8. The method according to claim 1, characterized in that, The image to be processed includes the first video frame from a video stream captured for the area associated with the target ticket dispenser. After associating the target human body with the ticket dispensing machine's ticket dispensing information generated during the associated time period at the target time, the method further includes: The target human body is tracked in the second video frame of the video stream, and identification description information is added to the target human body in the second video frame based on the identification information obtained after association; wherein: The second video frame includes video frames following the first video frame in the video stream.

9. The method according to claim 8, characterized in that, The method further includes: Subsequent video frames containing the added digit dispensing description information will be pushed to the terminal device associated with the target digit dispensing machine.

10. The method according to claim 1, characterized in that, The image to be processed includes the first video frame from a video stream captured for the area associated with the target ticket dispenser. After associating the target human body with the ticket dispensing machine's ticket dispensing information generated during the associated time period at the target time, the method further includes: The target human body is tracked in the second video frame, and the positional relationship between the target human body and the queuing prompt system is determined; wherein, the second video frame includes video frames following the first video frame in the video stream; In response to the target human body being outside the notification range of the call number notification system, a call number notification message is pushed to the user terminal of the target human body.

11. The method according to any one of claims 1-5 and 8-10, characterized in that, The image to be processed is the latest video frame from the video stream collected for the area associated with the target ticket dispenser.

12. An electronic device, characterized in that, Includes a processor and a memory connected to the processor, wherein, The memory stores program instructions; The processor is used to execute the program instructions stored in the memory to implement the method of any one of claims 1-11.

13. A computer-readable storage medium, characterized in that, The storage medium stores program instructions, which, when executed, implement the method as described in any one of claims 1-11.

Images