Personnel roll call method and device, electronic equipment and storage medium

Abstract

The invention provides a person roll call method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the position change information of each person based on the motion track of each person in a region; obtaining the risk degree of each person based on the position change information of each person in the area and the risk degree of the area; and performing roll call on each person based on a roll call mode corresponding to the risk degree of each person. On the basis of ensuring the roll call accuracy of the personnel, the roll call efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, device, electronic device and storage medium for personnel roll call. Background Art

[0002] In some application scenarios, it is necessary to conduct roll calls at regular intervals multiple times to confirm whether personnel are on duty. Existing roll call methods include manual roll call, punching roll call using attendance devices, and intelligent analysis roll call using monitoring devices.

[0003] Among them, manual roll call and punching roll call using attendance devices require personnel to interrupt their current actions to cooperate with the roll call, resulting in low roll call efficiency and poor user experience. It is difficult to obtain effective capture data of all personnel using intelligent analysis roll call with monitoring devices, and it is difficult to complete the roll call of all personnel within the specified time. Summary of the Invention

[0004] The present invention provides a method, device, electronic device and storage medium for personnel roll call, so as to solve the defect of low roll call efficiency in the prior art and achieve improved roll call efficiency.

[0005] The present invention provides a method for personnel roll call, including:

[0006] Based on the movement trajectories of each person within the area, obtain the position change information of each person;

[0007] Based on the position change information of each person within the area and the risk level of the area, obtain the risk level of each person;

[0008] Based on the roll call method corresponding to the risk level of each person, conduct roll call on each person.

[0009] According to the method for personnel roll call provided by the present invention, before obtaining the risk level of each person based on the position change information of each person within the area and the risk level of the area, it further includes:

[0010] Based on the length and perimeter of the enclosure of the area, determine the degree of enclosure of the area;

[0011] Based on the number of supervisors and the total number of personnel in the area, determine the degree of supervision of the area;

[0012] Based on the degree of enclosure and / or the degree of supervision of the area, determine the risk level of the area.

[0013] According to the method for personnel roll call provided by the present invention, the conducting roll call on each person based on the roll call method corresponding to the risk level of each person includes:

[0014] When the risk level of each person is greater than a preset threshold, divide each person into a first roll call group, and conduct roll call on each person in the first roll call group based on the face roll call method;

[0015] When the risk level of each person is less than or equal to the preset threshold, divide each person into a second roll call group, and conduct roll call on each person in the second roll call group based on the number roll call method.

[0016] According to a personnel roll call method provided by the present invention, the step of conducting roll call on each person in the first roll call group based on the face roll call method includes:

[0017] Based on the risk level of each person in the first roll call group, select a camera for each person from multiple cameras that capture the area;

[0018] According to the images of each person collected by the cameras selected for each person, conduct roll call on each person based on the face roll call method.

[0019] According to a personnel roll call method provided by the present invention, the step of selecting a camera for each person from multiple cameras that capture the area based on the risk level of each person in the first roll call group includes:

[0020] Select cameras for each person in turn in the order of decreasing risk level of each person in the first roll call group;

[0021] When selecting a camera for any person in the first roll call group, determine the distance between each unselected camera among the multiple cameras and the central axis of the any person;

[0022] Select a camera for the any person from the unselected cameras according to the distances corresponding to the unselected cameras.

[0023] According to a personnel roll call method provided by the present invention, the step of selecting a camera for each person from multiple cameras that capture the area based on the risk level of each person in the first roll call group includes:

[0024] When the roll call result of each person at the previous moment is a roll call failure, update the number of roll call failures of each person;

[0025] Based on the updated number of roll call failures of each person, update the risk level of each person;

[0026] Based on the updated risk level of each person, select a camera for each person from the multiple cameras.

[0027] According to a personnel roll call method provided by the present invention, after dividing each person into a second roll call group when the risk level of each person is less than or equal to the preset threshold, the method further includes:

[0028] Updating the position change information of each person in the first roll call group and the position change information of each person in the second roll call group at preset time intervals;

[0029] Updating the risk level of each person in the first roll call group according to the risk level of the area and the updated position change information of each person in the first roll call group;

[0030] Updating the risk level of each person in the second roll call group according to the risk level of the area and the updated position change information of each person in the second roll call group;

[0031] When the updated risk level of each person in the first roll call group is less than or equal to the preset threshold, dividing each person from the first roll call group into the second roll call group;

[0032] When the updated risk level of each person in the second roll call group is greater than the preset threshold, dividing each person from the second roll call group into the first roll call group.

[0033] The present invention also provides a personnel roll call device, including:

[0034] A first acquisition module, configured to obtain the position change information of each person based on the movement trajectories of each person in the area;

[0035] A second acquisition module, configured to obtain the risk level of each person based on the position change information of each person in the area and the risk level of the area;

[0036] A roll call module, configured to conduct a roll call for each person based on the roll call method corresponding to the risk level of each person.

[0037] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the program, the personnel roll call method as described in any one of the above is implemented.

[0038] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the personnel roll call method as described in any one of the above is implemented.

[0039] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the personnel roll call method as described in any one of the above is implemented.

[0040] The personnel roll call method, device, electronic device and storage medium provided by the present invention obtain the risk level of each person based on the position change information of each person in the area and the risk level of the area, accurately judge the possibility that each person is in a non-preset area, and use a suitable roll call method to roll call each person based on the risk level of each person, improving the roll call efficiency on the basis of ensuring the accuracy of personnel roll call. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0042] Figure 1 is one of the flow diagrams of the personnel roll call method provided by the embodiment of the present invention;

[0043] Figure 2 is the schematic diagram of area division in the personnel roll call method provided by the embodiment of the present invention;

[0044] Figure 3 is the schematic diagram of camera selection in the personnel roll call method provided by the embodiment of the present invention;

[0045] Figure 4 is the second flow diagram of the personnel roll call method provided by the embodiment of the present invention;

[0046] Figure 5 is the structural diagram of the personnel roll call device provided by the embodiment of the present invention;

[0047] Figure 6 is the structural diagram of the electronic device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0049] Figure 1 is one of the flow diagrams of the personnel roll call method provided by the embodiment of the present invention. The following will describe a personnel roll call method of the present invention, including: Figure 1 Describe a personnel roll call method of the present invention, including:

[0050] Step 101: Obtain the position change information of each person based on the movement trajectories of the people within the area.

[0051] The area can be a certain place where personnel roll call is required, such as a workshop, or it can be each area obtained by dividing a certain place. The place can be divided into areas based on the work content. Each person needs to move within a preset area, and the preset area can be the work post area of each person.

[0052] Figure 2 It is a schematic diagram of area division in the personnel roll call method provided by an embodiment of the present invention. As Figure 2 shown, a certain place is divided into 5 areas. Given that all the people entering the place are P, then at a certain moment T, the personnel sets in the 5 areas are P 1 , P 2 , P 3 , P 4 , and P 5 .

[0053] The roll call of the people within the area can start from one or more specified moments. Analyze the movement trajectories of each person within the area before each roll call period to obtain the position change information of each person.

[0054] The trajectory tracking function of a camera can be used to continuously record the movement trajectories of each person. It is also possible to obtain the movement trajectories of each person based on positioning devices carried by each person. The present embodiment does not limit the method for obtaining the movement trajectories.

[0055] The movement trajectories of each person within a preset duration before each roll call period can be obtained, and the dispersion of this segment of the movement trajectory can be used as the position change information of each person.

[0056] It is also possible to calculate the distances between the positions of each person at each moment in this segment of the movement trajectory and the position of each person at the initial moment of this roll call period, and calculate the average distance of all the distances. Based on the positions of each person at each moment in this segment of the movement trajectory and this average distance, the position change information of each person is obtained.

[0057] The calculation formula for the position change information of each person can be expressed as:

[0058]

[0059] where γ is the position change information of each person, n is the n moments before the roll call period, is the average distance between the positions of each person at the n moments and the position of each person at the initial moment of this roll call period, and S k is the position of each person at the k-th moment. The present embodiment does not limit the specific calculation method of the position change information.

[0060] The greater the position change information of each person, the more likely it is that the area where each person is located is not the preset area for that person.

[0061] Step 102: Obtain the risk level of each person based on the position change information of each person in the area and the risk level of the area.

[0062] The risk level of an area can be obtained based on the protection level of the area. The lower the protection level of the area, the higher the risk level. The people in the area are more likely to move to other areas, and the people in other areas are also more likely to move to this area.

[0063] The risk level of each person reflects the possibility that the area where each person is located is not the preset area. The greater the position change information of each person in the area and the higher the risk level of the area, the greater the possibility that each person leaves the preset area and the higher the risk level of each person.

[0064] The position change information γ of each person in the area can be multiplied by the risk level level of the area to obtain the risk level of each person. That is, the risk level Plevel of each person = level * γ.

[0065] The position change information γ of each person in the area and the risk level level of the area can also be weighted and added to obtain the risk level of each person. The specific calculation method of the risk level of the person in this embodiment is not limited.

[0066] Step 103: Call the roll for each person based on the roll call method corresponding to the risk level of each person.

[0067] The risk level of a person can be divided into levels based on one or more preset thresholds, and people with different risk level grades can be called the roll in different roll call methods.

[0068] People with a higher risk level grade are more likely to appear in a non-preset area. A more accurate roll call method can be used to call the roll for them, such as face roll call and card punch roll call, etc.

[0069] Among them, face roll call means collecting the face image of a person, matching the face image of the person with the face images of the people in the area stored in advance. If a face image with a similarity greater than the preset threshold is matched, the roll call for this person is successful; otherwise, the roll call for this person fails.

[0070] The face images of the people in the area stored in advance can be the face images captured at the entrance of the area by the people, or the face images pre-entered by the people.

[0071] When a person enters the area each time, they can punch in and take attendance, and use the face image captured during the punch-in and attendance-taking as the face image of the person in the area stored in advance.

[0072] Punching in and taking attendance means that a person punches in and takes attendance on the attendance device by means of face, fingerprint, etc.

[0073] For personnel with a relatively low risk level, the possibility of them appearing in a non-preset area is relatively small, and a more efficient attendance-taking method, such as counting the number of people, can be adopted.

[0074] Counting the number of people means taking a picture of the area, performing human body recognition on the image of the area, obtaining the total number of people in the area, and determining whether the total number of people in the area is consistent with the preset number of people in the area.

[0075] In this embodiment, based on the position change information of each person in the area and the risk level of the area, the risk level of each person is obtained, and the possibility of each person being in a non-preset area is accurately judged; based on the risk level of each person, a suitable attendance-taking method is adopted to take attendance on each person, improving the attendance-taking efficiency on the basis of ensuring the accuracy of personnel attendance-taking.

[0076] On the basis of the above embodiment, before obtaining the risk level of each person based on the position change information of each person in the area and the risk level of the area, this embodiment further includes:

[0077] Based on the length and perimeter of the fence of the area, determine the degree of enclosure of the area;

[0078] Based on the number of supervisors and the total number of people in the area, determine the degree of supervision of the area;

[0079] Based on the degree of enclosure and / or the degree of supervision of the area, determine the risk level of the area.

[0080] The degree of enclosure of the area reflects the protection degree of the area facilities. The fence may include buildings and equipment that prevent people from crossing the area. The length x of the fence can be determined according to the coverage of the fence.

[0081] The degree of enclosure of the area can be determined based on the proportion of the length x of the fence of the area in the perimeter y of the area. It is also possible to subtract the weighted sum of the length x of the fence of the area and the perimeter y of the area to determine the degree of enclosure of the area.

[0082] The higher the proportion of the length of the fence of the area in the perimeter of the area, the stronger the degree of enclosure of the area, and the less likely it is for people to leave the area.

[0083] The degree of supervision of an area reflects the degree of protection of area management. The degree of supervision of an area can be determined based on the ratio between the number of supervisors j in the area and the total number of personnel p. It can also be determined by subtracting the weighted number of supervisors j in the area from the weighted total number of personnel p.

[0084] The more the total number of personnel in the area and the fewer the number of supervisors, the lower the degree of supervision in the area, and the easier it is for personnel to appear in non-preset areas.

[0085] The risk degree of an area can be determined based on the degree of enclosure and / or the degree of supervision of the area.

[0086] When determining the risk degree of an area based on the degree of enclosure and the degree of supervision of the area, the first difference of 1 minus the degree of enclosure of the area and the second difference of 1 minus the degree of supervision of the area can be calculated. Multiply the first difference by the second difference as the risk degree of the area, or use the sum of the weighted first difference and the second difference as the risk degree of the area.

[0087] For example, when determining the risk degree of an area based on the degree of enclosure of the area, the risk degree level of the area can be

[0088] When determining the risk degree of an area based on the degree of supervision of the area, the risk degree level of the area can be

[0089] When determining the risk degree of an area based on the degree of enclosure and the degree of supervision of the area, the risk degree level of the area can be level = α * β.

[0090] In this embodiment, the degree of enclosure of the area is determined by the length and perimeter of the enclosure of the area, the degree of supervision of the area is determined based on the number of supervisors and the total number of personnel in the area, and the risk degree of the area is accurately determined based on the degree of enclosure and / or the degree of supervision of the area, so as to obtain a more accurate risk degree of personnel, accurately determine the possibility of personnel leaving the preset area, use a suitable roll call method for personnel based on the risk degree of personnel, and improve the roll call efficiency.

[0091] Based on the above embodiments, the roll call of each person based on the roll call method corresponding to the risk degree of each person includes:

[0092] In the case where the risk degree of each person is greater than the preset threshold, each person is divided into the first roll call group, and each person in the first roll call group is roll-called based on the face roll call method;

[0093] When the risk level of each person is less than or equal to the preset threshold, classify each person into the second roll call group, and conduct roll call for each person in the second roll call group based on the number-based roll call method.

[0094] Based on the risk levels of the personnel in the area, the personnel in the area are classified into different roll call groups, namely the first roll call group and the second roll call group. The risk levels of the personnel in the first roll call group are relatively high, and the risk levels of the personnel in the second roll call group are relatively low.

[0095] If all the personnel in the area are in the second roll call group, it indicates that the risk level of this area is relatively low, the position change information of the personnel after entering this area is relatively small, the risk levels of the personnel in this area are relatively low, and they are very likely to be in the preset area. When using the number-based roll call method for roll call, it is only necessary to determine whether the total number of personnel in the area is consistent with the preset number of personnel in the area, and there is no need to conduct face roll call for the personnel.

[0096] If there are personnel in the area belonging to the first roll call group, it indicates that the risk level of this area is relatively high, the position change information of the personnel after entering this area is relatively large, the risk levels of the personnel are relatively large, and they are very likely to be in a non-preset area. Use the face roll call method to conduct roll call for each person in the first roll call group to ensure the accuracy of personnel roll call. Use the number-based roll call method to conduct roll call for each person in the second roll call group. The risk levels of each person in the second roll call group are relatively low, and they are very likely to be in the preset area, so there is no need to conduct face roll call for the personnel. Since face roll call is conducted for some of the personnel in the area, on the basis of ensuring the accuracy of personnel roll call, the roll call time is shortened and the roll call efficiency is improved.

[0097] On the basis of the above embodiments, in this embodiment, the method of conducting roll call for each person in the first roll call group based on the face roll call method includes:

[0098] Based on the risk levels of each person in the first roll call group, select cameras for each person from multiple cameras shooting the area;

[0099] According to the images of each person collected by the cameras selected for each person, conduct roll call for each person based on the face roll call method.

[0100] The higher the risk level of a person, the greater the possibility that the person is in a non-preset area, and it is necessary to confirm whether the person is in a non-preset area through early roll call.

[0101] The cameras can be selected one by one for each person to take images for face roll call in the order of the risk levels of each person in the first roll call group from high to low.

[0102] At least one camera can be selected for each person to take pictures. When taking pictures, rotate the camera and take a face image of the person when the person is at the center point of the camera's picture, so as to quickly take a face image with better effect, improve the success rate of face roll call, and shorten the roll call time.

[0103] When the total number of people in the first roll call group is less than the number of cameras, multiple cameras that have not been selected among the multiple cameras are sequentially selected for each person in the order of the risk levels of the people in the first roll call group from high to low until all the multiple cameras have been selected;

[0104] When the number of people in the first roll call group is greater than the number of cameras, cameras among the multiple cameras are sequentially selected for each person in the order of the risk levels of the people in the first roll call group from high to low.

[0105] When the total number f of people in the first roll call group is less than the number of cameras, a camera can be separately selected for each person based on the risk level of each person in the first roll call group, and there are still extra cameras not selected after the selection. The extra unselected cameras are continued to be used to select cameras for each person one by one based on the risk level of each person in the first roll call group until all cameras are selected, making full use of the camera resources, quickly taking valid face images of the people, and improving the roll call efficiency.

[0106] For a person who selects multiple cameras, the person can be roll-called based on the face images taken by the multiple cameras. For example, if at least one face image matches an image with a similarity greater than a preset threshold, the roll call of the person is successful.

[0107] Suppose there are 5 cameras in total, and the number of people in the first roll call group is 3. After selecting cameras for each person one by one based on the risk level of each person, 2 cameras are left. The remaining 2 cameras are used to select cameras for each person one by one again based on the risk level of each person. Among the 3 people in the first roll call group, two people select 2 cameras and one person selects 1 camera.

[0108] When the total number f of people in the first roll call group is greater than the number of cameras, it means that the number of cameras is limited and a camera cannot be separately selected for each person based on the risk level of each person in the first roll call group.

[0109] After selecting a camera for any person from the multiple cameras in the shooting area in the order of the risk levels of the people in the first roll call group from high to low, face roll call is performed based on the face image taken by the camera. The multiple cameras in the shooting area are continued to be used as the basis for the next person to select a camera. The multiple cameras in the shooting area are used as the basis for each person to select a camera, making full use of the camera resources, enabling more people to take face images, and improving the roll call efficiency.

[0110] Assume there are 2 cameras in total, and the number of people in the first roll call group is 3. Select cameras in the order of the risk levels of the 3 people from the highest to the lowest. The first person selects a camera from the 2 cameras to take an image for face roll call. The second person selects a camera from the 2 cameras to take an image for face roll call. The third person selects a camera from the 2 cameras to take an image for face roll call.

[0111] In this embodiment, by selecting cameras for each person based on the risk level of each person in the first roll call group, the person with a higher risk level can perform face roll call earlier to confirm whether the person is in a non - preset area, meeting the personnel roll call requirements.

[0112] Based on the risk levels of each person in the first roll call group, on the basis of the above - mentioned embodiment, selecting cameras for each person from multiple cameras shooting the area includes:

[0113] Select cameras for each person in turn in the order of the risk levels of each person in the first roll call group from the highest to the lowest;

[0114] When selecting a camera for any person in the first roll call group, determine the distances between the unselected cameras among the multiple cameras and the central axis of the any person;

[0115] Select a camera for the any person from the unselected cameras according to the distances corresponding to the unselected cameras.

[0116] Select cameras to take images for each person one by one in the order of the risk levels of each person in the first roll call group from the highest to the lowest, so that the person with a higher risk level can perform face roll call earlier.

[0117] The cameras in the area can include three types, namely v 1 、v 2 and v 3 . Among them, v 1 The camera can take images of the entire area; v 2 can take images of a local part of this area; v 3 can take images of a local part of this area and can also rotate to take images of local parts of other areas. The cameras in the area can also include v 1 and v 2 two types.

[0118] When conducting a headcount in the area, the headcount of the number of people in the area can be based on the image of the area taken by the v 1 camera. At this time, the personnel roll call in this area does not require the participation of the v 2 and v 3 cameras, v 3The camera can turn to other adjacent areas for image capture.

[0119] When taking a roll call of people in an area, the v 2 and v 3 of the camera are required.

[0120] Figure 3 It is a schematic diagram of camera selection in the method for taking a roll call of people provided by an embodiment of the present invention. As Figure 3 shown, the orientation information of a person can be the face orientation of the person, such as the direction indicated by the arrow. Based on the face orientation of the person, the central axis of the person is determined, such as the straight line indicated by the arrow.

[0121] When selecting a camera for any person in the first roll call group, determine the distance between each currently unselected camera and the central axis of the person. Figure 3 The circles in it represent the positions of each currently unselected camera. Calculate the distance between the position of each camera and the central axis of the person, and the camera with the smallest distance can be selected to rotate the camera to capture an image for face roll call, so as to capture a better face image of a person with a high risk level as soon as possible, improve the success rate of face roll call, and shorten the roll call time.

[0122] In this embodiment, by selecting cameras for each person in the first roll call group in the order from the largest to the smallest risk level, when selecting a camera for each person, select based on the distance between each unselected camera and the central axis of each person, so as to preferentially capture a better face image of a person with a high risk level, improve the success rate of face roll call, and shorten the roll call time.

[0123] Based on the above embodiment, in this embodiment, the selecting cameras for each person from multiple cameras shooting the area based on the risk level of each person in the first roll call group includes:

[0124] When the roll call result of each person at the previous moment is a roll call failure, update the number of roll call failures of each person;

[0125] Based on the updated number of roll call failures of each person, update the risk level of each person;

[0126] Based on the updated risk level of each person, select cameras for each person from the multiple cameras.

[0127] During a complete roll call cycle, it may not be possible for all personnel within the first roll call group to capture valid face images simultaneously, and they may not be able to conduct roll call simultaneously or succeed in roll call simultaneously. After each personnel within the first roll call group has successfully completed roll call at each moment, the personnel who have successfully completed roll call can be removed from the first roll call group. At the next moment, continue to select cameras and conduct face roll call for the remaining personnel within the first roll call group until the roll call cycle ends or the personnel in the first roll call group are empty.

[0128] After each personnel within the first roll call group fails in roll call at each moment, update the number of roll call failures for each personnel, and the number of roll call failures δ for each personnel can be incremented by 1.

[0129] Based on the updated number of roll call failures for each personnel, update the risk level for each personnel. The updated number of roll call failures for each personnel can be weighted and added to the risk level for each personnel, or the updated number of roll call failures for each personnel can be multiplied by the risk level for each personnel to obtain the updated risk level for each personnel.

[0130] The calculation formula for the updated risk level Plevel′ for each personnel can be

[0131] Plevel′ = Plevel * (δ + 1).

[0132] In this embodiment, by updating the number of roll call failures in the case of roll call failure for each personnel and updating the risk level for each personnel based on the number of roll call failures, the higher the number of roll call times, the higher the risk level for each personnel, and cameras are preferentially allocated for face image capture, improving the roll call efficiency.

[0133] On the basis of the above embodiment, after dividing each personnel into the second roll call group when the risk level of each personnel is less than or equal to the preset threshold in this embodiment, it further includes:

[0134] Update the position change information of each personnel within the first roll call group and the position change information of each personnel within the second roll call group at every preset time interval;

[0135] Update the risk level of each personnel within the first roll call group according to the risk level of the area and the updated position change information of each personnel within the first roll call group;

[0136] Update the risk level of each personnel within the second roll call group according to the risk level of the area and the updated position change information of each personnel within the second roll call group;

[0137] When the updated risk level of each personnel within the first roll call group is less than or equal to the preset threshold, divide each personnel from the first roll call group into the second roll call group;

[0138] In the case where the updated risk level of each person in the second roll call group is greater than the preset threshold, each person is divided from the second roll call group into the first roll call group.

[0139] During the roll call period, the position of a person in the first roll call group and the second roll call group may change significantly, resulting in a change in the risk level of the person. The group is updated for the person based on the changed risk level.

[0140] The position change information of each person in the first roll call group and the second roll call group can be updated based on the latest positions of each person in the first roll call group and the second roll call group at each moment or at regular intervals. The position change information of each person can be recalculated based on the positions of each person in the most recent n moments. The risk level of each person is recalculated based on the updated position change information.

[0141] If the updated risk level of each person in the first roll call group is less than or equal to the preset threshold, each person can be divided from the first roll call group into the second roll call group for headcount. If the updated risk level of each person in the second roll call group is greater than the preset threshold, each person can be divided from the second roll call group into the first roll call group for camera selection and face roll call, thereby realizing the dynamic update of the first roll call group and the second roll call group and improving the accuracy of personnel roll call.

[0142] Figure 4 It is the second flowchart of the personnel roll call method provided by the embodiment of the present invention. As Figure 4 shown, a face image is collected at the entrance of the area for face roll call for the delimited area of the venue; the risk level of each person in the area is calculated, and each person is divided into a roll call group based on the risk level and roll called in different roll call methods; the positions of each person in the area are continuously monitored, and the position change information of each person is updated based on the positions, thereby updating the risk level of each person, and the roll call method of each person is updated based on the updated risk level of each person.

[0143] In this embodiment, by updating the position change information of each person in the first roll call group and the second roll call group, the risk level of each person in the first roll call group and the second roll call group is updated, and the roll call method of each person is updated based on the updated risk level of each person in the first roll call group and the second roll call group, improving the accuracy of roll call.

[0144] The personnel roll call device provided by the embodiment of the present invention will be described below. The personnel roll call device described below can be correspondingly referred to the personnel roll call method described above.

[0145] Figure 5 It is the structural schematic diagram of the personnel roll call device provided by the embodiment of the present invention. AsFigure 5 As shown, the device includes a first acquisition module 501, a second acquisition module 502, and a roll call module 503, where:

[0146] The first acquisition module 501 is configured to obtain the position change information of each person based on the movement trajectories of the persons within the area;

[0147] The second acquisition module 502 is configured to obtain the risk level of each person based on the position change information of each person within the area and the risk level of the area;

[0148] The roll call module 503 is configured to conduct a roll call for each person based on the roll call method corresponding to the risk level of each person.

[0149] In this embodiment, by obtaining the risk level of each person based on the position change information of each person within the area and the risk level of the area, the possibility that each person is in a non - preset area is accurately judged; and by using an appropriate roll call method based on the risk level of each person to conduct a roll call for each person, the roll call efficiency is improved on the basis of ensuring the accuracy of the roll call.

[0150] Figure 6 An example of the physical structure diagram of an electronic device is shown, such as Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communications interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the logical instructions in the memory 630 to execute the personnel roll call method, and the method includes: obtaining the position change information of each person based on the movement trajectories of the persons within the area; obtaining the risk level of each person based on the position change information of each person within the area and the risk level of the area; and conducting a roll call for each person based on the roll call method corresponding to the risk level of each person.

[0151] In addition, when the logical instructions in the above-mentioned memory 630 can be implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0152] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the personnel roll call method provided by the above-mentioned various methods. The method includes: obtaining the position change information of each person based on the movement trajectories of each person in the area; obtaining the risk level of each person based on the position change information of each person in the area and the risk level of the area; and conducting a roll call for each person based on the roll call method corresponding to the risk level of each person.

[0153] In yet another aspect, the present invention also provides a computer-readable storage medium with a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the personnel roll call method provided by the above-mentioned various methods. The method includes: obtaining the position change information of each person based on the movement trajectories of each person in the area; obtaining the risk level of each person based on the position change information of each person in the area and the risk level of the area; and conducting a roll call for each person based on the roll call method corresponding to the risk level of each person.

[0154] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for taking roll call of personnel, characterized in that, it includes: Based on the movement trajectories of each person within the area, obtain the position change information of each person; Based on the position change information of each person within the area and the risk level of the area, obtain the risk level of each person; Based on the roll call method corresponding to the risk level of each person, take roll call of each person.

2. The method for taking roll call of personnel according to claim 1, characterized in that, Before obtaining the risk level of each person based on the position change information of each person within the area and the risk level of the area, it further includes: Based on the length and perimeter of the enclosure of the area, determine the degree of enclosure of the area; Based on the number of supervisors and the total number of personnel in the area, determine the degree of supervision of the area; Based on the degree of enclosure and / or the degree of supervision of the area, determine the risk level of the area.

3. The method for taking roll call of personnel according to claim 1, characterized in that, Taking roll call of each person based on the roll call method corresponding to the risk level of each person includes: When the risk level of each person is greater than the preset threshold, divide each person into the first roll call group, and take roll call of each person within the first roll call group based on the face roll call method; When the risk level of each person is less than or equal to the preset threshold, divide each person into the second roll call group, and take roll call of each person within the second roll call group based on the number roll call method.

4. The method for taking roll call of personnel according to claim 3, characterized in that, Taking roll call of each person within the first roll call group based on the face roll call method includes: Based on the risk level of each person within the first roll call group, select a camera for each person from multiple cameras shooting the area; Based on the images of each person collected by the cameras selected for each person, take roll call of each person based on the face roll call method.

5. The method for taking roll call of personnel according to claim 4, characterized in that, Selecting a camera for each person from multiple cameras shooting the area based on the risk level of each person within the first roll call group includes: Select cameras for each person in turn in the order of the risk level of each person within the first roll call group from high to low; When selecting a camera for any person within the first roll call group, determine the distance between the mid-axis of each unselected camera among the multiple cameras and the any person; Based on the distances corresponding to the unselected cameras, select a camera for the any person from the unselected cameras.

6. The method for taking roll call of personnel according to claim 4, characterized in that, Selecting a camera for each person from multiple cameras shooting the area based on the risk level of each person within the first roll call group includes: When the roll call result of each person at the previous moment is a roll call failure, update the number of roll call failures of each person; Based on the updated number of roll call failures of each person, update the risk level of each person. Select a camera for each person from the multiple cameras based on the updated risk levels of the respective persons.

7. The method for taking roll call of persons according to claim 3, wherein, after classifying the respective persons into the second roll call group when the risk level of each person is less than or equal to the preset threshold, the method further includes: Updating the position change information of each person in the first roll call group and the position change information of each person in the second roll call group at every preset time interval; Updating the risk level of each person in the first roll call group according to the risk level of the area and the updated position change information of each person in the first roll call group; Updating the risk level of each person in the second roll call group according to the risk level of the area and the updated position change information of each person in the second roll call group; When the updated risk level of each person in the first roll call group is less than or equal to the preset threshold, classifying the respective persons from the first roll call group into the second roll call group; When the updated risk level of each person in the second roll call group is greater than the preset threshold, classifying the respective persons from the second roll call group into the first roll call group.

8. A device for taking roll call of persons, wherein, it includes: A first acquisition module, configured to obtain the position change information of the respective persons based on the movement trajectories of the persons in the area; A second acquisition module, configured to obtain the risk level of the respective persons based on the position change information of the persons in the area and the risk level of the area; A roll call module, configured to take roll call of the respective persons based on the roll call method corresponding to the risk level of the respective persons.

9. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the program, the method for taking roll call of persons according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the method for taking roll call of persons according to any one of claims 1 to 7 is implemented.

Images