On-duty monitoring method for target place

Abstract

The invention provides an on-duty monitoring method for a target place. The method comprises the following steps: acquiring the actual on-duty number of people corresponding to each inspection security check point in the target place at a plurality of inspection moments in a preset time period; on the basis of the actual on-duty number of people corresponding to all the inspection moments, under the condition that it is determined that the target actual on-duty number of people at the first inspection security inspection point at the target inspection moment is missing, the target actual on-duty number of people is determined based on information obtained by target equipment, the target device is a device capable of collecting the working condition of the first inspection security check point; and monitoring the on-duty condition of the target place based on the actual on-duty number of people and the target actual on-duty number of people. The monitoring accuracy of the on-duty condition of the target place can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an on-the-job monitoring method for a target location. Background Art

[0002] In many places, such as stations, factories, hospitals or banks, monitoring the presence of staff is key to ensuring operational efficiency and safety.

[0003] In the prior art, the on-duty status of the staff at each security checkpoint in the target location is usually checked at preset time intervals, and the on-duty status of the target location is monitored by recording all the actual on-duty numbers.

[0004] However, in the process of collecting the number of people on duty, it often happens that the inspection data is missing at certain times. In the prior art, the missing data is usually ignored, and the on-duty status of the target place is determined based on the non-missing data, which will cause the problem of low monitoring accuracy of the on-duty status of the target place. Summary of the invention

[0005] The present invention provides an on-the-job monitoring method for a target location, which is used to solve the defect of low monitoring accuracy of the on-the-job situation of the target location in the prior art and achieve the purpose of improving the monitoring accuracy of the on-the-job situation of the target location.

[0006] The present invention provides an on-the-job monitoring method for a target location, comprising: Obtain the actual number of people on duty at each security checkpoint in the target location at multiple check times within a preset time period; In the case where the target actual number of people on duty at the first inspection checkpoint at the target inspection time is missing based on the actual number of people on duty corresponding to all the inspection times, the target actual number of people on duty is determined based on information obtained by a target device, where the target device is a device that can collect the working conditions of the first inspection checkpoint; Based on the actual number of people on duty and the target actual number of people on duty, the on-duty status of the target place is monitored.

[0007] According to an on-the-job monitoring method of a target location provided by the present invention, the target device includes a camera device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Determine a second security checkpoint that is closest to the first security checkpoint; Controlling a first camera device corresponding to the second security checkpoint to rotate to a position of the first security checkpoint, and collecting information of the first security checkpoint through the first camera device, wherein the information collected by the first camera device includes a first image; Based on the first image, the actual number of on-duty personnel of the target is determined.

[0008] According to an on-the-job monitoring method of a target location provided by the present invention, the step of controlling the first camera device corresponding to the second inspection and security checkpoint to rotate to the position of the first inspection and security checkpoint includes: obtaining a position of the second inspection checkpoint relative to the first inspection checkpoint; Obtaining the current angle of the first camera device; determining a target angle based on the orientation and the current angle; The first camera device is controlled to rotate to the position of the first security checkpoint based on the target angle.

[0009] According to an on-the-job monitoring method of a target location provided by the present invention, the step of determining a second inspection and security checkpoint that is closest to the first inspection and security checkpoint includes: Controlling a second camera device corresponding to the first security checkpoint to collect images of the first security checkpoint; When image acquisition fails or the definition of the acquired second image is less than a preset definition, a second inspection and security checkpoint which is closest to the first inspection and security checkpoint is determined.

[0010] According to a method for monitoring on-the-job personnel at a target location provided by the present invention, determining the actual number of people on-the-job personnel at the target location based on the first image includes: The first image is input into a number detection model to obtain the actual number of people on duty output by the number detection model; the number detection model is obtained by training an initial number detection model based on a sample image and label information corresponding to the sample image, and the label information is used to characterize the sample staff wearing preset style clothing in the sample image.

[0011] According to an on-the-job monitoring method of a target location provided by the present invention, the target device includes a detection device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Acquire information acquired by each detection device at the first security checkpoint within the preset time period; The number of detection devices that have information within a first time period is determined as the actual number of people on duty at the target; the first time period includes the target inspection time.

[0012] According to an on-the-job monitoring method of a target location provided by the present invention, the target device includes a voice collection device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Acquire information collected by a voice collection device at the first security checkpoint in a second time period, where the information collected by the voice collection device includes voice information, and the second time period includes the target inspection time; Extracting at least one target voiceprint information from the voice information; Matching each target voiceprint information with each voiceprint information in a voiceprint library to obtain a matching result, wherein the voiceprint library stores the voiceprint information of each staff member at the first security checkpoint; The number of target voiceprint information indicating successful matching in the matching result is determined as the actual number of target persons on duty.

[0013] According to an on-the-job monitoring method of a target location provided by the present invention, the target device further includes a detection device; The determining, based on the first image, the actual number of people on duty at the target includes: Determining a first number of people on duty at the first security checkpoint based on the first image; Determining a second number of on-duty personnel at the first inspection and security checkpoint based on information acquired by all detection devices at the first inspection and security checkpoint; The actual number of on-duty personnel of the target is determined based on the first number of on-duty personnel, the first weight corresponding to the camera device, the second number of on-duty personnel and the second weight corresponding to the detection device.

[0014] According to a method for monitoring on-the-job status of a target place provided by the present invention, monitoring the on-the-job status of the target place based on the actual number of on-the-job persons and the target actual number of on-the-job persons includes: Determine the total actual number of employees on duty based on all the actual number of employees on duty and the target actual number of employees on duty; The total number of people actually on duty is divided by the number of people who should be on duty at the target place to obtain the on-duty rate of the target place, and the on-duty rate is used to characterize the on-duty situation of the target place.

[0015] According to a method for on-the-job monitoring of a target location provided by the present invention, the method further comprises: Obtaining the flow of people at each of the security checkpoints; When the flow of people at the third inspection and security checkpoint is greater than the first preset flow of people, the flow of people at the fourth inspection and security checkpoint is less than the second preset flow of people, and the actual number of people on duty at the third inspection and security checkpoint is less than the actual number of people on duty at the fourth inspection and security checkpoint, a prompt message is output, wherein the prompt message is used to indicate that some staff members of the fourth inspection and security checkpoint are transferred to the third inspection and security checkpoint, and the first preset flow of people is greater than the second preset flow of people.

[0016] The present invention also provides an on-the-job monitoring device for a target location, comprising: An acquisition module is used to obtain the actual number of people on duty at each security checkpoint in the target place at multiple inspection times within a preset time period; a determination module, configured to determine the target actual number of on-duty personnel at the first inspection and security checkpoint at the target inspection time based on the actual number of on-duty personnel corresponding to all the inspection times, and determine the target actual number of on-duty personnel based on information obtained by a target device, wherein the target device is a device that can collect working conditions of the first inspection and security checkpoint; A monitoring module is used to monitor the on-the-job status of the target place based on the actual number of on-the-job persons and the target actual number of on-the-job persons.

[0017] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an on-the-job monitoring method for a target location as described above is implemented.

[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the on-the-job monitoring method of a target location as described in any one of the above is implemented.

[0019] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned on-the-job monitoring methods for a target location.

[0020] The on-the-job monitoring method of the target place provided by the present invention obtains the actual on-the-job number corresponding to each inspection and security checkpoint in the target place at multiple inspection times within a preset time period, and determines the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time based on the actual on-the-job number corresponding to all inspection times. In the case where the target actual on-the-job number of the first inspection and security checkpoint is missing, the target actual on-the-job number is determined based on the information obtained by the target device, and the target device is a device that can collect the working conditions of the first inspection and security checkpoint, so as to monitor the on-the-job situation of the target place based on each actual on-the-job number and the target actual on-the-job number. Since when it is determined that the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time is missing, the missing data is not directly ignored, but the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time is predicted with the help of the information obtained by the target device, so that the missing data is compensated by the predicted target actual on-the-job number, so that when the on-the-job situation of the target place is monitored by the obtained actual on-the-job number and the predicted target actual on-the-job number, the accuracy of the monitoring result can be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic flow chart of an on-the-job monitoring method for a target location provided in an embodiment of the present invention.

[0023] Figure 2 A schematic structural diagram of an on-the-job monitoring device for a target location provided by an embodiment of the present invention.

[0024] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] At present, regular inspections are usually used to determine the actual number of people on duty at each inspection and security checkpoint at the target location. However, in the process of collecting the actual number of people on duty at each inspection and security checkpoint, the actual number of people on duty at certain times may be missing due to reasons such as equipment failure, human negligence or communication interruption. When determining the on-duty status of the target location, the missing data will be ignored, and the on-duty status of the target location will be determined only based on the non-missing data. However, the ignored data may contain key on-duty information, so the accuracy of the on-duty status of the target location determined by the above method is low.

[0027] In response to the above-mentioned problems, an embodiment of the present invention provides a method for monitoring on-the-job personnel at a target location. In the method, when it is found that the actual number of on-the-job personnel at a certain inspection and security checkpoint in the target location at the target inspection time is missing, the actual number of on-the-job personnel at the inspection and security checkpoint at the target inspection time can be predicted with the help of information obtained by a target device that can collect the working conditions of the inspection and security checkpoint, thereby supplementing the missing data based on the predicted actual number of on-the-job personnel. Since the missing data is supplemented, the monitoring accuracy of the on-the-job situation at the target location can be improved.

[0028] The execution subject of the method can be an electronic device such as a computer or a server, or a specially designed intelligent device, or a target location on-the-job monitoring device set in the electronic device or intelligent device, and the target location on-the-job monitoring device can be implemented by software, hardware, or a combination of the two. The method can be applied to scenes such as stations, factories, hospitals, or banks where on-the-job staff statistics are required to monitor the on-the-job situation.

[0029] Figure 1 A flow chart of an on-the-job monitoring method for a target location provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes: Step 101: Obtain the actual number of people on duty at each security checkpoint in the target location at multiple inspection times within a preset time period.

[0030] In this step, the preset time period can be determined according to the operation requirements of the target site and the scheduling requirements of the staff, or according to the actual needs of monitoring the on-the-job situation of the target site. For example, the preset time period can be a specific few hours in a day, such as 6 am to 10 pm, or a certain few days in a week or a month. In addition, multiple inspection times can be set within the preset time period, such as an inspection every preset time.

[0031] The target location includes multiple inspection and security checkpoints, such as entrances and exits, work areas, or next to key equipment. For example, if the target location is a station, the inspection and security checkpoints may include entrance locations, security checkpoint locations, and exit locations.

[0032] For example, the actual number of people on duty at each inspection checkpoint can be manually checked at each inspection time and input into the electronic device. At least one camera device can also be set at each inspection checkpoint to capture images of the inspection checkpoint through the camera device to determine the actual number of people on duty at the inspection checkpoint based on the captured images. The actual number of people on duty at the inspection checkpoint can also be determined by infrared, radar, or ultrasonic methods.

[0033] Step 102: When the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time is missing based on the actual number of people on duty corresponding to all inspection times, the target actual number of people on duty is determined based on the information obtained by the target device, and the target device is a device that can collect the working conditions of the first inspection and security checkpoint.

[0034] In this step, when the preset time period is about to end, that is, after the last inspection time set in the preset time period ends, it can be determined whether the actual number of people on duty corresponding to each preset inspection time is missing based on the actual number of people on duty obtained within the preset time period. When it is determined that the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time is missing, it means that the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time has not been collected. At this time, the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time will be predicted with the help of the information obtained by the target device. Among them, the target device is a device that can collect the working conditions of the first inspection and security checkpoint, for example, it can include a camera device, a security inspection detection device, or a sound receiving device. The information obtained by the target device can be understood as the information collected by the target device within the preset time period, such as the collected image, security inspection information, or audio information.

[0035] For example, assuming that the preset time period includes 06:00-09:55 in the morning, it is necessary to check the actual number of people on duty at the security checkpoints in the target location starting from 06:00 in the morning, wherein the inspection data is shown in the following Table 1: Table 1

[0036] It can be seen from Table 1 that the target number of people actually on duty at the security checkpoint A2 at the target inspection time of 09:00 is missing.

[0037] It should be noted that the best time to determine the on-duty status of the target location is usually when the preset time period is about to end. For example, when checking the on-duty status during the peak period of 7:00-9:00, it can be determined after 8:50 based on all the actual number of on-duty people collected and the predicted actual number of on-duty people, which can improve the monitoring accuracy of the on-duty status.

[0038] Step 103: Based on the actual number of people on duty and the target actual number of people on duty, monitor the on-duty status of the target location.

[0039] In this step, the on-the-job situation of the target place can be monitored based on the actual number of people on duty at each inspection and security checkpoint collected, and the predicted target actual number of people on duty at the first inspection and security checkpoint. For example, after determining all the actual number of people on duty at the target place based on the actual number of people on duty and the target actual number of people on duty, the on-the-job situation of the staff at the target place can be directly measured based on all the actual number of people on duty. It is also possible to further determine the on-the-job rate of the staff at the target place based on all the actual number of people on duty and the number of people who should be on duty at each inspection and security checkpoint in the target place, so as to measure the on-the-job situation of the staff at the target place through the on-the-job rate. For example, the higher the on-the-job rate, the better the on-the-job situation of the target place.

[0040] The on-the-job monitoring method of the target place provided by the embodiment of the present invention obtains the actual on-the-job number corresponding to multiple inspection times of each inspection and security checkpoint in the target place within a preset time period, and determines the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time based on the actual on-the-job number corresponding to all inspection times. In the case where the target actual on-the-job number of the first inspection and security checkpoint is missing, the target actual on-the-job number is determined based on the information obtained by the target device, and the target device is a device that can collect the working conditions of the first inspection and security checkpoint, so as to monitor the on-the-job situation of the target place based on each actual on-the-job number and the target actual on-the-job number. Since when it is determined that the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time is missing, the missing data is not directly ignored, but the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time is predicted with the help of the information obtained by the target device, so that the missing data is compensated by the predicted target actual on-the-job number, so that when the on-the-job situation of the target place is monitored by the obtained actual on-the-job number and the predicted target actual on-the-job number, the accuracy of the monitoring result can be greatly improved.

[0041] Exemplarily, based on the above-mentioned embodiment, when the above-mentioned target device includes a camera device, determining the actual number of target personnel on duty based on the information obtained by the target device can be achieved in the following way: determining a second inspection and security checkpoint that is closest to the first inspection and security checkpoint, controlling the first camera device corresponding to the second inspection and security checkpoint to rotate to the position of the first inspection and security checkpoint, and collecting information of the first inspection and security checkpoint through the first camera device, the information collected by the first camera device includes a first image, and based on the first image, determining the actual number of target personnel on duty.

[0042] Specifically, the actual number of people on duty at the first inspection and security checkpoint can be determined with the help of the camera equipment around the first inspection and security checkpoint. Among them, in order to improve the accuracy of the predicted actual number of people on duty, the second inspection and security checkpoint closest to the first inspection and security checkpoint can be first determined, and the first camera equipment set in the area where the second inspection and security checkpoint is located can be controlled to rotate, and rotated to the position where the monitoring area faces the first inspection and security checkpoint, so as to collect the first image of the first inspection and security checkpoint through the first camera equipment. It should be understood that in the target place, there are usually not only staff members, but also non-staff members, such as passengers. The staff members are generally dressed differently from non-staff members, such as staff members may wear armbands or uniforms, etc. Therefore, after the first image is collected, the first image is analyzed to distinguish the staff members from the first image and perform statistics to determine the actual number of people on duty at the first inspection and security checkpoint.

[0043] In this embodiment, the second inspection and security checkpoint that is closest to the first inspection and security checkpoint is determined, and the first camera device corresponding to the second inspection and security checkpoint is controlled to rotate to the position of the first inspection and security checkpoint to capture a first image of the first inspection and security checkpoint. Since the first camera device is closer to the first inspection and security checkpoint, the clarity of the first image can be guaranteed to be high, and thus the accuracy of the actual number of target personnel on duty determined based on the first image is also high.

[0044] Exemplarily, based on the above embodiments, when controlling the first camera device corresponding to the second inspection and security checkpoint to rotate to the position of the first inspection and security checkpoint, the current angle of the first camera device can be obtained by obtaining the orientation of the second inspection and security checkpoint relative to the first inspection and security checkpoint, and after determining the target angle based on the orientation and the current angle, the first camera device is controlled to rotate to the position of the first inspection and security checkpoint based on the target angle.

[0045] Specifically, the position of each inspection and security checkpoint relative to other inspection and security checkpoints can be calibrated in advance based on the actual physical position of each inspection and security checkpoint in the target location, wherein the position includes direction and position, such as the relative angle and relative position of any two inspection and security checkpoints.

[0046] Furthermore, based on the pre-calibrated azimuth relationship between any two inspection and security checkpoints, the azimuth of the second inspection and security checkpoint relative to the first inspection and security checkpoint, that is, the angle and position of the second inspection and security checkpoint relative to the first inspection and security checkpoint, can be obtained.

[0047] After obtaining the current angle of the first camera device, the target angle can be determined based on the position of the second inspection and security checkpoint relative to the first inspection and security checkpoint and the current angle of the first camera device. The target angle can be understood as the angle that the first camera device needs to rotate. After the first camera device rotates to the target angle, its monitoring field of view will rotate to the position of the first inspection and security checkpoint, so that the image of the first inspection and security checkpoint can be captured.

[0048] In this embodiment, the target angle can be determined based on the orientation of the second inspection and security checkpoint relative to the first inspection and security checkpoint and the current angle of the first camera device, and the first camera device can be controlled to rotate to the position of the first inspection and security checkpoint based on the target angle. In the above manner, fine control of the first camera device can be achieved, thereby ensuring that the first camera device can be accurately rotated to the first inspection and security checkpoint.

[0049] Illustratively, based on the above embodiments, when determining the second inspection and security checkpoint that is closest to the first inspection and security checkpoint, the second camera device corresponding to the first inspection and security checkpoint can be controlled to capture images of the first inspection and security checkpoint. If the image capture fails or the clarity of the captured second image is less than the preset clarity, the second inspection and security checkpoint that is closest to the first inspection and security checkpoint is determined.

[0050] Specifically, before mobilizing the first camera device around the first inspection and security checkpoint to collect images of the first inspection and security checkpoint, the second camera device installed at the first inspection and security checkpoint can be controlled to collect images. When the second camera device successfully collects images of the first inspection and security checkpoint and the clarity of the image is greater than or equal to the preset clarity, the first camera device around will not be mobilized to collect images, but the image collected by the second camera device will be directly analyzed to predict the actual number of target personnel on duty at the first inspection and security checkpoint.

[0051] When the second camera fails to capture the image of the first inspection and security checkpoint or the clarity of the captured second image is less than the preset clarity, the surrounding first camera devices will be mobilized to capture the image, that is, the second inspection and security checkpoint closest to the first inspection and security checkpoint is determined, and the first camera set at the second inspection and security checkpoint is mobilized to capture the image of the first inspection and security checkpoint.

[0052] In this embodiment, the second camera device corresponding to the first inspection and security checkpoint can be controlled to capture images of the first inspection and security checkpoint. When the image capture fails or the clarity of the captured second image is less than the preset clarity, the second inspection and security checkpoint closest to the first inspection and security checkpoint will be determined to mobilize the first camera device of the second inspection and security checkpoint to capture images of the first inspection and security checkpoint. This method can reduce unnecessary mobilization of camera devices and waste of resources, thereby optimizing the use of monitoring resources.

[0053] Exemplarily, based on the above embodiments, when determining the actual number of target people on duty based on the first image, the first image can be input into a number detection model to obtain the actual number of target people on duty output by the number detection model; the number detection model is obtained by training an initial number detection model based on sample images and label information corresponding to the sample images, and the label information is used to characterize sample staff wearing preset style clothing in the sample image.

[0054] Specifically, multiple sample images of each inspection and security checkpoint in the sample location can be obtained, and sample staff wearing preset style clothing can be marked in each sample image, and the number of these sample staff can be used as label information for each sample image, such as marking staff wearing armbands or staff in uniforms.

[0055] Each sample image is input into the initial number detection model to obtain the predicted number of people actually on duty output by the initial number detection model, wherein the predicted number of people actually on duty includes the predicted number of sample staff members wearing clothes of preset styles in the sample image. Based on the predicted number of people actually on duty and the label information, the loss information can be determined, and the model parameters of the initial number detection model can be adjusted based on the loss information. By repeatedly executing the above process until the number of repetitions reaches the preset number of times or the loss information is minimized, the final model is determined as the number detection model.

[0056] The obtained first image is input into the above-mentioned trained number detection model, and the target actual number of on-duty staff in the first image output by the number detection model can be obtained.

[0057] In this embodiment, when training the number detection model, by marking the sample staff wearing preset style clothing in the sample image, the interference of other non-staff can be eliminated, thereby improving the robustness of the number detection model. When predicting the actual number of target employees on duty based on the number detection model, the accuracy of the prediction results can be improved.

[0058] Exemplarily, based on the above embodiments, when the target device includes a detection device, when determining the actual number of target personnel on duty based on the information obtained by the target device, the information obtained by each detection device at the first inspection and security checkpoint within a preset time period can be obtained, and the number of detection devices that have information within the first time period can be determined as the actual number of target personnel on duty; the first time period includes the target inspection time.

[0059] Specifically, the detection equipment may include a handheld detector or a liquid detector, etc. When there are staff on duty at the first inspection and security checkpoint, and the detection equipment is used for security inspection, there will be a record of the use of the detection equipment or the detection data in the system. Therefore, it is possible to obtain the detection information obtained by each detection equipment at the first inspection and security checkpoint within a preset time period, and check all the detection information to check whether there is information obtained by the detection equipment within the first time period. Since the information obtained by different detection equipment contains the identification of the detection equipment, if there is information obtained by the detection equipment within the first time period, the number of detection equipment that has obtained information within the first time period can be determined based on the identification in the obtained information, so as to determine the number as the target actual number of people on duty. Among them, the first time period includes the target inspection time, such as the target inspection time as the starting point after extending the preset time period backward, or the target inspection time as the end point after extending the preset time period forward, or the target inspection time as the midpoint after extending forward and backward for a period of time.

[0060] For example, if the first inspection and security checkpoint was originally equipped with two handheld detectors and one liquid detector, by searching the information obtained by each detection device of the first inspection and security checkpoint within the preset time period, it is found that only the detection information reported by the handheld detector 1 and the liquid detector was reported within the first time period. Therefore, it can be predicted that the staff only used the handheld detector 1 and the liquid detector within the first time period, so that it can be determined that at the target inspection time, the actual number of target on-duty personnel at the first inspection and security checkpoint is 2.

[0061] In this embodiment, the actual number of target personnel on duty at the first inspection and security checkpoint at the target inspection time is predicted by using the detection information obtained by the detection equipment and based on the number of detection equipment that reported the detection information within the first time period. Since the working conditions of the detection equipment can directly reflect the on-the-job status of the staff, the accuracy of the prediction result can be improved by predicting the actual number of target personnel on duty through the information obtained by the detection equipment.

[0062] Exemplarily, based on the above embodiments, when the target device includes a voice collection device, when determining the actual number of target personnel on duty based on the information obtained by the target device, the information collected by the voice collection device of the first inspection and security checkpoint in the second time period can be obtained, and the information collected by the voice collection device includes voice information, and the second time period includes the target inspection time. At least one target voiceprint information is extracted from the voice information, and each target voiceprint information is matched with each voiceprint information in the voiceprint library to obtain a matching result. The voiceprint library stores the voiceprint information of each staff member of the first inspection and security checkpoint, and the number of target voiceprint information representing a successful match in the matching result is determined as the actual number of target personnel on duty.

[0063] Specifically, a voice collection device may be set at each inspection and security checkpoint in the target location, and the voice collection device may be a microphone or other sound receiving device. By obtaining the voice information collected by the voice collection device set at the first inspection and security checkpoint in the second time period, and performing pre-processing such as denoising on the voice information, the target voiceprint information may be extracted from the pre-processed voice information based on the voiceprint feature extraction algorithm. The second time period may be the same as or different from the first time period, and the specific setting method of the second time period is similar to that of the first time period, and will not be repeated here.

[0064] In addition, the voiceprint information of each staff member at each security checkpoint can be stored in the voiceprint library in advance. After the target voiceprint information is extracted, the target voiceprint information can be matched with the voiceprint information of each staff member at the first security checkpoint in the voiceprint library to obtain a matching result.

[0065] Furthermore, the number of target voiceprint information representing successful matches in all matching results can be determined as the actual number of target personnel on duty. Among them, if the voiceprint information of a staff member at the first security checkpoint in the voiceprint database is successfully matched, it means that the target voiceprint information that has successfully matched is the voiceprint of a staff member at the first security checkpoint.

[0066] In this embodiment, the target voiceprint information can be extracted from the voice information collected by the voice collection device, and the target voiceprint information is matched with the voiceprint information of the staff at the pre-set first inspection and security checkpoint, so as to determine the actual number of target personnel on duty based on the matching results. This method can achieve the purpose of automatically predicting the actual number of target personnel on duty, and improves the prediction efficiency of the actual number of target personnel on duty.

[0067] Exemplarily, based on the above embodiments, when the target device includes a camera device and a detection device, when determining the actual number of on-duty personnel of the target based on the first image, the first number of on-duty personnel at the first inspection checkpoint can be determined based on the first image, and the second number of on-duty personnel at the first inspection checkpoint can be determined based on the information obtained by all detection devices at the first inspection checkpoint. Then, the actual number of on-duty personnel of the target can be determined based on the first number of on-duty personnel, the first weight corresponding to the camera device, the second number of on-duty personnel and the second weight corresponding to the detection device.

[0068] Specifically, in order to further improve the accuracy of the predicted number of people actually on duty at the target, it can be determined from multiple dimensions. When the target device includes a camera device and a detection device, the first number of people on duty at the first inspection and security checkpoint can be determined based on the first image captured by the camera device in the manner described in the above embodiment, and the second number of people on duty at the first inspection and security checkpoint can be determined based on the information obtained by all detection devices at the first inspection and security checkpoint in the manner described in the above embodiment.

[0069] In addition, the first weight corresponding to the camera device and the second weight corresponding to the detection device can be pre-set. Generally, the accuracy of predicting the actual number of people on duty through the camera device is higher than the accuracy of predicting the actual number of people on duty through the detection device. Therefore, the first weight can be set greater than the second weight.

[0070] A weighted average value between the first number of people on duty and the first weight corresponding to the camera equipment and the second number of people on duty and the second weight corresponding to the detection equipment is determined, and the weighted average value is determined as the target actual number of people on duty.

[0071] In this embodiment, the first number of on-the-job personnel determined by the camera device and the second number of on-the-job personnel determined by the detection device are used to jointly determine the target actual number of on-the-job personnel. Since the determination is made from multiple dimensions, the accuracy of the determined target actual number of on-the-job personnel can be improved.

[0072] It should be understood that when the target device includes a camera device, a detection device and a voice collection device, the first number of people on duty at the first inspection checkpoint can be determined based on the first image taken by the camera device in the manner as described in the above embodiments, and the second number of people on duty at the first inspection checkpoint can be determined based on the information obtained by all detection devices at the first inspection checkpoint in the manner described in the above embodiments, and the third number of people on duty at the first inspection checkpoint can be determined through the voice information collected by the voice collection device.

[0073] In addition, the first weight corresponding to the camera device, the second weight corresponding to the detection device, and the third weight corresponding to the voice acquisition device may be preset. The weighted average between the first number of people on duty and the first weight corresponding to the camera device, the second number of people on duty and the second weight corresponding to the detection device, and the third number of people on duty and the third weight corresponding to the voice acquisition device is determined, and the weighted average is determined as the target actual number of people on duty.

[0074] Exemplarily, based on the above-mentioned embodiments, when monitoring the on-the-job situation of the target place based on the actual number of people on duty and the target actual number of people on duty, the total actual number of people on duty can be determined based on all the actual number of people on duty and the target actual number of people on duty, and the total actual number of people on duty can be divided by the number of people who should be on duty at the target place to obtain the on-the-job rate of the target place, and the on-the-job rate is used to characterize the on-the-job situation of the target place.

[0075] Specifically, after determining the target actual number of people on duty at the first security checkpoint, the sum of the actual number of people on duty at each security checkpoint and the predicted target actual number of people on duty can be determined, and the sum can be determined as the total actual number of people on duty in the target location.

[0076] In addition, the sum of the number of people who should be on duty at each security checkpoint in the target place can be determined as the number of people who should be on duty at the target place, and the ratio of the total actual number of people on duty to the number of people who should be on duty at the target place can be determined as the on-duty rate of the target place staff. The on-duty rate can characterize the on-duty status of the staff in the target place.

[0077] In one embodiment, the on-duty rate of the staff at the target location can be determined according to the following formula (1): (1) in, represents the actual number of people on duty at the i-th inspection and security checkpoint in the target location in the j-th query statistics, and C represents the sum of the target actual number of people on duty predicted for all inspection and security checkpoints that have missed the actual number of people on duty. represents the number of people who should be on duty at the i-th security checkpoint in the target place in the j-th query statistics, and n represents the total number of security checkpoints. Therefore, It includes the number of people who should be on duty at all inspection and security checkpoints. It should be noted that in the above formula (1), when the actual number of people on duty at the kth inspection and security checkpoint is queried for the jth time, When the data is lost or omitted, it is considered In addition, the selection of query statistics times j is determined according to the off-peak period, low-peak period and peak period.

[0078] The determined on-the-job rate can optimize the configuration of staff in the target location, providing important data support for the operation and management of the target location. For example, when the on-the-job rate of staff in the target location is less than the warning value, a warning message will be issued.

[0079] Exemplarily, on the basis of the above-mentioned embodiments, after determining the actual number of people on duty at each inspection and security checkpoint in the target place, the flow of people at each inspection and security checkpoint can also be obtained. When the flow of people at the third inspection and security checkpoint is greater than the first preset flow of people, the flow of people at the fourth inspection and security checkpoint is less than the second preset flow of people, and the actual number of people on duty at the third inspection and security checkpoint is less than the actual number of people on duty at the fourth inspection and security checkpoint, a prompt message is output, and the prompt message is used to indicate that part of the staff at the fourth inspection and security checkpoint is transferred to the third inspection and security checkpoint, and the first preset flow of people is greater than the second preset flow of people.

[0080] Specifically, the flow of people at each inspection and security checkpoint can be detected by a camera or infrared, ultrasonic and other detection equipment. When it is determined that the flow of people at the third inspection and security checkpoint is greater than the first preset flow of people, and the flow of people at the fourth inspection and security checkpoint is less than the second preset flow of people, since the first preset flow of people is greater than the second preset flow of people, the flow of people at the third inspection and security checkpoint exceeds the flow of people at the fourth inspection and security checkpoint, indicating that the third inspection and security checkpoint should require more on-duty staff. If the actual number of people on duty at the third inspection and security checkpoint is less than the actual number of people on duty at the fourth inspection and security checkpoint at this time, there may be a situation of congestion of people flow or insufficient staff at the third inspection and security checkpoint. Therefore, a prompt message will be output to remind some staff at the fourth inspection and security checkpoint to be transferred to the third inspection and security checkpoint to alleviate the situation of insufficient staff at the third inspection and security checkpoint.

[0081] In this embodiment, the staff at each inspection and security checkpoint can be dynamically adjusted according to the flow of people at each inspection and security checkpoint and the actual number of people on duty, so as to achieve the purpose of real-time dynamic optimization of human resource allocation in the target place.

[0082] The on-the-job monitoring device for a target location provided by the present invention is described below. The on-the-job monitoring device for a target location described below and the on-the-job monitoring method for a target location described above can be referred to each other.

[0083] Figure 2 The structural diagram of the on-the-job monitoring device of the target place provided by the embodiment of the present invention is shown in FIG. Figure 2 As shown, the on-the-job monitoring device 200 of the target location includes: An acquisition module 11 is used to acquire the actual number of people on duty at each security checkpoint in the target location at multiple inspection times within a preset time period; A determination module 12 is used to determine the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time based on the actual number of people on duty corresponding to all the inspection times, and in the case where the target actual number of people on duty at the first inspection and security checkpoint at the target inspection time is missing, based on information obtained by a target device, wherein the target device is a device that can collect the working conditions of the first inspection and security checkpoint; The monitoring module 13 is used to monitor the on-duty status of the target place based on the actual number of on-duty personnel and the target actual number of on-duty personnel.

[0084] In one example embodiment, the target device comprises a camera device; The determining module 12 is specifically used for: Determine a second security checkpoint that is closest to the first security checkpoint; Controlling a first camera device corresponding to the second security checkpoint to rotate to a position of the first security checkpoint, and collecting information of the first security checkpoint through the first camera device, wherein the information collected by the first camera device includes a first image; Based on the first image, the actual number of on-duty personnel of the target is determined.

[0085] In an exemplary embodiment, the determining module 12 is specifically configured to: obtaining a position of the second inspection checkpoint relative to the first inspection checkpoint; Obtaining the current angle of the first camera device; determining a target angle based on the orientation and the current angle; The first camera device is controlled to rotate to the position of the first security checkpoint based on the target angle.

[0086] In an exemplary embodiment, the determining module 12 is specifically configured to: Controlling a second camera device corresponding to the first security checkpoint to collect images of the first security checkpoint; When image acquisition fails or the definition of the acquired second image is less than a preset definition, a second inspection and security checkpoint which is closest to the first inspection and security checkpoint is determined.

[0087] In an exemplary embodiment, the determining module 12 is specifically configured to: The first image is input into a number detection model to obtain the actual number of people on duty output by the number detection model; the number detection model is obtained by training an initial number detection model based on a sample image and label information corresponding to the sample image, and the label information is used to characterize the sample staff wearing preset style clothing in the sample image.

[0088] In one example embodiment, the target device comprises a detection device; The determining module 12 is specifically used for: Acquire information acquired by each detection device at the first security checkpoint within the preset time period; The number of detection devices that have information within a first time period is determined as the actual number of people on duty at the target; the first time period includes the target inspection time.

[0089] In an exemplary embodiment, the target device includes a voice acquisition device; The determining module 12 is specifically used for: Acquire information collected by a voice collection device at the first security checkpoint in a second time period, where the information collected by the voice collection device includes voice information, and the second time period includes the target inspection time; Extracting at least one target voiceprint information from the voice information; Matching each target voiceprint information with each voiceprint information in a voiceprint library to obtain a matching result, wherein the voiceprint library stores the voiceprint information of each staff member at the first security checkpoint; The number of target voiceprint information indicating successful matching in the matching result is determined as the actual number of target persons on duty.

[0090] In an exemplary embodiment, the target device further comprises a detection device; The determining module 12 is specifically used for: Determining a first number of people on duty at the first security checkpoint based on the first image; Determining a second number of on-duty personnel at the first inspection and security checkpoint based on information acquired by all detection devices at the first inspection and security checkpoint; The actual number of on-duty personnel of the target is determined based on the first number of on-duty personnel, the first weight corresponding to the camera device, the second number of on-duty personnel and the second weight corresponding to the detection device.

[0091] In an exemplary embodiment, the monitoring module 13 is specifically configured to: Determine the total actual number of employees on duty based on all the actual number of employees on duty and the target actual number of employees on duty; The total number of people actually on duty is divided by the number of people who should be on duty at the target place to obtain the on-duty rate of the target place, and the on-duty rate is used to characterize the on-duty situation of the target place.

[0092] In an exemplary embodiment, the apparatus further comprises: an output module, wherein: The acquisition module 11 is also used to obtain the flow of people at each of the inspection and security checkpoints; An output module is used to output a prompt message when the flow of people at the third inspection and security checkpoint is greater than the first preset flow of people, the flow of people at the fourth inspection and security checkpoint is less than the second preset flow of people, and the actual number of people on duty at the third inspection and security checkpoint is less than the actual number of people on duty at the fourth inspection and security checkpoint. The prompt message is used to indicate that some staff members of the fourth inspection and security checkpoint should be transferred to the third inspection and security checkpoint, and the first preset flow of people is greater than the second preset flow of people.

[0093] The on-the-job monitoring device for the target place of this embodiment can be used to execute the method of any embodiment in the on-the-job monitoring method embodiment for the target place. Its specific implementation process and technical effects are similar to those in the on-the-job monitoring method embodiment for the target place. For details, please refer to the detailed description in the on-the-job monitoring method embodiment for the target place, which will not be repeated here.

[0094] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the on-the-job monitoring method of the target place, the method comprising: obtaining the actual on-the-job number corresponding to multiple inspection times of each inspection and security checkpoint in the target place within a preset time period; determining the target actual on-the-job number of the first inspection and security checkpoint at the target inspection time when the target actual on-the-job number is missing based on the actual on-the-job number corresponding to all the inspection times, determining the target actual on-the-job number based on the information obtained by the target device, the target device being a device that can collect the working conditions of the first inspection and security checkpoint; monitoring the on-the-job condition of the target place based on each of the actual on-the-job number and the target actual on-the-job number.

[0095] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program 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 on-the-job monitoring method of the target place provided by the above-mentioned methods, and the method includes: obtaining the actual number of on-the-job people corresponding to each inspection and security checkpoint in the target place within a preset time period at multiple inspection times; determining the target actual number of on-the-job people at the first inspection and security checkpoint at the target inspection time based on the actual number of on-the-job people corresponding to all the inspection times, and determining the target actual number of on-the-job people based on information obtained by the target device, the target device being a device that can collect the working status of the first inspection and security checkpoint; monitoring the on-the-job status of the target place based on the actual number of on-the-job people and the target actual number of on-the-job people.

[0097] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the on-the-job monitoring method for a target place provided by the above-mentioned methods, the method comprising: obtaining the actual number of on-the-job persons corresponding to each inspection and security checkpoint in the target place within a preset time period at multiple inspection times; determining, based on the actual number of on-the-job persons corresponding to all the inspection times, a target actual number of on-the-job persons at the first inspection and security checkpoint at the target inspection time, in the absence of the target actual number of on-the-job persons, based on information obtained by a target device, the target device being a device that can collect the working conditions of the first inspection and security checkpoint; monitoring the on-the-job status of the target place based on the actual number of on-the-job persons and the target actual number of on-the-job persons.

[0098] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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.

[0100] 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 it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for on-the-job monitoring of a target location, characterized in that: include: Obtain the actual number of people on duty at each security checkpoint in the target location at multiple check times within a preset time period; In the case where the target actual number of people on duty at the first inspection checkpoint at the target inspection time is missing based on the actual number of people on duty corresponding to all the inspection times, the target actual number of people on duty is determined based on information obtained by a target device, where the target device is a device that can collect the working conditions of the first inspection checkpoint; Based on the actual number of people on duty and the target actual number of people on duty, the on-duty status of the target place is monitored.

2. The on-the-job monitoring method of a target location according to claim 1, characterized in that: The target device includes a camera device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Determine a second security checkpoint that is closest to the first security checkpoint; Controlling a first camera device corresponding to the second security checkpoint to rotate to a position of the first security checkpoint, and collecting information of the first security checkpoint through the first camera device, wherein the information collected by the first camera device includes a first image; Based on the first image, the actual number of on-duty personnel of the target is determined.

3. The on-the-job monitoring method of a target location according to claim 2, characterized in that: The controlling the first camera device corresponding to the second security checkpoint to rotate to the position of the first security checkpoint includes: obtaining a position of the second inspection checkpoint relative to the first inspection checkpoint; Obtaining the current angle of the first camera device; determining a target angle based on the orientation and the current angle; The first camera device is controlled to rotate to the position of the first security checkpoint based on the target angle.

4. The on-the-job monitoring method of a target location according to claim 2, characterized in that: The determining of a second security checkpoint that is closest to the first security checkpoint includes: Controlling a second camera device corresponding to the first security checkpoint to collect images of the first security checkpoint; When image acquisition fails or the definition of the acquired second image is less than a preset definition, a second inspection and security checkpoint which is closest to the first inspection and security checkpoint is determined.

5. The on-the-job monitoring method of a target location according to claim 2, characterized in that: The determining, based on the first image, the actual number of people on duty at the target includes: The first image is input into a number detection model to obtain the actual number of people on duty output by the number detection model; the number detection model is obtained by training an initial number detection model based on a sample image and label information corresponding to the sample image, and the label information is used to characterize the sample staff wearing preset style clothing in the sample image.

6. The on-the-job monitoring method of a target location according to claim 1, characterized in that: The target device includes a detection device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Acquire information acquired by each detection device at the first security checkpoint within the preset time period; The number of detection devices that have information within a first time period is determined as the actual number of people on duty at the target; the first time period includes the target inspection time.

7. The on-the-job monitoring method of a target location according to claim 1, characterized in that: The target device includes a voice acquisition device; The determining the actual number of people on duty at the target based on the information obtained from the target device includes: Acquire information collected by a voice collection device at the first security checkpoint in a second time period, where the information collected by the voice collection device includes voice information, and the second time period includes the target inspection time; Extracting at least one target voiceprint information from the voice information; Matching each target voiceprint information with each voiceprint information in a voiceprint library to obtain a matching result, wherein the voiceprint library stores the voiceprint information of each staff member at the first security checkpoint; The number of target voiceprint information indicating successful matching in the matching result is determined as the actual number of target persons on duty.

8. The on-the-job monitoring method of a target location according to claim 2, characterized in that: The target device also includes a detection device; The determining, based on the first image, the actual number of people on duty at the target includes: Determining a first number of people on duty at the first security checkpoint based on the first image; Determining a second number of on-duty personnel at the first inspection and security checkpoint based on information acquired by all detection devices at the first inspection and security checkpoint; The actual number of on-duty personnel of the target is determined based on the first number of on-duty personnel, the first weight corresponding to the camera device, the second number of on-duty personnel and the second weight corresponding to the detection device.

9. The on-the-job monitoring method of a target location according to any one of claims 1 to 8, characterized in that: The monitoring of the on-the-job situation of the target place based on the actual number of people on duty and the target actual number of people on duty includes: Determine the total actual number of employees on duty based on all the actual number of employees on duty and the target actual number of employees on duty; The total number of people actually on duty is divided by the number of people who should be on duty at the target place to obtain the on-duty rate of the target place, and the on-duty rate is used to characterize the on-duty situation of the target place.

10. The on-the-job monitoring method of a target location according to any one of claims 1 to 8, characterized in that: The method further comprises: Obtaining the flow of people at each of the security checkpoints; When the flow of people at the third inspection and security checkpoint is greater than the first preset flow of people, the flow of people at the fourth inspection and security checkpoint is less than the second preset flow of people, and the actual number of people on duty at the third inspection and security checkpoint is less than the actual number of people on duty at the fourth inspection and security checkpoint, a prompt message is output, wherein the prompt message is used to indicate that some staff members of the fourth inspection and security checkpoint are transferred to the third inspection and security checkpoint, and the first preset flow of people is greater than the second preset flow of people.

Images