Target area supervision method and device and related product

Abstract

The invention discloses a target area supervision method and apparatus, and a related product. The method comprises the steps of obtaining target monitoring data of a target area within a first preset time period; analyzing and processing the target monitoring data to obtain target analysis data; determining a target risk probability corresponding to the target analysis data; when the target risk probability is greater than a preset risk probability, determining an emergency scheme set corresponding to the target analysis data, and obtaining a target emergency scheme set; generating a target prompt message according to the target emergency scheme set; generating a target prompt voice according to the target prompt message; playing a target prompt voice in a target security room corresponding to the target area by using an audio transmission technology to prompt a worker in the target security room to enter an emergency working state; and executing the target emergency operation according to the target emergency scheme set. By adopting the embodiment of the invention, the security can be timely and quickly notified.

Description

Technical Field

[0001] The present invention relates to the field of monitoring management technology, and in particular to a target area monitoring method, device and related products. Background Art

[0002] In certain specific areas (for example, cafeterias, tourist attractions, etc.), there are often large crowds of people gathering, and contact and interaction between people are relatively frequent, so conflicts are inevitable. For example, in the cafeteria, conflicts may arise due to problems such as queuing and competition for seats. In another example, in tourist attractions, friction and conflicts may arise due to factors such as crowded tourists and competition for photo spots.

[0003] In order to prevent conflicts from escalating and endangering the personal safety of others, corresponding emergency plans need to be implemented. For example, notifying security guards to arrive in time to stop the conflict. However, the process from conflict to notifying security guards takes some time, which may lead to the escalation of conflicts. Therefore, how to notify security guards in a timely and rapid manner has become a problem that needs to be solved urgently. Summary of the invention

[0004] The embodiment of the present invention provides a target area supervision method, device and related products, which obtains monitoring data of the target area, analyzes and processes the monitoring data to obtain analysis data, determines a risk probability based on the analysis data, and when the risk probability is greater than a certain value, notifies the staff of the security room, that is, notifies the security guard, so that they can arrive at the target area in time to ensure the safety of the people in the target area. In this way, the security guard can be notified in time and quickly.

[0005] In a first aspect, an embodiment of the present invention provides a target area supervision method, which is applied to a supervision system, and the method includes:

[0006] Acquire target monitoring data of a target area within a first preset time period;

[0007] Analyzing and processing the target monitoring data to obtain target analysis data;

[0008] Determining a target risk probability corresponding to the target analysis data;

[0009] When the target risk probability is greater than a preset risk probability, determining a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set;

[0010] generating a target prompt message according to the target emergency plan set;

[0011] Generate a target prompt voice according to the target prompt message;

[0012] Using audio transmission technology, the target prompt voice is played in the target security room corresponding to the target area to prompt the staff of the target security room to enter an emergency working state;

[0013] Execute target emergency operations according to the target emergency plan set.

[0014] In a second aspect, an embodiment of the present invention provides a target area supervision device, including: an acquisition unit, an analysis unit, a control unit, and an emergency unit, wherein:

[0015] The acquisition unit is used to acquire target monitoring data of the target area within a first preset time period;

[0016] The analysis unit is used to analyze and process the target monitoring data to obtain target analysis data; and determine the target risk probability corresponding to the target analysis data;

[0017] The control unit is used to determine the emergency plan set corresponding to the target analysis data when the target risk probability is greater than the preset risk probability, and obtain the target emergency plan set; generate a target prompt message according to the target emergency plan set; and generate a target prompt voice according to the target prompt message;

[0018] The emergency unit is used to use audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter the emergency working state; and perform the target emergency operation according to the target emergency plan set.

[0019] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory is used to store one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the present application.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the present application.

[0021] In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package.

[0022] It can be seen that by implementing the target area supervision method in the embodiment of the present invention, the following beneficial effects are achieved:

[0023] Obtain target monitoring data of the target area within a first preset time period; analyze and process the target monitoring data to obtain target analysis data; determine the target risk probability corresponding to the target analysis data; when the target risk probability is greater than the preset risk probability, determine the emergency plan set corresponding to the target analysis data to obtain the target emergency plan set; generate a target prompt message according to the target emergency plan set; generate a target prompt voice according to the target prompt message; use audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter the emergency working state; perform target emergency operations according to the target emergency plan set. On the one hand, by analyzing and processing the target monitoring data, potential risks and problems in the target area can be discovered in time. On the other hand, when the target risk probability is greater than the preset risk probability, use audio transmission technology to notify the staff of the security room, that is, notify the security guard, so that they can rush to the target area in time to ensure the safety of people in the target area. In this way, the security guard can be notified in time and quickly. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0025] Figure 1 It is a block diagram of a supervision system provided in an embodiment of the present application;

[0026] Figure 2 is a flow chart of a target area supervision method provided in an embodiment of the present application;

[0027] Figure 3 It is a block diagram of the functional units of a target area supervision device provided in an embodiment of the present application;

[0028] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The electronic devices described in the embodiments of the present application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, video matrices, monitoring platforms, mobile Internet devices (mobile internet devices, MID) or wearable devices, etc. The above are only examples and not exhaustive, including but not limited to the above devices. Of course, the above electronic devices can also be servers, for example, cloud servers.

[0033] See also Figure 1 , Figure 1 is a block diagram of a monitoring system 100 provided in an embodiment of the present application, such as Figure 1 As shown, the monitoring system 100 may include a monitoring module 101 , an analysis module 102 , a control module 103 , and a communication module 104 .

[0034] The monitoring module 101 may include at least one of the following: a thermal imaging sensor, a camera, a scanner, etc., which are not limited here; the monitoring module 101 may be used to collect and organize the monitoring data of the target area. The above monitoring data may include data on environmental sanitation, employee work conditions, dining conditions of the crowd, monitoring video, monitoring audio, etc. The monitoring module 101 may also transmit the organized data to the analysis module 102 or the control module 103.

[0035] The analysis module 102 can be used to analyze and process the data collected by the monitoring module 101 to extract useful information and obtain analysis results. This can be achieved using data mining, statistical analysis, pattern recognition and other technologies. The analysis module 102 can also classify, cluster, and mine association rules on the data according to the rules and algorithms preset by the staff in advance to discover potential problems and risks.

[0036] Among them, the control module 103 can determine the corresponding emergency plan set according to the analysis results of the analysis module 102. This can include early warning, notification, adjustment of operation process, suspension of production, notification of security room and other measures. The control module 103 can also be linked with other systems or devices to achieve real-time control and management of the target area.

[0037] The communication module 104 is responsible for transmitting the prompt message generated by the supervision system 100 to relevant personnel or systems, for example, to security guards or teachers. This can be achieved through text messages, emails, software push, video, audio, etc. The communication module 104 can also receive external feedback and instructions to adjust and optimize the supervision system.

[0038] See also Figure 2 , Figure 2 This is a flow chart of a target area supervision method provided in an embodiment of the present application. The method can be applied to a supervision system. The supervision system may include: a monitoring module, an analysis module, a control module, and a communication module. The method includes:

[0039] S201. Acquire target monitoring data of a target area within a first preset time period.

[0040] In the embodiment of the present application, the target area may be one of the following: a cafeteria, a library, a classroom, a scenic spot, etc., which is not limited here. The monitoring module may include a camera and a recording device; the monitoring data may include at least one of the following: environmental sanitation, employee work conditions, dining conditions of the crowd, surveillance video, surveillance audio, etc., which are not limited here.

[0041] In a specific embodiment, some suitable locations can be selected in the target area, for example, the center of the ceiling of the target area, the entrance and exit of the target area, etc., and the monitoring modules can be installed at these locations. Then, the target area can be monitored by the monitoring module within a first preset time period to obtain target monitoring data. Specifically, the first preset time period can be a pre-set or system default, or the first preset time period can be the duration of certain specific scenes. These specific scenes can include at least one of the following: queuing scenes, class scenes, travel scenes, etc., which are not limited here. Queuing scenes often appear in cafeterias, such as queuing for meals, queuing for payment, etc. In the queuing scene, the first preset time period can be the queuing time of the crowd. The monitoring module obtains the video / audio data of the crowd queuing within the first preset time period, that is, the target monitoring data of the target area.

[0042] S202: Analyze and process the target monitoring data to obtain target analysis data.

[0043] In the embodiment of the present application, the analysis method for analyzing and processing the target monitoring data may include at least one of the following: trend analysis, human behavior analysis, correlation analysis, prediction model, etc., which are not limited here.

[0044] In a specific embodiment, human behavior analysis can be used, and the analysis module can be used to perform human behavior analysis on relevant data in the target monitoring data to obtain target analysis data.

[0045] Optionally, in step S202, the target monitoring data includes a target monitoring video; and analyzing and processing the target monitoring data to obtain target analysis data may include the following steps:

[0046] A1. Divide the target area into regions to obtain a plurality of divided regions;

[0047] A2. Segment the target surveillance video at preset time intervals to obtain multiple surveillance videos;

[0048] A3. Performing face recognition on each of the plurality of surveillance videos to obtain a plurality of face recognition results; each face recognition result corresponds to a number of faces;

[0049] A4. Determine a face recognition result in which the number of faces among the multiple face recognition results is greater than or equal to a preset number of faces, and obtain at least one face recognition result;

[0050] A5. Performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data;

[0051] A6. Compare and analyze the target human behavior data with the preset dangerous behavior database to obtain target analysis data.

[0052] In the embodiment of the present application, the preset time interval and the preset number of faces can be pre-set or system default; the human behavior data can include at least one of the following: position data, posture data, motion data, facial expression data, etc., which are not limited here.

[0053] In a specific embodiment, the target area can be divided into multiple divided areas. Specifically, the target area can be divided into different areas according to the functions of different areas. For example, assuming that the target area is a cafeteria, it can be divided into: queuing area, dining area, food collection area, kitchen area, cleaning area, etc., which are not limited here. Then, the target monitoring video can be segmented at preset time intervals to obtain multiple monitoring videos.

[0054] Furthermore, face recognition can be performed on the above-mentioned multiple surveillance videos to obtain multiple face recognition results, each face recognition result corresponding to a number of faces. Specifically, faces in the above-mentioned multiple surveillance videos can be identified by a face recognition algorithm (for example, a feature extraction algorithm) to obtain multiple recognized faces. Then, these multiple recognized faces can be compared with a preset face library to determine the identity information of these multiple recognized faces to obtain multiple face recognition results. Then, face recognition results in which the number of faces in these multiple face recognition results is greater than or equal to the preset number of faces can be determined to obtain at least one face recognition result.

[0055] Furthermore, human behavior analysis can be performed on at least one surveillance video corresponding to at least one of the above-mentioned face recognition results to obtain target human behavior data. Specifically, human behavior in the surveillance video can be identified through a behavior recognition algorithm to determine the behavior type of each human body to obtain target human behavior data. Then, the target human behavior data can be compared and analyzed with a preset dangerous behavior database to obtain target analysis data. Specifically, each human behavior data in the target human behavior data can be compared with the data in the preset dangerous behavior database to obtain a target comparison result, and the number of occurrences, occurrence time, occurrence location of different dangerous behaviors in the target comparison result, as well as the degree of danger of different dangerous behaviors, can be counted to obtain the target analysis data.

[0056] In addition, dangerous persons can be identified for other face recognition results that are less than a preset number of faces among the above-mentioned multiple face recognition results. Specifically, the faces in other face recognition results can be compared with a preset face library to obtain identity data corresponding to the faces in other face recognition results, as well as their past behavior records in the target area. When dangerous behavior is found in the past behavior records, a human behavior analysis is performed to obtain other human behavior data. If no dangerous behavior is found, it can be determined that no dangerous behavior has occurred in the video corresponding to the other face recognition results, or the probability of dangerous behavior occurring is very small.

[0057] It needs to be explained that the preset face library can be the face database of the above-mentioned target area. Before entering the target area, students or employees can provide their identity information and face images through online registration or on-site registration to create their own face library records, thereby obtaining the preset face library; the preset dangerous behavior database includes dangerous behavior data of the human body, such as hitting actions, falling actions, etc., which are not limited here.

[0058] In this way, a plurality of divided areas are obtained by dividing the target area; a plurality of monitoring videos are obtained by segmenting the target surveillance video at preset time intervals; face recognition is performed on the plurality of surveillance videos to obtain a plurality of face recognition results; a face recognition result in which the number of faces is greater than or equal to the preset number of faces among the plurality of face recognition results is determined to obtain at least one face recognition result; a human behavior analysis is performed on at least one surveillance video corresponding to at least one face recognition result to obtain target human behavior data; the target human behavior data is compared and analyzed with a preset dangerous behavior database to obtain target analysis data. On the one hand, by dividing the target area and performing segmentation processing and face recognition on the surveillance video, the activities of people in the target area can be more accurately located and identified. On the other hand, by comparing and analyzing the human behavior data with the preset dangerous behavior database, it is possible to quickly and accurately determine whether the behavior of people conforms to the preset behavioral norms and standards, which helps to promptly discover abnormal behavior and safety hazards and take corresponding measures to resolve them.

[0059] Optionally, step A5, performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data, may include the following steps:

[0060] B1. Determine, according to the at least one face recognition result, personnel distribution data corresponding to the multiple divided areas in the at least one surveillance video to obtain multiple personnel distribution data; each divided area corresponds to one personnel distribution data;

[0061] B2. determining a first abnormality degree corresponding to each of the plurality of personnel distribution data, to obtain a plurality of first abnormality degrees;

[0062] B3. Determine the first analysis priorities of the multiple divided areas according to the multiple first abnormality degrees to obtain multiple first analysis priorities; each divided area corresponds to a first analysis priority; the greater the abnormality degree, the higher the priority;

[0063] B4. Perform human behavior analysis on the multiple divided areas according to the multiple first analysis priorities to obtain the target human behavior data.

[0064] In an embodiment of the present application, personnel distribution data may include at least one of the following: location data, number of people, crowd density, distribution time, personnel characteristics, etc., which are not limited here; abnormality is a parameter indicating the degree of abnormal behavior of the crowd, and the value range of abnormality can be 0 to 100.

[0065] In a specific embodiment, the personnel distribution data corresponding to multiple divided areas in at least one surveillance video can be determined based on the above-mentioned at least one face recognition result to obtain multiple personnel distribution data. Specifically, the face recognition results can be first cut and separated according to the above-mentioned multiple divided areas to obtain multiple partial face recognition results, one divided area corresponds to one partial face recognition result, and then, multiple personnel distribution data can be determined based on the multiple partial face recognition results.

[0066] Then, the first abnormality degree corresponding to each personnel distribution data in the multiple personnel distribution data can be determined to obtain multiple first abnormality degrees. Further, the first analysis priorities of the multiple divided areas can be determined according to the multiple first abnormality degrees to obtain multiple first analysis priorities. The larger the abnormality degree, the higher the priority. For example, the abnormality degree can be 0, then the corresponding first analysis priority is the lowest priority, and the abnormality degree can be 100, then the corresponding first analysis priority is the highest priority. Then, human behavior analysis can be performed on the multiple divided areas according to the multiple first analysis priorities to obtain target human behavior data. Specifically, human behavior analysis can be performed on the above-mentioned multiple divided areas according to the order of size of the multiple first analysis priorities. A human detection algorithm can be used to perform human body recognition on the divided areas in the monitoring video to obtain the position and boundary of each human body in the divided area, that is, human body coordinate data. Then, a behavior recognition algorithm can be used to perform behavior recognition on the human body in the divided area according to the human body coordinate data to determine the behavior data of each human body, for example, walking, standing, sitting, waving, clenching fists, hitting, etc., which are not limited here, to obtain target human behavior data.

[0067] In this way, the personnel distribution data corresponding to multiple divided areas in at least one surveillance video are determined through at least one face recognition result, and multiple personnel distribution data are obtained; then, the first abnormality degree corresponding to each personnel distribution data in the multiple personnel distribution data is determined, and multiple first abnormality degrees are obtained; then, the first analysis priority of the multiple divided areas is determined according to the multiple first abnormality degrees, and multiple first analysis priorities are obtained; finally, human behavior analysis is performed on the multiple divided areas according to the multiple first analysis priorities to obtain target human behavior data, and the first analysis priority of the divided area is determined according to the first abnormality degree. Resources and energy can be concentrated on areas that need attention, and areas with high analysis priority are given priority, and areas with low analysis priority are analyzed later, which can improve analysis efficiency.

[0068] Optionally, step B2, determining the first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees, may include the following steps:

[0069] C1. Determine the number of personnel corresponding to each personnel distribution data in the plurality of personnel distribution data to obtain a plurality of personnel numbers;

[0070] C2. Determine a reference abnormality degree corresponding to each number of personnel in the multiple numbers of personnel to obtain multiple reference abnormality degrees;

[0071] C3. Acquire environmental data corresponding to each of the multiple divided areas to obtain multiple environmental data;

[0072] C4. Determine a first influence coefficient corresponding to each of the plurality of environmental data to obtain a plurality of first influence coefficients;

[0073] C5. Optimizing corresponding reference abnormality degrees among the multiple reference abnormality degrees according to the multiple first influence coefficients to obtain the multiple first abnormality degrees.

[0074] In the embodiment of the present application, the environmental data may include at least one of the following: temperature, humidity, air quality, noise level, smoke concentration, etc., which are not limited here.

[0075] In a specific embodiment, the number of personnel corresponding to each personnel distribution data in a plurality of personnel distribution data may be determined first to obtain a plurality of personnel numbers. Specifically, the number of people may be included in the personnel distribution data, and the number of personnel may be obtained by selecting the corresponding number of people data from the above-mentioned plurality of personnel distribution data, thereby obtaining a plurality of personnel numbers. Then, a reference abnormality degree corresponding to each personnel number in the plurality of personnel numbers may be determined to obtain a plurality of reference abnormality degrees. Specifically, a mapping relationship between a preset number of personnel and an abnormality degree may be pre-stored, and a plurality of reference abnormality degrees corresponding to the above-mentioned plurality of personnel numbers may be determined based on the mapping relationship.

[0076] Further, the environmental data corresponding to each of the multiple divided areas can be obtained to obtain multiple environmental data. Specifically, the target area can be detected by multiple detection devices to obtain multiple environmental data. For example, the temperature of the target area can be detected by a temperature sensor, and the smoke concentration of the target area can be detected by a smoke sensor. Then, the first influence coefficient corresponding to each of the multiple environmental data is determined to obtain multiple first influence coefficients. Specifically, since the environment in which a person lives has a great influence on the person's mood, once the person's mood is not good, the probability of conflict with other people will increase to a certain extent. Therefore, when determining the abnormality, it is necessary to consider the impact of the environment on the person. In order to quantify the impact, the mapping relationship between the preset environmental data and the influence coefficient can be pre-stored, and the multiple first influence coefficients corresponding to the above multiple environmental data can be determined based on the mapping relationship; then, the corresponding reference abnormality in the multiple reference abnormality can be optimized according to the multiple first influence coefficients to obtain multiple first abnormality, as follows:

[0077] First abnormality degree = (1 + first influence coefficient) × reference abnormality degree;

[0078] Each of the multiple reference abnormality degrees may be optimized by the above formula to obtain multiple first abnormality degrees.

[0079] In this way, by determining the number of personnel corresponding to multiple personnel distribution data, multiple numbers of personnel are obtained; then, the reference abnormality degrees corresponding to the multiple numbers of personnel are determined to obtain multiple reference abnormality degrees; then, the environmental data corresponding to the multiple divided areas are obtained to obtain multiple environmental data; then, the first influence coefficients corresponding to the multiple environmental data are determined to obtain multiple first influence coefficients; finally, the corresponding reference abnormality degrees in the multiple reference abnormality degrees are optimized according to the multiple first influence coefficients to obtain multiple first abnormality degrees. On the one hand, by determining the number of personnel and the reference abnormality degrees, the population density and activity status in different areas can be more accurately understood. On the other hand, by obtaining the environmental data corresponding to the divided areas and determining the first influence coefficient corresponding to the environmental data, the influence of environmental factors on the abnormality of personnel can be considered, making the analysis results more comprehensive and accurate.

[0080] Optionally, in step A5, the target monitoring data also includes target monitoring audio data; the target monitoring audio data includes: recorded audio, recording time, and recording location; performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data may include the following steps:

[0081] D1. Determine the monitoring audio corresponding to the multiple divided areas according to the recording position in the target monitoring audio data, and obtain multiple monitoring audios; each monitoring audio corresponds to a divided area;

[0082] D2. Determine the text data corresponding to each of the multiple monitoring audios to obtain multiple text data;

[0083] D3, determining the second abnormality degrees corresponding to the plurality of divided areas according to the plurality of text data, to obtain a plurality of second abnormality degrees, wherein each second abnormality degree corresponds to a divided area;

[0084] D4. Determine the volume value corresponding to each of the multiple monitoring audios to obtain multiple volume values;

[0085] D5. Determine a second influence coefficient corresponding to each volume value in the multiple volume values ​​to obtain multiple second influence coefficients;

[0086] D6. Optimizing corresponding second abnormality degrees among the plurality of second abnormality degrees according to the plurality of second influence coefficients to obtain a plurality of third abnormality degrees;

[0087] D7. Determine the second analysis priorities of the multiple divided areas according to the multiple third abnormality degrees to obtain multiple second analysis priorities; each divided area corresponds to a second analysis priority;

[0088] D8. Perform human behavior analysis on the multiple divided areas according to the multiple second analysis priorities to obtain the target human behavior data.

[0089] In the embodiment of the present application, the method of converting the monitoring audio into text data may include at least one of the following: manual transcription, speech recognition technology, etc., which is not limited here.

[0090] In a specific embodiment, the recording position in the target monitoring audio data can be extracted first to obtain multiple recording positions, one recording position can correspond to one monitoring audio, and then the positional relationship between the above-mentioned multiple recording positions and the multiple divided areas can be determined. For example, if the recording position a is located in the divided area a, then the monitoring audio corresponding to the recording position a is the monitoring audio of the divided area a. In this way, multiple monitoring audios corresponding to the multiple divided areas can be obtained; each monitoring audio corresponds to a divided area; then, the text data corresponding to each monitoring audio in the multiple monitoring audios can be determined to obtain multiple text data. Specifically, the above-mentioned multiple monitoring audios can be converted into text using speech recognition technology to obtain multiple text data.

[0091] Next, second abnormality degrees corresponding to multiple divided areas can be determined based on multiple text data to obtain multiple second abnormality degrees; each second abnormality degree corresponds to a divided area. Specifically, keyword extraction can be performed on the text data. For example, the text data can be segmented first to split the text data into words or phrases. Then, a keyword extraction algorithm (for example, a text ranking algorithm Text Rank) can be used to extract keywords from the segmented text data to obtain multiple keywords. The expression meanings of the multiple keywords are analyzed, and a tension value can be assigned to each keyword according to different expression meanings. For example, a mapping relationship between preset keywords and tension values ​​can be pre-stored, and multiple tension values ​​corresponding to multiple keywords are determined based on the mapping relationship. The multiple tension values ​​are added together to obtain the total tension value of the text data, which is the second abnormality degree.

[0092] Further, the volume value corresponding to each monitoring audio in the multiple monitoring audios can be determined to obtain multiple volume values. Specifically, the monitoring audio can be converted into an audio signal first, and the volume value can be calculated according to the amplitude value of the audio signal. For example, the square root of the square average of the audio signal can be calculated using the root mean square method to obtain the volume value; the second influence coefficient corresponding to each volume value in the multiple volume values ​​is determined to obtain multiple second influence coefficients. Specifically, when people are excited or in conflict with others, their speaking voices will unconsciously become louder to express their bad mood. Therefore, when determining the second abnormality, the relationship between the volume value and the abnormality needs to be considered. The mapping relationship between the preset volume value and the influence coefficient can be pre-stored, and the multiple second influence coefficients corresponding to the above multiple volume values ​​are determined based on the mapping relationship; the corresponding second abnormality degrees in the multiple second abnormality degrees are optimized according to the multiple second influence coefficients to obtain multiple third abnormality degrees, as follows:

[0093] The third abnormality degree = (1 + second influence coefficient) × second abnormality degree;

[0094] The multiple second abnormality degrees can be optimized by the above formula to obtain multiple third abnormality degrees; then, the second analysis priorities of the multiple divided areas can be determined according to the multiple third abnormality degrees to obtain multiple second analysis priorities, and the greater the abnormality degree, the higher the priority; each second priority analysis level corresponds to a divided area; then, the multiple second analysis priorities can be sorted according to their sizes to obtain a second analysis priority order, and human behavior analysis can be performed on the multiple divided areas according to the second analysis priority order to obtain target human behavior data.

[0095] In this way, multiple monitoring audios corresponding to multiple divided areas are determined according to the recording positions in the target monitoring audio data; then, multiple text data corresponding to the multiple monitoring audios are determined, and multiple second abnormality degrees corresponding to the multiple divided areas are determined according to the multiple text data; then, multiple volume values ​​corresponding to the multiple monitoring audios are determined, and then multiple second influence coefficients corresponding to the multiple volume values ​​are determined; then, the corresponding second abnormality degrees in the multiple second abnormality degrees are optimized according to the multiple second influence coefficients to obtain multiple third abnormality degrees; finally, multiple second analysis priorities of the multiple divided areas are determined according to the multiple third abnormality degrees, and human behavior analysis is performed on the multiple divided areas according to the multiple second analysis priorities to obtain target human behavior data. On the one hand, by determining different monitoring audios corresponding to different divided areas according to the recording positions in the monitoring audio data, the sound conditions in different areas can be understood more accurately. On the other hand, by determining multiple volume values ​​corresponding to the multiple monitoring audios and determining multiple second influence coefficients corresponding to the multiple volume values, the influence of volume size on abnormality degree can be considered, making the analysis result more comprehensive and accurate.

[0096] S203: Determine the target risk probability corresponding to the target analysis data.

[0097] In the embodiment of the present application, the risk probability represents the probability of a dangerous event occurring in the target area.

[0098] In a specific embodiment, the target risk probability corresponding to the target area can be determined based on the target analysis data. Specifically, the target analysis data may include target dangerous behavior data, and the target danger level corresponding to the target dangerous behavior data. Then, a mapping relationship between a preset danger level and risk probability may be pre-stored, and the target risk probability corresponding to the target danger level may be determined based on the mapping relationship.

[0099] S204: When the target risk probability is greater than a preset risk probability, determine a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set.

[0100] In the embodiment of the present application, the emergency plan set may include methods for handling multiple dangerous events.

[0101] In a specific embodiment, when the target risk probability is greater than the preset risk probability, it can be considered that a dangerous event has occurred in the target area, or that a dangerous event is about to occur in the target area. In this case, it is necessary to determine the emergency plan set corresponding to the target analysis data through the control module to obtain the target emergency plan set.

[0102] Optionally, step S204, determining a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set, may include the following steps:

[0103] 41. Determine target risk events that may occur in the target area according to the target analysis data;

[0104] 42. Determine the emergency plan set corresponding to the target risk event and obtain the target emergency plan set.

[0105] In the embodiment of the present application, risk events may include at least one of the following: quarrels, fights, food safety incidents, stampedes, etc., which are not limited here; target risk events may include multiple risk events.

[0106] In a specific embodiment, target risk events that may occur in the target area can be determined based on target analysis data. Specifically, the target analysis data may include target dangerous behavior data. Then, target risk events that may occur in the target area can be judged based on the target dangerous behavior types in the target dangerous behavior data. A mapping relationship between preset dangerous behavior types and risk events can be pre-stored, and the target risk events corresponding to the target dangerous behavior types are determined based on the mapping relationship. For example, when the target dangerous behavior types include fisting, hitting, etc., fighting events can be added to the target risk events. When the personnel density in the target analysis data exceeds a preset density value (for example, 10 people per square meter), a stampede event can be added to the target risk events. And so on, the final target risk event can be obtained.

[0107] It should be explained that the target dangerous behavior data can be obtained based on surveillance videos, which include dangerous actions performed by people in the surveillance videos, such as hitting actions, falling actions, etc., which are not limited here.

[0108] Furthermore, the emergency plan set corresponding to the target risk event can be determined to obtain the target emergency plan set. Specifically, an emergency plan can be assigned to each risk event included in the target risk event, and the combination is the emergency plan set.

[0109] It should be explained that the regulatory system can formulate specific emergency plans based on the characteristics and possible impacts of different types of risk events. Emergency plans can include emergency response processes, emergency resource allocation, emergency communications, emergency training and drills, etc. By integrating the emergency plans formulated for each risk event, a complete set of emergency plans is formed.

[0110] S205: Generate a target prompt message according to the target emergency plan set.

[0111] In an embodiment of the present application, the communication module may generate a target prompt message according to the target emergency plan set. Specifically, the target prompt message may be determined according to the implementation of the target emergency plan. The target prompt message may also be displayed on a display screen in the target area so that people in the target area can understand the current situation and evacuate or take refuge. For example, assuming that the target emergency plan set is a plan to prevent trampling, then the target prompt message may be "Don't worry, please walk slowly according to the instructions of the staff", or the target prompt message may be "People in place A, there are fewer people in place B, you can go to place B, please do not take the elevator, please take the stairs", etc., and other similar suggestive words.

[0112] S206: Generate a target prompt voice according to the target prompt message.

[0113] In an embodiment of the present application, the control module may generate a target prompt voice according to the target prompt message. Specifically, it may determine what kind of help the target area currently needs according to the target prompt message, and generate a help voice based on the help needed by the target area, that is, the target prompt voice. For example, there are too many people in the target area and someone is needed to maintain order, then the target prompt voice may be "There are too many people in the target area, security guards, come quickly."

[0114] S207: using audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter an emergency working state.

[0115] In an embodiment of the present application, the target security room responsible for the target area can be found first, and then the target prompt voice can be played in the target security room using audio transmission technology through the communication module to prompt the staff of the target security room to enter the emergency working state.

[0116] Optionally, in step S207, after playing the target prompt voice in the target security room corresponding to the target area using the audio transmission technology, the method may further include the following steps:

[0117] 71. Obtain the security room monitoring data of the target security room within the second preset time period;

[0118] 72. Analyze and process the security room monitoring data to obtain security room analysis data;

[0119] 73. Determine a target optimization solution corresponding to the security room analysis data;

[0120] 74. Optimize the subsequent supervision process of the target area according to the target optimization plan.

[0121] In the embodiment of the present application, the second preset time period may be a system default or preset in advance.

[0122] In a specific embodiment, the security room monitoring data of the target security room within the second preset time period can be obtained through the monitoring module. Specifically, the target security room can be photographed by a camera within the second preset time period to obtain the security room monitoring data.

[0123] It needs to be explained that the second preset time period is the time period after the first preset time period. The purpose of obtaining the security room monitoring data is to determine whether the staff in the security room are performing their security work seriously and whether there is any slackness. If there is any slackness, corrections need to be made and the security room's work plan needs to be optimized.

[0124] Next, the security room monitoring data can be analyzed and processed through the analysis module to obtain security room analysis data. Specifically, the security behavior in the security room monitoring data can be analyzed, for example, whether there is any violation, whether the security work is carried out within the specified time, etc., to obtain security room analysis data.

[0125] Furthermore, the control module can determine a target optimization scheme corresponding to the security room analysis data; the supervision system can optimize the subsequent supervision process of the target area according to the target optimization scheme. Specifically, the poor performance of the target security room, that is, the security shortcomings, can be found out based on the security room analysis data. Then, an optimization scheme, that is, the target optimization scheme, can be formulated based on the security shortcomings. For example, a mapping relationship between preset security shortcomings and optimization schemes can be pre-stored, and the target optimization scheme corresponding to the security shortcomings of the target security room is determined based on the mapping relationship. Finally, the above-mentioned supervision system can execute the above-mentioned target optimization scheme to optimize the subsequent supervision process of the target area.

[0126] S208: Execute target emergency operations according to the target emergency plan set.

[0127] In an embodiment of the present application, the supervision system may perform a target emergency operation according to a target emergency plan set. Specifically, the emergency operation to be performed by the supervision system, that is, the target emergency operation, may be first determined according to the target emergency plan set. According to the target emergency operation, each component module in the above-mentioned supervision system may be controlled to work and perform the target emergency operation to protect the safety of personnel in the target area.

[0128] It can be seen that by implementing the target area supervision method in the embodiment of the present invention, the following beneficial effects are achieved:

[0129] Obtain target monitoring data of the target area within a first preset time period; analyze and process the target monitoring data to obtain target analysis data; determine the target risk probability corresponding to the target analysis data; when the target risk probability is greater than the preset risk probability, determine the emergency plan set corresponding to the target analysis data to obtain the target emergency plan set; generate a target prompt message according to the target emergency plan set; generate a target prompt voice according to the target prompt message; use audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter the emergency working state; perform target emergency operations according to the target emergency plan set. On the one hand, by analyzing and processing the target monitoring data, potential risks and problems in the target area can be discovered in time. On the other hand, when the target risk probability is greater than the preset risk probability, use audio transmission technology to notify the staff of the security room, that is, notify the security guard, so that they can rush to the target area in time to ensure the safety of people in the target area. In this way, the security guard can be notified in time and quickly.

[0130] See also Figure 3 , Figure 3 : is a functional unit composition block diagram of a target area supervision device 300 provided in an embodiment of the present application; the target area supervision device 300 includes: an acquisition unit 301, an analysis unit 302, a control unit 303, and an emergency unit 304, wherein:

[0131] The acquisition unit is used to acquire target monitoring data of the target area within a first preset time period;

[0132] The analysis unit is used to analyze and process the target monitoring data to obtain target analysis data; and determine the target risk probability corresponding to the target analysis data;

[0133] The control unit is used to determine the emergency plan set corresponding to the target analysis data when the target risk probability is greater than the preset risk probability, and obtain the target emergency plan set; generate a target prompt message according to the target emergency plan set; and generate a target prompt voice according to the target prompt message;

[0134] The emergency unit is used to use audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter the emergency working state; and perform the target emergency operation according to the target emergency plan set.

[0135] Optionally, the target monitoring data includes a target monitoring video; in terms of analyzing and processing the target monitoring data to obtain target analysis data, the analyzing unit 302 is specifically used to:

[0136] Dividing the target area into regions to obtain a plurality of divided regions;

[0137] Segmenting the target surveillance video at preset time intervals to obtain multiple surveillance videos;

[0138] Performing face recognition on each of the plurality of surveillance videos to obtain a plurality of face recognition results; each face recognition result corresponds to a number of faces;

[0139] Determine a face recognition result in which the number of faces among the multiple face recognition results is greater than or equal to a preset number of faces, and obtain at least one face recognition result;

[0140] Performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data;

[0141] The target human behavior data is compared and analyzed with a preset dangerous behavior database to obtain the target analysis data.

[0142] Optionally, in the aspect of performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data, the analyzing unit 302 is further specifically used for:

[0143] Determine personnel distribution data corresponding to the multiple divided areas in the at least one surveillance video according to the at least one face recognition result, and obtain multiple personnel distribution data; each divided area corresponds to one personnel distribution data;

[0144] Determine a first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees;

[0145] Determine the first analysis priorities of the multiple divided areas according to the multiple first abnormality degrees to obtain multiple first analysis priorities; each divided area corresponds to a first analysis priority; the greater the abnormality degree, the higher the priority;

[0146] Human behavior analysis is performed on the multiple divided areas according to the multiple first analysis priorities to obtain the target human behavior data.

[0147] Optionally, in determining the first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees, the analyzing unit 302 is further specifically configured to:

[0148] Determine the number of personnel corresponding to each personnel distribution data in the plurality of personnel distribution data to obtain a plurality of personnel numbers;

[0149] Determine a reference abnormality degree corresponding to each number of personnel in the multiple numbers of personnel to obtain multiple reference abnormality degrees;

[0150] Acquire environmental data corresponding to each of the multiple divided areas to obtain multiple environmental data;

[0151] Determine a first influence coefficient corresponding to each of the plurality of environmental data to obtain a plurality of first influence coefficients;

[0152] Corresponding reference abnormality degrees among the plurality of reference abnormality degrees are optimized according to the plurality of first influence coefficients to obtain the plurality of first abnormality degrees.

[0153] Optionally, in determining the emergency plan set corresponding to the target analysis data to obtain the target emergency plan set, the control unit 303 is specifically configured to:

[0154] Determining target risk events that may occur in the target area according to the target analysis data;

[0155] Determine a set of emergency plans corresponding to the target risk event to obtain the target emergency plan set.

[0156] Optionally, the target monitoring data also includes target monitoring audio data; the target monitoring audio data includes: monitoring audio, recording time, and recording location; in performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data, the analysis unit 302 is further specifically used to:

[0157] Determine the monitoring audio corresponding to the multiple divided areas according to the recording position in the target monitoring audio data, and obtain multiple monitoring audios; each monitoring audio corresponds to a divided area;

[0158] Determine the text data corresponding to each monitoring audio in the multiple monitoring audios to obtain multiple text data;

[0159] Determine the second abnormality degrees corresponding to the plurality of divided areas according to the plurality of text data to obtain a plurality of second abnormality degrees; each second abnormality degree corresponds to a divided area;

[0160] Determine a volume value corresponding to each of the multiple monitoring audios to obtain multiple volume values;

[0161] Determine a second influence coefficient corresponding to each volume value in the multiple volume values ​​to obtain multiple second influence coefficients;

[0162] Optimizing corresponding second abnormality degrees among the plurality of second abnormality degrees according to the plurality of second influence coefficients to obtain a plurality of third abnormality degrees;

[0163] Determine the second analysis priorities of the plurality of divided areas according to the plurality of third abnormality degrees, to obtain a plurality of second analysis priorities; each divided area corresponds to a second analysis priority;

[0164] Human behavior analysis is performed on the multiple divided areas according to the multiple second analysis priorities to obtain the target human behavior data.

[0165] Optionally, after playing the target prompt voice in the target security room corresponding to the target area using the audio transmission technology, the target area supervision device 300 is specifically used to:

[0166] Acquire security room monitoring data of the target security room within a second preset time period;

[0167] Analyzing and processing the security room monitoring data to obtain security room analysis data;

[0168] Determine a target optimization solution corresponding to the security room analysis data;

[0169] The subsequent supervision process of the target area is optimized according to the target optimization plan.

[0170] In a specific implementation, the target area supervision device 300 described in the embodiment of the present invention may also execute other implementations described in the target area supervision method provided in the above embodiment of the present invention, which will not be described in detail here.

[0171] See also Figure 4 , Figure 4 : is a structural diagram of an electronic device provided in an embodiment of the present application, the electronic device includes a processor, a memory and one or more programs, the electronic device may also include a communication interface, the processor, the memory and the communication interface are interconnected through a bus; the one or more programs are stored in the memory and are configured to be executed by the processor. In the embodiment of the present invention, the program includes instructions for executing the following steps:

[0172] Acquire target monitoring data of a target area within a first preset time period;

[0173] Analyzing and processing the target monitoring data to obtain target analysis data;

[0174] Determining a target risk probability corresponding to the target analysis data;

[0175] When the target risk probability is greater than a preset risk probability, determining a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set;

[0176] generating a target prompt message according to the target emergency plan set;

[0177] Generate a target prompt voice according to the target prompt message;

[0178] Using audio transmission technology, the target prompt voice is played in the target security room corresponding to the target area to prompt the staff of the target security room to enter an emergency working state;

[0179] Execute target emergency operations according to the target emergency plan set.

[0180] Optionally, in the aspect of analyzing and processing the target monitoring data to obtain target analysis data, the target monitoring data includes a target monitoring video, and the program further includes instructions for executing the following steps:

[0181] Dividing the target area into regions to obtain a plurality of divided regions;

[0182] Segmenting the target surveillance video at preset time intervals to obtain multiple surveillance videos;

[0183] Performing face recognition on each of the plurality of surveillance videos to obtain a plurality of face recognition results; each face recognition result corresponds to a number of faces;

[0184] Determine a face recognition result in which the number of faces among the multiple face recognition results is greater than or equal to a preset number of faces, and obtain at least one face recognition result;

[0185] Performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data;

[0186] The target human behavior data is compared and analyzed with a preset dangerous behavior database to obtain the target analysis data.

[0187] Optionally, in the aspect of performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data, the program further includes instructions for executing the following steps:

[0188] Determine personnel distribution data corresponding to the multiple divided areas in the at least one surveillance video according to the at least one face recognition result, and obtain multiple personnel distribution data; each divided area corresponds to one personnel distribution data;

[0189] Determine a first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees;

[0190] Determine the first analysis priorities of the multiple divided areas according to the multiple first abnormality degrees to obtain multiple first analysis priorities; each divided area corresponds to a first analysis priority; the greater the abnormality degree, the higher the priority;

[0191] Human behavior analysis is performed on the multiple divided areas according to the multiple first analysis priorities to obtain the target human behavior data.

[0192] Optionally, in the aspect of determining the first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees, the program further includes instructions for executing the following steps:

[0193] Determine the number of personnel corresponding to each personnel distribution data in the plurality of personnel distribution data to obtain a plurality of personnel numbers;

[0194] Determine a reference abnormality degree corresponding to each number of personnel in the multiple numbers of personnel to obtain multiple reference abnormality degrees;

[0195] Acquire environmental data corresponding to each of the multiple divided areas to obtain multiple environmental data;

[0196] Determine a first influence coefficient corresponding to each of the plurality of environmental data to obtain a plurality of first influence coefficients;

[0197] Corresponding reference abnormality degrees among the plurality of reference abnormality degrees are optimized according to the plurality of first influence coefficients to obtain the plurality of first abnormality degrees.

[0198] Optionally, in the aspect of determining the emergency plan set corresponding to the target analysis data to obtain the target emergency plan set, the program further includes instructions for executing the following steps:

[0199] Determining target risk events that may occur in the target area according to the target analysis data;

[0200] Determine a set of emergency plans corresponding to the target risk event to obtain the target emergency plan set.

[0201] Optionally, the target monitoring data also includes target monitoring audio data; the target monitoring audio data includes: monitoring audio, recording time, and recording location; in performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data, the program also includes instructions for executing the following steps:

[0202] Determine the monitoring audio corresponding to the multiple divided areas according to the recording position in the target monitoring audio data, and obtain multiple monitoring audios; each monitoring audio corresponds to a divided area;

[0203] Determine the text data corresponding to each monitoring audio in the multiple monitoring audios to obtain multiple text data;

[0204] Determine the second abnormality degrees corresponding to the plurality of divided areas according to the plurality of text data to obtain a plurality of second abnormality degrees; each second abnormality degree corresponds to a divided area;

[0205] Determine a volume value corresponding to each of the multiple monitoring audios to obtain multiple volume values;

[0206] Determine a second influence coefficient corresponding to each volume value in the multiple volume values ​​to obtain multiple second influence coefficients;

[0207] Optimizing corresponding second abnormality degrees among the plurality of second abnormality degrees according to the plurality of second influence coefficients to obtain a plurality of third abnormality degrees;

[0208] Determine the second analysis priorities of the plurality of divided areas according to the plurality of third abnormality degrees, to obtain a plurality of second analysis priorities; each divided area corresponds to a second analysis priority;

[0209] Human behavior analysis is performed on the multiple divided areas according to the multiple second analysis priorities to obtain the target human behavior data.

[0210] Optionally, after playing the target prompt voice in the target security room corresponding to the target area using the audio transmission technology, the program further includes instructions for executing the following steps:

[0211] Acquire security room monitoring data of the target security room within a second preset time period;

[0212] Analyzing and processing the security room monitoring data to obtain security room analysis data;

[0213] Determine a target optimization solution corresponding to the security room analysis data;

[0214] The subsequent supervision process of the target area is optimized according to the target optimization plan.

[0215] It needs to be explained that the above-mentioned electronic device may include a monitoring system.

[0216] An embodiment of the present invention also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an electronic device.

[0217] The embodiment of the present invention further provides a computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer comprises an electronic device.

[0218] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0219] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0220] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0221] The units described above 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0222] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0223] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0224] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A target area supervision method, characterized in that: Applied to a regulatory system, the method comprises: Acquire target monitoring data of a target area within a first preset time period; Analyzing and processing the target monitoring data to obtain target analysis data; Determining a target risk probability corresponding to the target analysis data; When the target risk probability is greater than a preset risk probability, determining a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set; generating a target prompt message according to the target emergency plan set; Generate a target prompt voice according to the target prompt message; Using audio transmission technology, the target prompt voice is played in the target security room corresponding to the target area to prompt the staff of the target security room to enter an emergency working state; Execute target emergency operations according to the target emergency plan set.

2. The method according to claim 1, characterized in that The target monitoring data includes a target monitoring video; the target monitoring data is analyzed and processed to obtain target analysis data, including: Dividing the target area into regions to obtain a plurality of divided regions; Segmenting the target surveillance video at preset time intervals to obtain multiple surveillance videos; Performing face recognition on each of the plurality of surveillance videos to obtain a plurality of face recognition results; each face recognition result corresponds to a number of faces; Determine a face recognition result in which the number of faces among the multiple face recognition results is greater than or equal to a preset number of faces, and obtain at least one face recognition result; Performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data; The target human behavior data is compared and analyzed with a preset dangerous behavior database to obtain the target analysis data.

3. The method according to claim 2, characterized in that The performing human behavior analysis on at least one surveillance video corresponding to the at least one face recognition result to obtain target human behavior data includes: Determine personnel distribution data corresponding to the multiple divided areas in the at least one surveillance video according to the at least one face recognition result, and obtain multiple personnel distribution data; each divided area corresponds to one personnel distribution data; Determine a first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees; Determine the first analysis priorities of the multiple divided areas according to the multiple first abnormality degrees to obtain multiple first analysis priorities; each divided area corresponds to a first analysis priority; the greater the abnormality degree, the higher the priority; Human behavior analysis is performed on the multiple divided areas according to the multiple first analysis priorities to obtain the target human behavior data.

4. The method according to claim 3, characterized in that The determining a first abnormality degree corresponding to each of the plurality of personnel distribution data to obtain a plurality of first abnormality degrees includes: Determine the number of personnel corresponding to each personnel distribution data in the plurality of personnel distribution data to obtain a plurality of personnel numbers; Determine a reference abnormality degree corresponding to each number of personnel in the multiple numbers of personnel to obtain multiple reference abnormality degrees; Acquire environmental data corresponding to each of the multiple divided areas to obtain multiple environmental data; Determine a first influence coefficient corresponding to each of the plurality of environmental data to obtain a plurality of first influence coefficients; Corresponding reference abnormality degrees among the plurality of reference abnormality degrees are optimized according to the plurality of first influence coefficients to obtain the plurality of first abnormality degrees.

5. The method according to any one of claims 1 to 4, characterized in that: The step of determining a contingency plan set corresponding to the target analysis data to obtain a target contingency plan set includes: Determining target risk events that may occur in the target area according to the target analysis data; Determine a set of emergency plans corresponding to the target risk event to obtain the target emergency plan set.

6. The method according to claim 2, characterized in that The target monitoring data also includes target monitoring audio data; The target monitoring audio data includes: monitoring audio, recording time, and recording location; the human behavior analysis of at least one monitoring video corresponding to the at least one face recognition result is performed to obtain the target human behavior data, including: Determine the monitoring audio corresponding to the multiple divided areas according to the recording position in the target monitoring audio data, and obtain multiple monitoring audios; each monitoring audio corresponds to a divided area; Determine the text data corresponding to each monitoring audio in the multiple monitoring audios to obtain multiple text data; Determine the second abnormality degrees corresponding to the plurality of divided areas according to the plurality of text data to obtain a plurality of second abnormality degrees; each second abnormality degree corresponds to a divided area; Determine a volume value corresponding to each of the multiple monitoring audios to obtain multiple volume values; Determine a second influence coefficient corresponding to each volume value in the multiple volume values ​​to obtain multiple second influence coefficients; Optimizing corresponding second abnormality degrees among the plurality of second abnormality degrees according to the plurality of second influence coefficients to obtain a plurality of third abnormality degrees; Determine the second analysis priorities of the plurality of divided areas according to the plurality of third abnormality degrees, to obtain a plurality of second analysis priorities; each divided area corresponds to a second analysis priority; Human behavior analysis is performed on the multiple divided areas according to the multiple second analysis priorities to obtain the target human behavior data.

7. The method according to any one of claims 1 to 4, characterized in that: After playing the target prompt voice in the target security room corresponding to the target area using the audio transmission technology, the method further includes: Acquire security room monitoring data of the target security room within a second preset time period; Analyzing and processing the security room monitoring data to obtain security room analysis data; Determine a target optimization solution corresponding to the security room analysis data; The subsequent supervision process of the target area is optimized according to the target optimization plan.

8. A target area monitoring device, characterized in that: The target area supervision device includes: an acquisition unit, an analysis unit, a control unit, and an emergency unit, wherein: The acquisition unit is used to acquire target monitoring data of the target area within a first preset time period; The analysis unit is used to analyze and process the target monitoring data to obtain target analysis data; and determine the target risk probability corresponding to the target analysis data; The control unit is used to determine the emergency plan set corresponding to the target analysis data when the target risk probability is greater than the preset risk probability, and obtain the target emergency plan set; generate a target prompt message according to the target emergency plan set; and generate a target prompt voice according to the target prompt message; The emergency unit is used to use audio transmission technology to play the target prompt voice in the target security room corresponding to the target area to prompt the staff of the target security room to enter the emergency working state; and perform the target emergency operation according to the target emergency plan set.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images