Intelligent monitoring method, device, computer equipment and storage medium

Abstract

The present invention discloses an intelligent monitoring method, device, computer equipment and storage medium, wherein the method includes: collecting basic information of mobile personnel, target address and MAC address of portable electronic devices; generating action path and activity space according to target address; collecting real-time data and performing structured processing on real-time data to obtain structured data, storing structured data in an acceleration processing layer, and storing historical data in a batch processing layer; performing correlation analysis on the spatiotemporal relationship of real-time data, outputting the behavior space trajectory of mobile personnel and the residence time at each monitoring point; outputting the probability of trajectory abnormality through a classification model based on supervised learning, and issuing an alarm when the probability exceeds a threshold. The present invention collects relevant information of mobile personnel and monitors mobile personnel in combination with multiple monitoring points, thereby improving the information coverage of mobile personnel, strengthening the trajectory tracking of mobile personnel, and protecting the interests of community residents.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method, device, computer equipment and storage medium based on time-space relationship. Background Art

[0002] With the rapid development of my country's social economy, especially the people-oriented new urbanization construction in recent years, the population is rapidly gathering in cities and towns. The mobility of people in large and medium-sized cities is constantly increasing, and local services based on communities are becoming more refined, making the mobility of people in communities more complicated.

[0003] In the new era, the service needs of community residents are becoming more diversified. Domestic service personnel such as nannies, cleaners, and repair and installation personnel, as well as commercial service personnel such as agents, food delivery, and tutors, frequently enter and exit the community, bringing greater challenges to community security.

[0004] Traditional property information and access control systems only cooperate with security personnel to perform manual registration and release at the entrances and exits of the community. There are problems such as low coverage of information on mobile personnel and inability to track the trajectory of mobile personnel after entering the community. It is difficult to meet the operating model of high-quality modern smart communities. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent monitoring method, device, computer equipment and storage medium based on time-space relationship, aiming to improve the information coverage of mobile personnel and strengthen the tracking of the trajectory of mobile personnel after entering the community.

[0006] The embodiment of the present invention provides an intelligent monitoring method based on time-space relationship, which includes:

[0007] Collect basic information, target addresses, and MAC addresses of mobile devices of mobile personnel entering the community; generate the movement paths and activity spaces of mobile personnel in the community based on their target addresses;

[0008] Based on AP probes set at multiple monitoring points, real-time data including MAC address information of electronic devices is collected, and the real-time data includes real-time coordinate location and residence time;

[0009] Performing structured processing on the real-time data to obtain structured data with spatiotemporal relationships, storing the structured data in a relational memory database of the acceleration processing layer, and periodically persisting the historical data in a disk database of the batch processing layer;

[0010] When receiving a query request, the temporal and spatial relationship of the real-time data is analyzed, and the behavior spatial trajectory of the mobile personnel and the stay time at each monitoring point are output;

[0011] The real-time data, action path and activity space are learned through a classification model based on supervised learning, and the probability of trajectory abnormality is output. When the probability exceeds a threshold, an abnormal trajectory alarm of mobile personnel is issued.

[0012] Preferably, generating the action path and activity space of the mobile personnel in the community according to the target address of the mobile personnel includes:

[0013] Collect community real estate information and community maps;

[0014] The target address is compared with the real estate information, and the movement paths and activity spaces of mobile personnel in the community are planned on the community map according to the comparison results.

[0015] Preferably, the target address is compared with the real estate information, and the movement paths and activity spaces of the mobile personnel in the community are planned on the community map according to the comparison result, including:

[0016] Collect the geographic coordinates of the smart access control system that mobile personnel pass through;

[0017] Comparing the target address with the real estate information, and finding the corresponding target real estate location on the community map according to the comparison result;

[0018] According to the location of the target real estate and the geographical coordinates of the intelligent access control system, the movement paths and activity spaces of mobile personnel in the community are planned on the community map.

[0019] Preferably, when receiving a query request, the temporal and spatial relationship of the real-time data is subjected to correlation analysis, and the behavior spatial trajectory of mobile personnel and the residence time at each monitoring point are output, including:

[0020] When receiving a query request, obtaining an ordered sequence of timestamps of mobile personnel at each monitoring point according to the real-time data, and obtaining the stay time at each monitoring point;

[0021] The behavior spatial trajectory of the mobile personnel is drawn through the ordered timestamp sequence and the device geographic coordinate information.

[0022] Preferably, the real-time data, action path and activity space are learned by a classification model based on supervised learning, the probability of trajectory abnormality is output, and an alarm of abnormal trajectory of mobile personnel is issued when the probability exceeds a threshold, including:

[0023] Annotating the real-time data, action path, and activity space to obtain a sample set;

[0024] Dividing the sample set to obtain a training sample set and a test sample set;

[0025] The training sample set is trained using the classification model based on supervised learning, and then the classification model based on supervised learning is tested using the test sample set to obtain a final classification model based on supervised learning;

[0026] The final classification model based on supervised learning is used for prediction to obtain the probability of abnormal trajectory. When the probability exceeds a threshold, an abnormal trajectory alert for mobile personnel is issued.

[0027] Preferably, it also includes:

[0028] According to the behavior spatial trajectory of mobile personnel and their stay time at each monitoring point, a behavior spatial trajectory map of mobile personnel, a heat map of mobile personnel flow, and a time series statistical map of historical data are drawn and displayed.

[0029] Preferably, when receiving the query request, obtaining the ordered time stamp sequence of the mobile personnel at each monitoring point according to the real-time data, and obtaining the stay time at each monitoring point, includes:

[0030] When a query request is received, the query type is obtained;

[0031] If the query type is real-time business, the real-time data stored in the acceleration processing layer is called in the form of stream data to process the real-time business;

[0032] If the query type is historical business, the historical data stored in the batch processing layer is called in the form of batch data to process the historical business.

[0033] The embodiment of the present invention provides an intelligent monitoring device based on time-space relationship, which includes:

[0034] The mobile personnel information collection unit is used to collect the basic information, target address and MAC address of the mobile personnel's portable electronic devices entering the community; according to the mobile personnel's target address, the mobile personnel's action path and activity space in the community are generated;

[0035] A real-time data acquisition unit, used to collect real-time data including MAC address information of electronic devices based on AP probes set at multiple monitoring points, wherein the real-time data includes real-time coordinate position and residence time;

[0036] A data storage unit, used to perform structured processing on the real-time data to obtain structured data with spatiotemporal relationships, store the structured data in a relational memory database of the acceleration processing layer, and periodically store historical data persistently in a disk database of the batch processing layer;

[0037] A data analysis unit, for performing correlation analysis on the spatiotemporal relationship of the real-time data when receiving a query request, and outputting the behavior spatial trajectory of mobile personnel and the residence time at each monitoring point;

[0038] The abnormal alarm unit is used to learn the real-time data, action path and activity space through a classification model based on supervised learning, output the probability of trajectory abnormality, and issue an abnormal trajectory alarm for mobile personnel when the probability exceeds a threshold.

[0039] An embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the intelligent monitoring method based on spatiotemporal relationship as described above when executing the computer program.

[0040] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the intelligent monitoring method based on the spatiotemporal relationship as described above is implemented.

[0041] The embodiment of the present invention provides an intelligent monitoring method, device, computer equipment and storage medium based on time-space relationship, wherein the method includes: collecting basic information, target address and MAC address of mobile personnel entering the community; generating the action path and activity space of the mobile personnel in the community according to the target address of the mobile personnel; collecting real-time data containing MAC address information of the electronic device based on AP probes set at multiple monitoring points, the real-time data including real-time coordinate position and residence time; performing structured processing on the real-time data to obtain structured data with time-space relationship, and storing the structured data in a relational memory database of an acceleration processing layer, and periodically storing historical data persistently in a disk database of a batch processing layer; when receiving a query request, performing correlation analysis on the time-space relationship of the real-time data, and outputting the behavior space trajectory of the mobile personnel and the residence time at each monitoring point; learning the real-time data, action path and activity space through a classification model based on supervised learning, outputting the probability of trajectory abnormality, and issuing an alarm for abnormal trajectory of the mobile personnel when the probability exceeds a threshold. The embodiment of the present invention collects relevant information of mobile personnel, combines multiple monitoring points to monitor mobile personnel in real time after they enter the community, and sends out an alarm when the trajectory of the mobile personnel is abnormal, thereby improving the information coverage of mobile personnel in the community, strengthening the trajectory tracking of mobile personnel after entering the community, and ensuring the personal safety and property safety of community residents. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0043] Figure 1 A schematic diagram of a flow chart of an intelligent monitoring method based on time-space relationship provided by an embodiment of the present invention;

[0044] Figure 2 A schematic block diagram of an intelligent monitoring device based on time-space relationship provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments 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.

[0046] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0048] See also Figure 1 , Figure 1 A schematic flow chart of an intelligent monitoring method based on time-space relationship provided by an embodiment of the present invention, the method may include steps S101 to S105:

[0049] S101, collecting basic information, target addresses, and MAC addresses of mobile personnel's portable electronic devices entering the community; generating the mobile personnel's action path and activity space in the community based on the mobile personnel's target addresses;

[0050] In this step, when a mobile person enters the community, the basic information and target address of the mobile person are collected through the query mechanism of the intelligent access control system, and the MAC address of the mobile person's portable electronic device is obtained. The basic information of the mobile person includes name and phone number, etc., and the mobile person's action path and activity space in the community are generated according to the mobile person's target address.

[0051] After the intelligent access control system collects the basic information and target address of the migrant workers, it records the current time when the migrant workers enter the community, and records the time when they leave the community when they leave the community, so as to count the total time the migrant workers spend in the community.

[0052] The movement paths and activity spaces of the mobile personnel entering the community are accurately planned. Specifically, after the movement paths and activity spaces of the mobile personnel are generated, the movement paths and activity spaces of the mobile personnel are displayed on the visualization platform.

[0053] In one embodiment, generating the action path and activity space of the mobile personnel in the community according to the target address of the mobile personnel includes:

[0054] Collect community real estate information and community maps;

[0055] The target address is compared with the real estate information, and the movement paths and activity spaces of mobile personnel in the community are planned on the community map according to the comparison results.

[0056] In this embodiment, the movement paths and activity spaces of the mobile personnel in the community are planned based on the real estate information and community map of the target community. The real estate information is collected through components such as the GIS community map and the community building information database (GIS is a technical system that collects, stores, manages, calculates, analyzes, displays and describes the relevant geographical distribution data in the entire or part of the earth's surface space under the support of computer hardware and software systems). By comparing the target address and real estate information, the best path is found on the community map, and the activity space of the mobile personnel in the community is planned.

[0057] By planning the movement paths and activity spaces of migrant workers in the community, the scope of their activities is set, which serves as the basis for subsequent geographic location analysis.

[0058] In a specific embodiment, the target address is compared with the real estate information, and the movement path and activity space of the mobile personnel in the community are planned on the community map according to the comparison result, including:

[0059] Collect the geographic coordinates of the smart access control system that mobile personnel pass through;

[0060] Comparing the target address with the real estate information, and finding the corresponding target real estate location on the community map according to the comparison result;

[0061] According to the location of the target real estate and the geographical coordinates of the intelligent access control system, the movement paths and activity spaces of mobile personnel in the community are planned on the community map.

[0062] In this embodiment, the intelligent access control system is arranged at each entrance and exit of the community, and mobile personnel enter the community through one of the intelligent access control systems. The coordinates of the mobile personnel entering the community are determined by the geographic coordinate information of the intelligent access control system itself, and the movement path and activity space of the mobile personnel in the community are planned. Specifically, according to the target address that the mobile personnel need to go to, the real estate location corresponding to the target address is found in the community map, and then the movement path and activity space of the mobile personnel are planned according to the community map.

[0063] If there is more than one target address that the mobile personnel need to go to, the real estate locations of all the target addresses are found on the community map in turn, and the plans are made on the community map according to the locations of each real estate. For example, delivery person A needs to go to target address b, target address c, and target address d. Target address b is located in building B in the community, target address c is located in building C in the community, and target address d is located in building D in the community. Based on the distance between building B, building C, and building D and the smart access control system where delivery person A is located, the movement path and activity space of the delivery person to each building are planned.

[0064] If the real estate locations of multiple target addresses are the same real estate location, the action path and activity space to the real estate location are directly planned.

[0065] S102, based on AP probes set at multiple monitoring points, collecting real-time data including MAC address information of electronic devices, wherein the real-time data includes real-time coordinate position and residence time;

[0066] In this step, the real-time data is collected through AP probes, and the AP probes are set at monitoring points distributed at multiple locations in the community.

[0067] In addition to the AP probe, the monitoring point also includes: an RFID module, a Wi-Fi module, a data collector, a data analyzer and a data storage device. The input end of the AP probe is connected to the input end of the RFID module and the input end of the Wi-Fi module respectively, the output end of the AP probe is connected to the input end of the data collector, the output end of the data collector is connected to the input end of the data analyzer, and the input end of the data analyzer is also connected to the output end of the data storage device.

[0068] The monitoring point monitors the real-time coordinate position of the electronic device by collecting the MAC address and signal strength of the electronic device, and obtains the residence time of the electronic device at the current location based on the duration of the current signal strength, thereby calculating the real-time coordinate position and residence time of the mobile personnel.

[0069] The real-time coordinate position includes geographic coordinate information, and the geographic coordinate information includes dimensions such as point (specific location), line (road or river), surface (park), and body (three-dimensional space).

[0070] S103, performing structured processing on the real-time data to obtain structured data with spatiotemporal relationships, storing the structured data in a relational memory database of the acceleration processing layer, and periodically storing historical data in a disk database of the batch processing layer;

[0071] In this step, structured data with a time-space relationship is constructed through the timestamp and geographic coordinate information of the real-time data, and the accuracy of the timestamp is obtained based on the effective signal frequency of the RFID module and the Wi-Fi module.

[0072] The real-time data is stored using the Lambda architecture, which includes an acceleration processing layer (SpeedLayer), a batch processing layer (BatchLayer) and a service layer (ServingLayer). In the Lambda architecture, the ServingLayer is used to respond to user query requests, the BatchLayer is used to process offline data, and the SpeedLayer is used to process real-time data. Data generation is continuous. During the continuous generation of real-time data, the previously saved real-time data will be overwritten by the existing real-time data. At this time, the previous real-time data becomes historical data relative to the existing real-time data. In order to distinguish the existing real-time data from the historical data, the data is stored in the relational memory database of the acceleration processing layer in the form of structured data, and the historical data is periodically persisted and stored in the disk database of the batch processing layer.

[0073] S104, when receiving a query request, performing correlation analysis on the spatiotemporal relationship of the real-time data, and outputting the behavior spatial trajectory of mobile personnel and the stay time at each monitoring point;

[0074] In this step, the real-time data includes real-time coordinate position and residence time. The spatial trajectory of the mobile personnel's behavior is obtained based on the spatiotemporal relationship of the real-time data and combined with the community map. The residence time of the mobile personnel at each monitoring point is obtained by monitoring through the AP probes set at each monitoring point.

[0075] In one embodiment, the S104 includes:

[0076] When receiving a query request, obtaining an ordered sequence of timestamps of mobile personnel at each monitoring point according to the real-time data, and obtaining the stay time at each monitoring point;

[0077] The behavior spatial trajectory of the mobile personnel is drawn through the ordered timestamp sequence and the device geographic coordinate information.

[0078] In this embodiment, the behavior space trajectory of the mobile personnel is drawn by obtaining the ordered time stamp sequence of the mobile personnel at each monitoring point. The time stamp is the most basic time series data, which is used to associate the value with the time point.

[0079] There are many monitoring points distributed in the community. When migrant workers enter the monitoring range of a monitoring point, the monitoring point will record the entry time of the migrant workers into the monitoring range. When the migrant workers leave the monitoring point, the departure time will be recorded to obtain the stay time of the migrant workers at each monitoring point.

[0080] In a specific embodiment, when receiving a query request, obtaining an ordered timestamp sequence of mobile personnel at each monitoring point according to the real-time data, and obtaining the stay time at each monitoring point, includes:

[0081] When a query request is received, the query type is obtained;

[0082] If the query type is real-time business, the real-time data stored in the acceleration processing layer is called in the form of stream data to process the real-time business;

[0083] If the query type is historical business, the historical data stored in the batch processing layer is called in the form of batch data to process the historical business.

[0084] In this embodiment, the query types are divided into real-time services and historical services. According to different query types, data of different processing layers are called for processing.

[0085] In the Lambda architecture, the acceleration processing layer is used to store real-time data, and the batch processing layer is used to store historical data. Therefore, when the query type is real-time business, the real-time data of the acceleration processing layer is called to process the real-time business; when the query type is historical business, the historical data of the batch processing layer is called to process the historical business.

[0086] S105. The real-time data, action path and activity space are learned through a classification model based on supervised learning, and the probability of trajectory abnormality is outputted. When the probability exceeds a threshold, an alarm of abnormal trajectory of mobile personnel is issued.

[0087] In this step, the known real-time data, action paths and activity spaces are used to learn these parameters through a classification model based on supervised learning, and the probability of abnormal spatial trajectories of the mobile personnel's behavior is output. If the probability is higher than a predetermined threshold, an abnormal alarm is issued to improve monitoring of the mobile personnel and ensure the personal and property safety of community residents.

[0088] The supervised learning is a type of machine learning method, which refers to the process of adjusting the parameters of the classifier using a set of samples of known categories to achieve the required performance. Based on the supervised learning method, the labeled data set is trained to obtain a classification model, and the probability of trajectory abnormality is output through the classification model, so as to realize the judgment of mobile personnel with abnormal trajectory.

[0089] In one embodiment, the S105 includes:

[0090] Annotating the real-time data, action path, and activity space to obtain a sample set;

[0091] Dividing the sample set to obtain a training sample set and a test sample set;

[0092] The training sample set is trained using the classification model based on supervised learning, and then the classification model based on supervised learning is tested using the test sample set to obtain a final classification model based on supervised learning;

[0093] The final classification model based on supervised learning is used for prediction to obtain the probability of abnormal trajectory. When the probability exceeds a threshold, an abnormal trajectory alert for mobile personnel is issued.

[0094] In this embodiment, the supervised learning is a training process, and the real-time data, action path and activity space are labeled and divided to obtain a training sample set and a test sample set. After the training sample set is trained by a classification model based on supervised learning, the classification model based on supervised learning is tested by a test sample set to obtain a final classification model based on supervised learning. The final classification model based on supervised learning will output the probability of trajectory anomaly and issue an abnormal alarm when the probability exceeds a threshold.

[0095] Supervised learning is the machine learning task of inferring a function from labeled training data. The training data consists of a set of training examples. In supervised learning, each instance consists of an input object (usually a vector) and a desired output value (also called a supervisory signal). The supervised learning algorithm analyzes the training data and produces an inferred function that can be used to map new instances.

[0096] In one embodiment, it further includes:

[0097] According to the behavior spatial trajectory of mobile personnel and their stay time at each monitoring point, a behavior spatial trajectory map of mobile personnel, a heat map of mobile personnel flow, and a time series statistical map of historical data are drawn and displayed.

[0098] In this embodiment, a map of the mobile personnel's behavior space trajectory is drawn through the mobile personnel's behavior space trajectory and displayed, so that the monitoring personnel can monitor the mobile personnel in the community more objectively and conveniently. If the mobile personnel encounter an abnormal situation in the community, the community security personnel can also respond more promptly through the visual interface. By drawing a heat map of the flow of mobile personnel, the range of activities of the mobile personnel and the density of mobile personnel in the area can be observed, so as to facilitate the community management personnel to more reasonably dispatch the community security forces to effectively manage the mobile personnel. The time series statistical chart of the historical data can count the time periods when the mobile personnel enter the community, find out the peak period of mobile personnel entering and leaving, and increase the monitoring intensity during the peak period of mobile personnel entering and leaving to ensure the safety of community residents.

[0099] See also Figure 2 , Figure 2 A schematic block diagram of an intelligent monitoring device based on time-space relationship provided by an embodiment of the present invention, the intelligent monitoring device based on time-space relationship 200 includes:

[0100] The mobile personnel information collection unit 201 is used to collect basic information, target addresses and MAC addresses of mobile personnel's portable electronic devices entering the community; according to the mobile personnel's target addresses, the mobile personnel's action paths and activity spaces in the community are generated;

[0101] A real-time data acquisition unit 202, configured to collect real-time data including MAC address information of electronic devices based on AP probes arranged at multiple monitoring points, wherein the real-time data includes real-time coordinates and residence time;

[0102] The data storage unit 203 is used to perform structured processing on the real-time data to obtain structured data with a spatiotemporal relationship, store the structured data in a relational memory database of the acceleration processing layer, and periodically store the historical data in a disk database of the batch processing layer;

[0103] The data analysis unit 204 is used to perform correlation analysis on the spatiotemporal relationship of the real-time data when receiving a query request, and output the behavior spatial trajectory of the mobile personnel and the stay time at each monitoring point;

[0104] The abnormal alarm unit 205 is used to learn the real-time data, action path and activity space through a classification model based on supervised learning, output the probability of trajectory abnormality, and issue an abnormal trajectory alarm for mobile personnel when the probability exceeds a threshold.

[0105] In one embodiment, the mobile personnel information collection unit 201 includes:

[0106] A community information collection unit, used to collect community real estate information and community maps;

[0107] The first information comparison unit is used to compare the target address with the real estate information, and plan the movement path and activity space of the mobile personnel in the community on the community map according to the comparison result.

[0108] In one embodiment, the first information comparison unit includes:

[0109] The access control coordinate collection unit is used to collect the geographic coordinates of the intelligent access control system through which mobile personnel pass;

[0110] A real estate confirmation unit, used to compare the target address with the real estate information, and find the corresponding target real estate location on the community map according to the comparison result;

[0111] The path planning unit is used to plan the movement paths and activity spaces of mobile personnel in the community on the community map according to the location of the target real estate and the geographical coordinates of the intelligent access control system.

[0112] In one embodiment, the data analysis unit 204 includes:

[0113] A time series acquisition unit, used for acquiring an ordered time stamp sequence of mobile personnel at each monitoring point according to the real-time data when receiving a query request, and acquiring the residence time at each monitoring point;

[0114] The trajectory drawing unit is used to draw the behavior space trajectory of the mobile personnel through the ordered timestamp sequence and the device geographic coordinate information.

[0115] In one embodiment, the abnormality alarm unit 205 includes:

[0116] A sample set acquisition unit, used to annotate the real-time data, action path and activity space to obtain a sample set;

[0117] A sample set division unit, used to divide the sample set into a training sample set and a test sample set;

[0118] A training and testing unit, used to train the training sample set using the classification model based on supervised learning, and then test the classification model based on supervised learning using the test sample set to obtain a final classification model based on supervised learning;

[0119] The abnormal probability prediction unit is used to use the final classification model based on supervised learning to make predictions to obtain the probability of trajectory abnormality, and to issue an abnormal trajectory alarm for mobile personnel when the probability exceeds a threshold.

[0120] In one embodiment, the intelligent monitoring device based on time-space relationship further includes:

[0121] The image display unit is used to draw and display the spatial trajectory diagram of the mobile personnel's behavior, the heat map of the mobile personnel flow, and the time series statistical diagram of historical data based on the mobile personnel's spatial trajectory of behavior and the time spent at each monitoring point.

[0122] In one embodiment, the time series acquisition unit includes:

[0123] A query type acquisition unit, used to acquire the query type when receiving a query request;

[0124] A real-time business processing unit, for invoking the real-time data stored in the acceleration processing layer in the form of stream data to process the real-time business if the query type is real-time business;

[0125] The historical business processing unit is used to call the historical data stored in the batch processing layer in the form of batch data to process the historical business if the query type is historical business.

[0126] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the intelligent monitoring method based on spatiotemporal relationship as described above when executing the computer program.

[0127] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the intelligent monitoring method based on the spatiotemporal relationship as described above is implemented.

[0128] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0129] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. An intelligent monitoring method based on time-space relationship, characterized in that: include: Collect basic information, destination addresses, and MAC addresses of mobile personnel's electronic devices when they enter the community; Generate the movement paths and activity spaces of mobile personnel in the community according to their target addresses; Based on AP probes set at multiple monitoring points, real-time data including MAC address information of electronic devices is collected, and the real-time data includes real-time coordinate location and residence time; The real-time coordinate position includes geographic coordinate information, and the geographic coordinate information includes dimensions of a specific position, a road or a river, a park, and a three-dimensional space; the monitoring point also includes: an RFID module, a Wi-Fi module, a data collector, a data analyzer, and a data storage device; the input end of the AP probe is respectively connected to the input end of the RFID module and the Wi-Fi module, the output end of the AP probe is connected to the input end of the data collector, the output end of the data collector is connected to the input end of the data analyzer, and the input end of the data analyzer is also connected to the output end of the data storage device; the monitoring point monitors the real-time coordinate position of the electronic device by collecting the MAC address of the electronic device and the signal strength of the electronic device, and obtains the residence time of the electronic device at the current position according to the duration of the current signal strength, so as to calculate the real-time coordinate position and residence time of the mobile personnel; when the mobile personnel enter the monitoring range of a certain monitoring point, the monitoring point records the entry time of the mobile personnel into the monitoring range, and when the mobile personnel leave the monitoring point, the departure time is recorded, so as to obtain the residence time of the mobile personnel at each monitoring point; The real-time data is structured to obtain structured data with spatiotemporal relationships, and the structured data is stored in a relational memory database of the acceleration processing layer, and historical data is periodically and persistently stored in a disk database of the batch processing layer; the real-time data is stored using a Lambda architecture, which includes an acceleration processing layer, a batch processing layer, and a service layer. In the Lambda architecture, the service layer is used to respond to user query requests, the batch processing layer is used to process offline data, and the acceleration processing layer is used to process real-time data; When receiving a query request, the temporal and spatial relationship of the real-time data is analyzed, and the behavior spatial trajectory of the mobile personnel and the stay time at each monitoring point are output; The real-time data, action path and activity space are learned through a classification model based on supervised learning, and the probability of abnormal trajectory is outputted. When the probability exceeds a threshold, an abnormal trajectory alarm of mobile personnel is issued; The method of generating the movement paths and activity spaces of the mobile personnel in the community according to the target addresses of the mobile personnel includes: collecting the real estate information and community map of the community; comparing the target address with the real estate information, and planning the movement paths and activity spaces of the mobile personnel in the community on the community map according to the comparison results; The target address is compared with the real estate information, and the movement path and activity space of the mobile personnel in the community are planned on the community map according to the comparison result, including: collecting the geographical coordinates of the smart access control system passed by the mobile personnel; comparing the target address with the real estate information, and finding the corresponding target real estate location on the community map according to the comparison result; planning the movement path and activity space of the mobile personnel in the community on the community map according to the target real estate location and the geographical coordinates of the smart access control system; if the mobile personnel need to go to more than one target address, then finding the real estate locations of all the target addresses on the community map in turn, and planning on the community map according to each real estate location; When receiving a query request, the temporal and spatial relationship of the real-time data is correlated and analyzed, and the behavior spatial trajectory of the mobile personnel and the residence time at each monitoring point are output, including: when receiving a query request, an ordered timestamp sequence of the mobile personnel at each monitoring point is obtained according to the real-time data, and the residence time at each monitoring point is obtained; and the behavior spatial trajectory of the mobile personnel is drawn through the ordered timestamp sequence and the geographic coordinate information of the device; The real-time data, action path and activity space are learned by the classification model based on supervised learning, and the probability of trajectory abnormality is outputted. When the probability exceeds a threshold, an abnormal trajectory alarm of mobile personnel is issued externally, including: marking the real-time data, action path and activity space to obtain a sample set; dividing the sample set to obtain a training sample set and a test sample set; training the training sample set by using the classification model based on supervised learning, and then testing the classification model based on supervised learning by using the test sample set to obtain a final classification model based on supervised learning; predicting by using the final classification model based on supervised learning to obtain the probability of trajectory abnormality, and issuing an abnormal trajectory alarm of mobile personnel externally when the probability exceeds a threshold; When receiving a query request, obtaining an ordered time stamp sequence of mobile personnel at each monitoring point according to the real-time data, and obtaining the stay time at each monitoring point, including: When a query request is received, the query type is obtained; If the query type is real-time business, the real-time data stored in the acceleration processing layer is called in the form of stream data to process the real-time business; If the query type is historical business, the historical data stored in the batch processing layer is called in the form of batch data to process the historical business.

2. The intelligent monitoring method based on time-space relationship according to claim 1 is characterized in that: Also includes: According to the behavior spatial trajectory of mobile personnel and their stay time at each monitoring point, a behavior spatial trajectory map of mobile personnel, a heat map of mobile personnel flow, and a time series statistical map of historical data are drawn and displayed.

3. An intelligent monitoring device based on time-space relationship, characterized in that: include: The mobile personnel information collection unit is used to collect the basic information, target address and MAC address of the mobile personnel's portable electronic devices entering the community; according to the mobile personnel's target address, the mobile personnel's action path and activity space in the community are generated; A real-time data acquisition unit, used to collect real-time data including MAC address information of electronic devices based on AP probes set at multiple monitoring points, wherein the real-time data includes real-time coordinate position and residence time; The real-time coordinate position includes geographic coordinate information, and the geographic coordinate information includes dimensions of a specific position, a road or a river, a park, and a three-dimensional space; the monitoring point also includes: an RFID module, a Wi-Fi module, a data collector, a data analyzer, and a data storage device; the input end of the AP probe is respectively connected to the input end of the RFID module and the Wi-Fi module, the output end of the AP probe is connected to the input end of the data collector, the output end of the data collector is connected to the input end of the data analyzer, and the input end of the data analyzer is also connected to the output end of the data storage device; the monitoring point monitors the real-time coordinate position of the electronic device by collecting the MAC address of the electronic device and the signal strength of the electronic device, and obtains the residence time of the electronic device at the current position according to the duration of the current signal strength, so as to calculate the real-time coordinate position and residence time of the mobile personnel; when the mobile personnel enter the monitoring range of a certain monitoring point, the monitoring point records the entry time of the mobile personnel into the monitoring range, and when the mobile personnel leave the monitoring point, the departure time is recorded, so as to obtain the residence time of the mobile personnel at each monitoring point; A data storage unit, used to perform structured processing on the real-time data to obtain structured data with spatiotemporal relationships, store the structured data in a relational memory database of the acceleration processing layer, and periodically store historical data persistently in a disk database of the batch processing layer; the real-time data is stored using a Lambda architecture, which includes an acceleration processing layer, a batch processing layer, and a service layer. In the Lambda architecture, the service layer is used to respond to user query requests, the batch processing layer is used to process offline data, and the acceleration processing layer is used to process real-time data; A data analysis unit, for performing correlation analysis on the spatiotemporal relationship of the real-time data when receiving a query request, and outputting the behavior spatial trajectory of mobile personnel and the residence time at each monitoring point; An abnormality alarm unit is used to learn the real-time data, action path and activity space through a classification model based on supervised learning, output the probability of trajectory abnormality, and issue an abnormal trajectory alarm for mobile personnel when the probability exceeds a threshold; The mobile personnel information collection unit comprises: A community information collection unit, used to collect community real estate information and community maps; A first information comparison unit is used to compare the target address with the real estate information, and plan the movement path and activity space of the mobile personnel in the community on the community map according to the comparison result; The first information comparison unit includes: The access control coordinate collection unit is used to collect the geographic coordinates of the intelligent access control system through which mobile personnel pass; A real estate confirmation unit, used to compare the target address with the real estate information, and find the corresponding target real estate location on the community map according to the comparison result; A path planning unit is used to plan the movement path and activity space of the mobile personnel in the community on the community map according to the location of the target real estate and the geographical coordinates of the intelligent access control system; if the mobile personnel need to go to more than one target address, the real estate locations of all the target addresses are found on the community map in turn, and planning is performed on the community map according to the locations of each real estate; The data analysis unit comprises: A time series acquisition unit, used for acquiring an ordered time stamp sequence of mobile personnel at each monitoring point according to the real-time data when receiving a query request, and acquiring the residence time at each monitoring point; A trajectory drawing unit, used for drawing the behavior space trajectory of the mobile personnel through the ordered timestamp sequence and the device geographic coordinate information; The abnormal alarm unit comprises: A sample set acquisition unit, used to annotate the real-time data, action path and activity space to obtain a sample set; A sample set division unit, used to divide the sample set into a training sample set and a test sample set; A training and testing unit, used to train the training sample set using the classification model based on supervised learning, and then test the classification model based on supervised learning using the test sample set to obtain a final classification model based on supervised learning; An abnormal probability prediction unit is used to use the final classification model based on supervised learning to make predictions to obtain the probability of abnormal trajectory, and to issue an abnormal trajectory alarm for mobile personnel when the probability exceeds a threshold; The time series acquisition unit comprises: A query type acquisition unit, used to acquire the query type when receiving a query request; A real-time business processing unit, for invoking the real-time data stored in the acceleration processing layer in the form of stream data to process the real-time business if the query type is real-time business; The historical business processing unit is used to call the historical data stored in the batch processing layer in the form of batch data to process the historical business if the query type is historical business.

4. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the intelligent monitoring method based on time-space relationship as described in any one of claims 1 to 2 when executing the computer program.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the intelligent monitoring method based on time-space relationship as described in any one of claims 1 to 2 is implemented.

Images