A mine personnel gathering risk monitoring and early warning method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of monitoring and early warning methods, devices, electronic equipment and storage medium of personnel gathering risk under mine, the method is uploaded to message queue with personnel positioning data and environmental data under mine and forms message stream;Through big data computing engine, real-time monitoring is carried out on the message queue and the positioning data and environmental data in the message stream are received in stream;The personnel positioning data and the environmental data are analyzed and the real-time early warning classification of each area under mine is updated according to the analysis result;According to real-time early warning classification, it is judged whether there is gathering risk in each area.Using the above method, the real-time, throughput and accuracy of early warning data can be greatly improved with the advantages of big data technology.A high-efficiency, reliable and intelligent personnel gathering risk early warning system can be constructed, which promotes the improvement of safety management level and the enhancement of emergency response capability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safety, and in particular to a detection and early warning method and device for underground personnel gathering risk, an electronic device and a storage medium. BACKGROUND

[0002] At present, the personnel gathering risk early warning function of underground coal mines mostly uses the websocket network transmission protocol to upload data, and cooperates with the OLTP (on-line transaction processing) system to analyze data, so as to realize the early warning of personnel gathering.

[0003] WebSocket is a protocol for full-duplex communication over a single TCP connection. WebSocket makes data exchange between client and server much easier, allowing the server to actively push data to the client. In the WebSocket API, the browser and the server only need to complete a handshake, and a persistent connection can be created between the two, and bidirectional data transmission can be performed, that is, the flow meter can send messages to the server and receive event-driven responses without polling the server to obtain responses. After the connection is created, the data packet header for protocol control is relatively small when data is exchanged between the server and the client. Without extensions, the header size is only 2 to 10 bytes (related to the length of the data packet) for server-to-client content; for client-to-server content, the header also needs to add an additional 4-byte mask. Since the protocol is full-duplex, the server can actively send data to the client at any time. Compared with HTTP requests that need to wait for the client to initiate a request before the server can respond, the delay is significantly less; even compared with long polling similar to Comet, it can deliver more data in a short time.

[0004] Although the real-time performance of data is guaranteed by using the above method, it is not a streaming calculation, and if it faces a large amount of data, it will cause data delay, congestion and other abnormal situations. SUMMARY

[0005] The present application provides a kind of monitoring and early warning method, device, electronic equipment and storage medium for underground personnel gathering risk, for realizing the real-time monitoring when underground personnel gathering related situation data volume is larger.

[0006] According to one aspect of the present application, a monitoring and early warning method for underground personnel gathering risk is provided, comprising:

[0007] The personnel positioning data and environmental data in the mine are uploaded to the message queue to form a message stream;

[0008] The big data computing engine is used for real-time monitoring of the message queue and real-time receiving of the personnel positioning data and the environment data in the message stream.

[0009] The personnel positioning data and the environment data are analyzed, and the real-time early warning classification of each area in the mine is updated according to the analysis result.

[0010] According to the real-time early warning classification, it is judged whether there is an aggregation risk in each area.

[0011] Further, the personnel positioning data and the environment data of the personnel in the mine are uploaded to the message queue to form a message stream, comprising:

[0012] The initial positioning data of the personnel in the mine is obtained by a positioning device worn by the personnel in the mine;

[0013] According to the initial positioning data, the area where the personnel is currently located is obtained;

[0014] The early warning classification of the last round of the area is obtained, and a marker adapted to the early warning classification of the last round is generated and encapsulated with the initial positioning data to form personnel positioning data;

[0015] The personnel positioning data and the environment data are written into the kafka message stream; wherein the kafka is provided with a personnel positioning data partition and an environment data partition, and the personnel positioning data partition has a plurality of partitions.

[0016] The personnel positioning data is written into the personnel positioning data partition, and the personnel positioning data is written into different personnel positioning data partitions according to the different markers; and the environment data is written into the environment data partition.

[0017] Further, the big data computing engine is used for real-time monitoring of the message queue and real-time receiving of the personnel positioning data and the environment data in the message stream, comprising:

[0018] The message stream is received in a polling manner, and each time the polling is performed, the data in the environment data partition is received first, and then the data in the personnel positioning data partition is received in a first receiving order, wherein the first receiving order is a partition receiving order from high to low according to the early warning classification indicated by the marker.

[0019] Further, after the data in the environment data partition is received first, and before the data in the personnel positioning data partition is received in the first receiving order, comprising:

[0020] whether there is an exception in real-time analysis of the environment data obtained in the current polling process, if yes, obtaining the area where the exception data is located, comparing the current environment data of the area with the environment data of the area in the last polling, if the environment data deteriorates, increasing the warning classification of the area according to the deterioration degree, if the environment data is stable or optimized, keeping the warning classification of the area same as the last round;

[0021] reclassifying and updating the first receiving sequence of the personnel positioning data partition according to the current highest warning classification of the area where the personnel positioning data is stored.

[0022] Further, the analysis of the personnel positioning data and the environment data and the updating of the real-time warning classification of each area in the mine according to the analysis result include:

[0023] obtaining the sorting of each area on the first receiving sequence corresponding to each polling in a preset first time, summing up the sorting of each area to obtain a comprehensive sorting index;

[0024] obtaining the real-time warning classification of each area in the current round according to the analysis of the personnel positioning data and the environment data of the area in the first time, according to the size of the comprehensive sorting index, and according to the period inversely proportional to the size of the comprehensive sorting index.

[0025] Further, each area is divided according to function and size, and each area has a unique identifier.

[0026] Further, the first time is 1 min-5 min.

[0027] The second aspect of the application provides a monitoring and early warning device for the gathering risk of personnel in a mine, which includes:

[0028] A data uploading module uploads personnel positioning data and environment data in the mine to a message queue to form a message stream;

[0029] A data receiving module real-time monitors the message queue through a big data computing engine and stream-receives the personnel positioning data and environment data in the message stream;

[0030] A warning rule updating module is used for analyzing the positioning data and the environment data and updating the real-time warning classification rule of each area in the mine according to the analysis result;

[0031] A risk judgment module judges whether there is a gathering risk in each area according to the real-time warning classification.

[0032] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it causes the electronic device to perform the method described in the first aspect of this application.

[0033] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect of this application.

[0034] In this embodiment, a method for monitoring and early warning of personnel gathering risks in mines is adopted, including uploading personnel location data and environmental data in the mine to a message queue to form a message stream; using a big data computing engine to monitor the message queue in real time and stream the personnel location data and environmental data in the message stream; analyzing the personnel location data and environmental data and updating the real-time early warning level of each area in the mine according to the analysis results; and determining whether there is a gathering risk in each area based on the real-time early warning level.

[0035] By employing the above methods, the advantages of big data technology can be leveraged to significantly improve the real-time performance, throughput, and accuracy of early warning data. This allows for the construction of an efficient, reliable, and intelligent early warning system for the risk of crowd gatherings, thereby enhancing safety management and emergency response capabilities. Attached Figure Description

[0036] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 This is a flowchart of a method for monitoring and early warning of the risk of personnel gathering in mines according to an embodiment of this application.

[0038] Figure 2 This is a schematic diagram of a module for monitoring and early warning of the risk of personnel gathering in mines according to an embodiment of this application.

[0039] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0040] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0041] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0042] As Figure 1 The flowchart of the mine personnel gathering risk monitoring and early warning method of the embodiment of the application is shown in the figure, and the mine personnel gathering risk monitoring and early warning method of the application includes the following steps:

[0043] Step S101, uploading the personnel positioning data and environmental data of the underground mine to the message queue to form a message stream.

[0044] The personnel positioning data includes personnel ID, personnel name, personnel state, personnel layer, personnel x coordinate, personnel y coordinate, data time, etc. The environmental data includes roadway width, ventilation condition, work nature, roadway width, ventilation condition, work nature, oxygen concentration, temperature, humidity, etc. Different environments are suitable for different number of personnel, so the personnel gathering risk needs to be considered from both the environmental data and the personnel data.

[0045] Step S102, real-time monitoring of the message queue by a big data computing engine and streaming receiving of the positioning data and environmental data in the message stream.

[0046] According to the real-time requirement of data processing, resource consumption and complexity, etc., a suitable big data computing engine is selected, such as Apache Flink, Apache Spark Streaming, etc., which can greatly improve the real-time performance and efficiency. The system can quickly identify the personnel gathering situation and issue an early warning in the first time, which is very important for preventing and handling emergencies. At the same time, by using advanced algorithms and models, the computing engine can deeply analyze the massive data and accurately judge the degree and trend of personnel gathering.

[0047] In this embodiment, Apache Flink is selected, which has strong state management and low delay processing capability and performs well in real-time stream processing scenarios. In the big data computing engine, a corresponding stream processing job is set, which continuously pulls data from Kafka and prepares for subsequent analysis and processing.

[0048] Step S103, analyzing the personnel positioning data and the environmental data and updating the real-time early warning classification of each area of the underground mine according to the analysis result. The areas are divided according to function and size, for example, the underground mine is divided into grid or polygon partitioning, and each area has a unique identifier.

[0049] Step S104, determine whether there is a gathering risk in each area according to the real-time early warning classification.

[0050] After receiving the personnel coordinate data, the big data computing engine will perform real-time analysis on the data based on the preset early warning classification rules.

[0051] Early warning classification rules: The rules should clearly define the key parameters such as personnel density threshold, gathering duration, etc. in different work areas. These parameters may vary due to factors such as work nature, site conditions, safety standards, etc. (In this case, considering that the early warning classification rules may not be fixed, it is made into a configuration, such as A work area, approved 10 people. B work area, approved 5 people)

[0052] Data analysis: Use spatial analysis algorithms (such as K-means clustering, DBSCAN density clustering, etc.) to process coordinate data and identify personnel distribution in each work area. At the same time, analyze the dynamic changes of personnel gathering in combination with the time dimension.

[0053] Judgment logic: According to the analysis results, determine whether each work point reaches or exceeds the preset personnel gathering threshold. If it does, further classify and evaluate the gathering degree. Once it is determined that there is excessive personnel gathering in a certain work point and it exceeds the specified threshold, the system will immediately trigger the corresponding classification alarm mechanism.

[0054] Alarm mode: Alarm modes can be diversified, including but not limited to SMS notification, email reminder, system pop-up window, voice broadcast, etc. Select appropriate alarm mode according to the degree of urgency and the characteristics of the recipient.

[0055] Alarm content: Alarm information should include specific work point location, current personnel gathering situation, gathering level, recommended measures, etc. Key information to enable relevant personnel to respond quickly.

[0056] Subsequent processing: After triggering the alarm, the system should record the alarm event and generate reports for subsequent analysis as needed. At the same time, support linkage with other safety management systems (such as emergency response systems, video monitoring systems, etc.) to achieve more comprehensive safety management.

[0057] In some preferred embodiments, the uploading of the personnel positioning data and environmental data under the mine to the message queue to form a message stream comprises:

[0058] Step S1011, obtain the initial positioning data of the personnel under the mine through the positioning device worn by the personnel under the mine. In this embodiment, the positioning device can be realized by technologies such as uwb positioning, RFID positioning, GPS positioning, etc.

[0059] Step S1012, an area where the person is currently located is obtained according to the initial positioning data. Specifically, according to the coordinates of the initial positioning data and the boundaries of each area, it can be judged which area the coordinates fall into.

[0060] Step S1013, a warning classification of the last round in the area is obtained, and a marker adapted to the warning classification of the last round is generated together with the initial positioning data to form personnel positioning data.

[0061] Step S1014, the personnel positioning data and the environment data are written into a kafka message stream; wherein the kafka is provided with a personnel positioning data partition and an environment data partition, and the personnel positioning data partition has multiple.

[0062] The personnel positioning data is written into the personnel positioning data partition, and the personnel positioning data is written into different personnel positioning data partitions according to the different markers; and the environment data is written into the environment data partition.

[0063] In the above embodiment, Kafka is used as a message middleware to realize decoupling between the positioning subsystem and the big data computing engine. The high throughput and low delay characteristics of Kafka can meet the needs of real-time data processing. Secondly, the stability and scalability of the system are also guaranteed, for example, the replica mechanism of Kafka, fault tolerance recovery of the big data computing engine and other functions can make the system still run stably under high load or fault conditions. According to the data processing amount and system resource situation, the number of partitions and replicas of Kafka and the resource allocation of the big data computing engine can be dynamically configured to realize load balancing.

[0064] According to the above embodiment, the warning classification of the last round in a certain area will affect the marker of the current personnel positioning data in the area, so that the personnel positioning data in different areas will be written into different kafka partitions due to the different markers, which is conducive to the optimization management of different risk level data, for example, different processing of data in different partitions to increase attention to possible abnormal situations and reduce attention to more regular situations.

[0065] In some preferred embodiments, the real-time monitoring of the message queue and the stream reception of the personnel positioning data and the environment data in the message stream by the big data computing engine include:

[0066] The message stream is received in a polling manner, and each time the polling is performed, the data in the environment data partition is received first, and then the data in the personnel positioning data partition is received in a first receiving order, wherein the first receiving order is a partition receiving order from high to low according to the warning classification indicated by the marker.

[0067] Since whether to gather is first related to environmental data, the environment is good, and more personnel can be gathered, the environment is poor, and the personnel gathering needs to be reduced, so in the polling receiving of the embodiment, the environmental data is received preferentially, thereby facilitating the overall judgment and identification of the environment first, and then the personnel positioning data in different environments can be identified in a targeted manner, and the personnel positioning data in the area with abnormal environmental data can be preferentially received and analyzed to achieve the fastest response to abnormal conditions.

[0068] In some preferred embodiments, after receiving the data in the first environmental data partition, and before receiving the data in the personnel positioning data partition in the first receiving order, the following is included:

[0069] Real-time analysis is performed on the environmental data obtained in the current round of polling process to determine whether there is an abnormality, if there is, the area where the abnormal data is located is obtained, the current environmental data in the area is compared with the environmental data in the area in the last polling, if the environmental data deteriorates, the warning level of the area is increased according to the deterioration degree, if the environmental data is stable or optimized, the warning level of the area is kept the same as the last round.

[0070] The personnel positioning data partition is reclassified and the first receiving order is updated according to the current highest warning level of the area where the personnel positioning data in each partition is located.

[0071] According to the above embodiment, it can be seen that the receiving order of personnel positioning data in each round is obtained under the joint influence of the warning level in the last round and the environmental data changed in the current round, which enables the system to consider both the historical regional conditions and the current temporary changes to optimize the personnel positioning data receiving order. For example, the historical regional gathering risk in the partition is considered to be low, if the environmental data of a certain area in the partition deteriorates in the current round, the warning level of the area is increased, for example, to level 3, although the warning levels of other areas in the partition are still level 1, the partition will be sorted as level 3 in the first receiving order.

[0072] In some optional embodiments, in the sorting of the first receiving order, if the highest warning levels of the areas in different partitions are the same, the partitions are sorted according to the number of highest warning levels from more to less. For example, the highest warning levels of the areas in the first partition and the second partition are both 3, the first partition has 2 areas with a warning level of 3, and the second partition has 1 area with a warning level of 3, so in the sorting of the receiving order, the first partition is before the second partition.

[0073] Since the environmental data in each round can change, which can be just normal fluctuation or can be a sustained change, although the embodiment adjusts the receiving order of the personnel positioning data according to the environmental data in each round, the overall judgment of the personnel gathering risk needs to be made by comprehensively considering the environmental data and the personnel positioning data, at this time, the data in a certain time span needs to be collected to identify the development trend and judge whether there is a real risk.

[0074] Therefore, in some preferred embodiments, the analysis of the personnel positioning data and the environmental data and the updating of the real-time warning classification of each area in the mine according to the analysis result comprises:

[0075] In step S1031, the ranking of each area on the first receiving order corresponding to each polling in a preset first time is obtained, and the rankings of each area are summed to obtain a comprehensive ranking index. In some preferred embodiments, the window can be set according to the warning requirements of the actual coal mine, that is, the first time, so that the data in the specified time range can be aggregated and analyzed.

[0076] The judgment process of the personnel gathering risk level in each round will refer to the results of multiple polling, and the first receiving order generated by a single polling can only reflect the risk level indicated by the environmental data of each area in a single polling, and the comprehensive ranking index will reflect the overall risk situation of the environmental indication of each area in the first time. For example, for the A area where the environmental data fluctuates and deteriorates in a polling and the areas corresponding to the personnel positioning data located in the same partition as the A area in the round, the corresponding comprehensive ranking index will be higher due to the fluctuation and deterioration of the A area, but if the fluctuation and deterioration of the environmental data of the A area is only accidental and quickly recovers to normal, the first receiving order of the partition where the A area is located will not be affected by this fluctuation in other polling. If the fluctuation and deterioration of the environmental data of the A area is sustained, the first receiving order of the partition where the A area is located will be continuously affected in the subsequent polling, which will cause the comprehensive ranking index of the partition where the A area is located to continuously increase. The above method obtains the comprehensive ranking index from the ranking of multiple polling to indicate the environmental change in a period of time, the more stable and better the environment is, the smaller the comprehensive ranking index is, and the more abnormal and sustained the environment is, the larger the comprehensive ranking index is.

[0077] In some optional embodiments, the personnel positioning data is written into different personnel positioning data partitions according to the different markers, comprising:

[0078] The personnel positioning data is divided into n*m partitions, the position in the personnel positioning data belongs to the nth partition and the m pre-warning levels corresponding to the marker; the number of the personnel positioning data partitions is N*M, wherein N is equal to the number of independent area sets, each independent area set has at least one area, the areas in the independent area set have the same function and are interconnected; M is the number of pre-warning levels; n belongs to N and m belongs to M.

[0079] In this way, the entire Kafka is configured into N*M partitions through the function and position of the area, and since the areas in each independent area set have the same function and are interconnected, and the marker corresponds to the pre-warning level of the last round, the areas in each independent area set are easily influenced to obtain the same marker, so that the personnel positioning data belonging to the same independent area set and having the same marker will be divided into the same partition, and the personnel gathering conditions of these areas will usually influence each other, so that when the first receiving order is sorted according to the partition, the comprehensive sorting index of each personnel positioning data in the partition, i.e., the corresponding area, will be affected as a whole, so that the abnormal condition of the independent area set is magnified and thus easily discovered by the system.

[0080] In step S1032, according to the size of the comprehensive sorting index, the real-time pre-warning classification of each area in the current round is obtained by combining the personnel positioning data and the environmental data of the area in the first time and the analysis of the area in the first time according to the period inversely proportional to the size of the comprehensive sorting index.

[0081] In some specific embodiments, the above-mentioned analysis and pre-warning process can be realized by Flink / Spark. For example, the DataStream API of Flink is used to process real-time data stream, a partition mapping function is defined to calculate the partition ID according to the personnel coordinates and the mine layer code, the state (such as ValueState or ListState) of Flink is used to maintain the personnel count of each partition, a risk judgment function is defined to trigger pre-warning when the count exceeds the threshold, and the Sink API of Flink is used to send the pre-warning information to the corresponding system or interface.

[0082] In the analysis process of some specific embodiments, the clustering degree can be identified by a density-based clustering algorithm DBSCAN, in which a neighborhood size (ε) and a minimum point number (MinPts) are preset as parameters of the clustering algorithm; for each point, check whether the number of points in its ε neighborhood is greater than or equal to MinPts, if yes, mark the point as a core point; from any core point, find all points density-reachable from the point to form a cluster; for non-core points, if they are in the ε neighborhood of a core point, mark them as boundary points; points that are neither core points nor boundary points are regarded as noise points. The data stream can be processed by using the DataStream API and state of Flink, and the clustering logic of DBSCAN can be implemented. The clustering effect can also be optimized by setting appropriate ε and MinPts parameters, and the personnel gathering risk can be judged according to the clustering result by using the DBSCAN algorithm provided by Spark MLlib, including training using the DataFrame API and the DBSCAN model of MLlib, and processing real-time or batch data.

[0083] Based on the same inventive concept as the method embodiments described above, the embodiments of the present application also provide a monitoring and early warning device for personnel gathering risk in a mine, as shown in Figure 2 The structure of the monitoring and early warning device for personnel gathering risk in a mine according to the embodiments of the present application is shown in the structure diagram of the monitoring and early warning device for personnel gathering risk in a mine according to the embodiments of the present application, which comprises:

[0084] A data uploading module is configured to upload the personnel positioning data and the environmental data in the mine to a message queue to form a message stream.

[0085] A data receiving module is configured to listen to the message queue in real time by a big data computing engine and stream-receive the personnel positioning data and the environmental data in the message stream.

[0086] An early warning rule updating module is configured to analyze the personnel positioning data and the environmental data and update the real-time early warning classification rules of each area in the mine according to the analysis result.

[0087] A risk judgment module is configured to judge whether there is a gathering risk in each area according to the real-time early warning classification.

[0088] In some preferred embodiments, the data uploading module configured to upload the personnel positioning data and the environmental data in the mine to a message queue to form a message stream comprises:

[0089] A positioning module is configured to obtain initial positioning data of personnel in the mine by a positioning device worn by the personnel in the mine.

[0090] A region acquisition module is configured to acquire a region where the person is currently located according to the initial positioning data.

[0091] A packaging module is configured to acquire a pre-warning classification of a previous round in the region, and to generate a marker adapted to the pre-warning classification of the previous round and package the initial positioning data to form person positioning data.

[0092] A writing module is configured to write the person positioning data and the environment data into a kafka message stream, wherein the kafka is provided with a person positioning data partition and an environment data partition, and the person positioning data partition has multiple.

[0093] The person positioning data is written into the person positioning data partition, and the person positioning data is written into different person positioning data partitions according to different markers; and the environment data is written into the environment data partition.

[0094] In some preferred embodiments, the data receiving module is configured to listen to the message queue in real time through a big data computing engine and stream-receive person positioning data and environment data in the message stream, including:

[0095] A sequential receiving module is configured to receive the message stream in a polling manner, and each time the polling is performed, data in the environment data partition is received first, and then data in the person positioning data partition is received in a first receiving order, wherein the first receiving order is a partition receiving order from high to low according to the pre-warning classification indicated by the marker.

[0096] In some preferred embodiments, the sequential receiving module includes:

[0097] An environment data anomaly querying module is configured to analyze whether there is an anomaly in the environment data obtained in the current polling process in real time, and if there is, to acquire a region where the anomaly data is located, and to compare current environment data in the region with environment data in the region in a previous round, and if the environment data is deteriorated, to increase a pre-warning classification of the region according to a deterioration degree, and if the environment data is stable or optimized, to keep the pre-warning classification of the region same as that in the previous round.

[0098] A sequential updating module is configured to re-classify and update the first receiving order of the person positioning data partition according to a current highest pre-warning classification of a region where person positioning data stored in the person positioning data partition is located.

[0099] In some preferred embodiments, the pre-warning rule updating module is configured to analyze the person positioning data and the environment data and update real-time pre-warning classification rules of each region in a mine according to an analysis result, including:

[0100] The comprehensive ranking module is configured to obtain a ranking of each region on the first receiving sequence in each round within a preset first time, and sum up the ranking of each region to obtain a comprehensive ranking index.

[0101] The analysis module is configured to analyze a real-time early warning level of each region according to the size of the comprehensive ranking index, a period inversely proportional to the size of the comprehensive ranking index, and the personnel positioning data and the environmental data of the region within the first time.

[0102] It should be noted that, although several units or sub-units of the apparatus are mentioned in the foregoing detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into units embodied by multiple units.

[0103] Based on the same inventive concept as the method embodiments described above, the embodiments of the present application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to enable the electronic device to implement the control method in the above embodiments.

[0104] In an embodiment, the electronic device can be a server, and in this embodiment, the structure of the electronic device can be as shown in Figure 3 The electronic device includes a memory 2001, a communication module 2003, and one or more processors 2002.

[0105] The memory 2001 is configured to store a computer program executed by the processor 2002. The memory 2001 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and programs required for running instant messaging functions, etc.; and the data storage area can store various instant messaging information and operation instruction sets, etc.

[0106] Memory 2001 may be volatile memory, such as random-access memory (RAM); memory 2001 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 2001 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 2001 may be a combination of the above-mentioned memories.

[0107] Processor 2002 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2002 is used to implement the above-mentioned audio data processing method when calling computer programs stored in memory 2001.

[0108] The communication module 2003 is used to communicate with terminal devices and other servers.

[0109] This application embodiment does not limit the specific connection medium between the memory 2001, communication module 2003, and processor 2002. This application embodiment... Figure 3 The memory 2001 and the processor 2002 are connected via a bus 2004, which is in... Figure 3 The connections between other components are illustrated with arrows and are for illustrative purposes only, not as limiting information. The Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 1 The text uses only one arrow to describe it, but does not indicate that there is only one bus or one type of bus.

[0110] With the same inventive concept as the above method embodiments, the embodiments of the present application also provide a computer readable storage medium for storing a computer program, which, when executed on a computer, causes the electronic device to implement the control method in the above embodiments. The computer readable storage medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0111] With the same inventive concept as the above method embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program, when the program product is executed on an electronic device, the computer program is used to cause the electronic device to perform the steps in the control method according to various exemplary embodiments of the present application described in the specification. The program product can adopt any combination of one or more readable media. These computer program commands can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the commands executed by the processor of the computer or other programmable data processing device produce a method for implementing the functions specified in one or more flows or blocks in the specification. Figure 1 The apparatus can be configured to perform one or more flows or blocks and / or one or more functions specified in the flows or blocks. Figure 1 The apparatus can be configured to perform one or more flows or blocks and / or one or more functions specified in the flows or blocks.

[0112] Although the preferred embodiments of the present application have been described, those skilled in the art who have the basic inventive concept can make additional changes and modifications to the embodiments. Therefore, the appended claims are intended to include the preferred embodiments and all changes and modifications falling within the scope of the present application.

Claims

1. A method for monitoring and early warning of gathering risk of underground personnel, characterized in that, the personnel positioning data and environmental data of underground personnel are uploaded to a message queue to form a message stream; the personnel positioning data and environmental data in the message stream are received in real time by a big data computing engine through real-time monitoring of the message queue, including: receiving the message stream in a polling manner, and at each polling, first receiving data in the environmental data partition, and analyzing the environmental data obtained in the current polling process in real time to determine whether there is an abnormality, if there is, obtaining the area where the abnormal data is located, comparing the current environmental data of the area with the environmental data of the area at the last polling, if the environmental data deteriorates, increasing the early warning classification of the area according to the degree of deterioration, if the environmental data is stable or optimized, keeping the early warning classification of the area the same as that of the last round; the personnel positioning data partition is reclassified and the first receiving order is updated according to the current highest early warning classification of the area where the personnel positioning data stored in each personnel positioning data partition is located, and then the data in the personnel positioning data partition is received according to the first receiving order, the first receiving order is a partition receiving order from high to low according to the early warning classification indicated by the marker, and the marker is adapted to the early warning classification; the personnel positioning data and the environmental data are analyzed and the real-time early warning classification of each area underground is updated according to the analysis result; whether there is a gathering risk in each area is determined according to the real-time early warning classification.

2. The method of claim 1, wherein, the personnel positioning data and environmental data of underground personnel are uploaded to a message queue to form a message stream, including: initial positioning data of underground personnel is obtained by a positioning device worn by the underground personnel; the area where the personnel is currently located is obtained according to the initial positioning data; the early warning classification of the area at the last round is obtained, and a marker adapted to the early warning classification at the last round is generated and encapsulated with the initial positioning data to form personnel positioning data; the personnel positioning data and the environmental data are written into a kafka message stream; wherein the kafka is provided with personnel positioning data partitions and environmental data partitions, and the personnel positioning data partitions have multiple personnel positioning data partitions; wherein the personnel positioning data is written into the personnel positioning data partitions, and the personnel positioning data is written into different personnel positioning data partitions according to the different markers; and the environmental data is written into the environmental data partitions.

3. The method of claim 1, wherein, the personnel positioning data and the environmental data are analyzed and the real-time early warning classification of each area underground is updated according to the analysis result, including: the sorting on the first receiving order of each area in a preset first time corresponding to each polling is obtained, and the sorting of each area is summed to obtain a comprehensive sorting index; according to the size of the comprehensive sorting index, a period inversely proportional to the size of the comprehensive sorting index is combined with the analysis of the personnel positioning data and the environmental data of the area in the first time to obtain the real-time early warning classification of each area in this round.

4. The method according to any one of claims 1 to 3, characterized in that, each area is divided according to function and size, and each area has a unique identifier.

5. The method of claim 3, wherein, the first time is 1 min-5 min.

6. A monitoring and early warning device for the risk of gathering of persons in a mine, characterized in that, including: The data uploading module uploads the personnel positioning data and the environment data of the underground mine to a message queue to form a message flow. The data receiving module receives the personnel positioning data and the environment data in the message flow in real time by monitoring the message queue through a big data computing engine, including: receiving the message flow in a polling manner, and at each polling, first receiving the data in the environment data partition, and performing real-time analysis on the environment data obtained in the current polling process to determine whether there is an abnormality, if there is, obtaining the region where the abnormal data is located, comparing the current environment data of the region with the environment data of the region in the last polling, if the environment data deteriorates, increasing the warning classification of the region according to the degree of deterioration, if the environment data is stable or optimized, keeping the warning classification of the region the same as that in the last polling; reclassifying the personnel positioning data partition according to the current highest warning classification of the region where the personnel positioning data stored in each personnel positioning data partition is located, and updating a first receiving order; then receiving the data in the personnel positioning data partition according to the first receiving order, the first receiving order being a partition receiving order from high to low according to the warning classification indicated by a marker, and the marker being adapted to the warning classification; The warning rule updating module is configured to analyze the personnel positioning data and the environment data and update the real-time warning classification rules of each region in the underground mine according to the analysis result. The risk judgment module is configured to determine whether there is an aggregation risk in each region according to the real-time warning classification.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program, so that the electronic device implements the method in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium is configured to store a computer program, when the computer program runs on a computer, so that the computer executes the method in any one of claims 1 to 5.

Images