Miner lamp-based abnormal event monitoring method and device, computer equipment and medium

Abstract

The invention provides an abnormal event monitoring method and device based on a mine lamp, computer equipment and a storage medium. The method comprises the following steps: acquiring environment parameter data and behavior data in a mine lamp use environment; performing exception identification on the environment parameter data and the behavior data to obtain an exception factor of the target exception event; performing association rule mining on the abnormal factors to obtain abnormal association rules; generating a factor association coefficient based on the abnormal association rule; processing the abnormal association rule set based on a weight determination model to obtain an abnormal factor weight; generating a dynamic abnormal coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight; and displaying the dynamic abnormal coefficient in a mine lamp monitoring page, if the dynamic abnormal coefficient is greater than a preset early warning threshold, generating early warning information corresponding to the target abnormal event, and sending the early warning information to a related user. According to the invention, the processing efficiency and the response timeliness of monitoring the abnormal event of the mine lamp are improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device, computer equipment and storage medium for monitoring abnormal events based on a mining lamp. Background Art

[0002] With the rapid progress and widespread application of modern technology, the importance of mining lamps as lighting equipment has become increasingly prominent, playing an irreplaceable role in many fields such as outdoor adventures, diving operations, mining, emergency rescue and even home emergency lighting. Mining lamps are not only required to have efficient and long-lasting lighting capabilities, but also to ensure safety and stability in extreme environments to ensure the personal safety of users and smooth work.

[0003] However, in the actual use of mining lamps, their safety management faces many challenges. At present, most mining lamps rely on manual inspections for abnormal event monitoring. However, the abnormal event monitoring method based on manual inspections has the following shortcomings: manual inspections require a lot of human resources and time costs, and it is difficult to achieve all-weather, uninterrupted monitoring, which easily leads to missed detection or delayed discovery of abnormal events. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, computer equipment and storage medium for monitoring abnormal events based on mining lamps, aiming to solve the technical problems in the prior art that the abnormal event monitoring method based on manual inspection requires a lot of human resources and time costs, is difficult to achieve all-weather, uninterrupted monitoring, and is prone to missed detection or delayed discovery of abnormal events.

[0005] To achieve the above object, the present invention provides a method for monitoring abnormal events based on a mining lamp, the method comprising:

[0006] Collect environmental parameter data and behavior data in the environment where the mining lamp is used based on target sensors;

[0007] Performing abnormality identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple;

[0008] Performing association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors;

[0009] generating a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule;

[0010] Processing the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor;

[0011] Generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight;

[0012] The dynamic abnormality coefficient is displayed in a preset mining lamp monitoring page, and it is determined in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold;

[0013] If so, generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

[0014] Optionally, performing abnormality identification processing on the environmental parameter data and the behavior data to obtain an abnormal factor of a target abnormal event includes:

[0015] Preprocessing the environmental parameter data and the behavior data respectively to obtain corresponding target environmental parameter data and target behavior data;

[0016] Based on a preset statistical analysis method, anomaly identification is performed on the target environmental parameter data to obtain corresponding abnormal data;

[0017] Performing image processing on the target behavior data based on a preset image processing algorithm to obtain corresponding image feature data;

[0018] Based on a preset behavior processing algorithm, the image feature data is subjected to abnormality recognition to obtain corresponding abnormal behavior;

[0019] An abnormal factor of the target abnormal event is generated based on the abnormal data and the abnormal behavior.

[0020] Optionally, performing association rule mining on the abnormal factor based on a preset data mining algorithm to obtain an abnormal association rule corresponding to the abnormal factor includes:

[0021] Get multiple preset association rule mining algorithms;

[0022] Determine a target association rule mining algorithm from all the association rule mining algorithms;

[0023] Based on the target association rule mining algorithm, association rule mining is performed on the abnormal factors to obtain abnormal association rules corresponding to the abnormal factors.

[0024] Optionally, generating a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule includes:

[0025] Converting the abnormal association rules into corresponding first feature vectors; each first feature vector corresponds to an abnormal factor;

[0026] Call the preset machine learning model;

[0027] Processing the first feature vector based on the machine learning model to obtain a feature importance score corresponding to the first feature vector;

[0028] The feature importance score is calculated based on a preset correlation coefficient calculation algorithm to obtain a correlation coefficient value corresponding to the abnormal association rule;

[0029] The correlation coefficient value is used as the factor association coefficient corresponding to the abnormal factor.

[0030] Optionally, the processing of the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor includes:

[0031] Converting the abnormal association rule into a corresponding second feature vector; wherein each second feature vector corresponds to an abnormal factor;

[0032] Performing feature engineering processing on the second feature vector to obtain a corresponding target feature vector;

[0033] Call the preset weight determination model;

[0034] Inputting the target feature vector into the weight determination model, processing the target feature vector through the weight determination model, and obtaining a weight corresponding to the target feature vector;

[0035] The weight is used as the abnormal factor weight corresponding to the abnormal factor.

[0036] Optionally, generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight includes:

[0037] Obtaining an abnormal factor value of the abnormal factor;

[0038] Call the preset abnormal coefficient calculation formula;

[0039] Based on the abnormal coefficient calculation formula, the abnormal factor value, the factor correlation coefficient and the abnormal factor weight are calculated to obtain a corresponding calculation result;

[0040] The calculation result is used as the dynamic abnormality coefficient of the target abnormal event.

[0041] Optionally, after generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight, the method further includes:

[0042] generating abnormality explanation information corresponding to the dynamic abnormality coefficient;

[0043] Call the preset monitoring log;

[0044] The dynamic anomaly coefficient and the anomaly explanation information are recorded in the monitoring log.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also provides an abnormal event monitoring device based on a mining lamp, and the abnormal event monitoring device based on a mining lamp comprises:

[0046] A collection module, used to collect environmental parameter data and behavior data in the use environment of the mining lamp based on the target sensor;

[0047] an identification module, used to perform abnormal identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple;

[0048] A mining module, used to perform association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors;

[0049] A first generating module, configured to generate a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule;

[0050] A processing module, used to process the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor;

[0051] A second generating module, configured to generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight;

[0052] A judgment module, used to display the dynamic abnormality coefficient in a preset mining lamp monitoring page, and to judge in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold;

[0053] The sending module is used to generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0055] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the abnormal event monitoring methods based on a mining lamp proposed in the embodiments of the present application are implemented.

[0056] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0057] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the abnormal event monitoring methods based on a mining lamp proposed in the embodiments of the present application are implemented.

[0058] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0059] The present invention provides a method, device, computer equipment and storage medium for monitoring abnormal events based on a mining lamp. The method comprises: firstly, collecting environmental parameter data and behavior data in the mining lamp use environment based on a target sensor; then performing abnormal identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of a target abnormal event; wherein the number of the abnormal factors includes multiple; then performing association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors; and generating factor association coefficients corresponding to the abnormal factors based on the abnormal association rules; and processing the abnormal association rule set based on a preset weight determination model to obtain abnormal factor weights corresponding to the abnormal factors; subsequently generating a dynamic abnormal coefficient of the target abnormal event based on the abnormal factors, the factor association coefficients and the abnormal factor weights; further displaying the dynamic abnormal coefficient in a preset mining lamp monitoring page, and judging in real time whether the dynamic abnormal coefficient is greater than a preset warning threshold; if so, generating warning information corresponding to the target abnormal event, and sending the warning information to relevant users. This application builds a complete automatic monitoring system based on the use of target sensors, data mining algorithms, abnormal association rules, weight determination models, and mining lamp monitoring pages, which can realize real-time monitoring and automatic early warning of the mining lamp use environment, ensuring timely response and taking measures when abnormal events occur, which is conducive to ensuring production safety and personnel safety. Through the automatic monitoring method for abnormal events of mining lamps provided by this application, manual inspections can be effectively avoided, thereby reducing the human resources and time costs required for monitoring abnormal events of mining lamps, and effectively improving the processing efficiency and response timeliness of abnormal event monitoring of mining lamps. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0062] Figure 2 is a flow chart of an abnormal event monitoring method based on a mining lamp provided by an embodiment of the present invention;

[0063] Figure 3 It is a structural schematic diagram of an embodiment of an abnormal event monitoring device based on a mining lamp according to the present application;

[0064] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0065] The abnormal event monitoring method based on a mining lamp provided by an embodiment of the present invention is applied to an abnormal event monitoring device based on a mining lamp. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0069] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0070] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0071] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0072] It should be noted that the abnormal event monitoring method based on the mining lamp provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the abnormal event monitoring device based on the mining lamp is generally arranged in the server / terminal device.

[0073] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0074] With the rapid progress and widespread application of modern technology, the importance of mining lamps as lighting equipment has become increasingly prominent, playing an irreplaceable role in many fields such as outdoor adventures, diving operations, mining, emergency rescue and even home emergency lighting. Mining lamps are not only required to have efficient and long-lasting lighting capabilities, but also to ensure safety and stability in extreme environments to ensure the personal safety of users and smooth work.

[0075] However, in the actual use of mining lamps, their safety management faces many challenges. At present, most mining lamps rely on manual inspections for abnormal event monitoring. However, the abnormal event monitoring method based on manual inspections has the following shortcomings: manual inspections require a lot of human resources and time costs, and it is difficult to achieve all-weather, uninterrupted monitoring, which easily leads to missed detection or delayed discovery of abnormal events.

[0076] Continue to refer Figure 2, shows a flow chart of an embodiment of the abnormal event monitoring method based on a mining lamp proposed in the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology.

[0077] The abnormal event monitoring method based on a mining lamp provided by an embodiment of the present invention comprises the following steps:

[0078] S210, collecting environmental parameter data and behavior data in the mining lamp use environment based on the target sensor.

[0079] In this step, the present invention can be applied to the business scenario of monitoring abnormal events in the use environment of the miner's lamp related to the miner's lamp. And the execution subject of the present invention can be specifically a monitoring system. Specifically, the miner's lamp can be equipped with a sensor with environmental perception and behavior analysis functions, that is, the above-mentioned target sensor, according to the use environment and needs of the miner's lamp. Among them, the environmental perception sensor may include a temperature sensor, a humidity sensor, and a light intensity sensor. The temperature sensor is used to monitor the ambient temperature, the humidity sensor is used to monitor the ambient humidity, and the light intensity sensor is used to monitor the light intensity. The behavior analysis sensor can be a camera, which is used to monitor the behavior of people in the use environment of the miner's lamp. In addition, the selected target sensor is integrated into the miner's lamp, or arranged in the environment where the miner's lamp is used, to ensure that the required data can be collected in real time. In addition, the above-mentioned environmental parameter data refers to various parameters in the use environment of the miner's lamp, including but not limited to temperature, humidity, and light intensity. The above-mentioned behavior data refers to the personnel behavior data collected by the camera, such as personnel movement trajectory data.

[0080] S220, performing abnormality identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple.

[0081] In this step, the above-mentioned abnormal identification processing of the environmental parameter data and the behavior data to obtain the specific implementation process of the abnormal factor of the target abnormal event will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated in detail here.

[0082] S230, performing association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors.

[0083] In this step, the above-mentioned specific implementation process of performing association rule mining on the abnormal factors based on the preset data mining algorithm to obtain the abnormal association rules corresponding to the abnormal factors will be further described in detail in the subsequent specific embodiments of the present application, and will not be elaborated on here.

[0084] S240: Generate a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule.

[0085] In this step, the specific implementation process of generating the factor association coefficient corresponding to the abnormal factor based on the abnormal association rule will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0086] S250, processing the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor.

[0087] In this step, the above-mentioned specific implementation process of processing the abnormal association rule set based on the preset weight determination model to obtain the abnormal factor weight corresponding to the abnormal factor will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated here.

[0088] S260: Generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient, and the abnormal factor weight.

[0089] In this step, the specific implementation process of generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated here.

[0090] S270, displaying the dynamic abnormality coefficient in a preset mining lamp monitoring page, and determining in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold.

[0091] In this step, the above-mentioned mining lamp monitoring page is a pre-built visual warning page for dynamic abnormal events corresponding to the mining lamp use environment. The construction process of the mining lamp monitoring page includes: Page design: Use front-end technologies such as HTML5 and CSS3 to design a user-friendly visual warning page to ensure that the page layout is clear and the information display is intuitive. Data response: Use programming languages ​​such as Python, R or Java to implement data response of the page to ensure that the page can display dynamic abnormality coefficients and related warning information in real time. Automated deployment: Use tools such as Jenkins and GitLab CI / CD to realize automated construction, testing and deployment of pages to ensure rapid iteration and stable operation of the early warning system. Among them, there is no specific limitation on the value of the above-mentioned warning threshold, which can be set according to actual warning needs.

[0092] S280: If yes, generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

[0093] In this step, if the dynamic abnormal coefficient is greater than the preset warning threshold, the early warning mechanism is automatically triggered to generate early warning information corresponding to the target abnormal event, and the early warning information is sent to relevant personnel through email, text message, instant messaging tools (such as Slack, DingTalk), etc. Among them, the above-mentioned relevant personnel may be the person responsible for the use environment of the mining lamp. In addition, the above-mentioned target abnormal event and the above-mentioned dynamic coefficient can be filled into the preset early warning information template to generate corresponding early warning information. The template content of the above-mentioned early warning information template can be set according to the actual early warning reminder needs. In addition, a detailed emergency response process can be further formulated for the above-mentioned target abnormal event, and the response measures under different warning levels are clarified and sent to relevant personnel at the same time to ensure that the relevant personnel can quickly and effectively respond to the currently sent target abnormal event. And the details of each emergency response can be recorded, including response time, processing process, processing results, etc., to provide a basis for subsequent analysis and improvement.

[0094] In an embodiment of the present invention, firstly, environmental parameter data and behavior data in the environment where a mining lamp is used are collected based on a target sensor; then, the environmental parameter data and the behavior data are subjected to abnormal identification processing to obtain abnormal factors of a target abnormal event; wherein, the number of the abnormal factors includes multiple; then, association rule mining is performed on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors; and factor association coefficients corresponding to the abnormal factors are generated based on the abnormal association rules; and the abnormal association rule set is processed based on a preset weight determination model to obtain abnormal factor weights corresponding to the abnormal factors; subsequently, a dynamic abnormal coefficient of the target abnormal event is generated based on the abnormal factors, the factor association coefficients and the abnormal factor weights; the dynamic abnormal coefficient is further displayed in a preset mining lamp monitoring page, and it is determined in real time whether the dynamic abnormal coefficient is greater than a preset warning threshold; if so, warning information corresponding to the target abnormal event is generated, and the warning information is sent to relevant users. This application builds a complete automatic monitoring system based on the use of target sensors, data mining algorithms, abnormal association rules, weight determination models, and mining lamp monitoring pages, which can realize real-time monitoring and automatic early warning of the mining lamp use environment, ensuring timely response and taking measures when abnormal events occur, which is conducive to ensuring production safety and personnel safety. Through the automatic monitoring method for abnormal events of mining lamps provided by this application, manual inspections can be effectively avoided, thereby reducing the human resources and time costs required for monitoring abnormal events of mining lamps, and effectively improving the processing efficiency and response timeliness of abnormal event monitoring of mining lamps.

[0095] Optionally, performing abnormality identification processing on the environmental parameter data and the behavior data to obtain an abnormal factor of a target abnormal event includes:

[0096] The environmental parameter data and the behavior data are preprocessed respectively to obtain corresponding target environmental parameter data and target behavior data.

[0097] In this step, the environmental parameter data is cleaned by removing noise, filling missing values, etc. to ensure data quality, and the cleaned data is formatted into a format suitable for subsequent processing, that is, the numerical data is converted into a format suitable for analysis to obtain the corresponding target environmental parameter data. In addition, the behavior data can be processed by removing noise, enhancing contrast, graying, etc. to improve the image quality of the behavior data, and the processed data is converted into a uniform resolution and format to obtain the corresponding target behavior data.

[0098] Based on a preset statistical analysis method, anomalies are identified on the target environmental parameter data to obtain corresponding abnormal data.

[0099] In this step, the statistical analysis method may include means, variances, standard deviations, etc., and the target environmental parameter data (such as temperature, humidity, light intensity, etc.) is analyzed for change trends by using the statistical analysis method to identify corresponding abnormal data. The abnormal data may include abnormal values ​​or abnormal patterns.

[0100] The target behavior data is processed based on a preset image processing algorithm to obtain corresponding image feature data.

[0101] In this step, the target behavior data is specifically image data. The above-mentioned image processing process includes: firstly, decoding the received target behavior data from the encoding format (such as JPEG, PNG) into processable pixel data. Then, using image processing algorithms (such as edge detection, corner detection, texture analysis, etc.) to extract useful features in the image, such as the outline of a person, the movement trajectory, etc., to obtain the corresponding image feature data.

[0102] Based on a preset behavior processing algorithm, abnormality identification is performed on the image feature data to obtain corresponding abnormal behavior.

[0103] In this step, the above-mentioned behavior processing algorithm includes a target detection algorithm and a behavior recognition algorithm. Specifically, the target detection algorithm is used to detect pedestrians or other key targets in the image feature data. Then the detected target is tracked and its movement trajectory, speed, acceleration and other motion parameters are recorded. After that, the behavior recognition algorithm is used to identify abnormal behaviors such as sudden acceleration, stopping, wandering, etc. according to the motion parameters and image features of the target. Among them, the above-mentioned target detection algorithm can adopt algorithms such as YOLO, SSD, Faster R-CNN, etc. The above-mentioned behavior recognition algorithm can adopt hidden Markov model, long short-term memory network LSTM, convolutional neural network CNN combined with recurrent neural network RNN, etc.

[0104] An abnormal factor of the target abnormal event is generated based on the abnormal data and the abnormal behavior.

[0105] In this step, the abnormal data and the abnormal behavior are integrated to obtain the abnormal factor of the target abnormal event, wherein the abnormal factor includes the abnormal data and the abnormal behavior.

[0106] In this embodiment, the corresponding target environment parameter data and target behavior data are obtained by preprocessing the environment parameter data and the behavior data respectively; then, the target environment parameter data is identified as abnormal based on a preset statistical analysis method to obtain corresponding abnormal data; then, the target behavior data is image processed based on a preset image processing algorithm to obtain corresponding image feature data; subsequently, the image feature data is identified as abnormal based on a preset behavior processing algorithm to obtain corresponding abnormal behavior; finally, an abnormal factor of the target abnormal event is generated based on the abnormal data and the abnormal behavior. The present application performs an abnormal analysis on the environment parameter data based on the use of a statistical analysis method to obtain abnormal data, and performs an abnormal analysis on the behavior data based on an image processing algorithm and a behavior processing algorithm to obtain abnormal behavior, and then based on the abnormal data and the abnormal behavior, the abnormal factor of the target abnormal event can be quickly and accurately generated, thereby improving the generation efficiency of the abnormal factor and ensuring the data accuracy of the obtained abnormal factor.

[0107] Optionally, performing association rule mining on the abnormal factor based on a preset data mining algorithm to obtain an abnormal association rule corresponding to the abnormal factor includes:

[0108] Get multiple preset association rule mining algorithms.

[0109] In this step, the above association rule mining algorithm may at least include Apriori algorithm, FP-growth algorithm, etc.

[0110] A target association rule mining algorithm is determined from all the association rule mining algorithms.

[0111] In this step, according to the type and quantity of abnormal factors, a suitable association rule mining algorithm can be selected from all the association rule mining algorithms as the above-mentioned target association rule mining algorithm, and preferably the Apriori algorithm can be used.

[0112] Based on the target association rule mining algorithm, association rule mining is performed on the abnormal factors to obtain abnormal association rules corresponding to the abnormal factors.

[0113] In this step, the parameters of the target association rule mining algorithm are set according to the actual business needs, such as the minimum support, the minimum confidence, etc., to determine the significance and accuracy of the mining results. Then, the target association rule mining algorithm is used to mine the association rules of the abnormal factors to find the correlation between the abnormal factors and the potential relationship between them and the target abnormal events. Then, according to the set abnormal value threshold, the abnormal association rules that meet the conditions (i.e., the abnormal value threshold) are screened out. Among them, the rule representation can also be performed: the screened abnormal association rules are expressed in an easy-to-understand manner, such as "If the temperature exceeds X degrees and the humidity is lower than Y%, then Z event may occur." In addition, there is no specific limitation on the determination method of the above-mentioned abnormal value threshold. For example, a reasonable abnormal value threshold can be set according to the experience or business rules of the actual application scenario. For example, when the temperature exceeds a certain value, dangerous events such as fire may be triggered. Alternatively, a statistical method (such as Z-score, IQR, etc.) is used to determine the abnormal value threshold to determine the significance of the abnormal association rules. In addition, the screened abnormal association rules are stored in a database for subsequent analysis and early warning.

[0114] In this embodiment, a plurality of preset association rule mining algorithms are obtained; then a target association rule mining algorithm is determined from all the association rule mining algorithms; then association rule mining is performed on the abnormal factors based on the target association rule mining algorithm to obtain abnormal association rules corresponding to the abnormal factors. The present application determines a target association rule mining algorithm from all the acquired association rule mining algorithms, and then performs association rule mining on the abnormal factors based on the target association rule mining algorithm, so as to realize intelligent and accurate acquisition of abnormal association rules corresponding to the abnormal factors, thereby ensuring the accuracy of the obtained abnormal association rules, and facilitating the generation of subsequent factor association coefficients and abnormal factor weights of abnormal factors.

[0115] Optionally, generating a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule includes:

[0116] The abnormal association rule is converted into a corresponding first feature vector. Each first feature vector corresponds to an abnormal factor.

[0117] In this step, the abnormal association rules are converted into a data format suitable for model processing, that is, the abnormal association rules are converted into feature vectors to obtain the corresponding first feature vectors, which can be referred to as features. Each feature corresponds to an abnormal factor, and the value of the feature can be the frequency of occurrence of the abnormal factor in the abnormal association rule or other quantitative indicators.

[0118] Call the preset machine learning model.

[0119] In this step, the above machine learning model can specifically adopt models such as random forest and gradient boosting tree, which provide built-in feature importance evaluation functions.

[0120] The first feature vector is processed based on the machine learning model to obtain a feature importance score corresponding to the first feature vector.

[0121] In this step, the first feature vectors are input into the machine learning model, and the feature importance score of each first feature vector is extracted by the machine learning model. This is usually a list of values, indicating the contribution of each first feature vector to the model prediction.

[0122] The feature importance score is calculated based on a preset correlation coefficient calculation algorithm to obtain a correlation coefficient value corresponding to the abnormal association rule.

[0123] In this step, the correlation coefficient calculation algorithm may specifically adopt the Pearson correlation coefficient and the Spearman rank correlation coefficient statistical algorithm. The feature importance score is calculated and processed by using the correlation coefficient calculation algorithm to quantify the linear or monotonic relationship between the abnormal factor and the abnormal event, and obtain the corresponding correlation coefficient value, which is used to determine the strength and direction of the association between the abnormal factor and the abnormal event.

[0124] The correlation coefficient value is used as the factor association coefficient corresponding to the abnormal factor.

[0125] In this embodiment, the abnormal association rule is converted into a corresponding first feature vector; then a preset machine learning model is called; the first feature vector is processed based on the machine learning model to obtain a feature importance score corresponding to the first feature vector; the feature importance score is subsequently calculated and processed based on a preset correlation coefficient calculation algorithm to obtain a correlation coefficient value corresponding to the abnormal association rule; finally, the correlation coefficient value is used as the factor correlation coefficient corresponding to the abnormal factor. The present application converts the abnormal association rule into a corresponding first feature vector, and then processes the first feature vector based on the use of a machine learning model and a correlation coefficient calculation algorithm, so as to achieve rapid and accurate generation of a factor correlation coefficient corresponding to the abnormal factor, thereby improving the intelligence of generating the factor correlation coefficient and ensuring the accuracy of the generated factor correlation coefficient.

[0126] Optionally, the processing of the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor includes:

[0127] The abnormal association rule is converted into a corresponding second feature vector, wherein each second feature vector corresponds to an abnormal factor.

[0128] In this step, the abnormal association rules are converted into a data format suitable for model processing, that is, the abnormal association rules are converted into feature vectors to obtain corresponding second feature vectors, which can be referred to as features. Each feature corresponds to an abnormal factor, and the value of the feature can be the frequency of occurrence of the abnormal factor in the abnormal association rule or other quantitative indicators.

[0129] Perform feature engineering processing on the second feature vector to obtain a corresponding target feature vector.

[0130] In this step, the feature engineering processing refers to performing necessary processing on the second feature vector, such as standardization and normalization, to ensure that features of different dimensions can participate in model processing fairly.

[0131] Call the preset weight determination model.

[0132] In this step, the weight determination model may specifically adopt a logistic regression model.

[0133] The target feature vector is input into the weight determination model, and the target feature vector is processed by the weight determination model to obtain a weight corresponding to the target feature vector.

[0134] In this step, the input target feature vector is processed by using a weight determination model, and the weight of each corresponding abnormal factor is determined. The weight of the abnormal factor reflects the importance of the abnormal factor in predicting dynamic abnormal events.

[0135] The weight is used as the abnormal factor weight corresponding to the abnormal factor.

[0136] In this embodiment, the abnormal association rule is converted into a corresponding second feature vector; then the second feature vector is subjected to feature engineering processing to obtain a corresponding target feature vector; then a preset weight determination model is called; subsequently, the target feature vector is input into the weight determination model, and the target feature vector is processed by the weight determination model to obtain a weight corresponding to the target feature vector; finally, the weight is used as the abnormal factor weight corresponding to the abnormal factor. The present application converts the abnormal association rule into a corresponding second feature vector and performs feature engineering processing to obtain a corresponding target feature vector, and then processes the target feature vector based on the use of the weight determination model to achieve rapid and accurate generation of abnormal factor weights corresponding to the abnormal factor, thereby improving the intelligence of generating abnormal factor weights and ensuring the accuracy of generated abnormal factor weights.

[0137] Optionally, generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight includes:

[0138] Obtain an abnormal factor value of the abnormal factor.

[0139] In this step, the above abnormal factor values ​​are directly derived from the data. The abnormal factor values ​​reflect the current status of each abnormal factor in the abnormal event.

[0140] Call the preset anomaly coefficient calculation formula.

[0141] In this step, the above abnormal coefficient calculation formula specifically includes: Among them, S is the dynamic anomaly coefficient, n is the total number of anomaly factors, F i is the abnormal factor value of the ith abnormal factor, p i is the factor correlation coefficient of the ith abnormal factor, w i is the abnormal factor weight of the ith abnormal factor. The abnormal coefficient calculation formula combines the contribution of different abnormal factors by weighted summation to quantitatively represent the dynamic abnormal degree of the abnormal event.

[0142] The abnormal factor value, the factor correlation coefficient and the abnormal factor weight are calculated based on the abnormal coefficient calculation formula to obtain a corresponding calculation result.

[0143] In this step, the abnormal factor value, the factor correlation coefficient and the abnormal factor weight are substituted into the corresponding positions of the abnormal coefficient calculation formula to perform calculation processing, thereby obtaining the corresponding calculation result.

[0144] The calculation result is used as the dynamic abnormality coefficient of the target abnormal event.

[0145] In this embodiment, by obtaining the abnormal factor value of the abnormal factor; then calling the preset abnormal coefficient calculation formula; then calculating and processing the abnormal factor value, the factor correlation coefficient and the abnormal factor weight based on the abnormal coefficient calculation formula to obtain the corresponding calculation result; and subsequently using the calculation result as the dynamic abnormal coefficient of the target abnormal event. The present application obtains the abnormal factor value of the abnormal factor, and by using the abnormal coefficient calculation formula to calculate and process the abnormal factor value, the factor correlation coefficient and the abnormal factor weight, it can quickly and accurately calculate the dynamic abnormal coefficient of the target abnormal event, thereby improving the calculation efficiency of the dynamic abnormal coefficient of the target abnormal event. And when calculating the dynamic abnormal coefficient of the target abnormal event, the weight of the abnormal factor is taken into account, which means that the influence of each abnormal factor on the abnormal degree of the target abnormal event will be accurately reflected. Compared with the method of ignoring the weight of the abnormal factor in the prior art, this calculation method can better reflect the abnormal nature of the dynamic target abnormal event, improve the accuracy of abnormal identification, and thus ensure the data accuracy of the dynamic abnormal coefficient of the target abnormal event.

[0146] Optionally, after generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight, the method further includes:

[0147] Anomaly explanation information corresponding to the dynamic anomaly coefficient is generated.

[0148] In this step, the above-mentioned abnormality explanation information refers to the information that explains the calculated dynamic abnormality coefficient and explains the abnormality degree of the current target abnormal event reflected by the abnormality explanation information.

[0149] Call the preset monitoring log.

[0150] In this step, the monitoring log specifically refers to a pre-built log for storing information on abnormal events related to the mining lamp.

[0151] The dynamic anomaly coefficient and the anomaly explanation information are recorded in the monitoring log.

[0152] In this step, the dynamic anomaly coefficient and the anomaly explanation information are recorded in the monitoring log for subsequent analysis and audit.

[0153] In this embodiment, by generating abnormal explanation information corresponding to the dynamic abnormal coefficient; then calling the preset monitoring log; and subsequently recording the dynamic abnormal coefficient and the abnormal explanation information in the monitoring log. The present application generates the dynamic abnormal coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight, and also intelligently generates abnormal explanation information corresponding to the dynamic abnormal coefficient, and then records the dynamic abnormal coefficient and the abnormal explanation information in the preset monitoring log, which can ensure the data security of the generated dynamic abnormal coefficient and the abnormal explanation information record, and is conducive to subsequent analysis and auditing, and improves the intelligence of data storage.

[0154] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of an abnormal event monitoring device 300 based on a mining lamp. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0155] An embodiment of the present invention provides an abnormal event monitoring device 300 based on a mining lamp. The abnormal event monitoring device 300 based on a mining lamp includes:

[0156] The acquisition module 310 is used to collect environmental parameter data and behavior data in the use environment of the mining lamp based on the target sensor;

[0157] The identification module 320 is used to perform abnormal identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple;

[0158] A mining module 330 is used to perform association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors;

[0159] A first generating module 340, configured to generate a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule;

[0160] A processing module 350 is used to process the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor;

[0161] A second generating module 360, configured to generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight;

[0162] The judgment module 370 is used to display the dynamic abnormality coefficient in a preset mining lamp monitoring page, and judge in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold;

[0163] The sending module 380 is used to generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

[0164] Optionally, the identification module 320 includes:

[0165] A preprocessing submodule, used to preprocess the environmental parameter data and the behavior data respectively to obtain corresponding target environmental parameter data and target behavior data;

[0166] A first identification submodule is used to identify abnormalities of the target environmental parameter data based on a preset statistical analysis method to obtain corresponding abnormal data;

[0167] A first processing submodule, configured to perform image processing on the target behavior data based on a preset image processing algorithm to obtain corresponding image feature data;

[0168] A second identification submodule is used to perform abnormality identification on the image feature data based on a preset behavior processing algorithm to obtain corresponding abnormal behavior;

[0169] A generating submodule is used to generate an abnormal factor of the target abnormal event based on the abnormal data and the abnormal behavior.

[0170] Optionally, the mining module 330 includes:

[0171] The first acquisition submodule is used to acquire a plurality of preset association rule mining algorithms;

[0172] A first determination submodule is used to determine a target association rule mining algorithm from all the association rule mining algorithms;

[0173] The mining submodule is used to perform association rule mining on the abnormal factors based on the target association rule mining algorithm to obtain abnormal association rules corresponding to the abnormal factors.

[0174] Optionally, the first generating module 340 includes:

[0175] A first conversion submodule, used to convert the abnormal association rule into a corresponding first feature vector; each first feature vector corresponds to an abnormal factor;

[0176] The first calling submodule is used to call a preset machine learning model;

[0177] a second processing submodule, configured to process the first feature vector based on the machine learning model to obtain a feature importance score corresponding to the first feature vector;

[0178] A first calculation submodule, configured to calculate the feature importance score based on a preset correlation coefficient calculation algorithm to obtain a correlation coefficient value corresponding to the abnormal association rule;

[0179] The second determining submodule is used to use the correlation coefficient value as a factor association coefficient corresponding to the abnormal factor.

[0180] Optionally, the processing module 350 includes:

[0181] A second conversion submodule, configured to convert the abnormal association rule into a corresponding second feature vector; wherein each second feature vector corresponds to an abnormal factor;

[0182] A third processing submodule is used to perform feature engineering processing on the second feature vector to obtain a corresponding target feature vector;

[0183] The second calling submodule is used to call a preset weight determination model;

[0184] a fourth processing submodule, configured to input the target feature vector into the weight determination model, process the target feature vector through the weight determination model, and obtain a weight corresponding to the target feature vector;

[0185] The third determining submodule is configured to use the weight as an abnormal factor weight corresponding to the abnormal factor.

[0186] Optionally, the second generating module 360 ​​includes:

[0187] A second acquisition submodule is used to obtain an abnormal factor value of the abnormal factor;

[0188] The third calling submodule is used to call a preset abnormal coefficient calculation formula;

[0189] A second calculation submodule is used to calculate the abnormal factor value, the factor correlation coefficient and the abnormal factor weight based on the abnormal coefficient calculation formula to obtain a corresponding calculation result;

[0190] The fourth determination submodule is used to use the calculation result as the dynamic abnormality coefficient of the target abnormal event.

[0191] Optionally, the abnormal event monitoring device 300 based on a mining lamp further includes:

[0192] A third generating module is used to generate abnormality explanation information corresponding to the dynamic abnormality coefficient;

[0193] Calling module, used to call the preset monitoring log;

[0194] A recording module is used to record the dynamic abnormality coefficient and the abnormality explanation information in the monitoring log.

[0195] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0196] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0197] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0198] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the abnormal event monitoring method based on the mining lamp. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0199] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the abnormal event monitoring method based on the mining lamp.

[0200] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0201] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the application crash processing program, and the application crash processing program can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned mining lamp-based abnormal event monitoring method.

[0202] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0203] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0204] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for monitoring abnormal events based on a mining lamp, characterized in that: include: Collect environmental parameter data and behavior data in the environment where the mining lamp is used based on target sensors; Performing abnormality identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple; Performing association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors; generating a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule; Processing the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor; Generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight; The dynamic abnormality coefficient is displayed in a preset mining lamp monitoring page, and it is determined in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold; If so, generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

2. The method according to claim 1, characterized in that The performing abnormality identification processing on the environmental parameter data and the behavior data to obtain the abnormal factor of the target abnormal event includes: Preprocessing the environmental parameter data and the behavior data respectively to obtain corresponding target environmental parameter data and target behavior data; Based on a preset statistical analysis method, anomaly identification is performed on the target environmental parameter data to obtain corresponding abnormal data; Performing image processing on the target behavior data based on a preset image processing algorithm to obtain corresponding image feature data; Based on a preset behavior processing algorithm, the image feature data is subjected to abnormality recognition to obtain corresponding abnormal behavior; An abnormal factor of the target abnormal event is generated based on the abnormal data and the abnormal behavior.

3. The method according to claim 1, characterized in that The performing association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors includes: Get multiple preset association rule mining algorithms; Determine a target association rule mining algorithm from all the association rule mining algorithms; Based on the target association rule mining algorithm, association rule mining is performed on the abnormal factors to obtain abnormal association rules corresponding to the abnormal factors.

4. The method according to claim 1, characterized in that: The generating a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule includes: Converting the abnormal association rules into corresponding first feature vectors; each first feature vector corresponds to an abnormal factor; Call the preset machine learning model; Processing the first feature vector based on the machine learning model to obtain a feature importance score corresponding to the first feature vector; The feature importance score is calculated based on a preset correlation coefficient calculation algorithm to obtain a correlation coefficient value corresponding to the abnormal association rule; The correlation coefficient value is used as the factor association coefficient corresponding to the abnormal factor.

5. The method according to claim 1, characterized in that The method of processing the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor includes: Converting the abnormal association rule into a corresponding second feature vector; wherein each second feature vector corresponds to an abnormal factor; Performing feature engineering processing on the second feature vector to obtain a corresponding target feature vector; Call the preset weight determination model; Inputting the target feature vector into the weight determination model, processing the target feature vector through the weight determination model, and obtaining a weight corresponding to the target feature vector; The weight is used as the abnormal factor weight corresponding to the abnormal factor.

6. The method according to claim 1, characterized in that The step of generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight includes: Obtaining an abnormal factor value of the abnormal factor; Call the preset abnormal coefficient calculation formula; Based on the abnormal coefficient calculation formula, the abnormal factor value, the factor correlation coefficient and the abnormal factor weight are calculated to obtain a corresponding calculation result; The calculation result is used as the dynamic abnormality coefficient of the target abnormal event.

7. The method according to claim 1, characterized in that After generating the dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight, the method further includes: generating abnormality explanation information corresponding to the dynamic abnormality coefficient; Call the preset monitoring log; The dynamic anomaly coefficient and the anomaly explanation information are recorded in the monitoring log.

8. An abnormal event monitoring device based on a mining lamp, characterized in that: include: A collection module, used to collect environmental parameter data and behavior data in the use environment of the mining lamp based on the target sensor; an identification module, used to perform abnormal identification processing on the environmental parameter data and the behavior data to obtain abnormal factors of the target abnormal event; wherein the number of the abnormal factors includes multiple; A mining module, used to perform association rule mining on the abnormal factors based on a preset data mining algorithm to obtain abnormal association rules corresponding to the abnormal factors; A first generating module, configured to generate a factor association coefficient corresponding to the abnormal factor based on the abnormal association rule; A processing module, used to process the abnormal association rule set based on a preset weight determination model to obtain an abnormal factor weight corresponding to the abnormal factor; A second generating module, configured to generate a dynamic abnormality coefficient of the target abnormal event based on the abnormal factor, the factor correlation coefficient and the abnormal factor weight; A judgment module, used to display the dynamic abnormality coefficient in a preset mining lamp monitoring page, and to judge in real time whether the dynamic abnormality coefficient is greater than a preset warning threshold; The sending module is used to generate warning information corresponding to the target abnormal event and send the warning information to relevant users.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the abnormal event monitoring method based on a mining lamp as described in any one of claims 1 to 7 are implemented.

10. 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 steps of the abnormal event monitoring method based on a mining lamp as described in any one of claims 1 to 7 are implemented.

Images