Production abnormal event monitoring method and system and readable storage medium

Abstract

The invention discloses a production abnormal event monitoring method and system and a readable storage medium, and the method is characterized in that the method comprises the steps: extracting event features corresponding to monitoring tasks according to the event level of each monitoring task in a monitoring queue; under the condition that an operation of a user for a target monitoring service is received, a target monitoring task is added into the monitoring queue, and the event level of the target monitoring task is controlled to be higher than at least one event level in the monitoring queue; when the event feature extraction of the target monitoring task is completed, calculating the event risk degree of the target monitoring service, and generating a risk characterization result; and displaying a risk monitoring page of the target monitoring service based on the risk representation result. According to the invention, by adding control means for the monitoring queue, the response degree of the monitoring event is improved, and meanwhile, the accuracy of the monitoring task is improved by utilizing the multi-dimensional event characteristics.

Description

Technical Field

[0001] The present invention relates to the field of data analysis and monitoring systems, and in particular to a production abnormality event monitoring method, system and readable storage medium. Background Art

[0002] With the popularization of Internet of Things (IoT) technology, modern monitoring systems have been widely used in industrial automation, urban intelligent management, traffic control, environmental monitoring and other fields. These systems usually collect and transmit a large amount of data in real time through various sensors and cameras. These data include temperature, pressure, video stream, gas concentration and other information. Effectively analyzing and processing these data is crucial to realize the intelligence and automation of the system.

[0003] Modern monitoring systems generate a huge amount of data, which is diverse and complex. It is a challenge to extract useful information and respond in a timely manner. Traditional data processing methods often seem to be unable to cope with massive amounts of data.

[0004] Dynamic events (such as equipment failure, environmental pollution, traffic accidents, etc.) often need to be identified and processed in a very short time, otherwise they may cause system failure or safety issues. Existing technologies are insufficient in real-time response and cannot meet the requirements of rapid detection of dynamic events and accurate processing according to severity levels. Summary of the invention

[0005] The present invention aims to solve the problems of poor real-time performance, low precision and weak adaptability in the prior art. In a first aspect, the present invention proposes a production abnormal event monitoring method, comprising the following steps:

[0006] According to the event level of each monitoring task in the monitoring queue, the event features corresponding to the monitoring task are extracted;

[0007] When receiving an operation of a user on a target monitoring service, adding a target monitoring task to the monitoring queue, and controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service;

[0008] When the target monitoring task completes the event feature extraction, the event risk level of the target monitoring business is calculated to generate a risk characterization result;

[0009] A risk monitoring page for the target monitored business is displayed based on the risk characterization result.

[0010] In one embodiment, adding the target monitoring task to the monitoring queue includes: adding the target monitoring task to the bit level with the highest event level in the monitoring queue.

[0011] In one embodiment, controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue includes: suspending the extraction of event features of all monitoring tasks in the monitoring queue whose event levels are before the target monitoring task.

[0012] In one embodiment, the method further includes: when the event feature extraction of the target monitoring task is completed, restarting the paused monitoring task.

[0013] In one of the embodiments, when the target monitoring task completes event feature extraction, the event risk level of the target monitoring business is calculated to generate a risk characterization result, specifically including: when the target monitoring task completes event feature extraction, event impact characteristics, spatiotemporal level characteristics and event duration characteristics are obtained; a preset event judgment model is used to calculate the event risk level of the event impact characteristics, the spatiotemporal level characteristics and the event duration characteristics to obtain an event abnormality; and a risk characterization result is generated based on the event abnormality.

[0014] In one embodiment, generating a risk characterization result based on the event abnormality specifically includes: when the event abnormality is within a preset abnormal threshold, determining that the risk characterization result is an abnormal result

[0015] The second aspect of the present invention provides a dynamic event processing device, comprising the following modules:

[0016] The extraction module is used to extract the event features corresponding to the monitoring tasks according to the event level of each monitoring task in the monitoring queue;

[0017] A control module, configured to, upon receiving an operation of a user on a target monitoring service, add a target monitoring task to the monitoring queue, and control the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service;

[0018] A calculation module, used to calculate the event risk level of the target monitoring business and generate a risk characterization result when the target monitoring task completes the event feature extraction;

[0019] A display module is used to display a risk monitoring page of the target monitoring business based on the risk characterization result.

[0020] In one embodiment, the control module further includes an adding submodule:

[0021] The adding submodule is used to add the target monitoring task to the level with the highest event level in the monitoring queue.

[0022] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned dynamic event processing method when executing the computer program.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the dynamic event processing method described above is implemented.

[0024] It has the following beneficial effects:

[0025] The present invention discloses a production abnormal event monitoring method, system and readable storage medium, characterized in that it includes: extracting event features corresponding to the monitoring task according to the event level of each monitoring task in the monitoring queue; in the case of receiving the user's operation on the target monitoring service, adding the target monitoring task to the monitoring queue, and controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of the event feature corresponding to the target monitoring service; when the target monitoring task completes the event feature extraction, calculating the event risk degree of the target monitoring service and generating a risk characterization result; based on the risk characterization result, displaying the risk monitoring page of the target monitoring service. The present invention improves the responsiveness of the monitoring event by increasing the control means for the monitoring queue, and at the same time improves the accuracy of the monitoring task by using multi-dimensional event features. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0027] Figure 2 It is a flow chart of a method for monitoring abnormal production events;

[0028] Figure 3 This is a schematic diagram of the relationship between event abnormality and event duration characteristics;

[0029] Figure 4 A block diagram of a production abnormality event monitoring device;

[0030] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0032] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0033] Figure 1 An exemplary system architecture 100 is shown to which the method for processing information or the apparatus for processing information according to the embodiments of the present application can be applied.

[0034] 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.

[0035] 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 platform software, etc.

[0036] The terminal devices 101 , 102 , and 103 may be various electronic devices with communication functions, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0037] The server 105 may be a server that provides various services, such as a background information processing server that processes the verification request information sent by the terminal devices 101, 102, and 103. The background information processing server may analyze the received verification request information and obtain a processing result (such as verification success information that indicates that the verification request is a legitimate request).

[0038] It should be noted that the method for processing information provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the device for processing information is generally set in the server 105. In addition, the dynamic event processing method provided in the embodiment of the present application is generally executed by the terminal devices 101, 102, and 103, and accordingly, the device for sending information is generally set in the terminal devices 101, 102, and 103.

[0039] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0040] 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.

[0041] refer to Figure 2 The present invention proposes a production abnormal event monitoring method, comprising the following steps:

[0042] S201: extracting event features corresponding to the monitoring tasks according to the event levels of the monitoring tasks in the monitoring queue;

[0043] Let’s take an industrial production monitoring device / system as an example. A variety of sensor devices are deployed to collect various data of the production line, including temperature, pressure, vibration, flow, machine status, etc. The data is stored in the form of data tuples, each of which contains information in multiple dimensions:

[0044] Timestamp: indicates the specific time when the data is collected.

[0045] Sensor ID: Identifies the sensor from which the data originated.

[0046] Sensor reading: The value measured by this sensor at a specific point in time.

[0047] Machine status: indicates the current operating status of the machine, such as running, shut down, maintenance, etc.

[0048] Event marker: used to identify whether the data tuple contains a known event (for training and evaluation).

[0049] During the start-up of the monitoring task, the event parameters of the monitoring events in the monitoring task are read in real time to monitor the production events.

[0050] S202: upon receiving an operation of a user for a target monitoring service, adding a target monitoring task to the monitoring queue, and controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service;

[0051] One possible situation is that the target monitoring task is added to the bit level with the highest event level in the monitoring queue.

[0052] One possible situation is: suspending the extraction of event features of all monitoring tasks in the monitoring queue whose event levels are before the target monitoring task.

[0053] One possible situation is: when the event feature extraction of the target monitoring task is completed, restart the suspended monitoring task

[0054] S203, when the target monitoring task completes the event feature extraction, calculating the event risk level of the target monitoring service and generating a risk characterization result;

[0055] One possible situation is that when the target monitoring task completes the event feature extraction, the event impact feature, the spatiotemporal level feature and the event duration feature are obtained; the event risk degree is calculated for the event impact feature, the spatiotemporal level feature and the event duration feature using a preset event judgment model to obtain the event abnormality; and the risk characterization result is generated based on the event abnormality.

[0056] In a specific embodiment, data feature extraction includes using a principal component analysis (PCA) algorithm and a linear discriminant analysis (LDA) algorithm.

[0057] In order to effectively analyze these data, we first use feature extraction algorithms to process the data tuples. In this embodiment, algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA) and time series analysis are used to extract meaningful features from massive data.

[0058] 1. Principal Component Analysis (PCA): PCA is a dimensionality reduction technique used to reduce the dimensions of data while retaining important information. Through PCA, we can identify the dominant features of the data, thereby reducing the computational complexity. In this embodiment, PCA is used to extract key features related to the occurrence of events, such as temperature change trends, pressure fluctuations, etc.

[0059] 2. Linear Discriminant Analysis (LDA): LDA is used to identify categorical features, helping us find the feature vectors that best characterize different event types in the data set. In this embodiment, LDA is used to distinguish the difference between normal and abnormal states, thereby helping to identify potential dynamic events.

[0060] 3. Time series analysis: Considering the time correlation of monitoring data, time series analysis methods (such as autoregressive integrated moving average model, ARIMA) are used to identify trends and cyclical changes in the data to detect abnormal fluctuations.

[0061] The extracted features may also include:

[0062] Event Type: Identify specific types of events based on sensor readings and historical data, such as overheating, overvoltage, abnormal vibration, etc.

[0063] Event status: Identifies the current status of the event, such as occurring, completed, likely to occur, etc.

[0064] Data Trending: Identify long-term trends and cyclical changes in data to predict potential events.

[0065] Specifically, calculate the abnormality of the event:

[0066]

[0067] Among them, y is the event abnormality, a is the event impact feature, b is the spatiotemporal level feature, and x is the event duration feature; the event abnormality Y is proportional to the event impact feature a and the spatiotemporal level feature b, as well as the event duration. The event impact feature may include but is not limited to temperature value, pressure value, flow value and vibration value. Taking the equipment temperature value as an example, the severity of different equipment temperature values ​​in different time periods and durations is different, and different response measures should be corresponding. For example, the temperature value of a section of data is intercepted, and the same temperature is monitored. It is used for high-speed production in the morning and continuously used for 4 hours, and the severity is different from that set to low-speed production in the afternoon and continuously used for 2 hours.

[0068] In a specific embodiment, the spatiotemporal level characteristics are divided according to the degree of impact caused by different events occurring in different time periods. The spatiotemporal level characteristics in the morning are lower, and the spatiotemporal level characteristics in the afternoon are higher. The temperature threshold set in the morning and the temperature threshold set in the afternoon are also different. Through continued learning of the event judgment model, the set extreme value threshold or the set average threshold can be changed, or different response measures corresponding to different severities can be adjusted through continued learning of the event judgment model.

[0069] In a specific embodiment, the event impact feature a is specifically:

[0070]

[0071] Among them, T w To influence the parameter range, T n To set the extreme value threshold, is the average value of the influencing parameter, To set the average threshold, the influencing parameter is at least one of the temperature value, pressure value, flow value and vibration value. Taking the temperature value as an example, the influencing factor is that the range value indicates that the temperature change should be maintained within a certain fluctuation range. If the change is too large, it means that the temperature is abnormal. At the same time, the average temperature value cannot be higher than the normal level, otherwise it also means that the temperature is abnormal. Therefore, the range value and the average value are positively correlated with the abnormality of the event. Through the continued learning of the event judgment model, the setting of the range threshold or the setting of the average threshold can be changed, or different response measures corresponding to different severities can be adjusted through the continued learning of the event judgment model.

[0072] In a specific embodiment, when there are multiple influencing parameters, the influencing factors are a1, a2, ...an, the event impacts are y1, y2, ...yn, and the total event impact y = (y1+y2+...yn) / n.

[0073] If the impact factor of an event is large, the impact degree corresponding to each impact factor can be calculated separately, and the total impact degree of the event can be calculated, and then the average value can be calculated.

[0074] One possible situation is that when the abnormality of the event is within a preset abnormal threshold, the risk characterization result is determined to be an abnormal result.

[0075] refer to Figure 3 , Figure 3 It describes the relationship between the severity of the event y and the duration of the event x. When the sum of the event impact feature a and the spatiotemporal level feature b is 0.5, 5, 10 and 20 respectively, firstly, a and b are both greater than 0, so a and b are respectively proportional to the abnormality of the event y. It can be seen from the figure that the larger the sum of a and b, the greater the severity y in the same duration.

[0076] S204: Display a risk monitoring page for the target monitored business based on the risk characterization result.

[0077] Another optional implementation is to input the data features and event abnormality of each set of event data into an event judgment model to obtain event response measures recommended by the event judgment model.

[0078] The event judgment model of the present invention learns event response measures for different event abnormalities, which can avoid misjudgment and misoperation to a greater extent, can monitor different devices at the same time, and make more accurate response measures according to different data characteristics and different severities.

[0079] After extracting the data features, we establish an event judgment model to identify dynamic events in the monitoring system. The establishment of the event judgment model includes the following steps: 1) Model selection: In this embodiment, we use a classification model based on support vector machine (SVM). SVM can effectively process high-dimensional data and has strong generalization ability. In addition, considering the diversity and complexity of the data, deep learning models (such as convolutional neural network CNN, recurrent neural network RNN) can also be used for modeling to improve recognition accuracy. 2) Model training: Use the labeled data set to train the selected model. The training data includes known event types and states. Through training, we get a model that can distinguish different events. 3) Model validation: Through cross-validation technology, evaluate the accuracy and stability of the model to ensure its performance on unlabeled data. Cross-validation methods include K-fold cross-validation and leave-one-out validation. 4) Feature importance analysis: Through feature importance analysis, identify the features that have the greatest impact on event recognition, optimize the model structure, and improve the interpretability of the model.

[0080] In a specific embodiment, the optimization step specifically includes:

[0081] Collecting feedback data, wherein the feedback data includes at least one of delayed response, false positive information, and missed negative information;

[0082] Adjust the parameters and structure of the event judgment model based on feedback data;

[0083] Regularly retrain and update the event judgment model.

[0084] The present invention discloses a production abnormal event monitoring method, system and readable storage medium, which are characterized by comprising: extracting event features corresponding to the monitoring task according to the event level of each monitoring task in the monitoring queue; when receiving the user's operation on the target monitoring service, adding the target monitoring task to the monitoring queue, and controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of the event feature corresponding to the target monitoring service; when the target monitoring task completes the event feature extraction, calculating the event risk level of the target monitoring service and generating a risk characterization result; based on the risk characterization result, displaying the risk monitoring page of the target monitoring service. The present invention improves the responsiveness of monitoring events by adding control means for the monitoring queue, and at the same time improves the accuracy of monitoring tasks by using multi-dimensional event features.

[0085] like Figure 4 As shown, a dynamic event processing device includes the following modules:

[0086] Extraction module 401, used for extracting event features corresponding to monitoring tasks according to the event level of each monitoring task in the monitoring queue;

[0087] A control module 402 is used to add a target monitoring task to the monitoring queue when receiving an operation of a user on a target monitoring service, and control the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service;

[0088] A calculation module 403 is used to calculate the event risk level of the target monitoring business and generate a risk characterization result when the target monitoring task completes the event feature extraction;

[0089] The display module 404 is configured to display a risk monitoring page of the target monitoring business based on the risk characterization result.

[0090] In another embodiment, the control module 402 further includes an adding submodule:

[0091] The adding submodule is used to add the target monitoring task to the highest event level in the monitoring queue.

[0092] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for monitoring production abnormal events is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0093] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0095] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented:

[0096] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above method embodiments:

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring abnormal production events, characterized in that: The method comprises: According to the event level of each monitoring task in the monitoring queue, the event features corresponding to the monitoring task are extracted; When receiving an operation of a user on a target monitoring service, adding a target monitoring task to the monitoring queue, and controlling the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service; When the target monitoring task completes the event feature extraction, the event risk level of the target monitoring business is calculated to generate a risk characterization result; A risk monitoring page for the target monitored business is displayed based on the risk characterization result.

2. The method for monitoring abnormal production events according to claim 1, characterized in that: The target monitoring task is added to the monitoring queue including: The target monitoring task is added to the bit level with the highest event level in the monitoring queue.

3. The method for monitoring abnormal production events according to claim 1, characterized in that: The event level of controlling the target monitoring task is higher than at least one event level in the monitoring queue, including: The extraction of event features of all monitoring tasks in the monitoring queue whose event levels are before the target monitoring task is suspended.

4. The method for monitoring abnormal production events according to claim 3, characterized in that: The method further comprises: When the event feature extraction of the target monitoring task is completed, the suspended monitoring task is restarted.

5. The method for monitoring abnormal production events according to claim 1, characterized in that: When the target monitoring task completes the event feature extraction, the event risk level of the target monitoring service is calculated to generate a risk characterization result, which specifically includes: When the target monitoring task completes the event feature extraction, event impact features, spatiotemporal level features, and event duration features are obtained; Calculate the event risk level of the event impact feature, the spatiotemporal level feature, and the event duration feature using a preset event judgment model to obtain the event abnormality; A risk characterization result is generated based on the abnormality of the event.

6. The method for monitoring abnormal production events according to claim 4, characterized in that: The generating of the risk characterization result based on the abnormality of the event specifically includes: When the abnormality of the event is within a preset abnormal threshold, the risk characterization result is determined to be an abnormal result.

7. A production abnormality event monitoring device, characterized in that: The device comprises: The extraction module is used to extract the event features corresponding to the monitoring tasks according to the event level of each monitoring task in the monitoring queue; A control module, configured to, upon receiving an operation of a user on a target monitoring service, add a target monitoring task to the monitoring queue, and control the event level of the target monitoring task to be higher than at least one event level in the monitoring queue, wherein the target monitoring task is a monitoring task of an event feature corresponding to the target monitoring service; A calculation module, used to calculate the event risk level of the target monitoring business and generate a risk characterization result when the target monitoring task completes the event feature extraction; A display module is used to display a risk monitoring page of the target monitoring business based on the risk characterization result.

8. The production abnormality event monitoring device according to claim 7, characterized in that: The control module also includes an adding submodule: The adding submodule is used to add the target monitoring task to the level with the highest event level in the monitoring queue.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images