Method, device, equipment and storage medium for generating hidden danger remediation work orders

Abstract

The present invention discloses a method, apparatus, device, and storage medium for generating a hidden danger remediation work order. The method comprises the following steps: determining the alarm type and hidden danger level assessment index corresponding to the hidden danger equipment based on the hidden danger equipment work order; invoking a pre-built hidden danger remediation measure knowledge base and querying the hidden danger remediation recommendation corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation based on the hidden danger remediation measure knowledge base; determining the hidden danger level of the hidden danger equipment based on the alarm type and the hidden danger level assessment index; determining a first priority corresponding to the hidden danger remediation recommendation based on the confidence level, and determining a second priority corresponding to the hidden danger equipment based on the hidden danger level; and generating a hidden danger remediation work order based on the first and second priorities. This improves the timeliness of hidden danger detection.

Description

Technical Field

[0001] The present invention relates to the technical field of hidden danger equipment remediation, and in particular to a method, device, equipment and storage medium for generating a hidden danger remediation work order. Background Art

[0002] There may be various hidden dangers during the operation of the equipment. If they are not discovered and handled in time, the equipment will not be able to operate normally.

[0003] Currently, the main method for troubleshooting and remediating equipment hazards is manual analysis to identify potential hazards and develop corresponding remediation plans. This process requires repeated verification with equipment manufacturers to confirm the feasibility of the remediation plans. This is time-consuming and labor-intensive, and is easily influenced by subjective factors, resulting in delayed hazard detection. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and computer-readable storage medium for generating a hidden danger remediation work order, aiming to improve the timeliness of hidden danger detection.

[0005] To achieve the above object, the present invention provides a method for generating a hidden danger remediation work order, the method comprising the following steps:

[0006] Determine the alarm type and hazard level assessment indicators corresponding to the hazardous equipment based on the hazardous equipment work order;

[0007] Invoking a pre-built hidden danger remediation measures knowledge base, and querying the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base;

[0008] Determine the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index;

[0009] Determining a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and determining a second priority corresponding to the hidden danger equipment according to the hidden danger level;

[0010] A hidden danger remediation work order is generated according to the first priority and the second priority.

[0011] Optionally, the step of determining the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index includes:

[0012] The alarm type and the hidden danger level assessment index are input into a pre-trained cluster analysis model to obtain the hidden danger level of the hidden danger equipment. The cluster analysis model is trained based on historical work order data pre-labeled with the hidden danger levels of different hidden danger equipment.

[0013] Optionally, before the step of calling a pre-built hidden danger remediation measures knowledge base and querying the hidden danger remediation recommendation item corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation item based on the hidden danger remediation measures knowledge base, the step further includes:

[0014] Determine the alarm type of the hidden danger equipment and the hidden danger remediation measures corresponding to the alarm type according to the historical work order data of the hidden danger equipment;

[0015] Obtain a set of hidden danger remediation measures corresponding to the alarm type;

[0016] Determining the similarity between each two hidden danger remediation measures in the set of hidden danger remediation measures;

[0017] Merging the hidden danger remediation measures in the hidden danger remediation measure set according to the similarity;

[0018] A hidden danger remediation measures knowledge base is constructed based on the merged hidden danger remediation measures set.

[0019] Optionally, after the step of constructing a hidden danger remediation measures knowledge base based on the merged hidden danger remediation measures set, the following steps are included:

[0020] Receive the marking operation of hidden danger remediation measures;

[0021] Performing information labeling on the hidden danger remediation measures in the merged hidden danger remediation measures set according to the labeling operation;

[0022] The hidden danger remediation measures knowledge base is updated according to the labeling results of the information labeling.

[0023] Optionally, after the step of generating a hidden danger remediation work order according to the first priority and the second priority, the method further includes:

[0024] Determining the accuracy of the remediation measure recommendation corresponding to the recommended remediation measure item in the hidden danger remediation work order;

[0025] The hidden danger remediation measure knowledge base and / or the hidden danger remediation work order are modified according to the accuracy of the remediation measure recommendation.

[0026] Optionally, the step of determining the accuracy of the remediation measure recommendation corresponding to the recommended remediation measure item in the hidden danger remediation work order includes:

[0027] Obtaining a first feature vector of a recommended remediation measure item for the alarm type and a second feature vector of an actual remediation measure item for the alarm type;

[0028] Performing cosine similarity calculation on the first eigenvector and the second eigenvector to obtain similarity between the recommended remediation measure item and the actual remediation measure item;

[0029] The accuracy of the remediation measure recommendation is determined according to the similarity; wherein, the higher the similarity, the higher the accuracy of the remediation measure recommendation.

[0030] Optionally, the step of revising the hidden danger remediation measure knowledge base and / or the hidden danger remediation work order according to the remediation measure recommendation accuracy includes:

[0031] When the accuracy of the remediation measure recommendation is lower than a preset accuracy, merging the annotation information of the recommended remediation measure item with the annotation information of the actual remediation measure item, and updating the annotation information of the recommended remediation measure item in the hidden danger remediation measure knowledge base with the merged annotation information;

[0032] and / or, obtaining a frequency of occurrence of a hidden danger of the hidden danger equipment, and updating a hidden danger level of the hidden danger equipment in the hidden danger remediation work order according to the frequency of occurrence of the hidden danger;

[0033] And / or, a preset probability model is used to calculate the occurrence probability of the hidden danger remediation measures corresponding to the alarm type, and the query order when calling the hidden danger remediation measures knowledge base for data query is modified according to the occurrence probability.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a device for generating a hidden danger remediation work order, which includes a memory, a processor, and a hidden danger remediation work order generation program stored on the processor and runnable on the processor. When the processor executes the hidden danger remediation work order generation program, it implements the steps of the hidden danger remediation work order generation method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a device for generating a hidden danger remediation work order, the device for generating a hidden danger remediation work order comprises: a first determination module, a query module, a second determination module, a third determination module and a generation module, wherein:

[0036] The first determination module is used to determine the alarm type and hidden danger level assessment index corresponding to the hidden danger equipment according to the hidden danger equipment work order;

[0037] Query module: used to call a pre-built hidden danger remediation measures knowledge base, and query the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base;

[0038] A second determining module is used to determine the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index;

[0039] a third determining module, configured to determine a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and to determine a second priority corresponding to the hidden danger equipment according to the hidden danger level;

[0040] Generation module: used to generate a hidden danger remediation work order based on the first priority and the second priority.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a program for generating a hidden danger remediation work order is stored. When the program for generating a hidden danger remediation work order is executed by a processor, the steps of the method for generating a hidden danger remediation work order as described above are implemented.

[0042] In an embodiment of the present invention, the alarm type and the hidden danger level assessment index corresponding to the hidden danger equipment are determined according to the hidden danger equipment work order, and then a pre-constructed hidden danger remediation measures knowledge base is called, and the hidden danger remediation recommendation items corresponding to the alarm type and the confidence of the hidden danger remediation recommendation items are queried based on the hidden danger remediation measures knowledge base, and the hidden danger level of the hidden danger equipment is determined according to the alarm type and the hidden danger level assessment index, and then the first priority corresponding to the hidden danger remediation recommendation item is determined according to the confidence of the hidden danger remediation recommendation item, and the second priority corresponding to the hidden danger equipment is determined according to the hidden danger level of the hidden danger equipment, so that the hidden danger remediation work order can be automatically generated according to the first priority and the second priority, without the need for manual investigation, and then there is no need for repeated verification with the equipment manufacturer, which can save processes and reduce human participation, and thus can improve the timeliness of hidden danger investigation, so as to improve the timeliness of hidden danger remediation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic structural diagram of a device for generating a hidden danger remediation work order according to an embodiment of the present invention;

[0044] Figure 2 This is a flow chart of a first embodiment of a method for generating a hidden danger remediation work order according to the present invention;

[0045] Figure 3 This is a flow chart of a second embodiment of a method for generating a hidden danger remediation work order according to the present invention;

[0046] Figure 4 This is a flow chart of the third embodiment of the method for generating a hidden danger remediation work order of the present invention.

[0047] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] The main solution of the present invention is: determining the alarm type and hidden danger level assessment index corresponding to the hidden danger equipment according to the hidden danger equipment work order; calling a pre-built hidden danger remediation measures knowledge base, and querying the hidden danger remediation recommendation items corresponding to the alarm type and the confidence of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base; determining the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index; determining the first priority corresponding to the hidden danger remediation recommendation item according to the confidence, and determining the second priority corresponding to the hidden danger equipment according to the hidden danger level; generating a hidden danger remediation work order according to the first priority and the second priority.

[0050] Currently, equipment hazard detection is typically performed manually, which is not only subject to subjective factors that lead to delayed detection, but also requires repeated verification with the equipment manufacturer, which increases the time consumption of the hazard detection process. Therefore, the above-mentioned solution provided by the present invention aims to improve the timeliness of hazard detection.

[0051] Reference Figure 1 , Figure 1 This is a structural diagram of a device for generating a hidden danger remediation work order for a hardware operating environment according to an embodiment of the present invention.

[0052] like Figure 1 As shown, the device for generating the hidden danger remediation work order may include: a communication bus 1002, a processor 1001, such as a CPU, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art will understand that Figure 1 The structure of the device for generating a hidden danger remediation work order shown in the figure does not constitute a limitation on the device for generating a hidden danger remediation work order, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0054] exist Figure 1 In the hidden danger remediation work order generation device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the hidden danger remediation work order generation device program stored in the memory 1005, and execute the relevant steps of each embodiment of the following hidden danger remediation work order generation device method.

[0055] It should be noted that the execution subject of the method for generating a hidden danger remediation work order proposed in each of the following embodiments can be a device for generating a hidden danger remediation work order, or it can be a device for generating a hidden danger remediation work order. Optionally, the device for generating a hidden danger remediation work order can be set in the device for generating a hidden danger remediation work order, or it can be set independently of the device for generating a hidden danger remediation work order. Among them, when the device for generating a hidden danger remediation work order and the device for generating a hidden danger remediation work order are set independently, the device for generating a hidden danger remediation work order and the device for generating a hidden danger remediation work order can be communicatively connected. The following will be explained by taking the application of the method for generating a hidden danger remediation work order to the device for generating a hidden danger remediation work order as an example.

[0056] Reference Figure 2 , Figure 2 This is a flow chart of a first embodiment of a method for generating a hidden danger remediation work order according to the present invention. In this embodiment, the method for generating a hidden danger remediation work order includes the following steps:

[0057] Step S10: Determine the alarm type and hazard level assessment index corresponding to the hazardous equipment according to the hazardous equipment work order;

[0058] It should be noted that a work order for a device with a potential danger is the work order data corresponding to a device with a potential danger, or a device with a potential danger that currently requires potential danger detection. Optionally, the content of the work order for a device with a potential danger may include: the work order data for the device with a potential danger (such as the work order serial number, work order name, work order subject, work order creator, work order creator's contact information, work order timeout status, dispatch instructions, etc.), the device data for the device with a potential danger (such as the faulty device model, faulty device manufacturer, etc.), and the potential danger data for the device with a potential danger (such as the network element type, alarm name, alarm type, alarm location, fault occurrence time, fault cause classification, fault response level, etc.). Of course, the work order for a device with a potential danger may also record more content information, such as the business type, customer service level, business assurance level, etc., which are merely listed here and are not specifically limited.

[0059] Optionally, the device for generating a hidden danger remediation work order is provided with a hidden danger mining and analysis module and a fault event monitoring module. When the hidden danger equipment work order is for a hidden danger equipment that currently needs to be detected for hidden dangers, the hidden danger mining and analysis module can be used to perform a hidden danger scan on the network elements of the hidden danger equipment that needs to be detected for hidden dangers according to a preset intelligent analysis algorithm to obtain a list of network elements that need to be detected for hidden dangers and a list of alarm titles (or hidden danger names); then, based on the fault event monitoring module, a pre-trained event definition model is used to perform event definition on the scanned network element list and alarm title list to obtain a list of faulty network elements, a list of fault events, and a list of associated alarm titles, and a hidden danger equipment work order is constructed based on the list of faulty network elements, the list of fault events, and the list of associated alarm titles. If the hidden danger equipment work order is the work order data corresponding to the hidden danger equipment that currently has hidden dangers, the manually input hidden danger equipment work order can be received; or, based on the hidden danger mining and analysis module, all network elements in the existing network operation state can be scanned for hidden dangers to obtain a network element list and an alarm title list, and then based on the fault event monitoring module, the event definition fault network element list, fault event list and related alarm title list can be performed, and the hidden danger equipment work order can be constructed according to the fault network element list, fault event list and related alarm title list.

[0060] Optionally, the same work order for a hazardous device may record the hazardous information of multiple hazardous devices at the same time, or the hazardous information of different hazardous devices may be recorded through different work orders for a hazardous device.

[0061] In this embodiment, the work order for a device with a hidden danger records the alarm type and hidden danger level assessment index corresponding to at least one device with a hidden danger, or the work order for a device with a hidden danger records relevant information about the alarm type and hidden danger level assessment index corresponding to at least one device with a hidden danger. Thus, after obtaining the work order for a device with a hidden danger, the alarm type and hidden danger level assessment index corresponding to the device with a hidden danger can be determined based on the work order for the device with a hidden danger. For example, if the work order for a device with a hidden danger records the alarm title, the alarm type of the device with a hidden danger can be analyzed based on the alarm title; if the work order for a device with a hidden danger records the alarm information for each alarm, the alarm frequency can be analyzed based on the alarm information for each alarm, and the alarm frequency obtained from the analysis can be used as the hidden danger level assessment index; alternatively, the alarm type and hidden danger level assessment index corresponding to the device with a hidden danger can be obtained directly from the work order for the device with a hidden danger, for example, the alarm type field and hidden danger level assessment index field corresponding to the device with a hidden danger can be obtained directly from the work order for the device with a hidden danger. Among these, the hidden danger level assessment index may include: network element attributes, alarm (or event) frequency, number of associated users, scope of business impact, etc.

[0062] Optionally, the step of determining the alarm type corresponding to the hidden danger device and the step of determining the hidden danger level assessment index corresponding to the hidden danger device can be performed simultaneously or successively in a preset order, which is not specifically limited here.

[0063] Step S20: calling a pre-built hidden danger remediation measures knowledge base, and querying the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base;

[0064] It should be noted that the device for generating hidden danger remediation work orders in this embodiment stores a pre-built knowledge base of hidden danger remediation measures. This knowledge base can be used to represent hidden danger information corresponding to different alarm types for different hidden danger devices (such as fault cause classification, hidden danger remediation recommendations, and the confidence level of the hidden danger remediation recommendations). Among them, the hidden danger remediation recommendations refer to hidden danger remediation measures that can be recommended for remediating the current alarm type of the current hidden danger device; the confidence level of the hidden danger remediation recommendation is used to indicate the accuracy of recommending the current hidden danger remediation recommendation for the current alarm type of the current hidden danger device.

[0065] After determining the alarm type corresponding to the hidden danger equipment, the pre-built hidden danger remediation measure knowledge base can be called to query the hidden danger remediation measure knowledge base for the hidden danger remediation item corresponding to the determined alarm type and the confidence level of the hidden danger remediation item.

[0066] Optionally, the pre-built knowledge base of hidden danger remediation measures can be constructed based on historical work order data corresponding to each device with hidden dangers. For example, historical work order data can be analyzed to establish correlations between hidden danger information corresponding to different alarm types for different devices with hidden dangers, and then the knowledge base of hidden danger remediation measures can be constructed based on these correlations. Alternatively, historical work order data pre-annotated with correlations between hidden danger information corresponding to different alarm types for different devices with hidden dangers can be input into a preset neural network model, and deep learning can be performed using the preset neural network model to obtain the knowledge base. This is not specifically limited here.

[0067] Optionally, a statistical analysis of the historical handling measures of this network element or similar network element devices can be performed in the form of charts or other means (including the distribution of faulty equipment manufacturers, fault provinces, fault cause categories, etc.). If a query based on the hidden danger remediation measures knowledge base shows that this network element (equipment) has had historical work orders, the details of the historical handling measures can be viewed by fault cause category and treatment measure category; if a query based on the hidden danger remediation measures knowledge base shows that this network element has not had historical work orders, but similar network elements have had historical fault work orders, the details of the historical handling measures can also be viewed by province, network element name, fault cause category, and treatment measure category.

[0068] Among them, the same hidden danger equipment may correspond to one or more different alarm types, and the same alarm type may also correspond to one or more different hidden danger remediation recommendation items; the confidence levels of different hidden danger remediation recommendation items corresponding to different alarm types may be the same or different, and the confidence levels of different hidden danger remediation recommendations corresponding to the same alarm type may also be the same or different, which is not specifically limited here.

[0069] Step S30: determining the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index;

[0070] It should be noted that the hidden danger level of a hidden danger device is used to represent the urgency of handling a hidden danger event of the hidden danger device. Optionally, the urgency can be reflected by the priority of the hidden danger device.

[0071] After determining the alarm type and the hidden danger level assessment indicator, the hidden danger level of the hidden danger device can be determined based on the determined alarm type and hidden danger level assessment indicator. For example, a correspondence between the alarm type and hidden danger level assessment indicator and the hidden danger level of the hidden danger device can be pre-established. Then, based on the determined alarm type and hidden danger level assessment indicator, the hidden danger level of the hidden danger device can be queried based on this correspondence.

[0072] In one embodiment, cluster analysis may be performed based on the determined alarm types and hidden danger level assessment indicators to obtain the hidden danger level of the hidden danger equipment.

[0073] Specifically, the determined alarm type and hidden danger level assessment index can be input into a pre-trained cluster analysis model. Correspondingly, the output result of the cluster analysis model is the hidden danger level of the hidden danger equipment, or the output result of the cluster analysis model is output information containing the hidden danger level of the hidden danger equipment.

[0074] The cluster analysis model can be obtained by training a preset neural network model using historical work order data pre-labeled with different hidden danger levels of equipment as a training dataset. The specific cluster analysis model is not specifically limited here.

[0075] Optionally, the hidden danger levels corresponding to different hidden danger devices may be divided in different ways, and the hidden danger level assessment indicators corresponding to different alarm types of different hidden danger devices may also be different.

[0076] Optionally, based on the different potential danger devices, the corresponding alarm types may include at least one of: core network element alarm, base station alarm, optical network unit (ONU) alarm, transmission / bearing network element alarm, dynamic ring network element alarm, etc.

[0077] For example, for core network element alarms, the corresponding hidden danger level can be defined as important; for transmission / bearing network element alarms, the hidden danger level of the first trunk network element can be defined as major, the hidden danger level of the second trunk network element can be defined as important, and the hidden danger level of the local network element can be defined as general; for dynamic environment network element alarms, the hidden danger level corresponding to the core site and machine building can be defined as important, and the others can be defined as general.

[0078] For example, for base station alarms, the following characteristics can be selected as hidden danger level assessment indicators: (1) Fault frequency, which can include the number of faults within 15 minutes, the number of faults within 1 hour, the number of faults within 1 day, and the number of faults within 7 days; (2) Number of complaints, which can include the number of complaints within 15 minutes, the number of complaints within 1 hour, the number of complaints within 1 day, and the number of complaints within 7 days; (3) Business volume, which can include the call volume within 15 minutes, the call volume within 1 hour, the call volume within 1 day, and the call volume within 7 days; (4) Traffic, which can include the traffic volume within 15 minutes, the traffic volume within 1 hour, the traffic volume within 1 day, and the traffic volume within 7 days; (5) Recent fault interval; (6) Number of online users; (7) HTTP access delay; (8) HTTP access success rate. Then, using base station alarms and their corresponding hidden danger level assessment indicators as input data, at least one of the unsupervised clustering algorithms, such as Gaussian mixture, K-means clustering algorithm, and DBSCAN (Density-Based Spatial Clustering of Applications with Noise), is used to perform cluster analysis on the base station data to analyze the hidden danger levels of different hidden danger devices. The rationality of the cluster analysis results is verified by manual sampling. Finally, the hidden danger levels of the base stations are divided into three categories (three levels): major, important, and general.

[0079] For ONU alarms, the following features can be selected as indicators for assessing the hidden danger level: (1) Fault frequency, which can include the number of faults within 15 minutes, the number of faults within 1 hour, the number of faults within 1 day, and the number of faults within 7 days; (2) Number of complaints, which can include the number of complaints within 15 minutes, the number of complaints within 1 hour, the number of complaints within 1 day, and the number of complaints within 7 days; (3) Traffic, which can include the traffic within 15 minutes, the traffic within 1 hour, the traffic within 1 day, and the traffic within 7 days; (4) Interval between recent faults; (5) Number of online users; (6) HTTP access delay; and (7) HTTP access success rate. Then, using ONU alarms and their corresponding hidden danger level assessment indicators as input data, at least one of the unsupervised clustering algorithms, such as Gaussian mixture, K-means clustering algorithm, and DBSCAN (Density-Based Spatial Clustering of Applications with Noise), was used to perform cluster analysis on the base station data to obtain the hidden danger levels of different hidden danger devices. The rationality of the cluster analysis results was verified by manual sampling. Finally, the ONU hidden danger levels were divided into three categories (three levels): major, important, and general.

[0080] Optionally, different cluster analysis models can be set up separately for the alarm types corresponding to different hidden danger devices, so that after determining the alarm type and hidden danger level assessment index, the corresponding cluster analysis model can be called according to the alarm type corresponding to different hidden danger devices, and then the hidden danger level assessment index corresponding to the alarm type is input as input data into the cluster analysis model, and then the cluster analysis model outputs the hidden danger level of the hidden danger device.

[0081] It should be noted that steps S20 and S30 can be executed simultaneously or sequentially in a predetermined order, which is not specifically limited here. For example, to improve processing efficiency, steps S20 and S30 can be executed simultaneously; or, step S20 can be executed directly after determining the alarm type, without waiting until the hidden danger level assessment index is determined, while step S30 needs to be executed after determining the alarm type and hidden danger level assessment index. In other words, step S20 can be executed first and then step S30 to improve processing efficiency.

[0082] Step S40: determining a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and determining a second priority corresponding to the hidden danger equipment according to the hidden danger level;

[0083] After querying the recommended hidden danger remediation item corresponding to the alarm type and the confidence level of the hidden danger remediation item, the priority level corresponding to the hidden danger remediation item can be determined based on the confidence level (recorded as the first priority level). After determining the hidden danger level corresponding to the hidden danger device, the priority level corresponding to the hidden danger device can be determined based on the hidden danger level (recorded as the second priority level).

[0084] Optionally, the higher the confidence level of the hidden danger remediation recommendation item, the higher the priority corresponding to the hidden danger remediation recommendation item.

[0085] For example, the recommended hazard remediation items can be sorted from high to low according to their confidence level, with the ranking number of the sorted recommended hazard remediation items serving as their corresponding priority. Recommendations with the same confidence level will have the same ranking number and the same priority level. Alternatively, different confidence ranges can be assigned, with each confidence range corresponding to a different priority level. For example, when the confidence level of a recommended hazard remediation item falls within a first confidence range, the priority level can be assigned to the first level; when the confidence level of the recommended hazard remediation item falls within a second confidence range, the priority level can be assigned to the second level; and when the confidence level of the recommended hazard remediation item falls within a third confidence range, the priority level can be assigned to the third level. The first confidence range is greater than the second confidence range, and the second confidence range is greater than the third confidence range. Priority level one is higher than priority level two, and priority level two is higher than priority level three. Of course, more or fewer confidence ranges and priority levels for recommended hazard remediation items can be assigned. This is merely an example and not intended to be limiting.

[0086] Optionally, the higher the hidden danger level corresponding to the hidden danger device, the higher the priority corresponding to the hidden danger device.

[0087] For example, the hidden danger equipment can be sorted from high to low according to the hidden danger level, and the arrangement number of the sorted hidden danger equipment is used as the corresponding priority of the hidden danger equipment. Among them, for hidden danger equipment with the same hidden danger level, the corresponding arrangement number is the same, and the corresponding priority is also the same. Alternatively, when there are many hidden danger levels, different hidden danger levels can correspond to the priority of the same hidden danger equipment. For example, when the hidden danger level is within the first hidden danger level range, the priority of the hidden danger equipment is determined to be level one; when the hidden danger level is within the second hidden danger level range, the priority of the hidden danger equipment is determined to be level two; when the hidden danger level is within the second hidden danger level range, the priority of the hidden danger equipment is determined to be level three. Among them, the first hidden danger level range is larger than the second hidden danger level range, and the second hidden danger level range is larger than the third hidden danger level range; the priority of level one is higher than the priority of level two, and the priority of level two is higher than the priority of level three. Of course, more or fewer hidden danger level ranges and priorities of hidden danger equipment can be divided. This is just an enumeration without specific limitation.

[0088] Step S50: Generate a hidden danger remediation work order according to the first priority and the second priority.

[0089] It should be noted that the hidden danger remediation work order can be used to display the hidden danger information corresponding to different alarm types of different hidden danger equipment, such as hidden danger remediation measures, fault cause classification, etc., so that users can perform hidden danger remediation according to the hidden danger remediation work order without the need for manual hidden danger inspection and specified hidden danger remediation plan.

[0090] Optionally, the displayed content of the hidden danger remediation work order includes but is not limited to: hidden danger name, hidden danger equipment name, hidden danger level, recommended hidden danger remediation measures and fault classification cause, etc., which are not specifically limited here.

[0091] Optionally, when generating a hazard remediation work order based on the first and second priorities, different hazard remediation recommendations may be marked using different marking methods based on the first priority level, and different hazard equipment may be marked using different marking methods based on the second priority level. Specifically, marking and distinguishing may be achieved by adding annotation information using different colors, shapes, or symbols, etc., which is not specifically limited here.

[0092] Optionally, when generating a hidden danger remediation work order based on the first and second priorities, the recommended hidden danger remediation items can be sorted by the first priority, and the devices with hidden dangers can be sorted by the second priority before the corresponding hidden danger remediation work order is output. Specifically, after sorting the devices with hidden dangers by the second priority, the recommended hidden danger remediation items corresponding to the different alarm types of each device with hidden dangers can be sorted by the first priority, thereby improving the visualization of the hidden danger remediation work order.

[0093] Optionally, the hidden danger remediation work order can be presented in the form of charts or other means.

[0094] Optionally, different hidden danger devices may correspond to different hidden danger remediation work orders, and then the hidden danger remediation work orders corresponding to different hidden danger devices may be sent to corresponding hidden danger devices to prevent information leakage.

[0095] This embodiment determines the first priority of the hidden danger remediation recommendation items and the second priority corresponding to the hidden danger equipment, so that the hidden danger remediation work order can be automatically generated according to the first priority and the second priority, without the need for manual investigation, which can reduce human participation, thereby improving the timeliness of hidden danger investigation and thus improving the timeliness of hidden danger remediation.

[0096] Based on the above embodiment, a second embodiment of the method for generating a hidden danger remediation work order of the present invention is proposed. Figure 3In this embodiment, before step S20, the following steps are further included:

[0097] Step S11: determining the alarm type of the hazardous equipment and the hazard remediation measures corresponding to the alarm type based on the historical work order data of the hazardous equipment;

[0098] Step S12: Obtain a set of hidden danger remediation measures corresponding to the alarm type;

[0099] Step S13: determining the similarity between every two hidden danger remediation measures in the hidden danger remediation measures set;

[0100] Step S14: merging the hidden danger remediation measures in the hidden danger remediation measure set according to the similarity;

[0101] Step S15: constructing a hidden danger remediation measures knowledge base based on the merged hidden danger remediation measures set.

[0102] Before calling the hidden danger remediation measures knowledge base, you must first build it. Because there may be multiple hidden danger remediation measures corresponding to different alarm types of hidden danger equipment, and these multiple hidden danger remediation measures may have different names but essentially the same treatment measures, in order to streamline the hidden danger remediation measures knowledge base and improve the efficiency of calling the hidden danger remediation measures knowledge base for data queries, the same hidden danger remediation measures corresponding to the same alarm type of the same hidden danger equipment can be merged together, and then the hidden danger remediation measures knowledge base can be built based on the merged hidden danger remediation measures.

[0103] Specifically, the steps to build a knowledge base of hidden danger remediation measures can be divided into the following steps:

[0104] (1) The alarm type of the device with hidden dangers and the corresponding hidden danger remediation measures can be determined based on the historical work order data of the device with hidden dangers. For example, the historical work order data can be preprocessed first, and the key fields of the historical work order data can be parsed and structured to extract the field information such as network element type, alarm title, hidden danger remediation measures, etc. from the historical work order data, and then aggregated into an index to establish a mapping relationship with the historical work order data. Based on the extracted field information, the alarm type of the device with hidden dangers and the corresponding hidden danger remediation measures can be determined.

[0105] (2) The hidden danger remediation measures corresponding to the same alarm type belonging to the same hidden danger equipment can be queried according to the index of each historical work order data, and the hidden danger remediation measures corresponding to the same alarm type can be divided into the same group of hidden danger remediation measures corresponding to the same alarm type of the same hidden danger equipment.

[0106] (3) extracting the feature vector of each hidden danger remediation measure in the set of hidden danger remediation measures, performing similarity calculation on every two of the feature vectors, and obtaining the similarity between every two hidden danger remediation measures in the set of hidden danger remediation measures.

[0107] Specifically, each hidden danger remediation measure in the set of hidden danger remediation measures corresponding to the same alarm type is processed through keyword extraction, subject word / nominal entity recognition, stop word filtering, and text segmentation. Feature extraction algorithms such as TF-IDF (termfrequency–inverse document frequency, a common weighting technique used in information retrieval and data mining) are then used to extract features, resulting in a multidimensional feature vector for each hidden danger remediation measure. The cosine similarity of the feature vectors of each hidden danger remediation measure in the set of hidden danger remediation measures corresponding to the same alarm type is then calculated, resulting in a hidden danger remediation measure similarity score matrix, which is used to evaluate the similarity between each pair of hidden danger remediation measures in the set.

[0108] (4) merging the hidden danger remediation measures in the hidden danger remediation measure set according to the similarity;

[0109] The higher the similarity between hidden danger remediation measures, the more likely they represent the same hidden danger remediation measure. To merge hidden danger remediation measures, you can set multiple confidence levels to group and merge similar treatment measures. The confidence level of the hidden danger remediation recommendation can be represented by the similarity between the hidden danger remediation measures.

[0110] For example, hidden danger remediation measures with similarity greater than or equal to a preset similarity threshold can be grouped together as one piece of form data, while hidden danger remediation measures with similarity lower than the preset similarity threshold can be grouped together as separate hidden danger remediation measures and each piece of form data can be grouped together as one piece of form data.

[0111] (5) Constructing a knowledge base of hidden danger remediation measures based on the merged set of hidden danger remediation measures.

[0112] Optionally, after grouping similar hidden danger remediation measures, the different hidden danger remediation measures corresponding to the same alarm type for the same hidden danger device can be ranked by confidence level, and a hidden danger remediation measure knowledge base can be constructed based on this ranking. The hidden danger remediation measure knowledge base not only records the hidden danger remediation measures corresponding to the alarm types of multiple hidden danger devices (i.e., hidden danger remediation recommendations), but also records the confidence level of the hidden danger remediation recommendations for subsequent review.

[0113] Optionally, the historical work order data may be the work order data of equipment with hidden dangers in the recent period, such as the historical work order data within a week; the historical work order data may also be the historical work order data filtered out according to preset filtering conditions, such as the historical work order data of equipment with hidden dangers that has a higher probability of hidden dangers, etc., which is not specifically limited here.

[0114] In one embodiment, after constructing the hidden danger remediation measures knowledge base, the hidden danger remediation measures that are grouped together can be redefined in a standardized manner to streamline the hidden danger remediation measures knowledge base. Specific streamlining steps may include:

[0115] (1) Receive the marking operation of hidden danger remediation measures.

[0116] Specifically, this could involve filtering out a collection of hidden danger remediation measures with merged items from the hidden danger remediation measures knowledge base, sorting them from highest to lowest by the number of merged items, and then having experts trigger annotation operations on each item in the sorted order. Alternatively, experts could freely select the appropriate merged items to trigger annotation operations based on actual circumstances. For example, by combining business logic to select key network element types and alarm title types, they could then annotate the merged hidden danger remediation measures.

[0117] (2) performing information labeling on the hidden danger remediation measures in the merged hidden danger remediation measures set according to the labeling operation;

[0118] After the expert triggers the labeling operation, the hidden danger remediation measures in the merged corresponding hidden danger remediation measures set can be labeled with information according to a fixed template format.

[0119] When labeling information, summaries of hidden danger remediation measures extracted based on expert experience, corrected classification error items, and cases of hidden danger remediation measures marked with hidden danger excavation value can be introduced as labeling information.

[0120] (3) updating the hidden danger remediation measures knowledge base according to the labeling results of the information labeling.

[0121] After information labeling, the labeling information corresponding to the information labeling can be added to the hidden danger remediation measures knowledge base and associated with the corresponding hidden danger remediation measures set for storage to achieve the update of the hidden danger remediation measures knowledge base; or, after information labeling, the labeling information corresponding to the information labeling can be used to replace the original labeling information of the corresponding hidden danger remediation measures set in the hidden danger remediation measures knowledge base to achieve the update of the hidden danger remediation measures knowledge base.

[0122] In this way, by standardizing the labeling of the corresponding hidden danger remediation measures in the hidden danger remediation measures knowledge base, it is not only convenient for data query, but also enables the generated hidden danger remediation work orders to be sufficiently streamlined.

[0123] This embodiment groups and merges the hidden danger remediation measures corresponding to the same alarm type of the same hidden danger equipment to construct a hidden danger remediation measures knowledge base, thereby streamlining the hidden danger remediation measures knowledge base and improving the query efficiency of calling the hidden danger remediation measures knowledge base for data query.

[0124] Based on the above embodiments, a third embodiment of the method for generating a hidden danger remediation work order of the present invention is proposed. Figure 4 In this embodiment, after step S50, the following steps are further included:

[0125] Step S60: determining the accuracy of the remediation measure recommendation corresponding to the hidden danger remediation recommendation item in the hidden danger remediation work order;

[0126] Step S70: Modify the hidden danger remediation measure knowledge base and / or the hidden danger remediation work order according to the accuracy of the remediation measure recommendation.

[0127] After a hidden danger remediation work order is generated, the hidden danger remediation measures recommended in the hidden danger remediation work order may not be accurate. Therefore, after determining the accuracy of the remediation measures recommended corresponding to the hidden danger remediation recommended items in the hidden danger remediation work order, the hidden danger remediation measures knowledge base and the hidden danger remediation work order can be revised according to the accuracy of the remediation measures recommended to improve the accuracy of the hidden danger remediation measures recommended.

[0128] In one embodiment, the accuracy of the remediation measure recommendation corresponding to the hidden danger remediation recommendation item in the hidden danger remediation work order may be determined by:

[0129] (1) obtaining a first eigenvector of a hidden danger remediation recommendation item corresponding to the alarm type and a second eigenvector of an actual remediation measure item corresponding to the alarm type;

[0130] Specifically, the generated hidden danger remediation work order is not only provided with a field for recording the recommended hidden danger remediation items, but also provided with a field for recording the hidden danger remediation measures actually adopted when performing hidden danger remediation (referred to as the actual remediation measures item), which can be entered manually.

[0131] After obtaining the hidden danger remediation recommendation items from the hidden danger remediation work order, the obtained hidden danger remediation recommendation items can be subjected to keyword extraction, subject word / named entity recognition, stop word filtering, text segmentation, and other processing, and then feature extraction algorithms such as TF-IDF are used to perform feature extraction to obtain the feature vector of the hidden danger remediation recommendation items corresponding to the current alarm type of the current hidden danger device (recorded as the first feature vector). Correspondingly, after obtaining the actual remediation measure items from the hidden danger remediation work order, the obtained actual remediation measure items can be subjected to keyword extraction, subject word / named entity recognition, stop word filtering, text segmentation, and other processing, and then feature extraction algorithms such as TF-IDF are used to perform feature extraction to obtain the feature vector of the actual remediation measure items corresponding to the current alarm type of the current hidden danger device (recorded as the second feature vector).

[0132] (2) performing cosine similarity calculation on the first eigenvector and the second eigenvector to obtain the similarity between the recommended remediation measure item and the actual remediation measure item;

[0133] (3) Determining the accuracy of the remediation measure recommendation based on the similarity; wherein, the higher the similarity, the higher the accuracy of the remediation measure recommendation.

[0134] Specifically, different similarity ranges can be divided, and different similarity ranges correspond to different remediation measure recommendation accuracy. For example, 10 similarity ranges can be divided from low to high similarity, and correspondingly, 10 remediation measure recommendation accuracy levels can be obtained from low to high accuracy.

[0135] Optionally, the actual remediation measures item may carry alarm data, performance data, complaint data, etc. during the actual remediation process to reversely verify the hidden danger remediation situation.

[0136] In another embodiment, when the hidden danger remediation measures knowledge base and the hidden danger remediation work order are revised based on the accuracy of the remediation measures recommendation, the labeling information of the corresponding hidden danger measures in the hidden danger remediation measures knowledge base can be updated, and the hidden danger level of the corresponding hidden danger equipment in the hidden danger remediation work order can also be updated. The query order of querying data in the hidden danger remediation measures knowledge base based on the alarm type and / or the calling order of calling data in the hidden danger remediation measures knowledge base based on the alarm type can also be corrected.

[0137] Optionally, the labeling information of the recommended remediation measures item corresponding to the current alarm type of the current hidden danger device and the labeling information of the corresponding actual remediation measures item can be merged, and the labeling information of the corresponding hidden danger remediation measures item in the hidden danger remediation measures knowledge base can be updated with the merged labeling information. Specifically, when the accuracy of the remediation measure recommendation is lower than the preset accuracy, the labeling information of the recommended remediation measures item corresponding to the current alarm type of the current hidden danger device can be obtained from the hidden danger remediation work order (recorded as the first labeling information), and the labeling information of the actual remediation measures item corresponding to the current alarm type of the current hidden danger device can be obtained from the hidden danger remediation work order (recorded as the second labeling information), and then the first labeling information and the second labeling information are taken as the union to obtain the target labeling information, and the labeling information of the recommended remediation measures item in the hidden danger remediation measures knowledge base is replaced with the obtained target labeling information to achieve the update of the labeling information of the recommended remediation measures item, so that the next time the hidden danger remediation measures knowledge base is called for data query, it can be more accurate.

[0138] Optionally, the frequency of hidden dangers occurring during the actual remediation process for the current hidden danger device (recorded as the hidden danger occurrence frequency) can be obtained from the hidden danger remediation work order, and the hidden danger level of the hidden danger device in the hidden danger remediation work order can be updated based on the hidden danger occurrence frequency. For example, if the hidden danger occurrence frequency increases above the average hidden danger occurrence frequency before the hidden danger remediation, the hidden danger level of the current hidden danger device can be increased; or if the hidden danger occurrence frequency shows an increasing trend during the hidden danger remediation process, the hidden danger level of the current hidden danger device can be increased, etc., so that the hidden danger remediation of the current hidden danger device can be prioritized.

[0139] Optionally, the order in which data is retrieved from the remediation measures knowledge base based on the alarm type and / or the order in which data is searched from the remediation measures knowledge base based on the alarm type can be adjusted based on the probability of occurrence of the hidden danger remediation measures corresponding to the alarm type in the hidden danger remediation measures or historical work order data. For example, a preset probability model can be used to calculate the probability of occurrence of the hidden danger remediation measures corresponding to the current alarm type of the current hidden danger device. Based on this probability, the order in which data is retrieved from the remediation measures knowledge base based on the alarm type and / or the order in which data is searched from the remediation measures knowledge base based on the alarm type can be modified. The higher the probability of occurrence, the higher the order in which data is retrieved and / or the higher the order in which data is searched.

[0140] In this example, by correcting the hidden danger remediation measures knowledge base and / or hidden danger remediation work orders based on the accuracy of remediation measures recommendations, the accuracy of calling the hidden danger remediation measures knowledge base for data query and the accuracy of generating hidden danger remediation work orders can be improved, thereby improving the accuracy of hidden danger remediation measures recommendations.

[0141] In addition, an embodiment of the present invention also provides a device for generating a hidden danger remediation work order, which includes a memory, a processor, and a hidden danger remediation work order generation program stored on the processor and runnable on the processor. When the processor executes the hidden danger remediation work order generation program, it implements the steps of the hidden danger remediation work order generation method described above.

[0142] In addition, an embodiment of the present invention further provides a device for generating a hidden danger remediation work order, the device comprising: a first determination module, a query module, a second determination module, a third determination module and a generation module, wherein:

[0143] The first determination module is used to determine the alarm type and hidden danger level assessment index corresponding to the hidden danger equipment according to the hidden danger equipment work order;

[0144] Query module: used to call a pre-built hidden danger remediation measures knowledge base, and query the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base;

[0145] A second determining module is used to determine the hidden danger level of the hidden danger equipment according to the alarm type and the hidden danger level assessment index;

[0146] a third determining module, configured to determine a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and to determine a second priority corresponding to the hidden danger equipment according to the hidden danger level;

[0147] Generation module: used to generate a hidden danger remediation work order based on the first priority and the second priority.

[0148] Optionally, the device for generating the hidden danger remediation work order may include the apparatus for generating the hidden danger remediation work order or be communicatively connected to the apparatus for generating the hidden danger remediation work order.

[0149] It should be noted that the various embodiments of the above-mentioned hidden danger remediation work order generation device are basically the same as the various embodiments of the above-mentioned hidden danger remediation work order generation method, and will not be repeated here.

[0150] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which stores a program for generating a hidden danger remediation work order. When the program for generating a hidden danger remediation work order is executed by a processor, the steps of the method for generating a hidden danger remediation work order as described above are implemented.

[0151] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0152] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0153] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially 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) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, TV, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0154] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for generating a hidden danger remediation work order, characterized in that: The method for generating the hidden danger remediation work order includes: Determine the alarm type and hazard level assessment index corresponding to the hazardous equipment according to the work order of the hazardous equipment, wherein different alarm types of different hazardous equipment correspond to different hazard level assessment indexes; Invoking a pre-built hidden danger remediation measures knowledge base, and querying the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base; According to the alarm type corresponding to different hidden danger equipment, calling the corresponding cluster analysis model, inputting the alarm type and the hidden danger level assessment index into the cluster analysis model, and obtaining the hidden danger level of the hidden danger equipment; Determining a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and determining a second priority corresponding to the hidden danger equipment according to the hidden danger level; generating a hidden danger remediation work order according to the first priority and the second priority; Before the step of calling a pre-built hidden danger remediation measures knowledge base and querying the hidden danger remediation recommendation item corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation item based on the hidden danger remediation measures knowledge base, the method further includes: Determine the alarm type of the hidden danger equipment and the hidden danger remediation measures corresponding to the alarm type according to the historical work order data of the hidden danger equipment; Obtain a set of hidden danger remediation measures corresponding to the alarm type; Determining the similarity between each two hidden danger remediation measures in the set of hidden danger remediation measures; Merging the hidden danger remediation measures in the hidden danger remediation measure set according to the similarity, and grouping the hidden danger remediation measures with similarity greater than or equal to a preset similarity threshold into the same group as a piece of form data; A hidden danger remediation measures knowledge base is constructed based on the merged hidden danger remediation measures set.

2. The method for generating a hidden danger remediation work order according to claim 1, wherein: After the step of constructing a hidden danger remediation measures knowledge base based on the merged hidden danger remediation measures set, the method includes: Receive the marking operation of hidden danger remediation measures; Performing information labeling on the hidden danger remediation measures in the merged hidden danger remediation measures set according to the labeling operation; The hidden danger remediation measures knowledge base is updated according to the labeling results of the information labeling.

3. The method for generating a hidden danger remediation work order according to claim 1, wherein: After the step of generating a hidden danger remediation work order according to the first priority and the second priority, the method further includes: Determining the accuracy of the remediation measure recommendation corresponding to the recommended remediation measure item in the hidden danger remediation work order; The hidden danger remediation measure knowledge base and / or the hidden danger remediation work order are modified according to the accuracy of the remediation measure recommendation.

4. The method for generating a hidden danger remediation work order according to claim 3, wherein: The step of determining the accuracy of the remediation measure recommendation corresponding to the recommended remediation measure item in the hidden danger remediation work order includes: Obtaining a first feature vector of a recommended remediation measure item for the alarm type and a second feature vector of an actual remediation measure item for the alarm type; Performing cosine similarity calculation on the first eigenvector and the second eigenvector to obtain similarity between the recommended remediation measure item and the actual remediation measure item; The accuracy of the remediation measure recommendation is determined according to the similarity; wherein, the higher the similarity, the higher the accuracy of the remediation measure recommendation.

5. The method for generating a hidden danger remediation work order according to claim 3, wherein: The step of revising the hidden danger remediation measure knowledge base and / or the hidden danger remediation work order according to the remediation measure recommendation accuracy includes: When the accuracy of the remediation measure recommendation is lower than a preset accuracy, merging the annotation information of the recommended remediation measure item with the annotation information of the actual remediation measure item, and updating the annotation information of the recommended remediation measure item in the hidden danger remediation measure knowledge base with the merged annotation information; and / or, obtaining a frequency of occurrence of a hidden danger of the hidden danger equipment, and updating a hidden danger level of the hidden danger equipment in the hidden danger remediation work order according to the frequency of occurrence of the hidden danger; And / or, a preset probability model is used to calculate the occurrence probability of the hidden danger remediation measures corresponding to the alarm type, and the query order when calling the hidden danger remediation measures knowledge base for data query is modified according to the occurrence probability.

6. A device for generating a hidden danger remediation work order, characterized in that: The device for generating the hidden danger remediation work order includes a memory, a processor, and a hidden danger remediation work order generation program stored in the memory and runnable on the processor. When the processor executes the hidden danger remediation work order generation program, it implements the steps of the hidden danger remediation work order generation method described in any one of claims 1-5.

7. A device for generating a hidden danger remediation work order, wherein the device is applied to the method for generating a hidden danger remediation work order according to claim 1, characterized in that: The device for generating the hidden danger remediation work order includes: a first determination module, a query module, a second determination module, a third determination module and a generation module, wherein the first determination module is used to determine the alarm type and hidden danger level assessment index corresponding to the hidden danger equipment according to the hidden danger equipment work order; Query module: used to call a pre-built hidden danger remediation measures knowledge base, and query the hidden danger remediation recommendation items corresponding to the alarm type and the confidence level of the hidden danger remediation recommendation items based on the hidden danger remediation measures knowledge base. Different hidden danger equipment and different alarm types correspond to different hidden danger level assessment indicators; A second determination module is configured to call a corresponding cluster analysis model according to the alarm type corresponding to different hidden danger devices, input the alarm type and the hidden danger level assessment index into the cluster analysis model, and obtain the hidden danger level of the hidden danger device; a third determining module, configured to determine a first priority corresponding to the hidden danger remediation recommendation item according to the confidence level, and to determine a second priority corresponding to the hidden danger equipment according to the hidden danger level; Generation module: used to generate a hidden danger remediation work order based on the first priority and the second priority.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program for generating a hidden danger remediation work order. When the program for generating a hidden danger remediation work order is executed by a processor, the steps of the method for generating a hidden danger remediation work order according to any one of claims 1 to 5 are implemented.

Images