Monitoring device alarm signal screening method, system, device and storage medium

Abstract

The application provides a monitoring device alarm signal screening method, system, device and storage medium. The application inputs acquired service data into a data recognition model to mark each sub-data in the service data with a corresponding label, determines a target entity label in the service data according to each label, and generates a corresponding first data table. The first data table at least includes each preset label and a sub-data access bit corresponding to each preset label. According to each preset label, the application matches an entity label and an entity relationship label in the corresponding service data, extracts a first target sub-data, fills the first target sub-data into a corresponding sub-data access bit, acquires a target label in each preset label in the first data table, determines a second target sub-data, and judges whether the monitoring device has an abnormal condition according to the second target sub-data. If yes, the first data table is sent to a user, so as to solve the problem that it is difficult to analyze the traditional power grid monitoring information through manual monitoring.

Description

Technical Field

[0001] This invention belongs to the technical field of alarm signal filtering for monitoring equipment, specifically relating to methods, systems, devices, and storage media for alarm signal filtering for monitoring equipment. Background Technology

[0002] A power grid is an integrated system consisting of substations and transmission and distribution lines of various voltages within a power system. It comprises three units: substation, transmission, and distribution. The task of the power grid is to transmit and distribute electrical energy and to change voltage.

[0003] With the continuous expansion of the power grid, the number and types of power grid equipment are also rapidly increasing. The amount of equipment alarm data received by the production command center has increased significantly compared to the past. Daily monitoring work lacks systematic tools for comprehensive processing and cleaning of monitoring data. Besides the relatively obvious five distinguishing features (accident, anomaly, exceeding limits, displacement, and notification), it is difficult to quickly identify the validity of alarm signals. This influx of information causes great inconvenience to the commanders (monitors) at the production command center. For example, a commander (monitor) at a local power production command center needs to monitor 352 substations and 798 lines. The monitoring equipment is massive, with an average of 30,000 alarms monitored daily, including 1,960 accidents, 10,300 anomalies, 3,300 exceeding limits, and 2,100 displacements. Especially during severe weather, monitors often face several times or even dozens of times more power grid monitoring information than during normal operations, increasing the difficulty of monitoring and analysis. Summary of the Invention

[0004] Based on this, the present invention provides a method, system, device and storage medium for filtering alarm signals of monitoring equipment, aiming to solve the problem that it is difficult to analyze power grid monitoring information through manual monitoring in the prior art.

[0005] A first aspect of this invention provides a method for filtering alarm signals from monitoring devices, the method comprising:

[0006] Real-time acquisition of business data, inputting the business data into a data identification model to obtain labels for all sub-data in the business data, wherein the labels include entity labels and entity relationship labels;

[0007] Based on the tags of all sub-data in the business data, determine the tags of each target entity, and generate a corresponding first data table based on each target entity tag. The first data table includes at least each preset tag and the sub-data access bits corresponding to each preset tag.

[0008] According to each of the preset tags, match the corresponding entity tags and entity relationship tags in the business data, and according to the entity tags and entity relationship tags, obtain the corresponding first target sub-data and fill it into the corresponding sub-data access position;

[0009] Obtain the target tags from each of the preset tags in the first data table, and determine the second target sub-data based on the target tags;

[0010] Based on the second target sub-data, determine whether there is any abnormality in the monitoring equipment;

[0011] If so, then send the first data table to the user.

[0012] Furthermore, the step of determining the target entity label based on the labels of all sub-data in the business data, and generating a corresponding first data table based on each target entity label, wherein the first data table includes at least each preset label and the sub-data access bit corresponding to each preset label, includes:

[0013] Based on the target entity tags, the first data table is expanded to obtain a second data table, wherein the second data table further includes at least a target preset tag and the measure access position corresponding to the target preset tag.

[0014] Furthermore, the step of determining whether the monitoring device has any abnormalities based on the second target sub-data includes:

[0015] When it is determined that there is an abnormality in the monitoring equipment, the entity tag corresponding to the second target sub-data is determined based on the second target sub-data;

[0016] Based on the entity tags corresponding to the second target sub-data, match the corresponding associated entity tags, and call the target data table generated by the associated entity tags;

[0017] Determine the preset tags associated with the entity tags corresponding to the second target sub-data in the target data table, and obtain the corresponding associated sub-data;

[0018] Based on the second target sub-data and the associated sub-data, determine the measure label and fill the measure label into the measure access position.

[0019] Furthermore, the step of acquiring business data in real time, inputting the business data into a data identification model, and obtaining labels for all sub-data in the business data, wherein the labels include entity labels and entity relationship labels, precedes the following steps:

[0020] Historical business data is acquired, the historical business data is divided into several historical sub-data, and each historical sub-data is manually labeled to obtain historical entity labels and historical entity relationship labels, wherein the historical entity labels and the historical entity relationship labels form a training set;

[0021] Construct a neural network model, train the neural network model to convergence based on the training set, and obtain the data identification model.

[0022] Furthermore, the step of sending the first data table to the user includes:

[0023] Obtain the permission category of each preset tag in the first data table, and determine whether a preset category exists in each of the permission categories;

[0024] If so, the first target sub-data of the corresponding preset label is encrypted, and the first data table is updated.

[0025] Furthermore, the step of determining whether the monitoring device has any abnormalities based on the second target sub-data includes:

[0026] Based on the second target sub-data, obtain the corresponding target label and target entity label;

[0027] Based on the target tag and the target entity tag, obtain the matching evaluation rules, and call the preset conditions in the evaluation rules;

[0028] Determine whether the second target sub-data satisfies the preset condition;

[0029] If not, an exception label will be output to indicate that there is an abnormal situation with the monitoring equipment.

[0030] Furthermore, the step of determining the measure tag based on the second target sub-data and the associated sub-data, and filling the measure tag into the measure access bit, includes:

[0031] Obtain the anomaly tags and determine whether the number of anomaly tags is unique;

[0032] If not, determine whether there is a combination relationship between the abnormal tags;

[0033] If so, the corresponding exception tags are merged to generate the measure tag.

[0034] A second aspect of the present invention provides a monitoring device alarm signal filtering system, the system comprising:

[0035] The tag determination module is used to acquire business data in real time, input the business data into the data identification model, and obtain the tags of all sub-data in the business data, wherein the tags include entity tags and entity relationship tags;

[0036] The first data table generation module is used to determine the target entity label based on the labels of all sub-data in the business data, and generate a corresponding first data table based on each target entity label. The first data table includes at least each preset label and the sub-data access position corresponding to each preset label.

[0037] The matching module is used to match the entity tags and entity relationship tags in the corresponding business data according to each of the preset tags, and to obtain the corresponding first target sub-data according to the entity tags and entity relationship tags, and fill it into the corresponding sub-data access position;

[0038] The acquisition module is used to acquire target tags from each of the preset tags in the first data table, and determine second target sub-data based on the target tags;

[0039] The judgment module is used to determine whether there is any abnormality in the monitoring equipment based on the second target sub-data;

[0040] The sending module is used to send the first data table to the user when there is an abnormal situation in the monitoring device.

[0041] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the monitoring device alarm signal filtering method provided in the first aspect.

[0042] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the alarm signal filtering method for a temperature observation device provided in the first aspect.

[0043] The monitoring device alarm signal filtering method, system, device, and storage medium provided in the embodiments of the present invention have the following beneficial effects:

[0044] By inputting the acquired business data into the data identification model, each sub-data in the business data is labeled with a corresponding tag. Based on each tag, the target entity tag is determined, and a corresponding first data table is generated. This first data table includes at least each preset tag and the corresponding sub-data access position. Then, based on each preset tag, the corresponding entity tag and entity relationship tag in the business data are matched, and the first target sub-data is extracted and filled into the corresponding sub-data access position. The target tag in each preset tag in the first data table is obtained. Based on the target tag, the second target sub-data is determined, and based on the second target sub-data, it is determined whether there is an abnormality in the monitoring equipment. If so, the first data table is sent to the user to solve the problem that traditional power grid monitoring information is difficult to analyze through manual monitoring. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating the implementation of the alarm signal filtering method for monitoring equipment provided in the first embodiment of the present invention.

[0046] Figure 2 This is a data table provided in the first embodiment of the present invention, taking remote signaling tagging as an example;

[0047] Figure 3 This is a structural block diagram of the alarm signal filtering system for monitoring equipment provided in the second embodiment of the present invention;

[0048] Figure 4 This is a structural block diagram of the electronic device provided in the third embodiment of the present invention. Detailed Implementation

[0049] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0050] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0052] Example 1

[0053] Please see Figure 1 , Figure 1 The present invention illustrates a method for filtering alarm signals of a monitoring device according to a first embodiment of the present invention, the method specifically including steps S01 to S06.

[0054] Step S01: Acquire business data in real time, input the business data into the data identification model, and obtain the labels of all sub-data in the business data, wherein the labels include entity labels and entity relationship labels.

[0055] Among them, business data refers to monitoring data sent by monitoring equipment, while sub-data can be fields. First, based on the actual operation and working standards of the power grid, combined with human experience, alarm signal data from multi-source heterogeneous equipment, i.e., business data, is classified into the following tags using data identification technology: associated, debugging operation, manual operation, ignored, not in production, related maintenance, constantly lit, telemetry action, equipment defect, etc. Alarm signals marked with the above tags are identified as invalid signals that can be ignored for monitoring, while the rest are valid signals that are of concern for monitoring. Specifically, the data identification technology is implemented by building a tag management service. Based on a big data platform, multi-source data is extracted. The tag management service is an intermediate component between the underlying data and the upper-layer business applications. It is responsible for the automated maintenance of the underlying data, automatically classifying and dividing the data tables. The classified data is identified and processed by the tag factory according to customized rules, and finally, relevant tags are generated for use by the upper-layer applications.

[0056] It should be noted that tags are highly refined feature identifiers obtained through data analysis, facilitating data identification by machines or humans. An entity or relationship in the tag management service corresponds to one or more physical data tables. The connection between entities and relationships is achieved through the primary key, foreign key, or unique identifier of the physical table, typically corresponding to all fields in the data table except for the primary and foreign keys. To automate the tagging of business data, a data identification model needs to be established. In this embodiment, the process of establishing the data identification model is as follows: historical business data is acquired, broken down into several historical sub-data, and each historical sub-data is manually labeled to obtain historical entity tags and historical entity relationship tags. These tags form a training set, a neural network model is constructed, and the neural network model is trained to convergence based on the training set to obtain the data identification model. The neural network model can refer to a complex network system formed by a large number of interconnected processing units (called neurons), which can be used to handle information processing problems involving multiple factors and conditions.

[0057] Step S02: Determine the target entity label based on the labels of all sub-data in the business data, and generate a corresponding first data table based on each target entity label. The first data table includes at least each preset label and the sub-data access position corresponding to each preset label.

[0058] Specifically, after business data is input into the data identification model, all sub-data within the business data are labeled. First, the labels of the target entities are determined, such as... Figure 2 As shown, taking remote signaling tagging as an example, the target entity tag is "remote signaling". When a key or unique field of remote signaling appears in the business data, the target entity tag is confirmed, and a corresponding first data table is generated. The header of the first data table is "Remote Signaling Data Table". The first data table also includes each preset tag and its corresponding sub-data access position. Each preset tag is a remote signaling key, remote signaling meter ID, occurrence time, remote signaling content, and alarm category. The sub-data access position is a reserved position for filling in the corresponding field, used to fill in the obtained corresponding field. In addition, based on each preset tag in the first data table, the target preset tag is determined, and the first data table is expanded to obtain a second data table. The second data table also includes at least the target preset tag and the corresponding measure access position. In this embodiment, the target preset tag is "maintenance", and the maintenance tag also has a corresponding measure access position for filling in the corresponding measure.

[0059] Step S03: Match the entity tag and entity relationship tag in the corresponding business data according to each preset tag, and obtain the corresponding first target sub-data according to the entity tag and entity relationship tag, and fill it into the corresponding sub-data access position.

[0060] Since each entity label corresponds to a separate field, and the entity relationship labels establish a connection between the entity labels, the corresponding first target sub-data is obtained based on the entity label and entity relationship labels, and then filled into the corresponding sub-data access position to obtain a data table with data content.

[0061] Step S04: Obtain the target tags from each of the preset tags in the first data table, and determine the second target sub-data based on the target tags.

[0062] Step S05: Based on the second target sub-data, determine whether there is an abnormality in the monitoring device. If so, proceed to step S06.

[0063] Among them, the target label refers to the label that can be used to judge whether the device has any abnormality. The corresponding data is the second target sub-data. Taking remote signaling tagging as an example, the target label can be the occurrence time and remote signaling content, and the corresponding data is the second target sub-data. Based on the target label and the target entity label, that is, based on the remote signaling, the matching judgment rule is obtained, and the preset conditions in the judgment rule are called to determine whether the second target sub-data meets the preset conditions. If not, an abnormal label is output to indicate that there is an abnormal situation in the monitoring device. The abnormal label can be filled into the sub-data access position corresponding to the alarm category in the form of a level.

[0064] Specifically, the system acquires abnormal tags and determines whether the number of abnormal tags is unique. If not, it checks whether there is a combination relationship between the abnormal tags. If so, it merges the corresponding abnormal tags to generate a measure tag. Understandably, when the number of abnormal tags is not unique, for example, there are two tags: one for bus voltage exceeding the upper limit and the other for capacitor / reactor having no available capacity. Each tag corresponds to a specific data entity, attribute, condition, and condition value. Since the upper limit of bus voltage and no available capacity of capacitor / reactor are pre-set to have a combination relationship, when these two abnormal situations occur, they can be merged to generate a measure tag requiring manual voltage adjustment. Based on the logical method of tag derivation and combination, the system provides an interactive function, allowing users to easily select and combine existing tags to generate higher-level tags, thus improving the user experience.

[0065] Additionally, when an anomaly is detected in the monitoring equipment, the entity tag corresponding to the second target sub-data is determined based on the second target sub-data. Then, based on the entity tag corresponding to the second target sub-data, the corresponding associated entity tag is matched, and the target data table generated by the associated entity tag is called to determine the preset tag associated with the entity tag corresponding to the second target sub-data in the target data table. The corresponding associated sub-data is then obtained. Based on the second target sub-data and the associated sub-data, the measure tag is determined and filled into the measure access position. For example, taking bus voltage over-limit as an example, historical voltage telemetry data is stored at the minute level, while real-time voltage telemetry data occurs at the second level. When a voltage exceedance occurs, the second-level exceedance data can be tagged with both an exceedance tag and a time tag. When an oil temperature exceedance occurs, multi-dimensional associations are provided based on substation, voltage level, occurrence time, specific transformer, and reactor. This involves matching associated entity tags such as substation, voltage level, occurrence time, specific transformer, and reactor, and calling the target data table generated from these associated entity tags. Simultaneously, combined with transformer and reactor equipment defect data, pre-maintenance test data, load rate, ambient temperature and humidity, and oil temperature curves, specific tags are applied to predict oil temperature changes over a certain period. Based on these specific tags, corresponding action tags can be determined and filled into the action access field. Based on these tags, power big data analysis is achieved, cleaning and tagging a large number of equipment alarm signals from substations, identifying valid signals and recommending them to monitoring personnel, thus reducing the difficulty of monitoring and analysis.

[0066] In step S06, the first data table is sent to the user.

[0067] It should be noted that when determining if there are any abnormalities in the monitoring equipment, the first data table is sent to the user. The corresponding abnormal data columns in the first data table can be marked to make them more easily noticed by the user. Furthermore, to ensure the security of sensitive data, when maintaining multi-source business data, the system will perform hierarchical maintenance based on data ownership, profession, and individual, limiting the data scope to ensure that users can access the data they need while preventing unauthorized users from viewing other data. Specifically, the system retrieves the permission categories of each preset tag in the first data table. Permission categories can include two main categories: shared and non-shared. Non-shared categories can be further divided into subcategories, allowing for permission assignment by user or role. The system then checks if a preset category exists in each permission category. If so, the first target sub-data of the corresponding preset tag is encrypted, and the first data table is updated. Encryption can involve removing or hiding the data content. As the smallest granularity of a data entity is a field in a data table, the management of a single data entity can achieve field-level permission management and control. Data entities are divided into shared and non-shared types; shared data entities can be used by all users. Non-shared data entities can be authorized by user or role. Only authorized users can use the corresponding data entity, and only authorized data table fields.

[0068] In summary, the alarm signal filtering method for monitoring equipment in the above embodiments of the present invention, by inputting the acquired business data into a data identification model, marks each sub-data in the business data with corresponding tags, determines the target entity tags based on each tag, and generates a corresponding first data table, which includes at least each preset tag and the sub-data access position corresponding to each preset tag, then matches the entity tags and entity relationship tags in the corresponding business data based on each preset tag, extracts the first target sub-data, fills it into the corresponding sub-data access position, obtains the target tags in each preset tag in the first data table, determines the second target sub-data based on the target tags, and judges whether there is an abnormality in the monitoring equipment based on the second target sub-data. If so, the first data table is sent to the user, thereby solving the problem that traditional power grid monitoring information is difficult to analyze through manual monitoring.

[0069] Example 2

[0070] Please see Figure 3 , Figure 3 This is a structural block diagram of a monitoring equipment alarm signal filtering system provided in Embodiment 2 of the present invention. The monitoring equipment alarm signal filtering system 200 includes: a tag determination module 21, a first data table generation module 22, a matching module 23, an acquisition module 24, a judgment module 25, and a sending module 26, wherein:

[0071] The tag determination module 21 is used to acquire business data in real time, input the business data into the data identification model, and obtain the tags of all sub-data in the business data, wherein the tags include entity tags and entity relationship tags;

[0072] The first data table generation module 22 is used to determine the target entity label based on the labels of all sub-data in the business data, and generate a corresponding first data table based on the target entity label. The first data table includes at least each preset label and the sub-data access position corresponding to each preset label.

[0073] The matching module 23 is used to match the entity tags and entity relationship tags in the corresponding business data according to each of the preset tags, and to obtain the corresponding first target sub-data according to the entity tags and entity relationship tags, and fill it into the corresponding sub-data access position;

[0074] The acquisition module 24 is used to acquire target tags from each of the preset tags in the first data table, and determine second target sub-data based on the target tags;

[0075] The judgment module 25 is used to determine whether there is an abnormality in the monitoring device based on the second target sub-data;

[0076] The sending module 26 is used to send the first data table to the user when there is an abnormal situation in the monitoring device.

[0077] Furthermore, in some optional embodiments of the present invention, the first data table generation module 22 includes:

[0078] An extension unit is used to extend the first data table according to the target entity tags to obtain a second data table, wherein the second data table further includes at least a target preset tag and a measure access bit corresponding to the target preset tag.

[0079] Furthermore, in some optional embodiments of the present invention, the monitoring equipment alarm signal filtering system 200 further includes:

[0080] The entity tag determination module is used to determine the entity tag corresponding to the second target sub-data based on the second target sub-data when it is determined that there is an abnormal situation in the monitoring device;

[0081] The matching module is used to match the corresponding associated entity tags based on the entity tags corresponding to the second target sub-data, and call the target data table generated by the associated entity tags;

[0082] The associated sub-data acquisition module is used to determine the preset tag associated with the entity tag corresponding to the second target sub-data in the target data table, and to acquire the corresponding associated sub-data;

[0083] The measure label determination module is used to determine the measure label based on the second target sub-data and the associated sub-data, and fill the measure label into the measure access position.

[0084] Furthermore, in some optional embodiments of the present invention, the monitoring equipment alarm signal filtering system 200 further includes:

[0085] The training set generation module is used to acquire historical business data, split the historical business data into several historical sub-data, and manually label each of the historical sub-data to obtain historical entity labels and historical entity relationship labels, wherein the historical entity labels and the historical entity relationship labels form a training set;

[0086] The data identification model building module is used to construct a neural network model, train the neural network model to convergence based on the training set, and obtain the data identification model.

[0087] Furthermore, in some optional embodiments of the present invention, the sending module 26 includes:

[0088] The first judgment unit is used to obtain the permission category of each preset tag in the first data table, and to determine whether a preset category exists in each of the permission categories;

[0089] The encryption processing unit is used to encrypt the first target sub-data of the corresponding preset tag and update the first data table when it is determined that a preset category exists in each of the permission categories.

[0090] Furthermore, in some optional embodiments of the present invention, the determining module 25 includes:

[0091] The first acquisition unit is used to acquire the corresponding target label and the target entity label based on the second target sub-data;

[0092] The calling unit is used to obtain the matching evaluation rules based on the target tag and the target entity tag, and to call the preset conditions in the evaluation rules;

[0093] The second judgment unit is used to determine whether the second target sub-data satisfies the preset condition;

[0094] The output unit is used to output an abnormal label when it is determined that the second target sub-data does not meet the preset conditions, so as to indicate that there is an abnormal situation in the monitoring equipment.

[0095] Furthermore, in some optional embodiments of the present invention, the measure label determination module includes:

[0096] The third judgment unit is used to obtain the abnormal tags and determine whether the number of abnormal tags is unique;

[0097] The fourth judgment unit is used to determine whether there is a combination relationship between the abnormal tags when the number of abnormal tags is not unique.

[0098] The merging unit is used to merge the corresponding abnormal tags to generate the measure tag when it is determined that there is a combination relationship between the abnormal tags.

[0099] In summary, the monitoring equipment alarm signal filtering system in the above embodiments of the present invention, by inputting the acquired business data into a data identification model, marks each sub-data in the business data with corresponding tags, determines the target entity tags based on each tag, and generates a corresponding first data table. The first data table includes at least each preset tag and the sub-data access position corresponding to each preset tag. Then, based on each preset tag, it matches the corresponding entity tags and entity relationship tags in the business data, extracts the first target sub-data, fills it into the corresponding sub-data access position, obtains the target tags in each preset tag in the first data table, determines the second target sub-data based on the target tags, and judges whether there is an abnormality in the monitoring equipment based on the second target sub-data. If so, it sends the first data table to the user, thereby solving the problem that traditional power grid monitoring information is difficult to analyze through manual monitoring.

[0100] Example 3

[0101] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 4 The diagram shows an electronic device according to the third embodiment of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the monitoring device alarm signal filtering method as described above.

[0102] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0103] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0104] It should be pointed out that, Figure 4 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0105] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the monitoring device alarm signal filtering method described above.

[0106] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0107] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0108] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0110] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for filtering alarm signals from monitoring equipment, characterized in that, The method includes: Real-time acquisition of business data, inputting the business data into a data identification model to obtain labels for all sub-data in the business data, wherein the labels include entity labels and entity relationship labels; Based on the tags of all sub-data in the business data, determine the tags of each target entity, and generate a corresponding first data table based on each target entity tag. The first data table includes at least each preset tag and the sub-data access bits corresponding to each preset tag. The step of determining the target entity label based on the labels of all sub-data in the business data, and generating a corresponding first data table based on each target entity label, wherein the first data table includes at least each preset label and the sub-data access bit corresponding to each preset label, further includes: Based on the target entity tags, the first data table is expanded to obtain a second data table, wherein the second data table further includes at least a target preset tag and a measure access bit corresponding to the target preset tag; According to each of the preset tags, match the corresponding entity tags and entity relationship tags in the business data, and according to the entity tags and entity relationship tags, obtain the corresponding first target sub-data and fill it into the corresponding sub-data access position; Obtain the target tags from each of the preset tags in the first data table, and determine the second target sub-data based on the target tags; Based on the second target sub-data, determine whether there are any abnormalities in the monitoring equipment; If so, then send the second data table to the user; The step of determining whether the monitoring device has any abnormalities based on the second target sub-data includes: When it is determined that there is an abnormality in the monitoring equipment, the entity tag corresponding to the second target sub-data is determined based on the second target sub-data; Based on the entity tags corresponding to the second target sub-data, match the corresponding associated entity tags, and call the target data table generated by the associated entity tags; Determine the preset tags associated with the entity tags corresponding to the second target sub-data in the target data table, and obtain the corresponding associated sub-data; Based on the second target sub-data and the associated sub-data, determine the measure label and fill the measure label into the measure access position.

2. The alarm signal filtering method for monitoring equipment according to claim 1, characterized in that, The step of acquiring business data in real time, inputting the business data into a data identification model, and obtaining labels for all sub-data in the business data, wherein the labels include entity labels and entity relationship labels, includes the following prior steps: Historical business data is acquired, the historical business data is divided into several historical sub-data, and each historical sub-data is manually labeled to obtain historical entity labels and historical entity relationship labels, wherein the historical entity labels and the historical entity relationship labels form a training set; Construct a neural network model, train the neural network model to convergence based on the training set, and obtain the data identification model.

3. The alarm signal filtering method for monitoring equipment according to claim 2, characterized in that, The step of sending the second data table to the user includes: Obtain the permission category of each preset tag in the second data table, and determine whether a preset category exists in each of the permission categories; If so, the first target sub-data of the corresponding preset label is encrypted, and the second data table is updated.

4. The alarm signal filtering method for monitoring equipment according to claim 3, characterized in that, The step of determining whether the monitoring device has any abnormalities based on the second target sub-data includes: Based on the second target sub-data, obtain the corresponding target label and target entity label; Based on the target tag and the target entity tag, obtain the matching evaluation rules, and call the preset conditions in the evaluation rules; Determine whether the second target sub-data satisfies the preset condition; If not, an exception label will be output to indicate that there is an abnormal situation with the monitoring equipment.

5. The alarm signal filtering method for monitoring equipment according to claim 4, characterized in that, The step of determining the measure tag based on the second target sub-data and the associated sub-data, and filling the measure tag into the measure access bit, includes: Obtain the anomaly tags and determine whether the number of anomaly tags is unique; If not, determine whether there is a combination relationship between the abnormal tags; If so, the corresponding exception tags are merged to generate the measure tag.

6. A monitoring equipment alarm signal filtering system, characterized in that, The system is used to implement the monitoring equipment alarm signal filtering method as described in any one of claims 1-5, the system comprising: The tag determination module is used to acquire business data in real time, input the business data into the data identification model, and obtain the tags of all sub-data in the business data, wherein the tags include entity tags and entity relationship tags; The first data table generation module is used to determine the target entity label based on the labels of all sub-data in the business data, and generate a corresponding first data table based on each target entity label. The first data table includes at least each preset label and the sub-data access position corresponding to each preset label. The first data table generation module also includes: An extension unit is used to extend the first data table according to each of the target entity tags to obtain a second data table, wherein the second data table further includes at least a target preset tag and a measure access bit corresponding to the target preset tag; The matching module is used to match the entity tags and entity relationship tags in the corresponding business data according to each of the preset tags, and to obtain the corresponding first target sub-data according to the entity tags and entity relationship tags, and fill it into the corresponding sub-data access position; The acquisition module is used to acquire target tags from each of the preset tags in the first data table, and determine second target sub-data based on the target tags; The judgment module is used to determine whether there is any abnormality in the monitoring equipment based on the second target sub-data; The sending module is used to send a second data table to the user when there is an abnormal situation in the monitoring equipment; The monitoring equipment alarm signal filtering system also includes: The entity tag determination module is used to determine the entity tag corresponding to the second target sub-data based on the second target sub-data when it is determined that there is an abnormal situation in the monitoring device; The matching module is used to match the corresponding associated entity tags based on the entity tags corresponding to the second target sub-data, and call the target data table generated by the associated entity tags; The associated sub-data acquisition module is used to determine the preset tag associated with the entity tag corresponding to the second target sub-data in the target data table, and to acquire the corresponding associated sub-data; The measure label determination module is used to determine the measure label based on the second target sub-data and the associated sub-data, and fill the measure label into the measure access position.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the alarm signal filtering method for monitoring equipment as described in any one of claims 1-5.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the alarm signal filtering method for monitoring equipment as described in any one of claims 1-5.

Images