CN114818652A - Alarm information processing method and device, electronic equipment and storage medium - Google Patents
Alarm information processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114818652A CN114818652A CN202210354293.8A CN202210354293A CN114818652A CN 114818652 A CN114818652 A CN 114818652A CN 202210354293 A CN202210354293 A CN 202210354293A CN 114818652 A CN114818652 A CN 114818652A
- Authority
- CN
- China
- Prior art keywords
- alarm
- model
- information
- vector
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides an alarm information processing method, an alarm information processing device, electronic equipment and a storage medium, wherein the alarm information processing method firstly acquires corpus data configured in a monitoring system; then, based on a pre-training model, obtaining a plurality of characteristic vectors of the corpus data; then establishing an alarm vector model aiming at a plurality of feature vectors; and finally, carrying out similarity calculation on the real-time alarm information and the alarm vector model, and if the maximum value of the similarity is greater than a threshold value N, selecting trigger information corresponding to the maximum value of the similarity as the associated information of the current real-time alarm information. The invention can reduce the manual alarm association information setting, improve the operation and maintenance work efficiency and improve the alarm processing efficiency.
Description
Technical Field
The present application relates to the field of monitoring alarms, and in particular, to an alarm information processing method and apparatus, an electronic device, and a storage medium.
Background
The monitoring system is an indispensable system for each enterprise, can help people to discover the service operation condition in time, can handle in time when abnormal, and is an indispensable part for improving the enterprise intellectualization.
The alarm information processing is an important link of daily operation and maintenance monitoring, and currently, it is a common practice that in a monitoring system, alarm receiver information is set individually according to each alarm item, and after a fault occurs, alarm information is sent to a receiver through various communication media.
The method is controllable under the condition that the number of the monitoring alarm items is not large, but reduces the operation and maintenance efficiency by manual independent setting after the number of the monitoring alarm items and the alarm items is in the order of thousands of items.
Disclosure of Invention
The invention provides an alarm information processing method, an alarm information processing device, electronic equipment and a storage medium, which can automatically judge and trigger alarm associated information, further reduce artificial alarm associated information setting and improve operation and maintenance working efficiency.
In a first aspect, an embodiment of the present invention provides an alarm information processing method, where the processing method includes:
acquiring configured corpus data in a monitoring system;
acquiring a plurality of feature vectors of the corpus data based on a pre-training model;
establishing an alarm vector model for a plurality of the feature vectors;
and performing similarity calculation on the real-time alarm information and the alarm vector model, and if the maximum value of the similarity is greater than a threshold value N, selecting trigger information corresponding to the maximum value of the similarity as the associated information of the current real-time alarm information.
Optionally, the obtaining a plurality of feature vectors of the corpus data based on the pre-training model includes:
loading a pre-training model and configuring a model information flow structure;
performing word segmentation on the corpus data to obtain input _ ids and segments; when the word segmentation is carried out on the material data, a token dictionary built in a bert is adopted for realizing the input of sentences with the same length;
and inputting input _ ids and segments into a pre-training model to obtain the feature vector.
Optionally, the loading the pre-training model and configuring the model information flow structure includes:
loading the pre-training model is realized through a load _ trained _ model _ from _ check () function; get _ layer () function according to its index to obtain the weight of all layers of model and store it in output _ layer list;
and configuring a model information flow structure, and establishing a function chain model by taking the pre-training model as a layer input and the output _ layer as an output.
Optionally, the obtaining input _ ids and segments by performing word segmentation on the corpus data includes:
tokenize () is used for carrying out word segmentation on corpus data, and the corpus data is changed into tokens;
converting the token into a format to obtain input _ ids and segments, wherein the input _ ids represents that each token is converted into a corresponding index, and the segments represent statements to which words at positions corresponding to the indexes belong.
Optionally, the token is converted into a format to obtain input _ ids and segments, and the input _ ids and the segments are realized through a method token. Setting the maximum sequence length of a statement in a token.
Optionally, the alarm vector model is established for a plurality of feature vectors, and the alarm vector model is obtained by performing a feature vector matrix serialization operation.
Optionally, in the similarity calculation of the real-time alarm information and the alarm vector model, a cosine similarity algorithm is used to calculate the similarity between the feature vector of the real-time alarm information and each trigger vector in the alarm vector model, where the cosine similarity algorithm has a formula:
and theta is an included angle between the vector A and the vector B, Ai represents information of each trigger in the alarm vector model, and Bi represents current real-time alarm information.
In a second aspect, an embodiment of the present invention provides an alert information processing apparatus including:
the data acquisition module is used for acquiring corpus data;
the data processing module is used for analyzing and processing the corpus data to obtain a plurality of characteristic vectors of the corpus data and establishing an alarm vector model aiming at the plurality of characteristic vectors;
and the analysis processing module is used for carrying out similarity calculation on the real-time alarm information and the alarm vector model, and selecting trigger information corresponding to the maximum similarity value as the associated information of the current real-time alarm information if the maximum similarity value is greater than a threshold value N.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program thereon, and the processor implements the method according to any one of the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the invention provides a computer-readable storage medium on which is stored a computer program which, when executed by a processor, implements the method of any one of the first aspects.
Advantageous effects
The invention provides an alarm information processing method, an alarm information processing device, electronic equipment and a storage medium, which can convert corpus data into a plurality of corresponding characteristic vectors by utilizing a pre-training model, establish an alarm vector model for the plurality of characteristic vectors, finally judge by setting a similarity threshold value N directly through comparing the similarity between real-time alarm information and the alarm vector model, and select trigger information corresponding to the value with the maximum similarity as the associated information of the real-time alarm information if the maximum similarity is greater than the similarity threshold value N. The alarm associated information can be automatically judged and triggered, so that the manual setting of the alarm associated information can be reduced, and the operation and maintenance working efficiency is improved.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of any embodiment of the invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present invention will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements.
FIG. 1 shows a flow diagram of an alert information processing method of an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an alarm information processing apparatus according to an embodiment of the present invention;
fig. 3 shows a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.
It should be noted that, the description of the embodiment of the present invention is only for clearly illustrating the technical solutions of the embodiment of the present invention, and does not limit the technical solutions provided by the embodiment of the present invention.
FIG. 1 illustrates a flow diagram of a method for training a character recognition model, in accordance with an embodiment of the present invention; referring to fig. 1, the training method includes:
s1, obtaining configured corpus data in a monitoring system;
the corpus data mainly takes a text data format as a main part, and comprises trigger alarm configuration information configured in a monitoring system, wherein the trigger alarm configuration information is a logic expression for evaluating data acquired by a project and representing the current system condition, so that people know that something happens and possibly needs to be noticed, and comprises information such as a trigger name (namely an alarm name), an alarm host, alarm receiver information, a fault processing mode and the like;
s2, acquiring a plurality of feature vectors of the corpus data based on a pre-training model;
specifically, a feature vector is obtained based on the natural language keras-bert;
wherein, the obtaining of the plurality of feature vectors of the corpus data based on the pre-training model includes:
s21, loading a pre-training model and configuring a model information flow structure;
the pre-training model uses a pre-training model which is downloaded locally, such as a Google BERT model and a Chinese pre-training BERT model;
specifically, the loading the pre-training model and configuring the model information flow structure includes:
s211, loading a pre-training model through a load _ trained _ model _ from _ check () function; get _ layer () function according to its index to obtain the weight of all layers of model and store it in output _ layer list;
in the initialization stage of the loading model, traversing the number of network layers according to the number n of the user-defined network layers, wherein n is greater than 0; the index is based on the order of horizontal graph traversal (bottom-up);
s212, configuring a model information flow structure, and establishing a function chain model to realize the function chain model by taking a pre-training model as one layer input and an output _ layer as output; model (inputs ═ input _ layer, outputs ═ output _ layer);
s22, segmenting the corpus data to obtain input _ ids and segments; when the word segmentation is carried out on the material data, a token dictionary built in a bert is adopted for realizing the input of sentences with the same length;
specifically, the obtaining input _ ids and segments by segmenting the corpus data includes:
s221, segmenting the corpus data by using a method token, token () and changing the corpus data into tokens; generally, the words are mainly segmented from three granularities of words, words and phrases, wherein the words comprise BPE, WordPieces and the like, the main purpose is to carry out independent carrying of some words with uniform high frequency, such as prefixes at the beginning of de in english, or top-level est and the like, the words are generally automatically learned on large-scale linguistic data through statistical frequency, specifically, texts are often input in batches in actual use, the lengths of the texts are different, but the lengths of sentences input by Bert are the same, in order to realize the process, when segmenting the linguistic data, a Token dictionary with built-in Bert is adopted for realizing the input of the sentences with the same length, such as [ UNK ] [ CLS ] [ SEP ] [ MASK ] and the like, wherein [ UNK ] represents unrecognized Token, UNK ] is Unknown, and words which do not appear in the Bert dictionary are replaced by the Token; [ PAD ] represents padding oken, only the data of the maximum sequence length in the sequence is reserved when the sentence length is larger than the maximum sequence length, if the sentence length is smaller than the maximum sequence length, the [ PAD ] is used for padding, the [ PAD ] is generally placed at the first position of a word list, index is 0, and bit padding is carried out by using [0 ]; because the text classification belongs to a sequence level task, a [ CLS ] zone bit is added in front of the current sequence, and the classifier with customized output corresponding to the [ CLS ] zone bit is output for classification; [ SEP ] indicates that a text with two sentences is concatenated into an input sequence, and the Token is inserted between the two sentences as a partition, for example, the input text is "ad slot display statistical anomaly", and a Token list is obtained after splitting a word example: [ '[ CLS ]', 'broadly', 'advertisement', 'place', 'spread', 'now', 'system', 'meter', 'iso', 'normal', '[ SEP ]' ];
then, Token needs to be converted into a certain form of input, that is, the format of Token needs to be converted, which may be the Token sequence itself, or the Token may be converted into a number;
s222, converting the tokens into formats to obtain input _ ids and segments, wherein the input _ ids represents that each token is converted into a corresponding index, and the segments represent sentences to which words at positions corresponding to the indexes belong;
specifically, input _ ids and segments are obtained after token is converted into a format, and the method is realized through token. Setting the maximum sequence length of a statement in a token/encode () function, using PAD (PAD application data) filling if the length is insufficient, and otherwise, cutting the length;
taking the conversion into numbers as an example: for each token character, it can be converted into an integer representing its position in the vocabulary; input _ ids obtained after converting the token into a format is shown as [101,2408,1440,855,2245,4385,5320,6369,2460,2382], and segments are shown as [0,0,0,0,0,0 ];
s23, inputting input _ ids and segments into a pre-training model to obtain the feature vector;
specifically, input _ ids and segments are input into a model prediction method of a pre-training model to obtain a feature vector; s3, establishing an alarm vector model aiming at the plurality of feature vectors;
specifically, an alarm vector model is established for a plurality of eigenvectors, and the alarm vector model is obtained by performing serialization operation on eigenvector matrixes;
s4, similarity calculation is carried out on the real-time alarm information and the alarm vector model, and if the maximum value of the similarity is larger than a threshold value N, trigger information corresponding to the maximum value of the similarity is selected and is related information of the current real-time alarm information; if the maximum value of the similarity is smaller than the threshold value N, informing a responsible person to perfect the alarm correlation information;
specifically, in the similarity calculation of the real-time alarm information and the alarm vector model, a cosine similarity algorithm is used to calculate the similarity between the feature vector of the real-time alarm information and each trigger vector in the alarm vector model, and the cosine similarity algorithm formula is as follows:
and theta is an included angle between the vector A and the vector B, Ai represents information of each trigger in the alarm vector model, and Bi represents current real-time alarm information.
Specifically, the feature vector of the real-time alarm information is obtained through the natural language keras-bert.
The similarity obtained by the cosine similarity algorithm is sorted according to the sequence of similarity values from large to small, so that the extraction of the maximum value of the similarity is facilitated.
The invention provides an alarm information processing method, which can convert corpus data into a plurality of corresponding characteristic vectors by utilizing a pre-training model, establish an alarm vector model for the plurality of characteristic vectors, finally judge by directly comparing the similarity between real-time alarm information and the alarm vector model and setting a similarity threshold value N, and select trigger information corresponding to the value with the maximum similarity as the associated information of the real-time alarm information if the maximum similarity is greater than the similarity threshold value N. The alarm associated information can be automatically judged and triggered, so that the manual setting of the alarm associated information can be reduced, and the operation and maintenance working efficiency is improved.
Fig. 2 shows a block diagram of an alarm information processing apparatus according to an embodiment of the present invention. As shown in fig. 2, the warning information processing apparatus includes:
the data acquisition module 10 is used for acquiring corpus data;
the data processing module 20 is configured to analyze and process the corpus data to obtain a plurality of feature vectors of the corpus data, and establish an alarm vector model for the plurality of feature vectors;
and the analysis processing module 30 is configured to perform similarity calculation on the real-time alarm information and the alarm vector model, and if the maximum similarity is greater than the threshold N, select trigger information corresponding to the maximum similarity, which is the associated information of the current real-time alarm information.
The embodiment of the invention provides an alarm information processing device, which firstly obtains corpus data through a data obtaining module 10, then obtains a plurality of characteristic vectors of the corpus data through a data processing module 20 by analyzing the corpus data, establishes an alarm vector model aiming at the plurality of characteristic vectors, comprises a plurality of trigger vectors in the alarm vector model, can also obtain real-time alarm information through the data obtaining module 10, mainly obtains an alarm name in the real-time alarm information, obtains the characteristic vector of the real-time alarm information through the data processing module 20, carries out similarity calculation on the characteristic vector of the real-time alarm information and each trigger vector in the alarm vector model through an analyzing and processing module 30, and sets a similarity threshold N for judgment: and if the maximum similarity is greater than the threshold N, selecting trigger information corresponding to the maximum similarity, wherein the trigger information is the associated information of the current real-time alarm information. The real-time alarm information (alarm name) and the trigger information can be automatically identified and matched without manual setting, so that the labor consumption is reduced, and the working efficiency is improved.
An electronic device according to an embodiment of the present invention is also provided, fig. 3 shows a schematic structural diagram of an electronic device to which an embodiment of the present invention can be applied, as shown in fig. 3, a computer electronic device, and fig. 3 shows a schematic structural diagram of an electronic device to which an embodiment of the present invention can be applied, as shown in fig. 3, the computer electronic device includes a Central Processing Unit (CPU)401 that can execute various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for system operation are also stored. The CPU 401, ROM 402, and RAM403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware. The described units or modules may also be provided in a processor, and may be described as: a processor comprises a data acquisition module 10, a data processing module 20 and an analysis processing module 30, wherein the names of the modules do not form a limitation to the modules, for example, the data processing module 20 can be further described as a data processing module for analyzing and processing the corpus data to obtain an alarm vector model of the data.
As another aspect, the present invention also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the warning information processing apparatus described in the above embodiments; or it may be a computer-readable storage medium that exists separately and is not built into the electronic device. The computer readable storage medium stores one or more programs for use by one or more processors in performing an alert information processing method described in the present invention.
The foregoing description is only exemplary of the preferred embodiments of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features and (but not limited to) features having similar functions disclosed in the present invention are mutually replaced to form the technical solution.
Claims (10)
1. An alarm information processing method is characterized in that: the method comprises the following steps:
acquiring configured corpus data in a monitoring system;
acquiring a plurality of feature vectors of the corpus data based on a pre-training model;
establishing an alarm vector model for a plurality of the feature vectors;
and performing similarity calculation on the real-time alarm information and the alarm vector model, and if the maximum value of the similarity is greater than a threshold value N, selecting trigger information corresponding to the maximum value of the similarity as the associated information of the current real-time alarm information.
2. The alarm information processing method according to claim 1, wherein:
the obtaining of the plurality of feature vectors of the corpus data based on the pre-training model includes:
loading a pre-training model and configuring a model information flow structure;
performing word segmentation on the corpus data to obtain input _ ids and segments; when the words are segmented for the material data, a token dictionary built in a bert is adopted for realizing the input of sentences with the same length;
and inputting input _ ids and segments into a pre-training model to obtain the feature vector.
3. The warning information processing method according to claim 2, wherein:
the loading of the pre-training model and configuring the model information flow structure comprises:
loading the pre-training model is realized through a load _ trained _ model _ from _ check () function; get _ layer () function according to its index to obtain the weight of all layers of model and store it in output _ layer list;
and configuring a model information flow structure, and establishing a function chain model by taking the pre-training model as a layer input and the output _ layer as an output.
4. The warning information processing method according to claim 2, wherein:
the word segmentation of the corpus data to obtain input _ ids and segments comprises the following steps:
tokenize () is used for carrying out word segmentation on corpus data, and the corpus data is changed into tokens;
converting the tokens into formats to obtain input _ ids and segments, wherein the input _ ids represents that each token is converted into a corresponding index, and the segments represent statements to which words at corresponding positions of the indexes belong.
5. The warning information processing method according to claim 4, wherein:
converting the token into a format to obtain input _ ids and segments, and realizing the input _ ids and the segments through a method token. Setting the maximum sequence length of a statement in a token.
6. The alarm information processing method according to claim 1, wherein:
and establishing an alarm vector model aiming at the plurality of characteristic vectors, and obtaining the alarm vector model through characteristic vector matrix serialization operation.
7. The alarm information processing method according to claim 1, wherein:
in the similarity calculation of the real-time alarm information and the alarm vector model, a cosine similarity algorithm is adopted to calculate the similarity between the feature vector of the real-time alarm information and each trigger vector in the alarm vector model, and the cosine similarity algorithm formula is as follows:
and theta is an included angle between the vector A and the vector B, Ai represents information of each trigger in the alarm vector model, and Bi represents current real-time alarm information.
8. An alert information processing apparatus characterized by comprising:
the data acquisition module is used for acquiring corpus data;
the data processing module is used for analyzing and processing the corpus data to obtain a plurality of characteristic vectors of the corpus data and establishing an alarm vector model aiming at the plurality of characteristic vectors;
and the analysis processing module is used for carrying out similarity calculation on the real-time alarm information and the alarm vector model, and selecting trigger information corresponding to the maximum similarity value as the associated information of the current real-time alarm information if the maximum similarity value is greater than a threshold value N.
9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, characterized in that:
the processor, when executing the computer program, implements the method of any of claims 1-7.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the method is characterized in that:
the computer program, when executed by a processor, implements the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354293.8A CN114818652A (en) | 2022-04-06 | 2022-04-06 | Alarm information processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354293.8A CN114818652A (en) | 2022-04-06 | 2022-04-06 | Alarm information processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114818652A true CN114818652A (en) | 2022-07-29 |
Family
ID=82532221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210354293.8A Pending CN114818652A (en) | 2022-04-06 | 2022-04-06 | Alarm information processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114818652A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980181A (en) * | 2023-06-21 | 2023-10-31 | 江南信安（北京）科技有限公司 | Method and system for detecting associated alarm event |
| CN116991684A (en) * | 2023-08-03 | 2023-11-03 | 北京优特捷信息技术有限公司 | Alarm information processing method, device, equipment and medium |
-
2022
- 2022-04-06 CN CN202210354293.8A patent/CN114818652A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980181A (en) * | 2023-06-21 | 2023-10-31 | 江南信安（北京）科技有限公司 | Method and system for detecting associated alarm event |
| CN116980181B (en) * | 2023-06-21 | 2024-02-20 | 江南信安（北京）科技有限公司 | Method and system for detecting associated alarm event |
| CN116991684A (en) * | 2023-08-03 | 2023-11-03 | 北京优特捷信息技术有限公司 | Alarm information processing method, device, equipment and medium |
| CN116991684B (en) * | 2023-08-03 | 2024-01-30 | 北京优特捷信息技术有限公司 | Alarm information processing method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110472090B (en) | Image retrieval method based on semantic tags, related device and storage medium | |
| CN110705301B (en) | Entity relationship extraction method and device, storage medium and electronic equipment | |
| CN114818652A (en) | Alarm information processing method and device, electronic equipment and storage medium | |
| CN110580308B (en) | Information auditing method and device, electronic equipment and storage medium | |
| CN107291775B (en) | Method and device for generating repairing linguistic data of error sample | |
| CN111866004B (en) | Security assessment method, apparatus, computer system, and medium | |
| CN112347223B (en) | Document retrieval method, apparatus, and computer-readable storage medium | |
| CN113254643B (en) | Text classification method and device, electronic equipment and text classification program | |
| CN113590764B (en) | Training sample construction method and device, electronic equipment and storage medium | |
| CN113806580B (en) | Cross-modal hash retrieval method based on hierarchical semantic structure | |
| CN107291774B (en) | Error sample identification method and device | |
| CN112036168A (en) | Event subject recognition model optimization method, device and equipment and readable storage medium | |
| CN114416979A (en) | Text query method, text query equipment and storage medium | |
| CN113282433B (en) | Cluster anomaly detection method, device and related equipment | |
| CN111782811A (en) | E-government affair sensitive text detection method based on convolutional neural network and support vector machine | |
| CN116910599A (en) | Data clustering method, system, electronic equipment and storage medium | |
| CN111581377A (en) | Text classification method and device, storage medium and computer equipment | |
| CN115563985A (en) | Statement analysis method, statement analysis device, statement analysis apparatus, storage medium, and program product | |
| CN115080745A (en) | Multi-scene text classification method, device, equipment and medium based on artificial intelligence | |
| KR20050033852A (en) | Apparatus, method, and program for text classification using frozen pattern | |
| CN113987180A (en) | Method and apparatus for outputting information and processing information | |
| CN114417029A (en) | Model training method and device, electronic equipment and storage medium | |
| CN115618968B (en) | New idea discovery method and device, electronic device and storage medium | |
| CN112906726B (en) | Model training method, image processing device, computing equipment and medium | |
| CN114218384A (en) | Corpus classification method, model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |