CN110598645B - Method for rapidly repairing faults and risks of information system - Google Patents
Method for rapidly repairing faults and risks of information system Download PDFInfo
- Publication number
- CN110598645B CN110598645B CN201910874195.5A CN201910874195A CN110598645B CN 110598645 B CN110598645 B CN 110598645B CN 201910874195 A CN201910874195 A CN 201910874195A CN 110598645 B CN110598645 B CN 110598645B
- Authority
- CN
- China
- Prior art keywords
- alarm
- information
- text
- similar
- repairing
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000008439 repair process Effects 0.000 claims description 43
- 230000011218 segmentation Effects 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000012015 optical character recognition Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 description 24
- 238000012423 maintenance Methods 0.000 description 7
- 230000000692 anti-sense effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005067 remediation Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- 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
- G06F40/216—Parsing using statistical methods
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/26—Techniques for post-processing, e.g. correcting the recognition result
- G06V30/262—Techniques for post-processing, e.g. correcting the recognition result using context analysis, e.g. lexical, syntactic or semantic context
- G06V30/274—Syntactic or semantic context, e.g. balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method for rapidly repairing faults and risks of an information system, which comprises the following steps: step 1, acquiring text image information containing alarm information; step 2, identifying alarm information in the text image information, generating text alarm information and displaying the text alarm information; step 3, searching alarm information, generating a similar alarm record and a historical alarm record and a repairing scheme thereof, and sending the similar alarm record and the historical alarm record; step 4, displaying similar alarm records and historical alarm records and repairing schemes thereof to the user; step 5, repairing equipment alarms according to the similar alarms and/or the repairing schemes of the historical alarms; and 6, recording alarm information and a repairing scheme.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method for rapidly repairing faults and risks of an information system.
Background
Currently, we are in the information age, and many industries depend on information systems. The information system (Information system) is a man-machine integrated system composed of computer hardware, network and communication devices, computer software, information resources, information users and regulations for the purpose of processing information streams. In order to ensure the normal operation of the information system, operation and maintenance personnel and an operation and maintenance system are required. When the operation and maintenance system detects the faults and risks of the information system, an alarm is generated, and operation and maintenance personnel are notified in the modes of sound and light, a webpage, a short message, an email, an instant messaging tool, a printed body work order and the like, wherein the content of the alarm generally comprises: the time at which the failure and risk occur, the address of the device at which the failure and risk occur, the cause of the failure and risk, etc. The operation and maintenance personnel usually need to search for the solution of the alarm by inquiring a technical manual, internet web pages, consulting other people and the like by depending on working experience, and then implement alarm repair. The repairing method has the following problems that the repairing method is seriously dependent on experience of operation and maintenance personnel, the efficiency of inquiring technical manuals and manually inputting alarm information is low, web page results of internet searching are required to be selected, the repairing is incorrect and untimely, the normal operation of an enterprise information system is affected, and huge economic loss and negative influence are brought to enterprises in serious cases.
In order to solve the problems, the invention provides a method for quickly repairing faults and risks of an information system.
Disclosure of Invention
The invention is realized by adopting the following technical scheme:
a method of quickly repairing alarms of faults and risks of an information system, comprising the steps of:
step 1, acquiring text image information of alarm information of faults and risks of an information system;
step 2, identifying alarm information in the text image information, generating text alarm information and displaying the text alarm information;
step 3, retrieving alarm description information, generating a similar alarm record and a historical alarm record and a repairing scheme thereof, and sending the similar alarm record and the historical alarm record;
step 4, displaying similar alarm records and historical alarm records and repairing schemes thereof to the user;
step 5, repairing equipment alarms according to the similar alarms and/or the repairing schemes of the historical alarms;
and 6, recording alarm information and a repairing scheme of the information system.
The method comprises the following steps of (1) acquiring text image information containing alarm information by the following steps: the electronic equipment scans or photographs the alarming text information on the alarming equipment to obtain image information; or screen capturing is carried out on the text information displayed on the electronic equipment to obtain image information; or by the electronic device from other devices communicatively connected thereto.
The method, wherein the step 2 of identifying the alarm information in the image information to generate and display the alarm description information includes: the electronic equipment analyzes the image information obtained in the step 1, determines the text information therein and identifies the text information, and generates display data, wherein the display data comprises the identification result of the text information.
The method comprises the following steps: the electronic equipment utilizes an optical character recognition method to recognize the character information, and a primary recognition result is generated; and then extracting the alarm occurrence time in the primary identification result through semantic analysis, and generating an identification result of text information by the equipment address and the alarm reason of the alarm occurrence to generate display data.
The method, wherein retrieving the alarm description information in step 3, generating the similar alarm record and the history alarm record includes: the electronic equipment sends the alarm information generated in the step 2 to a server through a network; the server acquires the similar alarm record and the historical alarm record of the alarm device and the alarm repair scheme thereof by inquiring the knowledge base, and then sends the similar alarm record and the historical alarm record of the alarm device and the alarm repair scheme thereof to the electronic device through the network.
The method comprises the following steps: querying similar alert records includes: firstly, dividing words and filtering invalid words of an alarm reason, then inquiring an error code dictionary in a knowledge base to check whether the alarm reason contains an error code of an information system, and processing according to two conditions: 1) If the error code of the information system is contained, retrieving the knowledge base according to the error code; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type; aiming at the error code condition of an information system contained in the alarm reasons, two conditions are treated: 1) If the search result exists, the search result is fed back to the user in a descending order according to the result satisfaction degree, wherein the result satisfaction degree is obtained by fitting calculation according to the click check times of the search result and the times of applying the repair scheme; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type.
The method comprises the following steps: checking whether the alarm reasons contain equipment type conditions according to equipment type dictionaries in the query knowledge base, and processing according to two conditions: 1) If the equipment type is contained, traversing a knowledge base according to the equipment type, and calculating the similarity of the alarm reasons; 2) Otherwise, traversing the full knowledge base, and calculating the similarity with the alarm reason information; for the case of containing the device type, two cases are handled: 1) If the search result exists, feeding back to the user in descending order according to the similarity of the alarm reasons; 2) Otherwise, traversing the full knowledge base, and calculating the similarity of the alarm reasons; inquiring the alarm reasons and the repaired alarms containing one or more word segmentation results in the alarm repair scheme in a knowledge base, calculating the similarity value of the alarms according to a text similarity algorithm, setting a similarity threshold, and transmitting the alarm records and the alarm repair scheme higher than the threshold to the electronic equipment; the alarm reason similarity adopts a semantic cosine similarity algorithm.
The method comprises the following steps of: the electronic equipment responds to the detection of an operation instruction of a user on the currently presented similar alarm record, and judges whether clicking operation on the similar alarm record exists or not; and responding to the fact that the judgment result is yes, presenting details of similar alarms, wherein the details of the similar alarms comprise: the time of alarm occurrence, the address of the equipment where the alarm occurs, the reason of the alarm, the name and contact of the alarm repairing person, the alarm repairing time and the alarm repairing scheme.
The method comprises the following steps of: the electronic equipment responds to the detection of an operation instruction of a user on the currently presented historical alarm record, and judges whether clicking operation is carried out on the historical alarm record or not; in response to the determination that the history alert is yes, presenting details of the history alert, the details of the history alert including: the time of alarm occurrence, the address of the equipment where the alarm occurs, the reason of the alarm, the name and contact of the alarm repairing person, the alarm repairing time and the alarm repairing scheme.
In the method, in the step 5, the user executes alarm repair according to a similar alarm repair scheme and/or a historical alarm repair scheme with high similarity, and the user inputs the solution and repair time after repairing the alarm and sends the solution and repair time to the server.
In the method, in step 6, the server records information of the current equipment alarm in a database, and the method comprises the following steps: the method comprises the steps of text image information of a current alarm, the occurrence time of the identified alarm, the address of equipment for generating the alarm, the reason of the alarm, and the solution and repair time recorded after the user repairs the alarm.
The method comprises the following steps of:
1) The method comprises the steps of performing text word segmentation on alarm reasons to be queried and a plurality of alarm reasons in a knowledge base;
2) Constructing a word segmentation result set, and respectively taking a union of the alarm reasons to be queried and the alarm reason word segmentation results of the knowledge base;
3) Counting word frequency vectors, respectively traversing an alarm reason word segmentation set to be queried and an alarm reason word segmentation set in a knowledge base, setting 1 if the word segmentation is in a union set of the alarm reason word segmentation set to be queried and the knowledge base, otherwise setting 0 to obtain word segmentation vectors of alarm reason word segmentation results of the alarm reason to be queried and the knowledge base;
4) And calculating the cosine included angle value of the vectors, and evaluating the similarity of the alarm reasons to be queried and the information base by calculating the cosine value of the included angle of each alarm reason of the two vectors. 13. The method of one of claims 12, wherein calculating using a semantic-based cosine similarity algorithm further comprises:
5) Calculating semantic similarity: let the semantic similarity symbol be R, defined as: antisense, uncertain and near sense, and take the values as follows: r= -1, antisense; r=1, indeterminate; r=2, proximal. The calculation process is as follows: extracting verbs and adjectives in the alarm reason word segmentation result, then querying a hyponym dictionary and an anticnym dictionary, and if the verbs and the adjective dictionary are simultaneously present in the hyponym dictionary, then obtaining hyponym semantics; if the simultaneous occurrence in the anti-ambiguous word dictionary is, then it is anti-ambiguous; otherwise, it is uncertain semantics;
the alarm similarity is calculated, and the calculation formula is as follows: sim=r×cos (θ), where R is defined as semantic similarity, where Cos (θ) is defined as vector cosine included angle value.
The method comprises the following steps:
wherein X and Y represent vectors, and X and Y represent the modulus of the vectors X and Y, X i And y i Representing the components of vectors X and Y.
Drawings
FIG. 1 is a system block diagram of the present invention;
FIG. 2 is a flow chart of the alarm repair of the present invention;
FIG. 3 is an image of the warning message of the present invention;
FIG. 4 is a diagram showing the result of identifying the alarm information according to the present invention;
FIG. 5 is similar alarm details of the present invention;
FIG. 6 is a diagram of historical alert information of the present invention;
FIG. 7 is a schematic diagram of the alarm similarity calculation process of the present invention.
Detailed Description
The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates a system architecture 100 to which the method of quickly repairing alarms of faults and risks of an information system of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminals 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium for providing communication links between the terminals 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 105 via a network using the terminals 101, 102, 103 to receive and send messages. The terminals 101, 102, 103 may install various client applications such as web browsers, instant messaging tools, text image recognition type applications, shopping type applications, etc. In addition, the terminals 101, 102, 103 may perform recognition analysis on text information included in text image information acquired by the user therethrough, and feed back analysis results (e.g., generated presentation data) to the user.
The background server may analyze the request instruction transmitted by the application on the terminal 101, 102, 103 and may transmit the processing result (such as response information related to the request instruction) to the terminal 101, 102, 103.
The server 105 may be a server providing various services, such as providing a text image recognition service to applications on the terminals 101, 102, 103.
It should be noted that, the method for repairing the alarm information provided in the embodiments of the present application is generally executed by the terminals 101, 102, 103 and the server 105, and accordingly, the alarm information repairing device is generally disposed in the terminals 101, 102, 103 and the server 105.
It should be understood that the number of terminals, networks and servers in fig. 1 is merely illustrative. There may be any number of terminals, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of an alert information repair method according to the present application is shown. The method may comprise the steps of:
step 201 obtains text image information of faults and risks of the information system.
In this embodiment, the alert information repair method is executed on the electronic device (for example, the terminals 101, 102, 103 shown in fig. 1) and the image information including the text information may be acquired by various methods. For example, the electronic equipment can acquire image information by scanning or photographing text information (such as alarm information generated by a monitoring platform of an information system) through an image acquisition device (such as a camera) arranged on the electronic equipment; for another example, the electronic device may obtain image information from other devices communicatively coupled thereto, such as image information sent by other devices via chat tools, and such as image information obtained from a remote database. Thus, the user can conveniently acquire the image information containing the text information in various scenes (such as on-line or off-line).
The text arranged on the image-text layout is commonly referred to as "print". The size and shape of each printed word are different, and are generally represented by word level (or word size, number of dots) and font, such as text information on paper media, billboards, etc. The non-printed text is typically text other than the printed text described above, such as text information displayed on an electronic screen or handwritten text information. Therefore, the limitation of the image information can be reduced, and the application range can be improved. In addition, the content of the text information may include one or more characters of numerals, letters, symbols, kanji, and the like.
In the present embodiment, the image information 300 acquired in step 201 is as shown in fig. 3, and the image includes and is not limited to only the content shown in 301, including: the time at which the alarm occurred, the address of the device at which the alarm occurred, and the reason for the alarm.
In this embodiment, first, the electronic device may analyze the image information acquired in step 201 to determine text information therein. Then, the text information can be identified by using a common text identification method to generate display data. The presentation data may include a recognition result of the text information.
In some optional implementations of the present embodiments, first, the electronic device may identify the text information using an optical character recognition (OCR, optical Character Recognition) method to generate a primary recognition result; then, the alarm occurrence time in the primary recognition result can be extracted through semantic analysis (such as regular expressions, vocabulary dictionary, error code dictionary and the like), and the recognition result of the text information is generated by the device address where the alarm occurs and the alarm reason, so as to generate the display data.
In this embodiment, the electronic device sends the alert information generated in step 202 to the server 105 through the network. The server 105 then obtains similar alarm records and historical alarm records for the alarm device by querying the knowledge base. The server then sends the similar alert record and the historical alert record for the alert device and its alert solutions to the electronic device over the network.
In some alternative implementations of this embodiment, querying the similar alert record may be first performing word segmentation on the alert cause and filtering the invalid words, for example, word segmentation results of "Oracle buffer hit rate exceeds" such as Oracle, buffer, hit rate, exceeds, then querying the database for the alert cause and the repaired alert containing one or more word segmentation results in the alert repair scheme, and then calculating the similarity value of the alert according to the alert similarity algorithm. Finally, descending order according to the similarity. To reduce the number of similar alarm records presented, a similarity threshold may be set, below which alarm records will be discarded from being sent to the electronic device. Here, word segmentation, i.e., word Segmentation, generally refers to the segmentation of a character sequence into individual words. The word segmentation is the basis of text mining, and the word segmentation is successfully carried out on a section of input characters, so that the effect of automatically identifying sentence meaning by a computer can be achieved.
In this embodiment, as shown in fig. 7, the process of querying the similar alarm records is to firstly perform word segmentation and invalid word filtering on the alarm reasons, and then query the error code dictionary in the knowledge base to check whether the alarm reasons contain the error codes of the information system, and the two cases are processed: 1) If the error code of the information system is contained, retrieving the knowledge base according to the error code; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type. Aiming at the error code condition of an information system contained in the alarm reasons, two conditions are treated: 1) If the search result is found out in the knowledge base, the knowledge records including the same error code alarm reasons are fed back to the user in descending order according to the result satisfaction degree, wherein the result satisfaction degree is obtained by fitting calculation according to the click check times of the search result and the applied times of the repair scheme; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type. Checking whether the alarm reasons contain equipment type conditions according to equipment type dictionaries in the query knowledge base, and processing according to two conditions: 1) If the equipment type is contained, traversing a knowledge base according to the equipment type, and calculating the similarity of the alarm reasons; 2) Otherwise, traversing the knowledge base, and calculating the similarity with the alarm reason information; aiming at the situation of traversing the knowledge base according to the equipment type, two situations are treated: 1) If the search result is found out the knowledge record including the alarm reasons of the same equipment type in the knowledge base, feeding back to the user in descending order according to the similarity of the alarm reasons; 2) Otherwise, traversing the knowledge base, and calculating the similarity of the alarm reasons. And inquiring the alarm reasons and the repaired alarms containing one or more word segmentation results in the alarm repair scheme in a knowledge base, calculating the similarity value of the alarms according to a text similarity algorithm, setting a similarity threshold, and transmitting the alarm records and the alarm repair scheme higher than the threshold to the electronic equipment.
In this embodiment, the alarm cause similarity adopts a cosine similarity algorithm based on semantics, and the specific algorithm is as follows:
1) The text word segmentation of the alarm reasons, for example, the alarm reason A is the alarm to be inquired, the alarm reasons B and C are the data of the knowledge base, and the word segmentation results are as follows:
the alarm reason A is that word segmentation results of the Oracle buffer hit rate exceeding are Oracle, buffer, hit rate exceeding.
The alarm reason B is that word segmentation results of the Oracle buffer area hit rate exceeding the threshold value of 80 percent are as follows: "Oracle", "buffer", "hit rate", "exceed", "threshold", "80%".
The alarm reason C is that word segmentation results of the Oracle buffer area hit rate lower than the threshold value by 50 percent are as follows: "Oracle", "buffer", "hit rate", "below", "threshold", "50%".
2) Constructing word segmentation result sets, respectively taking a union of the alarm reasons to be queried and the alarm reason word segmentation results of the knowledge base, for example, the word segmentation result sets of the alarm reasons A and B are as follows: [ "Oracle", "buffer", "hit rate", "superscalar", "exceeding", "threshold", "80%" ],
the word segmentation result set of the alarm reasons A and C is as follows: [ "Oracle", "buffer", "hit rate", "superscalar", "below", "threshold", "50%" ]
3) And counting word frequency vectors, respectively traversing the alarm reason word segmentation set to be queried and the alarm reason word segmentation set in the knowledge base, setting to 1 if the word segmentation is in the union of the alarm reason word segmentation set and the knowledge base, and setting to 0 if the word segmentation is not in the union of the alarm reason word segmentation set and the knowledge base. For example, the word segmentation vector when the alarm reasons A and B are compared is:
alarm reason a word segmentation vector: [1,1,1,1,0,0,0]
Alarm reason B word segmentation vector: [1,1,1,0,1,1,1]
The word frequency vector when the alarm reasons A and C are compared is as follows:
alarm reason a word segmentation vector: [1,1,1,1,0,0,0]
Alarm reason C word segmentation vector: [1,1,1,0,1,1,1]
4) And calculating cosine included angle values of the vectors, and evaluating the similarity of the two vectors by calculating cosine values of included angles of the two vectors. The closer the cosine value is to 1, the more similar the two vectors are. Conversely, the closer the cosine value is to 0, the less similar the two vectors are represented.
The formula:
(wherein X and Y representVectors, X and Y represent the modulus of the vectors X and Y, X i And y i Components representing vectors X and Y).
For example, the cosine angle between alarm reasons a and B is 0.6124, and the cosine angle between alarm reasons a and C is 0.6124.
5) And calculating semantic similarity. Because the vector cosine included angle value only judges the similarity according to the character string characteristics, the judgment of semantic characteristics is lacking, and the alarm with opposite semantics is easy to have high similarity. For example: the cosine included angle value of the alarm reasons A and B is the same as the cosine included angle value of the alarm reasons A and C, but the alarm reasons A and C are antisense semantic relations. Therefore, it is necessary to judge the similarity according to the semantic features. Semantic similarity notation is R, defined as: antisense, uncertain and near sense, and take the values as follows: r= -1, antisense; r=1, indeterminate; r=2, proximal. The calculation process is as follows: extracting verbs and adjectives in the alarm reason word segmentation result, then querying a hyponym dictionary and an anticnym dictionary, and if the verbs and the adjective dictionary are simultaneously present in the hyponym dictionary, then obtaining hyponym semantics; if the simultaneous occurrence in the anti-ambiguous word dictionary is, then it is anti-ambiguous; otherwise, the semantics are uncertain. For example: the semantic similarity r=2 of the alarm cause a and the alarm B, and the semantic similarity r= -1 of the alarm cause a and the alarm C.
The alarm similarity is calculated, and the calculation formula is as follows: sim=r×cos (θ), where R is defined as semantic similarity. Where Cos (θ) is defined as the vector cosine angle value. For example: the similarity of the alarm causes a and B is equal to sim=2× 0.6124 = 1.2248, and the similarity of the alarm causes a and C is equal to sim= -1× 0.6124 = -0.6124. The alarm reason B is more similar to the alarm reason a than the alarm reason C.
In some alternative implementations of this embodiment, querying the historical alert record for the alert device may be querying the database for alert records that occur at the same device address as the current alert device address and that have been repaired and in descending order of time. To reduce the history of the presentation, a time threshold may be set (e.g., a point in time close to the time of failure may be set as the time threshold) below which the alarm record will be discarded from being sent to the electronic device. .
And step 204, feeding back the display data to the user.
In this embodiment, the electronic device feeds back presentation data generated 202 and 203 to the user in the form of a screen display.
In this embodiment, as shown in fig. 4, the presentation data 400 for the user includes: 401. 402 and 403. Wherein 401 represents a current alert information area, comprising: the address of the device where the alarm occurred and the reason for the alarm. 402 represents a list of similar alarms. 403 represents a historical alert list for the current alert device.
In the embodiment, the electronic device determines whether clicking operation exists on the similar alarm record or not in response to detecting an operation instruction of the user on the currently presented similar alarm record; in response to the determination that yes, details 500 of the similar alarm will be presented, as shown in fig. 5, where the details of the similar alarm include: the method comprises the steps of alarming occurrence time, equipment address of alarming occurrence, alarming reason, name and contact of alarming repairing person, alarming repairing time and alarming repairing scheme, wherein the alarming reason comprises: the alarming text image information and alarming text description, the alarming repair person contact way comprises: mobile phones, landline phones, and email, alert remediation schemes include: the method comprises the steps of a text alarm repair scheme, a picture alarm repair scheme and a code alarm repair scheme.
In this embodiment, the method further includes: the electronic equipment responds to the detection of an operation instruction of a user on the currently presented historical alarm record, and judges whether clicking operation is carried out on the historical alarm record or not; in response to the determination that the result is yes, details 600 of the historical alert will be presented, as shown in fig. 6, where the details of the historical alert include: the method comprises the steps of alarming occurrence time, equipment address of alarming occurrence, alarming reason, name and contact of alarming repairing person, alarming repairing time and alarming repairing scheme, wherein the alarming reason comprises: the alarming text image information and alarming text description, the alarming repair person contact way comprises: mobile phones, landline phones, and email, alert remediation schemes include: the method comprises the steps of a text alarm repair scheme, a picture alarm repair scheme and a code alarm repair scheme.
At step 206, alert information and solutions are recorded.
In this embodiment, the server 105 will record information of the current device alert in the database, including: the text image information of the current alarm, the identified alarm occurrence time, the address of the equipment where the alarm occurs, the reason of the alarm, and the solution and repair time recorded after the user repairs the alarm, thereby expanding the record of the alarm database and providing parameter data for the later repair of the alarm.
By the invention, operation and maintenance personnel can conveniently know what kind of faults and risks happen to the system, and can quickly obtain solutions of the same or similar problems, thereby providing a good solution for quickly solving the faults and risks of the system.
Claims (1)
1. A method for quickly repairing alarms of faults and risks of an information system, comprising the steps of:
step 1, acquiring text image information of alarm information of faults and risks of an information system;
step 2, identifying alarm information in the text image information, generating text alarm information and displaying the text alarm information;
step 3, retrieving alarm description information, generating a similar alarm record and a historical alarm record and a repairing scheme thereof, and sending the similar alarm record and the historical alarm record;
step 4, displaying similar alarm records and historical alarm records and repairing schemes thereof to the user;
step 5, repairing equipment alarms according to the similar alarms and/or the repairing schemes of the historical alarms;
step 6, recording alarm information and a repairing scheme of the information system;
in the step 1, text image information containing alarm information is acquired by the following method: the electronic equipment scans or photographs the alarming text information on the alarming equipment to obtain image information; or screen capturing is carried out on the text information displayed on the electronic equipment to obtain image information; or acquiring image information from other devices communicatively connected thereto by the electronic device;
the step 2 of identifying the alarm information in the image information to generate alarm description information and displaying the alarm description information comprises the following steps: the electronic equipment analyzes the image information obtained in the step 1, determines the text information therein and identifies the text information, and generates display data, wherein the display data comprises an identification result of the text information;
the electronic equipment utilizes an optical character recognition method to recognize the character information, and a primary recognition result is generated; then extracting the alarm occurrence time in the primary identification result through semantic analysis, and generating an identification result of text information by the equipment address and the alarm reason of the alarm occurrence to generate display data;
the method, wherein retrieving the alarm description information in step 3, generating the similar alarm record and the history alarm record includes: the electronic equipment sends the alarm information generated in the step 2 to a server through a network; the server acquires similar alarm records, historical alarm records of the alarm equipment and an alarm repair scheme thereof by inquiring a knowledge base, and then sends the similar alarm records, the historical alarm records of the alarm equipment and the alarm repair scheme thereof to the electronic equipment through a network;
the method comprises the following steps: querying similar alert records includes: firstly, dividing words and filtering invalid words of an alarm reason, then inquiring an error code dictionary in a knowledge base to check whether the alarm reason contains an error code of an information system, and processing according to two conditions: 1) If the error code of the information system is contained, retrieving the knowledge base according to the error code; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type; aiming at the error code condition of an information system contained in the alarm reasons, two conditions are treated: 1) If the search result exists, the search result is fed back to the user in a descending order according to the result satisfaction degree, wherein the result satisfaction degree is obtained by fitting calculation according to the click check times of the search result and the times of applying the repair scheme; 2) Otherwise, inquiring a device type dictionary in the knowledge base to check whether the alarm reasons contain the device type;
the method comprises the following steps: checking whether the alarm reasons contain equipment type conditions according to equipment type dictionaries in the query knowledge base, and processing according to two conditions: 1) If the equipment type is contained, traversing a knowledge base according to the equipment type, and calculating the similarity of the alarm reasons; 2) Otherwise, traversing the full knowledge base, and calculating the similarity with the alarm reason information; for the case of containing the device type, two cases are handled: 1) If the search result exists, feeding back to the user in descending order according to the similarity of the alarm reasons; 2) Otherwise, traversing the full knowledge base, and calculating the similarity of the alarm reasons; inquiring the alarm reasons and the repaired alarms containing one or more word segmentation results in the alarm repair scheme in a knowledge base, calculating the similarity value of the alarms according to a text similarity algorithm, setting a similarity threshold, and transmitting the alarm records and the alarm repair scheme higher than the threshold to the electronic equipment; the alarm reason similarity adopts a semantic cosine similarity algorithm;
the method comprises the following steps of: the electronic equipment responds to the detection of an operation instruction of a user on the currently presented similar alarm record, and judges whether clicking operation on the similar alarm record exists or not; and responding to the fact that the judgment result is yes, presenting details of similar alarms, wherein the details of the similar alarms comprise: the time of alarm occurrence, the address of the equipment where the alarm occurs, the reason of the alarm, the name and contact of the alarm repairing person, the alarm repairing time and the alarm repairing scheme.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910874195.5A CN110598645B (en) | 2019-09-17 | 2019-09-17 | Method for rapidly repairing faults and risks of information system |
| CN202310832678.5A CN116862474A (en) | 2019-09-17 | 2019-09-17 | Alarm system for rapidly repairing faults and risks of information system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910874195.5A CN110598645B (en) | 2019-09-17 | 2019-09-17 | Method for rapidly repairing faults and risks of information system |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310832678.5A Division CN116862474A (en) | 2019-09-17 | 2019-09-17 | Alarm system for rapidly repairing faults and risks of information system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110598645A CN110598645A (en) | 2019-12-20 |
| CN110598645B true CN110598645B (en) | 2023-05-23 |
Family
ID=68860287
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310832678.5A Pending CN116862474A (en) | 2019-09-17 | 2019-09-17 | Alarm system for rapidly repairing faults and risks of information system |
| CN201910874195.5A Active CN110598645B (en) | 2019-09-17 | 2019-09-17 | Method for rapidly repairing faults and risks of information system |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310832678.5A Pending CN116862474A (en) | 2019-09-17 | 2019-09-17 | Alarm system for rapidly repairing faults and risks of information system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN116862474A (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113497716B (en) * | 2020-03-18 | 2023-03-10 | 华为技术有限公司 | Similar fault recommendation method and related equipment |
| CN111953541B (en) * | 2020-08-10 | 2023-12-05 | 腾讯科技（深圳）有限公司 | Alarm information processing method, device, computer equipment and storage medium |
| CN114118454A (en) * | 2021-10-20 | 2022-03-01 | 郑州云海信息技术有限公司 | Equipment management method, device, equipment and readable medium based on 5G network |
| CN115827398B (en) * | 2023-02-24 | 2023-06-23 | 天翼云科技有限公司 | Method and device for calculating component value of alarm information, electronic equipment and storage medium |
| CN115952796A (en) * | 2023-03-14 | 2023-04-11 | 华北电力科学研究院有限责任公司 | Power equipment fault analysis method and device |
| CN118012725B (en) * | 2024-04-09 | 2024-07-09 | 西安热工研究院有限公司 | Trusted management platform alarm management method, system, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012036345A1 (en) * | 2010-09-17 | 2012-03-22 | 주식회사 엔웨이브 | Optical character recognition and dictionary search system and method in a server-linked integrated page |
| CN109241282A (en) * | 2018-08-08 | 2019-01-18 | 麒麟合盛网络技术股份有限公司 | A kind of warning message assemblage method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894747B (en) * | 2016-03-25 | 2020-05-08 | 国家电网公司 | Alarm signal treatment decision suggestion method based on monitoring expert knowledge base |
| CN106713007A (en) * | 2016-11-15 | 2017-05-24 | 郑州云海信息技术有限公司 | Alarm monitoring system and alarm monitoring method and device for server |
| CN107196804B (en) * | 2017-06-01 | 2020-07-10 | 国网山东省电力公司信息通信公司 | Alarm centralized monitoring system and method for terminal communication access network of power system |
-
2019
- 2019-09-17 CN CN202310832678.5A patent/CN116862474A/en active Pending
- 2019-09-17 CN CN201910874195.5A patent/CN110598645B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012036345A1 (en) * | 2010-09-17 | 2012-03-22 | 주식회사 엔웨이브 | Optical character recognition and dictionary search system and method in a server-linked integrated page |
| CN109241282A (en) * | 2018-08-08 | 2019-01-18 | 麒麟合盛网络技术股份有限公司 | A kind of warning message assemblage method and device |
Non-Patent Citations (2)
| Title |
|---|
| 基于数据挖掘的网管告警处理方法研究;许劭庆;马彪;安海英;;软件工程(第12期);全文 * |
| 论网络舆情监测分析系统;方俊青;;法制与社会(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116862474A (en) | 2023-10-10 |
| CN110598645A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598645B (en) | Method for rapidly repairing faults and risks of information system | |
| CN108874777B (en) | Text anti-spam method and device | |
| CN110008343B (en) | Text classification method, apparatus, device and computer readable storage medium | |
| CN109918554A (en) | Web data crawling method, device, system and computer readable storage medium | |
| WO2011044658A1 (en) | System and method for text cleaning | |
| WO2008068987A1 (en) | Pure adversarial approach for identifying text content in images | |
| CN112966081B (en) | Method, device, equipment and storage medium for processing question and answer information | |
| US20190220481A1 (en) | System and method for feature recognition and document searching based on feature recognition | |
| CN110096681B (en) | Contract term analysis method, apparatus, device and readable storage medium | |
| CN112541359A (en) | Document content identification method and device, electronic equipment and medium | |
| CN113190689B (en) | Construction method, device, equipment and medium of electric power safety knowledge graph | |
| CN113590802B (en) | Session content abnormity detection method and device, electronic equipment and storage medium | |
| CN108650104A (en) | The treating method and apparatus of one population message | |
| CN107291774B (en) | Error sample identification method and device | |
| CN104184653A (en) | Message filtering method and device | |
| CN103605690A (en) | Device and method for recognizing advertising messages in instant messaging | |
| CN111338915A (en) | Dynamic alarm grading method and device, electronic equipment and storage medium | |
| CN113657088A (en) | Interface document analysis method and device, electronic equipment and storage medium | |
| CN114244795B (en) | Information pushing method, device, equipment and medium | |
| CN115017898A (en) | Sensitive text recognition method and device, electronic equipment and storage medium | |
| CN113971205A (en) | Threat report attack behavior extraction method, device, equipment and storage medium | |
| CN115879110A (en) | System for identifying financial risk website based on fingerprint penetration technology | |
| CN114254109B (en) | Method and device for determining industry category | |
| CN113849622A (en) | Visual cognition question-answering method and system for civil aviation documents | |
| CN1987856A (en) | History control apparatus |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |