CN112560465B - Batch abnormal event monitoring method and device, electronic equipment and storage medium - Google Patents
Batch abnormal event monitoring method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112560465B CN112560465B CN202011502286.5A CN202011502286A CN112560465B CN 112560465 B CN112560465 B CN 112560465B CN 202011502286 A CN202011502286 A CN 202011502286A CN 112560465 B CN112560465 B CN 112560465B
- Authority
- CN
- China
- Prior art keywords
- complaint
- abnormal
- analysis model
- work order
- data
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 182
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 171
- 238000012549 training Methods 0.000 claims abstract description 42
- 230000000007 visual effect Effects 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 21
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013139 quantization Methods 0.000 claims description 10
- 238000002790 cross-validation Methods 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000009977 dual effect Effects 0.000 claims description 2
- 238000011056 performance test Methods 0.000 claims description 2
- 238000012806 monitoring device Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 14
- 230000004913 activation Effects 0.000 description 10
- 238000010606 normalization Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 4
- 238000005315 distribution function Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Debugging And Monitoring (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a data analysis technology, and discloses a monitoring method for batch abnormal events, which comprises the following steps: training a pre-constructed language analysis model by using a historical complaint sample set to obtain a complaint analysis model; carrying out abnormal event analysis on the complaint work order set by using the complaint analysis model to obtain an analysis result set of the complaint work order set; extracting abnormal reports from the complaint work list set according to a preset rule and an analysis result set, grouping the abnormal reports according to the correlation degree, and arranging the grouping to obtain an abnormal event importance ranking table; and drawing an abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph. The present invention also relates to blockchain techniques, the set of historical complaint samples may be stored in a blockchain node. The invention also provides a monitoring device, equipment and a computer readable storage medium for batch abnormal events. The invention can timely find and summarize abnormal report in a large number of complaints.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a method and apparatus for monitoring batch abnormal events, an electronic device, and a computer readable storage medium.
Background
Along with the gradual improvement of people consciousness and the diversity of reporting ways, enterprises can receive various complaints, and in order to stand on the market and advance with time, the enterprises must conduct targeted treatment on various complaints, otherwise, the enterprises are eliminated by society.
At present, the complaints of enterprises are processed by professional departments, the processing workload is huge, the inter-department cooperation efficiency is low, important abnormal events cannot be timely found, and the situation that the abnormal events are misreported and missed report easily occurs, so that the enterprises cannot timely find out own important problems, and the important abnormal events are found out from a plurality of reports in the first time, so that the problems to be solved by the enterprises are urgent.
Disclosure of Invention
The invention provides a method and a device for monitoring batch abnormal events, electronic equipment and a computer readable storage medium, and aims to timely find out abnormal reports in a large number of complaints.
In order to achieve the above object, the present invention provides a method for monitoring batch abnormal events, including:
Acquiring a historical complaint sample set, and training a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model;
acquiring a complaint work order set, and analyzing abnormal events of the complaint work order set by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, so as to obtain an analysis result set of the complaint work order set;
extracting abnormal reports from the complaint work list set according to a preset rule and the analysis result set, grouping the abnormal reports according to the correlation degree, and arranging the grouping to obtain an abnormal event importance ranking table;
and drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
Optionally, training the pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model, including:
performing quantization and cleaning operations on the historical complaint sample set to obtain quantized data;
analyzing abnormal data in the quantized data by utilizing a correlation algorithm in the language analysis model;
Training the language analysis model by using the abnormal data to obtain the complaint analysis model.
Optionally, training the language analysis model by using the abnormal data to obtain the complaint analysis model includes:
according to the abnormal data, carrying out K-fold cross validation training on the language analysis model to obtain a primary complaint analysis model;
and performing performance evaluation on the primary complaint analysis model to obtain an evaluation score, and performing parameter adjustment on the primary complaint analysis model when the evaluation score is larger than a preset performance threshold until the evaluation score is smaller than or equal to the preset performance threshold, so as to obtain the trained complaint analysis model.
Optionally, the performing performance evaluation on the primary complaint analysis model to obtain an evaluation score includes:
performing performance test on the primary complaint analysis model according to the following dual index weighted strategy to obtain an evaluation score F:
F＝0.3*FRR+0.7*FAR
FRR＝FN/(TP+FN)*100％
FAR＝FP/(TN+FP)*100％
wherein FRR represents rejection rate, FAR represents false recognition rate, TP is test result common, actual common, FP is test result common, actual abnormality, FN is test result abnormality, actual abnormality, TN is test result abnormality, actual common.
Optionally, before the training of the pre-constructed language analysis model by using the historical complaint sample set, the method further includes:
deleting special symbols from sample data obtained from a preset database or network;
and according to preset keywords, performing word segmentation processing on the sample data, inquiring dirty data, and performing cleaning processing on the dirty data to obtain the historical complaint sample set.
Optionally, the analyzing the abnormal event by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, and obtaining an analysis result set of the complaint work order set includes:
mapping the worksheet content field in each complaint worksheet in the complaint worksheet set to obtain worksheet content data;
carrying out abnormal event analysis on the work order content data by utilizing the complaint analysis model to obtain the probability that the complaint work order is reported abnormally;
when the probability is smaller than a preset abnormal event probability value, judging that the complaint work order is commonly reported;
and when the probability is larger than a preset abnormal event probability value, judging that the complaint work order is the abnormal report.
Optionally, before the acquiring the complaint worksheet set, the method further includes:
connecting the complaint analysis model with a pre-constructed recall engine;
and receiving the complaint work order set in real time by using the recall engine.
In order to solve the above problems, the present invention further provides a device for monitoring batch abnormal events, the device comprising:
the model construction module is used for acquiring a historical complaint sample set, and training a pre-constructed language analysis model by utilizing the historical complaint sample set to obtain a trained complaint analysis model;
the data processing module is used for acquiring a complaint work order set, analyzing abnormal events of the complaint work order set by utilizing the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, and obtaining an analysis result set of the complaint work order set;
the list arranging module is used for extracting abnormal reports from the complaint work list set according to preset rules and the analysis result set, grouping the abnormal reports according to the relevance and arranging the grouping to obtain an abnormal event importance list;
and the monitoring module is used for drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of monitoring for batch anomaly events described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium including a storage data area storing created data and a storage program area storing a computer program; the method for monitoring the batch abnormal events is realized when the computer program is executed by a processor.
According to the embodiment of the invention, the complaint analysis model is constructed by utilizing the historical complaint set and the language analysis model, whether the complaint content of each complaint work order is abnormal report can be primarily judged, and different abnormal reports are arranged in groups through similarity analysis, so that an abnormal event importance ranking table is obtained and visually displayed. Therefore, the method, the device, the electronic equipment and the storage medium for monitoring the batch abnormal events can timely find out the abnormal report in batch complaints.
Drawings
FIG. 1 is a flow chart of a method for monitoring batch abnormal events according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of a device for monitoring batch abnormal events according to an embodiment of the present application;
fig. 3 is a schematic diagram of an internal structure of an electronic device for implementing a method for monitoring a batch abnormal event according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a monitoring method for batch abnormal events. The execution subject of the batch abnormal event monitoring method includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the electronic device of the method provided by the embodiment of the application. In other words, the method for monitoring the batch abnormal events may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flow chart of a method for monitoring batch abnormal events according to an embodiment of the invention is shown. In this embodiment, the method for monitoring a batch of abnormal events includes:
s1, acquiring a historical complaint sample set, and training a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model.
In the embodiment of the present invention, the historical complaint sample set may be all complaint information received in a preset historical period of time in a preset enterprise or a certain industry. Wherein the set of historical complaint samples may be stored in a distributed manner in blockchain nodes.
In detail, in the embodiment of the present invention, the S1 includes:
performing quantization and cleaning operations on the historical complaint sample set to obtain quantized data; analyzing abnormal data in the quantized data by utilizing a correlation algorithm in the language analysis model; training the language analysis model by using the abnormal data to obtain the complaint analysis model.
The embodiment of the invention carries out quantization and cleaning operation on the historical complaint sample set to obtain quantized data. The quantization is a process of carrying out format normalization processing on the historical complaint sample set and is used for increasing training efficiency of the language analysis model. The cleaning is a process of removing the duplication and filling in null values of the quantized data. The quantization and cleaning processes described in the embodiments of the present invention may be accomplished by specific functions in Python.
The language analysis model in the embodiment of the invention is a BERT-base-Chinese model, wherein BERT (Bidirectional Encoder Representation from Transformers) is a pre-trained language characterization model, and the pre-trained model disclosed by the BERT-base-Chinese model is a language characterization model based on Chinese basis. Further, in the embodiment of the present invention, the correlation algorithm may be a BM25 algorithm. The BM25 algorithm is an algorithm that evaluates the relevance between search terms and documents.
In detail, in the embodiment of the present invention, training the pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model includes:
according to the abnormal data, carrying out K-fold cross validation training on the language analysis model to obtain a primary complaint analysis model;
and performing performance evaluation on the primary complaint analysis model to obtain an evaluation score, and performing parameter adjustment on the primary complaint analysis model when the evaluation score is larger than a preset performance threshold until the evaluation score is smaller than or equal to the preset performance threshold, so as to obtain the trained complaint analysis model.
In the embodiment of the invention, the K-fold cross validation is a process of equally dividing the quantized data into K parts, taking one part as test data and the other K-1 parts as training data, and repeating K times, thereby obtaining the optimal parameters of the language analysis model.
In detail, in the embodiment of the present invention, the training for performing K-fold cross validation on the language analysis model according to the anomaly data to obtain a primary complaint analysis model includes:
step I, dividing a historical complaint sample set corresponding to the abnormal data into K parts in equal proportion;
step II, taking K-1 historical complaint sample sets as training data and the rest 1 historical complaint sample sets as test data, and extracting character features of the training data by using a feature extraction layer in the language analysis model to obtain a feature sequence training set;
in the embodiment of the present invention, the history complaint sample set includes a history complaint work order and a complaint label set corresponding to the history complaint work order, such as, for example, a severe service attitude of a hall manager of a complaint work order 1 ". Times.website, a sudden opening of a complaint work order 2" app "and a sudden drop of each time, where the complaint label of the complaint work order 1 is a common complaint, and the complaint label of the complaint work order 2 is an abnormal complaint.
Further, the feature sequence training set obtained after the character feature extraction is [ 'hall manager' -ordinary, 'APP' -abnormal, 'flash back' -abnormal … … ].
III, executing activation operation on the feature sequence training set by utilizing a plurality of linear activation layers of the language analysis model to obtain a predicted sequence set;
in an embodiment of the present invention, the linear activation layer includes normalization and activation functions, and the activation functions may use gaussian distribution functions.
According to the embodiment of the invention, normalization is carried out on the characteristic sequence training set to obtain a characteristic sequence normalization set, gaussian distribution of the characteristic sequence normalization set is calculated by utilizing the Gaussian distribution function, and the prediction sequence set is obtained according to the Gaussian distribution.
And IV, calculating an error value of the language analysis model according to the prediction sequence set, and judging the magnitude relation between the error value and a preset error threshold.
According to the embodiment of the invention, the error value of the prediction sequence set and the complaint label set is calculated by using the Lipin variance formula.
Step V, if the error value is larger than the error threshold value, adjusting the internal parameters of the language analysis model, and returning to the step II;
And step VI, if the error value is smaller than or equal to the error threshold value, verifying the language analysis model by using the test data, returning to the step II when the verification is failed, and obtaining a primary complaint analysis model when the step II is repeated K times.
Further, the embodiment of the invention utilizes a dual index weighted strategy to evaluate the primary complaint analysis model, and the primary complaint analysis model is evaluated according to an evaluation score F:
F＝0.3*FRR+0.7*FAR
FRR＝FN/(TP+FN)*100％
FAR＝FP/(TN+FP)*100％
in the formula, FRR represents rejection rate, FAR represents false recognition rate, TP represents real instance, namely model prediction is common report and actual number of common reports, FP represents false positive instance, namely model prediction is common report and actual number of abnormal reports, FN represents false negative instance, namely model prediction is abnormal report and actual number of common reports, TN represents true negative instance, namely model prediction is abnormal report and actual number of abnormal reports.
Wherein a smaller value of the evaluation score F indicates a better model, the embodiment of the present invention sets the preset performance threshold to 0.15.
In the embodiment of the invention, when the complaint work order input by the user is received, the complaint work order can be judged to be abnormal report or common report by utilizing the complaint analysis model.
In other embodiments of the present invention, before S1, the method may further include:
deleting special symbols from sample data obtained from a preset database or network;
and according to preset keywords, performing word segmentation processing on the sample data, inquiring dirty data, and deleting the dirty data to obtain the historical complaint sample set.
The sample data are common report information and abnormal report information which are acquired in a network and/or in a preset historical time period. In the embodiment of the invention, the special symbols comprise emoticons, punctuation marks and the like. The dirty data is data which is not in a given range in the system or is meaningless for actual business, such as dirty words, language and Qi aid words and the like, or is illegitimate in a data format. In the embodiment of the present invention, the data not within the given range refers to the data outside the work order content field, the work order time field and the work order type field.
Furthermore, the embodiment of the invention can use a jieba tool to segment the sample data so as to eliminate dirty data such as o's "," and the like in the sample data and generate misjudgment on the relevance division, and increase the relevance analysis of effective keywords such as machine fault, XX business hall and the like.
S2, acquiring a complaint work order set, and analyzing abnormal events of the complaint work order set by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, thereby obtaining an analysis result set of the complaint work order set.
In the embodiment of the present invention, the complaint worksheet set refers to a set of complaint worksheets, and the complaint worksheets are public opinion forms generated for solving problems in banks or other enterprises, where the complaint worksheets include: reporting time, work order content, business category, processing opinion and other fields.
In detail, in the embodiment of the present invention, the S2 includes:
mapping the worksheet content field in each complaint worksheet in the complaint worksheet set to obtain worksheet content data; carrying out abnormal event analysis on the work order content data by using the complaint analysis model to obtain the probability that the complaint work order is reported abnormally; when the probability is smaller than a preset abnormal event probability value, judging that the complaint work order is commonly reported; and when the probability is larger than a preset abnormal event probability value, judging that the complaint work order is the abnormal report.
In the embodiment of the invention, in order to further increase the analysis efficiency of the complaint analysis model, the embodiment of the invention maps the worksheet content field to obtain worksheet content data. The mapping is to transfer the worksheet content field from a physical storage address to a logic space address, and directly read the worksheet content data corresponding to the worksheet content field through a pointer in the logic space address, so that the data security of the complaint worksheet is improved, and the running speed of the complaint analysis model is also improved.
According to the embodiment of the invention, the complaint worksheets are subjected to abnormal correlation analysis through the complaint analysis model, so that the analysis result scores of whether each complaint worksheet is an abnormal event worksheet or not can be obtained.
Further, in other embodiments of the present invention, before S2, the method may further include:
and connecting the complaint analysis model with a pre-constructed recall engine, and receiving the complaint work order set by using the recall engine.
According to the embodiment of the invention, the recall engine and the complaint analysis model are connected according to the API interface of the pre-built recall engine, and the complaint work orders reported by the masses are stored in real time.
S3, extracting abnormal reports from the complaint work list set according to a preset rule and the analysis result set, grouping the abnormal reports according to the relevance, and arranging the grouping to obtain an abnormal event importance ranking table.
In the embodiment of the invention, the preset rule is to normalize the analysis result score to enable the analysis result score to be between 0 and 1, and set an abnormal demarcation value, such as 0.6, when the analysis result score is greater than or equal to 0.6, the complaint work order is judged to be an abnormal report, and when the analysis result score is less than 0.6, the complaint work order is judged to be a common report.
Further, the embodiment of the invention extracts the abnormal reports, extracts text features of each abnormal report according to relevance analysis, groups similar abnormal events to obtain a data table containing abnormal names and event numbers, and arranges the data table according to the event numbers to obtain the abnormal event importance ranking table.
And S4, drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
In the embodiment of the invention, in a pre-constructed Web end, the total number of the abnormal events in the abnormal event importance level list is calculated, the length of a data bar is set to be 100% according to the total number, gradual filling is set, the abnormal events of each group are dynamically filled according to the number of the abnormal events, and the abnormal events are arranged in a descending manner from top to bottom according to the number proportion of the abnormal reports, so that a visualized abnormal complaint monitoring graph is completed.
According to the embodiment of the invention, the complaint analysis model is constructed by utilizing the historical complaint set and the language analysis model, whether the complaint content of each complaint work order is abnormal report can be primarily judged, and different abnormal reports are arranged in groups through similarity analysis, so that an abnormal event importance ranking table is obtained and visually displayed. Therefore, the embodiment of the invention can timely find out abnormal report in batch complaints.
FIG. 2 is a schematic block diagram of a batch anomaly monitoring device according to the present invention.
The monitoring device 100 for batch abnormal events according to the present invention may be installed in an electronic apparatus. The monitoring device for batch abnormal events may include a model construction module 101, a data processing module 102, a schedule module 103, and a monitoring module 104 according to the implemented functions. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the model construction module 101 is configured to obtain a historical complaint sample set, and train a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model.
In detail, the model construction module 101 is specifically configured to: performing quantization and cleaning operations on the historical complaint sample set to obtain quantized data; analyzing abnormal data in the quantized data by utilizing a correlation algorithm in the language analysis model; training the language analysis model by using the abnormal data to obtain the complaint analysis model.
The embodiment of the invention carries out quantization and cleaning operation on the historical complaint sample set to obtain quantized data. The quantization is a process of performing format normalization processing on the sample set, and is used for increasing training efficiency of the language analysis model. The cleaning is a process of removing the duplication and filling in null values of the quantized data. The quantization and cleaning processes described in the embodiments of the present invention may be accomplished by specific functions in Python.
The language analysis model in the embodiment of the invention is a BERT-base-Chinese model, wherein BERT (Bidirectional Encoder Representation from Transformers) is a pre-trained language characterization model, and the pre-trained model disclosed by the BERT-base-Chinese model is a language characterization model based on Chinese basis. Further, in the embodiment of the present invention, the correlation algorithm may be a BM25 algorithm. The BM25 algorithm is an algorithm that evaluates the relevance between search terms and documents. In detail, in the embodiment of the present invention, the analyzing the abnormal data in the quantized data by using the relevance algorithm in the language analysis model includes:
according to the abnormal data, carrying out K-fold cross validation training on the language analysis model to obtain a primary complaint analysis model;
And performing performance evaluation on the primary complaint analysis model to obtain an evaluation score, and performing parameter adjustment on the primary complaint analysis model when the evaluation score is larger than a preset performance threshold until the evaluation score is smaller than or equal to the preset performance threshold, so as to obtain the trained complaint analysis model.
In the embodiment of the invention, the K-fold cross validation is a process of equally dividing the quantized data into K parts, taking one part as test data and the other K-1 parts as training data, and repeating K times, thereby obtaining the optimal parameters of the language analysis model.
In detail, in the embodiment of the present invention, the training for performing K-fold cross validation on the language analysis model according to the anomaly data to obtain a primary complaint analysis model includes:
step I, dividing a historical complaint sample set corresponding to the abnormal data into K parts in equal proportion;
step II, taking K-1 historical complaint sample sets as training data and the rest 1 historical complaint sample sets as test data, and extracting character features of the training data by using a feature extraction layer in the language analysis model to obtain a feature sequence training set;
In the embodiment of the present invention, the history complaint sample set includes a history complaint work order and a complaint label set corresponding to the history complaint work order, such as, for example, a severe service attitude of a hall manager of a complaint work order 1 ". Times.website, a sudden opening of a complaint work order 2" app "and a sudden drop of each time, where the complaint label of the complaint work order 1 is a common complaint, and the complaint label of the complaint work order 2 is an abnormal complaint.
Further, the feature sequence training set obtained after the character feature extraction is [ 'hall manager' -ordinary, 'APP' -abnormal, 'flash back' -abnormal … … ].
III, executing activation operation on the feature sequence training set by utilizing a plurality of linear activation layers of the language analysis model to obtain a predicted sequence set;
in an embodiment of the present invention, the linear activation layer includes normalization and activation functions, and the activation functions may use gaussian distribution functions.
According to the embodiment of the invention, normalization is carried out on the characteristic sequence training set to obtain a characteristic sequence normalization set, gaussian distribution of the characteristic sequence normalization set is calculated by utilizing the Gaussian distribution function, and the prediction sequence set is obtained according to the Gaussian distribution.
And IV, calculating an error value of the language analysis model according to the prediction sequence set, and judging the magnitude relation between the error value and a preset error threshold.
According to the embodiment of the invention, the error value of the prediction sequence set and the complaint label set is calculated by using the Lipin variance formula.
Step V, if the error value is larger than the error threshold value, adjusting the internal parameters of the language analysis model, and returning to the step II;
and step VI, if the error value is smaller than or equal to the error threshold value, verifying the language analysis model by using the test data, returning to the step II when the verification is failed, and obtaining a primary complaint analysis model when the step II is repeated K times.
Further, the embodiment of the invention utilizes a dual index weighted strategy to evaluate the primary complaint analysis model, and the primary complaint analysis model is evaluated according to an evaluation score F:
F＝0.3*FRR+0.7*FAR
FRR＝FN/(TP+FN)*100％
FAR＝FP/(TN+FP)*100％
in the formula, FRR represents rejection rate, FAR represents false recognition rate, TP represents real instance, namely model prediction is common report and actual number of common reports, FP represents false positive instance, namely model prediction is common report and actual number of abnormal reports, FN represents false negative instance, namely model prediction is abnormal report and actual number of common reports, TN represents true negative instance, namely model prediction is abnormal report and actual number of abnormal reports.
Wherein a smaller value of the evaluation score F indicates a better model, the embodiment of the present invention sets the preset performance threshold to 0.15.
In other embodiments of the present invention, the model construction module 101 may be further configured to: deleting special symbols from sample data obtained from a preset database or network; and according to preset keywords, performing word segmentation processing on the sample data, inquiring dirty data, and deleting the dirty data to obtain the historical complaint sample set.
The sample data are common report information and abnormal report information which are acquired in a network and/or in a preset historical time period. In the embodiment of the invention, the special symbols comprise emoticons, punctuation marks and the like. The dirty data is data which is not in a given range in the system or is meaningless for actual business, such as dirty words, language and Qi aid words and the like, or is illegitimate in a data format. In the embodiment of the present invention, the data not within the given range refers to the data outside the work order content field, the work order time field and the work order type field.
Furthermore, the embodiment of the invention can use a jieba tool to segment the sample data so as to eliminate dirty data such as o's "," and the like in the sample data and generate misjudgment on the relevance division, and increase the relevance analysis of effective keywords such as machine fault, XX business hall and the like.
The data processing module 102 is configured to obtain a complaint work order set, analyze the complaint work order set for abnormal events by using the complaint analysis model, obtain an analysis result of each complaint work order in the complaint work order set, and obtain an analysis result set of the complaint work order set.
In the embodiment of the invention, the complaint work order set refers to a set of complaint work orders, the complaint work orders are public opinion forms generated by solving problems through mobile phone user opinions, wherein the complaint work orders comprise: reporting time, work order content, business category, processing opinion and other fields.
In detail, in the embodiment of the present invention, the data processing module 102 is configured to: mapping the worksheet content field in each complaint worksheet in the complaint worksheet set to obtain worksheet content data; carrying out abnormal event analysis on the work order content data by using the complaint analysis model to obtain the probability that the complaint work order is reported abnormally; when the probability is smaller than a preset abnormal event probability value, judging that the complaint work order is commonly reported; and when the probability is larger than a preset abnormal event probability value, judging that the complaint work order is the abnormal report.
In the embodiment of the invention, in order to further increase the analysis efficiency of the complaint analysis model, the embodiment of the invention maps the worksheet content field to obtain worksheet content data. The mapping is to transfer the worksheet content field from a physical storage address to a logic space address, and directly read the worksheet content data corresponding to the worksheet content field through a pointer in the logic space address, so that the data security of the complaint worksheet is improved, and the running speed of the complaint analysis model is also improved.
According to the embodiment of the invention, the complaint worksheets are subjected to abnormal correlation analysis through the complaint analysis model, so that the analysis result scores of whether each complaint worksheet is an abnormal event worksheet or not can be obtained.
Further, in other embodiments of the present invention, the data processing module 102 may be further configured to: and connecting the complaint analysis model with a pre-constructed recall engine, and receiving the complaint work order set by using the recall engine.
According to the embodiment of the invention, the recall engine and the complaint analysis model are connected according to the API interface of the pre-built recall engine, and the complaint work orders reported by the masses are stored in real time.
The schedule module 103 is configured to extract abnormal reports from the complaint worksheets according to a preset rule and the analysis result set, group the abnormal reports according to a correlation degree, and arrange the groups to obtain an abnormal event importance schedule.
In the embodiment of the invention, the preset rule is to normalize the analysis result score to enable the analysis result score to be between 0 and 1, and set an abnormal demarcation value, such as 0.6, when the analysis result score is greater than or equal to 0.6, the complaint work order is judged to be an abnormal report, and when the analysis result score is less than 0.6, the complaint work order is judged to be a common report.
Further, the embodiment of the invention extracts the abnormal reports, extracts text features of each abnormal report according to relevance analysis, groups similar abnormal events to obtain a data table containing abnormal names and event numbers, and arranges the data table according to the event numbers to obtain the abnormal event importance ranking table.
The monitoring module 104 is configured to draw the abnormal event importance level schedule by using a pre-constructed Web terminal, so as to obtain a visual abnormal complaint monitoring graph.
In the embodiment of the invention, in a pre-constructed Web end, the total number of the abnormal events in the abnormal event importance level list is calculated, the length of a data bar is set to be 100% according to the total number, gradual filling is set, the abnormal events of each group are dynamically filled according to the number of the abnormal events, and the abnormal events are arranged in a descending manner from top to bottom according to the number proportion of the abnormal reports, so that a visualized abnormal complaint monitoring graph is completed.
According to the embodiment of the invention, the complaint analysis model is constructed by utilizing the historical complaint set and the language analysis model, whether the complaint content of each complaint work order is abnormal report can be primarily judged, and different abnormal reports are arranged in groups through similarity analysis, so that an abnormal event importance ranking table is obtained and visually displayed. Therefore, the embodiment of the invention can timely find out abnormal report in batch complaints.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a method for monitoring batch abnormal events according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a monitoring program 12 for batch exception events.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the monitoring program 12 for batch abnormal events, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (for example, a monitor program for executing a batch of abnormal events, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The monitoring program 12 of batch abnormal events stored in the memory 11 of the electronic device 1 is a combination of a plurality of computer programs, which when run in the processor 10, can realize:
Acquiring a historical complaint sample set, and training a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model;
acquiring a complaint work order set, and analyzing abnormal events of the complaint work order set by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, so as to obtain an analysis result set of the complaint work order set;
extracting abnormal reports from the complaint work list set according to a preset rule and the analysis result set, grouping the abnormal reports according to the correlation degree, and arranging the grouping to obtain an abnormal event importance ranking table;
and drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring a historical complaint sample set, and training a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model;
acquiring a complaint work order set, and analyzing abnormal events of the complaint work order set by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, so as to obtain an analysis result set of the complaint work order set;
extracting abnormal reports from the complaint work list set according to a preset rule and the analysis result set, grouping the abnormal reports according to the correlation degree, and arranging the grouping to obtain an abnormal event importance ranking table;
And drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any accompanying diagram representation in the claims should not be considered as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (7)
1. A method for monitoring batch abnormal events, the method comprising:
acquiring a historical complaint sample set, and training a pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model;
acquiring a complaint work order set, and analyzing abnormal events of the complaint work order set by using the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, so as to obtain an analysis result set of the complaint work order set;
Extracting abnormal reports from the complaint work list set according to a preset rule and the analysis result set, grouping the abnormal reports according to the correlation degree, and arranging the grouping to obtain an abnormal event importance ranking table;
drawing the abnormal event importance level list by utilizing a pre-constructed Web end to obtain a visual abnormal complaint monitoring graph;
the training of the pre-constructed language analysis model by using the historical complaint sample set to obtain a trained complaint analysis model comprises the following steps: performing quantization and cleaning operations on the historical complaint sample set to obtain quantized data; analyzing abnormal data in the quantized data by utilizing a correlation algorithm in the language analysis model; training the language analysis model by using the abnormal data to obtain the complaint analysis model;
training the language analysis model by using the abnormal data to obtain the complaint analysis model, wherein the training comprises the following steps: according to the abnormal data, carrying out K-fold cross validation training on the language analysis model to obtain a primary complaint analysis model; performing performance evaluation on the primary complaint analysis model to obtain an evaluation score, and performing parameter adjustment on the primary complaint analysis model when the evaluation score is greater than a preset performance threshold until the evaluation score is less than or equal to the preset performance threshold, so as to obtain a trained complaint analysis model;
Performing performance evaluation on the primary complaint analysis model to obtain an evaluation score, wherein the performance evaluation comprises the following steps: performing performance test on the primary complaint analysis model according to the following dual index weighted strategy to obtain an evaluation score F:
wherein ,representing the rejection rate; />Representing the false recognition rate; TP is the test result common, actual common; FP is the common test result, the actual abnormality; FN is abnormal test result and actual abnormality; TN is the abnormal test result, and is actual and common.
2. The method for monitoring batch anomaly events of claim 1, wherein prior to training a pre-constructed linguistic analysis model using the set of historical complaint samples, the method further comprises:
deleting special symbols from sample data obtained from a preset database or network;
and according to preset keywords, performing word segmentation processing on the sample data, inquiring dirty data, and performing cleaning processing on the dirty data to obtain the historical complaint sample set.
3. The method for monitoring abnormal events in batch according to claim 1, wherein the analyzing the abnormal events in the complaint bill set by using the complaint analysis model to obtain the analysis result of each complaint bill in the complaint bill set, and obtaining the analysis result set of the complaint bill set comprises:
Mapping the worksheet content field in each complaint worksheet in the complaint worksheet set to obtain worksheet content data;
carrying out abnormal event analysis on the work order content data by utilizing the complaint analysis model to obtain the probability that the complaint work order is reported abnormally;
when the probability is smaller than a preset abnormal event probability value, judging that the complaint work order is commonly reported;
and when the probability is larger than a preset abnormal event probability value, judging that the complaint work order is the abnormal report.
4. The method for monitoring batch anomaly events of claim 1, wherein prior to obtaining the set of complaint worksheets, the method further comprises:
connecting the complaint analysis model with a pre-constructed recall engine;
and receiving the complaint work order set in real time by using the recall engine.
5. A batch abnormal event monitoring apparatus for implementing the batch abnormal event monitoring method according to any one of claims 1 to 4, characterized in that the apparatus comprises:
the model construction module is used for acquiring a historical complaint sample set, and training a pre-constructed language analysis model by utilizing the historical complaint sample set to obtain a trained complaint analysis model;
The data processing module is used for acquiring a complaint work order set, analyzing abnormal events of the complaint work order set by utilizing the complaint analysis model to obtain an analysis result of each complaint work order in the complaint work order set, and obtaining an analysis result set of the complaint work order set;
the list arranging module is used for extracting abnormal reports from the complaint work list set according to preset rules and the analysis result set, grouping the abnormal reports according to the relevance and arranging the grouping to obtain an abnormal event importance list;
and the monitoring module is used for drawing the abnormal event importance level list by utilizing the pre-constructed Web end to obtain a visual abnormal complaint monitoring graph.
6. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of monitoring for batch anomaly events of any one of claims 1 to 4.
7. A computer-readable storage medium comprising a storage data area storing created data and a storage program area storing a computer program; the method for monitoring batch abnormal events according to any one of claims 1 to 4 is realized when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011502286.5A CN112560465B (en) | 2020-12-18 | 2020-12-18 | Batch abnormal event monitoring method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011502286.5A CN112560465B (en) | 2020-12-18 | 2020-12-18 | Batch abnormal event monitoring method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112560465A CN112560465A (en) | 2021-03-26 |
| CN112560465B true CN112560465B (en) | 2023-09-19 |
Family
ID=75063382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011502286.5A Active CN112560465B (en) | 2020-12-18 | 2020-12-18 | Batch abnormal event monitoring method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560465B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051291A (en) * | 2021-04-16 | 2021-06-29 | 平安国际智慧城市科技股份有限公司 | Work order information processing method, device, equipment and storage medium |
| CN113128223A (en) * | 2021-05-17 | 2021-07-16 | 深圳博沃智慧科技有限公司 | Method, device and equipment for identifying pollution complaint repeated clues |
| CN117610667B (en) * | 2024-01-17 | 2024-04-26 | 湖南傲思软件股份有限公司 | Fault handling expert system, method and computer equipment based on open source large model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2578520A1 (en) * | 2004-09-10 | 2006-03-23 | Exxonmobil Research And Engineering Company | Application of abnormal event detection technology to fluidized catalytic cracking unit |
| CN103729444A (en) * | 2013-12-30 | 2014-04-16 | 清华大学 | Abnormal data detection method based on potential relation among equipment monitoring data |
| JP2017211806A (en) * | 2016-05-25 | 2017-11-30 | 株式会社日立製作所 | Communication monitoring method, security management system, and program |
| CN110716932A (en) * | 2019-09-09 | 2020-01-21 | 平安国际智慧城市科技股份有限公司 | Data processing method, system, device and storage medium |
| CN111859384A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Abnormal event monitoring method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7079010B2 (en) * | 2004-04-07 | 2006-07-18 | Jerry Champlin | System and method for monitoring processes of an information technology system |
-
2020
- 2020-12-18 CN CN202011502286.5A patent/CN112560465B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2578520A1 (en) * | 2004-09-10 | 2006-03-23 | Exxonmobil Research And Engineering Company | Application of abnormal event detection technology to fluidized catalytic cracking unit |
| CN103729444A (en) * | 2013-12-30 | 2014-04-16 | 清华大学 | Abnormal data detection method based on potential relation among equipment monitoring data |
| JP2017211806A (en) * | 2016-05-25 | 2017-11-30 | 株式会社日立製作所 | Communication monitoring method, security management system, and program |
| CN110716932A (en) * | 2019-09-09 | 2020-01-21 | 平安国际智慧城市科技股份有限公司 | Data processing method, system, device and storage medium |
| CN111859384A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Abnormal event monitoring method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112560465A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560465B (en) | Batch abnormal event monitoring method and device, electronic equipment and storage medium | |
| CN109325165B (en) | Network public opinion analysis method, device and storage medium | |
| CN112541745B (en) | User behavior data analysis method and device, electronic equipment and readable storage medium | |
| CN109145216A (en) | Network public-opinion monitoring method, device and storage medium | |
| US10445354B2 (en) | System to determine a credibility weighting for electronic records | |
| CN113626607B (en) | Abnormal work order identification method and device, electronic equipment and readable storage medium | |
| CN115002200A (en) | User portrait based message pushing method, device, equipment and storage medium | |
| CN113961764A (en) | Method, device, equipment and storage medium for identifying fraud telephone | |
| CN114358854A (en) | Customer loss early warning method, device, equipment and storage medium | |
| CN114969484A (en) | Service data searching method, device, equipment and storage medium | |
| CN113505273A (en) | Data sorting method, device, equipment and medium based on repeated data screening | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN115099680B (en) | Risk management method, apparatus, device and storage medium | |
| CN114708073A (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
| CN114996386A (en) | Business role identification method, device, equipment and storage medium | |
| CN113888265A (en) | Product recommendation method, device, equipment and computer-readable storage medium | |
| CN114548825B (en) | Complaint work order distortion detection method, device, equipment and storage medium | |
| CN113688924B (en) | Abnormal order detection method, device, equipment and medium | |
| CN113887941B (en) | Business process generation method, device, electronic equipment and medium | |
| CN114781833B (en) | Capability assessment method, device and equipment based on business personnel and storage medium | |
| CN114723523B (en) | Product recommendation method, device, equipment and medium based on user capability image | |
| CN112528112B (en) | Data collection and analysis method and device, electronic equipment and storage medium | |
| CN116188049B (en) | Potential user mining method and device based on chain analysis | |
| CN116775852A (en) | Label-based data recommendation method, device, equipment and storage medium | |
| CN114860904A (en) | Intelligent outbound method, device, electronic equipment and readable storage medium |
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 |