KR101808642B1 - Big data log predictive analysis system - Google Patents
Big data log predictive analysis system Download PDFInfo
- Publication number
- KR101808642B1 KR101808642B1 KR1020160015712A KR20160015712A KR101808642B1 KR 101808642 B1 KR101808642 B1 KR 101808642B1 KR 1020160015712 A KR1020160015712 A KR 1020160015712A KR 20160015712 A KR20160015712 A KR 20160015712A KR 101808642 B1 KR101808642 B1 KR 101808642B1
- Authority
- KR
- South Korea
- Prior art keywords
- module
- log
- analysis
- regression
- value
- Prior art date
Links
Images
Classifications
-
- G06F17/30368—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G06F17/3007—
-
- G06F17/30318—
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The Big Data Log Predictive Analysis System of the present invention is a system for real-time calculation of predicted values for a log to be analyzed using measured values of a log to be analyzed obtained by collecting, processing and analyzing logs and a regression equation stored in the statistical prediction system Analysis system; And acquiring an analysis target log according to a predetermined period from the log analysis system to generate and store the regression equation for a log to be analyzed and obtaining an actual value and a calculated prediction value extracted from the log analysis system, And a statistical prediction system for comparing and analyzing the log data in real time, wherein the log analysis system comprises: a collection module for collecting logs; A parsing module for extracting a parameter value and an actual value of the log collected through the collection module in real time; A predicted value calculation module for calculating a predicted value for an analysis target log in real time using a parameter value extracted through the parsing module and a regression equation for an analysis target log stored in the statistical prediction system; A statistical database storing the processed logs processed and analyzed through the parsing module; And a file database in which an original log collected through the collection module is stored, wherein the statistical prediction system obtains a processing log or an original log from the statistical database or the file database as a log to be analyzed according to a predetermined cycle A log acquisition module; A log refinement module for refining an analysis target log acquired through the log acquisition module; A setup module for setting options for linear and logistic regression equations; A parameter selection module for selecting a parameter (parameter) of the analysis target log that is refined through the log refinement module according to an option set through the setup module; A linear regression module for generating a linear regression equation having the largest value of the adjusted decision factor (adjusted R 2 ) by combining the variables selected through the parameter selection module; A logistic regression module for generating a logistic regression equation having a largest modified correction factor (adjusted R 2 ) by combining the variables selected through the parameter selection module; A regression test module for performing regression analysis for testing the linear and logistic regression equations generated through the linear regression module and the logistic regression module; A regression formula storage module for storing linear and logistic regression equations verified by the regression equation test module; And a comparison and analysis module that obtains a predicted value computed through the predicted value computation module and an actual value extracted through the parsing module and compares and analyzes differences between values in real time.
According to the present invention, since the predictive value calculating module can calculate the predicted value of the log to be analyzed in real time using the regression formula generated through the statistical prediction system, it can respond promptly to security incidents and threats.
Description
The present invention relates to a big data log prediction analysis system.
Because Big Data is likened to crude oil in the 21st century, which starts to produce various values and determines future competitiveness, companies must understand and prepare for the upcoming data competition age.
In recent years, business success stories through statistical algorithm - based predictive analysis have been released, and are being transformed from post - measures based on historical data analysis to preemptive responses based on predictive analysis. Here, the predictive analysis encompasses various statistical techniques related to modeling, machine learning, and data mining, which are methods of analyzing current or past facts to perform predictions for future or unknown events.
This transition to preemptive response also affects security analytics and log analysis. In addition to analyzing, intelligent, and prolonged security analysis of large log (big data log) .
In this regard, the present applicant has proposed an integrated log analysis system of Korean Patent Registration No. 10-1484290 (hereinafter referred to as "prior art").
Specifically, the prior art is a technology capable of preemptively responding to security incidents and threats through regression analysis of analysis object information and time series analysis by performing prediction based on data stored in a statistical database.
Since the conventional technique performs indirect prediction analysis using only the log data stored in the statistical database, it is required to develop a technique for improving the accuracy and diversity of analysis, and a limited prediction analysis is performed through batch analysis It is necessary to develop a real-time prediction analysis technology that can calculate the predicted value of the log to be analyzed in real time and compare with the measured value.
Therefore, it is possible to improve the accuracy and diversity of analysis by performing direct prediction analysis using original log, to calculate the predicted value of the log to be analyzed in real time, and to perform real-time predictive analysis through comparison with actual value, The present invention provides a technique capable of promptly and promptly responding to a user's request.
The present invention has been made to solve the above problems, and it is an object of the present invention to provide a method and apparatus for performing a direct prediction analysis using an original log and automatically generating a regression equation for the self- And to provide a big data log prediction analysis system capable of calculating a predicted value for a log to be analyzed in real time.
In order to achieve the above object, a big data log predictive analysis system according to the present invention is characterized in that a large data log predictive analysis system for collecting, processing, and analyzing logs and using a measured value of a log to be analyzed and a regression equation stored in a statistical prediction system, A log analysis system for computing in real time; And acquiring an analysis target log according to a predetermined period from the log analysis system to generate and store the regression equation for a log to be analyzed and obtaining an actual value and a calculated prediction value extracted from the log analysis system, And a statistical prediction system for comparing and analyzing the log data in real time, wherein the log analysis system comprises: a collection module for collecting logs; A parsing module for extracting a parameter value and an actual value of the log collected through the collection module in real time; A predicted value calculation module for calculating a predicted value for an analysis target log in real time using a parameter value extracted through the parsing module and a regression equation for an analysis target log stored in the statistical prediction system; A statistical database storing the processed logs processed and analyzed through the parsing module; And a file database in which an original log collected through the collection module is stored, wherein the statistical prediction system obtains a processing log or an original log from the statistical database or the file database as a log to be analyzed according to a predetermined cycle A log acquisition module; A log refinement module for refining an analysis target log acquired through the log acquisition module; A setup module for setting options for linear and logistic regression equations; A parameter selection module for selecting a parameter (parameter) of the analysis target log that is refined through the log refinement module according to an option set through the setup module; A linear regression module for generating a linear regression equation having the largest value of the adjusted decision factor (adjusted R 2 ) by combining the variables selected through the parameter selection module; A logistic regression module for generating a logistic regression equation having a largest modified correction factor (adjusted R 2 ) by combining the variables selected through the parameter selection module; A regression test module for performing regression analysis for testing the linear and logistic regression equations generated through the linear regression module and the logistic regression module; A regression formula storage module for storing linear and logistic regression equations verified by the regression equation test module; And a comparison and analysis module that obtains a predicted value computed through the predicted value computation module and an actual value extracted through the parsing module and compares and analyzes differences between values in real time.
delete
delete
delete
The comparison and analysis module may include an error calculator for calculating an error by comparing a predicted value calculated through the predictive value calculation module with an actual value extracted through the parsing module; And an error determiner for determining whether the error value calculated through the error calculator is included in a predetermined reference error range.
In addition, when it is determined through the error determination unit that the error of the predicted value with respect to the measured value is out of the predetermined reference error range, the setup module resets the option for the corresponding regression equation.
The present invention has the following effects.
First, the log acquisition module not only can acquire or extract the processed logs stored in the statistical database, but also can acquire or extract the original logs stored in the file database, so that direct prediction analysis can be performed, Can be improved.
Second, since the comparison and analysis module is provided in the statistical prediction system, the statistical prediction system can automatically generate the self-verification and the improved regression equation by calculating the error of the predicted value with respect to the actual value of the analyzed log in real time, Predictive analysis can be performed.
Third, the predictive value calculation module can calculate the predicted value of the analyzed log in real time using the regression formula generated through the statistical prediction system, so that it can respond promptly to security incidents and threats.
1 is a block diagram showing a configuration of a big data log prediction analysis system according to the present invention.
Hereinafter, a detailed description of related art will be omitted if it is determined that the gist of the present invention may be unnecessarily obscured. In addition, numerals used in the description of the present invention are merely an identifier for distinguishing one component from another.
In addition, the terms used in the specification and claims should not be construed in a dictionary meaning, and the inventor may, on the principle that the inventor can properly define the concept of a term in order to explain its invention in the best way, And should be construed in light of the meanings and concepts consistent with the technical idea of the present invention.
Therefore, the embodiments shown in the present specification and the drawings are only exemplary embodiments of the present invention, and not all of the technical ideas of the present invention are presented. Therefore, various equivalents It should be understood that water and variations may exist.
The preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings.
< Big Data Description of log prediction analysis system>
1 is a block diagram showing a configuration of a big data log prediction analysis system according to the present invention.
1, a big data log prediction analysis system 10 includes a log analysis system 100 and a statistical prediction system 200. The system 10 includes a log analysis system 100 and a statistical prediction system 200 .
The log analysis system 100 is a configuration for collecting and processing logs and safely storing and analyzing them in a normalized or categorized form. The log analysis system 100 extracts or collects actual values of the log to be analyzed, .
The statistical prediction system 200 acquires an analysis target log according to a predetermined period from the log analysis system 100 and generates and stores a regression equation for the analysis target log for statistical prediction.
That is, the log analyzing system 100 calculates the predicted value of the log to be analyzed in real time using the actual value of the log to be analyzed and the regression equation stored in the statistical prediction system 200, and the statistical prediction system 200 ) Acquires the actual and predicted values extracted from the log analysis system and compares and analyzes the difference of the values in real time.
Hereinafter, detailed configurations in the log analysis system 100 and the statistical prediction system 200 will be described in detail so that the log analysis system 100 and the statistical prediction system 200 can perform the functions as described above .
The log analysis system 100 includes a collection module 110, a parsing module 120, an indexing module 130, an analysis module 140, a statistics database 150, a file database 160, And a predicted value calculation module 170.
Here, the collection module 110 collects logs, and the parsing module 120 extracts parameter values and actual values of logs collected through the collection module 110 in real time.
The indexing module 130 performs an indexing operation on the analyzed log through the parsing module 120. The analysis module 140 analyzes the indexed data through the indexing module 130, And the log is analyzed.
The statistical database 150 includes a parsing module 120 and indexing and analysis logs 140 stored in the indexing module 130 and the analysis module 140.
In addition, the file database 160 is a configuration in which original logs collected through the collection module 110 are stored. In this way, the original log stored through the file database 160 is preferably stored as a log of the normalized type.
In addition, the statistical prediction system 200 may be provided with a module for searching and extracting an original log stored in the file database 160. [
The predictive value calculation module 170 is a main constituent of the present invention and uses the parameter values of the log extracted through the parsing module 120 and the regression equations for the analysis target log stored in the statistical prediction system 200, And calculates a predicted value for the target pixel. The predicted value of the analysis target log calculated through the predictive value calculation module 170 is preferably stored in the statistical database 150. [
In addition, the predictive value calculation module 170 is not included in the log analysis system 100 according to the present invention, but may be separately provided for independent operation.
The statistical prediction system 200 includes a log acquisition module 210, a log refinement module 220, a setup module 230, a parameter selection module 240, a linear regression module 250, A regression equation module 260, a regression equation test module 270, a regression formula storage module 280, and a comparison analysis module 290.
Here, the log acquisition module 210 acquires from the statistical database 150 or the file database 160 an original log in the statistical database 150 or the file database 160 in the statistical database 150, .
That is, the log acquisition module 210 not only can acquire or extract the processing log stored in the statistics database 150, but also can perform direct prediction analysis because it can acquire or extract the original log stored in the file database 160 The accuracy and diversity of the analysis can be improved. The log acquisition module 210 is not included in the statistical prediction system 200 according to the embodiment, but can be separately provided for independent operation.
In addition, the log refinement module 220 refines the analysis target log obtained through the log acquisition module 210, and the setup module 230 uses a linear regression equation and a logistic regression equation Regression). That is, the setup module 230 may make various settings for generating linear regression and logistic regression models.
The parameter selection module 240 selects a variable (parameter) of the analyzed log through the log refining module 220 according to the option set through the setup module 230. [
In addition, the linear regression module 250 is configured to generate a linear regression equation having the largest modified correction factor (adjusted R 2 ) by combining the selected variables through the parameter selection module 240, and the logistic regression module 260 generates a logistic regression equation having the largest modified correction factor (adjusted R 2 ) by combining the selected variables through the parameter selection module 240.
In addition, the regression test module 270 may use regression analysis to test whether statistical problems with the linear regression and logistic regression equations generated through the linear regression module 250 and the logistic regression module 260 And the regression formula storage module 280 is a configuration for storing the linear regression equation and the logistic regression equation that are verified through the regression equation test module 270.
That is, the prediction value calculation module 170 acquires the parameter values for the log extracted through the parsing module 120, the linear regression equation and the logistic regression equation stored in the regression formula storage module 280, And calculates a predicted value.
Since the regression equation generated through the statistical prediction system 200 takes a lot of time and cost, the process log or the file database in the statistical database 150 160) is obtained or extracted as an analysis target log form to generate a regression equation.
Meanwhile, the comparison analysis module 290 obtains the predicted value of the analysis target log calculated through the predicted value calculation module 170 and the actual measurement value extracted through the parsing module 120, and compares and analyzes the difference of the values in real time to be. For this, the comparison analysis module 290 may include an error calculator 291 and an error calculator 292.
Here, the error calculating unit 291 compares the predicted value of the log to be analyzed calculated through the predicted value calculating module 170 with the actual value extracted through the parsing module 120 to calculate the error of the predicted value with respect to the measured value to be.
In addition, the error determination unit 292 determines whether the error value calculated by the error calculation unit 291 is included in the predetermined reference error range.
If it is determined through the error determination unit 292 that the error of the predicted value with respect to the actual value of the analysis target log is out of (or below) the predetermined reference error range (error tolerance range) , The regression equation based on the predicted value exceeding the reference error range is regenerated by resetting the option for the linear or logistic regression equation corresponding to the error value out of the preset reference error range and based on the regression formula thus regenerated The predictive value calculation module 170 re-computes the predictive value.
For example, if it is determined that the reference error range is less than 30%, if it is determined through the error determination unit 292 that the error of the predicted value with respect to the actual value of the log is greater than or equal to 30% (230) regenerates the regression equation by resetting the options for the corresponding linear or logistic regression equations. On the other hand, when the error of the predicted value with respect to the actual value of the analysis object log is determined to be less than 30% through the error determination unit 292, it is determined that the corresponding regression equation is highly reliable and the regression equation is regenerated You do not have to.
In addition, the error determination unit 292 may determine whether the outlier occurrence frequency is greater than the reference occurrence frequency of the predetermined outlier of the analysis target log within a predetermined time, 2 ) is less than the value of the modified decision coefficient (adjusted R 2 ). Accordingly, when it is determined through the error determination unit 292 that the value of the deviation value generation count or the adjustment decision coefficient (adjusted R 2 ) as described above is out of the reference value, the setup module 230 determines that the linear or non- The regression equation is regenerated by resetting the options for the logistic regression equation.
As described above, the predictive value calculation module 170 computes the predictive value for the analysis target log using the regression equation generated through the statistical prediction system 200, and the comparison and analysis module 290 compares the predictive value with the predictive value, Since the operation of comparing and analyzing the difference of the measured values extracted through the module 120 can save cost and time as compared with the operation of generating the regression equation described above, it is preferable to perform the analysis in real time.
Accordingly, the big data log predictive analysis system 10 of the present invention not only realizes highly reliable real-time predictive analysis by automatically generating verification and self-improved linearity or logistic, but also can save cost and time have.
Therefore, the big data log prediction analysis system 10 of the present invention can perform non-real-time and real-time predictive analysis through the log analysis system 100 and the statistical prediction system 200, It is possible to respond promptly and promptly to cyber attacks.
Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. And the scope of the present invention should be understood as the scope of the following claims and their equivalents.
Description of the Related Art [0002]
10: Big Data Log Prediction Analysis System
100: log analysis system
110: collection module
120: parsing module
130: Indexing module
140: Analysis module
150: Statistics database
160: File database
170: predicted value calculation module
200: Statistical forecasting system
210: log acquisition module
220: Log refinement module
230: Setup module
240: Parameter selection module
250: Linear regression module
260: Logistic regression module
270: regression test module
280: regression formula storage module
290: Comparative Analysis Module
291:
292:
Claims (6)
The log analyzing system obtains the analysis target log according to a predetermined period to generate and store the regression equation for the log to be analyzed and obtains the measured value and the calculated predicted value extracted from the log analysis system, And a statistical prediction system for comparing and analyzing in real time,
Wherein the log analysis system comprises:
A collection module for collecting logs;
A parsing module for extracting a parameter value and an actual value of the log collected through the collection module in real time;
A predicted value calculation module for calculating a predicted value for an analysis target log in real time using a parameter value extracted through the parsing module and a regression equation for an analysis target log stored in the statistical prediction system;
A statistical database storing the processed logs processed and analyzed through the parsing module; And
And a file database in which an original log collected through the collection module is stored,
The statistical prediction system includes:
A log acquisition module for acquiring, from the statistical database or the file database, a processing log or an original log as a log to be analyzed according to a predetermined cycle;
A log refinement module for refining an analysis target log acquired through the log acquisition module;
A setup module for setting options for linear and logistic regression equations;
A parameter selection module for selecting a parameter (parameter) of the analysis target log that is refined through the log refinement module according to an option set through the setup module;
A linear regression module for generating a linear regression equation having the largest value of the adjusted decision factor (adjusted R 2 ) by combining the variables selected through the parameter selection module;
A logistic regression module for generating a logistic regression equation having a largest modified correction factor (adjusted R 2 ) by combining the variables selected through the parameter selection module;
A regression test module for performing regression analysis for testing the linear and logistic regression equations generated through the linear regression module and the logistic regression module;
A regression formula storage module for storing linear and logistic regression equations verified by the regression equation test module; And
And a comparison and analysis module that obtains a predicted value computed through the predicted value computation module and an actual value extracted through the parsing module and compares and analyzes differences between values in real time.
Big Data Log Predictive Analysis System.
Wherein the comparison and analysis module comprises:
An error calculator for calculating an error by comparing a predicted value calculated through the predictive value calculation module with an actual value extracted through the parsing module; And
And an error determiner for determining whether the error value calculated through the error calculator is within a predetermined reference error range
Big Data Log Predictive Analysis System.
Wherein the setup module resets the option for the corresponding regression equation when it is determined through the error determination unit that the error of the predicted value with respect to the measured value is out of a predetermined reference error range,
Big Data Log Predictive Analysis System.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160015712A KR101808642B1 (en) | 2016-02-11 | 2016-02-11 | Big data log predictive analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160015712A KR101808642B1 (en) | 2016-02-11 | 2016-02-11 | Big data log predictive analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20170094661A KR20170094661A (en) | 2017-08-21 |
| KR101808642B1 true KR101808642B1 (en) | 2017-12-14 |
Family
ID=59757457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020160015712A KR101808642B1 (en) | 2016-02-11 | 2016-02-11 | Big data log predictive analysis system |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR101808642B1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102235712B1 (en) * | 2020-09-25 | 2021-04-05 | 주식회사 삼표산업 | Concrete slump prediction system |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101856543B1 (en) * | 2018-02-26 | 2018-05-11 | 주식회사 리앙커뮤니케이션즈 | Failure prediction system based on artificial intelligence |
| KR102396413B1 (en) * | 2020-06-25 | 2022-05-09 | 윤성종 | Social big data analysis report automatic provision system using big data and artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002505457A (en) | 1998-02-27 | 2002-02-19 | エムシーアイ・ワールドコム・インコーポレーテッド | System and method for extracting and predicting computing resource data, such as CPU consumption, using an auto-regression method |
| KR101264873B1 (en) * | 2012-08-07 | 2013-05-15 | 한국에너지기술연구원 | Wind power density prediction method using stepewise regression procedure |
| KR101484290B1 (en) | 2013-11-07 | 2015-01-20 | 유넷시스템주식회사 | Integrated log analysis system |
| KR101542235B1 (en) * | 2015-01-23 | 2015-08-06 | 주식회사 프로이트 | Method for mining of real-time data |
-
2016
- 2016-02-11 KR KR1020160015712A patent/KR101808642B1/en active IP Right Grant
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002505457A (en) | 1998-02-27 | 2002-02-19 | エムシーアイ・ワールドコム・インコーポレーテッド | System and method for extracting and predicting computing resource data, such as CPU consumption, using an auto-regression method |
| KR101264873B1 (en) * | 2012-08-07 | 2013-05-15 | 한국에너지기술연구원 | Wind power density prediction method using stepewise regression procedure |
| KR101484290B1 (en) | 2013-11-07 | 2015-01-20 | 유넷시스템주식회사 | Integrated log analysis system |
| KR101542235B1 (en) * | 2015-01-23 | 2015-08-06 | 주식회사 프로이트 | Method for mining of real-time data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102235712B1 (en) * | 2020-09-25 | 2021-04-05 | 주식회사 삼표산업 | Concrete slump prediction system |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20170094661A (en) | 2017-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11494594B2 (en) | Method for training model and information recommendation system | |
| KR101808642B1 (en) | Big data log predictive analysis system | |
| CN104615986B (en) | The method that pedestrian detection is carried out to the video image of scene changes using multi-detector | |
| US20160284344A1 (en) | Speech data recognition method, apparatus, and server for distinguishing regional accent | |
| EP3822977A1 (en) | Identification using spectroscopy | |
| RU2016118146A (en) | METHOD, SYSTEM AND COMPUTER PROGRAM FOR ACOUSTIC ANALYSIS OF THE MACHINE | |
| CN106407768B (en) | A kind of determination of device-fingerprint, the method and apparatus that target device is identified | |
| CN109684374B (en) | Method and device for extracting key value pairs of time series data | |
| CN106844170B (en) | Method and equipment for processing and analyzing fault influence surface | |
| CN106612511B (en) | Wireless network throughput evaluation method and device based on support vector machine | |
| CN109699003B (en) | Position determination method and device | |
| US20160188680A1 (en) | Electronic device and information searching method for the electronic device | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| US20200311401A1 (en) | Analyzing apparatus, control method, and program | |
| RU2015141553A (en) | System and method for detecting phishing scenarios | |
| CN110929644B (en) | Heuristic algorithm-based multi-model fusion face recognition method and device, computer system and readable medium | |
| US9418286B2 (en) | Information processing device, information processing method, and program | |
| KR20130075802A (en) | Detecting and tracing system of human using gradient histogram and method of the same | |
| KR102325629B1 (en) | Anomaly detecting method and anomaly detecting apparatus | |
| CN111835541B (en) | Method, device, equipment and system for detecting aging of flow identification model | |
| CN109359544B (en) | Portrait retrieval method and device | |
| CN112434648A (en) | Wall shape change detection method and system | |
| CN112434650A (en) | Multi-spectral image building change detection method and system | |
| CN111523308A (en) | Chinese word segmentation method and device and computer equipment | |
| CN117314919B (en) | Packaging bag production analysis method, system and storage medium based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A201 | Request for examination | ||
| E902 | Notification of reason for refusal | ||
| E701 | Decision to grant or registration of patent right | ||
| GRNT | Written decision to grant |