CN117194049A - Cloud host intelligent behavior analysis method and system based on machine learning algorithm - Google Patents
Cloud host intelligent behavior analysis method and system based on machine learning algorithm Download PDFInfo
- Publication number
- CN117194049A CN117194049A CN202311337589.XA CN202311337589A CN117194049A CN 117194049 A CN117194049 A CN 117194049A CN 202311337589 A CN202311337589 A CN 202311337589A CN 117194049 A CN117194049 A CN 117194049A
- Authority
- CN
- China
- Prior art keywords
- influence
- information
- analysis
- analyzed
- target
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 73
- 230000006399 behavior Effects 0.000 title claims abstract description 36
- 238000010801 machine learning Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000001052 transient effect Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 1
- 238000012806 monitoring device Methods 0.000 description 4
- 240000006409 Acacia auriculiformis Species 0.000 description 3
- 210000005069 ears Anatomy 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a cloud host intelligent behavior analysis method and a cloud host intelligent behavior analysis system based on a machine learning algorithm, and the cloud host intelligent behavior analysis method comprises an information intelligent acquisition unit, a self-adaptive processing analysis unit and an information output unit.
Description
Technical Field
The application relates to the technical field of intelligent behavior analysis of cloud hosts, in particular to a cloud host intelligent behavior analysis method and system based on a machine learning algorithm.
Background
Machine learning is a multi-domain interdisciplinary, and relates to multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like, and cloud host behavior data refers to information for recording and describing various operations and behaviors of a cloud host in the running process.
According to the patent application number CN200810211334.8, the patent comprises at least one terminal client provided with an auris Free card, at least one machine room manager provided with an auris Free card and at least one monitoring device, wherein the auris Free card is connected with a router or a switch through a network cable, the monitoring device is connected with the router or the switch through the network cable, and the monitoring device is a SmartTrack intelligent image processor or a behavior recognition monitoring device i vBox. The intelligent analysis system for the computer user behavior combines intelligent digital video monitoring equipment with machine room management, performs intelligent analysis on various machine behaviors of users in the network cluster, and ensures scientificity and standardization of machine management in the network cluster.
Part of the existing cloud host behavior is usually monitored when the cloud host behavior is analyzed, abnormal behavior or fault conditions are displayed, but specific reasons for the abnormal conditions are not reasonably analyzed, so that the same errors can occur in the follow-up operation, the overall operation state can be further influenced, and the use experience of a user can be reduced.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a cloud host intelligent behavior analysis method and a cloud host intelligent behavior analysis system based on a machine learning algorithm, which solve the problem that the abnormal situation is not reasonably analyzed, and the overall running state is affected in the follow-up running process.
In order to achieve the above purpose, the application is realized by the following technical scheme: a cloud host intelligent behavior analysis system based on a machine learning algorithm, comprising:
the information intelligent acquisition unit is used for acquiring basic information of a target object and transmitting the basic information to the self-adaptive processing analysis unit, wherein the target object is: the cloud host runs a program, and the basic information comprises: computing resources;
the self-adaptive processing unit is used for acquiring and analyzing the transmitted basic information of the target object, analyzing the running state of the target object, and classifying the target object according to the resource consumption to obtain a classification result, wherein the classification result comprises the following steps: the high-consumption object and the normal-consumption object, and transmitting the classification result to the behavior preprocessing analysis unit, wherein the specific classification mode is as follows:
s1: the target object is obtained, marked and recorded as i, i=1, 2, … and j, the calculation resource occupation ratio record of the target object in unit time is obtained as Zi, and the calculation resource occupation ratio average value record of the target object i in the time period T is obtained as Zi p The method comprises the steps of carrying out a first treatment on the surface of the Here, the resource occupation ratio and the resource consumption are the same concept.
S2: then the calculated target object calculation resource duty ratio mean Zi p Sequencing from small to large, calculating the average value of all target objects as Zp, and simultaneously recording Zi p Comparing with Zp, zi p Classifying target objects corresponding to ≡zp as high-consumption objects, and classifying Zi p <The target object corresponding to Zp is classified as a normal consumption object;
the data storage unit is used for storing the history information and transmitting the history information to the behavior preprocessing analysis unit;
the behavior preprocessing analysis unit is used for acquiring and analyzing the transmitted classification result, acquiring the history information stored by the data storage unit, generating an analysis result by combining the history information with analysis of the high-consumption object in the classification result, transmitting the analysis result to the information output unit, and generating the analysis result in the following specific mode:
p1: obtaining all running target objects, judging classification results of the target objects, obtaining objects to be analyzed, and comparing the objects to be analyzed with the target objects to obtain analysis information, wherein the analysis information specifically comprises: the influence information exists and the influence information does not exist, and the specific mode for obtaining the analysis information is as follows:
p11: the running target object is marked as n, n=1, 2, … and m, the corresponding CPU occupation ratio is obtained and recorded as Cn, then the object to be analyzed is obtained, and whether the running of the object to be analyzed affects the CPU occupation ratio of the running target object is judged;
p12: when an object to be analyzed runs, the object Cn corresponding to the running object changes, the influence between the object Cn and the object is indicated, meanwhile, the time value of the change of the object Cn is obtained, otherwise, the influence between the object Cn and the object is not indicated;
p2: then, a target object with influence corresponding to the object to be analyzed is obtained and marked as an object with influence, a=1, 2, … and b are marked at the same time, a corresponding time value is obtained and marked as Ta, and then the target object with influence is classified according to the time value Ta, wherein the specific classification processing mode is as follows:
acquiring a final value of CPU occupation ratio change in a time value Ta, comparing the final value with a starting value of an influence object, classifying the influence object as a transient influence object when the final value is the same as the starting value, and not performing any processing, otherwise classifying the influence object as a permanent influence object when the final value is different from the starting value; the final value is represented as the CPU occupation ratio of the whole influence object after the change, and the initial value is represented as the average value after the CPU occupation ratio is stable in the running process of the influence object;
p3: the method comprises the steps of obtaining a permanent influence object, carrying out label processing on the permanent influence object and marking the permanent influence object as y, wherein y=1, 2, … and k, obtaining a corresponding network occupation value of the permanent influence object in the history information under a normal operation state, and carrying out analysis and comparison on the permanent influence object according to the network occupation value to obtain an analysis result, wherein the specific processing mode is as follows:
p31: the permanently affected object of any one label is obtained and taken as a label object, and the label object in s time periods t is obtainedIs used as Gs, and calculates the average value of the network duty ratio of the label object as Gs p The method comprises the steps of carrying out a first treatment on the surface of the It should be noted that the network occupation ratio is expressed as a network occupation ratio required by the labeled object when running.
P32: then the network occupation value of the operation mark object of the object to be analyzed is obtained and recorded as Gz p At the same time Gs p And Gz p Comparing when Gs p ≥Gz p When the Gs are used for analyzing the label object, the influence of the object to be analyzed on the label object is represented and influence interference information is generated p <Gz p And when the method is used, the object to be analyzed does not influence the label object, generates influence non-interference information, and similarly obtains all target objects to be analyzed to obtain corresponding analysis results. It should be noted that Gzp is represented as a network duty average of the whole labeled object in a time period in which the object to be analyzed operates;
and the information output unit is used for acquiring the transmitted analysis result and displaying the analysis result to an operator through the display equipment.
Advantageous effects
The application provides a cloud host intelligent behavior analysis method and system based on a machine learning algorithm. Compared with the prior art, the method has the following beneficial effects:
according to the application, different running programs are subjected to high-consumption and normal-consumption classification processing according to the CPU occupation ratio, so that a user can conveniently and quickly identify the running states of the different programs, whether the running effects exist among the different programs or not is judged according to the network occupation ratio, analysis and judgment are performed according to the generated real-time data, so that the accuracy and scientificity of analysis are ensured, and finally, the analysis results are collected and output to an operator, so that the operator can conveniently avoid the mutual interference during the running of the different programs, and the overall use experience is improved.
Drawings
FIG. 1 is a flow chart of a system of the present application;
FIG. 2 is a flow chart of the method of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, the present application provides a cloud host intelligent behavior analysis system based on a machine learning algorithm, including:
the information intelligent acquisition unit is used for acquiring basic information of a target object and transmitting the basic information to the self-adaptive processing analysis unit, wherein the target object is: the cloud host runs a program, and the basic information comprises: computing resources. Here, it should be noted that the computing resources include: CPU resources, memory resources, hard disk resources and network resources, and the cloud host running program is all installed programs.
The self-adaptive processing unit is used for acquiring and analyzing the transmitted basic information of the target object, analyzing the running state of the target object, and classifying the target object according to the resource consumption to obtain a classification result, wherein the classification result comprises the following steps: the high-consumption object and the normal-consumption object, and transmits the classification result to the behavior preprocessing analysis unit, and the specific mode of generating the classification result is as follows:
s1: the target object is obtained, marked and recorded as i, i=1, 2, … and j, the calculation resource occupation ratio record of the target object in unit time is obtained as Zi, and the calculation resource occupation ratio average value record of the target object i in the time period T is obtained as Zi p The method comprises the steps of carrying out a first treatment on the surface of the Here, the resource occupation ratio and the resource consumption are the same concept.
S2: then the calculated target object calculation resource duty ratio mean Zi p Sequencing from small to large, calculating the average value of all target objects as Zp, and simultaneously recording Zi p Comparing with Zp, zi p Classifying target objects corresponding to ≡zp as high-consumption objects, and classifying Zi p <The target object corresponding to Zp is classified as a normal consumption object.
The behavior preprocessing analysis unit is used for acquiring and analyzing the transmitted classification result, acquiring the history information stored by the data storage unit, generating an analysis result by combining the history information with analysis of the high-consumption object in the classification result, transmitting the analysis result to the information output unit, and generating the analysis result in the following specific mode:
p1: obtaining all running target objects, judging classification results of the target objects, obtaining objects to be analyzed, and comparing the objects to be analyzed with the target objects to obtain analysis information, wherein the analysis information specifically comprises: the influence information exists and the influence information does not exist, and the specific way of generating the analysis information is as follows:
p11: the running target object is marked as n, n=1, 2, … and m, the corresponding CPU occupation ratio is obtained and recorded as Cn, then the object to be analyzed is obtained, and whether the running of the object to be analyzed affects the CPU occupation ratio of the running target object is judged;
p12: when the object to be analyzed runs, the object Cn corresponding to the running object changes, the influence between the object Cn and the object is indicated, meanwhile, the time value of the change of the object Cn is obtained, and otherwise, the influence between the object Cn and the object is not indicated.
It should be noted that, the object to be analyzed represents a program to be run by the cloud host, the classification result of the judging target object is embodied as judging whether the running target object is a high-consumption object or a normal-consumption object, and the time value is represented as the time length of the change, and is embodied as the time from the change to the last stable value.
P2: then, a target object with influence corresponding to the object to be analyzed is obtained and marked as an object with influence, a=1, 2, … and b are marked at the same time, a corresponding time value is obtained and marked as Ta, and then, the target object with influence is classified according to the time value Ta, wherein the specific classification method is as follows:
acquiring a final value of CPU occupation ratio change in a time value Ta, comparing the final value with a starting value of an influence object, classifying the influence object as a transient influence object when the final value is the same as the starting value, and not performing any processing, otherwise classifying the influence object as a permanent influence object when the final value is different from the starting value; the final value is expressed as the CPU occupation ratio of the whole of the affected object after the change, and the initial value is expressed as the average value after the CPU occupation ratio is stabilized during the operation of the affected object.
P3: the method comprises the steps of obtaining a permanent influence object, carrying out label processing on the permanent influence object and marking the permanent influence object as y, wherein y=1, 2, … and k, obtaining a corresponding network occupation value of the permanent influence object in the history information under a normal operation state, analyzing and comparing the permanent influence object according to the network occupation value to obtain an analysis result, and generating the analysis result in the following specific mode:
p31: acquiring a permanent influence object of any label and taking the permanent influence object as a label object, simultaneously acquiring a network duty ratio record of the label object within s time periods t as Gs, and calculating a label object network duty ratio average value record as Gs p The method comprises the steps of carrying out a first treatment on the surface of the It should be noted that the network occupation ratio is expressed as a network occupation ratio required by the labeled object when running.
P32: then the network occupation value of the operation mark object of the object to be analyzed is obtained and recorded as Gz p At the same time Gs p And Gz p Comparing when Gs p ≥Gz p When the Gs are used for analyzing the label object, the influence of the object to be analyzed on the label object is represented and influence interference information is generated p <Gz p And when the method is used, the object to be analyzed does not influence the label object, generates influence non-interference information, and similarly obtains all target objects to be analyzed to obtain corresponding analysis results. It should be noted that Gzp is represented as a network duty average of the whole labeled object during a time period in which the object to be analyzed operates.
And the information output unit is used for acquiring the transmitted analysis result and displaying the analysis result to an operator through the display equipment.
A cloud host intelligent behavior analysis method based on a machine learning algorithm specifically comprises the following steps:
step one: firstly, classifying high-consumption objects and normal-consumption objects of a cloud host running program through resource consumption to obtain classification results;
step two: then analyzing the high-consumption object according to the CPU occupation ratio and obtaining the influence information and the influence information which do not exist;
step three: then judging and analyzing the time corresponding to the information of the existence influence, and classifying the existence influence into a short-lived existence influence and a permanent existence influence according to the time;
step four: and finally, analyzing the target object corresponding to the permanent influence according to the network occupation value and obtaining influence interference information and influence non-interference information.
Some of the data in the above formulas are numerical calculated by removing their dimensionality, and the contents not described in detail in the present specification are all well known in the prior art.
The above embodiments are only for illustrating the technical method of the present application and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present application may be modified or substituted without departing from the spirit and scope of the technical method of the present application.
Claims (7)
1. The cloud host intelligent behavior analysis system based on the machine learning algorithm is characterized by comprising:
the information intelligent acquisition unit is used for acquiring basic information of a target object and transmitting the basic information to the self-adaptive processing analysis unit, wherein the target object is: the cloud host runs a program, and the basic information comprises: computing resources;
the self-adaptive processing unit is used for acquiring and analyzing the transmitted basic information of the target object, analyzing the running state of the target object, and classifying the target object according to the resource consumption to obtain a classification result, wherein the classification result comprises the following steps: high-consumption objects and normal-consumption objects, and transmitting classification results to a behavior preprocessing analysis unit;
the data storage unit is used for storing the history information and transmitting the history information to the behavior preprocessing analysis unit;
the behavior preprocessing analysis unit is used for acquiring and analyzing the transmitted classification result, acquiring the history information stored by the data storage unit, generating an analysis result by combining the history information with the analysis of the high-consumption object in the classification result, and transmitting the analysis result to the information output unit;
and the information output unit is used for acquiring the transmitted analysis result and displaying the analysis result to an operator through the display equipment.
2. The intelligent behavior analysis system of a cloud host based on a machine learning algorithm according to claim 1, wherein the specific way for the adaptive processing unit to generate the classification result is:
s1: the target object is obtained, marked and recorded as i, i=1, 2, … and j, the calculation resource occupation ratio record of the target object in unit time is obtained as Zi, and the calculation resource occupation ratio average value record of the target object i in the time period T is obtained as Zi p ；
S2: then the calculated target object calculation resource duty ratio mean Zi p Sequencing from small to large, calculating the average value of all target objects as Zp, and simultaneously recording Zi p Comparing with Zp, zi p Classifying target objects corresponding to ≡zp as high-consumption objects, and classifying Zi p <The target object corresponding to Zp is classified as a normal consumption object.
3. The intelligent behavior analysis system of a cloud host based on a machine learning algorithm according to claim 1, wherein the specific manner of generating the analysis result by the behavior preprocessing unit is as follows:
p1: obtaining all running target objects, judging classification results of the target objects, obtaining objects to be analyzed, and comparing the objects to be analyzed with the target objects to obtain analysis information, wherein the analysis information specifically comprises: presence and absence of influence information;
p2: then, a target object with influence corresponding to the object to be analyzed is obtained and is marked as an object with influence, a=1, 2, … and b are marked at the same time, a corresponding time value is obtained and is marked as Ta, and then the object with influence is classified according to the time value Ta;
p3: and obtaining a corresponding network occupation ratio of the permanently influenced object in the history information under the normal running state, and analyzing and comparing the permanently influenced object according to the network occupation ratio to obtain an analysis result.
4. The intelligent behavior analysis system of cloud host based on machine learning algorithm as set forth in claim 3, wherein the specific way of generating analysis information in P1 is as follows:
p11: the running target object is marked as n, n=1, 2, … and m, the corresponding CPU occupation ratio is obtained and recorded as Cn, then the object to be analyzed is obtained, and whether the running of the object to be analyzed affects the CPU occupation ratio of the running target object is judged;
p12: when the object to be analyzed runs, the object Cn corresponding to the running object changes, the influence between the object Cn and the object is indicated, meanwhile, the time value of the change of the object Cn is obtained, and otherwise, the influence between the object Cn and the object is not indicated.
5. The intelligent behavior analysis system of a cloud host based on a machine learning algorithm according to claim 3, wherein the specific classification processing mode in P2 is:
and acquiring a final value of the CPU duty ratio change in the time value Ta, comparing the final value with a starting value of the influence object, classifying the influence object as a transient influence object when the final value is the same as the starting value, and not performing any processing, otherwise classifying the influence object as a permanent influence object when the final value is different from the starting value.
6. The intelligent behavior analysis system of a cloud host based on a machine learning algorithm according to claim 3, wherein the specific processing manner in P3 is as follows:
p31: acquiring a permanent influence object of any label and taking the permanent influence object as a label object, simultaneously acquiring a network duty ratio record of the label object within s time periods t as Gs, and calculating a label object network duty ratio average value record as Gs p ；
P32: then the network occupation value of the operation mark object of the object to be analyzed is obtained and recorded as Gz p At the same time Gs p And Gz p Comparing when Gs p ≥Gz p When the Gs are used for analyzing the label object, the influence of the object to be analyzed on the label object is represented and influence interference information is generated p <Gz p And when the method is used, the object to be analyzed does not influence the label object, generates influence non-interference information, and similarly obtains all target objects to be analyzed to obtain corresponding analysis results.
7. A cloud host intelligent behavior analysis method based on a machine learning algorithm according to any one of claims 1-6, characterized in that the method specifically comprises the following steps:
step one: firstly, classifying high-consumption objects and normal-consumption objects of a cloud host running program through resource consumption to obtain classification results;
step two: then analyzing the high-consumption object according to the CPU occupation ratio and obtaining the influence information and the influence information which do not exist;
step three: then judging and analyzing the time corresponding to the information of the existence influence, and classifying the existence influence into a short-lived existence influence and a permanent existence influence according to the time;
step four: and finally, analyzing the target object corresponding to the permanent influence according to the network occupation value and obtaining influence interference information and influence non-interference information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337589.XA CN117194049B (en) | 2023-10-16 | 2023-10-16 | Cloud host intelligent behavior analysis method and system based on machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337589.XA CN117194049B (en) | 2023-10-16 | 2023-10-16 | Cloud host intelligent behavior analysis method and system based on machine learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117194049A true CN117194049A (en) | 2023-12-08 |
| CN117194049B CN117194049B (en) | 2024-02-27 |
Family
ID=88994401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311337589.XA Active CN117194049B (en) | 2023-10-16 | 2023-10-16 | Cloud host intelligent behavior analysis method and system based on machine learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194049B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944707A (en) * | 2017-11-28 | 2018-04-20 | 广东华仝九方科技有限公司 | A kind of deduction of points computational methods of terminal fitness |
| KR20180076838A (en) * | 2016-12-28 | 2018-07-06 | 부산대학교 산학협력단 | System and Method for Analyzing Access Information based on Intelligent Vision Processing |
| CN111654343A (en) * | 2020-06-04 | 2020-09-11 | 马霖 | Resource allocation system and method based on mobile communication network |
| CN112084040A (en) * | 2020-09-28 | 2020-12-15 | 上海道客网络科技有限公司 | Container resource planning system and method based on application mirror image data identification |
| CN115981806A (en) * | 2022-12-04 | 2023-04-18 | 复旦大学 | Self-adaptive risk-resistant Kubernets cluster scheduling method based on penalty factors |
-
2023
- 2023-10-16 CN CN202311337589.XA patent/CN117194049B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20180076838A (en) * | 2016-12-28 | 2018-07-06 | 부산대학교 산학협력단 | System and Method for Analyzing Access Information based on Intelligent Vision Processing |
| CN107944707A (en) * | 2017-11-28 | 2018-04-20 | 广东华仝九方科技有限公司 | A kind of deduction of points computational methods of terminal fitness |
| CN111654343A (en) * | 2020-06-04 | 2020-09-11 | 马霖 | Resource allocation system and method based on mobile communication network |
| CN112084040A (en) * | 2020-09-28 | 2020-12-15 | 上海道客网络科技有限公司 | Container resource planning system and method based on application mirror image data identification |
| CN115981806A (en) * | 2022-12-04 | 2023-04-18 | 复旦大学 | Self-adaptive risk-resistant Kubernets cluster scheduling method based on penalty factors |
Non-Patent Citations (1)
| Title |
|---|
| 班晏子婧 等: "面向Web应用的智能监控系统的设计与实现", 《智能计算机与应用》, 30 September 2022 (2022-09-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117194049B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190228296A1 (en) | Significant events identifier for outlier root cause investigation | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN113518011B (en) | Abnormality detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN111475680A (en) | Method, device, equipment and storage medium for detecting abnormal high-density subgraph | |
| US20060173559A1 (en) | Methods and systems for a prediction model | |
| US11620474B2 (en) | Model reselection for accommodating unsatisfactory training data | |
| CN109660533B (en) | Method and device for identifying abnormal flow in real time, computer equipment and storage medium | |
| CN116975938B (en) | Sensor data processing method in product manufacturing process | |
| US10705940B2 (en) | System operational analytics using normalized likelihood scores | |
| CN111754241A (en) | User behavior perception method, device, equipment and medium | |
| CN115828145A (en) | Online monitoring method, system and medium for electronic equipment | |
| JP3718765B2 (en) | Plant diagnostic equipment | |
| CN114047710A (en) | Intelligent household data analysis method and device, terminal equipment and storage medium | |
| CN113518058B (en) | Abnormal login behavior detection method and device, storage medium and computer equipment | |
| CN117194049B (en) | Cloud host intelligent behavior analysis method and system based on machine learning algorithm | |
| CN114297034B (en) | Cloud platform monitoring method and cloud platform | |
| CN109978038B (en) | Cluster abnormity judgment method and device | |
| CN113656452A (en) | Method and device for detecting abnormal index of call chain, electronic equipment and storage medium | |
| CN112862019A (en) | Method for dynamically screening aperiodic anomaly | |
| CN113569879A (en) | Training method of abnormal recognition model, abnormal account recognition method and related device | |
| CN110365650A (en) | A kind of industry internet risk monitoring method, system, device and storage medium | |
| CN110569277A (en) | Method and system for automatically identifying and classifying configuration data information | |
| CN112651447B (en) | Ontology-based resource classification labeling method and system | |
| CN115292146B (en) | System capacity estimation method, system, equipment and storage medium | |
| JP7401747B2 (en) | Sorting program, sorting device and sorting method |
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 |