CN113610190B - Abnormal network behavior mining system based on big data - Google Patents
Abnormal network behavior mining system based on big data Download PDFInfo
- Publication number
- CN113610190B CN113610190B CN202110975586.3A CN202110975586A CN113610190B CN 113610190 B CN113610190 B CN 113610190B CN 202110975586 A CN202110975586 A CN 202110975586A CN 113610190 B CN113610190 B CN 113610190B
- Authority
- CN
- China
- Prior art keywords
- task
- operator
- data
- calculation
- network behavior
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Virology (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses an abnormal network behavior mining system based on big data, which comprises a basic service layer, a calculation and storage layer and an application layer, wherein the basic service layer provides data calculation, data storage and task management capability for upper layer services by depending on a Hadoop cluster ecological environment; the computing and storage layer is used as a core of the abnormal network behavior mining system, supports operator model compiling and computing tasks submitted by the application layer, and stores computing results into corresponding databases; the application layer supports analysts to write an operator model in the form of a graphical page through a WEB system, submits tasks to a big data cluster for calculation after compiling is completed, and analyzes task results through data overview. The system can write the slave task execution flow, monitor the task flow, preview the one-stop flow of the task result, simplify the submission difficulty of the big data mining task, provide user authority layering, and better manage the user task and the user task data.
Description
Technical Field
The invention belongs to the technical field of networks, and particularly relates to an abnormal network behavior mining system based on big data.
Background
At present, network attack methods are more and more diversified, and excavation models are also continuously complicated. Analysts are urgent to autonomously design attack mining models aiming at different attacks, suspicious clues are found from a large amount of multi-source heterogeneous data, and at present, a plurality of relational databases are used for storing multi-source heterogeneous data accessed from multiple channels, and operators are written, compiled and scheduled all by hand; adopting traditional office tools to carry out data statistics, summarization and display;
however, the traditional relational database has the defects that the size of data stored in the relational database is limited, massive data cannot be stored, the requirement on the data structure is very high, most of the data is heterogeneous data because the analysis data come from different channels, the data structure is more various, and a plurality of heterogeneous data cannot be stored in one table at the same time, so that the analysis operation of each dimension under various requirements cannot be met; the operator is written, compiled and scheduled by full hands, so that the working efficiency is low, and the processing capacity is limited; the prior art cannot meet the service requirement, so we propose an abnormal network behavior mining system based on big data.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an abnormal network behavior mining system based on big data, through the system, the task execution flow writing, the task flow monitoring, the task result previewing one-stop flow, the submission difficulty of big data mining tasks is simplified, the user authority layering is provided, and the user tasks and the user task data are better managed.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the abnormal network behavior mining system based on big data comprises a basic service layer, a calculation and storage layer and an application layer, wherein the basic service layer is used for providing data calculation, data storage and task management capability for upper layer services by depending on a Hadoop cluster ecological environment;
the computing and storage layer is used as a core of the abnormal network behavior mining system, supports operator model compiling and computing tasks submitted by the application layer, and stores computing results into corresponding databases;
and the application layer supports analysts to write an operator model in the form of a graphical page through a WEB system, submits tasks to a big data cluster for calculation after compiling, and supports subsequent business decisions through data overview analysis of task results.
Preferably, in the application layer, the specific method for writing the operator model by the analyst is as follows:
1) An analyst creates operator configuration at an abnormal network behavior mining platform end according to specific service requirements, writes operator model codes based on the service requirements, submits the codes to a system Server end after the operator model codes are completed, the Server end issues complete model codes to a Hadoop cluster for compiling operation, and waits for a compiling result to return to a WEB end;
2) After the operator model is successfully compiled, a calculation task is created on an abnormal network behavior mining platform, and an operator and task attributes which are successfully compiled are configured and then submitted to a system Server end, a calculation engine of the Server end submits the task to a Hadoop cluster to wait for task queue to be executed after preprocessing operations such as task decomposition and data connection, and task states are detected at regular time and returned to the WEB end;
3) After the task execution is completed, the task execution result can be checked and analyzed through data preview, and the subsequent decision of the service is guided according to the task execution result.
Preferably, the calculation and storage layer adopts Spark as a calculation basis of an operator task, and Spark is a general large-scale data processing engine for open source, and the operator task can be rapidly submitted to a distributed cluster for calculation and processing through the framework.
Preferably, the operator model: mathematically, it can be interpreted as a function space to function space mapping O: x- > X is a processing unit, often refers to a function, and when an operator is used, input and output are often generated, the operator finishes conversion of corresponding data, in the project, an operator task is compiled and submitted mainly through an excavating platform, and finally the task is submitted to a big data platform to finish calculation and storage.
Preferably, the operator task is responsible for submitting a certain operator successfully compiled to a certain node of the cluster, and completing subsequent calculation and output operations.
Preferably, operator types for dividing operators into business logic are arranged in the operator model, so that analysts can classify and merge different operators conveniently.
Preferably, the user of the system logs in through the administrator user at first, and the user name can be used for logging in the system through the new role and the user added by the user module;
after successful login, the system related technical indexes and the health state of the target cluster are displayed in a dashboard form through a home page, so that the overall operation overview data of the system is observed.
Preferably, the operator management of the system specifically comprises: clicking a new operator, and enabling a user to newly add operator codes according to operator constraint requirements, and compiling, checking, saving, deleting and updating own operators;
the task management is specifically as follows: clicking to create a task, checking an operator which is compiled according to a system prompt, supporting configuration of configuring a Crontab for timing execution, starting execution of the task after issuing the task, warehousing a task result, and performing task storage, updating, deleting and task issuing execution; the viewing of the real-time state of the task is supported, and clicking on the relevant task can view the task execution result data.
The invention has the technical effects and advantages that: compared with the traditional abnormal network behavior mining system, the abnormal network behavior mining system based on big data provided by the invention supports the storage and retrieval of massive threat metadata by relying on the mature and open-source big data related technology; adopting a stable universal basic operator, submitting a platform on line, compiling an operator task to a big data cluster, and enabling a user to simply operate on the web to call the operator; and the data, operators, tasks and the like in the analysis platform can be uniformly managed and displayed through the visualization operation, and the visualized construction and test of various autonomous professional analysis models and the multidimensional display statistical analysis summary effect data can be realized.
Drawings
FIG. 1 is a diagram of an abnormal network behavior mining system architecture based on big data according to the present invention;
FIG. 2 is a flow chart of the computation of an operator task submission distributed cluster of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent. 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 invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides an abnormal network behavior mining system based on big data as shown in fig. 1-2, which comprises a basic service layer, a calculation and storage layer and an application layer, and is characterized in that: the basic service layer provides data computing, data storage and task management capabilities for upper layer services by means of the Hadoop cluster ecological environment;
the computing and storage layer is used as a core of the abnormal network behavior mining system, supports operator model compiling and computing tasks submitted by the application layer, and stores computing results into corresponding databases;
the application layer supports analysts to write an operator model in the form of a graphical page through a WEB system, submits tasks to a big data cluster for calculation after compiling is completed, analyzes task results through data overview, and supports subsequent business decisions;
the operator model: mathematically, it can be interpreted as a function space to function space mapping O: x- > X is a processing unit, often refers to a function, when operators are used, the operators often have input and output, the operators finish conversion of corresponding data, in the project, the operator tasks are compiled and submitted through a mining platform, and finally the tasks are submitted to a big data platform to finish calculation and storage, the operator tasks are responsible for submitting an operator successfully compiled to a certain node of a cluster to finish subsequent calculation and output operation, operator types for dividing business logic of the operators are arranged in an operator model, and the operators are convenient for analysts to classify and merge different operators;
supporting the storage and retrieval of massive threat metadata by relying on the mature open-source big data related technology; adopting a stable universal basic operator, submitting a platform on line, compiling an operator task to a big data cluster, and enabling a user to simply operate on the web to call the operator; the data, operators, tasks and the like in the analysis platform can be uniformly managed and displayed through the visualization operation, and the visualized construction and test of various autonomous professional analysis models and the multidimensional display statistical analysis summary effect data can be realized;
in the application layer, the specific method for writing the operator model by the analyst is as follows:
1) An analyst creates operator configuration at an abnormal network behavior mining platform end according to specific service requirements, writes operator model codes based on the service requirements, submits the codes to a system Server end after the operator model codes are completed, the Server end issues complete model codes to a Hadoop cluster for compiling operation, and waits for a compiling result to return to a WEB end;
2) After the operator model is successfully compiled, a calculation task is created on an abnormal network behavior mining platform, and an operator and task attributes which are successfully compiled are configured and then submitted to a system Server end, a calculation engine of the Server end submits the task to a Hadoop cluster to wait for task queue to be executed after preprocessing operations such as task decomposition and data connection, and task states are detected at regular time and returned to the WEB end;
3) After the task execution is completed, the task execution result can be checked and analyzed through data preview, and the subsequent decision of the service is guided according to the task execution result;
the application layer has: operator configuration and management, task management, preview, registration login and other functions, and the system has access control and supports multi-user authority allocation and control; the system is matched with a support operator to configure, compile and release to a big data platform to complete the execution and calculation of the task, and can adopt a visual mode to check the execution state of the task and the final data analysis and statistics summary of each dimension, so that the disaster recovery system is integrally equipped;
the calculation and storage layer adopts Spark as a calculation basis of an operator task, and Spark is a general large-scale data processing engine with open sources, and the operator task can be rapidly submitted to a distributed cluster for calculation and processing through the framework;
the system user logs in through the administrator user first, adds roles and users through the user module, and can log in the system with the user name;
after successful login, the system related technical indexes and the health state of the target cluster are displayed in a dashboard form through a home page, so that the overall operation overview data of the system is observed;
the operator management of the system is specifically as follows: clicking a new operator, and enabling a user to newly add operator codes according to operator constraint requirements, and compiling, checking, saving, deleting and updating own operators;
the task management is specifically as follows: clicking to create a task, checking an operator which is compiled according to a system prompt, supporting configuration of configuring a Crontab for timing execution, starting execution of the task after issuing the task, warehousing a task result, and performing task storage, updating, deleting and task issuing execution; the real-time state check of the task is supported, and the execution result data of the task can be checked by clicking the related task; the system can write from the task execution flow, monitor the task flow, preview one-stop flow of the task result, simplify the submission difficulty of big data mining tasks, provide user permission layering, and better manage user tasks and user task data;
optionally, the system mixes a multi-classification naive Bayes algorithm and a two-step screening incremental learning method; firstly, scanning current network behavior data by using a white list scanning engine to acquire normal behaviors for incremental learning; and obtaining the abnormal behavior by utilizing the output of the known abnormal behavior feature matching engine. The method comprises the steps of obtaining an original incremental training set DT comprising abnormal behaviors and normal behaviors, then adding the two-step screening to the incremental training set to train an existing model, and mixing a multi-classification naive Bayes algorithm:
let x= { X1, X2,.,. The term "xk" is a data tuple, which is described by k attributes { A1, A2,.,. Ak }; let D be the set of training tuples and associated class labels (training set). Assuming that there are n+1 class attribute values c= { C0, C1,..once, cn }, for a given tuple X, the naive bayes classification predicts the probability that X belongs to class Ci under the highest probability conditions, if and only if P (ci|x) > P (cj|x), (0+.ltoreq.j+.n, i+.j) since it is a fixed constant for all classes, according to the bayesian theorem it is only necessary to determine P (x|ci) P (Ci) max: that is, to predict class labels of X, P (X|Ci) P (Ci) is calculated for each class Ci;
the attribute values selected in the mobile internet industrial control network request are mutually independent, so that probability calculation can be performed based on the independent probability values P (x1|Ci), P (x2|Ci), … and P (xk|Ci) of each attribute: if the two-classification naive Bayes algorithm is used for classifying the malicious behaviors, n is equal to 1, and the total class number is 2, namely the classes only have normal behaviors and abnormal behaviors;
since abnormal behaviors may be caused by various malicious programs and the behaviors are not the same, a hybrid multi-classification naive Bayesian algorithm is adopted for analysis;
when modeling, adding behaviors of malicious programs of different categories into the training set D to perform multi-classification training; detecting according to the two categories during detection;
for n+1 classification sets C, C0 is defined as a normal behavior class, C ' is an abnormal behavior class, comprising n subsets of malicious program behaviors C ' = { C1, C2,..cn }, then c= { C0, C ' }.
When the classification detection is carried out on the network behavior X, for the network behavior X, when the class conditional probability P (C0|X) of the normal behavior class C0 is larger than the maximum value of the abnormal behavior class conditional probability, judging that the X is the normal behavior, and otherwise, judging that the X is the abnormal behavior;
the abnormal mining system is a big data service system capable of simplifying data mining, writing of task execution flow, task flow monitoring, task result previewing one-stop flow, simplifying submission difficulty of big data mining tasks, providing user authority layering, and better managing user tasks and user task data.
Finally, it should be noted that: the foregoing description is only illustrative of the preferred embodiments of the present invention, and although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements or changes may be made without departing from the spirit and principles of the present invention.
Claims (7)
1. The abnormal network behavior mining system based on big data comprises a basic service layer, a calculation and storage layer and an application layer, and is characterized in that: the basic service layer provides data computing, data storage and task management capabilities for upper layer services by means of the Hadoop cluster ecological environment;
the computing and storage layer is used as a core of the abnormal network behavior mining system, supports operator model compiling and computing tasks submitted by the application layer, and stores computing results into corresponding databases;
the application layer supports analysts to write an operator model in the form of a graphical page through a WEB system, submits tasks to a big data cluster for calculation after compiling is completed, analyzes task results through data overview, and supports subsequent business decisions;
in the application layer, the specific method for writing the operator model by the analyst is as follows:
1) An analyst creates operator configuration at an abnormal network behavior mining platform end according to specific service requirements, writes operator model codes based on the service requirements, submits the codes to a system Server end after the operator model codes are completed, the Server end issues complete model codes to a Hadoop cluster for compiling operation, and waits for a compiling result to return to a WEB end;
2) After the operator model is successfully compiled, a calculation task is created on an abnormal network behavior mining platform, and an operator and task attributes which are successfully compiled are configured and then submitted to a system Server end, a calculation engine of the Server end submits the task to a Hadoop cluster to wait for task queue to be executed after preprocessing operations such as task decomposition and data connection, and task states are detected at regular time and returned to the WEB end;
3) After the task execution is completed, the task execution result can be checked and analyzed through data preview, and the subsequent decision of the service is guided according to the task execution result.
2. The big data based anomaly network behavior mining system of claim 1, wherein: the calculation and storage layer adopts Spark as a calculation basis of operator tasks, and Spark is a general large-scale data processing engine for open source, and the operator tasks are rapidly submitted to a distributed cluster for calculation and processing through the processing engine.
3. The big data based anomaly network behavior mining system of claim 1, wherein: the operator model: mathematically, it can be interpreted as a function space to function space mapping O: x- > X is a processing unit, often refers to a function, and when an operator is used, input and output are often generated, the operator finishes conversion of corresponding data, an operator task is compiled and submitted mainly through an excavating platform in the operator model, and finally the task is submitted to a big data platform to finish calculation and storage.
4. The big data based anomaly network behavior mining system of claim 2, wherein: the operator task is responsible for submitting a certain operator which is successfully compiled to a certain node of the cluster, and completing subsequent calculation and output operations.
5. The big data based anomaly network behavior mining system of claim 3, wherein: operator types used for carrying out business logic division on operators are arranged in the operator model, so that analysts can classify and merge different operators conveniently.
6. The big data based anomaly network behavior mining system of claim 1, wherein: the system user logs in through the administrator user at first, and through the new role and user of the user module, the system can log in by the user name of the user;
after successful login, the system related technical indexes and the health state of the target cluster are displayed in a dashboard form through a home page, so that the overall operation overview data of the system is observed.
7. The big data based anomaly network behavior mining system of claim 6, wherein: the operator management of the system is specifically as follows: clicking a new operator, and enabling a user to newly add operator codes according to operator constraint requirements, and compiling, checking, saving, deleting and updating own operators;
the task management is specifically as follows: clicking to create a task, checking an operator which is compiled according to a system prompt, supporting configuration of configuring a Crontab for timing execution, starting execution of the task after issuing the task, warehousing a task result, and performing task storage, updating, deleting and task issuing execution; the viewing of the real-time state of the task is supported, and clicking on the relevant task can view the task execution result data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110975586.3A CN113610190B (en) | 2021-08-24 | 2021-08-24 | Abnormal network behavior mining system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110975586.3A CN113610190B (en) | 2021-08-24 | 2021-08-24 | Abnormal network behavior mining system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610190A CN113610190A (en) | 2021-11-05 |
| CN113610190B true CN113610190B (en) | 2024-02-02 |
Family
ID=78341814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110975586.3A Active CN113610190B (en) | 2021-08-24 | 2021-08-24 | Abnormal network behavior mining system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610190B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116932335B (en) * | 2023-09-18 | 2024-02-13 | 中国电子科技集团公司第十五研究所 | A task process monitoring method and system based on network transmission in a domestic environment |
| CN118094148B (en) * | 2024-02-19 | 2025-01-21 | 中国科学院空间应用工程与技术中心 | A method and system for mining and analyzing big data in aerospace engineering |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7328192B1 (en) * | 2002-05-10 | 2008-02-05 | Oracle International Corporation | Asynchronous data mining system for database management system |
| CN106407472A (en) * | 2016-11-01 | 2017-02-15 | 广西电网有限责任公司电力科学研究院 | Visual editing and management system for big data analysis and calculation task of order model |
| CN106844385A (en) * | 2015-12-07 | 2017-06-13 | 北京航天长峰科技工业集团有限公司 | A kind of method of combination Spark technique constructions elastic traffic model |
| CN107526600A (en) * | 2017-09-05 | 2017-12-29 | 成都优易数据有限公司 | A kind of visual numeric simulation analysis platform and its data cleaning method based on hadoop and spark |
| CN112202736A (en) * | 2020-09-15 | 2021-01-08 | 浙江大学 | Industrial control system communication network abnormity classification method based on statistical learning and deep learning |
| CN113225359A (en) * | 2021-07-12 | 2021-08-06 | 深圳市永达电子信息股份有限公司 | Safety flow analysis system based on brain-like calculation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7117208B2 (en) * | 2000-09-28 | 2006-10-03 | Oracle Corporation | Enterprise web mining system and method |
-
2021
- 2021-08-24 CN CN202110975586.3A patent/CN113610190B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7328192B1 (en) * | 2002-05-10 | 2008-02-05 | Oracle International Corporation | Asynchronous data mining system for database management system |
| CN106844385A (en) * | 2015-12-07 | 2017-06-13 | 北京航天长峰科技工业集团有限公司 | A kind of method of combination Spark technique constructions elastic traffic model |
| CN106407472A (en) * | 2016-11-01 | 2017-02-15 | 广西电网有限责任公司电力科学研究院 | Visual editing and management system for big data analysis and calculation task of order model |
| CN107526600A (en) * | 2017-09-05 | 2017-12-29 | 成都优易数据有限公司 | A kind of visual numeric simulation analysis platform and its data cleaning method based on hadoop and spark |
| CN112202736A (en) * | 2020-09-15 | 2021-01-08 | 浙江大学 | Industrial control system communication network abnormity classification method based on statistical learning and deep learning |
| CN113225359A (en) * | 2021-07-12 | 2021-08-06 | 深圳市永达电子信息股份有限公司 | Safety flow analysis system based on brain-like calculation |
Non-Patent Citations (1)
| Title |
|---|
| 基于Hadoop的大数据挖掘系统构建;李艳，刘成龙;信息通信(第2019年第2期期);第70-71页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610190A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11966395B2 (en) | Query generation based on merger of subqueries | |
| Grolinger et al. | Challenges for mapreduce in big data | |
| CN112527774B (en) | Data center construction method, system and storage medium | |
| US20240211479A1 (en) | Query Generation Based On A Logical Data Model With One-to-One Joins | |
| US7917463B2 (en) | System and method for data warehousing and analytics on a distributed file system | |
| Abdelhamid et al. | Incremental frequent subgraph mining on large evolving graphs | |
| Mezzanzanica et al. | A model-based evaluation of data quality activities in KDD | |
| US20040139426A1 (en) | Enterprise multi-agent software system | |
| CN110309110A (en) | A big data log monitoring method and device, storage medium and computer equipment | |
| CN115221337B (en) | Data weaving processing method, device, electronic device and readable storage medium | |
| Huang et al. | Survey on performance optimization for database systems | |
| CN113610190B (en) | Abnormal network behavior mining system based on big data | |
| CN114398442A (en) | Data-driven information processing system | |
| US20140068550A1 (en) | Selecting execution environments | |
| CN113127906A (en) | Unified authority management platform, method and storage medium based on C/S architecture | |
| Remil | How can subgroup discovery help AIOps? | |
| Fan et al. | Design and implementation of scientific research big data service platform for experimental data managing | |
| CN117010687A (en) | AutoML-based enterprise real-time risk monitoring and early warning method | |
| Huang et al. | Design of network traffic anomaly monitoring system based on data mining | |
| Mei et al. | Catcher: A Cache Analysis System for Top-k Pub/Sub Service | |
| US12400005B1 (en) | Managing security of a software development life cycle | |
| Gao et al. | Log Analysis System Based on Large Language Models | |
| Panda | Semantic Analysis and Query Suggestions for Distributed Redshift Systems | |
| Huang et al. | A Statistical-based Precursor Operator Analysis Method | |
| Yan et al. | Conflict resolution and missing completion in the fusion of domain ontology in cyber-physical systems |
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 |