CN110083641A - Intelligence analysis method and device based on goal behavior - Google Patents
Intelligence analysis method and device based on goal behavior Download PDFInfo
- Publication number
- CN110083641A CN110083641A CN201910347686.4A CN201910347686A CN110083641A CN 110083641 A CN110083641 A CN 110083641A CN 201910347686 A CN201910347686 A CN 201910347686A CN 110083641 A CN110083641 A CN 110083641A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior data
- algorithm
- historical behavior
- intelligence analysis
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The intelligence analysis method and device based on goal behavior that this application discloses a kind of, after being classified according to current behavior data to historical behavior data, strong related information and weak rigidity information between the two are obtained by Aprior algorithm and canonical correlation analysis, to establish internal association between the data of fragmentation, the information data for making subsequent recommendation is no longer simple data combination, and then optimize intelligence analysis as a result, improving the accuracy of intelligence analysis, completeness and efficiency.
Description
Technical field
This application involves grid computing technology field more particularly to a kind of intelligence analysis methods and dress based on goal behavior
It sets.
Background technique
As the level of informatization is constantly deepened, people are also increasingly strong to the craving of " big data " Analysis Service, using big
Therefore the product that data carry out intelligence analysis also comes into being.But existing intelligence analysis product is only to collected fragmentation
Data be combined, analysis can not be associated to the data of fragmentation, cause final intelligence analysis result precision compared with
It is low.
Summary of the invention
The embodiment of the present application provides a kind of intelligence analysis method and device based on goal behavior, solve in the prior art without
The problem of method is associated analysis to the data of fragmentation, and then optimize intelligence analysis result.
To solve the above problems, the embodiment of the present application provides a kind of intelligence analysis method based on goal behavior, it is suitable for
It calculates and is executed in equipment, include at least following steps:
Obtain multiple current behavior data of target；Wherein, multiple current behavior data include target subject data,
Time data, position data and event data；
According to each current behavior data, classify to each historical behavior data of storage in the database；
Based on Aprior algorithm, the of current behavior data described in same category and each historical behavior data is obtained
One related information, and it is based on canonical correlation analysis, obtain current behavior data described in same category and each historical behavior
After second related information of data, using same category of first related information and the second related information as information collection；
Based on a variety of proposed algorithms and the information collection, multiple recommendation indexes of the historical behavior data are obtained；Wherein,
The proposed algorithm and the recommendation index correspond；
Based on the default weight of each proposed algorithm, each corresponding recommendation index is weighted, is analyzed
As a result.
Further, described to according to each current behavior data, to each historical behavior number of storage in the database
According to classifying, specifically:
According to each current behavior data, it is based on k nearest neighbor algorithm, to each historical behavior data of storage in the database
Classify.
Further, further includes:
The analysis result be greater than preset threshold when, to user terminal push it is corresponding with the analysis result described in go through
History behavioral data.
Further, further includes:
When receiving the negative-feedback information that the user terminal is sent according to the historical behavior data, according to described negative
Feedback information adjusts the default weight of each proposed algorithm.
Further, multiple proposed algorithms include at least:
Proposed algorithm based on collaborative filtering, the proposed algorithm based on correlation rule and content-based recommendation algorithm.
Further, a kind of intelligence analysis device based on goal behavior is also provided, comprising:
Data acquisition module, for obtaining multiple current behavior data of target；Wherein, multiple current behavior data
Including target subject data, time data, position data and event data；
Data categorization module is used for according to each current behavior data, to each historical behavior of storage in the database
Data are classified；
Data association module obtains current behavior data described in same category and each institute for being based on Aprior algorithm
The first related information of historical behavior data is stated, and is based on canonical correlation analysis, obtains current behavior number described in same category
According to after the second related information of each historical behavior data, by same category of first related information and the second related information
As information collection；
Data recommendation module obtains the historical behavior data for being based on a variety of proposed algorithms and the information collection
Multiple recommendation indexes；Wherein, the proposed algorithm and the recommendation index correspond；
Interpretation of result module, for the default weight based on each proposed algorithm, to each corresponding recommendation index
It is weighted, obtains analysis result.
Further, the data categorization module is specifically used for:
According to each current behavior data, it is based on k nearest neighbor algorithm, to each historical behavior data of storage in the database
Classify.
Further, further includes:
Data alarm module, for being pushed and described point to user terminal when the analysis result is greater than preset threshold
Analyse the corresponding historical behavior data of result.
Further, further includes:
Data point reuse module, in the negative-feedback for receiving the user terminal and being sent according to the historical behavior data
When information, according to the negative-feedback information, the default weight of each proposed algorithm is adjusted.
Implement the embodiment of the present application, has the following beneficial effects:
A kind of intelligence analysis method and device based on goal behavior provided by the embodiments of the present application, according to current behavior number
After classifying to historical behavior data, by Aprior algorithm and canonical correlation analysis obtain between the two be associated with letter by force
Breath and weak rigidity information make the information data of subsequent recommendation no longer be to establish internal association between the data of fragmentation
Simple data combination, and then optimize intelligence analysis as a result, improving the accuracy of intelligence analysis, completeness and efficiency.
Detailed description of the invention
Fig. 1 is the flow diagram for the intelligence analysis method based on goal behavior that one embodiment of the application provides；
Fig. 2 is the process signal for the intelligence analysis method based on goal behavior that the further embodiment of the application provides
Figure；
Fig. 3 is the process signal for the intelligence analysis method based on goal behavior that another embodiment of the application provides
Figure；
Fig. 4 is the structural schematic diagram for the intelligence analysis device based on goal behavior that one embodiment of the application provides；
Fig. 5 is the structural representation for the intelligence analysis device based on goal behavior that another embodiment of the application provides
Figure；
Fig. 6 is the structural representation for the intelligence analysis device based on goal behavior that the further embodiment of the application provides
Figure.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Referring to Figure 1.
It is that the process of the intelligence analysis method based on goal behavior of one embodiment offer of the application is shown referring to Fig. 1
It is intended to, as shown in Figure 1, each step is specific as follows:
Step S11 obtains multiple current behavior data of target.
Wherein, multiple current behavior data include target subject data, time data, position data and event data.
In the present embodiment, target is determined by user, can be individual or entity, is also possible to event.According to 6W principle,
That is: What (what occurs), Where (occurring where), When (when occurring), Who (who is participated in), Why
(why doing so), How (how accomplishing), is collected the whole network resource, extracts, arranging and duplicate removal, obtains target
Multiple current behavior data after, by the storage of multiple current behavior data in relational database, so that it is determined that target's center.
Step S12 classifies to each historical behavior data of storage in the database according to each current behavior data.
Specifically, k nearest neighbor algorithm is based on according to each current behavior data, to each historical behavior of storage in the database
Data are classified.
In the present embodiment, by participle technique, by current behavior data according to target subject index, time index,
After point index and event index this 4 indexs are classified, it is based on k nearest neighbor algorithm, is classified to each historical behavior data, and
In of all categories, after selecting a plurality of historical behavior data at a distance from current behavior data within a preset range, it will be selected
A plurality of historical behavior data preparation into a relational database, to reduce classification workload, and improve efficiency.
In the present embodiment, the behaviour of target subject index, things or tissue；Time index is the time that event occurs；Ground
Point index is locale, including longitude and latitude, country, street etc.；Event index is the event occurred.
Step S13 is based on Aprior algorithm, obtains the of current behavior data and each historical behavior data in same category
One related information, and be based on canonical correlation analysis obtains the of current behavior data and each historical behavior data in same category
After two related informations, using same category of first related information and the second related information as information collection.
In the present embodiment, using Aprior algorithm, by same category of each historical behavior data, respectively with same category
Current behavior data be associated analysis, so that finding indicates there is the first related information of obvious inner link between data,
Help to carry out early warning to the event that future occurs, and by using Canonical Correlation Analysis, it will be each high in same category
Current behavior data in the historical behavior data and same category of dimension space are mapped to lower dimensional space, to find expression number
Between it is the second related information of weak correlative connection, and then helps that future event is more accurately predicted and is felt
Know.For example, each historical behavior data that target subject index will be belonged to, respectively with the current behavior number that belongs to target subject index
According to analysis is associated, to obtain each historical behavior data of target subject index, the current behavior with target subject index
The first related information and the second related information of data.
On the basis of obtaining information collection, by the fuzzy matching algorithm and accurate matching algorithm of knowledge based map, enclose
The target determined around user carries out behavioral data lookup, to obtain associated historical behavior data, and by the history of acquisition
Behavioral data is associated displaying in the data that visualization interface inputs in conjunction with user.
Step S14 is based on a variety of proposed algorithms and information collection, obtains multiple recommendation indexes of historical behavior data.
Wherein, proposed algorithm and recommendation index correspond.
In the present embodiment, it is calculated using information collection as the proposed algorithm based on collaborative filtering, the recommendation based on correlation rule
The parameter of method and content-based recommendation algorithm, to obtain multiple recommendation indexes of historical behavior data.
Step S15, the default weight based on each proposed algorithm are weighted each corresponding recommendation index, are analyzed
As a result.
In the present embodiment, by the existing proposed algorithm based on collaborative filtering, the proposed algorithm based on correlation rule and
Content-based recommendation algorithm combines, and weights a variety of proposed algorithms, thus analyzed as a result, specific formula is as follows:
Wherein, S is analysis as a result, n is proposed algorithm number, αiFor i-th of recommendation index, kiIt is weighed for i-th of proposed algorithm
Value.
After the present embodiment classifies to historical behavior data according to current behavior data, pass through Aprior algorithm and typical case
Correlation analysis obtains strong related information and weak rigidity information between the two, can be associated analysis to the data of each dimension,
To establish internal association between the data of fragmentation, making the information data of subsequent recommendation is no longer simple data combination,
And then optimize intelligence analysis result.
Refer to Fig. 2.
Further, referring to fig. 2, be the application further embodiment provide the intelligence analysis side based on goal behavior
The flow diagram of method.In addition to the process shown in Fig. 1, further includes:
Step S16, when analyzing result greater than preset threshold, to user terminal push history row corresponding with analysis result
For data.
In the present embodiment, the size by historical behavior data based on the analysis results, is arranged simultaneously in the form of descending
It is shown on terminal interface, if analysis result is greater than 80%, corresponding historical behavior data is pushed to use with alarm status
Family terminal.
The present embodiment shows corresponding historical behavior data by the size descending on terminal interface based on the analysis results,
To facilitate user to browse data, and when analyzing result greater than preset threshold, gone through accordingly to user terminal push
History behavioral data, and then allow users to obtain the higher prediction information of accuracy, so that user takes in time according to the information
Corresponding measure.
Please refer to Fig. 3.
It is the process of the intelligence analysis method based on goal behavior of another embodiment offer of the application referring to Fig. 3
Schematic diagram.In addition to the process shown in Fig. 2, further includes:
Step S17, when receiving the negative-feedback information that user terminal is sent according to historical behavior data, according to negative-feedback
Information adjusts the default weight of each proposed algorithm.
In the present embodiment, default weight is adjusted by the way of positive and negative feedback adjusting.If receiving user according to push
Historical behavior data send positive and negative feedforward information when, then it represents that the data fit actual desired of push；If receiving user's root
According to push historical behavior data send negative-feedback information when, then it represents that the data of push differ larger with actual result, this
When according to the negative-feedback of user, adjust the default weight of a proposed algorithm, such as reduce the power of the proposed algorithm based on collaborative filtering
Value, and increase the weight of content-based recommendation algorithm, and then improve the precision of propelling data.
The present embodiment adjusts the default weight of proposed algorithm according to the information of user feedback in real time, solves using fixed pre-
If weight will lead to the lower problem of intelligence analysis accuracy, to keep prediction data more accurate, and as user feedback is believed
Increasing for breath has higher accuracy.
Refer to Fig. 4.
Further, referring to fig. 4, be the application one embodiment provide the intelligence analysis device based on goal behavior
Structural schematic diagram.Include:
Data acquisition module 101, for obtaining multiple current behavior data of target.
Wherein, multiple current behavior data include target subject data, time data, position data and event data.
Data categorization module 102 is used for according to each current behavior data, to each historical behavior number of storage in the database
According to classifying.
Specifically, data categorization module 102 is used to be based on k nearest neighbor algorithm according to each current behavior data, to being stored in number
Classify according to each historical behavior data in library.
Data association module 103 obtains current behavior data and each history in same category for being based on Aprior algorithm
First related information of behavioral data, and it is based on canonical correlation analysis, obtain current behavior data and each history in same category
After second related information of behavioral data, using same category of first related information and the second related information as information collection.
Data recommendation module 104 obtains the multiple of historical behavior data and pushes away for being based on a variety of proposed algorithms and information collection
Recommend index.Wherein, proposed algorithm and recommendation index correspond.
Interpretation of result module 105 adds each corresponding recommendation index for the default weight based on each proposed algorithm
Power obtains analysis result.
After the present embodiment classifies to historical behavior data according to current behavior data, pass through Aprior algorithm and typical case
Correlation analysis obtains strong related information and weak rigidity information between the two, can be associated analysis to the data of each dimension,
To establish internal association between the data of fragmentation, making the information data of subsequent recommendation is no longer simple data combination,
And then optimize intelligence analysis result.
Refer to Fig. 5.
It is the structure of the intelligence analysis device based on goal behavior of another embodiment offer of the application referring to Fig. 5
Schematic diagram.In addition to the structure shown in Fig. 4, further includes:
Data alarm module 106, for being pushed to user terminal and analyzing result when analyzing result greater than preset threshold
Corresponding historical behavior data.
The present embodiment shows corresponding historical behavior data by the size descending on terminal interface based on the analysis results,
To facilitate user to browse data, and when analyzing result greater than preset threshold, gone through accordingly to user terminal push
History behavioral data, and then allow users to obtain the higher prediction information of accuracy, so that user takes in time according to the information
Corresponding measure.
Refer to Fig. 6.
It is the structure of the intelligence analysis device based on goal behavior of the further embodiment offer of the application referring to Fig. 6
Schematic diagram.In addition to the structure shown in Fig. 5, further includes:
Data point reuse module 107, in the negative-feedback information for receiving user terminal and being sent according to historical behavior data
When, according to negative-feedback information, adjust the default weight of each proposed algorithm.
The present embodiment adjusts the default weight of proposed algorithm according to the information of user feedback in real time, solves using fixed pre-
If weight will lead to the lower problem of intelligence analysis accuracy, to keep prediction data more accurate, and as user feedback is believed
Increasing for breath has higher accuracy.
The another embodiment of the application additionally provides a kind of intelligence analysis terminal device based on goal behavior, including processing
Device, memory and storage in the memory and are configured as the computer program executed by the processor, the place
Reason device realizes the intelligence analysis method based on goal behavior as described in above-described embodiment when executing the computer program.
The above is the preferred embodiment of the application, it is noted that for those skilled in the art
For, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also considered as
The protection scope of the application.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Claims (9)
1. a kind of intelligence analysis method based on goal behavior, which is characterized in that include at least following steps:
Obtain multiple current behavior data of target；Wherein, multiple current behavior data include target subject data, time
Data, position data and event data；
According to each current behavior data, classify to each historical behavior data of storage in the database；
Based on Aprior algorithm, obtain current behavior data described in same category and each historical behavior data first is closed
Join information, and be based on canonical correlation analysis, obtains current behavior data described in same category and each historical behavior data
The second related information after, using same category of first related information and the second related information as information collection；
Based on a variety of proposed algorithms and the information collection, multiple recommendation indexes of the historical behavior data are obtained；Wherein, described
Proposed algorithm and the recommendation index correspond；
Based on the default weight of each proposed algorithm, each corresponding recommendation index is weighted, analysis result is obtained.
2. the intelligence analysis method according to claim 1 based on goal behavior, which is characterized in that described to according to each institute
Current behavior data are stated, are classified to each historical behavior data of storage in the database, specifically:
According to each current behavior data, it is based on k nearest neighbor algorithm, each historical behavior data of storage in the database are carried out
Classification.
3. the intelligence analysis method according to claim 1 based on goal behavior, which is characterized in that further include:
When the analysis result is greater than preset threshold, the history row corresponding with the analysis result is pushed to user terminal
For data.
4. the intelligence analysis method according to claim 3 based on goal behavior, which is characterized in that further include:
When receiving the negative-feedback information that the user terminal is sent according to the historical behavior data, according to the negative-feedback
Information adjusts the default weight of each proposed algorithm.
5. the intelligence analysis method described in -5 any one based on goal behavior according to claim 1, which is characterized in that multiple
The proposed algorithm includes at least:
Proposed algorithm based on collaborative filtering, the proposed algorithm based on correlation rule and content-based recommendation algorithm.
6. a kind of intelligence analysis device based on goal behavior characterized by comprising
Data acquisition module, for obtaining multiple current behavior data of target；Wherein, multiple current behavior data include
Target subject data, time data, position data and event data；
Data categorization module is used for according to each current behavior data, to each historical behavior data of storage in the database
Classify；
Data association module obtains current behavior data described in same category and described goes through with each for being based on Aprior algorithm
First related information of history behavioral data, and be based on canonical correlation analysis, obtain same category described in current behavior data with
After second related information of each historical behavior data, using same category of first related information and the second related information as
Information collection；
Data recommendation module obtains the multiple of the historical behavior data for being based on a variety of proposed algorithms and the information collection
Recommend index；Wherein, the proposed algorithm and the recommendation index correspond；
Interpretation of result module carries out each corresponding recommendation index for the default weight based on each proposed algorithm
Weighting obtains analysis result.
7. the intelligence analysis device according to claim 6 based on goal behavior, which is characterized in that the data classification mould
Block is specifically used for:
According to each current behavior data, it is based on k nearest neighbor algorithm, each historical behavior data of storage in the database are carried out
Classification.
8. the intelligence analysis device according to claim 6 based on goal behavior, which is characterized in that further include:
Data alarm module, for being tied with the analysis to user terminal push when the analysis result is greater than preset threshold
The corresponding historical behavior data of fruit.
9. the intelligence analysis device according to claim 8 based on goal behavior, which is characterized in that further include:
Data point reuse module, in the negative-feedback information for receiving the user terminal and being sent according to the historical behavior data
When, according to the negative-feedback information, adjust the default weight of each proposed algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347686.4A CN110083641B (en) | 2019-04-26 | 2019-04-26 | Information analysis method and device based on target behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347686.4A CN110083641B (en) | 2019-04-26 | 2019-04-26 | Information analysis method and device based on target behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083641A true CN110083641A (en) | 2019-08-02 |
| CN110083641B CN110083641B (en) | 2021-07-09 |
Family
ID=67417189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910347686.4A Active CN110083641B (en) | 2019-04-26 | 2019-04-26 | Information analysis method and device based on target behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083641B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170277793A1 (en) * | 2016-03-24 | 2017-09-28 | NewsRx, LLC | Narrated search results |
| US10157352B1 (en) * | 2014-09-07 | 2018-12-18 | DataNovo, Inc. | Artificial intelligence machine learning, and predictive analytic for patent and non-patent documents |
| CN109272155A (en) * | 2018-09-11 | 2019-01-25 | 郑州向心力通信技术股份有限公司 | A kind of corporate behavior analysis system based on big data |
| CN109543963A (en) * | 2018-11-06 | 2019-03-29 | 深圳信息职业技术学院 | A kind of big data analysis method and system based on student's study habit |
-
2019
- 2019-04-26 CN CN201910347686.4A patent/CN110083641B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10157352B1 (en) * | 2014-09-07 | 2018-12-18 | DataNovo, Inc. | Artificial intelligence machine learning, and predictive analytic for patent and non-patent documents |
| US20170277793A1 (en) * | 2016-03-24 | 2017-09-28 | NewsRx, LLC | Narrated search results |
| CN109272155A (en) * | 2018-09-11 | 2019-01-25 | 郑州向心力通信技术股份有限公司 | A kind of corporate behavior analysis system based on big data |
| CN109543963A (en) * | 2018-11-06 | 2019-03-29 | 深圳信息职业技术学院 | A kind of big data analysis method and system based on student's study habit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083641B (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112258093B (en) | Data processing method and device for risk level, storage medium and electronic equipment | |
| CN109508360B (en) | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton | |
| CN113095442B (en) | Hail identification method based on semi-supervised learning under multi-dimensional radar data | |
| CN108366386B (en) | Method for realizing wireless network fault detection by using neural network | |
| CN110929918A (en) | 10kV feeder line fault prediction method based on CNN and LightGBM | |
| CN110222592B (en) | Construction method of time sequence behavior detection network model based on complementary time sequence behavior proposal generation | |
| CN109273096A (en) | A kind of risk management grading evaluation method based on machine learning | |
| CN111079860B (en) | Method for constructing multi-granularity response model of emergency based on scene similarity | |
| CN108540329A (en) | Network security inference method based on two-layer Bayesian network model | |
| CN117436724A (en) | Multi-source data visual analysis method and system based on smart city | |
| CN112087442A (en) | Time sequence related network intrusion detection method based on attention mechanism | |
| CN112801411B (en) | Network traffic prediction method based on generation of countermeasure network | |
| CN113364751A (en) | Network attack prediction method, computer-readable storage medium, and electronic device | |
| CN114338351B (en) | Network anomaly root cause determination method and device, computer equipment and storage medium | |
| CN111901134B (en) | Method and device for predicting network quality based on recurrent neural network model (RNN) | |
| Alsayadi et al. | Improving the regression of communities and crime using ensemble of machine learning models | |
| Klement et al. | Using SOM in the performance monitoring of the emergency call-taking system | |
| Sivasankar et al. | Knowledge discovery in medical datasets using a fuzzy logic rule based classifier | |
| CN118013207A (en) | Management method and system for acquisition and quality inspection of exploration operation data | |
| CN108133387A (en) | Multiple labeling k nearest neighbor algorithm based on Soft Inform ation | |
| CN113254580A (en) | Special group searching method and system | |
| Xu | Analysis and comparison of forecasting algorithms for telecom customer churn | |
| Faraoun et al. | Neural networks learning improvement using the k-means clustering algorithm to detect network intrusions | |
| CN110083641A (en) | Intelligence analysis method and device based on goal behavior | |
| Liu et al. | TS-SVM: Detect LDoS attack in SDN based on two-step self-adjusting SVM |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220112 Address after: 523000 B502, No. 17, headquarters Second Road, Songshanhu high tech Industrial Development Zone, Dongguan City, Guangdong Province Patentee after: Dongguan Zhidun Information Security Technology Co.,Ltd. Address before: No. 230, Waihuan West Road, Guangzhou University Town, Panyu, Guangzhou City, Guangdong Province, 510006 Patentee before: Guangzhou University |
|
| TR01 | Transfer of patent right |