CN108829846A - A kind of business recommended platform data cluster optimization system and method based on user characteristics - Google Patents
A kind of business recommended platform data cluster optimization system and method based on user characteristics Download PDFInfo
- Publication number
- CN108829846A CN108829846A CN201810636480.9A CN201810636480A CN108829846A CN 108829846 A CN108829846 A CN 108829846A CN 201810636480 A CN201810636480 A CN 201810636480A CN 108829846 A CN108829846 A CN 108829846A
- Authority
- CN
- China
- Prior art keywords
- optimization
- business recommended
- user characteristics
- user
- business
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The business recommended platform data cluster optimization system and method, the system that the present invention relates to a kind of based on user characteristics include：Business recommended UI based on user characteristics is embodied as user and shows interface and interact with user；User characteristics record system, realize that the various user characteristics by user on UI record；User characteristics storage system realizes that the various user characteristics by user on UI store；Business recommended engine realizes recommendation results.Cluster optimization thought of the invention is that each business recommended data clusters optimization request information is judged and analyzed, and each business recommended data clusters optimization request has different priority levels.The cluster strategy that business recommended data clusters optimization request is clustered optimization assay Function Optimization by the present invention clusters.Present invention dynamic, advantage high-efficient, accuracy is high are realized in conjunction with reward and expert decision-making library multi-story and multi-span semi-supervised learning method.
Description
Technical field
The present invention relates to big datas and data clustering technique field, and in particular to a kind of based on the business recommended of user characteristics
Platform data clusters optimization system and method.
Background technique
Big data analysis and data clusters have become the important trend of global operator development, and big data analysis and data are poly-
Class is generally regarded as one of the main trend of Next Generation of Digital transition by industry.Data clusters are that similar data are passed through
The method of classification is divided into different group or more subsets (subset), allows the member object in the same subset in this way
There are similar some attributes, is provided in business recommended platform according to functions such as the fastext of feature recommendations, help enterprise
The Rapid Popularization of realization business and online.Currently, big data analysis and data clusters have become world government/enterprise's industrial circle
Generally acknowledged development priority；The communications industry giant of international and national accelerates technical research, enterprise transformation is cooperated with alliance to seize
The dominant right and emerging market space of big data analysis and data clusters development.In this case, the big number in face of being increasingly urgent to
According to analysis and data clusters growth requirement, the business recommended platform data cluster optimization system based on user characteristics is for big data
Analysis and the rapid sustainable development of data clusters are of great significance.
But with big data analysis and the rapid growth of data clusters business, static state, low efficiency, accurate is produced with it
Spend the problems such as low.Existing big data cluster has the characteristic that data scale is big, convergence rate is slow, does not fully take into account static, effect
The aspect problems such as rate is low, accuracy is low.
Summary of the invention
In a first aspect, a kind of business recommended platform data based on user characteristics clusters optimization system, which includes：
Business recommended UI based on user characteristics is embodied as user and shows interface and interact with user；
User characteristics record system, realize that the various user characteristics by user on UI record；
User characteristics storage system realizes that the various user characteristics by user on UI store；
Business recommended engine realizes recommendation results.
With reference to first aspect, in a first possible implementation of that first aspect, the user characteristics storage system is real
Now the various user characteristics by user on UI are stored on file, database or memory cache；The business recommended engine is real
Recommendation results are gradually optimized according to certain method now and return to consequently recommended result.
With reference to first aspect, in a second possible implementation of that first aspect, the user is user in the Finance Mgmt Team, enterprise
User, government customer or personal user.
Second aspect, the present invention provide a kind of business recommended platform data cluster optimization method based on user characteristics, should
Method includes the following steps：
1) user accesses the business recommended UI based on user characteristics, and submits the business recommended data based on user characteristics poly-
Class optimization request；
2) various user characteristics are recorded in user characteristics record system；
3) various user characteristics are stored on the file, database or memory cache of user characteristics storage system；
4) business recommended engine is denoised and is clustered according to the relative users feature stored in user characteristics storage system
After optimization to, the recommendation business of respective type is sent to the business recommended UI based on user characteristics；
5) the business recommended UI based on user characteristics will be according to corresponding by the business recommended data clusters optimization request of user
Recommendation business return to relative users.
In conjunction with second aspect, in second aspect in the first possible implementation, the business recommended engine includes four
A part：Business recommended data clusters optimization request is received, is pushed away with hyperspace neural network clustering Optimization Tactics Analysis business
Recommend data clusters optimization request, recommendation results output, hyperspace neural network clustering optimisation strategy semi-supervised learning.
In conjunction with the first implementation of second aspect, in second of second aspect possible implementation, it is described with
The business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis the specific steps are：
1) each business recommended data clusters optimization request acquisition summarizes
Every preset time active reporting and periodically be asked mechanism obtain smart home communication optimization request, and by these
Information is summarized；
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,；
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d；
4) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
5) each cluster optimization analysis initial results acquisition summarizes
Business recommended data clusters optimization request recommendation results are obtained and summarized；
6) hyperspace neural network clustering optimisation strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with reward and expert decision-making library multi-story and multi-span semi-supervised learning method；
7) meet cluster optimization assay condition
According to hyperspace, neural network, deep learning, probability theory, biology, operational research, intelligent optimization, machine learning
Cluster optimization assay condition, that is, evaluation function (see formula 1-2) of scheduling theory is judged, is analyzed when being unsatisfactory for cluster optimization
It should continue iteration when evaluation condition；
8) current iteration number adds 1
Current iteration number increases by 1 time, namely；
9) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
10) each cluster optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes business recommended data clusters optimization request
Analyze recommendation results information；
11) meet current iteration number greater than maximum number of iterations
According to current iteration number be greater than maximum number of iterations evaluation condition judged, jumped to when being unsatisfactory for 6) after
It is continuous to be iterated, terminate when meeting.
It is described more in second aspect in the third possible implementation in conjunction with the first implementation of second aspect
Dimension space neural network clustering optimisation strategy semi-supervised learning specifically includes：
It clusters Optimized model and is represented by
Storage model includes Mijt k； (1-1)
Joint markov evaluation function：
Multi-story and multi-span majorized function：
Wherein k of the formula (1-1) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k
=1,2, ", the condition of d；Wherein, 1,2, L be hyperspace；
M in formula (1-3), (1-4) and (1-5)ijt kMainly include：WithBoth sides information vector, formula (1-2),
In (1-3), (1-4), (1-5) and (1-6) EmaxG、AmaxG、MmaxG、MmaxK、MminK、MminGThe current kth time iteration for respectively clustering optimization recommends efficiency, current kth time average recommendation
Time accuracy of efficiency, current kth, current kth time bat, historical information recommend maximum efficiency, historical information accurate
Spend maximum value, current kth time information vector, history maximum information vector, current kth time maximum information vector, current kth time most
Small information vector ,+1 information vector of kth ,+1 excitation factor of kth, kth+1 the experts database semi-supervised learning factor, history are most
Small information vector, so that this algorithm chooses local optimum.
Cluster optimization thought of the invention is that each business recommended data clusters optimization request information is judged and analyzed,
Each business recommended data clusters optimization request has different priority levels.The present invention by business recommended data clusters optimization request with
The cluster strategy of cluster optimization assay Function Optimization is clustered.In conjunction with reward and expert decision-making library Multi-Layer Feedback nerve net
Network semi-supervised learning method realizes present invention dynamic, advantage high-efficient, accuracy is high.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without any creative labor,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 be the application based on user characteristics business recommended platform data cluster optimization method specific embodiment it
One cluster optimization analysis execution flow chart；
Fig. 2 is the schematic diagram of storage model.
Specific embodiment
It elaborates below to embodiments herein.
In one embodiment of the invention, a kind of business recommended platform data cluster optimization system based on user characteristics
System, the system include：
Business recommended UI based on user characteristics is embodied as user and shows interface and interact with user；
User characteristics record system, realize that the various user characteristics by user on UI record；
User characteristics storage system realizes that the various user characteristics by user on UI store；
Business recommended engine realizes recommendation results.
Wherein, business recommended engine is mainly completed to carry out the business recommended data clusters optimization request based on user characteristics
Analysis processing, and will analysis treated relevant information is transmitted to corresponding analysis result.
In a second embodiment of the present invention, the user characteristics storage system realizes the various use by user on UI
Family characteristic storage is on file, database or memory cache；The business recommended engine implementation is by recommendation results according to certain side
Method gradually optimizes and returns to consequently recommended result.
In third embodiment of the invention, the user is user in the Finance Mgmt Team, enterprise customer, government customer or personal use
Family.
In the 4th embodiment of the invention, it is excellent to provide a kind of business recommended platform data cluster based on user characteristics
Change method, this method comprises the following steps：
1) user accesses the business recommended UI based on user characteristics, and submits the business recommended data based on user characteristics poly-
Class optimization request；
2) various user characteristics are recorded in user characteristics record system；
3) various user characteristics are stored on the file, database or memory cache of user characteristics storage system；
4) business recommended engine is denoised and is clustered according to the relative users feature stored in user characteristics storage system
After optimization to, the recommendation business of respective type is sent to the business recommended UI based on user characteristics；
5) the business recommended UI based on user characteristics will be according to corresponding by the business recommended data clusters optimization request of user
Recommendation business return to relative users.
In the 5th embodiment of the invention, the business recommended engine includes four parts：Business recommended data are poly-
Class optimization request receive, with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis, push away
Recommend result output, hyperspace neural network clustering optimisation strategy semi-supervised learning.
It is described to be pushed away with hyperspace neural network clustering Optimization Tactics Analysis business in the 6th embodiment of the invention
Recommend data clusters optimization request the specific steps are：
1) each business recommended data clusters optimization request acquisition summarizes
Every preset time active reporting and periodically be asked mechanism obtain smart home communication optimization request, and by these
Information is summarized；
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,；
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d；
4) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
5) each cluster optimization analysis initial results acquisition summarizes
Business recommended data clusters optimization request recommendation results are obtained and summarized；
6) hyperspace neural network clustering optimisation strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with reward and expert decision-making library multi-story and multi-span semi-supervised learning method；
7) meet cluster optimization assay condition
According to hyperspace, neural network, deep learning, probability theory, biology, operational research, intelligent optimization, machine learning
Cluster optimization assay condition, that is, evaluation function (see formula 1-2) of scheduling theory is judged, is analyzed when being unsatisfactory for cluster optimization
It should continue iteration when evaluation condition；
8) current iteration number adds 1
Current iteration number increases by 1 time, namely；
9) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
10) each cluster optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes business recommended data clusters optimization request
Analyze recommendation results information；
11) meet current iteration number greater than maximum number of iterations
According to current iteration number be greater than maximum number of iterations evaluation condition judged, jumped to when being unsatisfactory for 6) after
It is continuous to be iterated, terminate when meeting.
Wherein, each business recommended data clusters optimization request information mainly includes：Recommend efficiency E, accuracy A.By dividing
Analysing business recommended data clusters optimization request realizes the recommendation efficiency E for each business recommended data clusters optimization request, standard
Exactness A carries out cluster optimization, and hyperspace neural network clustering optimisation strategy semi-supervised learning is realized and provides recommendation results.
The algorithm is passively collected business recommended data clusters optimization request information and is analyzed in real time using actively simultaneous in real time, bright
Recommendation efficiency, the accuracy aspect index of aobvious each business recommended data clusters optimization recommendation results of optimization.In each iteration
Thought is analyzed in the optimization of hyperspace neural network clustering:In hyperspace, multiple cluster prioritization schemes are according to reward and specially
The direction that family's solution bank multi-story and multi-span semi-supervised learning optimisation strategy mode is determined to optimal suggested design migrates, and asks
Ask after input that output phase answers recommendation results after reward mechanism and experts database semi-supervised learning loop optimization.In conjunction with multidimensional sky
Between multi-story and multi-span optimize thought, based on hyperspace, neural network, deep learning, probability theory, biology, plan strategies for
The cluster optimization analysis of the advantages such as, intelligent optimization, machine learning obtains cluster optimization analysis result.
After business recommended data clusters optimization request arrival mode, which is clustered
The scheme of optimization assay Function Optimization is clustered into corresponding cluster result.If the business recommended data clusters optimization to arrive is asked
It asks and is delayed by, be endowed current higher acceleration Optimized Operation cluster priority.
In the 7th embodiment of the invention, the hyperspace neural network clustering optimisation strategy semi-supervised learning tool
Body includes：
It clusters Optimized model and is represented by
Storage model includes Mijt k, storage model is as shown in Figure 2； (1-1)
Joint markov evaluation function：
Multi-story and multi-span majorized function：
Wherein k of the formula (1-1) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k
=1,2 ..., the condition of d；Wherein, 1,2, L be hyperspace；
M in formula (1-3), (1-4) and (1-5)ijt kMainly include：WithBoth sides information vector, formula (1-2),
In (1-3), (1-4), (1-5) and (1-6) EmaxG、AmaxG、MmaxG、MmaxK、MminK、MminGThe current kth time iteration for respectively clustering optimization recommends efficiency, current kth time average recommendation
Time accuracy of efficiency, current kth, current kth time bat, historical information recommend maximum efficiency, historical information accurate
Spend maximum value, current kth time information vector, history maximum information vector, current kth time maximum information vector, current kth time most
Small information vector ,+1 information vector of kth ,+1 excitation factor of kth, kth+1 the experts database semi-supervised learning factor, history are most
Small information vector, so that this algorithm chooses local optimum.Cluster optimization thought of the invention is to each business recommended data clusters
Optimization request information is judged and is analyzed that each business recommended data clusters optimization request has different priority levels.The present invention
Business recommended data clusters optimization request is clustered with the cluster strategy for clustering optimization assay Function Optimization.In conjunction with prize
It encourages and expert decision-making library multi-story and multi-span semi-supervised learning method realizes that present invention dynamic, high-efficient, accuracy is high
Advantage.
Same and similar part may refer to each other between each embodiment in this specification.Invention described above is real
The mode of applying is not intended to limit the scope of the present invention..
Claims (7)
1. a kind of business recommended platform data based on user characteristics clusters optimization system, which includes：
Business recommended UI based on user characteristics is embodied as user and shows interface and interact with user；
User characteristics record system, realize that the various user characteristics by user on UI record；
User characteristics storage system realizes that the various user characteristics by user on UI store；
Business recommended engine realizes recommendation results.
2. system according to claim 1, which is characterized in that the user characteristics storage system is realized user on UI
Various user characteristics be stored on file, database or memory cache；The business recommended engine implementation presses recommendation results
Gradually optimize according to certain method and returns to consequently recommended result.
3. system according to claim 1 or 2, which is characterized in that the user is user in the Finance Mgmt Team, enterprise customer, government
User or personal user.
4. a kind of business recommended platform data based on user characteristics clusters optimization method, this method comprises the following steps：
1) user accesses the business recommended UI based on user characteristics, and submits the business recommended data clusters based on user characteristics excellent
Change request；
2) various user characteristics are recorded in user characteristics record system；
3) various user characteristics are stored on the file, database or memory cache of user characteristics storage system；
4) business recommended engine is denoised and is clustered optimization according to the relative users feature stored in user characteristics storage system
Afterwards, the recommendation business of respective type is sent to the business recommended UI based on user characteristics；
5) the business recommended UI based on user characteristics will be pushed away according to by the business recommended data clusters optimization request of user is corresponding
The business of recommending returns to relative users.
5. according to the method described in claim 4, it is characterized in that, the business recommended engine includes four parts：Business pushes away
Data clusters optimization request is recommended to receive, with the business recommended data clusters optimization of hyperspace neural network clustering Optimization Tactics Analysis
Request, recommendation results output, hyperspace neural network clustering optimisation strategy semi-supervised learning.
6. according to the method described in claim 5, it is characterized in that, described with hyperspace neural network clustering optimisation strategy point
Analyse business recommended data clusters optimization request the specific steps are：
1) each business recommended data clusters optimization request acquisition summarizes
It every preset time active reporting and is periodically asked mechanism and obtains the request of smart home communication optimization, and by these information
Summarized；
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,；
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d；
4) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
5) each cluster optimization analysis initial results acquisition summarizes
Business recommended data clusters optimization request recommendation results are obtained and summarized；
6) hyperspace neural network clustering optimisation strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with reward and expert decision-making library multi-story and multi-span semi-supervised learning method；
7) meet cluster optimization assay condition
It is managed according to hyperspace, neural network, deep learning, probability theory, biology, operational research, intelligent optimization, machine learning etc.
Cluster optimization assay condition, that is, evaluation function (see formula 1-2) of opinion is judged, optimizes assay when being unsatisfactory for cluster
It should continue iteration when condition；
8) current iteration number adds 1
Current iteration number increases by 1 time, namely；
9) with the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis
With the business recommended data clusters optimization request of hyperspace neural network clustering Optimization Tactics Analysis；
10) each cluster optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes business recommended data clusters optimization request analysis
Recommendation results information；
11) meet current iteration number greater than maximum number of iterations
According to current iteration number be greater than maximum number of iterations evaluation condition judged, jumped to when being unsatisfactory for 6) continue into
Row iteration terminates when meeting.
7. according to the method described in claim 5, it is characterized in that, the hyperspace neural network clustering optimisation strategy half is supervised
Educational inspector practises and specifically including：
It clusters Optimized model and is represented by
Storage model includes Mijt k； (1-1)
Joint markov evaluation function：
Multi-story and multi-span majorized function：
λ, β ∈ (0,1) ,+β=1 λ (1-3)
Wherein k of the formula (1-1) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k=1,
2, ", the condition of d；Wherein, 1,2, L be hyperspace；
M in formula (1-3), (1-4) and (1-5)ijt kMainly include：WithBoth sides information vector, formula (1-2), (1-
3), in (1-4), (1-5) and (1-6)EmaxG、AmaxG、MmaxG、MmaxK、MminK、MminGThe current kth time iteration for respectively clustering optimization recommends efficiency, current kth time average recommendation
Time accuracy of efficiency, current kth, current kth time bat, historical information recommend maximum efficiency, historical information accurate
Spend maximum value, current kth time information vector, history maximum information vector, current kth time maximum information vector, current kth time most
Small information vector ,+1 information vector of kth ,+1 excitation factor of kth, kth+1 the experts database semi-supervised learning factor, history are most
Small information vector, so that this algorithm chooses local optimum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810636480.9A CN108829846B (en) | 2018-06-20 | 2018-06-20 | Service recommendation platform data clustering optimization system and method based on user characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810636480.9A CN108829846B (en) | 2018-06-20 | 2018-06-20 | Service recommendation platform data clustering optimization system and method based on user characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108829846A true CN108829846A (en) | 2018-11-16 |
| CN108829846B CN108829846B (en) | 2021-09-10 |
Family
ID=64142713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810636480.9A Active CN108829846B (en) | 2018-06-20 | 2018-06-20 | Service recommendation platform data clustering optimization system and method based on user characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108829846B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
| CN111353576A (en) * | 2018-12-24 | 2020-06-30 | ***通信集团山西有限公司 | Information generation method, device and equipment based on fuzzy neural network |
| CN111859114A (en) * | 2020-06-18 | 2020-10-30 | 北京百度网讯科技有限公司 | Recommendation system optimization method, device, equipment and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508907A (en) * | 2011-11-11 | 2012-06-20 | 北京航空航天大学 | Dynamic recommendation method based on training set optimization for recommendation system |
| CN103544206A (en) * | 2013-07-16 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for achieving individualized recommendations |
| CN105069140A (en) * | 2015-08-19 | 2015-11-18 | 中国科学院自动化研究所 | Recommending method based on high-order user preferences |
| CN108023840A (en) * | 2017-12-12 | 2018-05-11 | 中国联合网络通信集团有限公司 | OVS network traffics accelerate optimization method and OVS network traffics to accelerate optimization system |
-
2018
- 2018-06-20 CN CN201810636480.9A patent/CN108829846B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508907A (en) * | 2011-11-11 | 2012-06-20 | 北京航空航天大学 | Dynamic recommendation method based on training set optimization for recommendation system |
| CN103544206A (en) * | 2013-07-16 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for achieving individualized recommendations |
| CN105069140A (en) * | 2015-08-19 | 2015-11-18 | 中国科学院自动化研究所 | Recommending method based on high-order user preferences |
| CN108023840A (en) * | 2017-12-12 | 2018-05-11 | 中国联合网络通信集团有限公司 | OVS network traffics accelerate optimization method and OVS network traffics to accelerate optimization system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353576A (en) * | 2018-12-24 | 2020-06-30 | ***通信集团山西有限公司 | Information generation method, device and equipment based on fuzzy neural network |
| CN111353576B (en) * | 2018-12-24 | 2023-09-19 | ***通信集团山西有限公司 | Information generation method, device and equipment based on fuzzy neural network |
| CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
| CN111859114A (en) * | 2020-06-18 | 2020-10-30 | 北京百度网讯科技有限公司 | Recommendation system optimization method, device, equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108829846B (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021063171A1 (en) | Decision tree model training method, system, storage medium, and prediction method | |
| US11481456B2 (en) | Model and pattern structure online unital learning: mapsoul | |
| CN101782976B (en) | Automatic selection method for machine learning in cloud computing environment | |
| Chen et al. | Efficient ant colony optimization for image feature selection | |
| CN106779087A (en) | A kind of general-purpose machinery learning data analysis platform | |
| US20200167659A1 (en) | Device and method for training neural network | |
| CN109766454A (en) | A kind of investor's classification method, device, equipment and medium | |
| Rahman et al. | Discretization of continuous attributes through low frequency numerical values and attribute interdependency | |
| CN108829846A (en) | A kind of business recommended platform data cluster optimization system and method based on user characteristics | |
| CN112967088A (en) | Marketing activity prediction model structure and prediction method based on knowledge distillation | |
| Shiue et al. | Development of machine learning‐based real time scheduling systems: using ensemble based on wrapper feature selection approach | |
| Pecori et al. | Incremental learning of fuzzy decision trees for streaming data classification | |
| Dai et al. | Hybrid deep model for human behavior understanding on industrial internet of video things | |
| CN111914094A (en) | Knowledge graph representation learning method based on ternary interaction | |
| Gong et al. | Evolutionary computation in China: A literature survey | |
| CN113705715B (en) | Time sequence classification method based on LSTM and multi-scale FCN | |
| Sun et al. | Dynamic Intelligent Supply-Demand Adaptation Model Towards Intelligent Cloud Manufacturing. | |
| Ni et al. | A novel ensemble pruning approach based on information exchange glowworm swarm optimization and complementarity measure | |
| CN115130620A (en) | Power consumption mode identification model generation method and device for power equipment | |
| Sood | Iterative solver selection techniques for sparse linear systems | |
| CN113191569A (en) | Enterprise management method and system based on big data | |
| CN112926952A (en) | Cloud computing-combined big data office business processing method and big data server | |
| Sathesh et al. | Analysis of Software Sizing and Project Estimation prediction by Machine Learning Classification | |
| Wu et al. | Multi-label regularized generative model for semi-supervised collective classification in large-scale networks | |
| Yi | Logistics scheduling optimisation and allocation of intercultural communication trade under internet of things and edge computing |
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 |