CN106202430A - Live platform user interest-degree digging system based on correlation rule and method for digging - Google Patents
Live platform user interest-degree digging system based on correlation rule and method for digging Download PDFInfo
- Publication number
- CN106202430A CN106202430A CN201610549934.XA CN201610549934A CN106202430A CN 106202430 A CN106202430 A CN 106202430A CN 201610549934 A CN201610549934 A CN 201610549934A CN 106202430 A CN106202430 A CN 106202430A
- Authority
- CN
- China
- Prior art keywords
- transaction events
- user interest
- degree
- tree
- frequent
- 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.)
- Pending
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of live platform user interest-degree digging system based on correlation rule and method, relate to data mining technology field, this system includes: data acquisition module, for obtaining live platform user behavioural information from server, generate sampling transaction events storehouse and test transaction events storehouse；Association Rules Model builds module, uses spark Computational frame that sampling transaction events storehouse is carried out the excavation of frequent mode, obtains Association Rules Model；User interest degree output module, for inputting Association Rules Model using test transaction events storehouse as input variable, it is thus achieved that the output variable of Association Rules Model, using output variable as user interest content.It is short that the present invention has the calculating cycle, the advantage that the accuracy of test result is high with practicality.
Description
Technical field
The present invention relates to data mining technology field, be specifically related to live platform user interest-degree based on correlation rule and dig
Pick system and method for digging.
Background technology
Along with developing rapidly of live industry, the number of users of webcast website is explosive growth, the most fast and effectively
The viewing interest of digging user, recommends its live content interested to user, is that present each webcast website is badly in need of considering
Problem.In prior art, user interest degree excavate also stop and according to such as personal experience, or simply by user's sight
See the method that A direct broadcasting room also have viewed B direct broadcasting room, found out the such correlation rule of A and B, and then given as user that to have viewed A straight
B direct broadcasting room is recommended to it the when of broadcasting, artificial screening subjective, and in the case of data volume is relatively big, be difficult to look for
Go out correlation rule.
Summary of the invention
For defect present in prior art, it is an object of the invention to provide live platform based on correlation rule and use
Family interest-degree digging system and method for digging so that the mining process of live platform user is more intelligent, has excavation speed
Fast and that digging efficiency is high advantage.
For reaching object above, the present invention adopts the technical scheme that:
A kind of live platform user interest-degree digging system based on correlation rule, including data acquisition module, for from
Server obtains live platform user behavioural information, generates sampling transaction events storehouse and test transaction events storehouse；
Association Rules Model builds module, uses spark Computational frame that sampling transaction events storehouse is carried out frequent mode
Excavate, obtain Association Rules Model；
User interest degree output module, for test transaction events storehouse is inputted Association Rules Model as input variable,
Obtain the output variable of Association Rules Model, using output variable as user interest content.
On the basis of technique scheme, sampling transaction events storehouse is the behavioural information note choosing user in the sampling time
Generate for event.
On the basis of technique scheme, test transaction events storehouse is the behavioural information note choosing user after the sampling time
Generate for event.
On the basis of technique scheme, described Association Rules Model builds module and includes:
Gauge outfit structural unit, described gauge outfit structural unit is used for constructing project gauge outfit, sets the calculating of spark Computational frame
Degree of parallelism, presets support threshold, scanning sample transaction events storehouse, it is thus achieved that comprise in sampling transaction events storehouse is whole frequent
Item and the support of each frequent episode, obtain frequent episode set F to all of frequent episode according to support descending；
FP-tree structural unit, described FP-tree structural unit is used for constructing original FP-tree, scanning sample transaction events storehouse,
Each frequent episode of each event in sampling transaction events storehouse is reset according to the order in frequent episode set F, and presses
According to the order after resetting, each frequent episode of each things is inserted in FP-tree, form original FP-tree；
Function calling cell, described function calling cell carries out the excavation of frequent episode for calling FP-growth function；
FP-tree computing module, described FP-tree computing module is used for carrying out FP-tree frequency set algorithm, obtains support more than propping up
The frequent mode of degree of holding threshold value.
The method for digging of live platform user interest-degree digging system based on correlation rule, comprises the steps:
S1, data acquisition module obtains live platform user behavioural information from server, chooses user in the sampling time
Behavioural information is designated as event, generates sampling transaction events storehouse；
S2, Association Rules Model builds module, based on spark Computational frame, sampling transaction events storehouse is carried out frequent mode
Excavation, obtain Association Rules Model；
S3, data acquisition module obtains live platform user behavioural information from server, chooses user after the sampling time
Behavioural information is designated as event, generates test transaction events storehouse；
S4, user interest degree output module is by as the input variable of Association Rules Model and defeated for test transaction events storehouse
Enter Association Rules Model, it is thus achieved that the output variable of Association Rules Model, using output variable as user interest content.
On the basis of technique scheme, also include:
S5, user interest degree output module generates user interest list according to user interest content.
On the basis of technique scheme, FP-tree frequency set algorithm is used to carry out the excavation of frequent mode.
On the basis of technique scheme, using FP-tree frequency set algorithm to carry out the excavation of frequent mode, concrete steps are such as
Under:
S21, constructs project gauge outfit: set the calculating degree of parallelism of spark Computational frame, presets support threshold, and scanning is adopted
Sample transaction events storehouse, it is thus achieved that the whole frequent episode comprised in sampling transaction events storehouse and the support of each frequent episode, to institute
Some frequent episode obtain frequent episode set F according to support descending；
S22, constructs original FP-tree: scanning sample transaction events storehouse again, by each event in sampling transaction events storehouse
Each frequent episode reset according to the order in frequent episode set F, and according to reset after order each things
Each frequent episode inserts in FP-tree, forms original FP-tree.
S23, calls FP-growth function and carries out the excavation of frequent episode；
S24, according to FP-tree frequency set algorithm, the support obtained is more than the frequent mode of support threshold.
On the basis of technique scheme, in FP-tree, a node represents a direct broadcasting room, corresponding one an of paths
The viewing behavioural information of user, on every paths, the count value of node represents that support, described support are used for determining any two
The correlation degree of individual direct broadcasting room.
On the basis of technique scheme, frequent mode is that each direct broadcasting room is general to the random viewing of other direct broadcasting room
Rate.
Compared with prior art, it is an advantage of the current invention that:
(1) based on correlation rule the live platform user interest-degree digging system of the present invention and method use association rule
Then carry out data management analysis, drastically reduce the area the time of calculating, build Association Rules Model based on Spark Computational frame,
The process that user interest degree is excavated is more intelligent, in terms of calculating speed faster, substantially reduces the calculating cycle, it is possible to
Significantly more efficient find correlation rule, it is ensured that the accuracy of test result and practicality.
(2) based on correlation rule the live platform user interest-degree digging system of the present invention and method, builds association rule
Then the algorithm of model has multiple, uses FP-tree frequency set algorithm in the present invention, and in FP-tree, a node represents a direct broadcasting room,
The viewing behavioural information of the corresponding user of one paths, on every paths, the count value of node represents support, and support is used
In determining the correlation degree of any two direct broadcasting room, utilize tree structure to directly obtain frequent item set, decrease scanning sample number
According to the number of times in storehouse, the efficiency of the algorithm of raising.
Accompanying drawing explanation
Fig. 1 is the system block diagram in the embodiment of the present invention；
Fig. 2 is the structured flowchart that in the embodiment of the present invention, Association Rules Model builds module；
Fig. 3 is the method flow diagram in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described in further detail.
Shown in Figure 1, the embodiment of the present invention provides a kind of live platform user interest-degree based on correlation rule to excavate
System, including: data acquisition module, for obtaining live platform user behavioural information from server, generate sampling transaction events
Storehouse and test transaction events storehouse, user behavior information is that user watches behavior each time, can be viewing a certain direct broadcasting room, viewing
A certain subregion or watch a certain column, watches a certain direct broadcasting room for user in the present embodiment.
Association Rules Model builds module, uses spark Computational frame that sampling transaction events storehouse is carried out frequent mode
Excavating, obtain Association Rules Model, wherein frequent mode is that each direct broadcasting room watches probability at random to other direct broadcasting room.Based on
Spark Computational frame builds Association Rules Model so that the process that user interest degree excavates is more intelligent, is calculating speed side
Face faster, substantially reduces the calculating cycle.
Shown in Figure 2, Association Rules Model builds module and includes:
Gauge outfit structural unit, gauge outfit structural unit is used for constructing project gauge outfit, and the calculating setting spark Computational frame is parallel
Degree, presets support threshold, scanning sample transaction events storehouse, it is thus achieved that in sampling transaction events storehouse whole frequent episode of comprising and
The support of each frequent episode, obtains frequent episode set F to all of frequent episode according to support descending；
FP-tree structural unit, FP-tree structural unit is used for constructing original FP-tree, scanning sample transaction events storehouse, will adopt
Each frequent episode of each event in sample transaction events storehouse is reset according to the order in frequent episode set F, and according to weight
Order after row is inserted each frequent episode of each things in FP-tree, forms original FP-tree；
Function calling cell, function calling cell carries out the excavation of frequent episode for calling FP-growth function；
FP-tree computing module, FP-tree computing module is used for carrying out FP-tree frequency set algorithm, obtains support more than support
The frequent mode of threshold value.
User interest degree output module, for test transaction events storehouse is inputted Association Rules Model as input variable,
Obtain the output variable of Association Rules Model, using output variable as user interest content, and then find the interest of user to watch
Point, can recommend, to user, the viewing content that user likes, and improves comfort level and the sense organ degree of user, effectively reduces user's stream
Situation about losing occurs.
Shown in Figure 3, the embodiment of the present invention provides live platform user interest-degree digging system based on correlation rule
Method for digging, comprise the steps:
S1, data acquisition module obtains live platform user behavioural information from server, chooses user in the sampling time
Behavioural information is designated as event, generates sampling transaction events storehouse；
S2, Association Rules Model builds module, based on spark Computational frame, sampling transaction events storehouse is carried out frequent mode
Excavation, obtain Association Rules Model；
Use FP-tree frequency set algorithm to carry out the excavation of frequent mode, specifically comprise the following steps that
S21, constructs project gauge outfit: set the calculating degree of parallelism of spark Computational frame, presets support threshold, and scanning is adopted
Sample transaction events storehouse, it is thus achieved that the whole frequent episode comprised in sampling transaction events storehouse and the support of each frequent episode, to institute
Some frequent episode obtain frequent episode set F according to support descending；
S22, constructs original FP-tree: scanning sample transaction events storehouse again, by each event in sampling transaction events storehouse
Each frequent episode reset according to the order in frequent episode set F, and according to reset after order each things
Each frequent episode inserts in FP-tree, and in FP-tree, each node represents a direct broadcasting room, the corresponding user's of a paths
Viewing behavioural information, on every paths, the count value of node represents support, and support is for determining any two direct broadcasting room
Correlation degree, if node has existed when frequent episode inserts, then the support of this frequent episode node adds 1, if frequent episode is inserted
Fashionable node does not exists, then creating support is the node of 1, and in this node link to project gauge outfit.
Following description can be made for above-mentioned false code:
The input of FP-growth function: tree refers to original original FP-tree or refers to the condition under certain pattern
FP-tree, A refers to the suffix of pattern, but the A=null when calling for the first time, after in recursive call later, A is only pattern
Sew；
The output of FP-growth function: export all of pattern and support thereof during recursive call, and each time
Call in the pattern of FP-growth output result and necessarily include the pattern suffix that FP-growth function inputs.
At the ground floor of FP-growth recursive call, A=null before and after pattern, obtain is frequent 1 collection；To each
Frequent 1 collection, carries out recursive call FP-growth () and obtains polynary frequent item set.
S24, according to FP-tree frequency set algorithm, the support finally given is more than the frequent mode of support threshold, frequent mould
Formula is that each direct broadcasting room watches probability at random to other direct broadcasting room.Utilize tree structure to directly obtain frequent item set, decrease
The number of times of scanning sample data base, the efficiency of the algorithm of raising
S3, data acquisition module obtains live platform user behavioural information from server, chooses user after the sampling time
Behavioural information, generates test transaction events storehouse；
S4, user interest degree output module is by as the input variable of Association Rules Model and defeated for test transaction events storehouse
Enter Association Rules Model, it is thus achieved that the output variable of Association Rules Model, using output variable as user interest content；
S5, generates user interest list according to user interest content, recommends to user according to the user interest list generated
Its viewing content interested.
The present invention is not limited to above-mentioned embodiment, for those skilled in the art, without departing from
On the premise of the principle of the invention, it is also possible to make some improvements and modifications, these improvements and modifications are also considered as the protection of the present invention
Within the scope of.The content not being described in detail in this specification belongs to prior art known to professional and technical personnel in the field.
Claims (10)
1. a live platform user interest-degree digging system based on correlation rule, it is characterised in that including: data acquisition module
Block, for obtaining live platform user behavioural information from server, generates sampling transaction events storehouse and test transaction events storehouse；
Association Rules Model builds module, uses spark Computational frame that sampling transaction events storehouse is carried out the excavation of frequent mode,
Obtain Association Rules Model；
User interest degree output module, for inputting Association Rules Model using test transaction events storehouse as input variable, it is thus achieved that
The output variable of Association Rules Model, using output variable as user interest content.
A kind of live platform user interest-degree digging system based on correlation rule, its feature exists
It is to choose the behavioural information of user in the sampling time to be designated as event and generate in: sampling transaction events storehouse.
A kind of live platform user interest-degree digging system based on correlation rule, its feature exists
In: test the behavioural information of user after transaction events storehouse is to choose the sampling time and be designated as what event generated.
A kind of live platform user interest-degree digging system based on correlation rule, its feature exists
In: described Association Rules Model builds module and includes:
Gauge outfit structural unit, described gauge outfit structural unit is used for constructing project gauge outfit, and the calculating setting spark Computational frame is parallel
Degree, presets support threshold, scanning sample transaction events storehouse, it is thus achieved that in sampling transaction events storehouse whole frequent episode of comprising and
The support of each frequent episode, obtains frequent episode set F to all of frequent episode according to support descending；
FP-tree structural unit, described FP-tree structural unit is used for constructing original FP-tree, scanning sample transaction events storehouse, will adopt
Each frequent episode of each event in sample transaction events storehouse is reset according to the order in frequent episode set F, and according to weight
Order after row is inserted each frequent episode of each things in FP-tree, forms original FP-tree；
Function calling cell, described function calling cell carries out the excavation of frequent episode for calling FP-growth function；
FP-tree computing module, described FP-tree computing module is used for carrying out FP-tree frequency set algorithm, obtains support more than support
The frequent mode of threshold value.
5. use the excavation side of live platform user interest-degree digging system based on correlation rule as claimed in claim 1
Method, it is characterised in that comprise the steps:
S1, data acquisition module obtains live platform user behavioural information from server, chooses the behavior of user in the sampling time
Information is designated as event, generates sampling transaction events storehouse；
S2, Association Rules Model structure module carries out frequent mode based on spark Computational frame to sampling transaction events storehouse and digs
Pick, obtains Association Rules Model；
S3, data acquisition module obtains live platform user behavioural information from server, chooses the behavior of user after the sampling time
Information is designated as event, generates test transaction events storehouse；
S4, user interest degree output module will be tested the transaction events storehouse input variable as Association Rules Model, and inputted pass
Connection rule model, it is thus achieved that the output variable of Association Rules Model, using output variable as user interest content.
6. live platform user interest-degree method for digging based on correlation rule as claimed in claim 5, it is characterised in that also
Including:
S5, user interest degree output module generates user interest list according to user interest content.
7. live platform user interest-degree method for digging based on correlation rule as claimed in claim 5, it is characterised in that: adopt
The excavation of frequent mode is carried out with FP-tree frequency set algorithm.
8. live platform user interest-degree method for digging based on correlation rule as claimed in claim 7, it is characterised in that: adopt
Carry out the excavation of frequent mode with FP-tree frequency set algorithm, specifically comprise the following steps that
S21, constructs project gauge outfit: set the calculating degree of parallelism of spark Computational frame, presets support threshold, scanning sample thing
Business event base, it is thus achieved that the whole frequent episode comprised in sampling transaction events storehouse and the support of each frequent episode, to all of
Frequent episode obtains frequent episode set F according to support descending；
S22, constructs original FP-tree: scanning sample transaction events storehouse again, every by each event in sampling transaction events storehouse
Individual frequent episode is reset according to the order in frequent episode set F, and according to each each things of order after resetting
Frequent episode inserts in FP-tree, forms original FP-tree；
S23, calls FP-growth function and carries out the excavation of frequent episode；
S24, according to FP-tree frequency set algorithm, the support obtained is more than the frequent mode of support threshold.
9. live platform user interest-degree method for digging based on correlation rule as claimed in claim 8, it is characterised in that:
In FP-tree, a node represents a direct broadcasting room, the viewing behavioural information of the corresponding user of a paths, and every paths saves
The count value of point represents support, and described support is for determining the correlation degree of any two direct broadcasting room.
10. live platform user interest-degree method for digging based on correlation rule as claimed in claim 8, it is characterised in that:
Frequent mode is that each direct broadcasting room watches probability at random to other direct broadcasting room.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610549934.XA CN106202430A (en) | 2016-07-13 | 2016-07-13 | Live platform user interest-degree digging system based on correlation rule and method for digging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610549934.XA CN106202430A (en) | 2016-07-13 | 2016-07-13 | Live platform user interest-degree digging system based on correlation rule and method for digging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106202430A true CN106202430A (en) | 2016-12-07 |
Family
ID=57482071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610549934.XA Pending CN106202430A (en) | 2016-07-13 | 2016-07-13 | Live platform user interest-degree digging system based on correlation rule and method for digging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106202430A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107396200A (en) * | 2017-08-22 | 2017-11-24 | 深圳市中青合创传媒科技有限公司 | The method that net cast is carried out based on social software |
| CN107835441A (en) * | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
| CN107908776A (en) * | 2017-11-30 | 2018-04-13 | 国网浙江省电力公司经济技术研究院 | Frequent mode Web Mining algorithm and system based on affairs project incidence matrix |
| CN108271050A (en) * | 2016-12-30 | 2018-07-10 | 武汉斗鱼网络科技有限公司 | The method and device that a kind of direct broadcasting room program is recommended |
| CN108345959A (en) * | 2018-01-11 | 2018-07-31 | 佛山市顺德区中山大学研究院 | A kind of cell gate inhibition alarm prediction technique based on development of Mobile Internet technology |
| CN110162664A (en) * | 2018-12-17 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Video recommendation method, device, computer equipment and storage medium |
| CN110750561A (en) * | 2018-07-20 | 2020-02-04 | 深圳市诚壹科技有限公司 | Method and device for mining associated application program |
| CN111310066A (en) * | 2020-02-27 | 2020-06-19 | 湖北工业大学 | Friend recommendation method and system based on topic model and association rule algorithm |
| CN112180752A (en) * | 2020-10-14 | 2021-01-05 | 四川长虹电器股份有限公司 | System and method for automatically generating intelligent household scene linkage setting |
| CN113419950A (en) * | 2021-06-22 | 2021-09-21 | 平安壹钱包电子商务有限公司 | Method and device for generating UI automation script, computer equipment and storage medium |
| CN113435948A (en) * | 2021-08-25 | 2021-09-24 | 汇通达网络股份有限公司 | E-commerce platform data monitoring method and system |
| CN115080565A (en) * | 2022-06-08 | 2022-09-20 | 陕西天诚软件有限公司 | Multi-source data unified processing system based on big data engine |
| CN115563192A (en) * | 2022-11-22 | 2023-01-03 | 山东科技大学 | High-utility periodic frequent pattern mining method applied to purchase pattern |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140214537A1 (en) * | 2013-01-31 | 2014-07-31 | Samsung Electronics Co., Ltd. | User terminal and method and system for providing advertisement |
| CN105069087A (en) * | 2015-08-03 | 2015-11-18 | 成都康赛信息技术有限公司 | Web log data mining based website optimization method |
-
2016
- 2016-07-13 CN CN201610549934.XA patent/CN106202430A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140214537A1 (en) * | 2013-01-31 | 2014-07-31 | Samsung Electronics Co., Ltd. | User terminal and method and system for providing advertisement |
| CN105069087A (en) * | 2015-08-03 | 2015-11-18 | 成都康赛信息技术有限公司 | Web log data mining based website optimization method |
Non-Patent Citations (2)
| Title |
|---|
| 张荣: "基于关联规则的用户兴趣模型的研究与应用", 《中国优秀硕士学位论文全文数据库》 * |
| 谢欢: "大数据挖掘中的并行算法研究及应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108271050A (en) * | 2016-12-30 | 2018-07-10 | 武汉斗鱼网络科技有限公司 | The method and device that a kind of direct broadcasting room program is recommended |
| CN108271050B (en) * | 2016-12-30 | 2020-01-03 | 武汉斗鱼网络科技有限公司 | Live broadcast room program recommendation method and device |
| CN107396200A (en) * | 2017-08-22 | 2017-11-24 | 深圳市中青合创传媒科技有限公司 | The method that net cast is carried out based on social software |
| CN107835441B (en) * | 2017-10-10 | 2020-01-03 | 武汉斗鱼网络科技有限公司 | Live broadcast recommendation method, storage medium, device and system based on path prediction |
| CN107835441A (en) * | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
| CN107908776A (en) * | 2017-11-30 | 2018-04-13 | 国网浙江省电力公司经济技术研究院 | Frequent mode Web Mining algorithm and system based on affairs project incidence matrix |
| CN108345959A (en) * | 2018-01-11 | 2018-07-31 | 佛山市顺德区中山大学研究院 | A kind of cell gate inhibition alarm prediction technique based on development of Mobile Internet technology |
| CN110750561A (en) * | 2018-07-20 | 2020-02-04 | 深圳市诚壹科技有限公司 | Method and device for mining associated application program |
| CN110162664A (en) * | 2018-12-17 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Video recommendation method, device, computer equipment and storage medium |
| CN111310066A (en) * | 2020-02-27 | 2020-06-19 | 湖北工业大学 | Friend recommendation method and system based on topic model and association rule algorithm |
| CN111310066B (en) * | 2020-02-27 | 2023-06-09 | 湖北工业大学 | Friend recommendation method and system based on topic model and association rule algorithm |
| CN112180752A (en) * | 2020-10-14 | 2021-01-05 | 四川长虹电器股份有限公司 | System and method for automatically generating intelligent household scene linkage setting |
| CN113419950A (en) * | 2021-06-22 | 2021-09-21 | 平安壹钱包电子商务有限公司 | Method and device for generating UI automation script, computer equipment and storage medium |
| CN113435948A (en) * | 2021-08-25 | 2021-09-24 | 汇通达网络股份有限公司 | E-commerce platform data monitoring method and system |
| CN115080565A (en) * | 2022-06-08 | 2022-09-20 | 陕西天诚软件有限公司 | Multi-source data unified processing system based on big data engine |
| CN115563192A (en) * | 2022-11-22 | 2023-01-03 | 山东科技大学 | High-utility periodic frequent pattern mining method applied to purchase pattern |
| CN115563192B (en) * | 2022-11-22 | 2023-03-10 | 山东科技大学 | Method for mining high-utility periodic frequent pattern applied to purchase pattern |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106202430A (en) | Live platform user interest-degree digging system based on correlation rule and method for digging | |
| Page et al. | Three ingredients for improved global aftershock forecasts: Tectonic region, time‐dependent catalog incompleteness, and intersequence variability | |
| CN103106279B (en) | Clustering method a kind of while based on nodal community and structural relationship similarity | |
| CN104424235B (en) | The method and apparatus for realizing user profile cluster | |
| CN107066476A (en) | A kind of real-time recommendation method based on article similarity | |
| CN108804619A (en) | Interest preference prediction technique, device, computer equipment and storage medium | |
| CN106203631B (en) | The parallel Frequent Episodes Mining and system of description type various dimensions sequence of events | |
| Teng et al. | Seismicity declustering and hazard analysis of the Oklahoma–Kansas region | |
| CN102289507A (en) | Method for mining data flow weighted frequent mode based on sliding window | |
| CN104216874B (en) | Positive and negative mode excavation method and system are weighted between the Chinese word based on coefficient correlation | |
| CN105740245A (en) | Frequent item set mining method | |
| CN102122291A (en) | Blog friend recommendation method based on tree log pattern analysis | |
| Li et al. | Assembly processes of waterbird communities across subsidence wetlands in China: A functional and phylogenetic approach | |
| CN109118155B (en) | Method and device for generating operation model | |
| CN106294715A (en) | A kind of association rule mining method based on attribute reduction and device | |
| CN110471957A (en) | Localization difference secret protection Mining Frequent Itemsets based on frequent pattern tree (fp tree) | |
| Pastén et al. | Time-based network analysis before and after the m w 8.3 illapel earthquake 2015 Chile | |
| CN103885993A (en) | Public opinion monitoring method and device for microblog | |
| CN109582714A (en) | A kind of government affairs item data processing method based on time fading correlation | |
| CN102799616A (en) | Outlier point detection method in large-scale social network | |
| CN108182294A (en) | A kind of film based on frequent item set growth algorithm recommends method and system | |
| US10444062B2 (en) | Measuring and diagnosing noise in an urban environment | |
| CN107908696A (en) | A kind of parallel efficiently multidimensional space data clustering algorithm GRIDEN based on grid and density | |
| Rijal et al. | Development of tree recruitment models for 10 species groups in the sugar maple-dominated mixed forests of eastern Canada | |
| CN104794120B (en) | A kind of mass seismic data takes out diversity method parallel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |