CN106469191A - A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method - Google Patents
A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method Download PDFInfo
- Publication number
- CN106469191A CN106469191A CN201610778143.4A CN201610778143A CN106469191A CN 106469191 A CN106469191 A CN 106469191A CN 201610778143 A CN201610778143 A CN 201610778143A CN 106469191 A CN106469191 A CN 106469191A
- Authority
- CN
- China
- Prior art keywords
- label
- priority
- behavior
- attribute
- based control
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of adaptive user portrait automotive engine system of Behavior-based control scene and method, the first level dividing system connecting including signal and dynamic labels digging system, the default threshold value judging whether label lost efficacy in described priority dividing system, the label for allowing priority be less than threshold value is in failure state；Described dynamic labels digging system extracts suspicious candidate attribute in real time according to adaptive algorithm, judges to decide whether to become available label by priority dividing system after judging.The present invention passes through priority dividing system given threshold, the label that priority is less than threshold value can be allowed to be in failure state it is ensured that optimum portrait model；Suspicious candidate attribute is extracted in real time by adaptive algorithm, judges to decide whether to become available label by priority dividing system, it is possible to resolve the problem of tag deactivation and static after judging.
Description
Technical field
The present invention relates to big data field, the adaptive user portrait automotive engine system of more particularly, to a kind of Behavior-based control scene
And method.
Background technology
After the Internet gradually steps into the big data epoch, bring a series of changing inevitably to enterprise and consumer behavior
Become and reinvent.Maximum of which change is no more than, and all behaviors of consumer seem will be all " visualization " in face of enterprise.
Further investigation with big data technology and application, how the absorbed point of enterprise is sought for accurate using big data if increasingly focusing on
Pin service, and then deeply excavate potential commercial value.Then, the concept of " user's portrait " is also just arisen at the historic moment.
User draws a portrait (User Profile), and as the foundation of big data, it ideally takes out the information of a user
Overall picture, for precisely, rapidly analyzing the important informations such as user behavior custom, consumption habit further, there is provided enough data
Basis, has established the foundation stone in big data epoch.
User draws a portrait, and that is, user profile labeling is it is simply that enterprise passes through to collect and analysis consumer's society attribute, life are practised
After the data of main information such as used, consuming behavior, the business overall picture Zuo Shi enterprise application ideally taking out a user is big
The basic mode of data technique.User draws a portrait and provides enough Information bases for enterprise, and enterprise can be helped to be quickly found out essence
The more extensive feedback information such as quasi- user group and user's request.
But traditional portrait automotive engine system ineffective treatment ratio is more serious, meaningless or label that meaning is very weak in actual scene
Attribute is too many, and needs a large amount of handmarkings to set known label attribute it is impossible to according to unknown come dynamical min using scene
Attribute.
Content of the invention
In order to overcome the deficiencies in the prior art, the present invention provides a kind of adaptive user portrait engine of Behavior-based control scene
System and method, using adaptive algorithm, it is possible to resolve the problem of tag deactivation and static.
For this reason, first aspect present invention provides a kind of adaptive user portrait automotive engine system of Behavior-based control scene, bag
Include first level dividing system and the dynamic labels digging system of signal connection, in described priority dividing system, default judgement label is
The threshold value of no inefficacy, the label for allowing priority be less than threshold value is in failure state；Described dynamic labels digging system according to
Adaptive algorithm extracts suspicious candidate attribute in real time, judges to decide whether to become available mark by priority dividing system after judging
Sign.
Second aspect present invention provides a kind of adaptive user portrait method of Behavior-based control scene, comprises the steps：
S1, according to trade classification, obtain the tag attributes coming high priority in industry；
S2, adopting multiple data mining algorithms, obtaining and the degree of association of tag attributes being previously set, thus being sorted
The weighted value crossed；
S3, setting threshold value, the too low tag attributes of the exclusion degree of association；
S4, suspicious candidate attribute is extracted in real time according to adaptive algorithm；
S5, obtain candidate attribute after, through determining whether of priority dividing system, finally decide whether to become available
Tag attributes.
Preferably, described adaptive algorithm by counting, associate, clustering algorithm comprehensive Design forms.
Preferably, the data mining algorithm in described step S2 includes association and collaborative filtering.
Further, described step S4 includes：
S401, input User action log, the various actions of segmentation daily record, carry out classification process, by known label attribute
After rejecting, retain Unknown Label attribute；
The compatible degree of difference, similarity and scene between S402, the characteristic vector of each Unknown Label attribute of calculating, according to
Formula comprehensively draws a scoring to judge whether this attribute can become candidate's label.
Compared with prior art, the present invention passes through priority dividing system given threshold, and priority can be allowed to be less than threshold value
Label be in failure state it is ensured that optimum portrait model；Suspicious candidate attribute is extracted in real time by adaptive algorithm, through sentencing
Have no progeny and judge to decide whether to become available label by priority dividing system, it is possible to resolve the asking of tag deactivation and static
Topic.
Brief description
Fig. 1 is the flow chart of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings embodiments of the invention are described in detail.
The present invention provides a kind of adaptive user portrait automotive engine system of Behavior-based control scene, the first level connecting including signal
Dividing system and dynamic labels digging system, in described priority dividing system, the default threshold value judging whether label lost efficacy, uses
It is in failure state in the label allowing priority be less than threshold value；Described dynamic labels digging system is taken out in real time according to adaptive algorithm
Take suspicious candidate attribute, judge to decide whether to become available label by priority dividing system after judging.
Work process comprises the steps：
S1, according to trade classification, obtain the tag attributes coming high priority in industry；
S2, adopting multiple data mining algorithms, obtaining and the degree of association of tag attributes being previously set, thus being sorted
The weighted value crossed；
S3, setting threshold value, the too low tag attributes of the exclusion degree of association；
S401, input User action log, the various actions of segmentation daily record, carry out classification process, by known label attribute
After rejecting, retain Unknown Label attribute；
The compatible degree of difference, similarity and scene between S402, the characteristic vector of each Unknown Label attribute of calculating, according to
Formula comprehensively draw a scoring come to judge whether this attribute can become that candidate's label extracts in real time according to adaptive algorithm can
Doubtful candidate attribute；
S5, obtain candidate attribute after, through determining whether of priority dividing system, finally decide whether to become available
Tag attributes.
Described adaptive algorithm is by counting, associate, clustering algorithm comprehensive Design forms.
Data mining algorithm in described step S2 includes association and collaborative filtering.
To sum up, the present invention passes through priority dividing system given threshold, and the label that priority is less than threshold value can be allowed to be in
Failure state model it is ensured that optimum is drawn a portrait；Suspicious candidate attribute is extracted in real time by adaptive algorithm, by preferential after judging
Level dividing system judges to decide whether to become available label, it is possible to resolve the problem of tag deactivation and static.
The above, the only present invention preferably specific embodiment, but protection scope of the present invention is not limited thereto,
Any those familiar with the art the invention discloses technical scope in, technology according to the present invention scheme and its
Inventive concept equivalent or change in addition, all should be included within the scope of the present invention.
Claims (5)
1. a kind of adaptive user of Behavior-based control scene draws a portrait automotive engine system it is characterised in that including the first level that signal connects
Dividing system and dynamic labels digging system, in described priority dividing system, the default threshold value judging whether label lost efficacy, uses
It is in failure state in the label allowing priority be less than threshold value；Described dynamic labels digging system is taken out in real time according to adaptive algorithm
Take suspicious candidate attribute, judge to decide whether to become available label by priority dividing system after judging.
2. a kind of adaptive user portrait method of Behavior-based control scene is it is characterised in that comprise the steps：
S1, according to trade classification, obtain the tag attributes coming high priority in industry；
S2, adopting multiple data mining algorithms, obtaining and the degree of association of tag attributes being previously set, thus obtaining collated
Weighted value；
S3, setting threshold value, the too low tag attributes of the exclusion degree of association；
S4, suspicious candidate attribute is extracted in real time according to adaptive algorithm；
S5, obtain candidate attribute after, through determining whether of priority dividing system, finally decide whether to become available label
Attribute.
3. a kind of adaptive user portrait method of Behavior-based control scene according to claim 2 is it is characterised in that described
Data mining algorithm in step S2 includes association and collaborative filtering.
4. a kind of adaptive user portrait method of Behavior-based control scene according to claim 2 is it is characterised in that described
Adaptive algorithm is by counting, associate, clustering algorithm comprehensive Design forms.
5. a kind of adaptive user portrait method of Behavior-based control scene according to claim 2 is it is characterised in that described
Step S4 includes：
S401, input User action log, the various actions of segmentation daily record, carry out classification process, known label attribute is rejected
Afterwards, retain Unknown Label attribute；
The compatible degree of difference, similarity and scene between S402, the characteristic vector of each Unknown Label attribute of calculating, according to formula
Comprehensively draw a scoring to judge whether this attribute can become candidate's label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610778143.4A CN106469191A (en) | 2016-08-31 | 2016-08-31 | A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610778143.4A CN106469191A (en) | 2016-08-31 | 2016-08-31 | A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106469191A true CN106469191A (en) | 2017-03-01 |
Family
ID=58230063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610778143.4A Pending CN106469191A (en) | 2016-08-31 | 2016-08-31 | A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106469191A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908606A (en) * | 2017-10-31 | 2018-04-13 | 上海壹账通金融科技有限公司 | Method and system based on different aforementioned sources automatic report generation |
| CN109146539A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | The update method and device of user's portrait |
| CN109446215A (en) * | 2018-10-31 | 2019-03-08 | 北京百分点信息科技有限公司 | A kind of logical engine method of ID drawing real-time priority-based |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
| CN105741134A (en) * | 2016-01-26 | 2016-07-06 | 北京百分点信息科技有限公司 | Method and apparatus for applying cross-data-source marketing crowds to marketing |
-
2016
- 2016-08-31 CN CN201610778143.4A patent/CN106469191A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
| CN105741134A (en) * | 2016-01-26 | 2016-07-06 | 北京百分点信息科技有限公司 | Method and apparatus for applying cross-data-source marketing crowds to marketing |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908606A (en) * | 2017-10-31 | 2018-04-13 | 上海壹账通金融科技有限公司 | Method and system based on different aforementioned sources automatic report generation |
| CN109146539A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | The update method and device of user's portrait |
| CN109446215A (en) * | 2018-10-31 | 2019-03-08 | 北京百分点信息科技有限公司 | A kind of logical engine method of ID drawing real-time priority-based |
| CN109446215B (en) * | 2018-10-31 | 2022-04-12 | 北京百分点科技集团股份有限公司 | Real-time ID pull-through engine method based on priority |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104346370B (en) | Picture search, the method and device for obtaining image text information | |
| EP2889618B1 (en) | Image processing device, program, image processing method, computer-readable medium, and image processing system | |
| CN102426583B (en) | Chinese medicine tongue manifestation retrieval method based on image content analysis | |
| CN104408449B (en) | Intelligent mobile terminal scene literal processing method | |
| CN103703472A (en) | Semantic parsing of objects in video | |
| CN106354755A (en) | Optimizing and processing method for user's portrait | |
| CN108090429A (en) | Face bayonet model recognizing method before a kind of classification | |
| CN101661559A (en) | Digital image training and detecting methods | |
| CN105787133B (en) | Advertisement information filtering method and device | |
| US20120109715A1 (en) | Visualizing visitation patterns at sites of a commercial facility | |
| CN111274926A (en) | Image data screening method and device, computer equipment and storage medium | |
| CN111209818A (en) | Video individual identification method, system, equipment and readable storage medium | |
| CN108537286A (en) | A kind of accurate recognition methods of complex target based on key area detection | |
| CN110188730A (en) | Face datection and alignment schemes based on MTCNN | |
| CN107145778B (en) | Intrusion detection method and device | |
| CN106469191A (en) | A kind of adaptive user portrait automotive engine system of Behavior-based control scene and method | |
| CN101980210A (en) | Marked word classifying and grading method and system | |
| CN111767878A (en) | Deep learning-based traffic sign detection method and system in embedded device | |
| CN106650670A (en) | Method and device for detection of living body face video | |
| CN108647703B (en) | Saliency-based classification image library type judgment method | |
| CN103793717A (en) | Methods for determining image-subject significance and training image-subject significance determining classifier and systems for same | |
| CN104573675A (en) | Operating image displaying method and device | |
| CN103390151A (en) | Face detection method and device | |
| CN106326451A (en) | Method for judging webpage sensing information block based on visual feature extraction | |
| CN112115884A (en) | Form recognition method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170301 |