CN109003138A - A kind of advertisement recommender system and method based on client's taste analysis - Google Patents
A kind of advertisement recommender system and method based on client's taste analysis Download PDFInfo
- Publication number
- CN109003138A CN109003138A CN201810819683.1A CN201810819683A CN109003138A CN 109003138 A CN109003138 A CN 109003138A CN 201810819683 A CN201810819683 A CN 201810819683A CN 109003138 A CN109003138 A CN 109003138A
- Authority
- CN
- China
- Prior art keywords
- unit
- user
- advertisement
- information
- module
- 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
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Abstract
The invention discloses a kind of advertisement recommender systems and method based on client's taste analysis, including user log-in block, processing module, excavate module, advertisement recommending module and storage module, the user log-in block, processing module, excavate module, advertisement recommending module and storage module are placed in inside recommendation apparatus, the user log-in block includes logging request unit, authentication unit and Account Logon unit, the logging request unit is used to receive the logging request of client, obtain the request data package of log-on message, the authentication unit includes identifying code transmission unit and identifying code receiving unit, after identifying code transmission unit is used for login username, send identifying code verifying, identifying code receiving unit is used to receive the identifying code that user feedback is returned, carry out identifying code verifying.The advertisement recommender system and method based on client's taste analysis, be used only it is safe and efficient, and can accurately according to consumer taste carry out recommended advertisements.
Description
Technical field
The present invention relates to a kind of advertisement recommender systems and method based on client's taste analysis, belong to technical field of advertisement.
Background technique
Advertisement is exactly publicized widely as its name suggests, i.e., informs certain part things to social the public.Advertisement divides government public
Accuse and commercial advertisement, commercial advertisement is that industrial and commercial enterprises are to promote the sale of goods or provide service, with way of paying, by advertising media to
Consumer or user propagate the means of commodity or information on services.Commdity advertisement is exactly such economic advertisement.With internet skill
The development of art obtains information by internet, and life, amusement and work are at a part for people's lives.Businessman is in order to improve
Popularity promotes commodity, often through internet delivered advertisements.Existing advertisement recommended method is often based upon the basic money of user
Material, the personal method modeled to the click behavior of advertisement realize the recommendation of advertisement, but this recommended method does not account for
User is orientated advertisement real feelings, the depth of level of interest is excavated, and is especially difficult to the negative emotions of user, in some instances it may even be possible to
It is the interested behavior of user by the Activity recognition of user's negative emotions, the advertisement of recommendation, which is difficult to avoid that, generates harassing and wrecking to user,
The accuracy that advertisement is recommended is not high.
It is present to solve the problems, such as because of a kind of advertisement recommender system and method based on client's taste analysis of the invention,
It is the current most important thing.
Summary of the invention
It is an object of the invention to invent a kind of advertisement recommender system and method based on client's taste analysis, on solving
State the problem of proposing in background technique.
Realizing the technical solution of above-mentioned purpose is: system is recommended in a kind of advertisement based on client's taste analysis of one of present invention
System, including user log-in block, processing module, excavation module, advertisement recommending module and storage module, the user log in mould
Block, processing module, excavation module, advertisement recommending module and storage module are placed in inside recommendation apparatus.
Preferably, the user log-in block includes logging request unit, authentication unit and Account Logon unit, described to step on
Record request unit is used to receive the logging request of client, obtains the request data package of log-on message, the authentication unit includes
Identifying code transmission unit and identifying code receiving unit after identifying code transmission unit is used for login username, send identifying code verifying,
Identifying code receiving unit is used to receive the identifying code that user feedback is returned, and carries out identifying code verifying, it is ensured that and it is to log in person, it is described
Account Logon unit is for carrying out user's login by user name and identifying code after obtaining correct identifying code.
Preferably, the processing module includes reading unit, initialization unit and taxon, and the reading unit is used for
The personal information and browsing record, the initialization unit for reading user log-in block are used to extract the content of user, remove nothing
Information and content, the taxon is for classifying to user according to the effective information of extraction module, convenient for subsequent
Information integration and information recommendation.
Preferably, the excavation module includes weight analysis unit, time attenuation analysis unit, temperature attenuation analysis list
Member, liveness attenuation analysis unit and modeling unit, the weight analysis unit is connected with reading unit and taxon, to whole
Information after reason carries out behavior weight analysis, obtains behavior weight coefficient;The time attenuation analysis unit and propose reading unit
It is connected with taxon, time attenuation analysis is carried out to the information after arrangement, obtains time attenuation coefficient;The temperature decaying point
Analysis unit is connected with reading unit and taxon, carries out temperature attenuation analysis to the information after arrangement, obtains temperature decaying system
Number;The liveness attenuation analysis unit is connected with reading unit and taxon, carries out liveness to the information after arrangement and declines
Deduction analysis, obtains liveness attenuation coefficient;The modeling unit declines with weight analysis unit, time attenuation analysis unit, temperature
Subtract analytical unit and liveness attenuation analysis unit is respectively connected with, to behavior weight coefficient, time attenuation coefficient, temperature decaying system
Several or liveness attenuation coefficient is normalized, and establishes the interest model of the user, and then obtain each of the user
The potential consumption demand of kind.
Preferably, the advertisement recommending module includes that scoring unit, the first screening unit, filter element and the second screening are single
Member, the scoring unit are convenient to recommend top quality advertisement, institute to user by scoring for scoring all advertisements
The first screening unit is stated for obtaining target recommended advertisements range according to scoring screening Candidate Recommendation advertisement, the filter element is used
In by within the scope of targeted advertisements illegal contents and user dislike content be filtered, second screening unit be used for according to mistake
Screening obtains target recommended advertisements in Candidate Recommendation advertisement after filter.
Preferably, the storage module includes personal information storage element, browsing record storage element, the storage of thoughts information
Unit and noninductive information storage unit, the personal information after the personal information storage element is used to improve user store
And integration, the browsing record storage element are convenient for the subsequent lookup browsing content of user, the thoughts for storing browsing record
Information storage unit is convenient for storing the interested information of user, to facilitate information to integrate, so that subsequent advertisement pushes away
The true hobby being more close to the users is recommended, the noninductive information storage unit is used to store the information that user dislikes, into
Row information integration, facilitate subsequent advertisement recommend when can filter out such content so that subsequent advertisement recommend more close to
The true hobby of user.
A kind of method of advertisement recommender system based on client's taste analysis of the two of the present invention, comprising the following steps:
S1, user are logged in by user log-in block;
S2, processing module are after the completion of user logs in, by personal information storage element, browsing record storage in storage module
Unit, thoughts information storage unit and noninductive information storage unit are integrated and are analyzed, convenient for extract user point of interest and
Dislike point;
S3, the interest model of user is analyzed come the various potential interest demands of searching by excavating module;
S4, the processing for passing through advertisement recommending module after the completion of excavating, carry out the advertisement that recommended user is interested and likes;
Various information are stored and are integrated by S5, last storage module, convenient for next time recommend when advertisement recommend more close to
The true hobby at family.
Preferably, by excavate module by the interest model of user analyze come, comprising:
Behavior weight analysis is carried out to the information after arrangement, obtains behavior weight coefficient;
Time attenuation analysis is carried out to the information after arrangement, obtains time attenuation coefficient;
Temperature attenuation analysis is carried out to the information after arrangement, obtains temperature attenuation coefficient;
Liveness attenuation analysis is carried out to the information after arrangement, obtains liveness attenuation coefficient;
To behavior weight coefficient, time attenuation coefficient, place is normalized in temperature attenuation coefficient or liveness attenuation coefficient
Reason, establishes the interest model of the user.
The beneficial effects of the present invention are: being somebody's turn to do advertisement recommender system and method based on client's taste analysis, stepped on by user
Record module increases the login security of user, can protect the privacy of user, is carried out by information of the processing module to user
Integration removes some useless information, and convenient for the calculating of follow-up, use can be established according to the information handled well by excavating module
The interest model at family, convenient for preferably recommending the advertisement according to consumer taste, advertisement recommending module will further reduce the scope,
And the content of user's dislike is removed, recommend optimal advertisement out, information is stored by storage device, is looked into convenient for next time
Look for, should advertisement recommender system and method based on client's taste analysis, be used only it is safe and efficient, and can accurately according to
Consumer taste carries out recommended advertisements.
Detailed description of the invention
Fig. 1 is the frame diagram of advertisement recommender system of the invention;
Fig. 2 is the frame diagram of user log-in block of the invention;
Fig. 3 is the frame diagram of processing module of the invention.
Fig. 4 is the frame diagram of excavation module of the invention;
Fig. 5 is the frame diagram of advertisement recommending module of the invention;
Fig. 6 is the frame diagram of storage module of the invention;
Fig. 7 is the flow diagram of advertisement recommended method of the invention.
In figure: module, 4 advertisement recommending modules, 5 storage modules, 6 logins are excavated in 1 user log-in block, 2 processing modules, 3
Request unit, 7 authentication units, 8 Account Logon units, 9 reading units, 10 initialization units, 11 taxons, 12 weight analysis
Unit, 13 time attenuation analysis units, 14 temperature attenuation analysis units, 15 liveness attenuation analysis units, 16 modeling units, 17
Score unit, 18 first screening units, 19 filter elements, 20 second screening units, 21 personal information storage elements, 22 browsing notes
Record storage element, 23 thoughts information storage units, 24 noninductive information storage units.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings.
The present invention provides a kind of advertisements based on client's taste analysis of one of the present invention as shown in figures 1 to 6 to recommend system
System, including user log-in block 1, processing module 2, excavation module 3, advertisement recommending module 4 and storage module 5, the user step on
Record module 1, processing module 2, excavation module 3, advertisement recommending module 4 and storage module 5 are placed in inside recommendation apparatus.
The user log-in block 1 includes logging request unit 6, authentication unit 7 and Account Logon unit 8, the login
Request unit 6 is used to receive the logging request of client, obtains the request data package of log-on message, the authentication unit 7 includes
Identifying code transmission unit and identifying code receiving unit after identifying code transmission unit is used for login username, send identifying code verifying,
Identifying code receiving unit is used to receive the identifying code that user feedback is returned, and carries out identifying code verifying, it is ensured that and it is to log in person, it is described
Account Logon unit 8 is for carrying out user's login by user name and identifying code after obtaining correct identifying code.
The processing module 2 includes reading unit 9, initialization unit 10 and taxon 11, and the reading unit 9 is used for
The personal information and browsing record of user log-in block 1 are read, the initialization unit 10 is used to extract the content of user, removal
Useless information and content, the taxon 11 are convenient for for being classified according to the effective information of extraction module to user
Subsequent information integration and information recommendation.
The excavation module 3 includes weight analysis unit 12, time attenuation analysis unit 13, temperature attenuation analysis unit
14, liveness attenuation analysis unit 15 and modeling unit 16, the weight analysis unit 12 and reading unit 9 and taxon 11
It is connected, behavior weight analysis is carried out to the information after arrangement, obtains behavior weight coefficient;The time attenuation analysis unit 13 with
It proposes reading unit 9 to be connected with taxon 11, time attenuation analysis is carried out to the information after arrangement, obtains time attenuation coefficient;
The temperature attenuation analysis unit 14 is connected with reading unit 9 and taxon 11, carries out temperature decaying to the information after arrangement
Analysis obtains temperature attenuation coefficient;The liveness attenuation analysis unit 15 is connected with reading unit 9 and taxon 11, right
Information after arrangement carries out liveness attenuation analysis, obtains liveness attenuation coefficient;The modeling unit 16 and weight analysis list
Member 12, time attenuation analysis unit 13, temperature attenuation analysis unit 14 and liveness attenuation analysis unit 15 are respectively connected with, to row
For weight coefficient, time attenuation coefficient, temperature attenuation coefficient or liveness attenuation coefficient are normalized, described in foundation
The interest model of user, and then obtain the various potential consumption demands of the user.
The advertisement recommending module 4 includes that scoring unit 17, the first screening unit 18, filter element 19 and the second screening are single
Member 20, the scoring unit 17 are conveniently recommended by scoring to user top quality wide for scoring all advertisements
It accuses, first screening unit 18 is used to obtain target recommended advertisements range, the mistake according to scoring screening Candidate Recommendation advertisement
Filter unit 19 be used for by within the scope of targeted advertisements illegal contents and user dislike content be filtered, second screening unit
20 for obtaining target recommended advertisements according to screening in filtered Candidate Recommendation advertisement.
The storage module 5 includes personal information storage element 21, browsing record storage element 22, thoughts information storage list
Member 23 and noninductive information storage unit 24, the personal information after the personal information storage element 21 is used to improve user carry out
Storage and integration, the browsing record storage element 22 are convenient for the subsequent lookup browsing content of user, institute for storing browsing record
Thoughts information storage unit 23 is stated convenient for storing the interested information of user, to facilitate information to integrate, so that subsequent
Advertisement recommend the true hobby be more close to the users, the information that the noninductive information storage unit 24 is used to dislike user into
Row storage, carries out information integration, facilitates subsequent advertisement that can filter out such content when recommending, so that subsequent advertisement is recommended
The true hobby being more close to the users.
Referring to Fig. 7, the method for the one of the two of the present invention advertisement recommender system based on client's taste analysis, including it is following
Step:
S1, user are logged in by user log-in block 1;
S2, processing module 2 record personal information storage element 21, browsing in storage module 5 after the completion of user logs in
Storage element 22, thoughts information storage unit 23 and noninductive information storage unit 24 are integrated and are analyzed, convenient for extracting user
Point of interest and dislike point;
S3, the interest model of user is analyzed come the various potential interest demands of searching by excavating module 3;
S4, the processing for passing through advertisement recommending module 4 after the completion of excavating, carry out the advertisement that recommended user is interested and likes;
Various information are stored and are integrated by S5, last storage module 5, convenient for next time recommend when advertisement recommend more close to
The true hobby at family.
Above embodiments are used for illustrative purposes only, rather than limitation of the present invention, the technology people in relation to technical field
Member, without departing from the spirit and scope of the present invention, can also make various transformation or modification, therefore all equivalent
Technical solution also should belong to scope of the invention, should be limited by each claim.
Claims (8)
1. a kind of advertisement recommender system based on client's taste analysis, which is characterized in that including user log-in block (1), processing
Module (2) excavates module (3), advertisement recommending module (4) and storage module (5), the user log-in block (1), processing module
(2), module (3), advertisement recommending module (4) and storage module (5) is excavated to be placed in inside recommendation apparatus.
2. the advertisement recommender system according to claim 1 based on client's taste analysis, which is characterized in that the user steps on
Recording module (1) includes logging request unit (6), authentication unit (7) and Account Logon unit (8), the logging request unit (6)
For receiving the logging request of client, the request data package of log-on message is obtained, the authentication unit (7) includes identifying code hair
After sending unit and identifying code receiving unit, identifying code transmission unit to be used for login username, identifying code verifying is sent, identifying code connects
It receives unit and is used to receive the identifying code that user feedback is returned, carry out identifying code verifying, it is ensured that it is to log in person, the Account Logon
Unit (8) is for carrying out user's login by user name and identifying code after obtaining correct identifying code.
3. the advertisement recommender system according to claim 1 based on client's taste analysis, which is characterized in that the processing mould
Block (2) includes reading unit (9), initialization unit (10) and taxon (11), and the reading unit (9) is for reading user
The personal information of login module (1) and browsing record, the initialization unit (10) are used to extract the content of user, remove useless
Information and content, the taxon (11) is for classifying to user according to the effective information of extraction module, after being convenient for
Continuous information integration and information recommendation.
4. the advertisement recommender system according to claim 1 based on client's taste analysis, which is characterized in that the excavation mould
Block (3) includes that weight analysis unit (12), time attenuation analysis unit (13), temperature attenuation analysis unit (14), liveness decline
Subtract analytical unit (15) and modeling unit (16), the weight analysis unit (12) and reading unit (9) and taxon (11)
It is connected, behavior weight analysis is carried out to the information after arrangement, obtains behavior weight coefficient;The time attenuation analysis unit (13)
With propose reading unit (9) and taxon (11) is connected, time attenuation analysis is carried out to the information after arrangement, obtains time decaying
Coefficient;The temperature attenuation analysis unit (14) is connected with reading unit (9) and taxon (11), to the information after arrangement into
Row temperature attenuation analysis obtains temperature attenuation coefficient;The liveness attenuation analysis unit (15) and reading unit (9) and classification
Unit (11) is connected, and carries out liveness attenuation analysis to the information after arrangement, obtains liveness attenuation coefficient;The modeling unit
(16) decay with weight analysis unit (12), time attenuation analysis unit (13), temperature attenuation analysis unit (14) and liveness
Analytical unit (15) is respectively connected with, to behavior weight coefficient, time attenuation coefficient, temperature attenuation coefficient or liveness decaying system
Number is normalized, and establishes the interest model of the user, and then obtain the various potential consumption demands of the user.
5. the advertisement recommender system according to claim 1 based on client's taste analysis, which is characterized in that the advertisement pushes away
Recommending module (4) includes scoring unit (17), the first screening unit (18), filter element (19) and the second screening unit (20), institute
Commentary sub-unit (17) is convenient to recommend top quality advertisement, institute to user by scoring for scoring all advertisements
The first screening unit (18) are stated for obtaining target recommended advertisements range according to scoring screening Candidate Recommendation advertisement, the filtering is single
First (19) be used for by within the scope of targeted advertisements illegal contents and user dislike content and be filtered, second screening unit
(20) for obtaining target recommended advertisements according to screening in filtered Candidate Recommendation advertisement.
6. the advertisement recommender system according to claim 1 based on client's taste analysis, which is characterized in that the storage mould
Block (5) includes personal information storage element (21), browsing record storage element (22), thoughts information storage unit (23) and noninductive
Information storage unit (24), the personal information storage element (21) be used for by user improve after personal information carry out storage and
Integration, browsing record storage element (22) browse record for storing, and are convenient for the subsequent lookup browsing content of user, described to have
Sense information storage unit (23) is convenient for storing the interested information of user, to facilitate information to integrate, so that subsequent
The true hobby be more close to the users is recommended in advertisement, the information that the noninductive information storage unit (24) is used to dislike user into
Row storage, carries out information integration, facilitates subsequent advertisement that can filter out such content when recommending, so that subsequent advertisement is recommended
The true hobby being more close to the users.
7. a kind of method of the advertisement recommender system described in claim 1 based on client's taste analysis, which is characterized in that including
Following steps:
S1, user are logged in by user log-in block (1);
S2, processing module (2) remember the interior personal information storage element (21) of storage module (5), browsing after the completion of user logs in
Record storage element (22), thoughts information storage unit (23) and noninductive information storage unit (24) are integrated and are analyzed, and are convenient for
Extract the point of interest and dislike point of user;
S3, the interest model of user is analyzed come the various potential interest demands of searching by excavating module (3);
S4, the processing for passing through advertisement recommending module (4) after the completion of excavating, carry out the advertisement that recommended user is interested and likes;
Various information are stored and are integrated by S5, last storage module (5), and advertisement recommendation is more close to the users when recommending convenient for next time
True hobby.
8. the method for advertisement recommender system according to claim 7, which is characterized in that by excavating module (3) for user
Interest model analyze come, comprising:
Behavior weight analysis is carried out to the information after arrangement, obtains behavior weight coefficient;
Time attenuation analysis is carried out to the information after arrangement, obtains time attenuation coefficient;
Temperature attenuation analysis is carried out to the information after arrangement, obtains temperature attenuation coefficient;
Liveness attenuation analysis is carried out to the information after arrangement, obtains liveness attenuation coefficient;
To behavior weight coefficient, time attenuation coefficient, temperature attenuation coefficient or liveness attenuation coefficient are normalized,
Establish the interest model of the user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810819683.1A CN109003138A (en) | 2018-07-24 | 2018-07-24 | A kind of advertisement recommender system and method based on client's taste analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810819683.1A CN109003138A (en) | 2018-07-24 | 2018-07-24 | A kind of advertisement recommender system and method based on client's taste analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109003138A true CN109003138A (en) | 2018-12-14 |
Family
ID=64597135
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810819683.1A Pending CN109003138A (en) | 2018-07-24 | 2018-07-24 | A kind of advertisement recommender system and method based on client's taste analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109003138A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111861404A (en) * | 2020-07-23 | 2020-10-30 | 海南随手电子商务有限公司 | Data processing method and device based on intelligent machine and electronic equipment |
CN112270566A (en) * | 2020-10-30 | 2021-01-26 | 深圳市易阳新媒体科技有限公司 | Intelligent advertisement recommendation method, system and device |
CN113822696A (en) * | 2021-03-09 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information display method, device, system, electronic equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
CN104991917A (en) * | 2015-06-23 | 2015-10-21 | 上海斐讯数据通信技术有限公司 | Personalized advertisement pushing system and method |
US20170098249A1 (en) * | 2013-03-15 | 2017-04-06 | Google Inc. | Customized landing pages |
CN106651470A (en) * | 2017-01-12 | 2017-05-10 | 安徽大尺度网络传媒有限公司 | Directed advertisement promotion system based on user behavior prediction analysis |
CN106910081A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | A kind of information processing method and device |
CN108230026A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
-
2018
- 2018-07-24 CN CN201810819683.1A patent/CN109003138A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170098249A1 (en) * | 2013-03-15 | 2017-04-06 | Google Inc. | Customized landing pages |
CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
CN104991917A (en) * | 2015-06-23 | 2015-10-21 | 上海斐讯数据通信技术有限公司 | Personalized advertisement pushing system and method |
CN106910081A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | A kind of information processing method and device |
CN106651470A (en) * | 2017-01-12 | 2017-05-10 | 安徽大尺度网络传媒有限公司 | Directed advertisement promotion system based on user behavior prediction analysis |
CN108230026A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111861404A (en) * | 2020-07-23 | 2020-10-30 | 海南随手电子商务有限公司 | Data processing method and device based on intelligent machine and electronic equipment |
CN111861404B (en) * | 2020-07-23 | 2024-04-12 | 海南随手电子商务有限公司 | Data processing method and device based on intelligent machine and electronic equipment |
CN112270566A (en) * | 2020-10-30 | 2021-01-26 | 深圳市易阳新媒体科技有限公司 | Intelligent advertisement recommendation method, system and device |
CN113822696A (en) * | 2021-03-09 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information display method, device, system, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yao et al. | Automated crowdturfing attacks and defenses in online review systems | |
US9495586B1 (en) | Identity verification using biometric data | |
WO2017202006A1 (en) | Data processing method and device, and computer storage medium | |
US20170193533A1 (en) | Automatic detection of user personality traits based on social media image posts | |
US20140019264A1 (en) | Framework for product promotion and advertising using social networking services | |
CA3138730C (en) | Public-opinion analysis method and system for providing early warning of enterprise risks | |
Mohanty et al. | Photo sleuth: Combining human expertise and face recognition to identify historical portraits | |
CN102356405A (en) | Associating rendered advertisements with digital content | |
CN109003138A (en) | A kind of advertisement recommender system and method based on client's taste analysis | |
Kigerl | Profiling cybercriminals: Topic model clustering of carding forum member comment histories | |
Ayed | Architecting User-centric Privacy-as-a-set-of-services: Digital Identity-related Privacy Framework | |
CN112765565B (en) | Copyright protection method and system based on block chain | |
Akre et al. | Smart Digital Marketing of Financial Services to Millennial Generation using emerging technological tools and buyer persona | |
KR101945726B1 (en) | Contents-converging dynamic advertising system | |
Manek et al. | Detection of fraudulent and malicious websites by analysing user reviews for online shopping websites | |
Manoj et al. | Genuine ratings for mobile apps with the support of authenticated users’ reviews | |
CN115526659A (en) | Data analysis method, device, equipment and storage medium based on questionnaire | |
KR20160106510A (en) | Generating device for contents information of weather | |
Awasthi et al. | Review of techniques to prevent fake accounts on social media | |
US20240007502A1 (en) | Automated social media-related brand protection | |
US11616760B1 (en) | Model thresholds for digital content management and selection | |
Bindu et al. | Fake Profile Identification in Social Network Using Machine Learning and NLP | |
Ponce et al. | Data mining in Web applications | |
Stergiou | Social Engineering and Influence: A Study that Examines Kevin Mitnick’s Attacks through Robert Cialdini’s Influence Principles | |
CN115017994A (en) | Classification model training method and device |
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: 20181214 |