CN109993570A - A kind of orientation launches the method and system of moving advertising - Google Patents
A kind of orientation launches the method and system of moving advertising Download PDFInfo
- Publication number
- CN109993570A CN109993570A CN201910031108.XA CN201910031108A CN109993570A CN 109993570 A CN109993570 A CN 109993570A CN 201910031108 A CN201910031108 A CN 201910031108A CN 109993570 A CN109993570 A CN 109993570A
- Authority
- CN
- China
- Prior art keywords
- keyword
- user
- words
- word
- keyword feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
-
- 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
- G06Q30/0277—Online advertisement
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
A kind of orientation launches the method and system of moving advertising, and this method comprises the following steps: 1) dictionary of the production for keyword participle word cutting;2) user's keyword is extracted;3) user's keyword feature weight library is established;4) keyword feature model is generated;5) keyword set is obtained;6) target audience is extracted;7) moving advertising is launched.Concrete implementation of the present invention chooses the expansion scheme that keyword feature generates algorithm model Key of Implementation word based on advertising user solicited message, then by recommending set of words to obtain target audience crowd, guidance advertisement dispensing is contacting even closer audient crowd with ad content, is finally completed the positioning for moving advertising and launches.
Description
Technical field
The present invention relates to Internet technical fields, and in particular to a kind of orientation launches the method and system of moving advertising.
Background technique
With the high speed development of internet and the communication technology, mobile device has become people's trip and essential deposits
And there is moving advertising of all shapes and colors in duration in existing mobile device, however numerous moving advertisings and can not detain
The heart for ringing user, it is not only fixed since current moving advertising generallys use the dispensing that the form casted net all over the sky carries out advertisement
Position condition selection is limited, and the defect with flexibility deficiency and information delay, and then can not the effective audient of precise positioning
Group and accurately reflect user demand.
Summary of the invention
It is above-mentioned to solve the purpose of the present invention is to provide method and system and method that a kind of orientation launches moving advertising
The problem of being proposed in background technique.
In order to solve the above technical problem, the present invention provides following technical solutions:
A method of orientation launches moving advertising, comprising the following steps:
1) dictionary of the production for keyword participle word cutting;
Required to keyword participle word cutting dictionary include at least: TV play, film, variety show, animation and star name
Claim;
2) user's keyword is extracted;
According to acquired user data, and then user's word information is analyzed, passes through the word for keyword participle word cutting again later
Allusion quotation and stop words carry out participle word cutting, realize the extraction of user's keyword feature;
3) user's keyword feature weight library is established;
According to the frequency and timing that user's keyword feature occurs, user's keyword is carried out at decaying using attenuation function
Reason,
Then the foundation in user's keyword feature weight library is completed;
4) keyword feature model is generated;
It is loaded into keyword feature library, is converted into corpus set, is then melted into vector form, carries out the similarity meter in vector space
It calculates, to generate keyword feature model;
5) keyword set is obtained;
Obtain the relevant recommendation word of keyword feature by keyword feature model, next to above-mentioned recommendation word be combined into
And
It is formed and recommends set of words;Specifically include following sub-step:
A) clear required recommendation set of words quantity;
B) client's keyword is inputted, several groups of recommendation set of words with keyword feature correlation maximum are obtained;
C) quantity for recommending set of words and keyword quantity are compared, on the one hand, the number as recommended set of words in step b
Amount meets the requirement for recommending the quantity of set of words, then arranges to the recommendation set of words in step b;On the other hand, if
Recommend the quantity of set of words to be unsatisfactory for recommending the requirement of the quantity of set of words in step b, then client's keyword is divided again
Word word cutting carries out the calculating of keyword feature model using the phrase after participle word cutting again, to recommend word lacking in supplying
The quantity of set;If recommending the quantity of set of words needed for not being able to satisfy still, the hot word in user's keyword feature weight library is selected
Recommend the quantity of set of words needed for supplying;
6) target audience is extracted;
According to set of words is recommended, related objective audient is filtered out in user's keyword feature weight library;
7) moving advertising is launched;
Finally moving advertising is invested in above-mentioned target audience.
Further, the dictionary for keyword participle word cutting crawls required keyword by web crawlers device.
A kind of system that orientation launches moving advertising, it is characterised in that include at least consisting of part:
1) user's keyword feature weight library module can be converted into corpus, and generate keyword feature model by vector form;
2) keyword feature model module, for obtaining recommendation word associated with keyword feature;
3) keyword expansion recommends set of words module, is combined using recommendation word associated with keyword feature, and by group
Keyword expansion after conjunction recommends set of words to compare with user's keyword feature weight library, to realize the sieve of target audience
Choosing;
4) it extracts audient and carries out putting module, for moving advertising orientation to be finally delivered to target audience.
Further, user's keyword feature weight library module is made of following submodule:
User request information module: analyzing the word information of user, and then filters out the keyword in above-mentioned word information;
User's keyword cleans conversion module: the dictinary information for keyword participle word cutting and deactivated word information are obtained, and
With
The keyword filtered out compares, and believes to obtain keyword relevant to the keyword participle dictionary of word cutting is used for
Breath;
User's keyword attenuation processing module: for the keyword after conversion module cleaning converts will to be cleaned by user's keyword
Information carries out attenuation function attenuation processing;
Module is established in user's keyword feature weight library: carrying out arrangement combination for the key word information after attenuation processing, finally
Realize the foundation in user's keyword feature weight library.
It is further preferred that the dictionary for keyword participle word cutting includes at least the information of Chinese or the information of English.
The beneficial effects obtained by the present invention are as follows being:
With the development of science and technology, the continuous maturation of the relevant technologies, a large amount of advertising user solicited message can be collected, this hair
Bright original intention is that the keyword by above-mentioned derives out the target audience crowd of keyword, and then fast and flexible catches use
The point of interest at family and user demand accurately is reflected, to efficiently carry out positioning dispensing advertisement, therefore is solving movement
While advertisement is blindly bombed greatly, more targetedly implement the dispensing of displacement advertisement.User's keyword feature weight
The foundation in library further improves the positioning to moving advertising target audience.
Specifically, the present invention is for advertiser, launches advertisement and find intention group, be no longer look for a needle in a haystack as be stranded
Difficulty, but precisely touching reaches target audience group, then realizes that sophistication is launched, improves advertising conversion effect and promote advertisement and launch
The purpose of ROI.
For media dispensing for, more good ad data can be recycled, further optimize launch algorithm and
While reducing dispensing cost, more advertisers is attracted or have carried out more advertisement dispensings.
For a user, the problem of advertisement is spread unchecked not only is alleviated to a certain extent, and selected moving advertising is cut
User demand is closed, and then is easy to user and receives ad content, promote the experience of user and improves cognition of the user for brand.
To sum up, concrete implementation of the present invention chooses keyword feature based on advertising user solicited message and generates algorithm model
The expansion scheme of Key of Implementation word, then by recommend set of words obtain target audience crowd, guidance advertisement launch with advertisement
The even closer audient crowd of content association is finally completed the positioning for moving advertising and launches.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, the implementation with invention
Example is used to explain the present invention together, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of the method for orientation dispensing moving advertising in the present invention;
Fig. 2 is the flow chart for establishing keyword set in the present invention;
Fig. 3 is a kind of flow chart of the system of orientation dispensing moving advertising in the present invention;
Fig. 4 is the flow chart of user's keyword feature weight library module in the present invention;
Fig. 5 is the flow chart of embodiment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Specific embodiment is as shown in Figs. 1-5:
Step 1, dictionary of the production for keyword participle word cutting;Such as user's duration in network site of cinema and TV is crawled by crawler software
Star's title of browsing, such as Zhang Yishan and Zhang Guorong.
It should be noted that also title includes the video display performer intimate with this star, example to the star collected in dictionary
Such as the entitled Zhang Yishan of the star collected in dictionary, then same as the poplar purple that Zhang Yishan is intimate included by this dictionary.
Step 2, the information carried according to advertising user request, carry out character processing, cleaning is obtained by filtration containing Chinese or
Word information containing English.
Word information containing Chinese in this step includes at least the word information of Chinese addend word and the word letter of Chinese plus English
Breath similarly knows that the word information containing English includes at least the word information of the word information and English plus Chinese of English addend word.
Step 3, using stammerer participle technique, Custom Dictionaries obtained in stop words and step 1 are loaded, carry out segmenting word
The keyword frequency is converted after operation, by Exception Filter frequency keyword, to form user's keyword feature.
Step 4, in conjunction with user in user's keyword feature weight library for the search history of keyword, utilization index decaying
Function merges newest user's keyword feature as time decay factor, and then generates newest user's keyword feature weight
Library.
Step 5, newest user's keyword feature weight library is loaded, newest user's keyword feature is constituted instruct later
Practice corpus set.
Step 6, corpus set is inputted, and converts term vector form for corpus set, then spatially by term vector
Similarity calculation, next construct keyword feature model.
Step 7, client's vocabulary relevant to advertisement is collected, input Word similarity will be then obtained with keyword feature model
Maximum preceding several recommendation set of words.
Step 8, according to the quantity for recommending set of words is obtained in step 7, it is carried out with required recommendation set of words quantity
Comparison, if the quantity of the recommendation set of words in step 7 is unsatisfactory for the quantity of required recommendation set of words, again to client's
Keyword carries out participle word cutting processing.
Step 9, using in step 8 segment word cutting processing after and again progress the calculating of keyword feature model vocabulary to step
Need in rapid 8 recommend the recommendation set of words of set of words quantity to be supplied needed for meeting.
Step 10, if the recommendation set of words quantity in step 9 is still unsatisfactory for recommending set of words quantity needed for step 8,
It then selects and the hot word in word feature weight library is recommended to be supplied.
Step 11, according to recommendation set of words information obtained, priority is carried out with user keyword feature weight library
With the user for being then withdrawn as target audience crowd.
Step 12, finally positioning moving advertising is carried out according to the target audience crowd provided in step 11 to launch.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, right appended by the scope of the present invention
It is required that rather than above description limit, it is intended that by fall in the equivalent requirements of the claims containing by all in justice and range
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (5)
1. a kind of method that orientation launches moving advertising, it is characterised in that: the following steps are included:
1) dictionary of the production for keyword participle word cutting;
Required to keyword participle word cutting dictionary include at least: TV play, film, variety show, animation and star name
Claim;
2) user's keyword is extracted;
According to acquired user data, and then user's word information is analyzed, passes through the word for keyword participle word cutting again later
Allusion quotation and stop words carry out participle word cutting, realize the extraction of user's keyword feature;
3) user's keyword feature weight library is established;
According to the frequency and timing that user's keyword feature occurs, user's keyword is carried out at decaying using attenuation function
Reason then completes the foundation in user's keyword feature weight library;
4) keyword feature model is generated;
It is loaded into keyword feature library, is converted into corpus set, is then melted into vector form, carries out the similarity meter in vector space
It calculates, to generate keyword feature model;
5) keyword set is obtained;
Obtain the relevant recommendation word of keyword feature by keyword feature model, next to above-mentioned recommendation word be combined into
And it is formed and recommends set of words;Specifically include following sub-step:
A) the clear required quantity for recommending set of words;
B) client's keyword is inputted, several groups of recommendation set of words with keyword feature correlation maximum are obtained;
C) quantity for recommending set of words and keyword quantity are compared, on the one hand, the number as recommended set of words in step b
Amount meets the requirement for recommending the quantity of set of words, then arranges to the recommendation set of words in step b;On the other hand, if step b
The middle quantity for recommending set of words is unsatisfactory for recommending the requirement of the quantity of set of words, then carries out participle to client's keyword again and cut
Word carries out the calculating of keyword feature model using the phrase after participle word cutting again, to recommend set of words lacking in supplying
Quantity;If recommending the quantity of set of words needed for not being able to satisfy still, the hot word in user's keyword feature weight library is selected to supply
The required quantity for recommending set of words;
6) target audience is extracted;
According to set of words is recommended, related objective audient is filtered out in user's keyword feature weight library;
7) moving advertising is launched;
Finally moving advertising is invested in above-mentioned target audience.
2. the method that a kind of orientation according to claim 1 launches moving advertising, it is characterised in that: described to be used for keyword
The dictionary of participle word cutting crawls required keyword by web crawlers device.
3. a kind of system that orientation launches moving advertising, it is characterised in that: include at least:
1) user's keyword feature weight library module can be converted into corpus, and generate keyword feature model by vector form;
2) keyword feature model module, for obtaining recommendation word associated with keyword feature;
3) keyword expansion recommends set of words module, is combined using recommendation word associated with keyword feature, and by group
Keyword expansion after conjunction recommends set of words to compare with user's keyword feature weight library, to realize the sieve of target audience
Choosing;
4) it extracts audient and carries out putting module, for moving advertising orientation to be finally delivered to target audience.
4. the system that a kind of orientation according to claim 3 launches moving advertising, it is characterised in that: user's keyword
Feature weight library module is made of following submodule:
User request information module: analyzing the word information of user, and then filters out the keyword in above-mentioned word information;
User's keyword cleans conversion module: the dictinary information for keyword participle word cutting and deactivated word information are obtained, and
It is compared with the keyword filtered out, to obtain key word information relevant to the keyword participle dictionary of word cutting is used for;
User's keyword attenuation processing module: for the keyword after conversion module cleaning converts will to be cleaned by user's keyword
Information carries out attenuation function attenuation processing;
Module is established in user's keyword feature weight library: carrying out arrangement combination for the key word information after attenuation processing, finally
Realize the foundation in user's keyword feature weight library.
5. the method that a kind of orientation according to claim 1 launches moving advertising, it is characterised in that: segmented for keyword
The dictionary of word cutting includes at least the information of Chinese or the information comprising English.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910031108.XA CN109993570B (en) | 2019-01-14 | 2019-01-14 | Method and system for directionally delivering mobile advertisement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910031108.XA CN109993570B (en) | 2019-01-14 | 2019-01-14 | Method and system for directionally delivering mobile advertisement |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109993570A true CN109993570A (en) | 2019-07-09 |
CN109993570B CN109993570B (en) | 2023-09-01 |
Family
ID=67129983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910031108.XA Active CN109993570B (en) | 2019-01-14 | 2019-01-14 | Method and system for directionally delivering mobile advertisement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109993570B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110717788A (en) * | 2019-10-12 | 2020-01-21 | 北京搜狐新媒体信息技术有限公司 | Target user screening method and device |
CN111882370A (en) * | 2020-09-27 | 2020-11-03 | 武汉卓尔数字传媒科技有限公司 | Advertisement recommendation method and device and electronic equipment |
CN113763005A (en) * | 2020-09-23 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Picture advertisement pushing method, electronic equipment and computer readable storage medium |
CN116777525A (en) * | 2023-06-21 | 2023-09-19 | 深圳市创致联创科技有限公司 | Popularization and delivery system based on group optimization algorithm |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通(北京)广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
CN106354818A (en) * | 2016-08-30 | 2017-01-25 | 电子科技大学 | Dynamic user attribute extraction method based on social media |
CN106682925A (en) * | 2015-11-06 | 2017-05-17 | 北京奇虎科技有限公司 | Method and device for recommending advertisement content |
US20180129749A1 (en) * | 2015-09-08 | 2018-05-10 | Tencent Technology (Shenzhen) Company Limited | Method, apparatus, and system for recommending real-time information |
-
2019
- 2019-01-14 CN CN201910031108.XA patent/CN109993570B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通(北京)广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
US20180129749A1 (en) * | 2015-09-08 | 2018-05-10 | Tencent Technology (Shenzhen) Company Limited | Method, apparatus, and system for recommending real-time information |
CN106682925A (en) * | 2015-11-06 | 2017-05-17 | 北京奇虎科技有限公司 | Method and device for recommending advertisement content |
CN106354818A (en) * | 2016-08-30 | 2017-01-25 | 电子科技大学 | Dynamic user attribute extraction method based on social media |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110717788A (en) * | 2019-10-12 | 2020-01-21 | 北京搜狐新媒体信息技术有限公司 | Target user screening method and device |
CN113763005A (en) * | 2020-09-23 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Picture advertisement pushing method, electronic equipment and computer readable storage medium |
CN111882370A (en) * | 2020-09-27 | 2020-11-03 | 武汉卓尔数字传媒科技有限公司 | Advertisement recommendation method and device and electronic equipment |
CN116777525A (en) * | 2023-06-21 | 2023-09-19 | 深圳市创致联创科技有限公司 | Popularization and delivery system based on group optimization algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN109993570B (en) | 2023-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109993570A (en) | A kind of orientation launches the method and system of moving advertising | |
CN105227975B (en) | Advertisement placement method and device | |
US9591089B2 (en) | Content preview generation using social network analysis | |
US20190392487A1 (en) | System, Device, and Method of Automatic Construction of Digital Advertisements | |
US8793256B2 (en) | Method and apparatus for selecting related content for display in conjunction with a media | |
US9283476B2 (en) | Information collection during game play | |
CN109460512B (en) | Recommendation information processing method, device, equipment and storage medium | |
CN104992347B (en) | A kind of method and device of video matching advertisement | |
Delre et al. | The effects of shared consumption on product life cycles and advertising effectiveness: The case of the motion picture market | |
CN109155136A (en) | The computerized system and method for highlight are detected and rendered automatically from video | |
CN109815368A (en) | Resource recommendation method, device, equipment and computer readable storage medium | |
CN110390048A (en) | Information-pushing method, device, equipment and storage medium based on big data analysis | |
CN108230050A (en) | Advertisement placement method and system | |
CN106355446B (en) | A kind of advertisement recommender system of network and mobile phone games | |
CN109360020A (en) | A kind of generation method and device of advertisement | |
CN104657879A (en) | User engagement-based contextually-dependent automated pricing for non-guaranteed delivery | |
KR20100114860A (en) | Touchpoint customization system | |
US20100318427A1 (en) | Enhancing database management by search, personal search, advertising, and databases analysis efficiently using core-set implementations | |
CN107392666A (en) | Advertisement data processing method, device and advertisement placement method and device | |
CN106095841A (en) | Method is recommended in a kind of mobile Internet advertisement based on collaborative filtering | |
CN107808309A (en) | A kind of advertisement based on different social networks is integrated, issues system, method and system | |
CN110598095B (en) | Method, device and storage medium for identifying article containing specified information | |
CN110020200A (en) | A kind of personalized recommendation method and system based on history material | |
Shafiee et al. | The effect of implementing SEO techniques and websites design methods on e-tourism development: A study of travel agencies e-tourism websites | |
CN108334518A (en) | A kind of advertisement loading 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |