CN106055566B - Mobile phone games recommended method towards mobile advertising user - Google Patents
Mobile phone games recommended method towards mobile advertising user Download PDFInfo
- Publication number
- CN106055566B CN106055566B CN201610333697.3A CN201610333697A CN106055566B CN 106055566 B CN106055566 B CN 106055566B CN 201610333697 A CN201610333697 A CN 201610333697A CN 106055566 B CN106055566 B CN 106055566B
- Authority
- CN
- China
- Prior art keywords
- user
- game
- entity
- advertisement
- records
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000005295 random walk Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The mobile phone games recommended method towards mobile advertising user that the invention discloses a kind of, mobile phone user often click the advertisement of some mobile phone application push when applying using mobile phone.The ad click behavior of mobile phone user reflects the interest preference of mobile phone user to a certain extent.Entity extraction is carried out by introducing document to advertisement, is recorded according to the ad click of mobile phone user, constructs the advertisement entity set of mobile phone user's preference.For, with the user of game records, game entity set, game set and the advertisement entity set for further extracting user's preferences portray the interest preference of user jointly in mobile advertising user.For the mobile advertising user with game records, by carrying out cosine similarity calculating to user model, building neighbour user's set carries out personalized recommendation；For the mobile advertising user of not game records, the cosine similarity of these users with the advertising user with game records, building neighbour user's set, to carry out personalized recommendation are calculated.
Description
Technical field
The present invention relates to the technical fields that mobile phone games are recommended, and refer in particular to a kind of mobile phone trip towards mobile advertising user
Play recommended method.
Background technique
With the rapid development of Internet, the information faced in people's daily life is growing day by day.It is faced to solve people
Massive information is felt at a loss, and recommender system is come into being.Current proposed algorithm is divided into three kinds: the recommendation based on collaborative filtering
System, content-based recommendation system and mixed recommender system.Recommender system based on collaborative filtering mainly includes
The technologies such as User-Based, Item-Based and Model-Based.Amazon shopping website mainly uses Item-Based skill
Art is analyzed by the historical record to user, carries out personalized recommendation to user.Content-based recommendation system, mainly structure
The feature vector for building article, user, the similarity by calculating feature vector carry out personalized recommendation.Current some news websites
Mainly use content-based recommendation system.Mixed type recommender system is by the recommender system based on collaborative filtering and based on interior
The advantages of recommender system of appearance is combined, and draws the two, has wider array of adaptation range.
The unique attraction of growing day by day and mobile phone games of mobile phone user, so that being swum to mobile phone user's personalized recommendation
Play becomes trend of the times.However, mobile phone games recommend field have the characteristics that from conventional recommendation it is different: user's Game Cycle
Length, mobile phone user's game records are few.Therefore, compared with conventional recommendation, data have bigger sparsity for mobile phone games recommendation.And
In mobile Internet, moving advertising be it is generally existing, many users can usually click in installation and using mobile application when
To the advertisement of push, to become mobile advertising user.Potential mobile phone games user is excavated from mobile advertising user, for them
Recommend suitable mobile phone games, while pushing mobile phone games marketing, so that push more accurateization of moving advertising, favorably
In the win-win development for promoting mobile phone games industry and moving advertising industry.
Mobile phone user implies the interest preference of user in the behavior of different field, and has certain correlation.Phase
Than using the user data of single field of play to carry out mobile phone games recommendation, the behavioral data in conjunction with user in advertisement field, energy
The interest of user is preferably portrayed, to further promote accuracy and diversity that mobile phone games are recommended.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of mobile phone games towards mobile advertising user
Recommended method is more added by utilizing behavioral data of the mobile subscriber in advertisement field and the behavioral data in field of play
Site preparation portrays user interest preference, and then preferably models to user and game recommdation.This method has good extension
Property, and can apply in other recommendation fields.
To achieve the above object, technical solution provided by the present invention are as follows: the mobile phone games towards mobile advertising user push away
Recommend method, comprising the following steps:
1) it by being segmented to the content of introducing of advertisement and game, using the keyword extraction techniques based on figure, obtains
The significant noun in content, i.e. entity are introduced in advertisement and game；
2) for the mobile advertising user with game records, the advertising aggregator and game set of user are constructed, based on wide
It accuses and the entity in content is introduced in game, construct the entity sets of preferences of user；Moving advertising for not game records is used
Family constructs the advertising aggregator of user, introduces the entity in content based on advertisement, constructs the entity sets of preferences of user；
3) for the mobile advertising user with game records, the frequency of game, building movement are logged according to mobile subscriber
Set is had a preference in the game of advertising user；
4) for the mobile advertising user with game records, in conjunction with the entity preference of user and the game set of preferences of user
It closes, constructs the feature vector of user；For the mobile advertising user of not game records, the entity preference based on user, building
The feature vector of user；
5) for the mobile advertising user with game records, in conjunction with game entity, advertisement entity, game sets of preferences three
A part calculates the neighbour user of user；For the mobile advertising user of not game records, based on advertisement entity from trip
Neighbour user is found in the mobile advertising user of play record；
6) proposed algorithm based on User-Based provides the user with game recommdation list.
In step 1), data are introduced to game, are segmented using the common participle tool with part-of-speech tagging, this
Game is just introduced data and resolves into document-word form by sample；During participle, non-nominal vocabulary is filtered out；It is based on
The method of calculate node different degree calculates the importance of each entity node in graph theory；According to the adjoining of entity in entity sets
Relationship establishes figure, and the weight on side is all 1 in figure, and the rank value of each node is then calculated using the random walk restarted, public
Formula is as shown in 1-1；
Wherein, rank (ei) presentation-entity eiSignificance level in a document, α expression random walk restart parameter, In
(ei) refer to entity eiNeighborhood, | Out (ej) | refer to entity ejNeighbours' number；
Finally, extracting the entity that N before data rank value is introduced in each game according to the rank value of each entity；Similarly,
It is able to use same method and calculates the top n entity that data are introduced in each advertisement.
In step 3), for the mobile advertising user with game records, is concentrated in game data, find out each user
One week game login record of user is more than game twice, is put into the game sets of preferences of user by the game played；Game is inclined
The a part of good set as user characteristics embodies preference of the user in game selection.
In step 4), in the mobile advertising user for having game records, by the advertisement entity set of user, game
Entity sets and game records fusion, the preference profile of user is portrayed from multiple dimensions, and one reflection user of final building is whole
The feature vector of preference, dimension are the sum of user's game entity, advertisement entity and game records length, and form is as follows:
User characteristics={ { game entity 1, game entity 2 ... }, { advertisement entity 1, advertisement entity 2 ... }, { game
Record 1, game records 2 ... } }
For the mobile advertising user of not game records, using the advertisement entity set of user construct user characteristics to
Amount, dimension is the length of user advertising entity sets, and form is as follows:
User characteristics={ advertisement entity 1, advertisement entity 2 ... }.
In step 5), the neighbor lists of two kinds of different advertising users are calculated, for the moving advertising for there are game records
The similarity calculation of user, user are divided into three parts: the similarity of game entity, the similarity of advertisement entity, game records
Similarity, the similarity that each section obtains is with different weight w1,w2,w3Aggregative weighted is carried out, the most last phase of user is calculated
Like degree；Wherein, w1,w2,w3It needs to be adjusted according to experiment, is initialized as 1/3,1/3,1/3, i.e. three parts similarity calculation
As a result proportion is identical；Calculation formula is as shown in 5-1:
Similar(u1,u2)=w1*cosine(gameEntity1,gameEntity2)
+w2*cosine(adEntity1,adEntity2)
+w3*cosine(gameList1,gameList2) (5-1)
Wherein, gameEntity is game entity set, and adEntity is advertisement entity set, and gameList is user's trip
Play set of records ends；Wherein cosine is cosine similarity, and calculation formula is as shown in 5-2:
Finally, according to the height of cosine similarity, the Top-N neighbour user of user is found out；
For the mobile advertising user of not game records, by calculating the user and the moving advertising with game records
The cosine similarity of user, to construct neighbour's user list of the user, shown in the following 5-3 of calculation formula:
Similar(u1,u2)=cosine (adEntity1,adEntity2) (5-3)
Wherein, u1It is the mobile advertising user of not game records, u2It is the mobile advertising user for having game records, finally
u1Neighbour user be all the mobile advertising user for having game records.
In step 6), pushed away according to the game records in its neighbour user using following formula for each user
It recommends:
Wherein, Neigh (ui) it is uiTop-N neighbour user, gameList is user's game records；
Finally, from big to small according to the value of grade, the preceding Top-K game of user is found out as recommendation list.
Compared with prior art, the present invention have the following advantages that with the utility model has the advantages that
1, for the mobile advertising user of not game records, the present invention is using the certain customers and has game records
The similitude of mobile advertising user carries out mobile phone games recommendation, overcomes the cold start-up problem in conventional mobile phone game recommdation.
2, for the mobile advertising user with game records, the present invention is from the advertisement entity preference of user, game entity
Preference and game sets of preferences are set out, and user preference is more completely featured, and are overcoming conventional mobile phone game recommdation algorithm institute
The data sparsity problem faced simultaneously, improves the accuracy and diversity of recommendation.
Detailed description of the invention
Fig. 1 is the mobile phone games recommended method flow chart of invention.
Fig. 2 is that advertisement of the invention or game entity extract flow chart.
Fig. 3 is that document-entity bipartite graph is introduced in advertisement of the invention.
Specific embodiment
The present invention is further explained in the light of specific embodiments.
As shown in Figure 1, the mobile phone games recommended method described in the present embodiment towards mobile advertising user, including following step
It is rapid:
1) it by being segmented to the content of introducing of advertisement and game, using the keyword extraction techniques based on figure, obtains
The significant noun in content, i.e. entity are introduced in advertisement and game.
Entity refers to some significant nouns, can be in gaming some towards code name (such as three states, the Warring states), name
(Cao behaviour, Song Jiang), place name (Chibi) etc.；Advertisement field can be some field nouns (as finance, sport), role (damp father,
Peppery mother) etc..Data are introduced to game, using common participle tool such as HandLP, OpenCLAS etc. with part-of-speech tagging into
Row participle, thus introduces data for game and resolves into document-word form.During participle, filter out non-nominal
Vocabulary.At this time since the entity number of document is still more, therefore calculated based on the method for calculate node different degree in graph theory each
The importance of entity node.Figure is established according to the syntople of entity in entity sets, the weight on side is all 1 in figure, is then made
The rank value of each node is calculated with the random walk restarted, formula is as shown in 1-1.Finally, according to the rank of each entity
Value, extracts the entity that N before data rank value is introduced in each game.Each advertisement, which is calculated, using same method introduces data
Top n entity.The process of the step is as shown in Figure 2.
Wherein, rank (ei) presentation-entity eiSignificance level in a document, α expression random walk restart parameter, In
(ei) refer to entity eiNeighborhood, | Out (ej) | refer to entity ejNeighbours' number.
2) for the mobile advertising user with game records, the advertising aggregator and game set of user are constructed, based on wide
It accuses and the entity in content is introduced in game, construct the entity sets of preferences of user；Moving advertising for not game records is used
Family constructs the advertising aggregator of user, introduces the entity in content based on advertisement, constructs the entity sets of preferences of user.
User in moving advertising is divided into two kinds: one is the users with game records；Another kind is no game note
The user of record.For two different advertising users, the recommended method that we use is different.But in advertisement entity preference
Building on, using identical method.
If a user is interested in some advertisement entity, this advertisement entity of there is a strong possibility property appears in the use
Document is introduced in the multiple advertisements clicked at family.It is recorded according to the ad click of mobile phone user, constructs advertisement-sterogram, such as Fig. 3
It is shown.Wherein vertex includes advertisement vertex vaAnd entity vertex veAnd the two side E between class vertex, the weight calculation on side are adopted
With formula 2-1.
Side E (v between advertisement-entitya,ve) weight in two directions is different.Side right w from advertisement to entity
(va,ve) the rank value that is calculated by step 1 determines, it embodies entity and introduces importance in document in advertisement；From entity to advertisement
Side right w (ve,va) it is defined as the inverse i.e. 1/Out (v) of entity out-degree.Based on the figure, rank is found out using Random Walk Algorithm
It is worth highest k1 node, i.e. Top-k1 advertisement entity liking of user.
There is the mobile advertising user of game records for those, the game played to it is obtained using identical method
Top-k2 game entity of this kind of advertising user preference.
3) for the mobile advertising user with game records, the frequency of game, building movement are logged according to mobile subscriber
Set is had a preference in the game of advertising user.Specifically: for the mobile advertising user with game records, concentrated in game data,
The game that each user played is found out, is more than game twice by one week game login record of user, the game for being put into user is inclined
Good set.The a part of game sets of preferences as user characteristics embodies preference of the user in game selection.
4) for the mobile advertising user with game records, in conjunction with the entity preference of user and the game set of preferences of user
It closes, constructs the feature vector of user；For the mobile advertising user of not game records, the entity preference based on user, building
The feature vector of user.
For in the mobile advertising user for having game records, by the advertisement entity set of user, game entity set and
Game records fusion, the preference profile of user is portrayed from multiple dimensions, the feature of one reflection user's entirety preference of final building
Vector, dimension are the sum of user's game entity, advertisement entity and game records length.Form is as follows:
User characteristics={ { game entity 1, game entity 2 ... }, { advertisement entity 1, advertisement entity 2 ... }, { game
Record 1, game records 2 ... } }
For the mobile advertising user of not game records, using the advertisement entity set of user construct user characteristics to
Amount, dimension is the length of user advertising entity sets.Form is as follows:
User characteristics={ advertisement entity 1, advertisement entity 2 ... }.
5) for the mobile advertising user with game records, in conjunction with game entity, advertisement entity, game sets of preferences three
A part calculates the neighbour user of user；For the mobile advertising user of not game records, based on advertisement entity from trip
Neighbour user is found in the mobile advertising user of play record.
Calculate the neighbor lists of two kinds of different advertising users.For the mobile advertising user for having game records, user's
Similarity calculation is divided into three parts: similarity, the similarity of advertisement entity, the similarity of game records of game entity, each
The similarity that part obtains is with different weight w1,w2,w3Aggregative weighted is carried out, the final similarity of user is calculated.Wherein,
w1,w2,w3It needs to be adjusted according to experiment, is initialized as 1/3,1/3,1/3, i.e. three parts similarity calculation result institute accounting
Heavy phase is same.Calculation formula is as shown in 5-1:
Similar(u1,u2)=w1*cosine(gameEntity1,gameEntity2)
+w2*cosine(adEntity1,adEntity2)
+w3*cosine(gameList1,gameList2) (5-1)
Wherein, gameEntity is game entity set, and adEntity is advertisement entity set, and gameList is user's trip
Play set of records ends.Wherein cosine is cosine similarity, and calculation formula is as shown in 5-2:
Finally, according to the height of cosine similarity, the Top-N neighbour user of user is found out.
For the mobile advertising user of not game records, we are by calculating the user and the movement with game records
The cosine similarity of advertising user, to construct neighbour's user list of the user, shown in the following 5-3 of calculation formula:
Similar(u1,u2)=cosine (adEntity1,adEntity2) (5-3)
Wherein, u1It is the mobile advertising user of not game records, u2It is the mobile advertising user for having game records, finally
u1Neighbour user be all the mobile advertising user for having game records.
6) proposed algorithm based on User-Based provides the user with game recommdation list.
Recommended according to the game records in its neighbour user using following formula for each user:
Wherein, Neigh (ui) it is uiTop-N neighbour user, gameList is user's game records；
Finally, from big to small according to the value of grade, the preceding Top-K game of user is found out as recommendation list.
Embodiment described above is only the preferred embodiments of the invention, and but not intended to limit the scope of the present invention, therefore
All shapes according to the present invention change made by principle, should all be included within the scope of protection of the present invention.
Claims (6)
1. the mobile phone games recommended method towards mobile advertising user, which comprises the following steps:
1) by segmenting to the content of introducing of advertisement and game, using the keyword extraction techniques based on figure, advertisement is obtained
The significant noun in content, i.e. entity are introduced with game；
2) for the mobile advertising user with game records, the advertising aggregator and game set of user are constructed, based on advertisement and
The entity in content is introduced in game, constructs the entity sets of preferences of user；For the mobile advertising user of not game records, structure
The advertising aggregator for building user introduces the entity in content based on advertisement, constructs the entity sets of preferences of user；
3) for the mobile advertising user with game records, the frequency of game is logged according to mobile subscriber, constructs moving advertising
Set is had a preference in the game of user；
4) for the mobile advertising user with game records, in conjunction with the entity preference of user and the game sets of preferences of user,
Construct the feature vector of user；For the mobile advertising user of not game records, the entity preference based on user constructs user
Feature vector；
5) for the mobile advertising user with game records, in conjunction with three game entity, advertisement entity, game sets of preferences portions
Divide the neighbour user for calculating user；For the mobile advertising user of not game records, remembered based on advertisement entity from game
Neighbour user is found in the mobile advertising user of record；
6) proposed algorithm based on User-Based provides the user with game recommdation list.
2. the mobile phone games recommended method according to claim 1 towards mobile advertising user, it is characterised in that: in step
1) in, data are introduced to game, is segmented using the common participle tool with part-of-speech tagging, thus introduces game
Data resolve into document-word form；During participle, non-nominal vocabulary is filtered out；Based on calculate node in graph theory
The method of different degree calculates the importance of each entity node；Figure, figure are established according to the syntople of entity in entity sets
The weight on middle side is all 1, the rank value of each node is then calculated using the random walk restarted, formula is as shown in 1-1；
Wherein, rank (ei) presentation-entity eiSignificance level in a document, α expression random walk restart parameter, In (ei)
Refer to entity eiNeighborhood, | Out (ej) | refer to entity ejNeighbours' number；
Finally, extracting the entity that N before data rank value is introduced in each game according to the rank value of each entity；Similarly, can
The top n entity that data are introduced in each advertisement is calculated using same method.
3. the mobile phone games recommended method according to claim 1 towards mobile advertising user, it is characterised in that: in step
3) it in, for the mobile advertising user with game records, is concentrated in game data, finds out the game that each user played, it will
One week game login record of user is more than game twice, is put into the game sets of preferences of user；Game sets of preferences is as use
A part of family feature embodies preference of the user in game selection.
4. the mobile phone games recommended method according to claim 1 towards mobile advertising user, it is characterised in that: in step
4) in, in the mobile advertising user for having game records, by the advertisement entity set, game entity set and game of user
Record fusion, the preference profile of user is portrayed from multiple dimensions, the feature vector of one reflection user's entirety preference of final building,
Dimension is the sum of user's game entity, advertisement entity and game records length, and form is as follows:
User characteristics={ { game entity 1, game entity 2 ... }, { advertisement entity 1, advertisement entity 2 ... }, { game records
1, game records 2 ... } }
For the mobile advertising user of not game records, user characteristics vector, dimension are constructed using the advertisement entity set of user
Degree is the length of user advertising entity sets, and form is as follows:
User characteristics={ advertisement entity 1, advertisement entity 2 ... }.
5. the mobile phone games recommended method according to claim 1 towards mobile advertising user, it is characterised in that: in step
5) in, the neighbor lists of two kinds of different advertising users are calculated, for the mobile advertising user for there are game records, user's is similar
Degree, which calculates, is divided into three parts: similarity, the similarity of advertisement entity, the similarity of game records of game entity, each section
The similarity obtained is with different weight w1,w2,w3Aggregative weighted is carried out, the final similarity of user is calculated；Wherein, w1,w2,
w3It needs to be adjusted according to experiment, is initialized as 1/3,1/3,1/3, i.e. three parts similarity calculation result proportion phase
Together；Calculation formula is as shown in 5-1:
Similar(u1,u2)=w1*cosine(gameEntity1,gameEntity2)
+w2*cosine(adEntity1,adEntity2)
+w3*cosine(gameList1,gameList2) (5-1)
Wherein, gameEntity is game entity set, and adEntity is advertisement entity set, and gameList is user's game note
Record set；Wherein cosine is cosine similarity, and calculation formula is as shown in 5-2:
Finally, according to the height of cosine similarity, the Top-N neighbour user of user is found out；
For the mobile advertising user of not game records, by calculating the user and the mobile advertising user with game records
Cosine similarity, to construct neighbour's user list of the user, shown in the following 5-3 of calculation formula:
Similar(u1,u2)=cosine (adEntity1,adEntity2) (5-3)
Wherein, u1It is the mobile advertising user of not game records, u2It is the mobile advertising user for having game records, final u1's
Neighbour user is the mobile advertising user for having game records.
6. the mobile phone games recommended method according to claim 1 towards mobile advertising user, it is characterised in that: in step
6) in, recommended according to the game records in its neighbour user using following formula for each user:
Wherein, Neigh (ui) it is uiTop-N neighbour user, gameList is user's game records；
Finally, from big to small according to the value of grade, the preceding Top-K game of user is found out as recommendation list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610333697.3A CN106055566B (en) | 2016-05-19 | 2016-05-19 | Mobile phone games recommended method towards mobile advertising user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610333697.3A CN106055566B (en) | 2016-05-19 | 2016-05-19 | Mobile phone games recommended method towards mobile advertising user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106055566A CN106055566A (en) | 2016-10-26 |
| CN106055566B true CN106055566B (en) | 2019-06-18 |
Family
ID=57177101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610333697.3A Expired - Fee Related CN106055566B (en) | 2016-05-19 | 2016-05-19 | Mobile phone games recommended method towards mobile advertising user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106055566B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121737B (en) * | 2016-11-29 | 2022-04-26 | 阿里巴巴集团控股有限公司 | Method, device and system for generating business object attribute identifier |
| TWI678667B (en) * | 2017-03-30 | 2019-12-01 | 王建鈞 | System and method for placement marketing by playing game in a user terminal device |
| CN108596695B (en) * | 2018-05-15 | 2021-04-27 | 口口相传(北京)网络技术有限公司 | Entity pushing method and system |
| CN110335073A (en) * | 2019-06-27 | 2019-10-15 | 杭州联汇科技股份有限公司 | A kind of accurate method for pushing of Instant Ads excavated based on user behavior data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2014118337A (en) * | 2014-05-07 | 2015-11-20 | Общество С Ограниченной Ответственностью "Яндекс" | DEVICE, AND ALSO WAY OF SELECTING AND PLACING TARGET MESSAGES ON THE SEARCH RESULTS PAGE |
| CN105389396A (en) * | 2015-12-22 | 2016-03-09 | 北京奇虎科技有限公司 | Social game recommendation method and device |
| CN105468723A (en) * | 2015-11-20 | 2016-04-06 | 小米科技有限责任公司 | Information recommendation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9256688B2 (en) * | 2013-08-09 | 2016-02-09 | Google Inc. | Ranking content items using predicted performance |
-
2016
- 2016-05-19 CN CN201610333697.3A patent/CN106055566B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2014118337A (en) * | 2014-05-07 | 2015-11-20 | Общество С Ограниченной Ответственностью "Яндекс" | DEVICE, AND ALSO WAY OF SELECTING AND PLACING TARGET MESSAGES ON THE SEARCH RESULTS PAGE |
| CN105468723A (en) * | 2015-11-20 | 2016-04-06 | 小米科技有限责任公司 | Information recommendation method and device |
| CN105389396A (en) * | 2015-12-22 | 2016-03-09 | 北京奇虎科技有限公司 | Social game recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106055566A (en) | 2016-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106055566B (en) | Mobile phone games recommended method towards mobile advertising user | |
| CN102929928B (en) | Multidimensional-similarity-based personalized news recommendation method | |
| JP4959788B2 (en) | Advertisement / information exposure method for improving hit ratio of context advertisement / information mapping and context advertisement / information recommendation service system using the same | |
| CN104317835B (en) | The new user of video terminal recommends method | |
| Lewis et al. | Down-to-the-minute effects of super bowl advertising on online search behavior | |
| JP6039287B2 (en) | System and method for recommending a blog | |
| CN110020893B (en) | Method, device and equipment for determining contribution degree of advertisement | |
| CN105488233A (en) | Reading information recommendation method and system | |
| US20110218859A1 (en) | Method, Apparatus and System for Increasing Website Data Transfer Speed | |
| CN101271559A (en) | Cooperation recommending system based on user partial interest digging | |
| CN104038517A (en) | Information pushing method based on group relation and server | |
| CN101446959A (en) | Internet-based news recommendation method and system thereof | |
| CN103778260A (en) | Individualized microblog information recommending system and method | |
| CN101764661A (en) | Data fusion based video program recommendation system | |
| CN105023178B (en) | A kind of electronic commerce recommending method based on ontology | |
| CN104751354B (en) | A kind of advertisement crowd screening technique | |
| CN103839169A (en) | Personalized commodity recommendation method based on frequency matrix and text similarity | |
| CN103914743A (en) | On-line serial content popularity prediction method based on autoregressive model | |
| CN101763351A (en) | Data fusion based video program recommendation method | |
| US20170199930A1 (en) | Systems Methods Devices Circuits and Associated Computer Executable Code for Taste Profiling of Internet Users | |
| CN101375306A (en) | System and method for providing user-customized event | |
| CN103368898A (en) | Method and system for accomplishing information push | |
| CN103186595A (en) | Method and system for recommending audios/videos | |
| CN109978584A (en) | A kind of information flow advertisement sending method and device | |
| CN111104606A (en) | Weight-based conditional wandering chart recommendation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190618 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |