CN103136435A - System, method and game platform capable of recommending games in personalization mode - Google Patents
System, method and game platform capable of recommending games in personalization mode Download PDFInfo
- Publication number
- CN103136435A CN103136435A CN2011103896027A CN201110389602A CN103136435A CN 103136435 A CN103136435 A CN 103136435A CN 2011103896027 A CN2011103896027 A CN 2011103896027A CN 201110389602 A CN201110389602 A CN 201110389602A CN 103136435 A CN103136435 A CN 103136435A
- Authority
- CN
- China
- Prior art keywords
- game
- user
- ranking list
- favorable rating
- playing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 230000003542 behavioural effect Effects 0.000 claims abstract description 13
- 230000002349 favourable effect Effects 0.000 claims description 64
- 238000001514 detection method Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 230000006399 behavior Effects 0.000 description 19
- 230000006870 function Effects 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Abstract
The invention discloses a system, a method and a game platform capable of recommending games in a personalization mode. The recommending system recommends the games according to a user identifier, and comprises a behavioral analysis module, a relative detecting module and a recommending module, wherein the behavioral analysis module is used for collecting historical data in which a user is interested and historical data about different games with which the user plays, obtaining basic preferring value of the user to different games according to the collected data, and obtaining a game preferring degree ranking list of the user to different games. The relative detecting module is used for calculating relevancy degrees of different games in the game preferring degree ranking list according to a relevancy algorithm, and ranking the relevancy degrees to obtain a possibly preferable degree ranking list of the games. The recommending module is used for recommending the possibly preferable degree ranking list of the games to the user. The recommending system analyzes the collected historical data in which the user is interested and the historical data of different games, explores the favor degree of the user to the games, and therefore the recommending system can specifically recommend the games to the users with different personalities.
Description
Technical field
The present invention relates to Internet technical field, relate in particular to a kind of system, method and a kind of gaming platform of personalized recommendation game.
Background technology
Along with the development of Internet technology, online game becomes the network service that more and more Internet users pay close attention to.Existing gaming platform is all generally to enumerate according to display modes such as game (as cards game, the game of sports class etc.) classification the game that the game services business provides, there is following shortcoming in this unified mode of recommending: the content of recommendation is stereotyped, can not actual touch and the game hobby of predictive user; The proposed algorithm that adopts does not have the machine learning ability, and the user can't feed back recommendation results, and recommendation results can not be evolved, and recommends precision not high.Therefore, be necessary to provide a kind of system or method that individualized game is provided recommends, satisfies user's individual demand for the user.
Summary of the invention
The main technical problem to be solved in the present invention is, a kind of system of personalized recommendation game is provided, and the behavior and the interest that show in the history that can play games according to the user recommend it may interested game to the user adaptively.
According to an aspect of the present invention, a kind of individualized game commending system is provided, recommend according to user identifier, comprise: the behavioural analysis module, be used for to collect user's that should user identifier historical interesting data and each game history data of playing that this user played, according to this user's historical interesting data and the game history data of each game that this user played, obtain this user to basis value of liking of each game, obtain this user to the game favorable rating ranking list of each game; The correlation detection module is used for according to degree of correlation algorithm, the relatedness computation line ordering of going forward side by side being carried out in each game of described game favorable rating ranking list, and obtaining playing may the favorable rating ranking list; Recommending module is used for playing and may recommends this user by the favorable rating ranking list.
According to another aspect of the present invention, provide a kind of gaming platform, this gaming platform uses individualized game commending system as above.
According to a further aspect of the invention, a kind of individualized game recommend method is provided, recommend according to user identifier, comprise: the behavioural analysis step, collection is to user's that should user identifier historical interesting data and game history data of each game that this user played, according to this user's historical interesting data and the game history data of each game that this user played, obtain this user to basis value of liking of each game, obtain this user to the game favorable rating ranking list of each game; The correlation detection step is carried out the relatedness computation line ordering of going forward side by side according to degree of correlation algorithm to each game in described game favorable rating ranking list, and obtaining playing may the favorable rating ranking list; Recommendation step will be played and may be recommended this user by the favorable rating ranking list.
The invention has the beneficial effects as follows: commending system is collected user's historical interesting data, and to these data analysis, explores the user to the hobby of game, thereby can the user of different individual characteies be recommended targetedly.In a kind of embodiment, user's historical interesting data is not only collected by system, also collect user's good friend's historical interesting data, and to these data analysis, explore user and good friend thereof to the hobby of game, thereby the user is recommended except the game of individual subscriber hobby, also recommend game that user's good friend likes to the user, for the user widens the game scope.In another embodiment, the user can carry out alternately with system, and whether the feedback content recommendation is suitable own, not only helps commending system to learn, and improves the recommendation precision, makes recommendation results constantly to evolve.
Description of drawings
Fig. 1 is the structural representation of a kind of embodiment of individualized game commending system of the present invention;
Fig. 2 is the schematic flow sheet of individualized game recommend method embodiment one of the present invention;
Fig. 3 is the schematic flow sheet of individualized game recommend method embodiment two of the present invention;
Fig. 4 is the schematic flow sheet of individualized game recommend method embodiment three of the present invention.
Embodiment
By reference to the accompanying drawings the present invention is described in further detail below by embodiment.
The design philosophy of the embodiment of the present invention is: recommend according to user identifier, at first collect user's historical interesting data and the game history data of game, the interesting data of collecting is analyzed, marked off the game that the user likes and the game of not liking; The game of liking for the user and the game of not liking utilize degree of correlation algorithm to infer the user game that may like and the game that may not like; Get rid of the game that the user may not like from the game that the user may like, the game that the user who obtains after getting rid of may be liked as the game recommdation of recommending to the user.Based on this, the embodiment of the present invention gives another kind of design philosophy, namely, collect user's good friend's historical interesting data, obtain the game that the good friend likes, filter out the game that game that the user may like and user may not like from the game that the good friend likes, the game that the good friend after getting rid of likes as the game recommdation of recommending to the user, the game of recommending this moment is the game that the hobby according to user's good friend obtains, and purpose is the game circle of amplifying the user.The user identifier of embodiment of the present invention indication comprises ID or the hardware ID of user's logging in game platform, and hardware ID comprises MAC Address or the network ip address of gaming platform place machine.
As shown in Figure 1, for the individualized game commending system that an embodiment of the present invention provides, recommend according to user identifier, comprise behavioural analysis module 100, correlation detection module 300 and recommending module 500, the functional description of each module is as follows:
behavioural analysis module 100 is used for collecting all users' historical interesting data and the game history data of all game, by user identifier, all users' historical interesting data is classified and obtain each user's historical interesting data, by game identifier, the game history data of all game is classified and obtain the game history data of each game, for the user corresponding with the user identifier of appointment, according to this user's historical interesting data and the game history data of each game that this user played, obtain this user to basis value of liking of each game, obtain this user to the game favorable rating ranking list of each game.The historical interesting data of some users includes but not limited to that the user is to the game number of times of the scoring of each game, the game duration of playing each game, each game of object for appreciation; The game history data of some game comprises that the user is to the scoring of this game, the duration that this game is playing, the number of times that this game is playing.Behavioural analysis module 100 comprises dimension calculating sub module 110 and basis sequence submodule 130.Wherein, dimension calculating sub module 110 is used for each dimension of the game corresponding with the game identifier of appointment is calculated the behavior value of this each dimension of playing, and then the behavior value of cumulative each dimension obtains the user to basis value of liking of this game.Dimension calculating sub module 110 comprises: be used for counting game the duration dimension the behavior value duration unit 111, be used for counting game object for appreciation time dimension the behavior value object for appreciation sub-cell 112, be used for the scoring unit 113 of behavior value of the dimensions of counting game.The behavior value of duration dimension equals the user and plays total duration of this game and the ratio of duration threshold value, and wherein, all users that the duration threshold value equals this game play total duration of this game and the ratio of all users' that play this game number; The behavior value of playing time dimension equals the total object for appreciation time and the ratio of playing subthreshold that the user plays this game, wherein, plays all users that subthreshold equals this game and plays total object for appreciation time of this game and the ratio of all users' of this game of object for appreciation number; The behavior value of dimensions equals the user to the scoring of this game and the ratio of scoring threshold value, and the scoring threshold value equals all users of this game to the overall score of this game and the ratio of all users' that play this game number.Sequence submodule 130 in basis sorts for the basis value of liking with all game and obtains the user to the game favorable rating ranking list of each game, and this list comprises user's " list of games of liking " or comprises user's " list of games of liking " and " list of games of not liking ".
Correlation detection module 300 is used for according to degree of correlation algorithm, the relatedness computation line ordering of going forward side by side being carried out in each game of described game favorable rating ranking list, and obtaining playing may the favorable rating ranking list.Correlation detection module 300 comprises relatedness computation submodule 310 and the value of liking sequence submodule 330.Relatedness computation submodule 310 is used for each game to game favorable rating ranking list, calculates other in this game and list degree of correlation between playing according to degree of correlation algorithm; The value of liking sequence submodule 330 is used for all game of described game favorable rating ranking list are sorted by the value of liking size, the sum of products of the value of the liking degree of correlation that equals to play basis like value corresponding with this game wherein, the i.e. value of liking=sum (the basis value of liking * correlation), then the game favorable rating ranking list after sorting is as game possibility favorable rating ranking list, and this list comprises user's " list of games that may like " and " list of games that may not like ".
Recommending module 500 is used for playing and may recommends the user by the favorable rating ranking list.If may there be " list of games that may like " and " list of games that may not like " in the game that obtains in the favorable rating ranking list simultaneously, exclude the game in " list of games that may not like " in " list of games that may like ", final " list of games that may like " that obtain after then getting rid of recommends the client.In a kind of example, recommending module 500 comprises that first recommends submodule, and this first recommends submodule to be used for frequent time period of game according to the user who records, and recommend the user with the form that the plays window possibility favorable rating ranking list of play within this time period.In another kind of example, recommending module 500 comprises that second recommends submodule, the game recommdation function key that this second interface of recommending submodule to be used for response commending system place gaming platform arranges, if the user triggers this game recommdation function key, will play and to recommend the user by the favorable rating ranking list.In another example, recommending module 500 comprises that simultaneously first recommends submodule and second to recommend submodule.
In another kind of embodiment, still as shown in Figure 1, for the user of logging in game platform, the individualized game commending system also comprises: good friend's analysis module 200 and comprehensive recommending module 500 '.Good friend's analysis module 200 is for the good friend's who collects the user historical interesting data and the game history data of all game that good friends played, according to the data acquisition user's who collects good friends basis value of liking to each game, the good friends that obtain the user are to the good friend of each game favorable rating ranking list of playing, and this list is namely " list of games that good friends like "; Comprehensive recommending module 500 ' be used for the game in " list of games that good friends like " eliminating user oneself " list of games that may like " and " list of games that may not like ", list of games and user oneself " list of games that may like " that the good friends that obtain after getting rid of are liked recommend the user.Similarly, in this embodiment, comprehensive recommending module 500 ' can comprise as the aforementioned and first recommend submodule and/or second to recommend submodule.
In another embodiment, still as shown in Figure 1, the individualized game commending system also comprises feedback module 700, be used for according to the user, the feedback of the game recommended being judged, if the user does not like the game feedback of recommending, no longer recommend this game next time during recommended games, namely may remove this game in the favorable rating ranking list in game.
Based on above-mentioned personalized recommendation system embodiment, the present invention also provides a kind of gaming platform, and adopting this commending system on this gaming platform is user's recommended games.Gaming platform can adopt various ways to user's recommended games, for example, recording user is the time period of game often, within this time period with the form that plays window to user's recommended games, and for example, the game recommdation function key is set in the interface of gaming platform, and the user carries out game recommdation after clicking this function key.
Based on above-mentioned personalized recommendation system embodiment, the present invention also provides corresponding personalized recommendation method.Below by several embodiment, this personalized recommendation method is explained.
Embodiment one:
If by the ID login platform of user's logging in game platform, namely the present embodiment is for there being gaming platform to use historical user for the user, as shown in Figure 2, recommend method comprises the steps:
Step S201 collects user's historical interesting data, obtains the user to the favorable rating ranking list of game according to historical interesting data analysis, and this list comprises " list of games of liking ";
what collect in commending system is all users' historical interesting data and the game history data of all game, then by user identifier, all users' historical interesting data is classified and obtain each user's historical interesting data, by game identifier, the game history data of all game is classified and obtain the game history data of each game, for the user corresponding with the user identifier of appointment, the user corresponding with the ID of user's logging in game platform in the present embodiment namely, analyze according to this user's historical interesting data and the game history data of all game that this user played, obtain this user to the favorable rating ranking list of game.
User's historical interesting data includes but not limited to the scoring to each game, the duration of playing games, number of times etc.And the game history data of game comprises that all users are to the scoring of this game, the duration that this game is playing, the number of times that this game is playing.According to the data analysis of collecting, time length, game often as high in the user is marked, that play are classified as the game that user oneself likes.
In this step, at first each dimension of the game corresponding with the game identifier of appointment is calculated the behavior value of each dimension, then the behavior value of cumulative each dimension is to obtain the user to basis value of liking of this game, basis value of liking of all game is sorted, thereby obtain the user to the ranking list of game favorable rating, i.e. " list of games of liking ".
Here said dimension, comprise the duration dimension, play time dimension, dimensions etc., and each dimension concrete meaning is as follows:
(1) duration dimension, relevant to the data of the duration of playing games, refer to user play games total duration of P and the ratio of duration threshold value, namely formula is: duration dimension=user total duration of P/duration threshold value of playing games.Wherein, the duration threshold value, claim again average duration, all users of the P that refers to play play games total duration of P and the ratio of all users' of the P that plays games number, formula is: play games all users' the number of total duration of the P/P that plays games of all users of duration threshold value=game P.
(2) play time dimension, relevant to the number of times of playing games, refer to user the play games total object for appreciation time and the ratio of playing subthreshold of P, namely formula is: the inferior dimension=user of object for appreciation total duration of the P/duration threshold value of playing games.Wherein, play subthreshold, claim again average play time, all users of the P that refers to play play games total object for appreciation time of P and the ratio of all users' of the P that plays games number, formula is: all users that play subthreshold=game P play games total object for appreciation of P inferior/all users' of the P that plays games number.
(3) dimensions, relevant to the scoring of game to the user, refer to the user to the scoring of game P and the ratio of scoring threshold value, namely formula is: dimensions=user is to the scoring of the P that plays/scoring threshold value.Wherein, the scoring threshold value claims again average score, refers to all users to the summation of the scoring of game P and all users' of the P that plays games the ratio of number, and formula is: the number of scoring threshold value=all users to all users of the scoring summation of the game P/P that plays games.
For example: known certain user U has played game A totally 8 times, and accumulative total duration 80 minutes has been played game B totally 6 times, accumulative total duration 50 minutes, and game B was commented 7 minutes; Yet the average object for appreciation time (namely playing subthreshold) of game A is 10 times, and average duration (being the duration threshold value) is 100 minutes, and the average object for appreciation of game B is inferior is 10 times, and average duration is 100 minutes, and average score is 5 minutes.So, each dimension of game A is calculated the behavior value of each dimension, in this example, duration dimension=80/100=0.8, play time dimension=8/10=0.8, dimensions=0/10=0, the behavior value of therefore cumulative each dimension can obtain user U to basis value of liking of game A, that is, user U is for basis value of liking=0.8+0.8+0=1.6 of game A; In like manner obtain user U and be 50/100+6/10+7/5=2.5 for basis value of liking of game B.
Should be understood that dimension herein is not limited to above three kinds, in other embodiment, more dimension can also be arranged, as scoring number of times dimension, its implication and computing formula and aforementioned three kinds similar.
Step S203 carries out relatedness computation for " list of games of liking " and processes, and obtains " list of games that may like ".Particularly, for each game in " list of games of liking ", utilize degree of correlation algorithm calculate in this game and " list of games of liking " other the game between the degree of correlation, all game in will " list of games of liking " are sorted by the size of the value of liking, " list of games that may like "; Here, the value of liking is the degree of correlation of game and the sum of products of corresponding basis value of liking.
The present embodiment adopts the degree of correlation of Pearson algorithm counting game, can also adopt other degree of correlation algorithms in other embodiment, as expert algorithm etc.The computing formula of Pearson algorithm is:
For example: basis value of liking of known games A is 1.5, basis value of liking of game B is 1.7, dependent game and the correlation thereof of A of obtaining after adopting degree of correlation algorithm to calculate playing is: the correlation of AA (game A and game A) is that the correlation of 1, AB (game A and game B) is 0.9; Dependent game and the correlation thereof of game B are: the correlation of BB (game B and game B) is that the correlation of 1, BA (game B and game A) is 0.8.So, the value of liking of game A and game B and dependent game separately thereof is respectively: the value of liking of AA=1.5*1=1.5, the value of liking of AB=1.5*0.9+1.7*0.8=2.71, the value of liking of BB=1.7*1=1.7, sorting by the value of liking size is AB, BB, AA; This game ordered list is namely user's " list of games that may like ".
Step S205 recommends the user with " list of games that may like ".
The recommend method of the present embodiment is based on the data that the game behavioural habits of analysis user self obtain and recommends, the hobby feature that namely according to individual subscriber, game sheet is revealed is to user's recommended games, the game style of recommending is comparatively concentrated, and degree of accuracy is high, the user's that often relatively fits regard.
Embodiment two:
If by the ID login platform of user's logging in game platform, namely the present embodiment is for there being gaming platform to use historical user for the user, as shown in Figure 3, recommend method comprises the steps:
Step S301 collects user's historical interesting data, analyzes according to historical interesting data, obtains the user to the favorable rating ranking list of game, and this list comprises " list of games of liking " and " list of games of not liking ";
For " list of games of liking ", the process that obtains " list of games of liking " in the step S201 of its procurement process and embodiment one is identical;
For " list of games of not liking ", its procurement process is similar to the process that obtains " list of games of liking " in the step S201 of embodiment one.Here, the game of the low game of scoring not being liked as the user.Similarly, the behavior value that each dimension calculates each dimension is also carried out in the game that the user does not like, then the behavior value that adds up each dimension obtains the user to basis value of liking of this game, with basis values of liking of all game by sorting from big to small, thereby obtain the user and game is not liked the ranking list of degree, i.e. " list of games of not liking ".
Step S303 carries out respectively relatedness computation for " list of games of liking " and " list of games of not liking " and processes, and obtains " list of games that may like " and " list of games that may not like ";
The relatedness computation processing procedure of " list of games of liking " is identical with the process of the step S203 of embodiment one, namely for each game in this list, utilize degree of correlation algorithm calculate in this game and " list of games of liking " other the game between the degree of correlation, all game in will " list of games of liking " are sorted by the size of the value of liking, " list of games that may like ";
For " list of games of not liking ", its relatedness computation processing procedure is similar to the process of the step S203 of embodiment one, namely for each game in this list, utilize degree of correlation algorithm calculate in this game and " list of games of not liking " other the game between the degree of correlation, all game in will " list of games of not liking " are sorted by the size of the value of liking, " list of games that may not like "; Here, the value of liking is the degree of correlation of game and the sum of products of corresponding basis value of liking.Usually, the value of liking in " list of games that may not like " is negative or smaller positive number, and the value in " list of games that may like " is larger positive number.
Step S305 filters " list of games that may like ", namely removes the game in " list of games that may not like " in " list of games that may like ", and " list of games that may like " after then filtering recommends the user.
The recommend method of the present embodiment is to remove the game that may not like on the basis of the game that may like, keep on improving to user's recommended games, it is more concentrated that the game style of recommendation is compared embodiment one, degree of accuracy is higher, the user's that also more fits regard.Embodiment one and embodiment two are all that hobby of playing games passing according to the user is its recommended games, along with the continuous renewal of playing in platform, adopt the proposed algorithm of embodiment one and embodiment two, can make the user have more multimachine can play his/her game that are fit to more, and no longer passive being confined in minority game also improved the stability that the user uses gaming platform simultaneously by this.
Embodiment three:
If by the ID login platform of user's logging in game platform, namely the present embodiment is for there being gaming platform to use historical user for the user, as shown in Figure 4, recommend method comprises the steps:
Step S401, collect user and good friends' thereof historical interesting data, obtain user oneself to the favorable rating ranking list of game according to user's oneself historical interesting data analysis, this list comprises " list of games of liking " and " list of games of not liking "; Analyze according to good friends' historical interesting data, obtain good friends to the favorable rating ranking list of game, this list comprises " list of games that good friends like ".Here said good friends, be that the user is the good friend on gaming platform or the people who pays close attention on gaming platform.
For " list of games of liking " and " list of games of not liking ", its procurement process is identical with the step S301 of embodiment two;
for " list of games that good friends like ", its procurement process is similar to the process that obtains " list of games of liking " in the step S201 of embodiment one, the behavior value that each dimension calculates each dimension is carried out in the game of namely each good friend being liked, then the behavior value that adds up each dimension obtains the good friend to basis value of liking of this game, with basis values of liking of all game by sorting from big to small, thereby obtain each good friend to the ranking list of game favorable rating, all good friends are combined and namely obtain " list of games that good friends like " the ranking list of game favorable rating.
Step S403 carries out respectively relatedness computation for " list of games of liking " and " list of games of not liking " and processes, and obtains " list of games that may like " and " list of games that may not like "; The processing procedure of this step is identical with the step S303 of embodiment two, no longer repeats at this.
Step S405, the game that the game that recommendation user oneself may like and good friend like; Particularly, the game that may like for user oneself, its obtain manner is: filter " list of games that may like ", namely remove the game in " list of games that may not like " in " list of games that may like ", " list of games that may like " after then filtering recommends the user; And the game of liking for the good friend, its obtain manner is: filtering in " list of games that the good friend likes " " list of games that may like " and " list of games that may not like ", " list of games that the good friend likes " after filtering recommended the user.
The recommend method of the present embodiment is not only recommended based on user's self game behavioural habits, also attempt game that commending friends likes to the user based on each good friend's of user game hobby, purpose be except keep on improving to the user recommends comparatively to fit the game of user's regard, also be the game scope that extends one's service, excavate the hobby feature that individual subscriber had not shown, recommend and its game that style is different in the past.
Embodiment four: for the user of logging in game platform not
If the user is the logging in game platform not, the present embodiment will carry out game recommdation according to hardware ID, and concrete recommend method is with embodiment one or embodiment two, and just the user's of this moment historical interesting data is the corresponding user's of this hardware ID historical interesting data.
Can find out from above-described embodiment, in various embodiments of the present invention, commending system is collected the data that the user carries out a series of game behavior, and to these data analysis, therefrom find out user play custom and the preference of behavior, thereby can the user of different individual characteies be recommended targetedly, proposed algorithm has explores the function that the user plays and likes, and has the ability of machine learning.In addition, the user can also carry out alternately with commending system, be that user after recommended game feeds back recommendation results again, the content that feedback is recommended whether suitable oneself, as the user, the game of recommending is directly shown and like or do not like, help commending system to learn, so toward covering, successively refinement, the game that makes commending system will filtering user direct according to user's feedback when the next update recommended games not like, thereby make the sustainable study of commending system, improve and recommend precision, also make recommendation results constantly to evolve.
In addition, recommendation step can adopt various ways to user's recommended games, for example, the time period that in commending system, recording user is often played, within this time period with the form that plays window to user's recommended games, and for example, the game recommdation function key is set in the interface of gaming platform, the user carries out game recommdation after clicking this function key.
Above-described embodiment is of the present invention giving an example, although disclose for the purpose of illustration most preferred embodiment of the present invention and accompanying drawing, but it will be appreciated by those skilled in the art that: without departing from the spirit and scope of the invention and the appended claims, various replacements, variation and modification are all possible.Therefore, the present invention should not be limited to most preferred embodiment and the disclosed content of accompanying drawing.
Claims (17)
1. an individualized game commending system, is characterized in that, recommends according to user identifier, comprising:
The behavioural analysis module, be used for to collect user's that should user identifier historical interesting data and each game history data of playing that this user played, according to this user's historical interesting data and the game history data of each game that this user played, obtain this user to basis value of liking of each game, obtain this user to the game favorable rating ranking list of each game;
The correlation detection module is used for according to degree of correlation algorithm, the relatedness computation line ordering of going forward side by side being carried out in each game of described game favorable rating ranking list, and obtaining playing may the favorable rating ranking list;
Recommending module is used for playing and may recommends this user by the favorable rating ranking list.
2. individualized game commending system as claimed in claim 1, is characterized in that, described behavioural analysis module comprises:
The dimension calculating sub module, be used for each dimension of the game corresponding with the game identifier of appointment is calculated, obtain the behavior value of this each dimension of playing, described dimension comprises the duration dimension, plays time dimension, dimensions, and the behavior value of cumulative each dimension obtains the user to basis value of liking of this game;
Sequence submodule in basis sorts for the basis value of liking with all game that the user played and obtains the user to the game favorable rating ranking list of each game.
3. individualized game commending system as claimed in claim 2, is characterized in that, described dimension calculating sub module comprises:
The duration unit, the behavior value that is used for the duration dimension of counting game, the behavior value of described duration dimension equals the user and plays total duration of this game and the ratio of duration threshold value, and all users that described duration threshold value equals this game play total duration of this game and the ratio of all users' that play this game number;
Play sub-cell, the behavior value that is used for the object for appreciation time dimension of counting game, the behavior value of described object for appreciation time dimension equals the total object for appreciation time and the ratio of playing subthreshold that the user plays this game, and all users that described object for appreciation subthreshold equals this game play total object for appreciation time of this game and the ratio of all users' of this game of object for appreciation number;
The scoring unit, the behavior value that is used for the dimensions of counting game, the behavior value of described dimensions equals the user to the scoring of this game and the ratio of scoring threshold value, and described scoring threshold value equals all users of this game to the overall score of this game and the ratio of all users' that play this game number.
4. individualized game commending system as described in claim 1-3 any one, is characterized in that, described correlation detection module comprises:
The relatedness computation submodule is used for each game to described game favorable rating ranking list, calculates other in this game and list degree of correlation between playing according to degree of correlation algorithm;
The value of liking sequence submodule, be used for all game of described game favorable rating ranking list are sorted by the value of liking size, the sum of products of basis value of liking that the degree of correlation that the described value of liking equals to play is corresponding with this game, the game favorable rating ranking list after sequence may the favorable rating ranking list for game.
5. individualized game commending system as claimed in claim 4, is characterized in that, for the user of logging in game platform, also comprises:
Good friend's analysis module, for the good friends' that collect the user historical interesting data and the game history data of all game that good friends played, according to the data acquisition user's who collects good friends basis value of liking to each game, the good friends that obtain the user are to the good friend of each game favorable rating ranking list of playing;
Comprehensive recommending module, be used for getting rid of the game of described game in may the favorable rating ranking list at the described good friend favorable rating ranking list of playing, with described game may the favorable rating ranking list and/or get rid of after good friend's favorable rating ranking list of playing recommend the user.
6. individualized game commending system as claimed in claim 5, it is characterized in that, also comprise: feedback module, be used for according to the user, the feedback of the game recommended being judged, if the user does not like the game recommended feedback, this game of removal in described game may favorable rating ranking list during recommended games next time.
7. individualized game commending system as claimed in claim 6, is characterized in that, described recommending module comprises that first recommends submodule and/or second to recommend submodule; Described first recommends submodule to be used for the time period of often playing according to the user who records, and will play and may recommend the user by the favorable rating ranking list with the form that plays window within this time period; The game recommdation function key that the described second interface of recommending submodule to be used for responding described commending system place gaming platform arranges if the user triggers this game recommdation function key, be recommended the user with the possible favorable rating ranking list of described game.
8. individualized game commending system as claimed in claim 7, is characterized in that, described user identifier comprises the ID of user's logging in game platform or the hardware ID of gaming platform place machine, and described hardware ID comprises MAC Address or network ip address; User's historical interesting data comprises the game number of times of the scoring to each game, the game duration of playing each game, each game of object for appreciation; The game history data of game comprises that all users are to the scoring of this game, the duration that this game is playing, the number of times that this game is playing.
9. a gaming platform, is characterized in that, uses individualized game commending system as described in any one in claim 1-8.
10. an individualized game recommend method, is characterized in that, recommends according to user identifier, comprising:
The behavioural analysis step, collection is to user's that should user identifier historical interesting data and game history data of each game that this user played, according to this user's historical interesting data and the game history data of each game that this user played, obtain this user to basis value of liking of each game, obtain this user to the game favorable rating ranking list of each game;
The correlation detection step is carried out the relatedness computation line ordering of going forward side by side according to degree of correlation algorithm to each game in described game favorable rating ranking list, and obtaining playing may the favorable rating ranking list;
Recommendation step will be played and may be recommended this user by the favorable rating ranking list.
11. individualized game recommend method as claimed in claim 10 is characterized in that, described behavioural analysis step comprises:
Each dimension of the game corresponding with the game identifier of appointment is calculated the behavior value of this each dimension of playing, described dimension comprises the duration dimension, plays time dimension, dimensions, and the behavior value of cumulative each dimension obtains the user to basis value of liking of this game;
Basis values of liking of all game that the user played is sorted obtain the user to the game favorable rating ranking list of each game.
12. individualized game recommend method as claimed in claim 11 is characterized in that, the behavior value of this each dimension of playing comprises the behavior value of duration dimension, the behavior value of playing time dimension, the behavior value of dimensions, wherein:
The behavior value of the duration dimension of this game equals the user and plays total duration of this game and the ratio of duration threshold value, and all users that described duration threshold value equals this game play total duration of this game and the ratio of all users' that play this game number;
The behavior value of the object for appreciation of this game time dimension equals the total object for appreciation time and the ratio of playing subthreshold that the user plays this game, and all users that described object for appreciation subthreshold equals this game play total object for appreciation time of this game and the ratio of all users' of this game of object for appreciation number;
The behavior value of the dimensions of this game equals the user to the scoring of this game and the ratio of scoring threshold value, and described scoring threshold value equals all users of this game to the overall score of this game and the ratio of all users' that play this game number.
13. individualized game recommend method as described in claim 10-12 any one is characterized in that, described correlation detection step comprises:
For each game in described game favorable rating ranking list, calculate other in this game and list degree of correlation between playing according to degree of correlation algorithm;
All game in described game favorable rating ranking list are sorted by the value of liking size, the sum of products of basis value of liking that the degree of correlation that the described value of liking equals to play is corresponding with this game, the game favorable rating ranking list after sequence may the favorable rating ranking list for game.
14. individualized game recommend method as claimed in claim 13 is characterized in that, for the user of logging in game platform, also comprises:
Good friend's analytical procedure, collection user's good friends' historical interesting data and the game history data of all game that good friends played, according to the data acquisition user's who collects good friends basis value of liking to each game, the good friends that obtain the user are to the good friend of each game favorable rating ranking list of playing;
Comprehensive recommendation step, get rid of the game of described game in may the favorable rating ranking list in described good friend plays the favorable rating ranking list, with described game may the favorable rating ranking list and/or get rid of after good friend's favorable rating ranking list of playing recommend the user.
15. individualized game recommend method as claimed in claim 14, it is characterized in that, also comprise: feedback step, according to the user, the feedback of the game recommended is judged, if the user does not like the game recommended feedback, this game of removal in described game may favorable rating ranking list during recommended games next time.
16. individualized game recommend method as claimed in claim 15, it is characterized in that, described recommendation step comprises: according to the time period that the user who records often plays, will play and may recommend the user by the favorable rating ranking list with the form that plays window within this time period; And/or respond the game recommdation function key that arranges in the interface of described commending system place gaming platform, if the user triggers this game recommdation function key, described game may be recommended the user by the favorable rating ranking list.
17. individualized game recommend method as claimed in claim 16 is characterized in that, described user identifier comprises the ID of user's logging in game platform or the hardware ID of gaming platform place machine, and described hardware ID comprises MAC Address or network ip address; User's historical interesting data comprises the game number of times of the scoring to each game, the game duration of playing each game, each game of object for appreciation; The game history data of game comprises that all users are to the scoring of this game, the duration that this game is playing, the number of times that this game is playing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110389602.7A CN103136435B (en) | 2011-11-30 | 2011-11-30 | System, method and gaming platform that a kind of individualized game is recommended |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110389602.7A CN103136435B (en) | 2011-11-30 | 2011-11-30 | System, method and gaming platform that a kind of individualized game is recommended |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103136435A true CN103136435A (en) | 2013-06-05 |
| CN103136435B CN103136435B (en) | 2016-06-29 |
Family
ID=48496255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110389602.7A Expired - Fee Related CN103136435B (en) | 2011-11-30 | 2011-11-30 | System, method and gaming platform that a kind of individualized game is recommended |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103136435B (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
| WO2015051750A1 (en) * | 2013-10-10 | 2015-04-16 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Determining ranking threshold for applications |
| CN104572962A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | APP (Application) recommendation method and system |
| CN104636470A (en) * | 2015-02-11 | 2015-05-20 | 广州华多网络科技有限公司 | Method and device for recommending business information |
| CN105045916A (en) * | 2015-08-20 | 2015-11-11 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Mobile game recommendation system and recommendation method thereof |
| CN105095305A (en) * | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Method and device for generating personalized page |
| CN105279206A (en) * | 2014-07-25 | 2016-01-27 | 北京龙源创新信息技术有限公司 | Intelligent recommendation method and system |
| CN105477860A (en) * | 2015-12-22 | 2016-04-13 | 北京奇虎科技有限公司 | Game activity recommending method and device |
| CN105536251A (en) * | 2015-12-15 | 2016-05-04 | 云南大学 | Automatic game task generation method based on user quality of experience fluctuation model |
| CN105617657A (en) * | 2015-12-22 | 2016-06-01 | 北京奇虎科技有限公司 | Intelligent game recommendation method and device |
| WO2016082164A1 (en) * | 2014-11-27 | 2016-06-02 | 刘一佳 | Method for recommending games and device for recommending games |
| CN105808642A (en) * | 2016-02-24 | 2016-07-27 | 北京百度网讯科技有限公司 | Recommendation method and device |
| CN106909584A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | A kind of game information method for pushing and device based on mobile terminal |
| CN106919988A (en) * | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | Game reserving method and device |
| CN107705190A (en) * | 2017-10-25 | 2018-02-16 | 深圳市国电科技通信有限公司 | A kind of vehicle leasing information recommendation method |
| CN107866071A (en) * | 2017-11-03 | 2018-04-03 | 杭州电魂网络科技股份有限公司 | Game role recommends method and apparatus |
| CN107908765A (en) * | 2017-11-27 | 2018-04-13 | 维沃移动通信有限公司 | A kind of game resource processing method, mobile terminal and server |
| CN108304853A (en) * | 2017-10-10 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Acquisition methods, device, storage medium and the electronic device for the degree of correlation of playing |
| CN108721896A (en) * | 2018-05-16 | 2018-11-02 | 北京奇虎科技有限公司 | Jump method, device, computing device and the computer storage media of games page |
| CN108763251A (en) * | 2018-04-02 | 2018-11-06 | 阿里巴巴集团控股有限公司 | The personalized recommendation method and device and electronic equipment of core body product |
| CN108744523A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
| CN108764950A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
| CN108744524A (en) * | 2018-04-10 | 2018-11-06 | 浙江工业大学 | A kind of recommendation method suitable for cognitive training platform |
| CN109450862A (en) * | 2018-10-17 | 2019-03-08 | Oppo广东移动通信有限公司 | Release news recommended method, device, storage medium and terminal |
| CN109908590A (en) * | 2019-02-27 | 2019-06-21 | 广州华多网络科技有限公司 | A kind of game recommdation method, apparatus, equipment and medium |
| CN110721475A (en) * | 2019-09-09 | 2020-01-24 | 福建省天奕网络科技有限公司 | Game role recommendation method and terminal |
| US10606845B2 (en) | 2013-10-10 | 2020-03-31 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Detecting leading session of application |
| CN111191136A (en) * | 2019-12-30 | 2020-05-22 | 华为技术有限公司 | Information recommendation method and related equipment |
| CN112237742A (en) * | 2019-07-16 | 2021-01-19 | 腾讯科技（深圳）有限公司 | Game recommendation method and device, readable storage medium and computer equipment |
| CN112295236A (en) * | 2020-10-09 | 2021-02-02 | 西安万像电子科技有限公司 | Game pushing method, device and system |
| CN112642151A (en) * | 2020-12-18 | 2021-04-13 | 咪咕互动娱乐有限公司 | Game strategy determining method and device, electronic equipment and storage medium |
| CN113413610A (en) * | 2021-06-21 | 2021-09-21 | 网易（杭州）网络有限公司 | Game item recommendation method, equipment and computer-readable storage medium |
| CN113491878A (en) * | 2021-07-16 | 2021-10-12 | 广州七七游网络科技有限公司 | Game information pushing method, device, equipment and readable storage medium |
| CN116077942A (en) * | 2023-04-06 | 2023-05-09 | 深圳尚米网络技术有限公司 | Method for realizing interactive content recommendation |
| CN116173513A (en) * | 2023-04-24 | 2023-05-30 | 深圳市乐易网络股份有限公司 | Intelligent game pushing system and method |
| CN117271904A (en) * | 2023-11-21 | 2023-12-22 | 厦门牛游果网络科技有限公司 | Game recommendation method and system based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080250026A1 (en) * | 2001-10-24 | 2008-10-09 | Linden Gregory D | Recommendations based on cross-site browsing activities of users |
| CN102054112A (en) * | 2009-10-29 | 2011-05-11 | 腾讯科技（深圳）有限公司 | System and method for recommending game and directory server |
-
2011
- 2011-11-30 CN CN201110389602.7A patent/CN103136435B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080250026A1 (en) * | 2001-10-24 | 2008-10-09 | Linden Gregory D | Recommendations based on cross-site browsing activities of users |
| CN102054112A (en) * | 2009-10-29 | 2011-05-11 | 腾讯科技（深圳）有限公司 | System and method for recommending game and directory server |
Non-Patent Citations (2)
| Title |
|---|
| 姚伶伶等: "交互电视中基于本体的个性化节目协同推荐", 《电视技术》 * |
| 梁洁: "基于混合模式的个性化推荐系统的研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN103544663B (en) * | 2013-06-28 | 2017-06-09 | Tcl集团股份有限公司 | The recommendation method of network open class, system and mobile terminal |
| WO2015051750A1 (en) * | 2013-10-10 | 2015-04-16 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Determining ranking threshold for applications |
| US10606845B2 (en) | 2013-10-10 | 2020-03-31 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Detecting leading session of application |
| CN103838884B (en) * | 2014-03-31 | 2017-03-01 | 联想(北京)有限公司 | Messaging device and information processing method |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
| CN105095305B (en) * | 2014-05-20 | 2019-03-08 | 深圳市腾讯计算机系统有限公司 | A kind of generation method and device of personal page |
| CN105095305A (en) * | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Method and device for generating personalized page |
| CN105279206A (en) * | 2014-07-25 | 2016-01-27 | 北京龙源创新信息技术有限公司 | Intelligent recommendation method and system |
| WO2016082164A1 (en) * | 2014-11-27 | 2016-06-02 | 刘一佳 | Method for recommending games and device for recommending games |
| CN104572962A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | APP (Application) recommendation method and system |
| CN104636470A (en) * | 2015-02-11 | 2015-05-20 | 广州华多网络科技有限公司 | Method and device for recommending business information |
| CN104636470B (en) * | 2015-02-11 | 2018-04-24 | 广州华多网络科技有限公司 | A kind of method and device of recommendation business information |
| CN105045916A (en) * | 2015-08-20 | 2015-11-11 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Mobile game recommendation system and recommendation method thereof |
| CN105536251A (en) * | 2015-12-15 | 2016-05-04 | 云南大学 | Automatic game task generation method based on user quality of experience fluctuation model |
| CN105617657A (en) * | 2015-12-22 | 2016-06-01 | 北京奇虎科技有限公司 | Intelligent game recommendation method and device |
| CN105477860A (en) * | 2015-12-22 | 2016-04-13 | 北京奇虎科技有限公司 | Game activity recommending method and device |
| CN105617657B (en) * | 2015-12-22 | 2019-06-18 | 北京奇虎科技有限公司 | Game intelligence recommended method and device |
| CN106909584B (en) * | 2015-12-23 | 2021-09-07 | 北京奇虎科技有限公司 | Game information pushing method and device based on mobile terminal |
| CN106909584A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | A kind of game information method for pushing and device based on mobile terminal |
| CN106919988A (en) * | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | Game reserving method and device |
| CN105808642A (en) * | 2016-02-24 | 2016-07-27 | 北京百度网讯科技有限公司 | Recommendation method and device |
| CN105808642B (en) * | 2016-02-24 | 2019-12-24 | 北京百度网讯科技有限公司 | Recommendation method and device |
| CN108304853A (en) * | 2017-10-10 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Acquisition methods, device, storage medium and the electronic device for the degree of correlation of playing |
| CN107705190A (en) * | 2017-10-25 | 2018-02-16 | 深圳市国电科技通信有限公司 | A kind of vehicle leasing information recommendation method |
| CN107866071A (en) * | 2017-11-03 | 2018-04-03 | 杭州电魂网络科技股份有限公司 | Game role recommends method and apparatus |
| CN107908765B (en) * | 2017-11-27 | 2024-01-16 | 维沃移动通信有限公司 | Game resource processing method, mobile terminal and server |
| CN107908765A (en) * | 2017-11-27 | 2018-04-13 | 维沃移动通信有限公司 | A kind of game resource processing method, mobile terminal and server |
| CN108764950A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
| CN108744523A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
| CN108763251A (en) * | 2018-04-02 | 2018-11-06 | 阿里巴巴集团控股有限公司 | The personalized recommendation method and device and electronic equipment of core body product |
| CN108763251B (en) * | 2018-04-02 | 2021-06-01 | 创新先进技术有限公司 | Personalized recommendation method and device for nuclear product and electronic equipment |
| CN108744524A (en) * | 2018-04-10 | 2018-11-06 | 浙江工业大学 | A kind of recommendation method suitable for cognitive training platform |
| CN108744524B (en) * | 2018-04-10 | 2021-10-15 | 浙江工业大学 | Recommendation method suitable for cognitive training platform |
| CN108721896B (en) * | 2018-05-16 | 2022-04-01 | 北京奇虎科技有限公司 | Game page jumping method and device, computing equipment and computer storage medium |
| CN108721896A (en) * | 2018-05-16 | 2018-11-02 | 北京奇虎科技有限公司 | Jump method, device, computing device and the computer storage media of games page |
| CN109450862A (en) * | 2018-10-17 | 2019-03-08 | Oppo广东移动通信有限公司 | Release news recommended method, device, storage medium and terminal |
| CN109450862B (en) * | 2018-10-17 | 2021-08-20 | Oppo广东移动通信有限公司 | Published information recommendation method and device, storage medium and terminal |
| CN109908590A (en) * | 2019-02-27 | 2019-06-21 | 广州华多网络科技有限公司 | A kind of game recommdation method, apparatus, equipment and medium |
| CN112237742A (en) * | 2019-07-16 | 2021-01-19 | 腾讯科技（深圳）有限公司 | Game recommendation method and device, readable storage medium and computer equipment |
| CN110721475B (en) * | 2019-09-09 | 2022-09-06 | 福建省天奕网络科技有限公司 | Game role recommendation method and terminal |
| CN110721475A (en) * | 2019-09-09 | 2020-01-24 | 福建省天奕网络科技有限公司 | Game role recommendation method and terminal |
| CN111191136A (en) * | 2019-12-30 | 2020-05-22 | 华为技术有限公司 | Information recommendation method and related equipment |
| WO2021136131A1 (en) * | 2019-12-30 | 2021-07-08 | 华为技术有限公司 | Information recommendation method and related device |
| CN112295236A (en) * | 2020-10-09 | 2021-02-02 | 西安万像电子科技有限公司 | Game pushing method, device and system |
| CN112642151A (en) * | 2020-12-18 | 2021-04-13 | 咪咕互动娱乐有限公司 | Game strategy determining method and device, electronic equipment and storage medium |
| CN113413610A (en) * | 2021-06-21 | 2021-09-21 | 网易（杭州）网络有限公司 | Game item recommendation method, equipment and computer-readable storage medium |
| CN113491878A (en) * | 2021-07-16 | 2021-10-12 | 广州七七游网络科技有限公司 | Game information pushing method, device, equipment and readable storage medium |
| CN116077942A (en) * | 2023-04-06 | 2023-05-09 | 深圳尚米网络技术有限公司 | Method for realizing interactive content recommendation |
| CN116173513A (en) * | 2023-04-24 | 2023-05-30 | 深圳市乐易网络股份有限公司 | Intelligent game pushing system and method |
| CN117271904A (en) * | 2023-11-21 | 2023-12-22 | 厦门牛游果网络科技有限公司 | Game recommendation method and system based on big data |
| CN117271904B (en) * | 2023-11-21 | 2024-02-09 | 厦门牛游果网络科技有限公司 | Game recommendation method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103136435B (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103136435B (en) | System, method and gaming platform that a kind of individualized game is recommended | |
| Bauckhage | Insights into internet memes | |
| US10475136B2 (en) | Social content connection system and method | |
| CN103353920B (en) | Method and device for recommending games based on SNS | |
| Pei-Lee et al. | Do the big five personality factors affect knowledge sharing behaviour? a study of malaysian univeristies | |
| CN103020845B (en) | A kind of method for pushing and system of mobile application | |
| Zhang et al. | Product information diffusion in a social network | |
| CN106980692A (en) | A kind of influence power computational methods based on microblogging particular event | |
| US8725773B2 (en) | System and method for generating a knowledge metric using qualitative internet data | |
| CN106997358A (en) | Information recommendation method and device | |
| CN107818166A (en) | A kind of information recommends method, apparatus, server and system | |
| CN108259638B (en) | Intelligent sorting method for personal group list, intelligent terminal and storage medium | |
| CN106104512A (en) | System and method for active obtaining social data | |
| CN103870454A (en) | Method and method for recommending data | |
| CN103198086A (en) | Information processing device, information processing method, and program | |
| CN103034508A (en) | Software recommending method and software recommending system | |
| CN102955813B (en) | A kind of information search method and system | |
| WO2005104436A1 (en) | Method and system for generating a population representative of a set of users of a communication network | |
| CN108230169B (en) | Information propagation model based on social influence and situation perception system and method | |
| KR101206863B1 (en) | Method and Apparatus for Producing User Reputation of Online Network | |
| CN110020152A (en) | Using recommended method and device | |
| Dellarocas et al. | Using online reviews as a proxy of word-of-mouth for motion picture revenue forecasting | |
| Wu et al. | Detecting Crowdturfing in Social Media. | |
| Hu et al. | To return or to explore: Modelling human mobility and dynamics in cyberspace | |
| CN103297457B (en) | A kind of recommendation method and system of microblog users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: SHENZHEN TIANQU NETWORK TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: SHENZHEN KUAIBO TECHNOLOGY CO., LTD. Effective date: 20141203 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 518000 SHENZHEN, GUANGDONG PROVINCE TO: 518057 SHENZHEN, GUANGDONG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20141203 Address after: 518057 Guangdong city of Shenzhen province Shenzhen city Nanshan District South six road No. 6 Building 7 room 701 to Kelon Applicant after: SHENZHEN TEEQEE NETWORK TECHNOLOGY Co.,Ltd. Address before: 518000 Guangdong city of Shenzhen province Nanshan District Gao Xin Road No. 009 Chinese Technology Development Institute Technology Park building three, 22 floor Applicant before: SHENZHEN QVOD TECHNOLOGY Co.,Ltd. |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 518057 Nanshan District, Shenzhen, Guangdong, Guangdong Province, 9, No. 3, building No. 3, China Science and Technology Development Institute. Patentee after: Shenzhen city cloud fun network Polytron Technologies Inc. Address before: 518057 701, room 7, Mai Kelong building, 6 Gaoxin six road, Nanshan District, Shenzhen, Guangdong, Shenzhen, China Patentee before: SHENZHEN TEEQEE NETWORK TECHNOLOGY Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160629 |