CN116173513B - Intelligent game pushing system and method - Google Patents

Intelligent game pushing system and method Download PDF

Info

Publication number
CN116173513B
CN116173513B CN202310442555.0A CN202310442555A CN116173513B CN 116173513 B CN116173513 B CN 116173513B CN 202310442555 A CN202310442555 A CN 202310442555A CN 116173513 B CN116173513 B CN 116173513B
Authority
CN
China
Prior art keywords
game
player
information
module
information data
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.)
Active
Application number
CN202310442555.0A
Other languages
Chinese (zh)
Other versions
CN116173513A (en
Inventor
贾瑞
黄耀豪
曹迪
何瑞斌
石一峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Leyi Network Co ltd
Original Assignee
Shenzhen Leyi Network Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Leyi Network Co ltd filed Critical Shenzhen Leyi Network Co ltd
Priority to CN202310442555.0A priority Critical patent/CN116173513B/en
Publication of CN116173513A publication Critical patent/CN116173513A/en
Application granted granted Critical
Publication of CN116173513B publication Critical patent/CN116173513B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/70—Game security or game management aspects
    • A63F13/79—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories
    • A63F13/798—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories for assessing skills or for ranking players, e.g. for generating a hall of fame
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/70—Game security or game management aspects
    • A63F13/79—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
    • A63F2300/55—Details of game data or player data management
    • A63F2300/5546—Details of game data or player data management using player registration data, e.g. identification, account, preferences, game history
    • A63F2300/558—Details of game data or player data management using player registration data, e.g. identification, account, preferences, game history by assessing the players' skills or ranking

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Business, Economics & Management (AREA)
  • Computer Security & Cryptography (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides an intelligent game pushing system and method, comprising an information acquisition module, an information filtering module, an information classification module, an information processing module, an evaluation module, a feature extraction module, a prediction pushing module and a return visit feedback module; acquiring information of a game platform and a player, combining and filtering, and classifying by utilizing a multi-combination classification method; evaluating the player and the game platform by combining the processing result, then constructing a grid topological structure diagram, and comprehensively calculating the correlation of grid elements to push the game to the player; the invention realizes the technical effects of higher safety of the player information data and the game platform information data and more accurate game result pushing to the player.

Description

Intelligent game pushing system and method
Technical Field
The invention relates to the technical field of online games, in particular to an intelligent game pushing system and method.
Background
The reasonable game can help people develop intelligence, exercise thinking and reaction ability, training skills, cultivate rule consciousness and the like, and along with the increase of life pressure, the reasonable game becomes an important path for people to decompress. How to solve the problem that the game which is interesting and suitable for the players is particularly important in massive games, and win-win of game consumers and a game development platform can be achieved by adaptively and intelligently searching the games which the players like based on a big data mining technology and pushing the games to the players.
In the prior art, there is a game recommendation method based on big data, which mainly includes: constructing a game recommendation heterogram based on the player and the game history data, wherein nodes in the graph are players and games; calculating the correlation distance between the nodes; inputting the correlation distance between the player and the game history data and between the nodes into the GP neural network, and outputting the feature vectors of the player and the game history data through the embedded layer; the method comprises the steps of obtaining update weights when all feature vectors are convolved, and outputting action vectors of players and game history data through a GP neural network aggregation layer according to the update weights and the feature vectors; and outputting a recommendation result of the game through the GP neural network output layer by each behavior vector.
However, the above-mentioned technique has at least the following problems: the data information pushing results for players and games are poor in accuracy, and the player game platform information security is low.
Disclosure of Invention
The intelligent game pushing system and the intelligent game pushing method solve the problems of poor accuracy of pushing results and low information safety of a game platform of a player in the prior art, and achieve the technical effects that the information data of the player and the information data of the game platform are higher in safety, and the game results are pushed to the player more accurately.
The invention specifically comprises the following technical scheme:
an intelligent game push system, comprising:
the system comprises an information acquisition module, an information filtering module, an information classification module, an information processing module, an evaluation module, a characteristic extraction module, a prediction pushing module and a return visit feedback module;
the information acquisition module acquires player registration information and game platform registration input information, provides a data basis for the following game pushing, and transmits the acquired information data to the information filtering module for filtering; the information acquisition module is provided with an encryption component, and the information of the player and the game platform is encrypted by utilizing the existing encryption means;
the information filtering module is used for carrying out combined filtering processing on the information data of the player and the game platform obtained by the information obtaining module to obtain more effective information data, and transmitting the combined and filtered information data to the information classifying module;
the information classification module classifies the information according to the characteristics of the data information by adopting a multi-combination classification method to obtain classified data, facilitates the processing of the follow-up player information data and game data, sends the classified data to the player information processing module and the game information processing module for comprehensive processing, and evaluates the classified data by the player evaluation module and the game evaluation module;
the information processing module is used for comprehensively processing the classified information data to obtain a parameter influence factor set, and sending the processed parameter influence factor set to the evaluation module;
the evaluation module evaluates the player and the game platform according to the comprehensively processed parameter influence factors and the classified information data to obtain evaluation results of the player and the game platform, and sends the evaluation results to the prediction pushing module;
the feature extraction module is used for carrying out feature extraction on the classified information data to obtain the characteristic information of the player and the game platform, and sending the obtained feature information to the prediction pushing module;
the prediction pushing module predicts and pushes the player according to the parameter influence factor set of the information processing module, the evaluation result of the evaluation module, the characteristic information acquired by the characteristic extraction module and the feedback result acquired by the return visit feedback module;
and the return visit feedback module is used for obtaining feedback of the recommended result by carrying out questionnaire investigation on the player, feeding the feedback result back to the prediction pushing module and further adjusting the game pushing operation process of the player.
An intelligent game pushing method comprises the following steps:
s1, acquiring information of a game platform and a player through an information acquisition module, carrying out combined filtering processing on acquired information data, and carrying out classification processing on the filtered information data by utilizing a multi-combination classification method to obtain classified information data;
s2, carrying out information processing on the classified information data, simultaneously evaluating the player and the game platform by combining the processing result, carrying out feature extraction on the classified information data to obtain feature information of the player and the game platform, and constructing a grid topological structure diagram according to the processing result;
and S3, supplementing grid elements in the network topology structure chart by counting return visit feedback of each player to the game platform, comprehensively calculating the correlation of the grid elements, and pushing the game to the player to obtain a pushing result.
Further, the step S1 specifically includes:
the method comprises the steps of obtaining information data of a player and a game platform, carrying out encryption processing on the information data through an encryption component, carrying out combination filtering on the obtained information data, and carrying out information classification on the information data after the filtering processing by utilizing a multi-combination method to obtain the information data after the classification processing.
Further, the step S2 specifically includes:
respectively carrying out player information data processing and game platform information data processing on the classified information data to obtain a parameter influence factor set of a player related to a game; the information data set and the parameter influence factor set after the classification processing of the players and the game platform are used as training sequences of the deep learning neural network, the training sequences are trained by the existing deep learning neural network, and finally, assessment results of the players and the game are obtained, namely, an assessment set is obtained; and extracting the characteristics of the classified information data to obtain the characteristic information of the player and game platform data information, and obtaining a characteristic information set.
Further, the step S2 further includes:
and constructing a grid topology structure chart according to the parameter influence factor set, the characteristic information set and the evaluation set which are obtained after the player and game platform information data are processed.
Further, the step S2 further includes:
for classified player information data setsGame platform information data set after classification processing +.>Specifically, the->Wherein, the method comprises the steps of, wherein,Xrepresenting the total number of classification criteria for a set of player data, set +.>Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstxUnder the individual classification criteria, player information data set, < ->；/>Wherein, the method comprises the steps of, wherein,Yrepresenting the total number of classification criteria for the game platform information data sets, set +.>Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstyGame platform information data set, < +_, under individual classification criteria>The method comprises the steps of carrying out a first treatment on the surface of the And comprehensively analyzing and processing the classified information data set to obtain a parameter influence factor set related to the game by the player.
Further, the step S3 includes:
and calculating a feedback factor representing a feedback result by a fusion calculation method through feedback of a player on the game platform, transmitting feedback factor information to a prediction pushing module, supplementing the grid topological structure diagram, and further recommending games according to grid elements in the grid topological structure diagram.
Further, the step S3 further includes:
obtaining a feedback parameter set of a game platform from a questionnaire, wherein the feedback parameter set comprises a game playing period, a time input, a game attraction point, a game playing benefit, a game purpose and other relevant game questionnaire contents; each option of the questionnaire is assigned by an empirical method so as to facilitate the calculation of a feedback factor; in the first placenFor example, the game platform defines a feedback factor calculation formula as follows:
，
wherein,,Rrepresenting the total number of questions in the questionnaire,Cindicating the number of active persons participating in the questionnaire,represent the firstiProblem No.jPoints corresponding to individual player selections, +.>Representing the total score corresponding to the most preferred item of all questions in the questionnaire.
Further, the step S3 further includes:
according to the network topology structure diagram constructed in the step S2, calculating the correlation of the associated elements according to the progressive relation of the grid elements, determining the correlation degree between the player and the game according to the correlation, and further determining the recommendation result, wherein the specific recommendation process is as follows:
the first step, calculating a first correlation degree of any player for any game;
calculating a relevant compensation value according to the parameter influence factor, the evaluation result, the feature vector and the feedback factor;
thirdly, determining a final correlation degree according to the first correlation degree and the correlation compensation value;
and fourthly, obtaining a correlation degree set of the player and each game platform, selecting an item with the largest correlation degree from the correlation degree sets to recommend the game for the player, and if a plurality of maximum values exist, recommending the game in time intervals.
The invention has at least the following technical effects or advantages:
1. according to the invention, the information of the player and the game platform is acquired, the information data is encrypted through the encryption component, so that the safety of the information data of the player and the game platform is ensured, the acquired information data is combined and filtered to obtain more accurate information data, so that the accuracy of a pushing result of the pushing system is ensured, and then the filtered information data is classified by utilizing a multi-combination method to obtain classified information data, so that a data basis is provided for subsequent data processing.
2. According to the invention, by constructing the grid topological structure diagram, factors influencing the pushing result are arranged in the grid, so that the expansion of a recommendation system is facilitated, the pushing result comprises an information data set after multi-combination classification processing, a parameter influence factor set related to a game by a player, characteristic information of information data of the player and a game platform and a feedback result obtained by return visit feedback, an accurate parameter basis is provided for game pushing, and a more accurate pushing result is further obtained in the game pushing system.
3. According to the invention, the correlation degree between the connected elements is calculated in the grid topological structure diagram, and updated and supplemented according to other influence elements to obtain more accurate correlation, the correlation between the player and the game is further determined, and the highest correlation is taken as a pushing result, namely, the more accurate pushing result, so that game pushing is completed.
Drawings
FIG. 1 is a block diagram of an intelligent game push system according to the present invention;
FIG. 2 is a flow chart of an intelligent game pushing method according to the invention;
fig. 3 is an exemplary diagram of a mesh topology according to the present invention.
Detailed Description
The embodiment of the invention solves the problems of poor accuracy of pushing results and lower information security of players and game platforms in the prior art by providing the intelligent game pushing system and the intelligent game pushing method, and the overall thinking is as follows:
firstly, acquiring information of a game platform and a player through an information acquisition module, carrying out combined filtering processing on acquired information data, and then carrying out classification processing on the filtered information data by utilizing a multi-combination classification method to obtain classified information data; then, carrying out information processing on the classified information data, simultaneously evaluating the player and the game platform by combining the processing result, carrying out feature extraction on the classified information data to obtain feature information of the player and the game platform, and constructing a grid topological structure diagram according to the processing result to provide basis for game pushing; and finally, supplementing grid elements in the network topology structure chart by counting return visit feedback of each player to the game platform, comprehensively calculating the correlation of the grid elements, and pushing the game to the player to obtain a more accurate pushing result.
The information data of the player and the game platform are acquired, the information data are encrypted through an encryption component, so that the safety of the information data of the player and the game platform is guaranteed, the acquired information data are combined and filtered to obtain more accurate information data, so that the accuracy of a recommendation result of the recommendation system is guaranteed, and then the information data after the filtering treatment are classified by a multi-combination method to obtain the information data after the classification treatment, so that a data base is provided for subsequent data treatment; the factors influencing the recommendation result are placed in the grid through constructing the grid topological structure diagram, so that the recommendation system is more convenient to develop, the influence recommendation result comprises information data sets which are subjected to multi-combination classification processing, parameter influence factor sets related to the game of a player, characteristic information of information data of the player and a game platform and feedback factors obtained through return visit feedback are calculated, accurate parameter basis is provided for game recommendation, and more accurate recommendation result is further obtained in the game recommendation system; the correlation between the connected elements is calculated in the grid topological structure diagram, and the correlation is updated and supplemented according to other influence elements to obtain more accurate correlation, so that the correlation between the player and the game is further determined, and the highest decorrelation is used as a recommendation result, namely a more accurate recommendation result, so that game recommendation is completed.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Referring to fig. 1, the intelligent game pushing system of the invention comprises the following parts:
the system comprises an information acquisition module, an information filtering module, an information classification module, an information processing module, an evaluation module, a characteristic extraction module, a prediction pushing module and a return visit feedback module;
the information acquisition module acquires player registration information and game platform registration input information, provides a data basis for the following game pushing, and transmits the acquired information data to the information filtering module for filtering;
particularly, an encryption component is arranged in the information acquisition module to encrypt information of the player and the game platform by utilizing the existing encryption means so as to ensure that the information of the player and the information of the game platform are not revealed and ensure the safety of a recommendation system;
the information filtering module is used for carrying out combined filtering processing on the information data of the player and the game platform obtained by the information obtaining module to obtain more effective information data, and transmitting the combined and filtered information data to the information classifying module;
the information classification module classifies the information according to the characteristics of the data information by adopting a multi-combination classification method to obtain classified data, facilitates the processing of the follow-up player information data and game data, sends the classified data to the player information processing module and the game information processing module for comprehensive processing, and evaluates the classified data by the player evaluation module and the game evaluation module;
the information processing module is used for comprehensively processing the classified information data to obtain a parameter influence factor set, and sending the processed parameter influence factor set to the evaluation module;
the evaluation module evaluates the player and the game platform according to the comprehensively processed parameter influence factors and the classified information data to obtain evaluation results of the player and the game platform, and sends the evaluation results to the prediction pushing module;
the feature extraction module is used for carrying out feature extraction on the classified information data to obtain the characteristic information of the player and the game platform, and sending the obtained feature information to the prediction pushing module;
the prediction pushing module predicts and pushes the player according to the parameter influence factor set of the information processing module, the evaluation result of the evaluation module, the characteristic information acquired by the characteristic extraction module and the feedback result acquired by the return visit feedback module;
the return visit feedback module is used for obtaining feedback of the recommended result by carrying out questionnaire investigation on the player, feeding the feedback result back to the prediction pushing module, and further adjusting the game pushing operation process of the player to obtain a more accurate and humanized pushing result.
The intelligent game pushing method comprises the following steps:
s1, acquiring information of a game platform and a player through an information acquisition module, carrying out combined filtering processing on acquired information data, and then carrying out classification processing on the filtered information data by utilizing a multi-combination classification method to obtain classified information data;
s11, collecting information data of a player and a game platform to obtain an information data set of the player and the game platform, and carrying out combined filtering processing on the information data set to obtain filtered information data;
collecting the registration information of the player and the push information of the game platform to obtain an information data set，/>Wherein->A data set representing the information of the player,，Mrepresenting the number of players, set->Any subset of (a) may be composed ofIndicating (I)>Represent the firstmInformation data set of individual players,/>The player information data comprises player age, player marital status, player family status, player game playing age, player gender, player income, ever playing game category, playing game corresponding time length, interested game category and other relevant information data; />Information data set representing game platform->，NRepresenting the number of game platforms, set->Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstnInformation data set of individual game platform, +.>The game platform information data comprises game types, game downloading amounts, game descriptions, game sharing times, game scores and other game information data;
in particular, the collected information data is encrypted by the existing encryption technology, and only the user with the secret key calls the information data, and the secret key is handed to the recommended system administrator for storage, so that the safety of the information data of the player and the game platform is ensured, and a safer environment is provided.
For the collected information data setThe combined filtering treatment is carried out, and the specific process is as follows:
firstly, setting different filtering criteria aiming at the characteristics of information data, wherein the filtering criteria comprise filtering, invalid filtering, conditional filtering, configuration filtering, verification filtering and the like; performing preliminary filtration on the collected information data set by utilizing a filtering criterion;
then, the information data set after preliminary filtering is subjected to final filtering processing by utilizing the prior noise reduction technology, so that a more accurate information data set is obtained；
As a specific embodiment, for the filter criteria, for player age, clipping filter criteria are employed: taking player information between 6 and 95 years old and deleting the player information of other ages;
finally, the information data set after combined filtering is obtained；
S12, classifying the combined and filtered information data, and laying a foundation for subsequent information data processing;
for the information data set after combination and filtrationThe method comprises the following steps of:
the first step, the information data set after the filtering processing is processed according to the data typePerforming preliminary classification treatment, wherein the data types include characters, numerical values, images and audios;
setting different classification criteria to carry out final classification processing on the data after preliminary classification processing, wherein the classification criteria comprise player information classification criteria and game platform information classification criteria, and specifically include age group classification, interest and hobby classification, player gender classification, game category classification, game downloading amount classification and the like; obtaining information data set of multi-combination classification processing；
As a specific embodiment, when classifying the filtered player information data set in age groups, a segment is set every five years old, and the player information is classified in segments, so that a data base is provided for further processing.
Thirdly, obtaining the classified information data set；
According to the invention, the information of the player and the game platform is acquired, the information data is encrypted through the encryption component, so that the safety of the information data of the player and the game platform is ensured, the acquired information data is combined and filtered to obtain more accurate information data, so that the accuracy of a pushing result of the pushing system is ensured, and then the filtered information data is classified by utilizing a multi-combination method to obtain classified information data, so that a data basis is provided for subsequent data processing.
S2, carrying out information processing on the classified information data, simultaneously evaluating a player and a game platform by combining a processing result, carrying out feature extraction on the classified information data to obtain feature information of the player and the game platform, and constructing a grid topological structure diagram according to the processing result to provide basis for game pushing;
s21, respectively carrying out player information data processing and game platform information data processing on the classified information data to obtain a parameter influence factor set of a player related to a game;
for classified player information data setsGame platform information data set after classification processing +.>Specifically, the->Wherein, the method comprises the steps of, wherein,Xrepresenting a total number of classification criteria for the set of player information data, the set of classification criteria being classification criteria associated with the classification of player information among the classification criteria; set->Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstxPlayer information data sets under individual classification criteria, +.>；/>Wherein, the method comprises the steps of, wherein,Yrepresenting the total number of classification criteria for the game platform information data sets, wherein the classification criteria for the game platform information data sets are the classification criteria related to game platform information classification in the classification criteria; set->Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstyGame platform information data set under individual classification criteria, < ->The method comprises the steps of carrying out a first treatment on the surface of the And (3) comprehensively calculating the player information data and the game platform information data under each classification criterion to obtain a parameter influence factor set related to the game of the player, wherein the parameter influence factor comprises player preference, game labels, each player playing time, game downloading frequency, game entering frequency, game sharing frequency and the like.
As a specific embodiment, when calculating the conventional parameter impact factor, an existing conventional calculation method is adopted to calculate, for example, the time length for playing each game, the frequency of downloading the game, the number of game entries, the number of game shares, and the like, which are obtained by only counting by using a statistical method, in this application, the calculation formula for redefining the preference of the player, and the type of the game tag is as follows:
，
wherein,,represent the firstmPlayer pair 1nPreference of the individual game platform,/->Represent the firstnScoring of the individual games; />Represent the firstmPlayer pair 1nPreference of the individual game platform, < >>，IRepresent the firstmTotal expenditure of the individual player for playing the game in a certain period,/->Represent the firstmThe first player is within a certain periodnPayout in the individual games;/>represent the firstmPlayer pair 1nThe attention of the individual game platforms,，Trepresent the firstmTotal duration of each player's daily game play, +.>Represent the firstmThe individual player is on daynDuration in the respective games, P represents the firstmFrequency of individual players entering the game every day, +.>Represent the firstmThe individual player enters the first daynFrequency of individual games, S represents the firstmThe number of games shared by the individual players in a certain period, < >>Represent the firstmSharing the first player in a certain periodnThe number of games;
，
wherein,,represent the firstnGame number onelThe weight value of the individual tag(s),Numrepresent the firstnTotal number of players of the game checkup tab, < >>Represent the firstnIn-game hooklThe number of players on the tag;grepresent the firstnTotal score of the individual game hook tab, < +.>Represent the firstnIn-game hooklScoring the individual tags;
finally, obtaining parameter influence factor sets of the player and the game platform，/>Wherein, the method comprises the steps of, wherein,Krepresenting the number of parameter influencing factors, set->Any one of the elements may be defined by +.>Indicating (I)>Represent the firstkIndividual parameter influencing factors,/->。
In particular, among the parameter impact factor sets, there are parameter impact factors related to only the player, parameter impact factors related to only the game platform, and parameter impact factors related to the player and the game platform.
S22, evaluating the player and the game platform according to the parameter influence factor set obtained after the player and the game platform information data are processed and the player and the game platform information data to obtain evaluation results of the player and the game platform;
the method comprises the steps that an information data set and a parameter influence factor set of players and game platforms after classification processing are used as training sequences of a deep learning neural network, the training sequences are trained by the existing deep learning neural network, and the training sequences comprise a BP neural network, a GP neural network and the like; finally, the evaluation results of the player and the game, namely an evaluation set, are obtained，/>Representing a set of player evaluation results and a set of game platform evaluation results, respectively, wherein->Wherein, the method comprises the steps of, wherein,Mrepresenting the total number of players, set->Any one of the elements may be defined by +.>Indicating (I)>Represent the firstmEvaluation result of individual player->Comprises the evaluation values of each evaluation item of the player, includingJThe number of elements to be added to the composition,Jrepresenting the total number of items evaluated->；/>Wherein N represents the total number of game platforms, set +.>Any one of the elements may be defined by +.>Indicating (I)>Representing the evaluation result of the nth game platform, < +.>Comprises the evaluation values of each evaluation item of the game platform, which comprisesPThe number of elements to be added to the composition,Pindicating that the total number of terms is to be evaluated,/>。
s23, extracting characteristics of the classified information data to obtain characteristic information of player and game platform data information;
when the characteristic extraction is carried out on the classified information data, the existing characteristic extraction technology is adopted to obtain a characteristic vector set of the player and game platform data information，/>Wherein, the method comprises the steps of, wherein,Hrepresenting the total number of feature vectors, set->Any one of the elements may be defined by +.>Indicating (I)>Represent the firsthIndividual feature vectors->。
In particular, the feature vector set is comprised of a player feature vector set and a game platform feature vector set.
Further, according to the parameter influence factor set, the characteristic information set and the evaluation set obtained after the player and game platform information data are processed, a grid topology structure diagram is constructed, and the specific construction is as follows: the information data set after the multi-combination classification processing, the parameter influence factor set of the player and the game, the characteristic information set of the player and the game platform information data and the feedback result obtained by the return visit feedback are arranged in each grid point in the grid topological structure diagram, and referring to fig. 3, as a specific embodiment, the method adopts the following steps ofmIndividual playerAnd (d)nPersonal game platform->For example, a->Representing player->Is the first of (2)xInformation data sets under the individual classification criteria; />Representing game platform->Is the first of (2)yInformation data sets under the individual classification criteria; />Is indicated at->In the case of classification only with the firstmA subset of individual player-related parameter impact factors; />Is indicated at->In the case of classification only with the firstnA subset of game platform-related parameter impact factors; />Representation->、A subset of parameter impact factors associated with the player and the game under the categorization; />Representation->Classification case NomEvaluation results of individual players; />Representation->Classification case NonEvaluation results of individual players; />Representation ofClassification case NomA feature vector set for each player; />Representation->Classification case NonFeature vector sets of the individual game platforms; />Representation of the first pairnFeedback factors for the individual game platforms;
in the grid topological graph, each grid point has other grid points related to the grid point, namely, all grid points are mutually connected, mutually influenced and mutually restricted, and a parameter basis is provided for game recommendation.
In particular, the feedback result consists of a feedback factor, which is introduced in step S3.
According to the invention, factors influencing the pushing result are placed in the grid by constructing the grid topological structure diagram, so that the expansion of a recommendation system is facilitated, the pushing result comprises an information data set after multi-combination classification processing, a parameter influence factor set related to a game by a player, characteristic information of information data of the player and a game platform and a feedback result obtained by return visit feedback, an accurate parameter basis is provided for game pushing, and a more accurate pushing result is further obtained in the game pushing system.
And S3, supplementing grid elements in the network topology structure chart by counting return visit feedback of each player to the game platform, comprehensively calculating the correlation of the grid elements, and pushing the game to the player to obtain a more accurate pushing result.
In particular, in the grid of the grid topology map, the associated grid elements are interconnected as part of the correlation calculation when making the prediction recommendation.
S31, through feedback of return visit of the player to the game platform, a fusion calculation method is adopted to calculate and obtain a feedback factor representing a feedback result, and feedback factor information is transmitted to a prediction pushing module.
In the return visit feedback module, feedback factors are obtained by acquiring feedback of the player on the game platform from a questionnaire of the player and combining a fusion calculation method with an experience methodThe specific process is as follows:
firstly, obtaining a feedback parameter set of a player to a game platform from a questionnaire, wherein the feedback parameter set comprises a game playing period, a time input, a game attraction point, a game playing benefit, a game purpose and other relevant game questionnaire contents; in particular, each option of the questionnaire is assigned an empirical score to facilitate the calculation of the feedback factor; subsequently, in the first placenFor example, the game platform defines a feedback factor calculation formula as follows:
，
wherein,,Rrepresenting the total number of questions in the questionnaire,Cindicating the number of active persons participating in the questionnaire,represent the firstiProblem No.jPersonal player selectionSelecting the corresponding score of ∈>Representing total points corresponding to the most preferred items of all questions in the questionnaire;
s32, game recommendation is carried out according to grid elements in the grid topological structure diagram;
according to the network topology structure diagram constructed in the step S2, calculating the correlation of the associated elements according to the progressive relation of the grid elements, determining the correlation degree between the player and the game according to the correlation, and further determining the recommendation result, wherein the specific recommendation process is as follows:
the first step, calculating a first correlation degree of any player for any game; the calculation formula is as follows
，
Wherein,,representing the relativity between the nth player and the nth game platform between the xth player classification information data and the y game platform classification information data set, wherein the relativity is calculated by using an empirical method after counting related element items between the two classification information data sets;
calculating a relevant compensation value according to the parameter influence factor, the evaluation result, the feature vector and the feedback factor; the calculation formula is as follows:
，
wherein,,expressed in the parameter influence factor set and the firstmIndividual player and the firstnSum of elements related to each game platform; />In the evaluation of playersIn the aggregate and the firstmIndividual player and the firstnSum of elements related to the individual game platform +.>Representing the total of the evaluation results of the player, ->And in game platform assessment setnPersonal gaming platform and the thmSum of individual player related elements +.>Representing a game platform evaluation result sum;expressed in the feature vector set and the firstmIndividual player and the firstnInner products of feature vectors associated with the individual game platforms; />Representing a feedback factor;
thirdly, determining a final correlation degree according to the first correlation degree and the correlation compensation value; the calculation formula is as follows:
，
finally, obtaining a correlation set of the player and each game platform, selecting the item with the largest correlation from the correlation sets to recommend the game for the player, and if a plurality of maximum values exist, recommending the game in time intervals.
According to the game push method, the correlation degree between the connected elements is calculated in the grid topological structure diagram, the correlation degree is updated and supplemented according to other influence elements, the more accurate correlation is obtained, the correlation between the player and the game is further determined, and the highest correlation is taken as a push result, namely the more accurate push result, so that game push is completed.
In summary, the intelligent game pushing system and the intelligent game pushing method are completed.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (8)

1. The pushing method of the intelligent game pushing system is characterized by comprising the following steps of:
s1, acquiring information of a game platform and a player through an information acquisition module, carrying out combined filtering processing on acquired information data, and carrying out classification processing on the filtered information data by utilizing a multi-combination classification method to obtain classified information data;
s2, carrying out information processing on the classified information data, simultaneously evaluating the player and the game platform by combining the processing result, carrying out feature extraction on the classified information data to obtain feature information of the player and the game platform, and constructing a grid topological structure diagram according to the processing result;
s3, supplementing grid elements in the grid topological structure diagram by counting return visit feedback of each player to the game platform, comprehensively calculating the correlation of the grid elements, and pushing the game to the player to obtain a pushing result;
according to the grid topological structure diagram constructed in the step S2, calculating the correlation of the associated elements according to the progressive relation of the grid elements, determining the correlation degree between the player and the game according to the correlation, and further determining the recommendation result, wherein the specific recommendation process is as follows:
the first step, calculating a first correlation degree of any player for any game;
calculating a relevant compensation value according to the parameter influence factor, the evaluation result, the feature vector and the feedback factor;
thirdly, determining a final correlation degree according to the first correlation degree and the correlation compensation value;
step four, obtaining a correlation degree set of the player and each game platform, selecting the item with the largest correlation degree from the correlation degree sets as the game recommendation of the player, and recommending in time periods if a plurality of maximum values exist;
the specific steps of the first step are as follows, and a first correlation degree of any player for any game is calculated; the calculation formula is as follows
，
Wherein,,representing the relativity between the nth player and the nth game platform between the xth player classification information data and the y game platform classification information data set, wherein the relativity is calculated by using an empirical method after counting related element items between the two classification information data sets;
calculating a relevant compensation value according to the parameter influence factor, the evaluation result, the feature vector and the feedback factor; the calculation formula is as follows:
，
wherein,,expressed in the parameter influence factor set and the firstmIndividual player and the firstnSum of elements related to each game platform; />And the first in the player evaluation setmIndividual player and the firstnSum of elements related to the individual game platform +.>Representing the total of the evaluation results of the player, ->And in game platform assessment setnPersonal gaming platform and the thmSum of individual player related elements +.>Representing a game platform evaluation result sum; />Expressed in the feature vector set and the firstmIndividual player and the firstnInner products of feature vectors associated with the individual game platforms; />Representing a feedback factor;
thirdly, determining a final correlation degree according to the first correlation degree and the correlation compensation value; the calculation formula is as follows:
，
finally, obtaining a correlation set of the player and each game platform, selecting the item with the largest correlation from the correlation sets to recommend the game for the player, and if a plurality of maximum values exist, recommending the game in time intervals.
2. The pushing method of the intelligent game pushing system according to claim 1, wherein the step S1 specifically includes:
the method comprises the steps of obtaining information data of a player and a game platform, carrying out encryption processing on the information data through an encryption component, carrying out combination filtering on the obtained information data, and carrying out information classification on the information data after the filtering processing by utilizing a multi-combination method to obtain the information data after the classification processing.
3. The pushing method of the intelligent game pushing system according to claim 1, wherein the step S2 specifically includes:
respectively carrying out player information data processing and game platform information data processing on the classified information data to obtain a parameter influence factor set of a player related to a game; the information data set and the parameter influence factor set after the classification processing of the players and the game platform are used as training sequences of the deep learning neural network, the training sequences are trained by the existing deep learning neural network, and finally, assessment results of the players and the game are obtained, namely, an assessment set is obtained; and extracting the characteristics of the classified information data to obtain the characteristic information of the player and game platform data information, and obtaining a characteristic information set.
4. The pushing method of an intelligent game pushing system according to claim 1, wherein the step S2 further comprises:
and constructing a grid topology structure chart according to the parameter influence factor set, the characteristic information set and the evaluation set which are obtained after the player and game platform information data are processed.
5. The pushing method of an intelligent game pushing system according to claim 1, wherein the step S2 further comprises:
for classified player information data setsGame platform information data set after classification processing +.>Specifically, the->Wherein, the method comprises the steps of, wherein,Xrepresenting the total number of classification criteria for a set of player data, set +.>Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstxUnder the individual classification criteria, player information data set, < ->；/>Wherein, the method comprises the steps of, wherein,Yrepresenting classification criteria for game platform information data setsTotal number of (1)/(1) set->Any subset of (2) may be defined by +.>Indicating (I)>Represent the firstyGame platform information data set, < +_, under individual classification criteria>The method comprises the steps of carrying out a first treatment on the surface of the And comprehensively analyzing and processing the classified information data set to obtain a parameter influence factor set related to the game by the player.
6. The pushing method of the intelligent game pushing system according to claim 1, wherein the step S3 specifically includes:
and calculating a feedback factor representing a feedback result by a fusion calculation method through feedback of a player on the game platform, transmitting feedback factor information to a prediction pushing module, supplementing the grid topological structure diagram, and further recommending games according to grid elements in the grid topological structure diagram.
7. The pushing method of an intelligent game pushing system according to claim 1, wherein the step S3 further comprises:
obtaining a feedback parameter set of a game platform from a questionnaire, wherein the feedback parameter set comprises a game playing period, a time input, a game attraction point, a game playing benefit, a game purpose and other relevant game questionnaire contents; each option of the questionnaire is assigned by an empirical method so as to facilitate the calculation of a feedback factor; in the first placenFor example, the game platform defines a feedback factor calculation formula as follows:
，
wherein,,Rrepresenting the total number of questions in the questionnaire,Cindicating the number of active persons participating in the questionnaire,represent the firstiProblem No.jPoints corresponding to individual player selections, +.>Representing the total score corresponding to the most preferred item of all questions in the questionnaire.
8. An intelligent game push system is characterized by comprising the following parts:
the system comprises an information acquisition module, an information filtering module, an information classification module, an information processing module, an evaluation module, a characteristic extraction module, a prediction pushing module and a return visit feedback module;
the information acquisition module acquires player registration information and game platform registration input information, provides a data basis for the following game pushing, and transmits the acquired information data to the information filtering module for filtering; the information acquisition module is provided with an encryption component, and the information of the player and the game platform is encrypted by utilizing the existing encryption means;
the information filtering module is used for carrying out combined filtering processing on the information data of the player and the game platform obtained by the information obtaining module and transmitting the combined and filtered information data to the information classifying module;
the information classification module classifies the information according to the characteristics of the data information by adopting a multi-combination classification method to obtain classified data, facilitates the processing of the follow-up player information data and game data, sends the classified data to the player information processing module and the game information processing module for comprehensive processing, and evaluates the classified data by the player evaluation module and the game evaluation module;
the information processing module is used for comprehensively processing the classified information data to obtain a parameter influence factor set, and sending the processed parameter influence factor set to the evaluation module;
the evaluation module evaluates the player and the game platform according to the comprehensively processed parameter influence factors and the classified information data to obtain evaluation results of the player and the game platform, and sends the evaluation results to the prediction pushing module;
the feature extraction module is used for carrying out feature extraction on the classified information data to obtain the characteristic information of the player and the game platform, and sending the obtained feature information to the prediction pushing module;
the prediction pushing module predicts and pushes the player according to the parameter influence factor set of the information processing module, the evaluation result of the evaluation module, the characteristic information acquired by the characteristic extraction module and the feedback result acquired by the return visit feedback module;
the return visit feedback module is used for obtaining feedback of the recommended result through carrying out questionnaire investigation on the player, feeding the feedback result back to the prediction pushing module and further adjusting the game pushing operation process of the player;
the intelligent game push system is configured to implement the method of claim 1.
CN202310442555.0A 2023-04-24 2023-04-24 Intelligent game pushing system and method Active CN116173513B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310442555.0A CN116173513B (en) 2023-04-24 2023-04-24 Intelligent game pushing system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310442555.0A CN116173513B (en) 2023-04-24 2023-04-24 Intelligent game pushing system and method

Publications (2)

Publication Number Publication Date
CN116173513A CN116173513A (en) 2023-05-30
CN116173513B true CN116173513B (en) 2023-07-25

Family

ID=86452415

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310442555.0A Active CN116173513B (en) 2023-04-24 2023-04-24 Intelligent game pushing system and method

Country Status (1)

Country Link
CN (1) CN116173513B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8298087B1 (en) * 2009-01-02 2012-10-30 Nintendo Of America Inc. Recommendation engine for electronic game shopping channel
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

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10957152B2 (en) * 2011-02-17 2021-03-23 Aristocrat Technologies Australia Pty Limited Gaming tracking and recommendation system
US9387392B1 (en) * 2011-02-17 2016-07-12 Aristocrat Technologies Australia Pty Limited Gaming tracking and recommendation system
CN103136435B (en) * 2011-11-30 2016-06-29 深圳市天趣网络科技有限公司 System, method and gaming platform that a kind of individualized game is recommended
US8984082B2 (en) * 2012-08-29 2015-03-17 Wetpaint.Com, Inc. Personalization based upon social value in online media
CN103353920B (en) * 2013-05-31 2017-05-17 北京百度网讯科技有限公司 Method and device for recommending games based on SNS
US10357718B2 (en) * 2017-02-28 2019-07-23 Electronic Arts Inc. Realtime dynamic modification and optimization of gameplay parameters within a video game application
CN108304853B (en) * 2017-10-10 2022-11-08 腾讯科技（深圳）有限公司 Game correlation obtaining method and device, storage medium and electronic device
CN110674394B (en) * 2019-08-20 2024-03-15 腾讯科技（深圳）有限公司 Knowledge graph-based information recommendation method, device and storage medium
CN110837598B (en) * 2019-11-11 2021-03-19 腾讯科技（深圳）有限公司 Information recommendation method, device, equipment and storage medium
US11417171B2 (en) * 2019-12-20 2022-08-16 Igt Artificial intelligence (AI) implementations for providing game recommendations at a gaming device, and related systems, devices, and methods
CN111632386A (en) * 2020-04-02 2020-09-08 海南喜相逢网络有限公司 Game recommendation platform and game recommendation method
US20210397971A1 (en) * 2020-06-22 2021-12-23 Nvidia Corporation Recommendation generation using one or more neural networks
CN112052386B (en) * 2020-08-10 2023-09-29 腾讯科技（深圳）有限公司 Information recommendation method, device and storage medium
CN114861074A (en) * 2022-07-07 2022-08-05 深圳市乐易网络股份有限公司 User data analysis method and system
CN115221403A (en) * 2022-07-14 2022-10-21 郑州润声电子科技有限公司 Game recommendation method based on big data

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8298087B1 (en) * 2009-01-02 2012-10-30 Nintendo Of America Inc. Recommendation engine for electronic game shopping channel
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

Also Published As

Publication number Publication date
CN116173513A (en) 2023-05-30

Similar Documents

Publication Publication Date Title
Chmait et al. Artificial intelligence and machine learning in sport research: An introduction for non-data scientists
CN109508789B (en) Method, storage medium, processor and apparatus for predicting hand
CN108537567B (en) Method and device for determining target user group
CN110245301A (en) A kind of recommended method, device and storage medium
CN108304853B (en) Game correlation obtaining method and device, storage medium and electronic device
Cowley et al. Real-time rule-based classification of player types in computer games
CN113268589B (en) Key user identification method, key user identification device, readable storage medium and computer equipment
CN111738294B (en) AI model training method, AI model using method, computer device, and storage medium
CN107657034A (en) A kind of event social networks proposed algorithm of social information enhancing
CN107807943A (en) Application program recommends method and device
CN110941769B (en) Target account determination method and device and electronic device
CN114470791A (en) Game item recommendation method and device, computer equipment, storage medium and product
CN112263835A (en) Game balance testing method and device, electronic equipment and storage medium
Shaker et al. Towards generic models of player experience
KR100542084B1 (en) Dynamic matching method of participants in on-line game and system carrying the smae
Sturn et al. Cropland Capture–a game for improving global cropland maps
CN116173513B (en) Intelligent game pushing system and method
Navandar et al. Modernizing sports an intelligent strategy for entertainment through internet of things in sports
Rezvani et al. Gamers' Behaviour and Communication Analysis in Massively Multiplayer Online Games: A Survey
Chen et al. Modeling game avatar synergy and opposition through embedding in multiplayer online battle arena games
Cavadenti et al. When cyberathletes conceal their game: Clustering confusion matrices to identify avatar aliases
Cornforth et al. Cluster evaluation, description, and interpretation for serious games: player profiling in Minecraft
CN116383504A (en) Information recommendation method based on gradient shuffling and related equipment
King Predicting a Quarterback's fantasy football point output for daily fantasy sports using statistical models
CN108136261B (en) Server and non-transitory computer-readable medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant