CN114939276A - Game operation data analysis method, system and storage medium - Google Patents
Game operation data analysis method, system and storage medium Download PDFInfo
- Publication number
- CN114939276A CN114939276A CN202210450364.4A CN202210450364A CN114939276A CN 114939276 A CN114939276 A CN 114939276A CN 202210450364 A CN202210450364 A CN 202210450364A CN 114939276 A CN114939276 A CN 114939276A
- Authority
- CN
- China
- Prior art keywords
- optimization
- feedback
- registered user
- game
- preset
- 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 38
- 238000007405 data analysis Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 319
- 238000004458 analytical method Methods 0.000 claims description 17
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 claims description 11
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000013433 optimization analysis Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 3
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- A63F13/85—Providing additional services to players
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a game operation data analysis method, a game operation data analysis system and a storage medium. The game operation data analysis method comprises the steps of obtaining the number of registered users corresponding to a game platform and basic registration information corresponding to each registered user; extracting feedback data corresponding to each registered user from a game platform background; carrying out optimization weight setting on each preset optimization direction corresponding to the game platform; analyzing each optimization stage and each preset optimization direction corresponding to the game platform; the method effectively solves the problem that the prior art does not analyze from the user experience level, and highlights the problems of the current game platform, thereby providing reliable reference basis and definite direction for the self perfection of the game platform, greatly improving the viscosity and the fidelity of the user and the game platform, simultaneously greatly improving the game experience corresponding to the user, and improving the operation efficiency of the game platform to a certain extent.
Description
Technical Field
The invention belongs to the technical field of game operation data analysis, and relates to a game operation data analysis method, a game operation data analysis system and a storage medium.
Background
Along with the rapid development of the internet technology, the electronic game industry has come to the fore, the electronic game becomes one of the first-choice entertainment modes of the current youth according to a plurality of characteristics of interest, interactivity, content richness and the like, and the game operation data needs to be analyzed in order to improve the operation efficiency of the electronic game platform.
The analysis of the current game operation data mainly focuses on the analysis of the user management level, such as the analysis of the data of the user, the user payment rate, the user playing time and the like, and obviously, the current game operation data analysis mode has the following problems:
1. the main influence factor of the audience rate of the game platform is the user game experience, the current game operation data analysis mode is not analyzed from the user experience level, and the method has certain limitation, cannot effectively highlight the problems of the current game platform and further cannot provide reliable reference basis for the improvement of the game platform;
2. the operating efficiency of the game platform is mainly reflected in the stickiness between the platform and the user, the feedback data of the user is not analyzed at present, the subjective feeling of the user on the platform cannot be reflected, further, a clear optimization direction cannot be provided for the game platform, further, the stickiness between the user and the game platform cannot be effectively improved, and meanwhile, the loyalty of the user cannot be effectively improved;
3. the experience feelings of people in different game stages to games can also have differences, the operation data of the game platform is not analyzed according to the game stage types of users at present, the game requirements corresponding to different game stages cannot be effectively reflected, the game experience feelings corresponding to different game stages cannot be effectively improved, and meanwhile, decision-making reference data cannot be provided for positioning in the optimization stage of the game platform.
Disclosure of Invention
In view of the above, to solve the problems in the background art, a game operation data analysis method, a system and a storage medium are provided;
the purpose of the invention can be realized by the following technical scheme:
the invention provides a game operation data analysis method in a first aspect, which comprises the following steps:
step 1, obtaining user registration information: acquiring the number of registered users corresponding to a game platform and basic registration information corresponding to each registered user, numbering each registered user according to a preset sequence, and sequentially marking the registered users as 1,2,. i,. m;
step 2, extracting user feedback data: extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data specifically comprises the number of feedback problems corresponding to each registered user and feedback information corresponding to each registered user during each feedback problem;
step 3, optimizing the direction weight setting: acquiring each preset optimization direction corresponding to the game platform, setting optimization weights according to each preset optimization direction corresponding to the game platform, numbering each preset optimization direction corresponding to the game platform according to a preset sequence, and sequentially marking the directions as 1,2,. j,. n;
step 4, analyzing platform optimization information: analyzing each optimization stage and each preset optimization direction corresponding to the game platform respectively based on basic registration information corresponding to each registered user and feedback data corresponding to each registered user, counting optimization value indexes corresponding to each optimization stage of the game platform and optimization value indexes corresponding to each preset optimization direction of the game platform respectively, matching and comparing the optimization value indexes corresponding to each optimization stage of the game platform with a set standard optimization value index, if the optimization value index corresponding to a certain optimization stage in the game platform reaches the set standard optimization value index, taking the optimization stage as a key optimization stage corresponding to the game platform, matching and comparing the optimization value indexes corresponding to each preset optimization direction of the game platform with the set standard optimization value index, if the optimization value index corresponding to a certain preset optimization direction in the game platform reaches the set standard optimization value index, taking the preset optimization direction as a key optimization direction corresponding to the game platform;
step 5, analysis result feedback: and feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
In one possible design, the basic registration information corresponding to each registered user includes registration duration and registration account information, where the registration account information includes a type corresponding to a registration account and a game stage in which the registration account is located, the registration account types include a normal type and a member type, and the game stage includes an early stage, a middle stage and a later stage.
In a possible design, the optimal weight setting is performed according to each preset optimal direction corresponding to the game platform, and the specific setting process is as follows:
acquiring each preset optimization direction corresponding to the game platform, wherein the preset optimization directions comprise user experience, story flow, interactive operation, game performance and game memory;
recording the optimization weight corresponding to user experience in the game platform as epsilon 1, recording the optimization weight corresponding to story flow as epsilon 2, recording the optimization weight corresponding to interactive operation as epsilon 3, recording the optimization weight corresponding to game performance as epsilon 4, and recording the optimization weight corresponding to game memory as epsilon 5, thus respectively obtaining the optimization weights corresponding to all preset optimization directions in the game platform in the mode, and recording the optimization weights as epsilon j J represents a number corresponding to each preset optimization direction, and j is 1, 2.
In a possible design, the analyzing step 4 analyzes each optimization stage corresponding to the game platform, and the specific analyzing process includes the following steps:
extracting registration time length from the basic registration information corresponding to each registered user, comparing the registration time length corresponding to each registered user with the set platform reference registration time length, calculating the registration time length influence weight corresponding to each registered user, and recording as eta i I denotes a number corresponding to each registered user, i ═ 1, 2.... m;
extracting registered account information from the basic registration information corresponding to each registered user, further extracting the type corresponding to the registered account from the registered account information corresponding to each registered user, if the registered account type corresponding to the registered user is a common type, recording the account influence weight corresponding to the registered user as sigma 1, and if the registered user corresponds to the registered user, recording the account influence weight as sigma 1If the account type is a member type, the account influence weight corresponding to the registered user is recorded as sigma 2, so as to obtain the account type influence weight corresponding to each registered user respectively, and recorded as sigma i Wherein σ is i The value is sigma 1 or sigma 2, and sigma 2 is more than sigma 1;
extracting game stages of registered accounts from the registered account information corresponding to each registered user, further acquiring the game stages of the accounts corresponding to each registered user, mutually comparing the game stages of the accounts corresponding to each registered user, counting the number of the registered users corresponding to each game stage, taking each game stage as an optimization stage, and extracting registration duration influence weight and account type influence weight corresponding to each registered user in each optimization stage;
and accumulating to obtain the comprehensive feedback problem times corresponding to each optimization stage based on the feedback problem times corresponding to each registered user and the registered user number corresponding to each optimization stage, and calculating the comprehensive feedback problem times corresponding to each optimization stage to obtain the optimization value index corresponding to each optimization stage of the game platform.
In one possible design, the calculation formula of the optimization value index corresponding to each optimization stage of the game platform is
Delta shown in the formula w The index is expressed as an optimized value index corresponding to each optimization stage of the game platform, w is expressed as each optimization stage, w is a1 or a2 or a3, a1, a2 and a3 are expressed as an early stage, a middle stage and a later stage, eta' w i′ The influence weight of the registration duration corresponding to each registered user in each optimization stage is represented, i 'is the number of each registered user corresponding to each optimization stage, i' is 1 ', 2',. m ', m' is less than or equal to m,
representing the influence weight of the account type corresponding to each registered user in each optimization stage,
in a possible design, in the step 4, each preset optimization direction corresponding to the game platform is analyzed, and a specific analysis process includes the following steps:
acquiring feedback information corresponding to each registered user in the game platform when the registered user feeds back the problem, and positioning a feedback mode corresponding to each registered user when the registered user feeds back the problem, wherein the feedback modes comprise a voice feedback mode and a text feedback mode, and recording influence weights corresponding to the voice feedback modes as
Recording the influence weight corresponding to the text feedback mode as
The influence weight corresponding to the feedback mode of each registered user in each feedback problem is obtained and recorded as
Take a value of
And
t is a number corresponding to each feedback problem, and t is 1, 2.
Identifying feedback information corresponding to each registered user in each feedback problem to obtain each feedback keyword corresponding to each registered user in each feedback problem, extracting an associated keyword set corresponding to each preset optimization direction from a game optimization information base based on each preset optimization direction corresponding to a game platform, and further analyzing to obtain the matching degree of each feedback problem of each registered user and each preset optimization direction;
comparing the matching degree of each feedback problem of each registered user with a preset standard matching degree based on the matching degree of each preset optimization direction, and if the matching degree of a certain feedback problem of a certain registered user with a certain preset optimization direction is greater than or equal to the preset standard matching degree, taking the preset optimization direction as the matching preset optimization direction corresponding to the feedback problem of the registered user, so as to respectively obtain the matching preset optimization direction corresponding to each registered user when feeding back the problem;
and analyzing and obtaining the optimization value index corresponding to each preset optimization direction based on the corresponding matching preset optimization direction of each registered user in each feedback problem.
In a possible design, the identifying the feedback information corresponding to each registered user when feeding back the question includes identifying the feedback information corresponding to each feedback question in a voice feedback mode and identifying the feedback information corresponding to each feedback question in a text feedback mode.
In one possible design, the analyzing step obtains an optimization value index corresponding to each preset optimization direction, and the specific analyzing step includes the following steps:
on the basis of the matching preset optimization direction corresponding to each registered user in each feedback problem, comparing the matching preset optimization directions corresponding to each registered user in each feedback problem with each other, and screening to obtain the comprehensive feedback times corresponding to each preset optimization direction;
obtaining a feedback mode corresponding to the preset optimization direction matched with each time of the registered user when feeding back the problem based on the feedback mode corresponding to each time of the registered user when feeding back the problem and the preset optimization direction matched with each time of the registered user when feeding back the problem;
comparing feedback modes corresponding to the preset optimization directions correspondingly matched with each registered user during each feedback problem, screening to obtain comprehensive feedback times corresponding to each feedback mode in each preset optimization direction, analyzing to obtain a main body feedback mode corresponding to each preset optimization direction based on the comprehensive feedback times corresponding to each feedback mode in each preset optimization direction, obtaining influence weights corresponding to the main body feedback modes in each preset optimization direction based on the influence weights corresponding to each feedback mode, and recording the influence weights as influence weights corresponding to the main body feedback modes in each preset optimization direction
The optimization value index corresponding to each preset optimization direction is calculated by using a calculation formula
Wherein, according to the formula shown in the formula, λ j Expressed as the optimization value index, R, corresponding to the jth preset optimization direction j Expressed as the number of integrated feedback times, R, corresponding to the jth preset optimization direction j ' is expressed as a set reference feedback number corresponding to the jth preset optimization direction.
A second aspect of the present invention provides a game operation count analysis system, including:
the user basic registration information acquisition module is used for acquiring the number of registered users corresponding to the game platform and the basic registration information corresponding to each registered user;
the user feedback data extraction module is used for extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data corresponding to each registered user comprises the feedback problem times corresponding to each registered user and feedback information corresponding to each registered user during each feedback problem;
the optimization weight setting module is used for acquiring each preset optimization direction corresponding to the game platform and performing optimization weight setting according to the preset optimization direction corresponding to the game platform;
the operation optimization analysis module is used for analyzing each optimization stage and each preset optimization direction corresponding to the game platform respectively based on the basic registration information corresponding to each registered user and the feedback data corresponding to each registered user, and outputting a key optimization stage and a key optimization direction corresponding to the game platform;
the game optimization information base is used for storing the associated keyword sets corresponding to the preset optimization directions;
and the feedback terminal is used for feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
A third aspect of the present invention provides a storage medium, where a computer program is burned in the storage medium, and when the computer program runs in a memory of a server, the method of the present invention is implemented.
Compared with the prior art, the invention has the following beneficial effects:
according to the game operation data analysis method, the key optimization stage and the key optimization direction corresponding to the game platform are analyzed based on the basic registration information corresponding to each registered user in the game platform and the feedback data corresponding to each registered user, so that the problem that the analysis is not performed from the user experience sense level in the prior art is effectively solved, the problems of the current game platform are highlighted, and a reliable reference basis is provided for the improvement of the game platform; on one hand, by analyzing the feedback data corresponding to each registered user, the subjective feeling of the user on the platform is visually displayed, a clear direction is provided for the optimization of the game platform, and the viscosity and the loyalty of the user and the game platform are greatly improved; on the other hand, the game stage of the user is analyzed, the game requirements corresponding to the user in different game stages are reflected, the game experience of the user in different game stages is greatly improved, and decision-making reference data is provided for positioning in the optimization stage of the game platform, so that the operation efficiency of the game platform is effectively improved to a certain extent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the steps of the method of the present invention;
FIG. 2 is a schematic diagram of the connection of modules of the system according to the method of the present invention.
Detailed Description
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Example one
Referring to fig. 1, the present invention provides a game operation data analysis method, which includes the following steps:
step 1, obtaining user registration information: acquiring the number of registered users corresponding to a game platform and basic registration information corresponding to each registered user, numbering each registered user according to a preset sequence, and sequentially marking the registered users as 1,2,. i,. m;
specifically, the basic registration information corresponding to each registered user includes registration duration and registration account information, where the registration account information includes a type corresponding to a registration account and a game stage in which the registration account is located, the registration account types include a common type and a member type, and the game stage includes an early stage, a middle stage and a later stage.
Step 2, extracting user feedback data: extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data specifically comprises the number of feedback problems corresponding to each registered user and feedback information corresponding to each registered user during each feedback problem;
it should be noted that the feedback information includes a feedback mode and feedback content.
Step 3, optimizing the direction weight setting: acquiring each preset optimization direction corresponding to the game platform, setting optimization weights according to each preset optimization direction corresponding to the game platform, numbering each preset optimization direction corresponding to the game platform according to a preset sequence, and sequentially marking the directions as 1,2,. j,. n;
illustratively, the optimal weight setting is performed according to each preset optimal direction corresponding to the game platform, and the specific setting process is as follows:
acquiring each preset optimization direction corresponding to the game platform, wherein the preset optimization directions comprise user experience, story flow, interactive operation, game performance and game memory;
recording the optimization weight corresponding to user experience in the game platform as epsilon 1, recording the optimization weight corresponding to story flow as epsilon 2, recording the optimization weight corresponding to interactive operation as epsilon 3, recording the optimization weight corresponding to game performance as epsilon 4, and recording the optimization weight corresponding to game memory as epsilon 5, thus respectively obtaining the optimization weights corresponding to all preset optimization directions in the game platform in the mode, and recording the optimization weights as epsilon j J represents a number corresponding to each preset optimization direction, and j is 1, 2.
Step 4, analyzing platform optimization information: analyzing each optimization stage and each preset optimization direction corresponding to the game platform respectively based on basic registration information corresponding to each registered user and feedback data corresponding to each registered user, counting optimization value indexes corresponding to each optimization stage of the game platform and optimization value indexes corresponding to each preset optimization direction of the game platform respectively, matching and comparing the optimization value indexes corresponding to each optimization stage of the game platform with a set standard optimization value index, if the optimization value index corresponding to a certain optimization stage in the game platform reaches the set standard optimization value index, taking the optimization stage as a key optimization stage corresponding to the game platform, matching and comparing the optimization value indexes corresponding to each preset optimization direction of the game platform with the set standard optimization value index, if the optimization value index corresponding to a certain preset optimization direction in the game platform reaches the set standard optimization value index, taking the preset optimization direction as a key optimization direction corresponding to the game platform;
illustratively, the analyzing is performed at each optimization stage of the game platform, and the specific analyzing process includes the following steps:
p1, extracting registration time length from the basic registration information corresponding to each registered user, comparing the registration time length corresponding to each registered user with the set platform reference registration time length, calculating the registration time length influence weight corresponding to each registered user, and recording as eta i I denotes a number corresponding to each registered user, i 1,2，
T in the formula i Expressed as the registration duration, T, corresponding to the ith registered user Reference to Expressed as a set platform reference registration duration;
p2, extracting the registered account information from the basic registered information corresponding to each registered user, further extracting the type corresponding to the registered account from the registered account information corresponding to each registered user, if the registered account type corresponding to the registered user is a common type, recording the account influence weight corresponding to the registered user as σ 1, if the registered account type corresponding to the registered user is a member type, recording the account influence weight corresponding to the registered user as σ 2, thereby respectively obtaining the account type influence weight corresponding to each registered user, and recording the account type influence weight as σ 2 i Wherein σ is i The value is sigma 1 or sigma 2, and sigma 2 is more than sigma 1;
p3, extracting the game stage of the registered account from the registered account information corresponding to each registered user, further acquiring the game stage of the account corresponding to each registered user, comparing the game stages of the accounts corresponding to each registered user with each other, counting the number of the registered users corresponding to each game stage, taking each game stage as an optimization stage, and extracting the registration duration influence weight and the account type influence weight corresponding to each registered user in each optimization stage;
p4, accumulating to obtain the times of the comprehensive feedback problems corresponding to each optimization stage based on the times of the feedback problems corresponding to each registered user and the number of the registered users corresponding to each optimization stage, and calculating the times of the comprehensive feedback problems corresponding to each optimization stage to obtain the optimization value index corresponding to each optimization stage of the game platform, wherein the specific calculation formula is
According to the formula, δ w The index is expressed as the optimized value index corresponding to the first optimized stage of the game platform, w represents each optimized stage, w is a1, a2, a3, a1, a2 and a3 are expressed as early stage, middle stage, low stage, high stage, low stage, high stage, low stage, high stage, low stage, high stage, low stage, high-grade, and low grade,In the later stage of the process,
the influence weight of the registration duration corresponding to each registered user in each optimization stage is represented, i 'is the number of each registered user corresponding to each optimization stage, i' is 1 ', 2',. m ', m' is less than or equal to m,
representing the influence weight of the account type corresponding to each registered user in each optimization stage,
in another example, the analyzing of each preset optimization direction corresponding to the game platform includes the following steps:
y1, obtaining feedback information corresponding to each registered user in the game platform when feeding back problems, and locating feedback modes corresponding to each registered user when feeding back problems, wherein the feedback modes comprise a voice feedback mode and a text feedback mode, and the influence weight corresponding to the voice feedback mode is recorded as
Recording the influence weight corresponding to the text feedback mode as
The influence weight corresponding to the feedback mode when each registered user feeds back the problem is obtained and recorded as
Take a value of
And
t is a number corresponding to each feedback problem, and t is 1, 2.
Y2, identifying feedback information corresponding to each registered user in each feedback problem to obtain each feedback keyword corresponding to each registered user in each feedback problem, extracting an associated keyword set corresponding to each preset optimization direction from a game optimization information base based on each preset optimization direction corresponding to the game platform, and further analyzing to obtain the matching degree of each feedback problem of each registered user and each preset optimization direction;
it should be noted that, the identification of the feedback information corresponding to each registered user in each feedback question includes identification of the feedback information corresponding to each feedback question in the voice feedback mode and identification of the feedback information corresponding to each feedback question in the text feedback mode, when the corresponding feedback mode of a certain registered user is a voice feedback mode when the problem is fed back at a certain time, converting the feedback content of the user corresponding to the problem in the feedback into a text form by a voice recognition technology, performing keyword recognition on the text form by combining the text recognition technology and a keyword extraction technology to obtain each feedback keyword corresponding to the problem in the feedback by the registered user, when a corresponding feedback mode of a certain registered user is a text feedback mode when the certain registered user feeds back a problem at a certain time, obtaining each feedback keyword corresponding to the registered user at the feedback problem by a text recognition technology and a keyword extraction technology;
it should be further noted that the speech recognition technology, the text recognition technology, and the keyword extraction technology described above are existing mature technologies, and the specific recognition and operation processes are not described herein again.
Further, the specific analysis process of the matching degree between each feedback problem of each registered user and each preset optimization direction is as follows:
y2-1, constructing the feedback question of each registered user at each time based on the corresponding feedback keyword of each registered user at each time of feeding back the questionThe time corresponding feedback keyword set is marked as F i t ＝{F i t 1,F i t 2,...F i t s,...F i t p}，F i t s represents the s-th feedback keyword corresponding to the ith user during the t-th feedback, s represents the number corresponding to each feedback keyword, and s is 1, 2.
Y2-2, and recording the associated keyword set corresponding to each preset optimization direction as H j ＝{H j 1,H j 2,...H j u,...H j v}，H j u represents a corresponding u-th associated keyword in a j-th preset optimization direction, u represents a number corresponding to each associated keyword, and u is 1, 2.... times.v;
y2-3, analyzing the matching degree of each feedback problem and each preset optimization direction of each registered user based on the feedback keyword set corresponding to each registered user in each feedback problem and the associated keyword set corresponding to each preset optimization direction, wherein the specific analysis formula is
According to what is shown in the formula,
and the matching degree of the ith feedback problem of the ith registered user and j preset optimization directions is represented.
Y3, comparing the matching degree of each feedback problem of each registered user with each preset optimization direction with a preset standard matching degree, and if the matching degree of a certain feedback problem of a certain registered user with a certain preset optimization direction is greater than or equal to the preset standard matching degree, taking the preset optimization direction as the matching preset optimization direction corresponding to the feedback problem of the registered user, so as to respectively obtain the matching preset optimization directions corresponding to the feedback problems of each registered user;
y4, analyzing and obtaining the optimization value index corresponding to each preset optimization direction based on the corresponding matching preset optimization direction of each registered user in each feedback problem, wherein the specific analysis process comprises the following steps:
on the basis of the matching preset optimization direction corresponding to each registered user in each feedback problem, comparing the matching preset optimization directions corresponding to each registered user in each feedback problem with each other, and screening to obtain the comprehensive feedback times corresponding to each preset optimization direction;
obtaining a feedback mode corresponding to the preset optimization direction matched with each time of the registered user when feeding back the problem based on the feedback mode corresponding to each time of the registered user when feeding back the problem and the preset optimization direction matched with each time of the registered user when feeding back the problem;
comparing feedback modes corresponding to preset optimization directions and correspondingly matched with each registered user during each feedback problem, screening to obtain comprehensive feedback times corresponding to each feedback mode in each preset optimization direction, sequencing the comprehensive feedback times corresponding to each feedback mode in each preset optimization direction from big to small, extracting a feedback mode ranked first in each optimization direction, taking the feedback mode as a main body feedback mode corresponding to each optimization direction, obtaining influence weights corresponding to the main body feedback modes in each preset optimization direction based on the influence weights corresponding to each feedback mode, and recording the influence weights as main body feedback modes
The optimization value index corresponding to each preset optimization direction is calculated by using a calculation formula
Wherein, according to the formula shown in the formula, λ j Expressed as the optimization value index, R, corresponding to the jth preset optimization direction j Expressed as the number of integrated feedback times, R, corresponding to the jth preset optimization direction j ' is expressed as a set reference feedback number corresponding to the jth preset optimization direction.
According to the embodiment of the invention, the key optimization stage and the key optimization direction corresponding to the game platform are analyzed based on the basic registration information corresponding to each registered user in the game platform and the feedback data corresponding to each registered user, so that on one hand, the problem that the analysis is not performed from the user experience level in the prior art is effectively solved, the problems existing in the current game platform are highlighted, and a reliable reference basis is provided for the self perfection of the game platform; on one hand, by analyzing the feedback data corresponding to each registered user, the subjective feeling of the user on the platform is visually displayed, a clear direction is provided for the optimization of the game platform, and the viscosity and the loyalty of the user and the game platform are greatly improved; on the other hand, the game stage of the user is analyzed, the game requirements corresponding to the user in different game stages are reflected, the game experience of the user in different game stages is greatly improved, and decision-making reference data is provided for positioning in the optimization stage of the game platform, so that the operation efficiency of the game platform is effectively improved to a certain extent.
Step 5, analysis result feedback: and feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
Example two
Referring to fig. 2, the present invention provides a game operation data analysis system, which includes a user basic registration information obtaining module, a user feedback data extracting module, an optimization weight setting module, an operation optimization parsing module, a game optimization information base and a feedback terminal;
according to the connection relation shown in the figure, the operation optimization analysis module is respectively connected with a user basic registration information acquisition module, a user feedback data extraction module, an optimization weight setting module, a game optimization information base and a feedback terminal;
the user basic registration information acquisition module is used for acquiring the number of registered users corresponding to the game platform and the basic registration information corresponding to each registered user;
the user feedback data extraction module is used for extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data corresponding to each registered user comprises the feedback problem times corresponding to each registered user and feedback information corresponding to each registered user during each feedback problem;
the optimization weight setting module is used for acquiring each preset optimization direction corresponding to the game platform and performing optimization weight setting according to the preset optimization direction corresponding to the game platform;
the operation optimization analysis module is used for respectively analyzing each optimization stage and each preset optimization direction corresponding to the game platform based on the basic registration information corresponding to each registered user and the feedback data corresponding to each registered user, and outputting a key optimization stage and a key optimization direction corresponding to the game platform;
the game optimization information base is used for storing the associated keyword sets corresponding to the preset optimization directions;
and the feedback terminal is used for feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
EXAMPLE III
The invention also provides a computer storage medium, wherein the storage medium is burned with a computer program, and the computer program realizes the method of the invention when running in the memory of the server.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
Claims (10)
1. A game play data analysis method, comprising:
step 1, obtaining user registration information: acquiring the number of registered users corresponding to a game platform and basic registration information corresponding to each registered user, numbering each registered user according to a preset sequence, and sequentially marking the registered users as 1,2,. i,. m;
step 2, extracting user feedback data: extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data specifically comprises the number of feedback problems corresponding to each registered user and feedback information corresponding to each registered user during each feedback problem;
step 3, optimizing the direction weight setting: acquiring each preset optimization direction corresponding to the game platform, setting optimization weights according to each preset optimization direction corresponding to the game platform, numbering each preset optimization direction corresponding to the game platform according to a preset sequence, and sequentially marking the directions as 1,2,. j,. n;
step 4, analyzing platform optimization information: analyzing each optimization stage and each preset optimization direction corresponding to the game platform respectively based on basic registration information corresponding to each registered user and feedback data corresponding to each registered user, counting optimization value indexes corresponding to each optimization stage of the game platform and optimization value indexes corresponding to each preset optimization direction of the game platform respectively, matching and comparing the optimization value indexes corresponding to each optimization stage of the game platform with a set standard optimization value index, if the optimization value index corresponding to a certain optimization stage in the game platform reaches the set standard optimization value index, taking the optimization stage as a key optimization stage corresponding to the game platform, matching and comparing the optimization value indexes corresponding to each preset optimization direction of the game platform with the set standard optimization value index, if the optimization value index corresponding to a certain preset optimization direction in the game platform reaches the set standard optimization value index, taking the preset optimization direction as a key optimization direction corresponding to the game platform;
step 5, analysis result feedback: and feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
2. A game play data analysis method according to claim 1, wherein: the basic registration information corresponding to each registered user comprises registration time and registration account information, wherein the registration account information comprises types corresponding to the registration accounts and game stages of the registration accounts, the types of the registration accounts comprise common types and member types, and the game stages comprise an early stage, a middle stage and a later stage.
3. A game play data analysis method according to claim 1, wherein: the optimization weight setting is carried out according to each preset optimization direction corresponding to the game platform, and the specific setting process is as follows:
acquiring each preset optimization direction corresponding to the game platform, wherein the preset optimization directions comprise user experience, story flow, interactive operation, game performance and game memory;
recording the optimization weight corresponding to user experience in the game platform as epsilon 1, recording the optimization weight corresponding to story flow as epsilon 2, recording the optimization weight corresponding to interactive operation as epsilon 3, recording the optimization weight corresponding to game performance as epsilon 4, and recording the optimization weight corresponding to game memory as epsilon 5, thus respectively obtaining the optimization weights corresponding to all preset optimization directions in the game platform in the mode, and recording the optimization weights as epsilon j J represents a number corresponding to each preset optimization direction, and j is 1, 2.
4. A game play data analysis method according to claim 1, wherein: in the step 4, each optimization stage corresponding to the game platform is analyzed, and the specific analysis process comprises the following steps:
extracting registration time length from the basic registration information corresponding to each registered user, comparing the registration time length corresponding to each registered user with the set platform reference registration time length, calculating the registration time length influence weight corresponding to each registered user, and recording the weight as eta i I represents a number corresponding to each registered user, i is 1, 2.
Extracting registration account information from the basic registration information corresponding to each registered user, further extracting the type corresponding to the registration account from the registration account information corresponding to each registered user, if the registration account type corresponding to the registered user is a common type, recording the account influence weight corresponding to the registered user as sigma 1, if the account type corresponding to the registered user is a member type, recording the account influence weight corresponding to the registered user as sigma 2, thereby respectively obtaining the account type influence weight corresponding to each registered user, and recording the account type influence weight as sigma 2 i Wherein σ is i The value is sigma 1 or sigma 2, and sigma 2 is more than sigma 1;
extracting a game stage of a registered account from registered account information corresponding to each registered user, further acquiring a game stage of the account corresponding to each registered user, comparing the game stages of the accounts corresponding to each registered user with each other, counting the number of the registered users corresponding to each game stage, taking each game stage as an optimization stage, and extracting a registration duration influence weight and an account type influence weight corresponding to each registered user in each optimization stage;
and accumulating to obtain the comprehensive feedback problem times corresponding to each optimization stage based on the feedback problem times corresponding to each registered user and the registered user number corresponding to each optimization stage, and calculating the comprehensive feedback problem times corresponding to each optimization stage to obtain the optimization value index corresponding to each optimization stage of the game platform.
5. The game play operation data analysis method according to claim 4, wherein: the optimization value index calculation formula corresponding to each optimization stage of the game platform is
Delta shown in the formula w The index is expressed as an optimized value index corresponding to each optimization stage of the game platform, w is expressed as each optimization stage, w is a1 or a2 or a3, a1, a2 and a3 are expressed as an early stage, a middle stage and a later stage, eta' w i′ The optimization method includes the steps of representing registration duration influence weights corresponding to all registered users in all optimization stages, representing i 'as numbers of all the registered users corresponding to all the optimization stages, wherein i' is 1 'and 2'. w i′ Representing account number type influence weight, sigma ', corresponding to each registered user in each optimization stage' w i′ ∈{σ1,σ2}。
6. A game play data analysis method according to claim 1, wherein: in the step 4, each preset optimization direction corresponding to the game platform is analyzed, and the specific analysis process comprises the following steps:
obtaining the correspondence of each registered user in the game platform during each feedback problemThe feedback information of the registered users is used for positioning the corresponding feedback modes of the registered users in each feedback problem, wherein the feedback modes comprise a voice feedback mode and a text feedback mode, and the influence weights corresponding to the voice feedback modes are recorded as
Recording the influence weight corresponding to the text feedback mode as
The influence weight corresponding to the feedback mode of each registered user in each feedback problem is obtained and recorded as
Take a value of
And
t is a number corresponding to each feedback problem, and t is 1, 2.
Identifying feedback information corresponding to each registered user when each registered user feeds back the problem to obtain each feedback keyword corresponding to each registered user when each registered user feeds back the problem, extracting a related keyword set corresponding to each preset optimization direction from a game optimization information base based on each preset optimization direction corresponding to a game platform, and analyzing to obtain the matching degree of each feedback problem of each registered user and each preset optimization direction;
comparing the matching degree of each feedback problem of each registered user with a preset standard matching degree based on the matching degree of each preset optimization direction, and if the matching degree of a certain feedback problem of a certain registered user with a certain preset optimization direction is greater than or equal to the preset standard matching degree, taking the preset optimization direction as the matching preset optimization direction corresponding to the feedback problem of the registered user, so as to respectively obtain the matching preset optimization direction corresponding to each registered user when feeding back the problem;
and analyzing and obtaining the optimization value index corresponding to each preset optimization direction based on the corresponding matching preset optimization direction of each registered user in each feedback problem.
7. The game play operation data analysis method according to claim 6, wherein: the step of identifying the feedback information corresponding to each registered user in each problem feedback comprises the step of identifying the feedback information corresponding to each feedback problem in a voice feedback mode and the step of identifying the feedback information corresponding to each feedback problem in a text feedback mode.
8. The game play operation data analysis method according to claim 6, wherein: the analysis is carried out to obtain the optimization value index corresponding to each preset optimization direction, and the specific analysis process comprises the following steps:
on the basis of the matching preset optimization direction corresponding to each registered user in each feedback problem, comparing the matching preset optimization directions corresponding to each registered user in each feedback problem with each other, and screening to obtain the comprehensive feedback times corresponding to each preset optimization direction;
obtaining a feedback mode corresponding to the preset optimization direction matched with each time of the registered user when feeding back the problem based on the feedback mode corresponding to each time of the registered user when feeding back the problem and the preset optimization direction matched with each time of the registered user when feeding back the problem;
comparing feedback modes corresponding to the preset optimization directions correspondingly matched with each registered user during each feedback problem, screening to obtain comprehensive feedback times corresponding to each feedback mode in each preset optimization direction, analyzing to obtain a main body feedback mode corresponding to each preset optimization direction based on the comprehensive feedback times corresponding to each feedback mode in each preset optimization direction, obtaining influence weights corresponding to the main body feedback modes in each preset optimization direction based on the influence weights corresponding to each feedback mode, and recording the influence weights as influence weights corresponding to the main body feedback modes in each preset optimization direction
The optimization value index corresponding to each preset optimization direction is calculated by using a calculation formula
Wherein λ is according to the formula j Expressed as the optimization value index, R, corresponding to the jth preset optimization direction j Is expressed as the comprehensive feedback times, R ', corresponding to the jth preset optimization direction' j And expressing the set reference feedback times corresponding to the jth preset optimization direction.
9. A game play data analysis system, comprising:
the user basic registration information acquisition module is used for acquiring the number of registered users corresponding to the game platform and the basic registration information corresponding to each registered user;
the user feedback data extraction module is used for extracting feedback data corresponding to each registered user from the game platform background, wherein the feedback data corresponding to each registered user comprises the feedback problem times corresponding to each registered user and the feedback information corresponding to each registered user during each feedback problem;
the optimization weight setting module is used for acquiring each preset optimization direction corresponding to the game platform and performing optimization weight setting according to the preset optimization direction corresponding to the game platform;
the operation optimization analysis module is used for respectively analyzing each optimization stage and each preset optimization direction corresponding to the game platform based on the basic registration information corresponding to each registered user and the feedback data corresponding to each registered user, and outputting a key optimization stage and a key optimization direction corresponding to the game platform;
the game optimization information base is used for storing the associated keyword sets corresponding to the preset optimization directions;
and the feedback terminal is used for feeding back the key optimization stage and the key optimization direction corresponding to the game platform background.
10. A storage medium, characterized by: the storage medium is burned with a computer program, which when run in the memory of the server implements the method of any of the preceding claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450364.4A CN114939276B (en) | 2022-04-26 | 2022-04-26 | Game operation data analysis method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450364.4A CN114939276B (en) | 2022-04-26 | 2022-04-26 | Game operation data analysis method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114939276A true CN114939276A (en) | 2022-08-26 |
| CN114939276B CN114939276B (en) | 2023-08-01 |
Family
ID=82907696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210450364.4A Active CN114939276B (en) | 2022-04-26 | 2022-04-26 | Game operation data analysis method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114939276B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101247251A (en) * | 2008-03-13 | 2008-08-20 | 腾讯科技（深圳）有限公司 | System and method for internet service resource popularization |
| GB201514927D0 (en) * | 2015-08-21 | 2015-10-07 | Senseye Ltd | User feedback for machine learning |
| CN107229658A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | Problem feedback information processing method and processing device |
| CN107851093A (en) * | 2015-06-30 | 2018-03-27 | 微软技术许可有限责任公司 | The text of free form is handled using semantic hierarchy structure |
| CN109446309A (en) * | 2018-10-30 | 2019-03-08 | 天津字节跳动科技有限公司 | Problem feedback method and device |
| US20190143216A1 (en) * | 2017-11-15 | 2019-05-16 | International Business Machines Corporation | Cognitive user experience optimization |
| 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 |
| WO2021207269A1 (en) * | 2020-04-07 | 2021-10-14 | Assia Spe, Llc | Systems and methods for remote collaboration |
-
2022
- 2022-04-26 CN CN202210450364.4A patent/CN114939276B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101247251A (en) * | 2008-03-13 | 2008-08-20 | 腾讯科技（深圳）有限公司 | System and method for internet service resource popularization |
| CN107851093A (en) * | 2015-06-30 | 2018-03-27 | 微软技术许可有限责任公司 | The text of free form is handled using semantic hierarchy structure |
| GB201514927D0 (en) * | 2015-08-21 | 2015-10-07 | Senseye Ltd | User feedback for machine learning |
| CN107229658A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | Problem feedback information processing method and processing device |
| US20190143216A1 (en) * | 2017-11-15 | 2019-05-16 | International Business Machines Corporation | Cognitive user experience optimization |
| CN109446309A (en) * | 2018-10-30 | 2019-03-08 | 天津字节跳动科技有限公司 | Problem feedback method and device |
| 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 |
| WO2021207269A1 (en) * | 2020-04-07 | 2021-10-14 | Assia Spe, Llc | Systems and methods for remote collaboration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114939276B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209844B (en) | Multimedia data matching method, device and storage medium | |
| CN110162593A (en) | A kind of processing of search result, similarity model training method and device | |
| US8204837B2 (en) | Information processing apparatus and method, and program for providing information suitable for a predetermined mood of a user | |
| CN103034508B (en) | Software recommendation method and system | |
| CN110557659B (en) | Video recommendation method and device, server and storage medium | |
| CN109241255A (en) | A kind of intension recognizing method based on deep learning | |
| CN113127746B (en) | Information pushing method based on user chat content analysis and related equipment thereof | |
| CN111209363B (en) | Corpus data processing method, corpus data processing device, server and storage medium | |
| CN111050191B (en) | Video generation method and device, computer equipment and storage medium | |
| CN106951471A (en) | A kind of construction method of the label prediction of the development trend model based on SVM | |
| CN114238607B (en) | Deep interactive AI intelligent job-searching consultant method, system and storage medium | |
| CN115186654B (en) | Method for generating document abstract | |
| CN111061838A (en) | Text feature keyword determination method and device and storage medium | |
| CN114065720A (en) | Conference summary generation method and device, storage medium and electronic equipment | |
| CN112819499A (en) | Information transmission method, information transmission device, server and storage medium | |
| CN110633410A (en) | Information processing method and device, storage medium, and electronic device | |
| CN114939276A (en) | Game operation data analysis method, system and storage medium | |
| CN107423307A (en) | The distribution method and device of a kind of internet information resource | |
| CN110858234A (en) | Method and device for pushing information according to human emotion | |
| CN106446696A (en) | Information processing method and electronic device | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| CN110490667B (en) | Data processing method and device and electronic equipment | |
| CN107544978A (en) | A kind of content based video retrieval system method | |
| CN110263346A (en) | Lexical analysis method, electronic equipment and storage medium based on small-sample learning | |
| CN110535749A (en) | Talk with method for pushing, device, electronic equipment and storage 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 |