CN111672128A - Game mall game recommendation method and system based on local reserved time identification - Google Patents
Game mall game recommendation method and system based on local reserved time identification Download PDFInfo
- Publication number
- CN111672128A CN111672128A CN202010420120.2A CN202010420120A CN111672128A CN 111672128 A CN111672128 A CN 111672128A CN 202010420120 A CN202010420120 A CN 202010420120A CN 111672128 A CN111672128 A CN 111672128A
- Authority
- CN
- China
- Prior art keywords
- game
- user terminal
- user
- record
- game application
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000014759 maintenance of location Effects 0.000 claims abstract description 55
- 230000006399 behavior Effects 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 41
- 238000009434 installation Methods 0.000 claims description 23
- 238000005192 partition Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000000717 retained effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method 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
- A63F13/70—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The game mall game recommendation method and system based on local reserved time identification are characterized in that the method comprises the following steps: the method comprises the steps of collecting a history record and/or a current record of each recording user terminal aiming at local storage of game applications, calculating the retention time of each recording user terminal aiming at the game applications according to the history record and/or the current record to form a data set, clustering the data set according to game types and/or game names, calculating the average retention time of the game applications corresponding to the game types and/or the game names under each cluster, and recommending the game types and/or the game names with the average retention time within a first preset threshold value in a game mall of a target user terminal as a target object.
Description
Technical Field
The invention relates to the technical field of game recommendation, in particular to a game mall game recommendation method and system based on local reserved time length identification.
Background
Along with the continuous improvement of the living standard of people, the entertainment demand of people is higher and higher, and more people like playing terminal games in spare time. With the rapid development of the internet technology, various terminal games are distributed in a game mall; in order to enhance the user experience, it is often necessary to recommend terminal games of interest to the user in a game mall.
Currently in a game mall, the main ways of game recommendation include: recommending according to the downloading amount, recommending according to the online time of each game, analyzing the recommendation of the related games according to the preference of the user downloading games, and the like.
The disadvantages of these game recommendations are: the local storage time, namely the retention time of the game, of the user is not considered, for example, some users delete some games in a short time after downloading the games, some users delete the games in a short time after the online time of the games is high, or the users prefer to download certain types of games, but the games do not have high game experience, and the retention time is also short.
The factor of the reserved time length is not considered by the existing game recommendation mode, so that the accuracy of game recommendation is poor, and poor game recommendation experience is brought to the user.
Disclosure of Invention
The purpose of the invention is as follows:
in order to overcome the defects in the background art, the embodiment of the invention provides a game recommendation method and system for a game mall based on local reserved time length identification, which can effectively solve the problems related to the background art.
The technical scheme is as follows:
a game mall game recommendation method based on local reserve duration identification, the method comprising:
acquiring a history record and/or a current record of each recording user terminal aiming at local storage of the game application, wherein the history record comprises the installation time and the uninstallation time of the game application, and the current record comprises the installation time and the current time of the game application;
calculating the retention time of each recorded user terminal for the game application according to the historical record and/or the current record to form a data set;
clustering the data set according to the game category and/or the game name, and calculating the average retention time of the game application corresponding to the game category and/or the game name under each cluster;
and recommending the game category and/or the game name with the average retention time within a first preset threshold as a target object in a game mall of the target user terminal.
As a preferred mode of the present invention, the method further includes:
collecting a user behavior log in the target user terminal and storing the user behavior log in a first database;
collecting the user behavior logs in each recorded user terminal and storing the partitions of the user behavior logs in a second database;
respectively analyzing and training the user behavior logs in the first database and the user behavior logs of the partitions in the second database by using a Mahout algorithm, and outputting respective training results;
finding out a training result matched with the training result in each area of the second database according to the training result of the first database;
and acquiring each recorded user terminal corresponding to the training result matched with the recorded user terminal in the second database, reserving the reserved time length corresponding to the game application in the data set, and deleting the reserved time length corresponding to the game application of each unmatched recorded user terminal from the data set.
As a preferred mode of the present invention, the method further includes:
respectively acquiring the equipment performance information of the target user terminal and the recording user terminals, wherein the equipment performance information comprises the name, the model, the CPU model, the GPU model, the memory size, the hard disk size, the operating system model and the battery capacity of the equipment;
respectively calculating the performance values of the target terminal and each recording user terminal according to the equipment performance information;
comparing the performance value of the target terminal with the performance values of all the recording user terminals, screening out the recording user terminals with performance difference thresholds within a second preset threshold, reserving the retention time aiming at the game application corresponding to the recording user terminals with the performance difference thresholds not within the second preset threshold in the data set, and deleting the retention time aiming at the game application corresponding to the recording user terminals with the performance difference thresholds not within the second preset threshold from the data set.
As a preferred mode of the present invention, the collecting the history and/or current record of each recording user terminal for the local storage of the game-like application includes:
acquiring a user identifier of each recording user terminal;
judging whether the recording user terminal is a continuous terminal of the same user or not according to the user identification;
if yes, respectively acquiring a recording user terminal before connection and a locally stored historical record and/or a current record of the recording user terminal corresponding to the recording user terminal after connection aiming at the game application;
and overlapping the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, with the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, after connection, to obtain the history record and/or the current record of the user.
As a preferred mode of the present invention, the user identifier includes account information of at least one application.
A game mall game recommendation system based on local reserve duration identification, the system comprising:
the system comprises a record acquisition module, a storage module and a processing module, wherein the record acquisition module is used for acquiring a history record and/or a current record of each recording user terminal aiming at the local storage of the game application, the history record comprises the installation time and the uninstallation time of the game application, and the current record comprises the installation time and the current time of the game application;
the reserved time calculation module is used for calculating the reserved time of each recorded user terminal aiming at the game application according to the historical record and/or the current record to form a data set;
the data clustering module is used for clustering the data set according to the game category and/or the game name;
the average reserved time calculation module is used for calculating the average reserved time of the game application corresponding to the game category and/or the game name under each cluster;
and the game recommending module is used for recommending the game category and/or the game name of which the average reserved time is within a first preset threshold value in a game mall of the target user terminal as a target object.
As a preferred mode of the present invention, the system further includes:
the first behavior log collection module is used for collecting the user behavior logs in the target user terminal and storing the user behavior logs in a first database;
the first database is used for storing a user behavior log in the target user terminal;
the second behavior log collection module is used for collecting the user behavior logs in the user terminals and storing the partitions of the user behavior logs in a second database;
the second database is used for storing the user behavior logs in the user terminals in a partitioning manner;
the log training module is used for analyzing and training the user behavior logs in the first database and the user behavior logs in the partitions in the second database respectively by using a Mahout algorithm and outputting respective training results;
the training result matching module is used for finding out a training result matched with the training result in each area of the second database according to the training result of the first database;
and the first retention duration processing module is used for acquiring each recorded user terminal corresponding to the training result matched with the recorded user terminal in the second database, retaining the retention duration corresponding to the game application in the data set, and deleting the retention duration corresponding to the game application of each unmatched recorded user terminal from the data set.
As a preferred mode of the present invention, the system further includes:
a performance information obtaining module, configured to obtain device performance information of the target user terminal and each of the recording user terminals, respectively, where the device performance information includes a name, a model, a CPU model, a GPU model, a memory size, a hard disk size, an operating system model, and a battery capacity of a device;
a performance value calculation module, configured to calculate performance values of the target terminal and the user terminals according to the device performance information;
the performance comparison module is used for comparing the performance value of the target terminal with the performance value of each recorded user terminal;
and the second reserved time processing module is used for screening out the recorded user terminals with the performance difference threshold value within a second preset threshold value, reserving the reserved time aiming at the game application corresponding to the recorded user terminals with the performance difference threshold value not within the second preset threshold value in the data set, and deleting the reserved time aiming at the game application corresponding to the recorded user terminals with the performance difference threshold value not within the second preset threshold value from the data set.
As a preferred mode of the present invention, the record collection module includes:
the user identification acquisition module is used for acquiring the user identification of each recorded user terminal;
a connection terminal judging module, which is used for judging whether the recording user terminal is the connection terminal of the same user according to the user identification;
a record obtaining module, configured to, when the recording user terminal is a connection terminal of the same user, respectively obtain a history record and/or a current record of a local storage of the game application by the recording user terminal before connection and the recording user terminal after connection corresponding to the recording user terminal;
and the record overlapping module is used for overlapping the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, with the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application.
As a preferred mode of the present invention, the user identifier includes account information of at least one application.
The invention realizes the following beneficial effects:
1. according to the game recommendation method and device, the history records and/or the current records of the game applications locally stored by the recording user terminals are collected, the retention time of the game applications of the recording user terminals is calculated according to the records to form a data set, the data set is clustered according to the game types and/or the game names, the average retention time of the game applications corresponding to the game types and/or the game names under the clustering is calculated, then the game types and/or the game names with the average retention time within a first preset threshold value are taken as target objects to be recommended in a game mall of the target user terminal, and therefore the game applications can be recommended based on the judgment of the retention time, the game recommendation accuracy is effectively improved, and higher game recommendation experience is brought to users.
2. The method and the device can keep the retention time length for the game application corresponding to the recording user terminal matched with the preference of the target user terminal user in the data set, and delete the retention time length for the game application corresponding to each unmatched recording user terminal from the data set, so that the preference of the user corresponding to each recording user terminal for collecting the historical record and/or the current record is matched with the preference of the target user terminal user, and the game application recommendation accuracy is improved.
3. The method and the device can compare the performance value of the target terminal with the performance value of each recording user terminal, screen out the recording user terminals with the performance difference threshold value within the second preset threshold value, reserve the retention time aiming at the game application corresponding to the recording user terminals with the performance difference threshold value not within the second preset threshold value in the data set, and delete the retention time aiming at the game application corresponding to the recording user terminals with the performance difference threshold value not within the second preset threshold value from the data set, so that the difference between the performance value corresponding to each recording user terminal for collecting the historical record and/or the current record and the performance value for the target user terminal is smaller, and the accuracy of game application recommendation is improved.
4. The invention can fuse the history records and/or the current records of the same user in different terminals, which are locally stored aiming at the game application, as the history records and/or the current records of the user, thereby ensuring that the collected history records and/or the current records of each recording user terminal aiming at the local storage of the game application meet the actual requirements.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic flowchart of a game recommendation method for a game mall based on local reserved duration identification according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a game recommendation method for a game mall based on local reserved duration identification according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart of a game recommendation method for a game mall based on local reserved duration identification according to a third embodiment of the present invention;
fig. 4 is a schematic flow chart of a game recommendation method for a game mall based on local reserved duration identification according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a first game mall game recommendation system identified based on local reserved time length according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a second game mall game recommendation system identified based on local reserved time length according to a fifth embodiment of the present invention;
fig. 7 is a schematic structural diagram of a third game mall game recommendation system identified based on a local reserved time length according to a fifth embodiment of the present invention;
fig. 8 is a schematic structural diagram of a fourth game mall game recommendation system identified based on a local retention time according to a fifth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example one
As shown with reference to fig. 1. The embodiment provides a game mall game recommendation method based on local reserved time length identification, which comprises the following steps of:
and S10, collecting a history record and/or a current record of each recording user terminal for the local storage of the game application, wherein the history record comprises the installation time and the uninstallation time of the game application, and the current record comprises the installation time and the current time of the game application.
The method provided by the present invention may be implemented by software installed or provided in the device, where the software may be an application program, such as a typical APP, or implemented by an operating system running in the device. The recording user terminal mentioned in the embodiment of the present invention refers to a terminal that has a history of installing a game application or has an installed game application, the target user terminal refers to a terminal waiting for game recommendation to the target user terminal, wherein the target user terminal may also be one of the recording user terminals, and the terminal mentioned in the embodiment of the present invention may specifically be an electronic device such as a mobile phone, a computer, a tablet, and the like.
In a specific implementation process, it is required to judge whether a game application is installed in a local storage space of a recording user terminal, and specifically, whether the game application exists can be identified by acquiring an icon and a name of each application, and if the game application is installed, acquiring a current record of the local storage of the game application, that is, acquiring installation time and current time of the game application, where the installation time may be application downloading time or application installation completion time.
If the game application is not installed in the local storage space of the user terminal, whether the game application is downloaded in the local storage space of the user terminal before is further judged, that is, a history of the local storage of the game application by the user terminal is obtained and recorded, specifically, when the game application is detected to be downloaded by the user in advance, once recording and archiving are performed (the installation time, the uninstallation time, the game information and the like are recorded), then in the embodiment of the invention, whether the installation history of the game application exists is judged by obtaining the archiving, and if the installation history and the uninstallation time of the game application exist, the installation history and the uninstallation time of the game application are obtained.
And S11, calculating the retention time of each recorded user terminal for the game application according to the history record and/or the current record to form a data set.
The mode of calculating and recording the retention time of the user terminal for the game application according to the history record is as follows: the unloading time minus the installation time, and the mode of calculating and recording the reserved time of the user terminal for the game application according to the current record is as follows: the current time minus the installation time.
In the embodiment of the present invention, the above time may be calculated in each time unit (for example, minutes, hours, days, etc.), and the present invention preferably calculates in days.
For example, the history of one of the recorded user terminals for one of the game applications is set as: if the installation time is 1 month and 1 day in 2020 year and the uninstallation time is 3 months and 1 day in 2020 year, the retention time for the game application can be obtained by calculation to be 60 days; setting the current record of the calendar of one record user terminal aiming at one game application as follows: if the installation time is 1 month and 1 day in 2020 and the current time is 1 month and 4 months in 2020, the retention time for the game application is 91 days by calculation.
After the data (the reserved duration for the game application) are acquired by each recording user terminal, the data are uploaded to the cloud for process storage, and a data set is formed.
S12, clustering the data set according to the game category and/or the game name, and calculating the average retention time of the game application corresponding to the game category and/or the game name under each cluster.
Wherein, the game category is divided into: actions, adventure, simulation, role-playing, leisure, and others.
In the embodiment of the invention, the data set is clustered according to the game category and/or the game name, that is, the retention durations corresponding to the game applications of which the game categories belong to the same category are gathered together, and/or the retention durations corresponding to the game applications of which the game names are the same are gathered together, and then the average retention duration of the game applications corresponding to the game categories and/or the game names in each cluster is calculated.
Specifically, the game category and/or the game name of each game application needs to be identified, then the corresponding retention time lengths are aggregated together based on the game category and/or the game name, and the average retention time length of the game applications corresponding to the game category and/or the game name under each cluster is calculated, where the average retention time length is an average value of all the retention time lengths aggregated together.
And S13, recommending the game category and/or the game name with the average retention time length within the first preset threshold value as a target object in the game mall of the target user terminal.
In the embodiment of the present invention, the first preset threshold may be set according to actual needs, and different values may be set for the game category and the game name, for example, 2 may be set for the game category, and 10 may be set for the game name.
That is, in the embodiment of the present invention, the game category whose average retention time period is within the top 2 is recommended as the target object in the game mall of the target user terminal, and the game name whose average retention time period is within the top 10 is recommended as the target object in the game mall of the target user terminal.
Example two
As shown with reference to fig. 2. In this embodiment, on the basis of the first embodiment, the method further includes the following steps:
S2O, collecting a user behavior log in the target user terminal and storing the user behavior log in a first database;
s21, collecting the user behavior logs in the recording user terminals and storing the user behavior logs in a second database in a partition mode;
s22, analyzing and training the user behavior logs in the first database and the user behavior logs in the partitions in the second database respectively by using a Mahout algorithm, and outputting respective training results;
s23, finding out a training result matched with the training result in each area of the second database according to the training result of the first database;
s24, obtaining each recording user terminal corresponding to the training result matched with the recording user terminal in the second database, keeping the corresponding retention time length for the game application in the data set, and deleting the retention time length for the game application corresponding to each unmatched recording user terminal from the data set.
In S20, when the user accesses the website or APP using the target user terminal, the user behavior log is collected by the user behavior log collection script code, and is sent through a predetermined protocol, and specifically sent to the first database for storage.
In S21, when the user accesses the website or APP using the recording user terminal, the user behavior log is collected by the user behavior log collection script code and sent through a predetermined protocol, and specifically sent to each area of the second database for storage.
In S22, the Mahout algorithm is used to analyze and train the user behavior logs in the first database and the user behavior logs in the partitions in the second database, respectively, that is, the user behavior logs in the first database are trained to find the preference of the target user terminal user, and the user behavior logs in the partitions in the second database are trained to find the preference of the users recording the partitions of the user terminal.
In S23, the preferences of the target user terminal user are matched with the preferences of the users in the respective areas of the recording user terminal to find corresponding matching results.
In S24, the retention period for the game-class application corresponding to the recording user terminal that matches the taste of the target user terminal user is retained in the data set, and the retention period for the game-class application corresponding to each recording user terminal that does not match is deleted from the data set.
EXAMPLE III
As shown with reference to fig. 3. In this embodiment, on the basis of the first embodiment, the method further includes the following steps:
s30, respectively acquiring the device performance information of the target user terminal and each recording user terminal, wherein the device performance information comprises the name, the model, the CPU model, the GPU model, the memory size, the hard disk size, the operating system model and the battery capacity of the device;
s31, respectively calculating the performance values of the target terminal and each recording user terminal according to the equipment performance information;
s32, comparing the performance value of the target terminal with the performance value of each recording user terminal, screening out the recording user terminals with the performance difference threshold value within a second preset threshold value, retaining the retention time for the game application corresponding to the recording user terminals with the performance difference threshold value not within the second preset threshold value in the data set, and deleting the retention time for the game application corresponding to the recording user terminals with the performance difference threshold value not within the second preset threshold value from the data set.
In the embodiment of the present invention, the name of the device may be understood as a brand name of the device, such as an iphone, a huaji mobile phone, a samsung mobile phone, and the like, and the model of the device may be understood as a specific model of the device, such as iphone11, huaji mate30pro, samsung S10, and the like.
The calculation mode of the performance value can be through running and dividing software to run and divide tests, thereby obtaining the performance value of each terminal.
In this embodiment of the present invention, the second preset threshold may be set according to actual needs, for example, it may be set to 5000 minutes, that is, in S32, when comparing the performance value of the target terminal with the performance values of the respective recording user terminals, the retention duration for the game application corresponding to the recording user terminal screened out to have a performance difference threshold with the performance value of the target terminal within 5000 minutes is retained in the data set, and the retention duration for the game application corresponding to the recording user terminal having a performance difference threshold not within 5000 minutes is deleted from the data set.
Example four
As shown with reference to fig. 4. In this embodiment, on the basis of the first embodiment, the step S10 specifically includes the following steps:
s40, acquiring the user identification of each recording user terminal;
s41, judging whether the recording user terminal is the connection terminal of the same user according to the user identification;
if yes, executing S42, and respectively obtaining the history record and/or the current record of the recording user terminal before connection and the recording user terminal after connection corresponding to the recording user terminal for the local storage of the game application;
and S43, overlapping the history and/or current record of the local storage of the game application by the recording user terminal before connection corresponding to the same user with the history and/or current record of the local storage of the game application by the recording user terminal after connection as the history and/or current record of the user.
The user identification comprises account information of at least one application, and the account information can represent the identity of the user and has a unique identity.
In S41, the specific determination method is: and judging whether the user identification has repeatability in each recording user terminal, and if so, considering that the user has a plurality of terminals.
For example, a user has multiple terminals simultaneously, or the terminals are replaced, in the former case, one of the terminals may be regarded as a recording user terminal before connection, and the other terminals are recording user terminals after connection; in the latter case, the terminal before replacement may be regarded as the recording user terminal before connection, and the terminal after replacement may be regarded as the recording user terminal after connection.
In S42, a history and/or a current record of the recording user terminal before the connection and the recording user terminal after the connection corresponding to the recording user terminal are obtained for the local storage of the game application, where the history and/or the current record obtained respectively refer to a history and/or a current record existing on a different terminal by the same user.
In S43, the history and/or current record of the recording user terminal before connection for the game application corresponding to the same user and the history and/or current record of the recording user terminal after connection for the game application are superimposed and used as the history and/or current record of the user, that is, the history and/or current record of the same user locally stored for the game application existing in different terminals are merged.
EXAMPLE five
As shown with reference to fig. 5-8. The embodiment provides a game mall game recommendation system based on local reserved time identification, which comprises:
a record collecting module 501, configured to collect a history record and/or a current record of each recording user terminal for local storage of the game application, where the history record includes an installation time and an uninstallation time of the game application, and the current record includes the installation time and the current time of the game application.
And a reserved time calculation module 502, configured to calculate reserved time of each recorded user terminal for the game application according to the history record and/or the current record, and form a data set.
A data clustering module 503, configured to cluster the data set according to the game category and/or the game name.
An average retention time calculation module 504, configured to calculate an average retention time of the game class application corresponding to the game class and/or the game name under each cluster.
And the game recommending module 505 is configured to recommend the game category and/or the game name of which the average remaining time is within the first preset threshold as the target object in the game mall of the target user terminal.
As a preferred mode of the present invention, the system further includes:
a first behavior log collecting module 506, configured to collect a user behavior log in the target user terminal and store the user behavior log in a first database 507.
A first database 507, configured to store a user behavior log in the target user terminal.
A second behavior log collecting module 508, configured to collect user behavior logs in the recording user terminals and store partitions of the user behavior logs in a second database 509.
And a second database 509, configured to store the user behavior logs in the record user terminals in a partitioned manner.
The log training module 510 is configured to analyze and train the user behavior logs in the first database 507 and the user behavior logs in the partitions in the second database 509 respectively by using a Mahout algorithm, and output respective training results.
The training result matching module 511 is configured to find a training result matching with the training result in each region of the second database 509 according to the training result of the first database 507.
The first remaining duration processing module 512 is configured to obtain each recorded user terminal corresponding to the training result matched with the recorded user terminal in the second database 509, retain the corresponding remaining duration for the game application in the data set, and delete the remaining duration for the game application corresponding to each unmatched recorded user terminal from the data set.
As a preferred mode of the present invention, the system further includes:
a performance information obtaining module 513, configured to obtain device performance information of the target user terminal and each of the recording user terminals, where the device performance information includes a name, a model, a CPU model, a GPU model, a memory size, a hard disk size, an operating system model, and a battery capacity of the device.
A performance value calculating module 514, configured to calculate performance values of the target terminal and the user terminals according to the device performance information.
A performance comparing module 515, configured to compare the performance value of the target terminal with the performance values of the recorded user terminals.
The second remaining duration processing module 516 is configured to screen out the recorded user terminals whose performance difference thresholds are within a second preset threshold, retain the remaining duration for the game application corresponding to the recorded user terminals whose performance difference thresholds are not within the second preset threshold in the data set, and delete the remaining duration for the game application corresponding to the recorded user terminals whose performance difference thresholds are not within the second preset threshold from the data set.
As a preferred mode of the present invention, the record acquisition module 501 includes:
a user identifier obtaining module 517, configured to obtain a user identifier of each recording user terminal.
A connection terminal determining module 518, configured to determine, according to the user identifier, whether the recorded user terminal is a connection terminal of the same user.
A record obtaining module 519, configured to, when the recording user terminal is a connection terminal of the same user, respectively obtain a history and/or a current record of the local storage of the game application by the recording user terminal before connection and the recording user terminal after connection corresponding to the recording user terminal.
A record overlapping module 520, configured to overlap a history and/or a current record of the recording user terminal corresponding to the same user, which is locally stored for the game application, with a history and/or a current record of the recording user terminal corresponding to the same user, which is locally stored for the game application, which is subsequently stored for the game application, as the history and/or the current record of the user.
As a preferred mode of the present invention, the user identifier includes account information of at least one application.
The implementation process of this embodiment is the same as that of the first, second, third, and fourth embodiments, and specific reference is made to the above.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (10)
1. A game mall game recommendation method based on local reserve duration identification is characterized by comprising the following steps:
acquiring a history record and/or a current record of each recording user terminal aiming at local storage of the game application, wherein the history record comprises the installation time and the uninstallation time of the game application, and the current record comprises the installation time and the current time of the game application;
calculating the retention time of each recorded user terminal for the game application according to the historical record and/or the current record to form a data set;
clustering the data set according to the game category and/or the game name, and calculating the average retention time of the game application corresponding to the game category and/or the game name under each cluster;
and recommending the game category and/or the game name with the average retention time within a first preset threshold as a target object in a game mall of the target user terminal.
2. The game mall game recommendation method based on local reserve duration identification according to claim 1, wherein the method further comprises:
collecting a user behavior log in the target user terminal and storing the user behavior log in a first database;
collecting the user behavior logs in each recorded user terminal and storing the partitions of the user behavior logs in a second database;
respectively analyzing and training the user behavior logs in the first database and the user behavior logs of the partitions in the second database by using a Mahout algorithm, and outputting respective training results;
finding out a training result matched with the training result in each area of the second database according to the training result of the first database;
and acquiring each recorded user terminal corresponding to the training result matched with the recorded user terminal in the second database, reserving the reserved time length corresponding to the game application in the data set, and deleting the reserved time length corresponding to the game application of each unmatched recorded user terminal from the data set.
3. The game mall game recommendation method based on local reserve duration identification according to claim 1, wherein the method further comprises:
respectively acquiring the equipment performance information of the target user terminal and the recording user terminals, wherein the equipment performance information comprises the name, the model, the CPU model, the GPU model, the memory size, the hard disk size, the operating system model and the battery capacity of the equipment;
respectively calculating the performance values of the target terminal and each recording user terminal according to the equipment performance information;
comparing the performance value of the target terminal with the performance values of all the recording user terminals, screening out the recording user terminals with performance difference thresholds within a second preset threshold, reserving the retention time aiming at the game application corresponding to the recording user terminals with the performance difference thresholds not within the second preset threshold in the data set, and deleting the retention time aiming at the game application corresponding to the recording user terminals with the performance difference thresholds not within the second preset threshold from the data set.
4. The game mall game recommendation method based on local duration of reservation identification according to claim 1, wherein the step of collecting the locally stored history and/or current records of each recording user terminal for the game-like applications comprises:
acquiring a user identifier of each recording user terminal;
judging whether the recording user terminal is a continuous terminal of the same user or not according to the user identification;
if yes, respectively acquiring a recording user terminal before connection and a locally stored historical record and/or a current record of the recording user terminal corresponding to the recording user terminal after connection aiming at the game application;
and overlapping the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, with the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, after connection, to obtain the history record and/or the current record of the user.
5. The game mall game recommendation method based on local reserved time identification as claimed in claim 4, wherein the user identifier comprises account information of at least one application.
6. A game mall game recommendation system based on local reserve duration identification, the system comprising:
the system comprises a record acquisition module, a storage module and a processing module, wherein the record acquisition module is used for acquiring a history record and/or a current record of each recording user terminal aiming at the local storage of the game application, the history record comprises the installation time and the uninstallation time of the game application, and the current record comprises the installation time and the current time of the game application;
the reserved time calculation module is used for calculating the reserved time of each recorded user terminal aiming at the game application according to the historical record and/or the current record to form a data set;
the data clustering module is used for clustering the data set according to the game category and/or the game name;
the average reserved time calculation module is used for calculating the average reserved time of the game application corresponding to the game category and/or the game name under each cluster;
and the game recommending module is used for recommending the game category and/or the game name of which the average reserved time is within a first preset threshold value in a game mall of the target user terminal as a target object.
7. The game mall game recommendation system identified based on local duration of reservation according to claim 6, further comprising:
the first behavior log collection module is used for collecting the user behavior logs in the target user terminal and storing the user behavior logs in a first database;
the first database is used for storing a user behavior log in the target user terminal;
the second behavior log collection module is used for collecting the user behavior logs in the user terminals and storing the partitions of the user behavior logs in a second database;
the second database is used for storing the user behavior logs in the user terminals in a partitioning manner;
the log training module is used for analyzing and training the user behavior logs in the first database and the user behavior logs in the partitions in the second database respectively by using a Mahout algorithm and outputting respective training results;
the training result matching module is used for finding out a training result matched with the training result in each area of the second database according to the training result of the first database;
and the first retention duration processing module is used for acquiring each recorded user terminal corresponding to the training result matched with the recorded user terminal in the second database, retaining the retention duration corresponding to the game application in the data set, and deleting the retention duration corresponding to the game application of each unmatched recorded user terminal from the data set.
8. The game mall game recommendation system identified based on local duration of reservation according to claim 6, further comprising:
a performance information obtaining module, configured to obtain device performance information of the target user terminal and each of the recording user terminals, respectively, where the device performance information includes a name, a model, a CPU model, a GPU model, a memory size, a hard disk size, an operating system model, and a battery capacity of a device;
a performance value calculation module, configured to calculate performance values of the target terminal and the user terminals according to the device performance information;
the performance comparison module is used for comparing the performance value of the target terminal with the performance value of each recorded user terminal;
and the second reserved time processing module is used for screening out the recorded user terminals with the performance difference threshold value within a second preset threshold value, reserving the reserved time aiming at the game application corresponding to the recorded user terminals with the performance difference threshold value not within the second preset threshold value in the data set, and deleting the reserved time aiming at the game application corresponding to the recorded user terminals with the performance difference threshold value not within the second preset threshold value from the data set.
9. The game mall game recommendation system identified based on local duration of reservation according to claim 6, wherein said record collection module comprises:
the user identification acquisition module is used for acquiring the user identification of each recorded user terminal;
a connection terminal judging module, which is used for judging whether the recording user terminal is the connection terminal of the same user according to the user identification;
a record obtaining module, configured to, when the recording user terminal is a connection terminal of the same user, respectively obtain a history record and/or a current record of a local storage of the game application by the recording user terminal before connection and the recording user terminal after connection corresponding to the recording user terminal;
and the record overlapping module is used for overlapping the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application, with the history record and/or the current record of the recording user terminal corresponding to the same user, which is stored locally for the game application.
10. The game mall game recommendation system according to claim 9, wherein the user identification comprises account information of at least one application.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010420120.2A CN111672128A (en) | 2020-05-18 | 2020-05-18 | Game mall game recommendation method and system based on local reserved time identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010420120.2A CN111672128A (en) | 2020-05-18 | 2020-05-18 | Game mall game recommendation method and system based on local reserved time identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111672128A true CN111672128A (en) | 2020-09-18 |
Family
ID=72451977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010420120.2A Pending CN111672128A (en) | 2020-05-18 | 2020-05-18 | Game mall game recommendation method and system based on local reserved time identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111672128A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131476A (en) * | 2020-09-27 | 2020-12-25 | 深圳市锐尔觅移动通信有限公司 | Application recommendation method, device, apparatus, terminal and readable storage medium |
| CN116485474A (en) * | 2023-04-29 | 2023-07-25 | 广州市安洛网络有限责任公司 | Accurate crowd of recreation advertisement is directional puts in system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514496A (en) * | 2012-06-21 | 2014-01-15 | 腾讯科技（深圳）有限公司 | Method and system for processing recommended target software |
| CN105045916A (en) * | 2015-08-20 | 2015-11-11 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Mobile game recommendation system and recommendation method thereof |
| CN105117440A (en) * | 2015-08-11 | 2015-12-02 | 北京奇虎科技有限公司 | Method and apparatus for determining to-be-recommended application (APP) |
| CN105991583A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Game application recommendation method, application server, terminal and system |
-
2020
- 2020-05-18 CN CN202010420120.2A patent/CN111672128A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514496A (en) * | 2012-06-21 | 2014-01-15 | 腾讯科技（深圳）有限公司 | Method and system for processing recommended target software |
| CN105991583A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Game application recommendation method, application server, terminal and system |
| CN105117440A (en) * | 2015-08-11 | 2015-12-02 | 北京奇虎科技有限公司 | Method and apparatus for determining to-be-recommended application (APP) |
| CN105045916A (en) * | 2015-08-20 | 2015-11-11 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Mobile game recommendation system and recommendation method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 方曙东、许桂秋, 浙江科学技术出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131476A (en) * | 2020-09-27 | 2020-12-25 | 深圳市锐尔觅移动通信有限公司 | Application recommendation method, device, apparatus, terminal and readable storage medium |
| CN112131476B (en) * | 2020-09-27 | 2023-12-08 | 深圳市锐尔觅移动通信有限公司 | Application recommendation method, device, apparatus, terminal and readable storage medium |
| CN116485474A (en) * | 2023-04-29 | 2023-07-25 | 广州市安洛网络有限责任公司 | Accurate crowd of recreation advertisement is directional puts in system |
| CN116485474B (en) * | 2023-04-29 | 2024-03-19 | 广州市安洛网络有限责任公司 | Accurate crowd of recreation advertisement is directional puts in system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107343047B (en) | Application promotion system and method | |
| CN112494952B (en) | Target game user detection method, device and equipment | |
| CN109947438B (en) | Game installation method based on machine learning, electronic equipment and readable storage medium | |
| CN111672128A (en) | Game mall game recommendation method and system based on local reserved time identification | |
| EP2897060A1 (en) | Subtitle processing method, device and system, and storage medium | |
| CN105701135A (en) | Application recommendation method and device | |
| CN103500177A (en) | Method and device for counting activated users | |
| CN110866249A (en) | Method and device for dynamically detecting malicious code and electronic equipment | |
| CN113688002A (en) | Log collection method and related device | |
| CN107102876B (en) | Application pushing method and device | |
| CN113254918A (en) | Information processing method, electronic device, and computer-readable storage medium | |
| CN116662351B (en) | Bank data acquisition method and system | |
| CN111683280A (en) | Video processing method and device and electronic equipment | |
| CN111144987A (en) | Abnormal shopping behavior limiting method, limiting assembly and shopping system | |
| CN113254919B (en) | Abnormal device identification method, electronic device, and computer-readable storage medium | |
| CN113747233B (en) | Music replacement method and device, electronic equipment and storage medium | |
| CN110752962A (en) | Monitoring method and device of advertisement interface | |
| CN110471926B (en) | File establishing method and device | |
| CN114513686A (en) | Method and device for determining video information and storage medium | |
| CN107453946B (en) | Field management method and device and electronic equipment | |
| CN111143377A (en) | Automatic driving simulation data collection method, device and system | |
| CN111127170A (en) | Method and device for purchasing medicines through intelligent medicine chest | |
| CN108763300B (en) | Data query method and device | |
| CN111105263A (en) | User identification method and device, electronic equipment and storage medium | |
| CN116861101B (en) | Data processing method and device for social matching |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200918 |