CN106445934A - Data processing method and apparatus - Google Patents
Data processing method and apparatus Download PDFInfo
- Publication number
- CN106445934A CN106445934A CN201510472894.9A CN201510472894A CN106445934A CN 106445934 A CN106445934 A CN 106445934A CN 201510472894 A CN201510472894 A CN 201510472894A CN 106445934 A CN106445934 A CN 106445934A
- Authority
- CN
- China
- Prior art keywords
- attribute
- application
- user
- dimension
- classification
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiments of the invention provide a data processing method and system. The method comprises the steps of collecting application log data of users, wherein the application log data is related to operation behaviors of the users to applications; for the users, analyzing attribute tendency information, in at least one dimension, of the applications in the application log data of the users; and predicting population attributes of the users according to the attribute tendency information of the applications, wherein each population attribute comprises a category corresponding to at least one dimension. The population attribute characteristics of the users are mined based on the applications, so that the processing efficiency is relatively high.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of data processing method and a kind of number
According to processing meanss.
Background technology
Application program (Application, APP) refers to various client software programs, and user makes
During with terminals such as such as smart mobile phone, panel computer and notebook computers, various applications generally can be installed
Program, executes various operations by application program, such as plays game, browses webpage, viewing video etc..
Third-party application platform can provide the user application, and that is, user can be in third-party application platform
Browse application, and download application.
Content of the invention
In view of the above problems it is proposed that the present invention is to provide one kind to overcome the problems referred to above or at least partly
The data processing method that solves the above problems and corresponding data processing equipment.
According to one aspect of the present invention, there is provided a kind of data processing method, including:Collect each user
Application daily record data, wherein, described application daily record data and user are related to the operation behavior applied;
For each user, respectively apply under at least one dimension in the application daily record data analyzing described user
Attribute trend information;Attribute trend information according to each application predicts the ascribed characteristics of population of described user, wherein,
The described ascribed characteristics of population includes the corresponding classification of at least one dimension.
Optionally, the described application daily record data collecting each user, including:For each user, collect
The operation behavior information to application for the described user, wherein, described operation behavior information includes:Download behavior
Information and/or navigation patterns information;Described operation behavior information is recorded, generates application daily record data,
Described application daily record data include each application log recording, described log recording include Download History and
/ or browse record.
Optionally, respectively apply under at least one dimension in the application daily record data of the described user of described analysis
Attribute trend information, including:Obtaining log recording determination from the application daily record data of described user should
With;For each dimension, search each log recording and apply in described dimension correspondence attribute of all categories
Propensity value, described classification and attribute propensity value are recorded as attribute trend information.
Optionally, the described attribute trend information according to each application predicts the ascribed characteristics of population of described user, bag
Include:For each dimension, the attribute trend information of the corresponding application of each log recording is counted, determines
Corresponding attribute propensity value of all categories;Choose the maximum classification of attribute propensity value as the population of described user
Attribute.
Optionally, when described log recording includes Download History and when browsing record, described each daily record is remembered
The attribute trend information of the corresponding application of record is counted, and determines corresponding attribute propensity value of all categories, including:
According to classification, the attribute propensity value of the corresponding application of Download History is added up, determine that each classification is corresponding
First attribute propensity value;According to classification, the attribute propensity value browsing the corresponding application of record is added up, really
The fixed corresponding second attribute propensity value of each classification;For each classification, belong to described first according to weight
Sexual orientation value and the second attribute propensity value are weighted suing for peace, as described classification corresponding attribute tendency
Value.
Optionally, also include:It is pre-configured with the ascribed characteristics of population tendency rule of application;Extract retouching of each application
State information, according to described ascribed characteristics of population tendency rule, described description information is analyzed, identifies each application
Attribute propensity value under each classification of each dimension.
Optionally, described dimension includes following at least one:Sex dimension, age dimension, academic dimension,
Purchasing power dimension, professional dimension and division of life span's dimension.
According to another aspect of the present invention, additionally provide a kind of data processing equipment, including:Daily record is received
Collection module, for collecting the application daily record data of each user, wherein, described application daily record data and user
Related to the operation behavior of application;Attribute trend analysis module, for for each user, analysis is described
The attribute trend information under at least one dimension is respectively applied in the application daily record data of user;The ascribed characteristics of population
Prediction module, for predicting the ascribed characteristics of population of described user according to the attribute trend information of each application, wherein,
The described ascribed characteristics of population includes the corresponding classification of at least one dimension.
Optionally, described log collection module, including:Behavioural information collects submodule, for for every
Individual user, collects the operation behavior information to application for the described user, wherein, described operation behavior packet
Include:Download behavioural information and/or navigation patterns information;Log recording submodule, for described operation row
Recorded for information, generated application daily record data, described application daily record data is included the day of each application
Will record, described log recording includes Download History and/or browses record.
Optionally, described attribute trend analysis module, including:Record acquisition submodule, for from described
Obtain log recording in the daily record data of user and determine application;Attribute is inclined to determination sub-module, for being directed to
Each dimension, searches each log recording and applies in described dimension correspondence attribute propensity value of all categories,
Described classification and attribute propensity value are recorded as attribute trend information.
Optionally, described ascribed characteristics of population prediction module, including:Statistics of attributes submodule, for for every
Individual dimension, counts to the attribute trend information of the corresponding application of each log recording, determines correspondence of all categories
Attribute propensity value;Attribute chooses submodule, for choosing the maximum classification of attribute propensity value as described
The ascribed characteristics of population of user.
Optionally, described statistics of attributes submodule, for including Download History and clear when described log recording
Look at record when, the attribute propensity value according to classification application corresponding to Download History adds up, and determines each
The corresponding first attribute propensity value of classification;According to classification, the attribute propensity value browsing the corresponding application of record is entered
Row is cumulative, determines the corresponding second attribute propensity value of each classification;For each classification, according to weight pair
Described first attribute propensity value and the second attribute propensity value are weighted suing for peace, corresponding as described classification
Attribute propensity value.
Optionally, also include:Application recognition module, the ascribed characteristics of population for being pre-configured with application is inclined to rule
Then;Extract the description information of each application, according to described ascribed characteristics of population tendency rule, described description information is entered
Row analysis, identifies each attribute propensity value applied under each classification of each dimension.
Optionally, described dimension includes following at least one:Sex dimension, age dimension, academic dimension,
Purchasing power dimension, professional dimension and division of life span's dimension.
User can embody the feature of user to the operation of application, therefore collects the application daily record of each user
Data, is analyzed determining each application under at least one dimension to the application daily record data of each user
Attribute trend information, then predicts the ascribed characteristics of population of described user by the attribute trend information of each application,
I.e. classification under each dimension for the user, thus the ascribed characteristics of population feature based on usage mining user, is processed
Efficiency is higher.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the skill of the present invention
Art means, and being practiced according to the content of description, and in order to allow, the present invention's is above and other
Objects, features and advantages can become apparent, below especially exemplified by the specific embodiment of the present invention.
Brief description
By reading the detailed description of hereafter preferred implementation, various other advantages and benefit are for this
Field those of ordinary skill will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation,
And it is not considered as limitation of the present invention.And in whole accompanying drawing, be denoted by the same reference numerals
Identical part.In the accompanying drawings:
Fig. 1 shows the steps flow chart of data processing method embodiment according to an embodiment of the invention
Figure;
Fig. 2 shows the steps flow chart of data processing method embodiment in accordance with another embodiment of the present invention
Figure;
Fig. 3 shows the structured flowchart of data processing equipment embodiment according to an embodiment of the invention;
Fig. 4 shows the structural frames of data processing equipment embodiment in accordance with another embodiment of the present invention
Figure.
Specific embodiment
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although showing in accompanying drawing
The exemplary embodiment of the disclosure it being understood, however, that may be realized in various forms the disclosure and not
Should be limited by embodiments set forth here.On the contrary, these embodiments are provided to be able to more thoroughly
Understand the disclosure, and complete for the scope of the present disclosure can be conveyed to those skilled in the art.
Embodiment one
With reference to Fig. 1, the step showing data processing method embodiment according to an embodiment of the invention
Flow chart, specifically may include steps of:
Step 102, collects the application daily record data of each user.
User is in using terminal it will usually downloading various application programs (referred to as applying) and being held by application
The various operations of row, such as browse application in third-party application platform, and for example in third-party application platform
Download application etc., user can produce corresponding data to application operating, collect user and put down in third-party application
The data genaration application daily record data related to the operation behavior of application in platform, therefore application daily record data and
User is related to the operation behavior of application.The application operating behavior of each user in a period of time can be collected
Information generates application daily record data
Wherein, in order to ensure the ageing of data, the time threshold collecting data can be set, to determine
The time of collector journal data, therefore may collect in the application daily record data generating in time threshold.Its
In, user can be recorded in application daily record data to data such as the operating time applied and Apply Nameses.
Step 104, for each user, respectively applies extremely in the application daily record data analyzing described user
Attribute trend information under a few dimension.
Step 106, predicts the ascribed characteristics of population of described user according to the attribute trend information of each application.
When user browses in third-party application platform, downloads application, actually same class user is to application
Download and browse and often there is certain general character, for example, male user often downloads military class application,
And women would generally download shopping class application, the user going to school would generally download the tool-class such as dictionary because
Public affairs, and using the application of health preserving class more than old user.Therefore by carrying out to the application daily record data of user point
Analysis is capable of determining that the feature of this user, the i.e. ascribed characteristics of population of user, and wherein, the ascribed characteristics of population refers to population
Intrinsic property and feature, including biological attribute and two aspects of social property.Biological attribute is society
The natural conditions of attribute, and realized by social property;Social property is that population is different from biocenose
Fundamental mark.Different according to dividing mode, the ascribed characteristics of population corresponds to multiple different dimensions, for example above-mentioned
Biological attribute and social property can be two dimensions of the ascribed characteristics of population, and for example can include under biological attribute
Sex dimension, and division of life span's dimension, professional dimension etc. under social property, can be included, can be according to need
Seek the dimension dividing the ascribed characteristics of population.And each dimension can also correspond to certain classification, such as sex dimension bag
Include masculinity and femininity.
The ascribed characteristics of population of each user therefore can be predicted based on application daily record data, be therefore directed to each and use
Family obtains it and applies daily record data, is then directed to each application in application daily record data, determines this application
Attribute trend information under each dimension.Wherein, attribute trend information refers to user to the ascribed characteristics of population
Tendency, such as download application A user be the tendency of male be 0.9, be that the tendency of women is 0.1.
Then the attribute trend information of each application is counted, determine genus of all categories under each dimension
The score of sexual orientation, thus predicting the ascribed characteristics of population of this user, wherein because application is likely to be of multiple dimensions
The attribute trend information of degree, one classification of each dimension correspondence therefore in the ascribed characteristics of population of user, that is, one
The ascribed characteristics of population of user potentially includes multiple classifications.
To sum up, user can embody the feature of user to the operation of application, therefore collects answering of each user
With daily record data, the application daily record data of each user is analyzed determining each application at least one dimension
Attribute trend information under degree, then predicts the population of described user by the attribute trend information of each application
Attribute, i.e. classification under each dimension for the user, thus the ascribed characteristics of population feature based on usage mining user,
Treatment effeciency is higher.
Embodiment two
On the basis of above-described embodiment, the present embodiment is discussed in detail and is divided based on the ascribed characteristics of population of application daily record
Analysis and the step of application.
With reference to Fig. 2, show the step of data processing method embodiment in accordance with another embodiment of the present invention
Rapid flow chart, specifically may include steps of:
Step 202, is pre-configured with the ascribed characteristics of population tendency rule of application.
Step 204, extracts the description information of each application, according to described ascribed characteristics of population tendency rule to described
Description information is analyzed, and identifies each attribute propensity value applied under each classification of each dimension.
The present embodiment has been pre-configured with the ascribed characteristics of population tendency rule of application, and this ascribed characteristics of population tendency rule is used
In the ascribed characteristics of population tendency excavating different application.I.e. APP (Application, application program) this
In granularity, can experience based on each field, define the ascribed characteristics of population tendency rule of some APP, with
Excavate the ascribed characteristics of population tendency of a collection of APP.For example, ascribed characteristics of population tendency rule is configured to:Title
In comprise " weapon " APP male tendency fraction be 0.9, women tendency fraction be 0.1;Title
In comprise " makeups " APP women tendency fraction be 0.9, male tendency fraction be 0.1;APP
Description information in comprise " menstrual period " APP women tendency fraction be 0.9, male tendency fraction be
0.1.
Then the title of various APP and the various description informations of brief introduction are extracted, according to this ascribed characteristics of population
Tendency rule is analyzed to described description information, can adopt the various analysis modes such as model training, build
Vertical corresponding attribute is inclined to judgement system, and this attribute tendency judgement system can include thousands of domain-plannings
It is inclined to rule with the APP ascribed characteristics of population.Corresponding decision model etc. can also be included, thus be directed to not dividing
The application analysed, only need to extract its description information and be analyzed according to ascribed characteristics of population tendency rule, you can know
This is not applied in the attribute propensity value under each classification of each dimension.
Wherein, different according to ascribed characteristics of population tendency rule, the dimension of the ascribed characteristics of population there is also difference, this reality
Apply dimension in example and include following at least one:Sex dimension, age dimension, academic dimension, purchasing power dimension
Degree, professional dimension and division of life span's dimension.At least two classifications, such as property can be included under each dimension
Other dimension includes:Masculinity and femininity.Under wherein each dimension, the criteria for classifying is different, and the classification comprising is also different,
Such as division of life span's dimension includes " reading middle and primary schools ", " studying in college ", " working ", " standard
Standby marriage ", " preparing fertility " etc., age dimension includes:Teenage, adult.Can be by a dimension
Under attribute propensity value of all categories and be set to 1, that is, the propensity value of male adds that the propensity value of women is 1,
And for example " reading middle and primary schools ", " studying in college ", " working ", " prepare marry " and " preparation
The respective propensity value of fertility " is 1 after adding up.
Step 206, for each user, collects the operation behavior information to application for the described user.
Step 208, records to described operation behavior information, generates application daily record data.
For each user, it is collected in the operation behavior information to application for the described user in a period of time, its
In, described operation behavior information includes:Download behavioural information and/or navigation patterns information, that is, user is the
Navigation patterns information can be generated, the download to application generates when application being browsed in tripartite's application platform
Download behavioural information, collect aforesaid operations behavioural information, when then obtaining operation from operation behavior information
Between, i.e. the time to each application-browsing, download, time started and end time etc. can be included, press
Tandem according to the operating time records to the operation behavior information of described application, such as according to operation
Time started to application operation behavior information record, obtain each application log recording, because
This described log recording includes Download History and/or browses record, generates application daily record data.
Step 210, for each user, obtains log recording from the application daily record data of described user
Determine application.
Step 212, for each dimension, each log recording of lookup is applied corresponding each in described dimension
The attribute propensity value of classification, described classification and attribute propensity value are recorded as attribute trend information.
Step 214, for each dimension, is carried out to the attribute trend information of the corresponding application of each log recording
Statistics, determines corresponding attribute propensity value of all categories.
Step 216, chooses the maximum classification of attribute propensity value as the ascribed characteristics of population of described user.
When the ascribed characteristics of population to a user is analyzed, can be from the application daily record data of this user
Each log recording, determines application from this log recording, and the operation behavior to this application, for example certain
One log recording is the Download History to application A.
Due to the different dimensions different classifications of correspondence, apply under each dimension to the tendency of classification not
Same, therefore can be directed to each dimension, each log recording of lookup is applied of all categories in this dimension correspondence
Attribute propensity value, for example, comprise in title " weapon " APP male tendency fraction be 0.9,
Women tendency fraction is 0.1;The women tendency fraction comprising the APP of " makeups " in title is 0.9,
Male's tendency fraction is 0.1, and each classification and the category corresponding attribute propensity value are recorded as applying
Attribute trend information under this dimension.Therefore each applied analysis in daily record data is gone out with its at least one dimension
Spend corresponding attribute trend information.
Then in the daily record data to a user under each dimension, all applications count, that is, obtain
The attribute trend information of all applications, counts each classification corresponding attribute propensity value, thus according to this use
The behavior to application for the family, determines this user under each dimension, attribute propensity value of all categories.For
Each dimension, chooses the maximum classification of attribute propensity value as the ascribed characteristics of population of this user, therefore one use
The ascribed characteristics of population at family includes the corresponding classification of each dimension, for example, analyze class under sex dimension for the user X
Not Wei women, the classification under life dimension be study in college, then user X is identified as studying in college
Women, or referred to as collegegirl.
In the embodiment of the present invention, in an application daily record, may have the download row to application for this user
For, it may have the navigation patterns to application for the user, therefore described log recording includes Download History and browses
Record, downloads behavior at that time and navigation patterns is distinct for a user, therefore can go to downloading
It is different weights to be set with navigation patterns it is assumed that download behavior is the first weight, navigation patterns are second
Weight, can be weighted according to different applications corresponding to different operating, thus analysis obtains more
The accurately ascribed characteristics of population.
The described attribute trend information to the corresponding application of each log recording counts, and determines correspondence of all categories
Attribute propensity value, including:According to classification, the attribute propensity value of the corresponding application of Download History is added up,
Determine the corresponding first attribute propensity value of each classification;According to classification to the attribute browsing the corresponding application of record
Propensity value is added up, and determines the corresponding second attribute propensity value of each classification;For each classification, press
Described first attribute propensity value and the second attribute propensity value are weighted sue for peace according to weight, as described class
Not corresponding attribute propensity value.
It is directed to each classification under a dimension, according to the difference of operation behavior, Download History is corresponded to
The attribute propensity value of application is added up, and determines the corresponding first attribute propensity value of each classification;And it is right
The attribute propensity value browsing the corresponding application of record is added up, and determines that corresponding second attribute of each classification inclines
To value, then according to the first weight is weighted obtaining the first weighted value to described first attribute propensity value,
According to the second weight, the second attribute propensity value is weighted obtaining the second weighted value, then calculates first and add
The sum of power neutralization the second weighted value, is recorded as the attribute propensity value of the category.
I.e. in the granularity of user, APP is browsed and APP in third-party application platform based on user
The log recording that the user behaviors such as download generate, will browse the attribute propensity value of APP or download APP
Attribute propensity value added up, using classification big for attribute propensity value accumulation result as user population belong to
Property, predicted the outcome.Then can be for example with equation below:
Wherein, tag represents a classification in a dimension, " male " of such as sex dimension and " female
Property " it is 2 classifications, " the reading middle and primary schools ", " studying in college " of division of life span's dimension, " ginseng
Processing work ", " preparing to marry ", " preparing fertility " are 5 classifications.
Cumulative item behavior ∈ download in formula represents the whole download APP row traveling through this user
For cumulative item behavior ∈ browse represents that traversal the whole of this netizen browse APP behavior.Fraction item
Score (behavior, tag) represents fraction under the category for the behavior, and that is, the APP relevant with the behavior exists
Attribute propensity value under the category.First weight of download behavior passes through weightdownloadControl, browse row
For the second weight pass through weightbrowseTo control.
Due to download be that the terminal that APP is downloaded to user is used, therefore generally it can be thought that under
The intention of load behavior is clearer and more definite, and that is, behavior dynamics is heavier, and data reliability more preferably, therefore can be arranged
weightdownload>weightbrowse.Therefore, as setting weightdownload=1, weightbrowseWhen=0, characterize
Only consider download behavior, conversely, being set to weightbrowse=0, weightdownload=0 characterize only consider clear
Look at behavior.
After predicting the ascribed characteristics of population of user according to application daily record data, can be based on this ascribed characteristics of population statistics
Analyze various data, various fields can also be applied to, the population that a certain application of such as statistical analysiss is downloaded
Type distribution, and for example when the third-party application platform of user browses or downloads intended application, can be based on
The ascribed characteristics of population of this user, is that user recommends this to be in the increasing of user's download of the classification of this ascribed characteristics of population
Application so that recommending that to more conform to user's request also more targeted.
User uses or generally implies certain feature during downloading above-mentioned application, and that is, same population belongs to
Property classification user there is general character when downloading application, the ascribed characteristics of population of above-mentioned digging user and download application
Ascribed characteristics of population distribution after, recommendation for APP can provide good data basis.The present embodiment leads to
The daily record data browsing or downloading behavior that overwriting has user determines the ascribed characteristics of population of user, thus being based on
The ascribed characteristics of population recommends APP for user, improves the business such as APP personalized recommendation, user property analysis
Accuracy.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of combination of actions,
But those skilled in the art should know, the embodiment of the present invention is not subject to limiting of described sequence of movement
System, because according to the embodiment of the present invention, some steps can be carried out using other orders or simultaneously.Its
Secondary, those skilled in the art also should know, embodiment described in this description belongs to be preferable to carry out
, necessary to the involved action not necessarily embodiment of the present invention.
Embodiment three
On the basis of above-described embodiment, the present embodiment additionally provides a kind of data processing equipment.
With reference to Fig. 3, show the structure of data processing equipment embodiment according to an embodiment of the invention
Block diagram, specifically can include as lower module:
Log collection module 302, for collecting the application daily record data of each user, wherein, described application
Daily record data is related to the operation behavior of application to user.
Attribute trend analysis module 304, for for each user, analyzing the application daily record of described user
The attribute trend information under at least one dimension is respectively applied in data.
Ascribed characteristics of population prediction module 306, predicts described user for the attribute trend information according to each application
The ascribed characteristics of population, wherein, the described ascribed characteristics of population includes the corresponding classification of at least one dimension.
To sum up, user can embody the feature of user to the operation of application, therefore collects answering of each user
With daily record data, the application daily record data of each user is analyzed determining each application at least one dimension
Attribute trend information under degree, then predicts the population of described user by the attribute trend information of each application
Attribute, i.e. classification under each dimension for the user, thus the ascribed characteristics of population feature based on usage mining user,
Treatment effeciency is higher.
With reference to Fig. 4, show the knot of data processing equipment embodiment in accordance with another embodiment of the present invention
Structure block diagram, specifically can include as lower module:
Application recognition module 408, the ascribed characteristics of population for being pre-configured with application is inclined to rule;Respectively should extract
Description information, is analyzed to described description information according to described ascribed characteristics of population tendency rule, identification
Respectively apply the attribute propensity value under each classification of each dimension.
Log collection module 402, for collecting the application daily record data of each user, wherein, described application
Daily record data is related to the operation behavior of application to user.
Attribute trend analysis module 404, for for each user, analyzing the application daily record of described user
The attribute trend information under at least one dimension is respectively applied in data.
Ascribed characteristics of population prediction module 406, predicts described user for the attribute trend information according to each application
The ascribed characteristics of population, wherein, the described ascribed characteristics of population includes the corresponding classification of at least one dimension.
In one alternative embodiment of the present invention, described log collection module 402, including:Behavioural information is received
Collection submodule 40202, for for each user, collecting the operation behavior information to application for the described user,
Wherein, described operation behavior information includes:Download behavioural information and/or navigation patterns information;Log recording
Submodule 40204, for recording to described operation behavior information, generates application daily record data, institute
State application daily record data include each application log recording, described log recording include Download History and/
Or browse record.
Described attribute trend analysis module 404, including:Record acquisition submodule 40402, for from institute
State and in the daily record data of user, obtain log recording determination application;Attribute is inclined to determination sub-module 40404,
Apply in described dimension correspondence attribute of all categories for for each dimension, searching each log recording
Propensity value, described classification and attribute propensity value are recorded as attribute trend information.
Described ascribed characteristics of population prediction module 406, including:Statistics of attributes submodule 40602, for being directed to
Each dimension, counts to the attribute trend information of the corresponding application of each log recording, it is of all categories right to determine
The attribute propensity value answered;Attribute chooses submodule 40604, for choosing the classification of attribute propensity value maximum
The ascribed characteristics of population as described user.
Described statistics of attributes submodule 40602, for when described log recording includes Download History and browses
During record, according to classification, the attribute propensity value of the corresponding application of Download History is added up, determine each class
Not corresponding first attribute propensity value;According to classification, the attribute propensity value browsing the corresponding application of record is carried out
Cumulative, determine the corresponding second attribute propensity value of each classification;For each classification, according to weight to institute
State the first attribute propensity value and the second attribute propensity value is weighted suing for peace, as the corresponding genus of described classification
Sexual orientation value.
Described dimension includes following at least one:Sex dimension, age dimension, academic dimension, purchasing power
Dimension, professional dimension and division of life span's dimension.
After predicting the ascribed characteristics of population of user according to application daily record data, can be based on this ascribed characteristics of population statistics
Analyze various data, various fields can also be applied to, the population that a certain application of such as statistical analysiss is downloaded
Type distribution, and for example when the third-party application platform of user browses or downloads intended application, can be based on
The ascribed characteristics of population of this user, is that user recommends this to be in the increasing of user's download of the classification of this ascribed characteristics of population
Application so that recommending that to more conform to user's request also more targeted.
User uses or generally implies certain feature during downloading above-mentioned application, and that is, same population belongs to
Property classification user there is general character when downloading application, the ascribed characteristics of population of above-mentioned digging user and download application
Ascribed characteristics of population distribution after, recommendation for APP can provide good data basis.The present embodiment leads to
The daily record data browsing or downloading behavior that overwriting has user determines the ascribed characteristics of population of user, thus being based on
The ascribed characteristics of population recommends APP for user, improves the business such as APP personalized recommendation, user property analysis
Accuracy.
For device embodiment, due to itself and embodiment of the method basic simlarity, so the comparison of description
Simply, in place of correlation, the part referring to embodiment of the method illustrates.
Algorithm and display be not solid with any certain computer, virtual system or miscellaneous equipment provided herein
There is correlation.Various general-purpose systems can also be used together with based on teaching in this.As described above,
It is obvious for constructing the structure required by this kind of system.Additionally, the present invention be also not for any specific
Programming language.It is understood that, it is possible to use various programming languages realize the content of invention described herein,
And the description above language-specific done is the preferred forms in order to disclose the present invention.
In description mentioned herein, illustrate a large amount of details.It is to be appreciated, however, that this
Inventive embodiment can be put into practice in the case of not having these details.In some instances, not
It is shown specifically known method, structure and technology, so as not to obscure the understanding of this description.
Similarly it will be appreciated that in order to simplify the disclosure and help understand one of each inventive aspect
Or multiple, in the description to the exemplary embodiment of the present invention above, each feature of the present invention is sometimes
It is grouped together in single embodiment, figure or descriptions thereof.However, should not be by the disclosure
Method be construed to reflect following intention:I.e. the present invention for required protection requires ratio in each claim
The more feature of middle feature be expressly recited.More precisely, as the following claims reflect
As, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows
Claims of specific embodiment are thus expressly incorporated in this specific embodiment, wherein each right
The separate embodiments all as the present invention for the requirement itself.
Those skilled in the art are appreciated that and the module in the equipment in embodiment can be carried out certainly
Adaptively change and they are arranged in one or more equipment different from this embodiment.Permissible
Module in embodiment or unit or assembly are combined into a module or unit or assembly, and in addition may be used
To be divided into multiple submodule or subelement or sub-component.Except such feature and/or process or
Outside at least some of unit excludes each other, using any combinations, (companion can be included to this specification
With claim, summary and accompanying drawing) disclosed in all features and so disclosed any method or
All processes of person's equipment or unit are combined.Unless expressly stated otherwise, this specification (includes companion
With claim, summary and accompanying drawing) disclosed in each feature can be by providing identical, equivalent or phase
Alternative features like purpose to replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include it
Included some features rather than further feature in its embodiment, but the group of the feature of different embodiment
Closing means to be within the scope of the present invention and formed different embodiments.For example, in following power
In sharp claim, embodiment required for protection one of arbitrarily can in any combination mode making
With.
The all parts embodiment of the present invention can be realized with hardware, or with one or more process
The software module run on device is realized, or is realized with combinations thereof.Those skilled in the art should
Understand, basis can be realized using microprocessor or digital signal processor (DSP) in practice
Some or all parts in the data processing method and appliance arrangement of the embodiment of the present invention some or
Person's repertoire.The present invention be also implemented as a part for executing method as described herein or
Whole equipment or program of device (for example, computer program and computer program).Such
The program realizing the present invention can store on a computer-readable medium, or can have one or many
The form of individual signal.Such signal can be downloaded from internet website and obtain, or in carrier signal
Upper offer, or provided with any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention,
And those skilled in the art can design replacement without departing from the scope of the appended claims
Embodiment.In the claims, any reference markss between bracket should not be configured to right
The restriction requiring.Word "comprising" does not exclude the presence of element not listed in the claims or step.Position
Word "a" or "an" before element does not exclude the presence of multiple such elements.The present invention can
Realize with by means of the hardware including some different elements and by means of properly programmed computer.
If in the unit claim listing equipment for drying, several in these devices can be by same
Individual hardware branch is embodying.The use of word first, second, and third does not indicate that any order.
These words can be construed to title.
The invention discloses A1, a kind of data processing method, including:Collect the application daily record of each user
Data, wherein, described application daily record data is related to the operation behavior of application to user;For each use
Family, respectively applies the attribute under at least one dimension to be inclined to letter in the application daily record data analyzing described user
Breath;Attribute trend information according to each application predicts the ascribed characteristics of population of described user, wherein, described population
Attribute includes the corresponding classification of at least one dimension.
A2, the method as described in A1, the application daily record data of each user of described collection, including:For
Each user, collects the operation behavior information to application for the described user, wherein, described operation behavior information
Including:Download behavioural information and/or navigation patterns information;Described operation behavior information is recorded, raw
Become application daily record data, described application daily record data includes the log recording of each application, described daily record note
Record includes Download History and/or browses record.
A3, the method as described in A2, respectively apply in the application daily record data of the described user of described analysis
Attribute trend information under at least one dimension, including:Obtain from the application daily record data of described user
Log recording determines application;For each dimension, search each log recording and apply in described dimension pair
Answer attribute propensity value of all categories, described classification and attribute propensity value are recorded as attribute trend information.
A4, the method as described in A3, the described attribute trend information according to each application predicts described user
The ascribed characteristics of population, including:For each dimension, the attribute trend information to the corresponding application of each log recording
Counted, determined corresponding attribute propensity value of all categories;Choose the maximum classification conduct of attribute propensity value
The ascribed characteristics of population of described user.
A5, the method as described in A4, when described log recording includes Download History and browses record,
The described attribute trend information to the corresponding application of each log recording counts, and determines corresponding genus of all categories
Sexual orientation value, including:According to classification, the attribute propensity value of the corresponding application of Download History is added up, really
The fixed corresponding first attribute propensity value of each classification;According to classification, the attribute browsing the corresponding application of record is inclined
Added up to value, determined the corresponding second attribute propensity value of each classification;For each classification, according to
Weight is weighted to described first attribute propensity value and the second attribute propensity value suing for peace, as described classification
Corresponding attribute propensity value.
A6, described method as arbitrary in A1 to A5, also include:It is pre-configured with the ascribed characteristics of population of application
Tendency rule;Extract the description information of each application, according to described ascribed characteristics of population tendency rule to described description
Information is analyzed, and identifies each attribute propensity value applied under each classification of each dimension.
A7, the method as described in A6, described dimension includes following at least one:Sex dimension, age
Dimension, academic dimension, purchasing power dimension, professional dimension and division of life span's dimension.
According to another aspect of the present invention, B8, a kind of data processing equipment are also disclosed, including:
Log collection module, for collecting the application daily record data of each user, wherein, described application daily record data
Related to the operation behavior of application to user;Attribute trend analysis module, for for each user, dividing
The attribute trend information under at least one dimension is respectively applied in the application daily record data analysing described user;People
Mouth attribute forecast module, for predicting that according to the attribute trend information of each application the population of described user belongs to
Property, wherein, the described ascribed characteristics of population includes the corresponding classification of at least one dimension.
B9, the device as described in B8, described log collection module, including:Behavioural information collects submodule
Block, for for each user, collecting the operation behavior information to application for the described user, wherein, described
Operation behavior information includes:Download behavioural information and/or navigation patterns information;Log recording submodule, uses
In recording to described operation behavior information, generate application daily record data, described application daily record data bag
Include the log recording of each application, described log recording includes Download History and/or browses record.
B10, the device as described in B9, described attribute trend analysis module, including:Record obtains son
Module, determines application for obtaining log recording from the daily record data of described user;Attribute tendency determines
Submodule, for for each dimension, each log recording of lookup is applied all kinds of in described dimension correspondence
Other attribute propensity value, described classification and attribute propensity value are recorded as attribute trend information.
B11, the device as described in B10, described ascribed characteristics of population prediction module, including:Statistics of attributes
Module, for for each dimension, counting to the attribute trend information of the corresponding application of each log recording,
Determine corresponding attribute propensity value of all categories;Attribute chooses submodule, maximum for choosing attribute propensity value
Classification as described user the ascribed characteristics of population.
B12, the device as described in B11, described statistics of attributes submodule, for when described log recording
During including Download History with browsing record, according to classification, the attribute propensity value of the corresponding application of Download History is entered
Row is cumulative, determines the corresponding first attribute propensity value of each classification;According to classification, to browsing, record is corresponding to answer
With attribute propensity value added up, determine the corresponding second attribute propensity value of each classification;For each
Classification, is weighted to described first attribute propensity value and the second attribute propensity value suing for peace according to weight, makees
For described classification corresponding attribute propensity value.
B13, described device as arbitrary in B8 to B11, also include:Application recognition module, for pre-
First configure the ascribed characteristics of population tendency rule of application;Extract the description information of each application, belong to according to described population
Sexual orientation rule is analyzed to described description information, and identification is each to apply under each classification of each dimension
Attribute propensity value.
B14, the device as described in B13, described dimension includes following at least one:Sex dimension, year
Age dimension, academic dimension, purchasing power dimension, professional dimension and division of life span's dimension.
Claims (10)
1. a kind of data processing method, including:
Collect the application daily record data of each user, wherein, described application daily record data is with user to application
Operation behavior is related;
For each user, respectively apply at least one dimension in the application daily record data analyzing described user
Under attribute trend information;
Attribute trend information according to each application predicts the ascribed characteristics of population of described user, wherein, described population
Attribute includes the corresponding classification of at least one dimension.
2. the method for claim 1 is it is characterised in that the application day of each user of described collection
Will data, including:
For each user, collect the operation behavior information to application for the described user, wherein, described operation
Behavioural information includes:Download behavioural information and/or navigation patterns information;
Described operation behavior information is recorded, generates application daily record data, described application daily record data
Including the log recording of each application, described log recording includes Download History and/or browses record.
3. method as claimed in claim 2 is it is characterised in that the application of the described user of described analysis
The attribute trend information under at least one dimension is respectively applied in daily record data, including:
Obtain log recording and determine application from the application daily record data of described user;
For each dimension, search each log recording and apply in described dimension correspondence attribute of all categories
Propensity value, described classification and attribute propensity value are recorded as attribute trend information.
4. method as claimed in claim 3 is it is characterised in that the described attribute according to each application inclines
To the ascribed characteristics of population of user described in information prediction, including:
For each dimension, the attribute trend information of the corresponding application of each log recording is counted, determines
Corresponding attribute propensity value of all categories;
Choose the maximum classification of attribute propensity value as the ascribed characteristics of population of described user.
5. method as claimed in claim 4 it is characterised in that when described log recording include download
When recording and browsing record, the described attribute trend information to the corresponding application of each log recording counts,
Determine corresponding attribute propensity value of all categories, including:
According to classification, the attribute propensity value of the corresponding application of Download History is added up, determine each classification pair
The the first attribute propensity value answered;
According to classification, the attribute propensity value browsing the corresponding application of record is added up, determine each classification pair
The the second attribute propensity value answered;
For each classification, according to weight, described first attribute propensity value and the second attribute propensity value are carried out
Weighted sum, as described classification corresponding attribute propensity value.
6. described method as arbitrary in claim 1 to 5 is it is characterised in that also include:
It is pre-configured with the ascribed characteristics of population tendency rule of application;
Extract the description information of each application, according to described ascribed characteristics of population tendency rule, described description information is entered
Row analysis, identifies each attribute propensity value applied under each classification of each dimension.
7. method as claimed in claim 6 is it is characterised in that described dimension includes following at least one
Kind:Sex dimension, age dimension, academic dimension, purchasing power dimension, professional dimension and division of life span's dimension
Degree.
8. a kind of data processing equipment, including:
Log collection module, for collecting the application daily record data of each user, wherein, described application daily record
Data is related to the operation behavior of application to user;
Attribute trend analysis module, for for each user, analyzing the application daily record data of described user
In respectively apply the attribute trend information under at least one dimension;
Ascribed characteristics of population prediction module, for predicting the people of described user according to the attribute trend information of each application
Mouth attribute, wherein, the described ascribed characteristics of population includes the corresponding classification of at least one dimension.
9. device as claimed in claim 8 is it is characterised in that described log collection module, including:
Behavioural information collects submodule, for for each user, collecting the operation to application for the described user
Behavioural information, wherein, described operation behavior information includes:Download behavioural information and/or navigation patterns information;
Log recording submodule, for recording to described operation behavior information, generates application daily record number
According to described application daily record data includes the log recording of each application, and described log recording is recorded under including
Record and/or browse record.
10. device as claimed in claim 9 is it is characterised in that described attribute trend analysis module,
Including:
Record acquisition submodule, should for obtaining log recording determination from the daily record data of described user
With;
Attribute is inclined to determination sub-module, applies for for each dimension, searching each log recording
Described dimension correspondence attribute propensity value of all categories, described classification and attribute propensity value is recorded as attribute and inclines
To information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510472894.9A CN106445934A (en) | 2015-08-04 | 2015-08-04 | Data processing method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510472894.9A CN106445934A (en) | 2015-08-04 | 2015-08-04 | Data processing method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106445934A true CN106445934A (en) | 2017-02-22 |
Family
ID=59216351
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510472894.9A Pending CN106445934A (en) | 2015-08-04 | 2015-08-04 | Data processing method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106445934A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107609040A (en) * | 2017-08-16 | 2018-01-19 | 深信服科技股份有限公司 | Data analysing method, data processing equipment and computer-readable recording medium |
CN108363762A (en) * | 2018-02-05 | 2018-08-03 | 广州阿里巴巴文学信息技术有限公司 | A kind of collection processing method of user trajectory, device and terminal device |
CN111880872A (en) * | 2020-06-28 | 2020-11-03 | 华为技术有限公司 | Method, terminal device, server and system for managing application program APP |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104424231A (en) * | 2013-08-26 | 2015-03-18 | 腾讯科技(深圳)有限公司 | Multi-dimensional data processing method and device |
CN104572962A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | APP (Application) recommendation method and system |
CN104574146A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | Service recommending method and system |
-
2015
- 2015-08-04 CN CN201510472894.9A patent/CN106445934A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424231A (en) * | 2013-08-26 | 2015-03-18 | 腾讯科技(深圳)有限公司 | Multi-dimensional data processing method and device |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104572962A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | APP (Application) recommendation method and system |
CN104574146A (en) * | 2014-12-31 | 2015-04-29 | 浙江大学 | Service recommending method and system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107609040A (en) * | 2017-08-16 | 2018-01-19 | 深信服科技股份有限公司 | Data analysing method, data processing equipment and computer-readable recording medium |
CN108363762A (en) * | 2018-02-05 | 2018-08-03 | 广州阿里巴巴文学信息技术有限公司 | A kind of collection processing method of user trajectory, device and terminal device |
CN111880872A (en) * | 2020-06-28 | 2020-11-03 | 华为技术有限公司 | Method, terminal device, server and system for managing application program APP |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107818344B (en) | Method and system for classifying and predicting user behaviors | |
CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
CN107862022B (en) | Culture resource recommendation system | |
US20190318407A1 (en) | Method for product search using the user-weighted, attribute-based, sort-ordering and system thereof | |
CN108345702A (en) | Entity recommends method and apparatus | |
CN109145216A (en) | Network public-opinion monitoring method, device and storage medium | |
WO2016035072A2 (en) | Sentiment rating system and method | |
JP5615857B2 (en) | Analysis apparatus, analysis method, and analysis program | |
TW201447797A (en) | Method and system for multi-phase ranking for content personalization | |
CN111209474A (en) | Online course recommendation method and device, computer equipment and storage medium | |
CN107562939A (en) | Vertical field news recommends method, apparatus and readable storage medium | |
KR101562279B1 (en) | Mobile device based on inference of user intent and content recommending method using the same | |
Zhou et al. | Predicting high-risk students using Internet access logs | |
CN111967914A (en) | User portrait based recommendation method and device, computer equipment and storage medium | |
US20150120634A1 (en) | Information processing device, information processing method, and program | |
CN110069693A (en) | Method and apparatus for determining target pages | |
CN106452809A (en) | Data processing method and device | |
EP2613275B1 (en) | Search device, search method, search program, and computer-readable memory medium for recording search program | |
CN112989824A (en) | Information pushing method and device, electronic equipment and storage medium | |
CN112417133A (en) | Training method and device of ranking model | |
CN106445934A (en) | Data processing method and apparatus | |
CN114579858A (en) | Content recommendation method and device, electronic equipment and storage medium | |
EP3323100A1 (en) | A method and system for analyzing mobile apps | |
CN111177564B (en) | Product recommendation method and device | |
Almeida et al. | A method for automatic generation of fuzzy membership functions for mobile device’s characteristics based on Google Trends |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20170222 |