CN107807997A - User's portrait building method, device and computing device based on big data - Google Patents
User's portrait building method, device and computing device based on big data Download PDFInfo
- Publication number
- CN107807997A CN107807997A CN201711092706.5A CN201711092706A CN107807997A CN 107807997 A CN107807997 A CN 107807997A CN 201711092706 A CN201711092706 A CN 201711092706A CN 107807997 A CN107807997 A CN 107807997A
- Authority
- CN
- China
- Prior art keywords
- user
- portrait
- information
- characteristic vector
- feature vector
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a kind of user's portrait building method, device, computing device and computer-readable storage medium based on big data.Wherein method includes：Obtain user's geographical location information and user operates the behavioural information of application program；Position point sequence is generated according to user's geographical location information；Position point sequence is learnt using the first deep learning algorithm, obtains user's geographic location feature vector corresponding to user；Behavioural information is learnt using the second deep learning algorithm, obtains user behavior characteristic vector；Drawn a portrait based on user's geographic location feature vector sum user behavior characteristic vector structuring user's.Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user, so as to easily provide the user the service of more becoming more meticulous according to user's portrait, overcome the metadata for relying only on user in the prior art, for example, the low-quality defect of user's portrait caused by the structuring user's such as age, sex, income portrait.
Description
Technical field
The present invention relates to technical field of data processing, and in particular to a kind of user's portrait building method based on big data,
Device, computing device and computer-readable storage medium.
Background technology
With the continuous development of network and information technology, all kinds of platform applications and give birth to, in order to improve the various functions of platform,
To facilitate platform to provide the user more preferable service, and the interests of protecting platform, it is to be understood that, every letter of analysis user
Breath.At present, the information of user is understood usually through the mode of structure user's portrait.
Existing user draws a portrait construction method, mainly according to the metadata of user, for example, sex, the age, occupation,
Constellation, height, body weight, shopping type, Brang Preference and/or income etc. carry out structuring user's portrait, and underuse because of interconnection
Net and caused big data, although the user's portrait constructed using a metadata can be instructed platform, not
The feature of user can be fully demonstrated, so that platform can not provide the user the service to become more meticulous, can not also be existed in user
To protecting platform interests during the behaviors such as fraud.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State the portrait of the user based on big data building method, device, computing device and the computer-readable storage medium of problem.
The building method according to an aspect of the invention, there is provided a kind of user based on big data draws a portrait, including：
Obtain user's geographical location information and user operates the behavioural information of application program；
Position point sequence is generated according to user's geographical location information；
Position point sequence is learnt using the first deep learning algorithm, it is special to obtain user geographical position corresponding to user
Sign vector；
Behavioural information is learnt using the second deep learning algorithm, obtains user behavior characteristic vector；
Drawn a portrait based on user's geographic location feature vector sum user behavior characteristic vector structuring user's.
Alternatively, position point sequence is generated according to user's geographical location information to further comprise：
Geographical location information is combined processing, generation positional information track；
Location point peripheral information is obtained based on the location point on positional information track, generates position point sequence；
Position point sequence is learnt using the first deep learning algorithm, it is special to obtain user geographical position corresponding to user
Sign vector further comprises：
Sequence Learning is carried out to position point sequence using trained time recurrent neural network, obtained corresponding to user
User's geographic location feature vector.
Alternatively, behavioural information is learnt using the second deep learning algorithm, obtains user behavior characteristic vector and enter
One step includes：
The action trail of user's operation application program is obtained according to behavioural information；
The action trail of application program is operated according to user, generates behavior sequence；
Sequence Learning is carried out to behavior sequence using trained time recurrent neural network, obtains user behavior feature
Vector.
Alternatively, method also includes：Location consistency characteristic vector is generated according to user's geographical location information；
Further comprised based on user's geographic location feature vector sum user behavior characteristic vector structuring user's portrait：
Checking treatment is carried out to user's geographic location feature vector according to location consistency characteristic vector；
Drawn according to user's geographic location feature vector sum user behavior characteristic vector structuring user's after checking treatment
Picture.
Alternatively, after structuring user's portrait, method also includes：Based on user's portrait sample training user interest hobby
Model；
The user's portrait input for being analysed to user is analyzed to user interest modeling hobbies, obtains the interest of the user
Hobby.
Alternatively, after structuring user's portrait, method also includes：Whether analysis user is drawn a portrait with abnormal based on user
Behavior.
Alternatively, user's geographical location information includes：IP information, WIFI information, base station information and/or GPS information.
Alternatively, behavioural information includes：Operation of the user to application program and the page residence time in application program.
According to another aspect of the present invention, there is provided a kind of user's portrait constructing apparatus based on big data, including：
Acquisition module, the behavioural information of application program is operated suitable for obtaining user's geographical location information and user；
First generation module, suitable for generating position point sequence according to user's geographical location information；
First study module, suitable for learning using the first deep learning algorithm to position point sequence, obtain user couple
The user's geographic location feature vector answered；
Second study module, suitable for learning using the second deep learning algorithm to behavioural information, obtain user behavior
Characteristic vector；
User's portrait constructing module, is used suitable for being constructed based on user's geographic location feature vector sum user behavior characteristic vector
Draw a portrait at family.
Alternatively, the first generation module further comprises：
Combined treatment unit, suitable for geographical location information is combined into processing, generation positional information track；
First generation unit, suitable for obtaining location point peripheral information based on the location point on positional information track, generate position
Put point sequence；
First study module is further adapted for：Position point sequence is carried out using trained time recurrent neural network
Sequence Learning, obtain user's geographic location feature vector corresponding to user.
Alternatively, the second study module further comprises：
Action trail generation unit, suitable for obtaining the action trail of user's operation application program according to behavioural information；
Behavior sequence generation unit, suitable for operating the action trail of application program according to user, generate behavior sequence；
Second unit, suitable for carrying out sequence to behavior sequence using trained time recurrent neural network
Practise, obtain user behavior characteristic vector.
Alternatively, device also includes：Second generation module, suitable for generating location consistency according to user's geographical location information
Characteristic vector；
User's portrait constructing module further comprises：
Checking treatment unit, suitable for being verified according to location consistency characteristic vector to user's geographic location feature vector
Processing；
User's portrait structural unit, suitable for according to user's geographic location feature vector sum user's row after checking treatment
It is characterized vectorial structuring user's portrait.
Alternatively, device also includes：Training module, suitable for based on user's portrait sample training user interest modeling hobbies；
Hobby analysis module, the user suitable for being analysed to user, which draws a portrait to input to user interest modeling hobbies, to be carried out
Analysis, obtains the hobby of the user.
Alternatively, device also includes：Abnormal behaviour analysis module, suitable for whether drawing a portrait analysis user with different based on user
Chang Hangwei.
Alternatively, user's geographical location information includes：IP information, WIFI information, base station information and/or GPS information.
Alternatively, behavioural information includes：Operation of the user to application program and the page residence time in application program.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, processor, memory and communication interface complete mutual communication by communication bus；
Memory is used to deposit an at least executable instruction, and executable instruction makes computing device above-mentioned based on big data
User draws a portrait and operated corresponding to building method.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, be stored with least one in storage medium
Executable instruction, executable instruction make computing device behaviour corresponding to user's portrait building method based on big data as described above
Make.
According to scheme provided by the invention, obtain user's geographical location information and user operates the behavior letter of application program
Breath, position point sequence is generated according to user's geographical location information, using the first deep learning algorithm to position point sequence
Practise, obtain user's geographic location feature vector corresponding to user, behavioural information is learnt using the second deep learning algorithm,
User behavior characteristic vector is obtained, is drawn a portrait based on user's geographic location feature vector sum user behavior characteristic vector structuring user's.
Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user, so as to
The service of more becoming more meticulous easily is provided the user according to user's portrait, overcomes the unitary number for relying only on user in the prior art
According to for example, the low-quality defect of user's portrait caused by the structuring user's such as age, sex, income portrait.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the flow signal of user's portrait building method according to an embodiment of the invention based on big data
Figure；
Fig. 2 shows that the flow of user's portrait building method in accordance with another embodiment of the present invention based on big data is shown
It is intended to；
Fig. 3 shows that the structure journey of user's portrait constructing apparatus according to an embodiment of the invention based on big data is shown
It is intended to；
Fig. 4 shows the structure journey of user's portrait constructing apparatus in accordance with another embodiment of the present invention based on big data
Schematic diagram；
Fig. 5 shows a kind of structural representation of computing device according to an embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 shows the flow signal of user's portrait building method according to an embodiment of the invention based on big data
Figure.As shown in figure 1, this method comprises the following steps：
Step S100, obtains user's geographical location information and user operates the behavioural information of application program.
Wherein, user's geographical location information can be what user terminal reported, and alternatively, the user in the present embodiment is geographical
Positional information can include the one or more in following information：IP information, WIFI information, base station information, GPS information, are based on
Above- mentioned information can determine the current geographical position of user, for example, city where can determining user based on IP address, is based on
Base station information can determine user the country one belongs to, and street information etc. can be determined based on GPS information, for example, obtaining
It is 118.119.85.36 to certain IP address, IP inquiry tables is inquired about according to accessed IP address, it may be determined that specifically geographical
Position is Sichuan Province Ziyang City, is merely illustrative of here without any restriction effect.Can according to above-mentioned four kinds of information
The geographical position of user is obtained, is no longer illustrated one by one here.
The behavioural information that user operates application program refers to caused behavioural information when user operates to application program,
Here behavioural information is not only additionally included in page institute's residence time of application program comprising specific operation, is operated according to user
Whether the behavior that the behavioural information of application program can analyze user is friendly, and the information that analysis user is of interest.
Step S101, position point sequence is generated according to user's geographical location information.
After user's geographical location information is got, position can be generated according to acquired user's geographical location information
Point sequence is put, in the position point sequence, the order of location point is particularly important, is the row that carries out according to time order and function order
Sequence, for example, the position point sequence generated by user's geographical location information in obtaining one day is：Beijing → Shanghai → tri-
Asia → Beijing, it is merely illustrative of here certainly without any restriction effect.
Step S102, position point sequence is learnt using the first deep learning algorithm, obtains user corresponding to user
Geographic location feature vector.
After position point sequence is obtained according to step S101, the first deep learning algorithm can be utilized to position point sequence
Learnt, position point sequence is learnt here primarily to obtain user's geographic location feature vector, with pass through to
Amount form represents user's geographical location information, is easy to subsequent construction user to draw a portrait.
Step S103, behavioural information is learnt using the second deep learning algorithm, obtains user behavior characteristic vector.
After the behavioural information of user's operation application program is obtained according to step S100, the second deep learning can be utilized
Algorithm learns to behavioural information, behavioural information is learnt here primarily to obtain user behavior characteristic vector,
To represent that user operates the behavioural information of application program by vector form, it is easy to subsequent construction user to draw a portrait.
Step S104, drawn a portrait based on user's geographic location feature vector sum user behavior characteristic vector structuring user's.
According to step S102 and step S103 obtain user's geographic location feature vector sum user behavior characteristic vector it
Afterwards, can be drawn a portrait according to resulting user's geographic location feature vector sum user behavior characteristic vector come structuring user's, the use
Family, which is drawn a portrait, can fully reflect the feature of user, overcome the metadata for relying only on user in the prior art, for example, the age,
User's portrait quality is low caused by the structuring user's such as sex, income portrait, can not provide the user lacking for the service that more becomes more meticulous
Fall into.
The method provided according to the above embodiment of the present invention, obtains user's geographical location information and user operates application program
Behavioural information, according to user's geographical location information generate position point sequence, using the first deep learning algorithm to location point sequence
Row are learnt, and user's geographic location feature vector corresponding to user are obtained, using the second deep learning algorithm to behavioural information
Learnt, obtain user behavior characteristic vector, constructed based on user's geographic location feature vector sum user behavior characteristic vector
User draws a portrait.Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user,
So as to easily provide the user the service of more becoming more meticulous according to user's portrait, overcome and rely only on user's in the prior art
One metadata, for example, the low-quality defect of user's portrait caused by the structuring user's such as age, sex, income portrait.
Fig. 2 shows that the flow of user's portrait building method in accordance with another embodiment of the present invention based on big data is shown
It is intended to.As shown in Fig. 2 this method comprises the following steps：
Step S200, obtains user's geographical location information and user operates the behavioural information of application program.
Step S201, geographical location information is combined processing, generation positional information track.
User's geographical location information can intuitively reflect customer location situation of change, be a kind of hand for analyzing user behavior
Section, any exception may can not be found by analyzing single user's geographical location information, and if multiple user's geographical location information
Analysis is combined, then is very easy to find exception, for example, xx xx days month xx, user A user's geographical location information morning
When be Beijing, noon is Shanghai, and the lower period of the day from 11 a.m. to 1 p.m will be Sanya, is changed into Beijing again during evening, for normal situation, a user is little
It may be shuttled within the time in four cities, for this kind of situation, if being only according to unique user geographical location information
It can not find to go wrong, and forming position information track, then problem is very easy to find, therefore, based on positional information track
Structuring user's portrait can lift the accuracy of user's portrait.
Specifically, after geographical location information is got, the geographical position according to residing for geographical location information determines user,
Each geographical position is considered as a location point, connects location point with straight line according to time order and function order, forming position
Information track.
Step S202, location point peripheral information is obtained based on the location point on positional information track, generates position point sequence.
Positional information track is made up of location point, and location point week is inquired about according to the location point on positional information track
The information enclosed, and location point peripheral information is obtained, such as Airport information, company information, mall information etc., around location point
Information and geographical location information generation position point sequence.
Step S203, Sequence Learning is carried out to position point sequence using trained time recurrent neural network, obtained
User's geographic location feature vector corresponding to user.
Used time recurrent neural network (LSTM) is trained based on substantial amounts of sample in the embodiment of the present invention
Obtain, by the location point sequence inputting generated to time recurrent neural network, the time recurrent neural network is to acquired
To position point sequence learnt, generation user geographic location feature vector.
Step S204, the action trail of user's operation application program is obtained according to behavioural information.
The behavioural information that user operates application program can intuitively reflect that user uses the situation of application program, according to row
Focus of the user to application program can be analyzed for information, or the operation that user carried out can be analyzed according to behavioural information
Whether it is a kind of friendly behavior.
For example, in general application program reuses the service that application program provides after requiring user's registration account,
And before user's registration, corresponding disclaimer can be shown to registered user, generally, friendly user can read accordingly
Disclaimer, know corresponding points for attention, while can also be fully understood by user's right, but non-friendly use for some
Family, it is simultaneously not concerned with having which clause in disclaimer, and is desirable to be rapidly completed registration, enters inside application program
The page, operated, such as borrow money etc..
In many cases, any exception may can not be found by analyzing single user behavior information, and if multiple users
Behavioural information combines analysis, then is very easy to find exception, and therefore, Behavior-based control trajectory creation user portrait can be lifted
The accuracy of user's portrait.
Specifically, after behavioural information is got, behavioural information is connected with straight line according to time order and function order, shape
The action trail of application program is operated into user.
Step S205, the action trail of application program is operated according to user, generate behavior sequence.
Action trail connects behavioural information with straight line according to time order and function order, therefore, can according to
Family operates the action trail of application program, generates behavior sequence.
Step S206, Sequence Learning is carried out to behavior sequence using trained time recurrent neural network, used
Family behavioural characteristic vector.
Used time recurrent neural network (LSTM) is trained based on substantial amounts of sample in the embodiment of the present invention
Obtain, the behavior sequence generated is inputted to time recurrent neural network, the time recurrent neural network is to accessed
Behavior sequence learnt, generate user behavior characteristic vector.
Step S207, location consistency characteristic vector is generated according to user's geographical location information.
User's geographical location information in the present embodiment can include the one or more in following information：IP information,
WIFI information, base station information, GPS information, but some information users can forge, for example, IP information, user can be pseudo-
IP address is made, user geographical position will be inaccurate so according to determined by IP information, and identified user geographical position is not
The accurate user's portrait finally constructed that may result in is inaccurate, so as to influence to provide a user the flat of service using user's portrait
The service that platform is provided, therefore, after user's geographical location information is got, it is also necessary to generated according to user's geographical location information
Location consistency characteristic vector, uniformity characteristic vector are used for the uniformity for representing each geographical position, can be used for user
Reason position feature vector is verified.
The present invention is not limited step S201- steps S203, step S204- steps S206, step S207 execution sequence
Fixed, step S201- steps S203 can be performed before or after step S204- steps S206, step S207, can also be simultaneously
Perform step S201, step S204, step S207.
Step S208, checking treatment is carried out to user's geographic location feature vector according to location consistency characteristic vector, obtained
User's geographic location feature vector after to checking treatment.
Specifically, user's geographic location feature vector can be verified according to location consistency characteristic vector, verified
User's geographic location feature vector afterwards reflects real user geographical position.
Step S209, constructed and used according to user's geographic location feature vector sum user behavior characteristic vector after checking treatment
Draw a portrait at family.
The user constructed using user provided by the invention portrait construction method is drawn a portrait, and can be applied to various flat
Platform, platform can be made to be better understood by user, so as to provide the user the service more to become more meticulous, to improve the Experience Degree of user,
For example, can apply to gaming platform, gaming platform can be made to know the game interested to user, so as to targetedly to
User pushes game advertisement；Apply also for finance company so that the finance company draws a portrait according to user understands whether user deposits
In abnormal behaviour, user's reference record is understood, corresponding service is provided user according to reference record, for example, do not made loans to it,
Or lending amount of money etc. is determined according to record.Here it is merely illustrative of, without any restriction effect.
In alternative embodiment of the present invention, after structuring user's portrait, method also includes：Based on user's portrait sample
Training user's hobby model, the user's portrait input for being analysed to user are analyzed to user interest modeling hobbies, obtained
To the hobby of the user.
Specifically, the user constructed by the use of user provided by the present invention portrait building method is drawn a portrait as sample
Row training, obtain input and drawn a portrait for user, export as the user interest modeling hobbies of user interest hobby, when needing to analyze certain use
The hobby at family, the user that the user is constructed using user provided by the invention portrait building method is drawn a portrait, then by institute's structure
The user made draws a portrait input to the user interest modeling hobbies of training, analyzes to obtain the user using the user interest modeling hobbies
Hobby.After the hobby of user is analyzed, it can be pushed accordingly to user according to the hobby of user
Information, for example, video messaging, game message etc., will not enumerate explanation here.
In alternative embodiment of the present invention, after structuring user's portrait, method also includes：Drawn a portrait and analyzed based on user
Whether user has abnormal behaviour.
For example, with the development of network technology, the application program much on debt-credit is proposed at present, for example, xx
Receipt, user can application program carry out debit operation, then to user make loans before, the affiliated company of application program needs to carry out
Risk assessment, credit of the user etc. is assessed, in the prior art, the reference record for being all based on third party's offer is judged,
However, the air control many times based on third party's data faces many problems：1st, the data cover rate of third party's data is limited, very
Multiple target user can not cover；2nd, reference cost is higher, and looks into third party's data and generally require user's mandate, Consumer's Experience
Difference.It is to be drawn a portrait based on big data come structuring user's using user provided in an embodiment of the present invention portrait building method, makes full use of
User's geographical location information and user operate the behavioural information of application program, avoid user's spurious information, and the user constructed draws
As more truly reflecting user profile, drawn a portrait based on user and analyze whether user has abnormal behaviour, can be public to credit
Department is instructed.
The method provided according to the above embodiment of the present invention, obtains user's geographical location information and user operates application program
Behavioural information, geographical location information is combined processing, generation positional information track, based on the position on positional information track
An acquisition location point peripheral information is put, position point sequence is generated, using trained time recurrent neural network to location point
Sequence carries out Sequence Learning, obtains user's geographic location feature vector corresponding to user, and user's operation is obtained according to behavioural information
The action trail of application program, the action trail of application program is operated according to user, generate behavior sequence, utilization is trained
Time recurrent neural network carries out Sequence Learning to behavior sequence, user behavior characteristic vector is obtained, according to user geographical position
Information generates location consistency characteristic vector, and school is carried out to user's geographic location feature vector according to location consistency characteristic vector
Processing is tested, is drawn according to user's geographic location feature vector sum user behavior characteristic vector structuring user's after checking treatment
Picture.Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user, so as to
It is enough that the service of more becoming more meticulous easily is provided the user according to user's portrait, and drawn a portrait according to user and determine user with the presence or absence of different
Chang Hangwei etc., the metadata for relying only on user in the prior art is overcome, for example, the structuring user's such as age, sex, income are drawn
The low-quality defect of user's portrait as caused by.
Fig. 3 shows that the structure journey of user's portrait constructing apparatus according to an embodiment of the invention based on big data is shown
It is intended to.As shown in figure 3, the device includes：Acquisition module 300, the first generation module 310, the first study module 320, second are learned
Practise module 330, user's portrait constructing module 340.
Acquisition module 300, the behavioural information of application program is operated suitable for obtaining user's geographical location information and user.
First generation module 310, suitable for generating position point sequence according to user's geographical location information.
First study module 320, suitable for learning using the first deep learning algorithm to position point sequence, obtain user
Corresponding user's geographic location feature vector.
Second study module 330, suitable for learning using the second deep learning algorithm to behavioural information, obtain user's row
It is characterized vector.
User's portrait constructing module 340, suitable for based on user's geographic location feature vector sum user behavior characteristic vector structure
Make user's portrait.
The device provided according to the above embodiment of the present invention, obtains user's geographical location information and user operates application program
Behavioural information, according to user's geographical location information generate position point sequence, using the first deep learning algorithm to location point sequence
Row are learnt, and user's geographic location feature vector corresponding to user are obtained, using the second deep learning algorithm to behavioural information
Learnt, obtain user behavior characteristic vector, constructed based on user's geographic location feature vector sum user behavior characteristic vector
User draws a portrait.Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user,
So as to easily provide the user the service of more becoming more meticulous according to user's portrait, overcome and rely only on user's in the prior art
One metadata, for example, the low-quality defect of user's portrait caused by the structuring user's such as age, sex, income portrait.
Fig. 4 shows the structure journey of user's portrait constructing apparatus in accordance with another embodiment of the present invention based on big data
Schematic diagram.As shown in figure 4, the device includes：Acquisition module 400, the first generation module 410, the first study module 420, second
Study module 430, the second generation module 440, user's portrait constructing module 450.
Acquisition module 400, the behavioural information of application program is operated suitable for obtaining user's geographical location information and user.
Wherein, user's geographical location information includes：IP information, WIFI information, base station information and/or GPS information.Behavior is believed
Breath includes：Operation of the user to application program and the page residence time in application program.
First generation module 410 further comprises：Combined treatment unit 411, suitable for geographical location information is combined
Processing, generation positional information track
First generation unit 412, suitable for obtaining location point peripheral information, generation based on the location point on positional information track
Position point sequence；
First study module 420 is further adapted for：Using trained time recurrent neural network to position point sequence
Sequence Learning is carried out, obtains user's geographic location feature vector corresponding to user.
Second study module 430 further comprises：Action trail generation unit 431, suitable for being used according to behavioural information
Family operates the action trail of application program.
Behavior sequence generation unit 432, suitable for operating the action trail of application program according to user, generate behavior sequence.
Second unit 433, suitable for carrying out sequence to behavior sequence using trained time recurrent neural network
Study, obtains user behavior characteristic vector.
Second generation module 440, suitable for generating location consistency characteristic vector according to user's geographical location information.
User's portrait constructing module 450 further comprises：Checking treatment unit 451, suitable for according to location consistency feature
Vector carries out checking treatment to user's geographic location feature vector；
User's portrait structural unit 452, suitable for being used according to user's geographic location feature vector sum after checking treatment
Family behavioural characteristic vector structuring user's portrait.
In a kind of optional embodiment of the present invention, device also includes：Training module 460, suitable for based on user's portrait sample
This training user hobby model；
Hobby analysis module 470, the user suitable for being analysed to user, which draws a portrait, to be inputted to user interest modeling hobbies
Analyzed, obtain the hobby of the user.
In a kind of optional embodiment of the present invention, device also includes：Abnormal behaviour analysis module 480, suitable for based on use
Whether family portrait analysis user has abnormal behaviour.
The device provided according to the above embodiment of the present invention, obtains user's geographical location information and user operates application program
Behavioural information, geographical location information is combined processing, generation positional information track, based on the position on positional information track
An acquisition location point peripheral information is put, position point sequence is generated, using trained time recurrent neural network to location point
Sequence carries out Sequence Learning, obtains user's geographic location feature vector corresponding to user, and user's operation is obtained according to behavioural information
The action trail of application program, the action trail of application program is operated according to user, generate behavior sequence, utilization is trained
Time recurrent neural network carries out Sequence Learning to behavior sequence, user behavior characteristic vector is obtained, according to user geographical position
Information generates location consistency characteristic vector, and school is carried out to user's geographic location feature vector according to location consistency characteristic vector
Processing is tested, is drawn according to user's geographic location feature vector sum user behavior characteristic vector structuring user's after checking treatment
Picture.Technical scheme provided by the invention, user's portrait based on big data construction can fully reflect the feature of user, so as to
It is enough that the service of more becoming more meticulous easily is provided the user according to user's portrait, and drawn a portrait according to user and determine user with the presence or absence of different
Chang Hangwei etc., the metadata for relying only on user in the prior art is overcome, for example, the structuring user's such as age, sex, income are drawn
The low-quality defect of user's portrait as caused by.
The embodiment of the present application additionally provides a kind of nonvolatile computer storage media, the computer-readable storage medium storage
Have an at least executable instruction, the computer executable instructions can perform in above-mentioned any means embodiment based on big data
User's portrait building method.
Fig. 5 shows a kind of structural representation of computing device according to an embodiment of the invention, of the invention specific real
Specific implementation of the example not to computing device is applied to limit.
As shown in figure 5, the computing device can include：Processor (processor) 502, communication interface
(Communications Interface) 504, memory (memory) 506 and communication bus 508.
Wherein：
Processor 502, communication interface 504 and memory 506 complete mutual communication by communication bus 508.
Communication interface 504, for being communicated with the network element of miscellaneous equipment such as client or other servers etc..
Processor 502, for configuration processor 510, it can specifically perform above-mentioned user's portrait construction side based on big data
Correlation step in method embodiment.
Specifically, program 510 can include program code, and the program code includes computer-managed instruction.
Processor 502 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that computing device includes, can be same type of processor, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 506, for depositing program 510.Memory 506 may include high-speed RAM memory, it is also possible to also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 510 specifically can be used for so that processor 502 perform in above-mentioned any means embodiment based on big data
User draw a portrait building method.The specific implementation of each step may refer to above-mentioned user's portrait based on big data in program 510
Corresponding description in corresponding steps and unit in constructed embodiment, will not be described here.Those skilled in the art can be clear
Recognize to Chu, for convenience and simplicity of description, the equipment of foregoing description and the specific work process of module, may be referred to foregoing
Corresponding process description in embodiment of the method, will not be repeated here.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
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 to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) are drawn a portrait structure to realize the user according to embodiments of the present invention based on big data
The some or all functions of some or all parts in manufacturing apparatus.The present invention is also implemented as being used to perform institute here
The some or all equipment or program of device of the method for description are (for example, computer program and computer program production
Product).Such program for realizing the present invention can store on a computer-readable medium, or can have one or more
The form of signal.Such signal can be downloaded from internet website and obtained, and either be provided or on carrier signal to appoint
What other forms provides.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
- The building method 1. a kind of user based on big data draws a portrait, including：Obtain user's geographical location information and user operates the behavioural information of application program；Position point sequence is generated according to user's geographical location information；The position point sequence is learnt using the first deep learning algorithm, it is special to obtain user geographical position corresponding to user Sign vector；The behavioural information is learnt using the second deep learning algorithm, obtains user behavior characteristic vector；Drawn a portrait based on user behavior characteristic vector structuring user's described in user's geographic location feature vector sum.
- 2. the method according to claim 11, wherein, it is described to enter one according to user's geographical location information generation position point sequence Step includes：The geographical location information is combined processing, generation positional information track；Location point peripheral information is obtained based on the location point on positional information track, generates position point sequence；It is described that the position point sequence is learnt using the first deep learning algorithm, obtain user's geography position corresponding to user Characteristic vector is put to further comprise：Sequence Learning is carried out to the position point sequence using trained time recurrent neural network, obtained corresponding to user User's geographic location feature vector.
- 3. method according to claim 1 or 2, wherein, it is described to utilize the second deep learning algorithm to the behavioural information Learnt, obtain user behavior characteristic vector and further comprise：The action trail of user's operation application program is obtained according to the behavioural information；The action trail of application program is operated according to user, generates behavior sequence；Sequence Learning is carried out to the behavior sequence using trained time recurrent neural network, obtains user behavior feature Vector.
- 4. according to the method described in claim any one of 1-3, wherein, methods described also includes：According to user's geography position Confidence breath generation location consistency characteristic vector；It is described to be further comprised based on user's geographic location feature vector sum user behavior characteristic vector structuring user's portrait：Checking treatment is carried out to user's geographic location feature vector according to the location consistency characteristic vector；Drawn a portrait according to user's geographic location feature vector sum user behavior characteristic vector structuring user's after checking treatment.
- 5. according to the method described in claim any one of 1-4, wherein, after structuring user's portrait, methods described also includes： Based on user portrait sample training user interest modeling hobbies；The user's portrait input for being analysed to user is analyzed to user interest modeling hobbies, obtains the interest love of the user It is good.
- 6. according to the method described in claim any one of 1-4, wherein, after structuring user's portrait, methods described also includes： Drawn a portrait based on the user and analyze whether user has abnormal behaviour.
- 7. according to the method described in claim any one of 1-6, wherein, user's geographical location information includes：IP information, WIFI information, base station information and/or GPS information.
- The constructing apparatus 8. a kind of user based on big data draws a portrait, including：Acquisition module, the behavioural information of application program is operated suitable for obtaining user's geographical location information and user；First generation module, suitable for generating position point sequence according to user's geographical location information；First study module, suitable for learning using the first deep learning algorithm to the position point sequence, obtain user couple The user's geographic location feature vector answered；Second study module, suitable for learning using the second deep learning algorithm to the behavioural information, obtain user behavior Characteristic vector；User's portrait constructing module, suitable for based on user behavior characteristic vector structure described in user's geographic location feature vector sum Make user's portrait.
- 9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage Device and the communication interface complete mutual communication by the communication bus；The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device such as right will Ask the user based on big data any one of 1-7 to draw a portrait corresponding to building method to operate.
- 10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium Make user based on big data of the computing device as any one of claim 1-7 draw a portrait to grasp corresponding to building method Make.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711092706.5A CN107807997A (en) | 2017-11-08 | 2017-11-08 | User's portrait building method, device and computing device based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711092706.5A CN107807997A (en) | 2017-11-08 | 2017-11-08 | User's portrait building method, device and computing device based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107807997A true CN107807997A (en) | 2018-03-16 |
Family
ID=61591841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711092706.5A Pending CN107807997A (en) | 2017-11-08 | 2017-11-08 | User's portrait building method, device and computing device based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107807997A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897801A (en) * | 2018-06-14 | 2018-11-27 | 青岛海信移动通信技术股份有限公司 | User behavior determines method and device |
| CN109086377A (en) * | 2018-07-24 | 2018-12-25 | 江苏通付盾科技有限公司 | Generation method, device and the calculating equipment of equipment portrait |
| CN110334936A (en) * | 2019-06-28 | 2019-10-15 | 阿里巴巴集团控股有限公司 | A kind of construction method, device and the equipment of credit qualification Rating Model |
| CN111079023A (en) * | 2019-12-30 | 2020-04-28 | Oppo广东移动通信有限公司 | Target account identification method, device, terminal and storage medium |
| CN111447465A (en) * | 2018-12-29 | 2020-07-24 | 北京奇虎科技有限公司 | Business flow state visualization processing method and device and computing equipment |
| CN111488899A (en) * | 2019-01-29 | 2020-08-04 | 杭州海康威视数字技术股份有限公司 | Feature extraction method, device, equipment and readable storage medium |
| CN112182434A (en) * | 2020-09-28 | 2021-01-05 | 北京红山信息科技研究院有限公司 | User portrait generation method, system, equipment and storage medium |
| CN112465565A (en) * | 2020-12-11 | 2021-03-09 | 加和（北京）信息科技有限公司 | User portrait prediction method and device based on machine learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1589560A (en) * | 2001-11-19 | 2005-03-02 | 意大利电信股份公司 | Method for checking the functionality of a content delivery network,related system and computer product |
| CN104635281A (en) * | 2015-02-17 | 2015-05-20 | 南京信息工程大学 | Method for controlling data quality of automatic meteorological station based on strong weather process correction |
| WO2016010835A1 (en) * | 2014-07-15 | 2016-01-21 | Microsoft Technology Licensing, Llc | Prioritizing media based on social data and user behavior |
| CN105376752A (en) * | 2015-11-11 | 2016-03-02 | 中国联合网络通信集团有限公司 | Method and device for determining key factors influencing development of mobile network |
| CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
| CN107291841A (en) * | 2017-06-01 | 2017-10-24 | 广州衡昊数据科技有限公司 | A kind of method and system based on position and the social target of user's portrait intelligent Matching |
-
2017
- 2017-11-08 CN CN201711092706.5A patent/CN107807997A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1589560A (en) * | 2001-11-19 | 2005-03-02 | 意大利电信股份公司 | Method for checking the functionality of a content delivery network,related system and computer product |
| WO2016010835A1 (en) * | 2014-07-15 | 2016-01-21 | Microsoft Technology Licensing, Llc | Prioritizing media based on social data and user behavior |
| CN104635281A (en) * | 2015-02-17 | 2015-05-20 | 南京信息工程大学 | Method for controlling data quality of automatic meteorological station based on strong weather process correction |
| CN105376752A (en) * | 2015-11-11 | 2016-03-02 | 中国联合网络通信集团有限公司 | Method and device for determining key factors influencing development of mobile network |
| CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
| CN107291841A (en) * | 2017-06-01 | 2017-10-24 | 广州衡昊数据科技有限公司 | A kind of method and system based on position and the social target of user's portrait intelligent Matching |
Non-Patent Citations (2)
| Title |
|---|
| 原娟娟等: "基于"用户画像"的农产品电商平台精准营销模式设计", 《电子商务》 * |
| 黄文彬等: "数据驱动的移动用户行为研究框架与方法分析", 《情报科学》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897801A (en) * | 2018-06-14 | 2018-11-27 | 青岛海信移动通信技术股份有限公司 | User behavior determines method and device |
| CN109086377A (en) * | 2018-07-24 | 2018-12-25 | 江苏通付盾科技有限公司 | Generation method, device and the calculating equipment of equipment portrait |
| CN109086377B (en) * | 2018-07-24 | 2021-02-02 | 江苏通付盾科技有限公司 | Equipment portrait generation method and device and computing equipment |
| CN111447465A (en) * | 2018-12-29 | 2020-07-24 | 北京奇虎科技有限公司 | Business flow state visualization processing method and device and computing equipment |
| CN111488899A (en) * | 2019-01-29 | 2020-08-04 | 杭州海康威视数字技术股份有限公司 | Feature extraction method, device, equipment and readable storage medium |
| CN111488899B (en) * | 2019-01-29 | 2024-02-23 | 杭州海康威视数字技术股份有限公司 | Feature extraction method, device, equipment and readable storage medium |
| CN110334936A (en) * | 2019-06-28 | 2019-10-15 | 阿里巴巴集团控股有限公司 | A kind of construction method, device and the equipment of credit qualification Rating Model |
| CN110334936B (en) * | 2019-06-28 | 2023-09-29 | 创新先进技术有限公司 | Method, device and equipment for constructing credit qualification scoring model |
| CN111079023A (en) * | 2019-12-30 | 2020-04-28 | Oppo广东移动通信有限公司 | Target account identification method, device, terminal and storage medium |
| CN112182434A (en) * | 2020-09-28 | 2021-01-05 | 北京红山信息科技研究院有限公司 | User portrait generation method, system, equipment and storage medium |
| CN112465565A (en) * | 2020-12-11 | 2021-03-09 | 加和（北京）信息科技有限公司 | User portrait prediction method and device based on machine learning |
| CN112465565B (en) * | 2020-12-11 | 2023-09-26 | 加和（北京）信息科技有限公司 | User portrait prediction method and device based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807997A (en) | User's portrait building method, device and computing device based on big data | |
| Bianchi et al. | Industrial policy for the manufacturing revolution: Perspectives on digital globalisation | |
| Mahajan et al. | Diffusion of new products: Empirical generalizations and managerial uses | |
| CN107862053A (en) | User's portrait building method, device and computing device based on customer relationship | |
| CN107729560A (en) | User's portrait building method, device and computing device based on big data | |
| CN105335409B (en) | A kind of determination method, equipment and the network server of target user | |
| Hawaldar et al. | The study on digital marketing influences on sales for B2B start-ups in South Asia | |
| CN107798118A (en) | User's portrait building method, device and computing device based on big data | |
| Liu et al. | Simulating the conversion of rural settlements to town land based on multi-agent systems and cellular automata | |
| CN111415199A (en) | Customer prediction updating method and device based on big data and storage medium | |
| CN106909560B (en) | Interest point ordering method | |
| CN109325845A (en) | A kind of financial product intelligent recommendation method and system | |
| CN110942338A (en) | Marketing enabling strategy recommendation method and device and electronic equipment | |
| CN113139140B (en) | Tourist attraction recommendation method based on space-time perception GRU and combined with user relationship preference | |
| CN110264270A (en) | A kind of behavior prediction method, apparatus, equipment and storage medium | |
| Lee et al. | Social preferences for small-scale solar photovoltaic power plants in South Korea: A choice experiment study | |
| CN105308591A (en) | Dynamics of tie strength from social interaction | |
| WO2021036184A1 (en) | Method and system for recommending target transaction code laying area | |
| Song et al. | An application of reinforced learning-based dynamic pricing for improvement of ridesharing platform service in seoul | |
| CN107077455A (en) | Flow mass is determined using the score traffic based on event | |
| CN115345530A (en) | Market address recommendation method, device and equipment and computer readable storage medium | |
| Jatschka et al. | A general cooperative optimization approach for distributing service points in mobility applications | |
| Becerra-Rozas et al. | Embedded learning approaches in the whale optimizer to solve coverage combinatorial problems | |
| Yuan et al. | Factors influencing the project duration of urban village redevelopment in contemporary China | |
| CN110335061A (en) | Trade mode portrait method for building up, device, medium and electronic equipment |
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 |
Application publication date: 20180316 |
|
| RJ01 | Rejection of invention patent application after publication |