CN110147821A - Targeted user population determines method, apparatus, computer equipment and storage medium - Google Patents
Targeted user population determines method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110147821A CN110147821A CN201910301218.3A CN201910301218A CN110147821A CN 110147821 A CN110147821 A CN 110147821A CN 201910301218 A CN201910301218 A CN 201910301218A CN 110147821 A CN110147821 A CN 110147821A
- Authority
- CN
- China
- Prior art keywords
- user
- targeted
- population
- behavior data
- common trait
- 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
- 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
-
- 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
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The invention discloses a kind of targeted user populations to determine method, apparatus, computer equipment and storage medium, which comprises establishes test assignment according to the user tag in default tag library, and sends client for the test assignment;The field feedback after user completes the test assignment is obtained from the client;The field feedback and the user day regular data in presetting database are combined, user behavior data collection is obtained;The user behavior data collection is screened according to default dimension, obtains the targeted user population with common trait information, wherein the common trait information is corresponding with the default dimension.Technical solution of the present invention is solved when facing the user group of substantial amounts, it is difficult to the problem of accurately determining targeted user population.
Description
Technical field
The present invention relates to field of information processing more particularly to targeted user population determine method, apparatus, computer equipment and
Storage medium.
Background technique
Precisely sold similar for target group with traditional merchant, social platform Internet-based or product also need
Lean operation is carried out for specific target group.Since different users has different personal preferences, to fangle
Attention rate, to susceptibility of price etc., it is numerous, therefore, the network operators of platform or product it should be understood that they
User, and specific target group are found out from huge user group, further operation then is done to this partial mass.
Traditional targeted user population method of determination depends on manual operation more, for example, carrying out questionnaire survey, electricity to user
Words return visit etc., alternatively, only carrying out the accurate matching of keyword to back-end data.However, with the high speed development of internet and use
The otherness of family increasing number, data is also increasing.By taking internet social platform as an example, the quantity for registering user is generally reached
Necessarily or even more than one hundred million ranks, traditional method are difficult to accurately distinguish potential user group from the user group of substantial amounts
Body.
Summary of the invention
The embodiment of the present invention provides a kind of targeted user population and determines method, apparatus, computer equipment and storage medium, with
It solves when facing the user group of substantial amounts, it is difficult to the problem of accurately determining targeted user population.
A kind of targeted user population determines method, comprising:
Test assignment is established according to the user tag in default tag library, and sends client for the test assignment;
The field feedback after user completes the test assignment is obtained from the client;
The field feedback and the user day regular data in presetting database are combined, user behavior number is obtained
According to collection;
The user behavior data collection is screened according to default dimension, obtains having the target of common trait information to use
Family group, wherein the common trait information is corresponding with the default dimension.
A kind of targeted user population determining device, comprising:
Test module, for establishing test assignment according to the user tag preset in tag library, and by the test assignment
It is sent to client;
Information acquisition module, for obtaining the user feedback letter after user completes the test assignment from the client
Breath;
Data binding modules, for tying the field feedback and the user day regular data in presetting database
It closes, obtains user behavior data collection;
Categorization module obtains having common special for screening the user behavior data collection according to default dimension
The targeted user population of reference breath, wherein the common trait information is corresponding with the default dimension.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize above-mentioned targeted user population determination side when executing the computer program
Method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes that above-mentioned targeted user population determines method when being executed by processor.
Above-mentioned targeted user population determines method, apparatus, computer equipment and storage medium, according in default tag library
User tag establishes test assignment, sends client for test assignment;And the user feedback after test assignment is completed with user
Information, i.e. user are to the response condition of test assignment as one of the foundation classified to user group;User feedback is believed
User day regular data in breath and presetting database is collectively as user behavior data collection, then according to default dimension to user's row
It is screened for data set, obtains the targeted user population with common trait information, wherein common trait information and default dimension
It spends corresponding;It is i.e. empty from the multidimensional data for collectively forming user behavior by the instant behavioral data of user and user's daily behavior data
Between in, find out the common trait information of targeted user population, the common trait information of the target group enabled more comprehensively,
The accurately real behavior of reaction user can more accurately find out target complex when facing the user group of substantial amounts
Body saves the time and efforts of network operator, promotes efficiency of operation.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram that targeted user population determines method in one embodiment of the invention;
Fig. 2 is the flow chart that targeted user population determines method in one embodiment of the invention;
Fig. 3 is the flow chart that targeted user population determines step S4 in method in one embodiment of the invention;
Fig. 4 is the flow chart that targeted user population determines step S3 in method in one embodiment of the invention;
Fig. 5 is the flow chart that target labels are obtained in one embodiment of the invention;
Fig. 6 is the schematic diagram of targeted user population determining device in one embodiment of the invention;
Fig. 7 is the schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Targeted user population provided by the invention determines method, can be applicable in the application environment such as Fig. 1, wherein service
End is the computer equipment for obtaining targeted user population, and server-side can be server or server cluster;Client is target
Computer terminal used by a user in user group, including but not limited to PC machine, mobile phone, tablet computer or other intelligence
It can terminal device;By network connection between client and server-side, network can be cable network or wireless network.The present invention
The targeted user population that embodiment provides determines that method is applied to server-side.
In one embodiment, as shown in Fig. 2, providing a kind of targeted user population determines method, specific implementation flow
Include the following steps:
S1: test assignment is established according to the user tag in default tag library, and sends client for test assignment.
User tag is the keyword or word for classifying to user.For example, " travelling ", " to Price Sensitive ", " purchase
Object ", " residence " etc..User tag can reflect certain features of user, possess the different use of the user representative of different labels
Family group.For example, if certain user possesses these labels such as " residence ", " take-away ", " chasing after play ", it substantially can reflect out the use
The behavioral characteristic at family.
Default tag library is to store the data structure of user tag.Specifically, default tag library can be database, data
Library can be deployed in server-side local, can also be connected by network with server-side.
User tag in default tag library can classify according to actual life.For example, can according to " clothing ",
" food ", " firmly ", " row " are divided into four classes;Can also according to " politics ", " economy ", " culture ", " amusement ", " sport " if etc. be divided into
Dry major class.Several user tags of each classification subordinate, such as " residence ", " open air ", " shopping ", " travelling ", " cuisines ".
Test assignment is to be established by server-side, and be sent to client, by the data collector of client executing.Test is appointed
The instant behavior being engaged in for obtaining user, user to the reaction of test assignment by as to user group classify according to it
One.
Test assignment can periodically be created by server-side, and the feedback letter of user is constantly collected with period regular hour
Breath.
Test assignment can be divided into different themes according to the needs of practical application.For example, red packet reward, reward on total mark,
Preferential activity, current events hot news, the red amusement information of net on line or under line etc..
The form of expression of test assignment can be the data collector based on pop-up interface, i.e. server-side is by pop-up circle
Face is pushed to client, after user clicks pop-up interface by client, movement or user that test assignment clicks user
The content of input is sent to server-side by HTTP, then server-side you can learn that user click action, wherein pop-up interface
Content can be the animation or text of advertising, if user is interested, can click pop-up.Alternatively, test assignment can be
One trivial games of server-side publication, notification message first pushed, etc..
Specifically, server-side can choose some user tags according to the needs of practical application from default tag library, will
User tag is bound with test assignment, then sends client corresponding to a certain number of user groups for test assignment
On end.
Wherein, label is chosen from default tag library, the label of preset quantity can be chosen respectively according to different classifications,
Label can also be randomly selected;User tag and test assignment are bound, i.e., by the feedback data of test assignment and user
Label establishes corresponding relationship, for example, by id (identification, identity) numbers id with user tag of test assignment
Number correspondence;During sending client for test assignment, it can specifically include diversified forms, for example, sending to client
Pop-up interface issues the SMS Tip with URL to client, sends a notification message to client.
S2: the field feedback after user completes test assignment is obtained from client.
Field feedback is to be transmitted to the feedback data of server-side after user completes test assignment.
When user completes test assignment in client, then server-side receives the field feedback from test assignment.Its
In, field feedback includes at least No. id of user identity information and user tag.If test assignment is provided with defeated to user
The interface entered, then field feedback further includes the information that user inputs during completing test assignment.User identifier letter
Breath specifically can be user No. id;The information that user inputs during completing test assignment can be user and be appointed according to test
The data of the prompt input of business, for example, prompting user's input handset number in an activity pop-up interface about prize drawing, then using
The cell-phone number at family is the data of prompt input of the user according to test assignment.
By taking pop-up interface as an example, pop-up interface can be one with the Web page for submitting function, and pop-up can wrap in interface
Include the materials such as picture, video, dynamic picture or text.Pop-up interface when the user clicks, then pop-up interface will be to representing server-side
The URL (Uniform Resource Locator, uniform resource locator) of address sends HTTP message, and server-side can basis
HTTP message makes a response the respondent behavior of user.It is to be appreciated that if in pop-up interface including the submission that user can input
List, then as user in list input data and submit after, server-side can be collected into the input information of user.
Server-side enters information as user feedback letter for user identity information, user tag id or other users
Breath, and can be with associated storage into database.
Alternatively, server-side can also save field feedback in the form of key-value pair.For example, field feedback is stored
For JSON file.Wherein, JSON (JavaScript Object Notation, JS object numbered musical notation) is a kind of data of lightweight
Exchange format.JSON file is stored with ASCII coding mode, can be quick by computer program independent of operating system
Reading or generation, be a kind of data interchange format of prevalence.
S3: field feedback and the user day regular data in presetting database are combined, user behavior number is obtained
According to collection.
Presetting database is the database for storing user information.The daily data of user in presetting database include using
Family since registration when, to Account Closure before all data.Specifically, the daily data of user include but is not limited to that user is basic
The information on services etc. that information, user login information, user interaction information, user enjoy or buy.
Wherein, user basic information includes but is not limited to user's registration time, subscriber identity information, as user name, name,
Identification card number etc., the tier levels of user, the email address of user and contact method etc.;User login information includes but is not limited to
User each online and offline time, IP address, the browser used, operating system or smart machine model etc.;User is mutual
Dynamic information include but is not limited to the speech number of user, deliver it is mutual between dynamic message or the quantity and other users of article
Dynamic message etc.;The information on services that user enjoys or buys includes but is not limited to the service class free or charged that user enjoys
Mesh, the right possessed etc..
User behavior data collection is the combination to the user day regular data in field feedback and presetting database.Its
In, user day regular data represents the daily behavior track of user, for example, the daily online and downtime of user has reacted use
Work and rest regular in the part at family;User buys the case where service and has reacted consumption habit and consumption demand of user, etc.;User is anti-
Feedforward information represents user to the extent of reaction of test assignment, is a kind of instant information feedback.For example, if user often triggers
About the test assignment of tourism trip information, then represents user and have deep love for travelling or fermenting plan of travel;If user often touches
The test assignment about Discount Promotion is sent out, then representing user may be a consumer to Price Sensitive;Etc..Therefore, to
Family feedback information in conjunction with user's day regular data in presetting database after user behavior data collection, can be more three-dimensional,
The conduct characteristics of one user of comprehensive description from many aspects.Further data mining work is done to these user behavior data collection
Make, can therefrom obtain the common trait of user.
Specifically, field feedback can be saved in presetting database by server-side, in the base of user day regular data
Increase field feedback on plinth, to constitute user behavior data collection.
S4: screening user behavior data collection according to default dimension, obtains having the target of common trait information to use
Family group, wherein common trait information is corresponding with default dimension.
Default dimension is the angle from network operator, the screening carried out to user group.For example, from user to platform loyalty
The angle really spent is screened, and continuously active user is obtained;It is screened, is obtained not from the angle of customer consumption wish height
With the user of consumption wish;It is screened alternatively, participating in movable enthusiasm according to user, obtains the use of different interest preferences
Family, etc..
Wherein, the user obtained after screening constitutes targeted user population;Common to the user obtained after screening, it is identical
Data be common trait information.Common trait information specifically can be numeric type data or character type data.Numeric type number
According to, it can it is the click volume to certain advertisement page in test assignment, alternatively, the quantity that user posts in platform, etc.;Character type
Data, it can it is the common interest preference of user, such as " outdoor on foot ", " body-building ", alternatively, the behavioural characteristic of user, such as
" rational consumer ", " any active ues ";The trade mark of user's centralized consumption or the title of service, etc..
Default dimension can specifically show as the set of keyword or keyword.For example, from user to platform loyalty
When angle is screened, the keyword for presetting dimension can be " loyalty ", " iron powder " or " dead loyal " etc..
User behavior data collection is screened according to preset dimension, detailed process includes but is not limited to following several:
(1) it is screened from angle of the user to platform loyalty, specific can be subdivided into again from user's registration, user is lived
Jump, user are retained, the five big stages of user's silencing and customer churn divide user.
Wherein, successive according to the user's registration time, user can be divided into new user and old user;It is continuous according to user
Or number of registering, login times, speech number for adding up etc., user can be divided into any active ues and inactive users;For
Inactive users can be classified as silent user if continuous or accumulative silencing is more than certain time, if continuous or accumulative silencing is super
Certain number is crossed, but user logs on or registers within the default time limit, then can be classified as and retain user;For silent user,
If continuing continuous or accumulative silencing is more than certain time, the user of loss can be classified as.
(2) it screens from the consumption wish height of user, user to user feedback information can specifically be screened,
And the related record with consumption in user day regular data is counted, such as consumption history record or the cumulative consumption amount of money
Deng.
Wherein, if it is more than a quota that user day regular data, which shows that certain user has more consumer record or the cumulative consumption amount of money,
Degree, and the test assignment lukewarm response to rewarding about red packet are seldom participated in robbing red packet activity, then can be classified as the user
The consumer group of inclined rationality;If user day regular data shows that certain customer consumption frequency is very high, and to about the red focus incident of net
Test assignment pay special attention to, then the user can be classified as impulsion consumption propensity the consumer group.
(3) it is screened from the situation of user's participation activity, specifically of user can be obtained according to the participation of user
People's preference, so that it is determined that user belongs to different target group.
Wherein, activity can be the questionnaire survey for having game and interest or be extended to objective with subject content
Trivial games, etc..For example, server-side can be according to the more of the number of participation with a trivial games based on the environmentally friendly knowledge of popularization
It is few, determine the number of users that environmental protection is paid close attention in user group.
Specifically, by taking trivial games as an example, server-side can obtain the user id for participating in trivial games from Web page, then
According to the number of users that user id confirmation participates in, so that it is determined that targeted user population out.
In the present embodiment, test assignment is established according to the user tag in default tag library, sends test assignment to
Client;And the field feedback after test assignment is completed with user, i.e. response condition conduct pair of the user to test assignment
One of the foundation that user group classifies;By the user day regular data in field feedback and presetting database collectively as
Then user behavior data collection screens user behavior data collection according to default dimension, obtains with common trait information
Targeted user population, wherein common trait information is corresponding with default dimension;I.e. from by the instant behavioral data of user and user
Daily behavior data collectively form in the multi-dimensional data space of user behavior, find out the common trait information of targeted user population,
The common trait information of the target group enabled more comprehensively, accurately reacts the real behavior of user, can face
When the user group of substantial amounts, target group are more accurately found out, save the time and efforts of network operator, promote operation effect
Rate.
Further, in one embodiment, for step S4, i.e., user behavior data collection is sieved according to default dimension
Choosing, obtains the targeted user population with common trait information, wherein common trait information is corresponding with default dimension, specifically
May include:
According to the corresponding field value condition of default dimension, is filtered out from user behavior data concentration and meet field value item
The user of part forms the targeted user population with common trait information.
Wherein, presetting the corresponding field of dimension specifically can be the literary name section in presetting database, alternatively, in test assignment
Obtain the variable of field feedback.For example, user couple can be reacted if screening from angle of the user to platform loyalty
The field of platform loyalty can be that literary name section " the continuous landing time of user " in presetting database, " user continuously registers time
Number " etc..Alternatively, to obtain the variables of user clicks, field as corresponding with default dimension in test assignment.
The value condition of field is the value range of field value, is the filtering rod screened to user behavior data collection
Part, for example, the value condition of field can be on or below preset threshold or within default value range.Citing comes
It says, screens the user high to platform loyalty, the value of literary name section " user's registration time " can be chosen before 2009
User, and the value of literary name section " the continuous login time of user " is more than 30 days users.
Specifically, server-side can choose the value range of several fields corresponding with default dimension as screening item
Part screens user behavior data collection, obtains the user for meeting field value condition, so that composition has common trait letter
The targeted user population of breath.
For example, server-side can be using user's registration, active time field as querying condition, from presetting database
It is matched, obtains the user for meeting field value condition;Alternatively, can according to user identity information to it in presetting database
In user's day regular data and field feedback of its feedback be compared;Obtain the user for meeting field value condition.
In the present embodiment, server-side is according to the corresponding field value condition of default dimension, to user behavior data collection into
Row screening, meets the user of field value condition, so that composition has the targeted user population of common trait information;I.e. with field
With field value as screening conditions, the target with common trait information corresponding with default dimension can be accurately matched
User group.
Further, in one embodiment, as shown in figure 3, being directed to step S4, i.e., according to default dimension to user behavior number
It is screened according to collection, obtains the targeted user population with common trait information, wherein common trait information and default dimension phase
It is corresponding, can also specifically it include the following steps:
S42: clustering is carried out to the user behavior data that user behavior data is concentrated, obtains at least two users point
Group.
Clustering refers to that the set by physics or abstract object is grouped into the analysis for the multiple classes being made of similar object
Process.It can be classified automatically to batch of data using clustering, and not have to carry out category division to batch of data in advance,
The movement of artificial default classification standard is reduced with this.Meanwhile when the data volume for needing to screen is especially big, the number of millions as above
According to record, and the content of data is complicated, is not easy to genealogical classification, carries out preliminary screening to data using clustering, obtains
Several groupings.
It generallys use cluster algorithm and carries out clustering.Cluster algorithm include but is not limited to hierarchical clustering method,
Decomposition method, dynamic state clustering, clustering ordered samples, has overlapping to cluster and fuzzy clustering etc. at addition method.
The user behavior data that user behavior data is concentrated, including user day regular data and field feedback.
Specifically, server-side can be passed to SPSS (Statistical using user behavior data collection as input
Product and Service Solutions, statistical product and service solution) in carry out clustering operation, thus
User is divided into different user groups by realization, obtains at least two user groupings.
Wherein, SPSS be IBM Corporation release it is a series of for statistical analysis operation, data mining, forecast analysis and
The software product of decision support task and the general name of related service.A variety of cluster algorithms are integrated in SPSS.Server-side benefit
Quickly a large amount of user behavior data collection can be divided with SPSS.
S43: feature extraction is carried out to user behavior data different in each user grouping, obtains each user grouping
Grouping feature.
After clustering, server-side needs to carry out feature to user behavior data different in each user grouping to mention
It takes, some common traits having between the obtained user in each user grouping, these common traits are user grouping
Grouping feature.
Specifically, server-side can be compared the user behavior data collection of user each in user grouping, find out row
For value identical in data set.
For example, after the clustering of SPSS, in an obtained user grouping, the line duration of each user is 21
After point, and shopping way is based on online shopping, night program request Online Video content based on literature and art or science fiction content, then
These features are to constitute the grouping feature of the user grouping, are represented a kind of using residence culture as the younger age group of keynote.
Further, server-side can be characteristic labeling by these, obtains the labels such as " residence culture ", " young man ", to
Represent the grouping feature of user grouping.
S44: by the corresponding user grouping of the grouping feature to match with default dimension, forming has common trait information
Targeted user population.
If network operator does not know about or not exclusively understands such user group but it needs to be determined that a kind of targeted user population
Feature, then clustering first can be carried out to data, obtain inhomogeneous user grouping, it is then that the grouping of user grouping is special
Sign is matched with default dimension, so that it is determined that the targeted user population with common trait information.
Specifically, server-side matches the grouping feature of labeling with default dimension, i.e., by grouping feature and representative
The keyword of default dimension is compared, if grouping feature matches with the keyword for representing default dimension, grouping feature institute
User grouping belong to the targeted user population with common trait information, wherein common trait information and default dimension phase
It is corresponding.
In the present embodiment, server-side carries out clustering to the user behavior data that user behavior data is concentrated, i.e., sharp
Preliminarily automatic classification is carried out to user behavior data collection with clustering, reduces the movement of artificial default classification standard;Then
Feature extraction carried out to the user behavior data in the user grouping obtained after clustering, and according to obtaining after feature extraction
The matching relationship of grouping feature and default dimension determines targeted user population, so that when facing large amount of complex data, Ke Yigeng
Quickly determine targeted user population.
Further, in one embodiment, as shown in figure 4, being directed to step S3, i.e., by field feedback and preset data
User day regular data in library is combined, and is obtained user behavior data collection, is specifically comprised the following steps:
S31: user identity information is obtained from field feedback, and according to user identity information from presetting database
It extracts and the matched user day regular data of user identity information.
User identity information is used for the information of one user identity of unique identification, for example, specifically can be user No. id.?
In test assignment, the feedback information of each test assignment includes user identity information.Meanwhile in the preset database, each
The data record of user can be got according to user identity information.
Specifically, server-side can obtain user identity information from the field of field feedback, and with user identifier
Information is querying condition, and acquisition and the matched user day regular data of user identity information, i.e., appoint test from presetting database
The day regular data of the user of feedback in the preset database is made in business.
S32: field feedback and user day regular data are associated storage, and as user behavior data collection.
Specifically, new field can be added in user day regular data in server-side, to save field feedback, make
User day regular data and field feedback can be inquired according to user identity information by obtaining.
For example, the feedback fields that Add User in the tables of data for being stored with user day regular data, user feedback field are specific
Including the user feedback time, No. id of test assignment, the corresponding user tag title of test assignment, the corresponding user of test assignment
The classification of label and other data etc. of user's input;The field feedback received is sequentially inserted into phase by server-side
In the field answered, to form user behavior data collection by field feedback and the daily data of user.
In the present embodiment, server-side carries out field feedback and user day regular data according to user identity information
Associated storage is conducive to quickly obtain user's row of structuring when classify to user or data are analyzed
For data set, meanwhile, it is also convenient for user data management.
Further, in one embodiment, as shown in figure 5, after step s4, i.e., according to default dimension to user behavior
Data set is screened, and after obtaining the targeted user population with common trait information, targeted user population determines method also
Include the following steps:
S5: the keyword in common trait information is extracted, and using keyword as target labels.
Specifically, server-side can carry out word frequency statistics to common trait information, i.e., occur in acquisition common trait information
The higher word of frequency is as keyword, and using keyword as target labels.
Further, threshold value can also be arranged to the word frequency of keyword in server-side, be more than the key of preset threshold with word frequency
Word is as target keywords.
S6: the user tag in target labels and default tag library is subjected to comparison of coherence, obtains comparison result.
Specifically, server-side can carry out comparison of coherence with the user tag in target labels and default tag library, that is, look into
It askes in default tag library with the presence or absence of in the consistent user tag of target labels.If the use in target labels and default tag library
Family label is consistent, then represents the common trait of targeted user population to be included into budget tag library.
S7: if comparison result be it is inconsistent, target labels are saved in default tag library.
If target labels and user tag in default tag library carry out comparison of coherence result be it is inconsistent, represent
It has been likely to occur new targeted user population and new user group's feature.Target labels are saved in pre- bidding by server-side
It signs in library, user is tested in order to which target labels can be used when a new round determines targeted user population.
In the present embodiment, server-side extracts the keyword in common trait information, and using keyword as target labels,
I.e. using keyword as the feature tag of targeted user population, and the user tag in target labels and default tag library is carried out
Comparison of coherence, with user group's feature of the user group and Xin that determine whether to occur new, meanwhile, to new user tag into
Row saves, and allows to the use when a new round determines targeted user population, that is, increases the user tag in default tag library,
Increase the range of identifiable user group.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of targeted user population determining device is provided, the targeted user population determining device with it is upper
It states targeted user population in embodiment and determines that method corresponds.As shown in fig. 6, the targeted user population determining device includes surveying
Die trial block 61, information acquisition module 62, data binding modules 63 and categorization module 64.Detailed description are as follows for each functional module:
Test module 61 for establishing test assignment according to the user tag preset in tag library, and test assignment is sent out
It is sent to client;
Information acquisition module 62, for obtaining the field feedback after user completes test assignment from client;
Data binding modules 63, for tying field feedback and the user day regular data in presetting database
It closes, obtains user behavior data collection;
Categorization module 64 is obtained for screening according to default dimension to user behavior data collection with common trait
The targeted user population of information, wherein common trait information is corresponding with default dimension.
Further, categorization module 64, comprising:
Field filter submodule 641 presets the corresponding field value condition of dimension for basis, from user behavior data collection
In filter out the user for meeting field value condition, form the targeted user population with common trait information.
Further, categorization module 64, further includes:
Clustering submodule 642, the user behavior data for concentrating to user behavior data carry out clustering, obtain
To at least two user groupings;
Feature extraction submodule 643, for carrying out feature extraction to user behavior data different in each user grouping,
Obtain the grouping feature of each user grouping;
It is grouped matched sub-block 644, the corresponding user grouping of grouping feature for will match with default dimension, composition
Targeted user population with common trait information.
Further, data binding modules 63, comprising:
Submodule 631 is inquired, for obtaining user identity information from field feedback, and according to user identity information
It is extracted from presetting database and the matched user day regular data of user identity information;
Sub-module stored 632, for field feedback and user day regular data to be associated storage, and as user
Behavioral data collection.
Further, user group's determining device is marked, further includes:
Keyword-extraction module 65 extracts the keyword in common trait information, and using keyword as target labels;
Feature comparison module 66, for the user tag in target labels and default tag library to be carried out comparison of coherence,
Obtain comparison result;
Target labels determining module 67, if for comparison result be it is inconsistent, target labels are saved in default label
In library.
Specific restriction about targeted user population determining device may refer to determine above for targeted user population
The restriction of method, details are not described herein.Modules in above-mentioned targeted user population determining device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize that a kind of targeted user population determines method.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize target user in above-described embodiment when executing computer program
Group determines the step of method, such as step S1 shown in Fig. 2 to step S4.Alternatively, reality when processor executes computer program
The function of each module/unit of targeted user population determining device in existing above-described embodiment, such as module 61 shown in Fig. 6 is to module
64 function.To avoid repeating, which is not described herein again.
In one embodiment, a computer readable storage medium is provided, computer program, computer program are stored thereon with
Realize that targeted user population determines method in above method embodiment when being executed by processor, alternatively, the computer program is located
Manage the function that each module/unit in targeted user population determining device in above-mentioned apparatus embodiment is realized when device executes.To avoid
It repeats, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided by the present invention,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of targeted user population determines method, which is characterized in that the targeted user population determines that method includes:
Test assignment is established according to the user tag in default tag library, and sends client for the test assignment;
The field feedback after user completes the test assignment is obtained from the client;
The field feedback and the user day regular data in presetting database are combined, user behavior data is obtained
Collection;
The user behavior data collection is screened according to default dimension, obtains the potential user group with common trait information
Body, wherein the common trait information is corresponding with the default dimension.
2. targeted user population as described in claim 1 determines method, which is characterized in that it is described according to default dimension to described
User behavior data collection is screened, and the targeted user population with common trait information is obtained, comprising:
According to the corresponding field value condition of the default dimension, is filtered out from user behavior data concentration and meet the word
The user of section value condition, forms the targeted user population with the common trait information.
3. targeted user population as described in claim 1 determines method, which is characterized in that it is described according to default dimension to described
User behavior data collection is screened, and the targeted user population with common trait information is obtained, further includes:
Clustering is carried out to the user behavior data that the user behavior data is concentrated, obtains at least two user groupings;
Feature extraction is carried out to the user behavior data different in each user grouping, obtains each use
The grouping feature of family grouping;
By the corresponding user grouping of the grouping feature to match with the default dimension, composition has common trait letter
The targeted user population of breath.
4. targeted user population as described in claim 1 determines method, which is characterized in that described by the field feedback
It is combined with the user day regular data in presetting database, obtains user behavior data collection, comprising:
User identity information is obtained from the field feedback, and according to the user identity information from presetting database
It extracts and the matched user day regular data of the user identity information;
The field feedback and the user day regular data are associated storage, and as the user behavior data
Collection.
5. the targeted user population as described in Claims 1-4 is any determines method, which is characterized in that according to default dimension pair
The user behavior data collection is screened, and after obtaining the targeted user population with common trait information, the target is used
Family group determines method, further includes:
The keyword in the common trait information is extracted, and using the keyword as target labels;
User tag in the target labels and the default tag library is subjected to comparison of coherence, obtains comparison result;
If the comparison result be it is inconsistent, the target labels are saved in the default tag library.
6. a kind of targeted user population determining device, which is characterized in that the targeted user population determining device, comprising:
Test module for establishing test assignment according to the user tag preset in tag library, and the test assignment is sent
To client;
Information acquisition module, for obtaining the field feedback after user completes the test assignment from the client;
Data binding modules, for the field feedback and the user day regular data in presetting database to be combined,
Obtain user behavior data collection;
Categorization module is obtained for screening according to default dimension to the user behavior data collection with common trait letter
The targeted user population of breath, wherein the common trait information is corresponding with the default dimension.
7. targeted user population determining device as claimed in claim 6, which is characterized in that the categorization module, comprising:
Field filter submodule, for according to the corresponding field value condition of the default dimension, from the user behavior data
Concentration filters out the user for meeting the field value condition, forms the targeted user population with the common trait information.
8. targeted user population determining device as claimed in claim 6, which is characterized in that the categorization module, further includes:
Clustering submodule, the user behavior data for concentrating to the user behavior data carry out clustering, obtain
At least two user groupings;
Feature extraction submodule is mentioned for carrying out feature to the user behavior data different in each user grouping
It takes, obtains the grouping feature of each user grouping;
It is grouped matched sub-block, the corresponding user grouping of grouping feature for will match with the default dimension, group
At the targeted user population with the common trait information.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
Any one of 5 targeted user populations determine method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization targeted user population determination side as described in any one of claim 1 to 5 when the computer program is executed by processor
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910301218.3A CN110147821A (en) | 2019-04-15 | 2019-04-15 | Targeted user population determines method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910301218.3A CN110147821A (en) | 2019-04-15 | 2019-04-15 | Targeted user population determines method, apparatus, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110147821A true CN110147821A (en) | 2019-08-20 |
Family
ID=67589744
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910301218.3A Pending CN110147821A (en) | 2019-04-15 | 2019-04-15 | Targeted user population determines method, apparatus, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110147821A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110585726A (en) * | 2019-09-16 | 2019-12-20 | 腾讯科技(深圳)有限公司 | User recall method, device, server and computer readable storage medium |
CN110609935A (en) * | 2019-08-29 | 2019-12-24 | 湖南草花互动网络科技有限公司 | User identity tag generation method and device, computer equipment and storage medium |
CN110795638A (en) * | 2019-11-13 | 2020-02-14 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
CN111222048A (en) * | 2020-01-03 | 2020-06-02 | 北京字节跳动网络技术有限公司 | User number query calculation method and device, electronic equipment and storage medium |
CN111782966A (en) * | 2020-06-30 | 2020-10-16 | 北京百度网讯科技有限公司 | User grouping method, device, computer equipment and medium |
CN111833108A (en) * | 2020-07-17 | 2020-10-27 | 上海国际技贸联合有限公司 | Information acquisition, analysis and processing system, method and storage medium |
CN111881270A (en) * | 2020-07-01 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Intelligent dialogue method and system |
CN112559826A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | User group dividing method and device, storage medium and electronic equipment |
CN112737848A (en) * | 2020-12-29 | 2021-04-30 | 青岛海尔科技有限公司 | Object type determination method and device, storage medium and electronic device |
WO2021175021A1 (en) * | 2020-03-06 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Product push method and apparatus, computer device, and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140129324A1 (en) * | 2012-11-06 | 2014-05-08 | Bottlenose, Inc. | System and method for dynamically placing and scheduling of promotional items or content based on momentum of activities of a targeted audience in a network environment |
CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
CN107464142A (en) * | 2017-08-09 | 2017-12-12 | 南京甄视智能科技有限公司 | Method, the user's portrait system for system of being drawn a portrait based on marketing feedback result back feeding user |
CN109086787A (en) * | 2018-06-06 | 2018-12-25 | 平安科技(深圳)有限公司 | User's portrait acquisition methods, device, computer equipment and storage medium |
US20190102652A1 (en) * | 2016-08-31 | 2019-04-04 | Tencent Technology (Shenzhen) Company Limited | Information pushing method, storage medium and server |
-
2019
- 2019-04-15 CN CN201910301218.3A patent/CN110147821A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140129324A1 (en) * | 2012-11-06 | 2014-05-08 | Bottlenose, Inc. | System and method for dynamically placing and scheduling of promotional items or content based on momentum of activities of a targeted audience in a network environment |
CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
US20190102652A1 (en) * | 2016-08-31 | 2019-04-04 | Tencent Technology (Shenzhen) Company Limited | Information pushing method, storage medium and server |
CN107464142A (en) * | 2017-08-09 | 2017-12-12 | 南京甄视智能科技有限公司 | Method, the user's portrait system for system of being drawn a portrait based on marketing feedback result back feeding user |
CN109086787A (en) * | 2018-06-06 | 2018-12-25 | 平安科技(深圳)有限公司 | User's portrait acquisition methods, device, computer equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
林森 等: "基于大数据理论的电力客户标签体系构建", 电气技术, no. 12, pages 98 - 112 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110609935A (en) * | 2019-08-29 | 2019-12-24 | 湖南草花互动网络科技有限公司 | User identity tag generation method and device, computer equipment and storage medium |
CN110585726A (en) * | 2019-09-16 | 2019-12-20 | 腾讯科技(深圳)有限公司 | User recall method, device, server and computer readable storage medium |
CN112559826A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | User group dividing method and device, storage medium and electronic equipment |
CN110795638A (en) * | 2019-11-13 | 2020-02-14 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
CN111222048A (en) * | 2020-01-03 | 2020-06-02 | 北京字节跳动网络技术有限公司 | User number query calculation method and device, electronic equipment and storage medium |
WO2021175021A1 (en) * | 2020-03-06 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Product push method and apparatus, computer device, and storage medium |
CN111782966A (en) * | 2020-06-30 | 2020-10-16 | 北京百度网讯科技有限公司 | User grouping method, device, computer equipment and medium |
CN111782966B (en) * | 2020-06-30 | 2023-07-28 | 北京百度网讯科技有限公司 | User grouping method, device, computer equipment and medium |
CN111881270A (en) * | 2020-07-01 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Intelligent dialogue method and system |
CN111833108A (en) * | 2020-07-17 | 2020-10-27 | 上海国际技贸联合有限公司 | Information acquisition, analysis and processing system, method and storage medium |
CN112737848A (en) * | 2020-12-29 | 2021-04-30 | 青岛海尔科技有限公司 | Object type determination method and device, storage medium and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110147821A (en) | Targeted user population determines method, apparatus, computer equipment and storage medium | |
CN108021929A (en) | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system | |
CN109741146A (en) | Products Show method, apparatus, equipment and storage medium based on user behavior | |
CN105989074A (en) | Method and device for recommending cold start through mobile equipment information | |
CN107871244A (en) | The detection method and device of a kind of advertising results | |
CN102360386A (en) | Intelligent shopping guide system and method of electronic commerce website | |
CN111859160A (en) | Method and system for recommending session sequence based on graph neural network | |
CN108885624A (en) | Information recommendation system and method | |
CN112559896B (en) | Information recommendation method, device, equipment and computer readable storage medium | |
JP2004171042A (en) | Advertisement circulating passage analyzing method, its implementing system and its processing program | |
CN102592236A (en) | Internet advertising crowd analysis system and analysis method | |
CN113177809A (en) | Automatic clustering method and application system for user consumption behaviors based on one-object-one-code | |
CN107370659A (en) | Health control public number extension system and method based on wechat group | |
KR101559719B1 (en) | Auto-learning system and method for derive effective marketing | |
CN101276450A (en) | Information processing device, information processing method and information processing program | |
CN114371946B (en) | Information push method and information push server based on cloud computing and big data | |
Zhang et al. | Mining target users for mobile advertising based on telecom big data | |
CN100555283C (en) | A kind of directly at the dissemination method and the system of user's relevant information | |
CN110362751A (en) | Business recommended method, apparatus, computer equipment and storage medium | |
CN116823410B (en) | Data processing method, object processing method, recommending method and computing device | |
Lee | Changes in marketing brought by AI | |
CN110209944B (en) | Stock analyst recommendation method and device, computer equipment and storage medium | |
CN106030648A (en) | Recommender system and operation method thereof | |
Halkiopoulos et al. | Cultural and tourism promotion through digital marketing approaches. A case study of social media campaigns in Greece | |
Sally et al. | A trend analysis on Sri Lankan politics based on facebook user reactions |
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 |