CN107908740A - Information output method and device - Google Patents
Information output method and device Download PDFInfo
- Publication number
- CN107908740A CN107908740A CN201711132306.2A CN201711132306A CN107908740A CN 107908740 A CN107908740 A CN 107908740A CN 201711132306 A CN201711132306 A CN 201711132306A CN 107908740 A CN107908740 A CN 107908740A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- probability
- portrait
- happening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The embodiment of the present application discloses information output method and device.One embodiment of this method includes:User's request is obtained, user's request includes user identifier;Inquiry user's portrait information matched with the user identifier in user draws a portrait information aggregate;By the user inquired portrait information input probability of happening prediction model trained in advance, generation probability of happening information corresponding with the user identifier simultaneously exports, the probability of happening prediction model is used for the correspondence for characterizing user's portrait information and probability of happening information, and the probability of happening information is used for the probability that indicating predetermined adopted event occurs.This embodiment offers a kind of forecasting mechanism based on user's portrait information, the method for enriching outgoing event probabilistic information.
Description
Technical field
The invention relates to field of computer technology, more particularly to information output method and device.
Background technology
The data or the testimonial material of offer that some service providers often fill according to user, the behavior to user carry out
Prediction, obtains the probability that predefined event occurs, for example, financial institution can carry according to the true directional user of the list filled in of user
The probability broken a contract for user after loan.
The content of the invention
The embodiment of the present application proposes information output method and device.
In a first aspect, the embodiment of the present application provides a kind of information output method, this method includes:User's request is obtained,
User's request includes user identifier;Inquiry user's portrait information matched with user identifier in user draws a portrait information aggregate;Will
The probability of happening prediction model that the user's portrait information input inquired is trained in advance, it is general to generate event corresponding with user identifier
Rate information simultaneously exports, and probability of happening prediction model is used to characterize user's portrait information and the correspondence of probability of happening information, thing
Part probabilistic information is used for the probability that indicating predetermined adopted event occurs.
In the present embodiment, probability of happening prediction model trains to obtain via following steps:Obtain History Order note
Record set, every History Order record in History Order set of records ends include user identifier and for indicating predetermined justice event
The target information of generation;The user identifier that the History Order record for not including target information in History Order set of records ends is included
It is determined as positive sample user identifier, the History Order comprising target information records the user's mark included in History Order set of records ends
Knowledge is determined as negative sample user identifier;By user's portrait information matched with positive sample user identifier in user's portrait information aggregate
It is determined as positive sample, user's portrait information matched with negative sample user identifier is determined as negative sample in user's portrait information aggregate
This, using machine learning method, training obtains probability of happening prediction model.
In the present embodiment, user's portrait information in user's portrait information aggregate is generated via following steps:It is right
The Network records of the targeted customer produced in preset time period carry out at least one of feature extraction, generation characteristic information;Will at least
One characteristic information is inputted to user's portrait information generation model trained in advance, and generation user's portrait information, user, which draws a portrait, to be believed
Breath generation model is used for the correspondence of characteristic feature information and user's portrait information.
In the present embodiment, Network records include text entry;And the targeted customer to being produced in preset time period
Network records carry out at least one of feature extraction, generation characteristic information, including:To the targeted customer's that is produced in preset time period
Text entry carries out semantic analysis, generates the number that keyword and keyword occur.
In the present embodiment, text entry includes at least one of following:Term, the browsed net of search engine record
The content information of page, the information of social platform issue.
In the present embodiment, Network records include record to be counted;And the targeted customer to being produced in preset time period
Network records carry out feature extraction, generation at least one of characteristic information, including:Used based on the target produced in preset time period
The record to be counted at family, counts the quantity of pre-set item to be counted.
In the present embodiment, record to be counted includes at least one of following:The order record of e-commerce platform, social activity are flat
Good friend's record of platform, the information issue record of the login record of social platform, social platform, target pages browse record.
In the present embodiment, user's portrait information further includes the time dimension information generated according to preset time period.
In the present embodiment, method further includes:Matched in response to the probability of happening information exported with the first presupposed information,
Order is requested to generate according to user.
In the present embodiment, method further includes:Matched in response to the probability of happening information exported with the second presupposed information,
User is asked to send to target device, instruction is generated in response to the order for receiving target device transmission, is asked according to user
Generate order.
Second aspect, the embodiment of the present application provide a kind of information output apparatus, which includes:Acquiring unit, is used for
User's request is obtained, user's request includes user identifier;Query unit, for inquiry and user in drawing a portrait information aggregate in user
Identify matched user's portrait information;Output unit, for the event for training the user inquired portrait information input in advance
Probabilistic Prediction Model, generates probability of happening information corresponding with user identifier and exports, and probability of happening prediction model is used to characterize
The correspondence of user's portrait information and probability of happening information, probability of happening information are used for the general of indicating predetermined adopted event generation
Rate.
In the present embodiment, device further includes probability of happening prediction model training unit, the training of probability of happening prediction model
Unit, is used for:History Order set of records ends is obtained, every History Order record in History Order set of records ends includes user and marks
The target information known and occurred for indicating predetermined adopted event;Going through for target information will not be included in History Order set of records ends
The user identifier that history order record includes is determined as positive sample user identifier, and target information is included in History Order set of records ends
The user identifier that History Order record includes is determined as negative sample user identifier;It will be used in user's portrait information aggregate with positive sample
Family identifies matched user information of drawing a portrait and is determined as positive sample, and user draws a portrait matched with negative sample user identifier in information aggregate
User's portrait information is determined as negative sample, and using machine learning method, training obtains probability of happening prediction model.
In the present embodiment, device further includes user's portrait information generating unit, and user's portrait information generating unit, is used
In:The Network records of targeted customer to being produced in preset time period carry out at least one of feature extraction, generation characteristic information;Will
At least one characteristic information is inputted to user's portrait information generation model trained in advance, generation user's portrait information, Yong Huhua
As information generation model is used for the correspondence of characteristic feature information and user's portrait information.
In the present embodiment, Network records include text entry;And user's portrait information generating unit, further configuration
For:The text entry of targeted customer to being produced in preset time period carries out semantic analysis, generates keyword and keyword
The number of appearance.
In the present embodiment, text entry includes at least one of following:Term, the browsed net of search engine record
The content information of page, the information of social platform issue.
In the present embodiment, Network records include record to be counted;And user's portrait information generating unit, further match somebody with somebody
Put and be used for:Record to be counted based on the targeted customer produced in preset time period, counts the number of pre-set item to be counted
Amount.
In the present embodiment, record to be counted includes at least one of following:The order record of e-commerce platform, social activity are flat
Good friend's record of platform, the information issue record of the login record of social platform, social platform, target pages browse record.
In the present embodiment, user's portrait information further includes the time dimension information generated according to preset time period.
In the present embodiment, device further includes the first order generation unit, and the first order generation unit, is used for:In response to
The probability of happening information exported is matched with the first presupposed information, and order is requested to generate according to user.
In the present embodiment, device further includes the second order generation unit, and the second order generation unit, is used for:In response to
The probability of happening information exported is matched with the second presupposed information, user is asked to send to target device, in response to receiving
The order generation instruction that target device is sent, order is requested to generate according to user.
The third aspect, the embodiment of the present application provide a kind of equipment, including:One or more processors;Storage device, is used
In the one or more programs of storage, when said one or multiple programs are performed by said one or multiple processors so that above-mentioned
One or more processors realize such as the above-mentioned method of first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, it is characterised in that such as first aspect above-mentioned method is realized when the program is executed by processor.
Information output method and device provided by the embodiments of the present application, are asked by obtaining user, then drawn a portrait in user
Inquiry user's portrait information matched with the user identifier in information aggregate, finally by the user inquired portrait information input
Trained probability of happening prediction model in advance, generates probability of happening information corresponding with the user identifier and exports, so as to carry
A kind of forecasting mechanism for information of drawing a portrait based on user, the method for enriching outgoing event probabilistic information are supplied.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that this application can be applied to exemplary system architecture figure therein;
Fig. 2 is the flow chart according to one embodiment of the information output method of the application;
Fig. 3 is a schematic diagram according to the application scenarios of the information output method of the application;
Fig. 4 is a kind of flow chart of optional implementation of trained probability of happening prediction model;
Fig. 5 is the structure diagram according to one embodiment of the information output apparatus of the application;
Fig. 6 is adapted for the structure diagram of the computer system of the server for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
It illustrate only easy to describe, in attached drawing and invent relevant part with related.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the exemplary system of the embodiment of the information output method that can apply the application or information output apparatus
System framework 100.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105,
106.Network 104 between terminal device 101,102,103 and server 105,106 provide communication link medium.Net
Network 104 can include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User 110 can be interacted with using terminal equipment 101,102,103 by network 104 with server 105,106, to connect
Receive or send data etc..Various applications, such as the application of shopping class, map class can be installed on terminal device 101,102,103
Using, pay class application, social class application, web browser applications, the application of search engine class, mobile phone assistant class using etc..
Terminal device 101,102,103 can be had display screen and support the various electronics of data communication function to set
It is standby, include but not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture
Experts Group Audio Layer III, dynamic image expert's compression standard audio aspect 3), MP4 (Moving
Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio aspect 4) player, knee
Mo(u)ld top half pocket computer and desktop computer etc..User can be submitted to server by terminal device 101,102,103 and be used
Ask at family.
Server 105,106 can be to provide the server of various services, such as to pacifying on terminal device 101,102,103
The application of dress provides the background server supported, server 105,106 can obtain user's request, and user's request includes using
Family identifies;Inquiry user's portrait information matched with the user identifier in user draws a portrait information aggregate;The use that will be inquired
Family portrait information input probability of happening prediction model trained in advance, generates probability of happening information corresponding with the user identifier
And export, the probability of happening prediction model is used for the correspondence for characterizing user's portrait information and probability of happening information, described
Probability of happening information is used for the probability that indicating predetermined adopted event occurs.
It should be noted that the information output method that the embodiment of the present application is provided can be performed by server 105,106,
Correspondingly, information output apparatus can be arranged in server 105,106.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow 200 of one embodiment of information output method according to the application is shown.The letter
Output method is ceased, is comprised the following steps:
Step 201, user's request is obtained.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information output method operation thereon can
Asked with obtaining user using the terminal of its submission request from user by wired connection mode or radio connection.Need
, it is noted that above-mentioned radio connection can include but is not limited to 3G/4G connections, WiFi connections, bluetooth connection, WiMAX companies
Connect, Zigbee connections, UWB (ultra wideband) connections and other it is currently known or in the future exploitation wireless connection sides
Formula.User's request can be permitted or be ratified etc. the information of processing with one side of device to be serviced that user submits.As an example, user
Request can be the request of participation activity, or generate the request of order (loan order, leasehold article order).User's request includes
User identifier, user identifier can be the information that the account of user, cell-phone number, mailbox etc. can be used for identifying user.
Step 202, inquiry user's portrait information matched with user identifier in user draws a portrait information aggregate.
In the present embodiment, above-mentioned electronic equipment can be inquired about with being obtained in step 201 in user draws a portrait information aggregate
The matched user of the user identifier that includes of user's request draw a portrait information.User draws a portrait information can be including remembering the network of user
Record the attribute information handled.Network records can be user by terminal access website or using caused by application
Data, for example, user's browses record, order data, logistics information and the other information of issue.
User's portrait information can include polytype information, for example, user draws a portrait, information can include age of user
Section, user's occupation, user behavior preference (tourism, civil servant examination), (family has old man, family to have child, family to have to subscriber household structure
Middle school student, two tire families), customer consumption situation (number that buys luxuries, restaurant class), user's asset-liabilities (whether have car,
Residential quarter class), user educate experience, feature (place city, subscriber household address, job stability) etc. under line.Can be with
User's portrait information of some types only retained in user's portrait information aggregate according to being actually needed, for example, can only retain
Number of users exceedes the type of user's portrait information of predetermined threshold value, can also regularly replace the user in user's portrait information aggregate
Draw a portrait information type, prevent due to model parameter divulge a secret cause output information accuracy decline.
The Network records of user are carried out with processing can use clustering algorithm, prediction algorithm, machine learning method, natural language
Processing method, text mining method etc. are sayed to realize, specific to user often logs in basketball website, it is known that user likes
Movement be basketball;User often buys books on network, it is known that user is fond of books;User often searches on network
Rope educating knowledge, it is known that user has child etc..
In some optional implementations of the present embodiment, user draw a portrait information aggregate in user draw a portrait information be via
Following steps generation:The Network records of targeted customer to being produced in preset time period carry out feature extraction, generation at least one
Item characteristic information;At least one characteristic information is inputted to user's portrait information generation model trained in advance, generation user and is drawn
Picture information, user's portrait information generation model are used for the correspondence of characteristic feature information and user's portrait information.
In some optional implementations of the present embodiment, Network records include text entry;And to preset time period
The Network records of the targeted customer of interior generation carry out at least one of feature extraction, generation characteristic information, including:To preset time period
The text entry of the targeted customer of interior generation carries out semantic analysis, generates the number that keyword and keyword occur.
In this implementation, the pretreatment such as cutting word can be carried out to text entry first, then can be by simple
Word frequency statistics, the classification with semantic word obtain the number that keyword and keyword occur, and can also pass through convolutional neural networks
Or text subject generation model obtains the theme distribution of text, determines that keyword and keyword go out according to the theme distribution of text
Existing number, text subject generation model can be that (Latent Dirichlet Allocation, imply Di Li Crays point to LDA
Cloth) model.With this, characteristic information can be expressed as a feature binary group (feature:Weight), wherein, feature generations
The classification of table feature, can be the classification of keyword, the weight of weight representative features, can be the number that keyword occurs.
In some optional implementations of the present embodiment, text entry includes at least one of following:Search engine records
Term, browsed webpage content information, social platform issue information.The content information of browsed webpage can be with
It is the title of browsed webpage, the content of browsed webpage article, picture, video, the mark of audio in browsed webpage
Topic and label etc..The information of social platform issue can be that the message of issue, forum post.
In some optional implementations of the present embodiment, Network records include record to be counted;And to preset time
The Network records of the targeted customer produced in section carry out at least one of feature extraction, generation characteristic information, including:Based on it is default when
Between the record to be counted of targeted customer that produces in section, count the quantity of pre-set item to be counted.At this time, feature binary group
In, the classification of feature representative features, can be item to be counted classification, the weight of weight representative features, can wait to unite
Count the quantity of item.
In some optional implementations of the present embodiment, record to be counted includes at least one of following:E-commerce is put down
The order record of platform, good friend's record, the login record of social platform, the information issue record of social platform, the mesh of social platform
The mark page browses record.The order record of e-commerce platform can include order total amount, single order maximum dollar amount, most
The small amount of money, quantity on order etc..Good friend's record of social platform can be the quantity of good friend in social platform.The login of social platform
Record can be the number logged in, the frequency logged in etc..Target pages browse the number of visits that record can be target pages,
Target pages can be configured according to actual needs, such as can be the page in default website.
In some optional implementations of the present embodiment, user's portrait information further includes what is generated according to preset time period
Time dimension information.Since part portrait information has timeliness, it is defeated that increase time dimension information can further improve information
The accuracy gone out.
Step 203, by the user inquired portrait information input probability of happening prediction model trained in advance, generation and use
Family identifies corresponding probability of happening information and exports.
In the present embodiment, the user inquired in step 202 can be drawn a portrait information input in advance by above-mentioned electronic equipment
Trained probability of happening prediction model, generates probability of happening information corresponding with user identifier and exports.The probability of happening predicts mould
Type is used for the correspondence for characterizing user's portrait information and probability of happening information, and probability of happening information is used for indicating predetermined adopted event
The probability of generation.Can be specific probable value or class information, for example, maximum probability, middle probability, small probability.It is predetermined
Adopted event can be the event of its related promise of user's request submitted of user's fail to act, for example, do not refund, not on schedule on schedule
Give back the events of default such as article.
Probability of happening prediction model can be trained to obtain based on positive negative sample, and probability of happening prediction model also may be used
Pre-established with the statistics based on draw a portrait to substantial amounts of user information and probability of happening information that is technical staff, be stored with it is more
A user's portrait information and the mapping table of the correspondence of probability of happening information;Can also be that technical staff is based on to a large amount of
The statistics of data and pre-set and store it is into above-mentioned electronic equipment, to one or more users draw a portrait information carry out numerical value
Calculate and obtain the calculation formula of the result of calculation for characterizing probability of happening information.
As an example, when information of drawing a portrait to user carries out numerical computations, the quantizing rule of user's portrait information can basis
Actual needs is configured.It can be that user draws a portrait that to include a certain attribute be then 1 to information, be then 0, or according to different
Degree is quantified to obtain more rich numerical value.For example, whether there is user's portrait information of child for characterization subscriber household, use
Having child in the man of family, then quantized value can be 1, and no then quantized value can be 0, in the case of user residential quarter is characterized
User's portrait information, user residential quarter are that high-grade then quantized value can be 3, and commonly then quantized value can be 2, poor, quantify
Value can be 1.
In some optional implementations of the present embodiment, method further includes:In response to the probability of happening information exported
Matched with the first presupposed information, order is requested to generate according to user.First presupposed information can be the scope of probable value, specifically may be used
To be configured according to actual needs, for example, less than 5 percent.It can also include other use in being asked except user identifier user
In the information of generation order, specifically depending on order species, for example, for order of providing a loan, can also include borrowing in user's request
Money amount information.If the probability of happening information of output is not matched with the first presupposed information, can also generate
In some optional implementations of the present embodiment, method further includes:In response to the probability of happening information exported
Matched with the second presupposed information, user is asked to send to target device, given birth in response to the order for receiving target device transmission
Into instruction, order is requested to generate according to user.Second presupposed information can be the scope of probable value, specifically can be according to actual need
It is configured, for example, ten five five to percent percent.Target device can be used to further locate user's request
The equipment of reason, such as can be equipment used in staff, or operation has the equipment of other models, and user is asked to send
To target device, manual analysis or the analysis of other dimensions can be carried out to it.
With continued reference to Fig. 3, Fig. 3 is a schematic diagram according to the application scenarios of the information output method of the present embodiment.
In the application scenarios of Fig. 3, user have sent loan requests 302 by terminal 301 to server 303 first.Server 303 receives
To after loan requests 302, the user identifier that loan requests 302 include is extracted, and based on the user identifier extracted, built in advance
User's portrait information 304 of the user is inquired about in vertical user's portrait information database, then the user inquired draws a portrait and believes
The input of breath 304 Default Probability prediction model trained in advance, generates the Default Probability information 306 of the user and exports.
The method that above-described embodiment of the application provides is asked by obtaining user, and user's request includes user's mark
Know;Inquiry user's portrait information matched with the user identifier, user's portrait information include in user draws a portrait information aggregate
The attribute information that the Network records of user are handled;By the user inquired portrait information input thing trained in advance
Part Probabilistic Prediction Model, generates probability of happening information corresponding with the user identifier and exports, the probability of happening predicts mould
Type is used for the correspondence for characterizing user's portrait information and probability of happening information, and the probability of happening information is used for indicating predetermined justice
The probability that event occurs, so as to provide a kind of forecasting mechanism for information of drawing a portrait based on user, enriches outgoing event probability letter
The method of breath.
With further reference to Fig. 4, it illustrates a kind of flow for the optional implementation for being trained probability of happening prediction model
400.The flow 400, comprises the following steps:
Step 401, History Order set of records ends is obtained.
In the present embodiment, the electronic equipment (such as server shown in Fig. 1) of information output method operation thereon can
To obtain History Order set of records ends.History Order record in History Order set of records ends can be based on above-mentioned electronic equipment
The historical user received asks the record of generated order.For example, the request of loan is applied in historical user's request for user,
History Order record in History Order set of records ends can be the record of loan order.Every in History Order set of records ends
History Order record includes user identifier and the target information occurred for indicating predetermined adopted event.By taking order of providing a loan as an example,
Predefined event can be event of default, i.e. user does not pay off loan within the period of agreement.
Step 402, the user that the History Order record that target information is not included in History Order set of records ends includes is marked
Knowledge is determined as positive sample user identifier, and the History Order comprising target information records the user included in History Order set of records ends
Mark is determined as negative sample user identifier.
In the present embodiment, above-mentioned electronic equipment will can not wrap in the History Order set of records ends that obtained in step 401
The user identifier that includes of History Order record containing target information is determined as positive sample user identifier, in History Order set of records ends
The user identifier that History Order record comprising target information includes is determined as negative sample user identifier.By taking order of providing a loan as an example,
Not comprising target information History Order record, can be the order record that event of default does not occur, i.e., user agreement when
Between the order record of loan has been paid off in section.History Order record comprising target information, can be that there occurs event of default
The order record that order record, i.e. user are not provided a loan clearly within the period of agreement.
Step 403, user's portrait information matched with positive sample user identifier in user's portrait information aggregate is determined as
Positive sample, user's information of drawing a portrait of matched with negative sample user identifier user in information aggregate of drawing a portrait are determined as negative sample, utilize
Machine learning method, training obtain probability of happening prediction model.
In the present embodiment, above-mentioned electronic equipment can by user draw a portrait information aggregate in in step 402 determine just
Sample of users identifies matched user information of drawing a portrait and is determined as positive sample, and user draws a portrait in information aggregate with being determined in step 402
The matched user of negative sample user identifier information of drawing a portrait be determined as negative sample, using machine learning method, training obtains event
Probabilistic Prediction Model.Machine learning method can be logistic regression (Logistic Regression), random forest (random
Forest), iteration decision tree (gradient boosting decision tree) or neutral net etc., utilize machine learning
Method, can get up sample and feature association, and input model and repetitive exercise arrive final probability of happening prediction model.
The flow of training probability of happening prediction model shown in above-mentioned Fig. 4, by obtaining History Order set of records ends, by history
The user identifier that the History Order record not comprising target information includes in order record set is determined as positive sample user identifier,
The user identifier that the History Order record comprising target information includes in History Order set of records ends is determined as negative sample user mark
Know;User's portrait information matched with positive sample user identifier in user's portrait information aggregate is determined as positive sample, Yong Huhua
As matched with negative sample user identifier user information of drawing a portrait is determined as negative sample in information aggregate, using machine learning method,
Training obtains probability of happening prediction model.Model training is carried out based on real order data, without additional configurations sample, lifting
The efficiency of model training.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides a kind of output of information to fill
The one embodiment put, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, which specifically can be applied to respectively
In kind electronic equipment.
As shown in figure 5, the information output apparatus 500 of the present embodiment includes:Acquiring unit 501, query unit 502, output
Unit 503.Wherein, acquiring unit 501, for obtaining user's request, user's request includes user identifier;Query unit 502, is used
Inquiry user's portrait information matched with user identifier, user's portrait information are included to user in information aggregate is drawn a portrait in user
The attribute information that is handled of Network records;Output unit 503, for user's information input inquired to be drawn a portrait in advance
First trained probability of happening prediction model, generates probability of happening information corresponding with user identifier and exports, probability of happening prediction
Model is used for the correspondence for characterizing user's portrait information and probability of happening information, and probability of happening information is used for indicating predetermined adopted thing
The probability that part occurs.
In the present embodiment, the acquiring unit 501 of information output apparatus 500, query unit 502, the tool of output unit 503
Body processing may be referred to Fig. 2 and correspond to step 201, step 202 and step 203 in embodiment.
In some optional implementations of the present embodiment, device further includes probability of happening prediction model training unit (figure
Not shown in), probability of happening prediction model training unit (not shown), is used for:Obtain History Order set of records ends, history
Every History Order record in order record set includes user identifier and the target occurred for indicating predetermined adopted event
Information;The user identifier that the History Order record for not including target information in History Order set of records ends includes is determined as positive sample
This user identifier, the user identifier that the History Order record comprising target information includes in History Order set of records ends are determined as bearing
Sample of users identifies;User's portrait information matched with positive sample user identifier in user's portrait information aggregate is determined as positive sample
This, user's portrait information matched with negative sample user identifier is determined as negative sample in user's portrait information aggregate, utilizes machine
Learning method, training obtain probability of happening prediction model.
In some optional implementations of the present embodiment, device further includes user and draws a portrait information generating unit (in figure not
Show), user's portrait information generating unit (not shown), is used for:Net to the targeted customer produced in preset time period
Network record carries out at least one of feature extraction, generation characteristic information;At least one characteristic information is inputted to use trained in advance
Family portrait information generation model, generation user's portrait information, user's portrait information generation model are used for characteristic feature information and use
The correspondence of family portrait information.
In some optional implementations of the present embodiment, Network records include text entry;And user's portrait information
Generation unit (not shown), is further configured to:To the text entry of targeted customer that is produced in preset time period into
Row semantic analysis, generates the number that keyword and keyword occur.
In some optional implementations of the present embodiment, text entry includes at least one of following:Search engine records
Term, browsed webpage content information, social platform issue information.
In some optional implementations of the present embodiment, Network records include record to be counted;And user draws a portrait and believes
Generation unit (not shown) is ceased, is further configured to:Based on the to be counted of the targeted customer produced in preset time period
Record, counts the quantity of pre-set item to be counted.
In some optional implementations of the present embodiment, record to be counted includes at least one of following:E-commerce is put down
The order record of platform, good friend's record, the login record of social platform, the information issue record of social platform, the mesh of social platform
The mark page browses record.
In some optional implementations of the present embodiment, user's portrait information further includes what is generated according to preset time period
Time dimension information.
In some optional implementations of the present embodiment, device further includes the first order generation unit and (does not show in figure
Go out), the first order generation unit (not shown), is used for:In response to the probability of happening information exported and the first default letter
Breath matching, order is requested to generate according to user.
In some optional implementations of the present embodiment, device further includes the second order generation unit and (does not show in figure
Go out), the second order generation unit (not shown), is used for:In response to the probability of happening information exported and the second default letter
Breath matching, user is asked to send to target device, and instruction is generated in response to the order for receiving target device transmission, according to
Family requests to generate order.
The device that above-described embodiment of the application provides, is asked by obtaining user, and user's request includes user's mark
Know;Inquiry user's portrait information matched with the user identifier, user's portrait information include in user draws a portrait information aggregate
The attribute information that the Network records of user are handled;By the user inquired portrait information input thing trained in advance
Part Probabilistic Prediction Model, generates probability of happening information corresponding with the user identifier and exports, the probability of happening predicts mould
Type is used for the correspondence for characterizing user's portrait information and probability of happening information, and the probability of happening information is used for indicating predetermined justice
The probability that event occurs, so as to provide a kind of forecasting mechanism for information of drawing a portrait based on user, enriches outgoing event probability letter
The method of breath.
Below with reference to Fig. 6, it illustrates suitable for for realizing the computer system 600 of the electronic equipment of the embodiment of the present application
Structure diagram.Electronic equipment shown in Fig. 6 is only an example, to the function of the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into program in random access storage device (RAM) 603 from storage part 608 and
Perform various appropriate actions and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interfaces 605 are connected to lower component:Importation 606 including keyboard, mouse etc.;Penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage part 608 including hard disk etc.;
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net performs communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., are installed on driver 610, in order to read from it as needed
Computer program be mounted into as needed storage part 608.
Especially, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
Apply in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is performed by central processing unit (CPU) 601, perform what is limited in the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable recording medium either the two any combination.Computer-readable recording medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.
The more specifically example of computer-readable recording medium can include but is not limited to:Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer-readable recording medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media can include believing in a base band or as the data that a carrier wave part is propagated
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Included on computer-readable medium
Program code any appropriate medium can be used to transmit, include but not limited to:Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for performing the application can be write with one or more programming languages or its combination
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to perform on the user computer, partly perform, performed as an independent software kit on the user computer,
Part performs or is performed completely on remote computer or server on the remote computer on the user computer for part.
In the situation of remote computer is related to, remote computer can pass through the network of any kind --- including LAN (LAN)
Or wide area network (WAN)-subscriber computer is connected to, or, it may be connected to outer computer (such as utilize Internet service
Provider passes through Internet connection).
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in attached drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor bag
Include acquiring unit, query unit and output unit.Wherein, the title of these units is not formed to the unit under certain conditions
The restriction of itself, for example, acquiring unit is also described as " unit for obtaining user's request ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment;Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device:User's request is obtained, user's request includes user identifier;Inquiry and the user in user draws a portrait information aggregate
Matched user's portrait information is identified, the attribute that user's portrait information includes handling the Network records of user is believed
Breath;By the user inquired portrait information input probability of happening prediction model trained in advance, generation and the user identifier pair
The probability of happening information answered simultaneously exports, and the probability of happening prediction model is used to characterizing user and draws a portrait information and probability of happening information
Correspondence, the probability of happening information is used for the probability that indicating predetermined adopted event occurs.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (13)
1. a kind of information output method, the described method includes:
User's request is obtained, user's request includes user identifier;
Inquiry user's portrait information matched with the user identifier in user draws a portrait information aggregate;
By the user inquired portrait information input probability of happening prediction model trained in advance, generation and the user identifier pair
The probability of happening information answered simultaneously exports, and the probability of happening prediction model is used to characterizing user and draws a portrait information and probability of happening information
Correspondence, the probability of happening information is used for the probability that indicating predetermined adopted event occurs.
2. according to the method described in claim 1, wherein, the probability of happening prediction model is to train to obtain via following steps
's:
History Order set of records ends is obtained, every History Order record in the History Order set of records ends includes user identifier
With the target information occurred for indicating predetermined adopted event;
The user identifier that the History Order record for not including target information in the History Order set of records ends includes is determined as
Positive sample user identifier, the user identifier that the History Order record comprising target information includes in the History Order set of records ends
It is determined as negative sample user identifier;
User's portrait information matched with the positive sample user identifier in user portrait information aggregate is determined as positive sample
This, user's portrait information matched with the negative sample user identifier is determined as negative sample in user's portrait information aggregate,
Using machine learning method, training obtains probability of happening prediction model.
3. according to the method described in claim 1, wherein, user that the user draws a portrait in information aggregate draw a portrait information be via
Following steps generation:
The Network records of targeted customer to being produced in preset time period carry out at least one of feature extraction, generation characteristic information;
At least one of described characteristic information is inputted to the user's portrait information generation model trained in advance, generation user, which draws a portrait, to be believed
Cease, user's portrait information generation model is used for the correspondence of characteristic feature information and user's portrait information.
4. according to the method described in claim 3, wherein, the Network records include text entry;And
The Network records of the targeted customer to being produced in preset time period carry out at least one of feature extraction, generation feature letter
Breath, including:
The text entry of targeted customer to being produced in preset time period carries out semantic analysis, generates keyword and keyword goes out
Existing number.
5. according to the method described in claim 4, wherein, the text entry includes at least one of following:Search engine records
Term, browsed webpage content information, social platform issue information.
6. according to the method described in claim 3, wherein, the Network records include record to be counted;And
The Network records of the targeted customer to being produced in preset time period carry out at least one of feature extraction, generation feature letter
Breath, including:
Record to be counted based on the targeted customer produced in preset time period, counts the quantity of pre-set item to be counted.
7. according to the method described in claim 6, wherein, the record to be counted includes at least one of following:E-commerce is put down
The order record of platform, good friend's record, the login record of social platform, the information issue record of social platform, the mesh of social platform
The mark page browses record.
8. according to the method described in claim 3, wherein, user's portrait information is further included gives birth to according to the preset time period
Into time dimension information.
9. according to the method any one of claim 1-8, wherein, the method further includes:
Matched in response to the probability of happening information exported with the first presupposed information, order is requested to generate according to the user.
10. according to the method any one of claim 1-8, wherein, the method further includes:
Matched in response to the probability of happening information exported with the second presupposed information, ask transmission to target to set the user
Standby, the order sent in response to receiving the target device generates instruction, and order is requested to generate according to the user.
11. a kind of information output apparatus, described device include:
Acquiring unit, for obtaining user's request, user's request includes user identifier;
Query unit, for the user's portrait information matched with the user identifier of inquiry in drawing a portrait information aggregate in user;
Output unit, for the user inquired to be drawn a portrait information input probability of happening prediction model trained in advance, generation with
The corresponding probability of happening information of the user identifier simultaneously exports, and the probability of happening prediction model is used to characterizing user and draws a portrait information
With the correspondence of probability of happening information, the probability of happening information is used for the probability that indicating predetermined adopted event occurs.
12. a kind of electronic equipment, including:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are performed by one or more of processors so that one or more of processors
Realize the method as described in any in claim 1-10.
13. a kind of computer-readable recording medium, is stored thereon with computer program, realized such as when which is executed by processor
Any method in claim 1-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711132306.2A CN107908740B (en) | 2017-11-15 | 2017-11-15 | Information output method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711132306.2A CN107908740B (en) | 2017-11-15 | 2017-11-15 | Information output method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107908740A true CN107908740A (en) | 2018-04-13 |
CN107908740B CN107908740B (en) | 2022-11-22 |
Family
ID=61844319
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711132306.2A Active CN107908740B (en) | 2017-11-15 | 2017-11-15 | Information output method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107908740B (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804638A (en) * | 2018-06-04 | 2018-11-13 | 北京天元创新科技有限公司 | Build the method and device of user's holography portrait |
CN108846520A (en) * | 2018-06-22 | 2018-11-20 | 北京京东金融科技控股有限公司 | Overdue loan prediction technique, device and computer readable storage medium |
CN109583932A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment of generation activity crowd |
CN109597833A (en) * | 2018-10-15 | 2019-04-09 | 平安科技(深圳)有限公司 | Event prediction method, apparatus, computer equipment and storage medium based on big data |
CN109948851A (en) * | 2019-03-20 | 2019-06-28 | 北京百度网讯科技有限公司 | Method and apparatus for predicted events probability of happening |
CN110489660A (en) * | 2019-07-22 | 2019-11-22 | 武汉大学 | A kind of user's economic situation portrait method of social media public data |
CN110737820A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating event information |
CN110866040A (en) * | 2018-08-27 | 2020-03-06 | 京东数字科技控股有限公司 | User portrait generation method, device and system |
CN110867030A (en) * | 2019-11-28 | 2020-03-06 | 中国银行股份有限公司 | Data processing method and device, electronic equipment and computer storage medium |
CN111052161A (en) * | 2018-08-10 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying drunk requesters in an online-to-offline service platform |
CN111159538A (en) * | 2019-12-09 | 2020-05-15 | 上海连尚网络科技有限公司 | Method and equipment for presenting reading information |
CN111178925A (en) * | 2018-11-09 | 2020-05-19 | 百度在线网络技术(北京)有限公司 | User portrait attribute prediction method, device, server and computer readable medium |
CN111274471A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, server and readable storage medium |
CN111325186A (en) * | 2020-03-23 | 2020-06-23 | 上海依图网络科技有限公司 | Video processing method, apparatus, medium, and system |
CN111414944A (en) * | 2020-03-11 | 2020-07-14 | 北京声智科技有限公司 | Electronic equipment control method and electronic equipment |
CN111582152A (en) * | 2020-05-07 | 2020-08-25 | 微特技术有限公司 | Method and system for identifying complex event in image |
CN112330321A (en) * | 2020-11-20 | 2021-02-05 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN112686702A (en) * | 2020-12-31 | 2021-04-20 | 平安消费金融有限公司 | Wool party identification method and device, computer equipment and storage medium |
CN113065894A (en) * | 2021-03-24 | 2021-07-02 | 天天惠民(北京)智能物流科技有限公司 | Data collection method and device based on user portrait and order analysis and storage medium |
CN114817725A (en) * | 2022-04-28 | 2022-07-29 | 杭州核新软件技术有限公司 | Behavior decision logic identification method and system |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279048A1 (en) * | 2013-03-14 | 2014-09-18 | Balderdash Inc. | Systems and methods for providing relevant pathways through linked information |
CN105224623A (en) * | 2015-09-22 | 2016-01-06 | 北京百度网讯科技有限公司 | The training method of data model and device |
CN105657003A (en) * | 2015-12-28 | 2016-06-08 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN105827676A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团上海有限公司 | System, method and device for acquiring user portrait information |
CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股(北京)有限公司 | Personalized video recommendation method and apparatus |
CN106296391A (en) * | 2016-08-08 | 2017-01-04 | 联动优势科技有限公司 | A kind of assessment exceeds the time limit the method and apparatus of probability |
WO2017028821A1 (en) * | 2015-08-20 | 2017-02-23 | 北京嘀嘀无限科技发展有限公司 | Method and system for predicting current order information on the basis of historical order |
CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
CN106803168A (en) * | 2016-12-30 | 2017-06-06 | 中国银联股份有限公司 | A kind of abnormal transfer accounts method for detecting and device |
CN106846041A (en) * | 2016-12-26 | 2017-06-13 | 携程计算机技术(上海)有限公司 | The distribution method and system of reward voucher |
CN106875066A (en) * | 2017-02-28 | 2017-06-20 | 百度在线网络技术(北京)有限公司 | With the Forecasting Methodology of car travel behaviour, device, server and storage medium |
CN106909686A (en) * | 2017-03-06 | 2017-06-30 | 吉林省盛创科技有限公司 | A kind of man-machine interaction builds user's portrait cluster calculation method |
CN106952155A (en) * | 2017-03-08 | 2017-07-14 | 深圳前海纵腾金融科技服务有限公司 | A kind of collection method and device based on credit scoring |
WO2017129076A1 (en) * | 2016-01-27 | 2017-08-03 | Huawei Technologies Co., Ltd. | System and method for prediction using synthetic features and gradient boosted decision tree |
CN107169629A (en) * | 2017-04-17 | 2017-09-15 | 四川九洲电器集团有限责任公司 | A kind of telecommunication fraud recognition methods and data processing equipment |
CN107205031A (en) * | 2017-05-31 | 2017-09-26 | 北京京东尚科信息技术有限公司 | Information prompting method, device and terminal device |
CN107277178A (en) * | 2017-08-07 | 2017-10-20 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN107274201A (en) * | 2016-04-07 | 2017-10-20 | 滴滴(中国)科技有限公司 | Marketing method, the apparatus and system drawn a portrait based on user |
CN107341145A (en) * | 2017-06-21 | 2017-11-10 | 华中科技大学 | A kind of user feeling analysis method based on deep learning |
-
2017
- 2017-11-15 CN CN201711132306.2A patent/CN107908740B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279048A1 (en) * | 2013-03-14 | 2014-09-18 | Balderdash Inc. | Systems and methods for providing relevant pathways through linked information |
CN105827676A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团上海有限公司 | System, method and device for acquiring user portrait information |
WO2017028821A1 (en) * | 2015-08-20 | 2017-02-23 | 北京嘀嘀无限科技发展有限公司 | Method and system for predicting current order information on the basis of historical order |
CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
CN105224623A (en) * | 2015-09-22 | 2016-01-06 | 北京百度网讯科技有限公司 | The training method of data model and device |
CN105657003A (en) * | 2015-12-28 | 2016-06-08 | 腾讯科技(深圳)有限公司 | Information processing method and server |
WO2017129076A1 (en) * | 2016-01-27 | 2017-08-03 | Huawei Technologies Co., Ltd. | System and method for prediction using synthetic features and gradient boosted decision tree |
CN107274201A (en) * | 2016-04-07 | 2017-10-20 | 滴滴(中国)科技有限公司 | Marketing method, the apparatus and system drawn a portrait based on user |
CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股(北京)有限公司 | Personalized video recommendation method and apparatus |
CN106296391A (en) * | 2016-08-08 | 2017-01-04 | 联动优势科技有限公司 | A kind of assessment exceeds the time limit the method and apparatus of probability |
CN106846041A (en) * | 2016-12-26 | 2017-06-13 | 携程计算机技术(上海)有限公司 | The distribution method and system of reward voucher |
CN106803168A (en) * | 2016-12-30 | 2017-06-06 | 中国银联股份有限公司 | A kind of abnormal transfer accounts method for detecting and device |
CN106875066A (en) * | 2017-02-28 | 2017-06-20 | 百度在线网络技术(北京)有限公司 | With the Forecasting Methodology of car travel behaviour, device, server and storage medium |
CN106909686A (en) * | 2017-03-06 | 2017-06-30 | 吉林省盛创科技有限公司 | A kind of man-machine interaction builds user's portrait cluster calculation method |
CN106952155A (en) * | 2017-03-08 | 2017-07-14 | 深圳前海纵腾金融科技服务有限公司 | A kind of collection method and device based on credit scoring |
CN107169629A (en) * | 2017-04-17 | 2017-09-15 | 四川九洲电器集团有限责任公司 | A kind of telecommunication fraud recognition methods and data processing equipment |
CN107205031A (en) * | 2017-05-31 | 2017-09-26 | 北京京东尚科信息技术有限公司 | Information prompting method, device and terminal device |
CN107341145A (en) * | 2017-06-21 | 2017-11-10 | 华中科技大学 | A kind of user feeling analysis method based on deep learning |
CN107277178A (en) * | 2017-08-07 | 2017-10-20 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
Non-Patent Citations (1)
Title |
---|
郭光明: "基于社交大数据的用户信用画像方法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804638A (en) * | 2018-06-04 | 2018-11-13 | 北京天元创新科技有限公司 | Build the method and device of user's holography portrait |
CN108846520A (en) * | 2018-06-22 | 2018-11-20 | 北京京东金融科技控股有限公司 | Overdue loan prediction technique, device and computer readable storage medium |
CN110737820A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating event information |
CN111052161A (en) * | 2018-08-10 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying drunk requesters in an online-to-offline service platform |
CN110866040A (en) * | 2018-08-27 | 2020-03-06 | 京东数字科技控股有限公司 | User portrait generation method, device and system |
CN109583932A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment of generation activity crowd |
CN109597833A (en) * | 2018-10-15 | 2019-04-09 | 平安科技(深圳)有限公司 | Event prediction method, apparatus, computer equipment and storage medium based on big data |
WO2020077871A1 (en) * | 2018-10-15 | 2020-04-23 | 平安科技(深圳)有限公司 | Event prediction method and apparatus based on big data, computer device, and storage medium |
CN111178925A (en) * | 2018-11-09 | 2020-05-19 | 百度在线网络技术(北京)有限公司 | User portrait attribute prediction method, device, server and computer readable medium |
CN111274471B (en) * | 2018-12-04 | 2024-03-05 | 北京嘀嘀无限科技发展有限公司 | Information pushing method, device, server and readable storage medium |
CN111274471A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, server and readable storage medium |
CN109948851A (en) * | 2019-03-20 | 2019-06-28 | 北京百度网讯科技有限公司 | Method and apparatus for predicted events probability of happening |
CN110489660B (en) * | 2019-07-22 | 2020-12-18 | 武汉大学 | User economic condition portrait method of social media public data |
CN110489660A (en) * | 2019-07-22 | 2019-11-22 | 武汉大学 | A kind of user's economic situation portrait method of social media public data |
CN110867030A (en) * | 2019-11-28 | 2020-03-06 | 中国银行股份有限公司 | Data processing method and device, electronic equipment and computer storage medium |
CN110867030B (en) * | 2019-11-28 | 2021-06-25 | 中国银行股份有限公司 | Data processing method and device, electronic equipment and computer storage medium |
CN111159538A (en) * | 2019-12-09 | 2020-05-15 | 上海连尚网络科技有限公司 | Method and equipment for presenting reading information |
CN111414944A (en) * | 2020-03-11 | 2020-07-14 | 北京声智科技有限公司 | Electronic equipment control method and electronic equipment |
CN111414944B (en) * | 2020-03-11 | 2023-09-15 | 北京声智科技有限公司 | Electronic equipment control method and electronic equipment |
CN111325186B (en) * | 2020-03-23 | 2023-05-05 | 上海依图网络科技有限公司 | Video processing method, device, medium and system |
CN111325186A (en) * | 2020-03-23 | 2020-06-23 | 上海依图网络科技有限公司 | Video processing method, apparatus, medium, and system |
CN111582152A (en) * | 2020-05-07 | 2020-08-25 | 微特技术有限公司 | Method and system for identifying complex event in image |
CN112330321A (en) * | 2020-11-20 | 2021-02-05 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN112686702A (en) * | 2020-12-31 | 2021-04-20 | 平安消费金融有限公司 | Wool party identification method and device, computer equipment and storage medium |
CN113065894A (en) * | 2021-03-24 | 2021-07-02 | 天天惠民(北京)智能物流科技有限公司 | Data collection method and device based on user portrait and order analysis and storage medium |
CN114817725B (en) * | 2022-04-28 | 2022-10-14 | 杭州核新软件技术有限公司 | Behavior decision logic identification method and system |
CN114817725A (en) * | 2022-04-28 | 2022-07-29 | 杭州核新软件技术有限公司 | Behavior decision logic identification method and system |
Also Published As
Publication number | Publication date |
---|---|
CN107908740B (en) | 2022-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107908740A (en) | Information output method and device | |
CN107172151A (en) | Method and apparatus for pushed information | |
CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
CN107908789A (en) | Method and apparatus for generating information | |
CN107944481A (en) | Method and apparatus for generating information | |
CN107491547A (en) | Searching method and device based on artificial intelligence | |
CN106845999A (en) | Risk subscribers recognition methods, device and server | |
CN109840730B (en) | Method and device for data prediction | |
CN108805594A (en) | Information-pushing method and device | |
CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
CN107862339A (en) | Method and apparatus for output information | |
CN107305551A (en) | The method and apparatus of pushed information | |
CN108491267A (en) | Method and apparatus for generating information | |
CN109783741A (en) | Method and apparatus for pushed information | |
CN108632311A (en) | Information-pushing method and device | |
CN108897853A (en) | The method and apparatus for generating pushed information | |
CN108280200A (en) | Method and apparatus for pushed information | |
CN112215448A (en) | Method and device for distributing customer service | |
CN112925911B (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
CN107911449A (en) | Method and apparatus for pushed information | |
CN109684624A (en) | A kind of method and apparatus in automatic identification Order Address road area | |
US20190147540A1 (en) | Method and apparatus for outputting information | |
CN113393306A (en) | Product recommendation method and device, electronic equipment and computer readable medium | |
CN109345166A (en) | Method and apparatus for generating information | |
CN108062423B (en) | Information-pushing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |