CN109767264A - Product data method for pushing, device, computer equipment and storage medium - Google Patents
Product data method for pushing, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109767264A CN109767264A CN201811560069.4A CN201811560069A CN109767264A CN 109767264 A CN109767264 A CN 109767264A CN 201811560069 A CN201811560069 A CN 201811560069A CN 109767264 A CN109767264 A CN 109767264A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- product
- product data
- angle value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000004141 dimensional analysis Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 25
- 239000013598 vector Substances 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 241001269238 Data Species 0.000 claims description 22
- 238000007405 data analysis Methods 0.000 claims description 21
- 239000000284 extract Substances 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000000047 product Substances 0.000 abstract description 316
- 239000006227 byproduct Substances 0.000 abstract description 14
- 238000013468 resource allocation Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 230000002452 interceptive effect Effects 0.000 description 6
- 238000007418 data mining Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of product data method for pushing, device, computer equipment and storage mediums based on resource allocation.The described method includes: receiving the product data acquisition request that service terminal is sent, product data acquisition request carries user's representation data;Preset product prediction model is obtained, multi dimensional analysis is carried out to user's representation data by product prediction model, obtains the preference angle value that user's representation data corresponds to multiple product data;Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred product data of preset quantity;By preferred product data-pushing to service terminal.Use this method that can effectively improve the push accuracy rate of product data to improve the pushing efficiency of product data.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of product data method based on resource allocation, dress
It sets, computer equipment and storage medium.
Background technique
With the fast development of computer technology, there is the mode promoted on more and more lines, but promoted on line
Resource is limited, and traditional below-the-line promotion is still very important the way of promotion.Business personnel, can not when pushing product data
The higher product data of matching degree are effectively pushed according to limited user information.
In traditional product data push mode, usually product data are directly pushed to according to existing user information
User terminal.And for unregistered potential user, can not product data directly be pushed to user.Existing usage mining
Or in the mode of product data push, personalized push can not be carried out according to the existing attribute information of target user and meet user
The product data of situation cause the pushing efficiency of product data lower.Therefore, the push for how effectively improving product data is quasi-
True rate becomes the current technical issues that need to address with the pushing efficiency for improving product data.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, it is quasi- to provide a kind of push that can effectively improve product data
True rate is to improve product data method for pushing, device, computer equipment and the storage medium of the pushing efficiency of product data.
A kind of product data method for pushing, which comprises
The product data acquisition request that service terminal is sent is received, the product data acquisition request carries user's portrait
Data;
Preset product prediction model is obtained, multidimensional is carried out to user's representation data by the product prediction model
Degree analysis, obtains the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred production of preset quantity
Product data;
By the preferred product data-pushing to the service terminal.
In one of the embodiments, before the preset product prediction model of acquisition, further includes: from presetting database
It is middle to obtain multiple user informations, user's history data and product data;To multiple user informations, user's history data and product number
According to clustering is carried out, cluster result is obtained;Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and correspondence
Feature dimensions angle value;Product prediction is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value
Model.
It is described in one of the embodiments, that multidimensional is carried out to user's representation data by the product prediction model
Degree analysis, obtains the preference angle value that user's representation data corresponds to multiple product data, comprising: to user's representation data
Feature extraction is carried out, corresponding multiple feature vectors are obtained;Multiple feature vectors are input in the product prediction model, are led to
It crosses the product prediction mould model to classify to user's representation data, corresponding class is added to user's representation data
Distinguishing label;Calculate accounting value and matching angle value that user's representation data corresponds to multiple product data;According to the accounting value
The preference angle value that user's representation data corresponds to each product data is calculated with matching angle value.
In one of the embodiments, the method also includes: obtained from presetting database according to predeterminated frequency multiple
User information, user's history data and product data;Multiple user informations, user's history data and product data are clustered
Analysis obtains analysis result;Feature selecting is carried out according to the analysis result, obtains multiple characteristic variables;According to preset calculation
Method calculates the weight of multiple characteristic variables;The product prediction model is carried out according to multiple characteristic variables and corresponding weight excellent
Change adjustment.
Product prediction request in one of the embodiments, carries geographical location information, by the preferred production
After product data-pushing to the service terminal, further includes: obtained according to the geographical location information multiple in preset range
Place representation data;Preset Data Analysis Model is obtained, by the Data Analysis Model according to multiple place representation datas
The matching analysis is carried out to user's representation data and the product data, obtains user's representation data and the product number
According to the preference angle value in the multiple places of correspondence;Multiple locality datas are ranked up according to the preference angle value in multiple places, are obtained pre-
If the preferred locality data of quantity;The preferred locality data is pushed into the service terminal.
A kind of product data driving means, described device include:
Request receiving module, for receiving the product data acquisition request of service terminal transmission, the product data are obtained
Request carries user's representation data;
Data analysis module, for obtaining preset product prediction model, by the product prediction model to the use
Family representation data carries out multi dimensional analysis, obtains the preference angle value that user's representation data corresponds to multiple product data;
Data acquisition module is obtained for being ranked up according to the preference angle value of multiple product data to multiple product data
Take the preferred product data of preset quantity;
Data-pushing module is used for the preferred product data-pushing to the service terminal.
Described device further includes model building module in one of the embodiments, for obtaining from presetting database
Multiple user informations, user's history data and product data;Multiple user informations, user's history data and product data are carried out
Clustering obtains cluster result;Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding feature
Dimension values;Product prediction model is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value.
The data analysis module is also used to carry out feature to user's representation data to mention in one of the embodiments,
It takes, obtains corresponding multiple feature vectors;Multiple feature vectors are input in the product prediction model, the product is passed through
Prediction mould model classifies to user's representation data, adds corresponding class label to user's representation data;Meter
Calculate accounting value and matching angle value that user's representation data corresponds to multiple product data;According to the accounting value and matching angle value
Calculate the preference angle value that user's representation data corresponds to each product data.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The product data acquisition request that service terminal is sent is received, the product data acquisition request carries user's portrait
Data;
Preset product prediction model is obtained, multidimensional is carried out to user's representation data by the product prediction model
Degree analysis, obtains the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred production of preset quantity
Product data;
By the preferred product data-pushing to the service terminal.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The product data acquisition request that service terminal is sent is received, the product data acquisition request carries user's portrait
Data;
Preset product prediction model is obtained, multidimensional is carried out to user's representation data by the product prediction model
Degree analysis, obtains the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred production of preset quantity
Product data;
By the preferred product data-pushing to the service terminal.
The said goods data push method, device, computer equipment and storage medium receive the product that service terminal is sent
After data acquisition request, product data acquisition request carries user's representation data, further obtains preset product prediction mould
Type carries out multi dimensional analysis to user's representation data by product prediction model, obtains user's representation data and correspond to multiple products
The preference angle value of data.By being analyzed using product prediction model user's representation data, can accurately and effectively analyze
User's representation data corresponds to the preference angle value of each product data out.And then according to the preference angle value of multiple product data to multiple
Product data are ranked up, and obtain the preferred product data of preset quantity;By preferred product data-pushing to service terminal.Pass through
User's representation data is analyzed using product prediction model, can accurately and effectively predict the production that specific user is inclined to
Product data, thus, it is possible to be conducive to business personnel effectively to be promoted according to the product data of prediction for specific user, into
And the popularization efficiency of product data can be effectively improved.
Detailed description of the invention
Fig. 1 is the application scenario diagram of product data method for pushing in one embodiment;
Fig. 2 is the flow diagram of product data method for pushing in one embodiment;
Fig. 3 is the flow diagram that product prediction model step is established in one embodiment;
Fig. 4 is the flow diagram for carrying out analytical procedure in one embodiment to user's representation data;
Fig. 5 is the structural block diagram of product data driving means in one embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Product data method for pushing provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, industry
Business terminal 102 is communicated with server 104 by network by network.Wherein, service terminal 102 can be, but not limited to be each
Kind personal computer, laptop, smart phone, tablet computer and portable wearable device, server 104 can be with solely
The server clusters of the either multiple servers compositions of vertical server is realized.Server 104 receives service terminal 102 and sends
Product data acquisition request after, product data acquisition request carries user's representation data, and server 104 further obtains pre-
If product prediction model, by product prediction model to user's representation data carry out multi dimensional analysis, obtain user draw a portrait number
According to the preference angle value of the multiple product data of correspondence.It, can by being analyzed using product prediction model user's representation data
Accurately and effectively analyze the preference angle value that user's representation data corresponds to each product data.Server 104 is in turn according to multiple
The preference angle value of product data is ranked up multiple product data, obtains the preferred product data of preset quantity, and will be preferred
Product data push to service terminal 102.It, can be accurate by being analyzed using product prediction model user's representation data
The product data that specific user is inclined to effectively are predicted, thus, it is possible to be conducive to business personnel according to the product data of prediction
It is effectively promoted for specific user, and then the popularization efficiency of product data can be effectively improved.
In one embodiment, as shown in Fig. 2, providing a kind of product data method for pushing, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step 202, the product data acquisition request that service terminal is sent is received, product data acquisition request carries user
Representation data.
Business personnel can input the user information of some user or the user information of certain class user by service terminal, this
A little user informations can be user's representation data.Service terminal then sends product data acquisition to server according to user information and asks
It asks, to obtain the product data to match for such user, carries out product promotion to be effectively directed to this kind of specific user.Its
In, product data acquisition request carries user's representation data, and user's representation data can be business personnel and pass through service terminal
The user information of input is also possible to user's representation data that business personnel obtains according to pre-generated grid representation data.
Specifically, server is before obtaining user's representation data according to grid representation data, available cartographic information,
To map information is divided, and multiple grids and corresponding gridding information are obtained;It is obtained in multiple grids according to gridding information
Consumer consumption behavior data and history are registered data;Preset Rating Model is obtained, by Rating Model in multiple grids
Consumer consumption behavior data and history data of registering are analyzed, and thus, it is possible to effectively obtain the appraisal result number of each grid
According to.Wherein, history data of registering may include that user in multiple third party applications based on location information registers data.
Server obtains landmark data and merchant data in each grid according to gridding information, and obtains preset data
Mining model is divided by landmark data and merchant data and appraisal result data of the data mining model to multiple grids
Analysis obtains the customer analysis data and ground point analysis data of each grid.And then according to customer analysis data and ground point analysis number
According to the corresponding crowd portrayal data of each grid of generation and place representation data.By utilizing Rating Model in multiple grids
Multiple consumer consumption behavior data and history are registered after data are scored, and data mining model is recycled to combine each grid
Appraisal result data and landmark data and merchant data are analyzed, and thus, it is possible to effectively analyze the people of each grid
Group's representation data and place representation data, wherein crowd portrayal data include a plurality of types of user's representation datas.
Step 204, preset product prediction model is obtained, multidimensional is carried out to user's representation data by product prediction model
Degree analysis, obtains the preference angle value that user's representation data corresponds to multiple product data.
After server receives the product data acquisition request that service terminal is sent, preset product prediction model is obtained.Its
In, product prediction model can be the model based on decision tree or neural network, include multiple preset in product prediction model
Product data.Server and then feature extraction is carried out to user's representation data, obtains corresponding feature vector, user is drawn a portrait number
According to feature vector be input in product prediction model, classified by product prediction model to user's representation data, thus
Classification belonging to user's representation data can be effectively obtained, and corresponding class label is added to user's representation data.
Server further carries out multi dimensional analysis to user's representation data, by the feature vector and class of user's representation data
The feature vector of distinguishing label is input in Data Analysis Model, calculates user's portrait according to the distribution Value Data of pre-set product data
The accounting value and matching angle value of data.Server further calculates product information according to the accounting value of class label and matching angle value
The preference angle value in corresponding multiple places, the preference of multiple product data is corresponded to thus, it is possible to effectively obtain user's representation data
Value.
Step 206, multiple product data are ranked up according to the preference angle value of multiple product data, obtain preset quantity
Preferred product data.
Step 208, by preferred product data-pushing to service terminal.
Server carries out multi dimensional analysis to user's representation data by product prediction model, obtains user's representation data pair
After the preference angle value for answering multiple product data, multiple product data are ranked up according to the preference angle value of multiple product data.
Specifically, server can carry out descending sort to multiple product data according to preference angle value by sequence accounting algorithm.In turn
Server extracts the preferred product data of preset quantity, for example, extracting first three higher product data of preference angle value.By
This can effectively obtain the preferred product data to match with user's representation data.
After server obtains the preferred product data of preset quantity, it can also be obtained according to grid representation data and be drawn with user
As the locality data that data match, and the corresponding electronic map of gain location data.Server is in turn by preferred product data
And corresponding locality data and electronic map be sent to service terminal.So that business personnel is whole by corresponding business
End according to the preferred product data of server push and locality data product information is effectively promoted.By utilizing production
Product prediction model analyzes user's representation data, can accurately and effectively predict the product number that specific user is inclined to
According to, thus, it is possible to be conducive to business personnel effectively to be promoted according to the product data of prediction for specific user, Jin Erneng
Enough effectively improve the popularization efficiency of product data.
In the said goods data push method, after server receives the product data acquisition request that service terminal is sent, produce
Product data acquisition request carries user's representation data, and server further obtains preset product prediction model, passes through product
Prediction model carries out multi dimensional analysis to user's representation data, obtains the preference that user's representation data corresponds to multiple product data
Value.By analyzing using product prediction model user's representation data, user's portrait number can be accurately and effectively analyzed
According to the preference angle value of each product data of correspondence.Server is in turn according to the preference angle value of multiple product data to multiple product numbers
According to being ranked up, the preferred product data of preset quantity are obtained, and by preferred product data-pushing to service terminal.Pass through utilization
Product prediction model analyzes user's representation data, can accurately and effectively predict the product number that specific user is inclined to
According to, thus, it is possible to be conducive to business personnel effectively to be promoted according to the product data of prediction for specific user, Jin Erneng
Enough effectively improve the popularization efficiency of product data.
It in one embodiment, further include the step for establishing product prediction model before obtaining preset product prediction model
Suddenly, which specifically includes the following contents:
Step 302, multiple user informations, user's history data and product data are obtained from presetting database.
Step 304, clustering is carried out to multiple user informations, user's history data and product data, obtains cluster knot
Fruit.
Step 306, feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding characteristic dimension
Value.
Step 308, product is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value
Prediction model.
Server needs to establish product prediction model before obtaining preset product prediction model.Specifically, server
The multiple user informations and user's history data of available multiple user terminals can also obtain multiple from third party database
User information and user's history data and product data.Server so to multiple user informations and user's history data and
Product data carry out clustering.Specifically, server to multiple user informations and user's history data and product data into
Row feature extraction extracts corresponding characteristic variable.Server extracts multiple user informations and user's history data and production
After the corresponding characteristic variable of product data, clustering is carried out to characteristic variable using preset clustering algorithm.For example, preset poly-
Class algorithm can be the method for k-means (k- mean algorithm) cluster.Server is by carrying out after repeatedly clustering characteristic variable
Obtain multiple cluster results.
Server is further respectively combined the characteristic variable in multiple cluster results, obtains multiple assemblage characteristics and becomes
Amount.Target variable is obtained, correlation test is carried out to multiple assemblage characteristic variables using target variable.When upchecking, to group
It closes characteristic variable and adds interactive tag.Utilize the corresponding characteristic variable of assemblage characteristic variable resolution after addition interactive tag.Add
Assemblage characteristic variable after adding interactive tag can be the characteristic variable for reaching preset threshold, and server, which then extracts, reaches default
The characteristic variable of threshold value.Server further calculates out the corresponding feature dimensions angle value of characteristic variable for reaching preset threshold.Wherein,
Characteristic variable may include multiple dimensions.Feature dimensions angle value can be expressed as characteristic dimension belonging to characteristic variable.
After server extracts multiple characteristic variables and corresponding feature dimensions angle value, then according to multiple characteristic variables and correspondence
Feature dimensions angle value according to preset algorithm construct product prediction model.Wherein, product prediction model can be based on decision tree or
Model neural network based.
Further, a large amount of user information and user's history data and product data that server can also will acquire
Generate trained and data and verifying collection data.Server carries out clustering to the mass data in training set, obtains cluster knot
After fruit, feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding feature dimensions angle value.Server then root
Preliminary product prediction model is established according to preset algorithm according to multiple characteristic variables and corresponding feature dimensions angle value.
After server establishes preliminary product prediction model, the mass data concentrated using verifying is to preliminary product prediction model
It carries out further training and verifies, when the data of the default assessed value of the satisfaction that verifying is concentrated reach default ratio, trained
The product prediction model of completion.By carrying out big data point to a large amount of user information and user's history data and product data
After analysis, data mining model is established according to predetermined manner using the characteristic variable and feature dimensions angle value of extraction and is trained, by
This can be effectively constructed out the analysis higher product prediction model of accuracy rate.
In one embodiment, multi dimensional analysis is carried out to user's representation data by product prediction model, obtains user
Representation data corresponds to the step of preference angle value of multiple product data, specifically includes the following contents:
Step 402, feature extraction is carried out to user's representation data, obtains corresponding multiple feature vectors.
Step 404, multiple feature vectors are input in product prediction model, user is drawn by product prediction mould model
As data are classified, corresponding class label is added to user's representation data.
Step 406, accounting value and matching angle value that user's representation data corresponds to multiple product data are calculated.
Step 408, the preference that user's representation data corresponds to each product data is calculated with matching angle value according to accounting value
Value.
After server receives the product data acquisition request that service terminal is sent, product data acquisition request carries user
Representation data, server further obtain preset product prediction model, by product prediction model to user's representation data into
Row multi dimensional analysis obtains the preference angle value that user's representation data corresponds to multiple product data.By utilizing product prediction model
User's representation data is analyzed, the preference that user's representation data corresponds to each product data can be accurately and effectively analyzed
Angle value.
It specifically, include multiple preset product data in product prediction model, server obtains preset product prediction
After model, feature extraction is carried out to user's representation data, obtains corresponding multiple feature vectors.Server then draws a portrait user number
It is input to product prediction model according to corresponding multiple feature vectors, product prediction mould model first divides user's representation data
Class obtains the corresponding classification of user's representation data, adds corresponding class label to user's representation data.Wherein, user draws a portrait
The corresponding class label of data can be one, or multiple.
After server analysis goes out the class label of user's representation data, product prediction model is in turn to user's representation data pair
The corresponding feature vector of feature vector and class label answered is analyzed, and corresponding according to user's representation data and class label
Feature vector calculate user's representation data correspond to multiple product data accounting value and match angle value.Server is then according to basis
Accounting value calculates the preference angle value that user's representation data corresponds to each product data with matching angle value.Server is in turn according to multiple
The preference angle value of product data is ranked up multiple product data, obtains the preferred product data of preset quantity, and will be preferred
Product data push to service terminal.It is corresponding each by can effectively analyze user's representation data using product prediction model
The preference degree of product data thus, it is possible to effectively improve the push accuracy rate of product data, and then can effectively improve
The popularization efficiency of product data.
In one embodiment, this method further include: obtain multiple user's letters from presetting database according to predeterminated frequency
Breath, user's history data and product data;Clustering is carried out to multiple user informations, user's history data and product data,
Obtain analysis result;Feature selecting is carried out based on the analysis results, obtains multiple characteristic variables;It is calculated according to preset algorithm multiple
The weight of characteristic variable;Adjustment is optimized to product prediction model according to multiple characteristic variables and corresponding weight.
Server obtains the corresponding multiple user informations of type of service, user's history number according to predeterminated frequency from database
According to after product data, feature extraction is carried out to multiple user informations, user's history data and product data, extracts multiple spies
Levy variable.Server carries out clustering to multiple user informations and user's history data and product data in turn.Specifically,
Server carries out feature extraction to multiple user informations and user's history data and product data, extracts corresponding feature and becomes
Amount.After server extracts multiple user informations and user's history data and the corresponding characteristic variable of product data, using pre-
If clustering algorithm to characteristic variable carry out clustering.For example, preset clustering algorithm can (k- mean value be calculated for k-means
Method) cluster method.Server obtains multiple cluster results after repeatedly clustering by carrying out to characteristic variable.
Server is further respectively combined the characteristic variable in multiple cluster results, obtains multiple assemblage characteristics and becomes
Amount.Target variable is obtained, correlation test is carried out to multiple assemblage characteristic variables using target variable.When upchecking, to group
It closes characteristic variable and adds interactive tag.Utilize the corresponding characteristic variable of assemblage characteristic variable resolution after addition interactive tag.Add
Assemblage characteristic variable after adding interactive tag can be the characteristic variable for reaching preset threshold, and server, which then extracts, reaches default
The characteristic variable of threshold value.Server further calculates out the corresponding feature dimensions angle value of characteristic variable for reaching preset threshold.Wherein,
Characteristic variable may include multiple dimensions.Feature dimensions angle value can be expressed as characteristic dimension belonging to characteristic variable.
After server extracts multiple characteristic variables and corresponding feature dimensions angle value, multiple spies are calculated according to preset algorithm
The corresponding weight of variable is levied, server in turn optimizes product prediction model according to multiple characteristic variables and corresponding weight
Adjustment, thus obtains updated product prediction model, and issue in real time to updated product prediction model.By pressing
Prediction model is adjusted using the characteristic variable and corresponding weight analyzed according to predeterminated frequency, thus, it is possible to effectively right
Product prediction model carries out dynamic adjustment, and then can effectively improve the assessment accuracy of product prediction model.
In one embodiment, product prediction request carry geographical location information, by preferred product data-pushing extremely
After service terminal, further includes: obtain multiple place representation datas in preset range according to geographical location information;It obtains default
Data Analysis Model, by Data Analysis Model according to multiple place representation datas to user's representation data and product data into
Row the matching analysis, obtains user's representation data and product data correspond to the preference angle value in multiple places;According to the inclined of multiple places
Good angle value is ranked up multiple locality datas, obtains the preferred locality data of preset quantity;Preferred locality data is pushed to
Service terminal.
After server receives the product data acquisition request that service terminal is sent, product data acquisition request carries user
Representation data, server further obtain preset product prediction model, by product prediction model to user's representation data into
Row multi dimensional analysis obtains the preference angle value that user's representation data corresponds to multiple product data.By utilizing product prediction model
User's representation data is analyzed, the preference that user's representation data corresponds to each product data can be accurately and effectively analyzed
Angle value.
Further, product prediction request carries geographical location information, and server is by preferred product data-pushing to industry
After terminal of being engaged in, then multiple place representation datas in preset range are obtained according to geographical location information.Server and then acquisition
Preset Data Analysis Model, by Data Analysis Model according to multiple place representation datas to user's representation data and product number
According to the matching analysis is carried out, obtains user's representation data and product data correspond to the preference angle value in multiple places.By believing user
The product data and place representation data and crowd portrayal data of breath and prediction carry out analysis matching, analyze this kind of user's
Distribution situation obtains the accounting rate of the target user of each place distribution.Server obtains user's representation data and product data
After the preference angle value in corresponding multiple places, multiple locality datas are ranked up according to the preference angle value in multiple places.Specifically,
Server can carry out descending sort to multiple locality datas according to preference angle value by sequence accounting algorithm.And then server mentions
The preferred locality data for taking out preset quantity, for example, extracting first three higher locality data of preference angle value pushes to the industry
Business terminal.It is possible thereby to effectively obtain the preferred locality data to match with user's representation data.And by target user's accounting
The highest address of rate pushes corresponding service terminal, and then the business personnel for being can effectively improve the popularization effect of product data
Rate.
It should be understood that although each step in the flow chart of Fig. 2-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 5, providing a kind of product data driving means, comprising: request receiving module
502, data analysis module 504, data acquisition module 506 and data pushing module 508, in which:
Request receiving module 502, for receiving the product data acquisition request of service terminal transmission, product data acquisition is asked
It asks and carries user's representation data;
Data analysis module 504 draws a portrait to user by product prediction model for obtaining preset product prediction model
Data carry out multi dimensional analysis, obtain the preference angle value that user's representation data corresponds to multiple product data;
Data acquisition module 506, for being ranked up according to the preference angle value of multiple product data to multiple product data,
Obtain the preferred product data of preset quantity;
Data-pushing module 508 is used for preferred product data-pushing to service terminal.
In one embodiment, which further includes model building module, for obtaining multiple use from presetting database
Family information, user's history data and product data;Cluster point is carried out to multiple user informations, user's history data and product data
Analysis, obtains cluster result;Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding characteristic dimension
Value;Product prediction model is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value.
In one embodiment, data analysis module 504 is also used to carry out feature extraction to user's representation data, obtains pair
The multiple feature vectors answered;Multiple feature vectors are input in product prediction model, by product prediction mould model to user
Representation data is classified, and adds corresponding class label to user's representation data;It calculates user's representation data and corresponds to multiple productions
The accounting value and matching angle value of product data;User's representation data, which is calculated, with matching angle value according to accounting value corresponds to each product data
Preference angle value.
In one embodiment, which further includes model optimization module, for according to predeterminated frequency from presetting database
It is middle to obtain multiple user informations, user's history data and product data;To multiple user informations, user's history data and product number
According to clustering is carried out, analysis result is obtained;Feature selecting is carried out based on the analysis results, obtains multiple characteristic variables;According to pre-
If algorithm calculate the weights of multiple characteristic variables;Product prediction model is carried out according to multiple characteristic variables and corresponding weight
It optimizes and revises.
In one embodiment, product prediction request carries geographical location information, which further includes that locality data pushes away
Module is sent, for obtaining multiple place representation datas in preset range according to geographical location information;Obtain preset data point
Model is analysed, matching point is carried out to user's representation data and product data according to multiple place representation datas by Data Analysis Model
Analysis, obtains user's representation data and product data corresponds to the preference angle value in multiple places;According to the preference angle value pair in multiple places
Multiple locality datas are ranked up, and obtain the preferred locality data of preset quantity;Preferred locality data is pushed into service terminal.
Specific about product data driving means limits the limit that may refer to above for product data method for pushing
Fixed, details are not described herein.Modules in the said goods data-pushing device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.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 database of machine equipment is for storing the data such as user's representation data, user information, user's history data and product data.The meter
The network interface for calculating machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor
To realize a kind of product data method for pushing.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
The product data acquisition request that service terminal is sent is received, product data acquisition request carries user's portrait number
According to;
Preset product prediction model is obtained, multi dimensional analysis is carried out to user's representation data by product prediction model,
Obtain the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred production of preset quantity
Product data;
By preferred product data-pushing to service terminal.
In one embodiment, it also performs the steps of when processor executes computer program and is obtained from presetting database
Take multiple user informations, user's history data and product data;To multiple user informations, user's history data and product data into
Row clustering, obtains cluster result;Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding spy
Levy dimension values;Product prediction mould is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value
Type.
In one embodiment, processor execute computer program when also perform the steps of to user's representation data into
Row feature extraction obtains corresponding multiple feature vectors;Multiple feature vectors are input in product prediction model, product is passed through
Prediction mould model classifies to user's representation data, adds corresponding class label to user's representation data;User is calculated to draw
As data correspond to the accounting value and matching angle value of multiple product data;User's representation data is calculated according to accounting value and matching angle value
The preference angle value of corresponding each product data.
In one embodiment, it is also performed the steps of when processor executes computer program according to predeterminated frequency from pre-
If obtaining multiple user informations, user's history data and product data in database;To multiple user informations, user's history data
Clustering is carried out with product data, obtains analysis result;Feature selecting is carried out based on the analysis results, is obtained multiple features and is become
Amount;The weight of multiple characteristic variables is calculated according to preset algorithm;It is pre- to product according to multiple characteristic variables and corresponding weight
It surveys model and optimizes adjustment.
In one embodiment, product prediction request carries geographical location information, when processor executes computer program
Also perform the steps of the multiple place representation datas obtained in preset range according to geographical location information;Obtain preset number
According to analysis model, by Data Analysis Model according to multiple place representation datas to user's representation data and product data progress
With analysis, obtains user's representation data and product data correspond to the preference angle value in multiple places;According to the preference in multiple places
Value is ranked up multiple locality datas, obtains the preferred locality data of preset quantity;Preferred locality data is pushed into business
Terminal.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
The product data acquisition request that service terminal is sent is received, product data acquisition request carries user's portrait number
According to;
Preset product prediction model is obtained, multi dimensional analysis is carried out to user's representation data by product prediction model,
Obtain the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred production of preset quantity
Product data;
By preferred product data-pushing to service terminal.
In one embodiment, it is also performed the steps of from presetting database when computer program is executed by processor
Obtain multiple user informations, user's history data and product data;To multiple user informations, user's history data and product data
Clustering is carried out, cluster result is obtained;Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding
Feature dimensions angle value;Product prediction mould is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value
Type.
In one embodiment, it also performs the steps of when computer program is executed by processor to user's representation data
Feature extraction is carried out, corresponding multiple feature vectors are obtained;Multiple feature vectors are input in product prediction model, production is passed through
Product prediction mould model classifies to user's representation data, adds corresponding class label to user's representation data;Calculate user
Representation data corresponds to the accounting value and matching angle value of multiple product data;User's portrait number is calculated according to accounting value and matching angle value
According to the preference angle value of each product data of correspondence.
In one embodiment, also performed the steps of when computer program is executed by processor according to predeterminated frequency from
Multiple user informations, user's history data and product data are obtained in presetting database;To multiple user informations, user's history number
Clustering is carried out according to product data, obtains analysis result;Feature selecting is carried out based on the analysis results, is obtained multiple features and is become
Amount;The weight of multiple characteristic variables is calculated according to preset algorithm;It is pre- to product according to multiple characteristic variables and corresponding weight
It surveys model and optimizes adjustment.
In one embodiment, product prediction request carries geographical location information, and computer program is executed by processor
When also perform the steps of according to geographical location information obtain preset range in multiple place representation datas;It obtains preset
Data Analysis Model carries out user's representation data and product data according to multiple place representation datas by Data Analysis Model
The matching analysis, obtains user's representation data and product data correspond to the preference angle value in multiple places;According to the preference in multiple places
Angle value is ranked up multiple locality datas, obtains the preferred locality data of preset quantity;Preferred locality data is pushed into industry
Business terminal.
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 herein,
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..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of product data method for pushing, which comprises
The product data acquisition request that service terminal is sent is received, the product data acquisition request carries user's portrait number
According to;
Preset product prediction model is obtained, various dimensions point are carried out to user's representation data by the product prediction model
Analysis, obtains the preference angle value that user's representation data corresponds to multiple product data;
Multiple product data are ranked up according to the preference angle value of multiple product data, obtain the preferred product number of preset quantity
According to;
By the preferred product data-pushing to the service terminal.
2. the method according to claim 1, wherein also being wrapped before the preset product prediction model of acquisition
It includes:
Multiple user informations, user's history data and product data are obtained from presetting database;
Clustering is carried out to multiple user informations, user's history data and product data, obtains cluster result;
Feature selecting is carried out according to cluster result, extracts multiple characteristic variables and corresponding feature dimensions angle value;
Product prediction model is established using NB Algorithm according to multiple characteristic variables and corresponding feature dimensions angle value.
3. the method according to claim 1, wherein described draw the user by the product prediction model
As data progress multi dimensional analysis, the preference angle value that user's representation data corresponds to multiple product data is obtained, comprising:
Feature extraction is carried out to user's representation data, obtains corresponding multiple feature vectors;
Multiple feature vectors are input in the product prediction model, the user is drawn by the product prediction mould model
As data are classified, corresponding class label is added to user's representation data;
Calculate accounting value and matching angle value that user's representation data corresponds to multiple product data;
The preference angle value that user's representation data corresponds to each product data is calculated with matching angle value according to the accounting value.
4. according to claim 1 to method described in 3 any one, which is characterized in that the method also includes:
Multiple user informations, user's history data and product data are obtained from presetting database according to predeterminated frequency;
Clustering is carried out to multiple user informations, user's history data and product data, obtains analysis result;
Feature selecting is carried out according to the analysis result, obtains multiple characteristic variables;
The weight of multiple characteristic variables is calculated according to preset algorithm;
Adjustment is optimized to the product prediction model according to multiple characteristic variables and corresponding weight.
5. the method according to claim 1, wherein the product prediction request carry geographical location information,
After by the preferred product data-pushing to the service terminal, further includes:
Multiple place representation datas in preset range are obtained according to the geographical location information;
Preset Data Analysis Model is obtained, by the Data Analysis Model according to multiple place representation datas to the user
Representation data and the product data carry out the matching analysis, obtain user's representation data and the product data correspond to it is multiple
The preference angle value in place;
Multiple locality datas are ranked up according to the preference angle value in multiple places, obtain the preferred locality data of preset quantity;
The preferred locality data is pushed into the service terminal.
6. a kind of product data driving means, described device include:
Request receiving module, for receiving the product data acquisition request of service terminal transmission, the product data acquisition request
Carry user's representation data;
Data analysis module draws the user by the product prediction model for obtaining preset product prediction model
As data progress multi dimensional analysis, the preference angle value that user's representation data corresponds to multiple product data is obtained;
Data acquisition module obtains pre- for being ranked up according to the preference angle value of multiple product data to multiple product data
If the preferred product data of quantity;
Data-pushing module is used for the preferred product data-pushing to the service terminal.
7. device according to claim 6, which is characterized in that described device further includes model building module, is used for from pre-
If obtaining multiple user informations, user's history data and product data in database;To multiple user informations, user's history data
Clustering is carried out with product data, obtains cluster result;Feature selecting is carried out according to cluster result, multiple features is extracted and becomes
Amount and corresponding feature dimensions angle value;It is established according to multiple characteristic variables and corresponding feature dimensions angle value using NB Algorithm
Product prediction model.
8. device according to claim 6, which is characterized in that the data analysis module is also used to draw a portrait to the user
Data carry out feature extraction, obtain corresponding multiple feature vectors;Multiple feature vectors are input to the product prediction model
In, classified by the product prediction mould model to user's representation data, to user's representation data addition pair
The class label answered;Calculate accounting value and matching angle value that user's representation data corresponds to multiple product data;According to described
Accounting value calculates the preference angle value that user's representation data corresponds to each product data with matching angle value.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811560069.4A CN109767264A (en) | 2018-12-20 | 2018-12-20 | Product data method for pushing, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811560069.4A CN109767264A (en) | 2018-12-20 | 2018-12-20 | Product data method for pushing, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109767264A true CN109767264A (en) | 2019-05-17 |
Family
ID=66451518
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811560069.4A Pending CN109767264A (en) | 2018-12-20 | 2018-12-20 | Product data method for pushing, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109767264A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428087A (en) * | 2019-06-25 | 2019-11-08 | 万翼科技有限公司 | Business stability prediction technique, device, computer equipment and storage medium |
CN110427234A (en) * | 2019-06-27 | 2019-11-08 | 阿里巴巴集团控股有限公司 | The methods of exhibiting and device of the page |
CN110751168A (en) * | 2019-09-03 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
CN112133431A (en) * | 2020-08-27 | 2020-12-25 | 绿瘦健康产业集团有限公司 | Health information message pushing method, device, medium and terminal equipment |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100961782B1 (en) * | 2009-05-28 | 2010-06-07 | 주식회사 모임 | Apparatus and method for presenting personalized goods information based on artificial intelligence, and recording medium thereof |
CN103955703A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Medical image disease classification method based on naive Bayes |
CN104820863A (en) * | 2015-03-27 | 2015-08-05 | 北京智慧图科技有限责任公司 | Consumer portrait generation method and device |
CN105069534A (en) * | 2015-08-18 | 2015-11-18 | 广州华多网络科技有限公司 | Customer loss prediction method and device |
CN105184084A (en) * | 2015-09-14 | 2015-12-23 | 深圳供电局有限公司 | Fault type predicting method and system for automatic electric power measurement terminals |
CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
CN106410781A (en) * | 2015-07-29 | 2017-02-15 | 中国电力科学研究院 | Power consumer demand response potential determination method |
CN106446015A (en) * | 2016-08-29 | 2017-02-22 | 北京工业大学 | Video content access prediction and recommendation method based on user behavior preference |
US20170053208A1 (en) * | 2015-08-17 | 2017-02-23 | Adobe Systems Incorporated | Behavioral Prediction for Targeted End Users |
CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
CN106886872A (en) * | 2017-01-20 | 2017-06-23 | 淮阴工学院 | Method is recommended in a kind of logistics based on cluster and cosine similarity |
CN107145536A (en) * | 2017-04-19 | 2017-09-08 | 畅捷通信息技术股份有限公司 | User's portrait construction method and device and recommendation method and apparatus |
CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技(深圳)有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
CN108205775A (en) * | 2016-12-20 | 2018-06-26 | 阿里巴巴集团控股有限公司 | The recommendation method, apparatus and client of a kind of business object |
WO2018126740A1 (en) * | 2017-01-04 | 2018-07-12 | 百度在线网络技术(北京)有限公司 | Method and device for pushing information |
CN108304668A (en) * | 2018-02-11 | 2018-07-20 | 河海大学 | A kind of Forecasting Flood method of combination hydrologic process data and history priori data |
CN108460651A (en) * | 2018-01-04 | 2018-08-28 | 金瓜子科技发展(北京)有限公司 | Vehicle recommends method and device |
CN108563681A (en) * | 2018-03-07 | 2018-09-21 | 阿里巴巴集团控股有限公司 | A kind of content recommendation method, device, electronic equipment and system |
CN108596679A (en) * | 2018-04-27 | 2018-09-28 | 中国联合网络通信集团有限公司 | Construction method, device, terminal and the computer readable storage medium of user's portrait |
CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
CN108876509A (en) * | 2018-05-11 | 2018-11-23 | 上海赢科信息技术有限公司 | Utilize the method and system of POI analysis user tag |
CN108960975A (en) * | 2018-06-15 | 2018-12-07 | 广州麦优网络科技有限公司 | Personalized Precision Marketing Method, server and storage medium based on user's portrait |
-
2018
- 2018-12-20 CN CN201811560069.4A patent/CN109767264A/en active Pending
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100961782B1 (en) * | 2009-05-28 | 2010-06-07 | 주식회사 모임 | Apparatus and method for presenting personalized goods information based on artificial intelligence, and recording medium thereof |
CN103955703A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Medical image disease classification method based on naive Bayes |
CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
CN104820863A (en) * | 2015-03-27 | 2015-08-05 | 北京智慧图科技有限责任公司 | Consumer portrait generation method and device |
CN106410781A (en) * | 2015-07-29 | 2017-02-15 | 中国电力科学研究院 | Power consumer demand response potential determination method |
US20170053208A1 (en) * | 2015-08-17 | 2017-02-23 | Adobe Systems Incorporated | Behavioral Prediction for Targeted End Users |
CN105069534A (en) * | 2015-08-18 | 2015-11-18 | 广州华多网络科技有限公司 | Customer loss prediction method and device |
CN105184084A (en) * | 2015-09-14 | 2015-12-23 | 深圳供电局有限公司 | Fault type predicting method and system for automatic electric power measurement terminals |
CN106446015A (en) * | 2016-08-29 | 2017-02-22 | 北京工业大学 | Video content access prediction and recommendation method based on user behavior preference |
CN108205775A (en) * | 2016-12-20 | 2018-06-26 | 阿里巴巴集团控股有限公司 | The recommendation method, apparatus and client of a kind of business object |
CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
WO2018126740A1 (en) * | 2017-01-04 | 2018-07-12 | 百度在线网络技术(北京)有限公司 | Method and device for pushing information |
CN106886872A (en) * | 2017-01-20 | 2017-06-23 | 淮阴工学院 | Method is recommended in a kind of logistics based on cluster and cosine similarity |
CN107145536A (en) * | 2017-04-19 | 2017-09-08 | 畅捷通信息技术股份有限公司 | User's portrait construction method and device and recommendation method and apparatus |
CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技(深圳)有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
CN108460651A (en) * | 2018-01-04 | 2018-08-28 | 金瓜子科技发展(北京)有限公司 | Vehicle recommends method and device |
CN108304668A (en) * | 2018-02-11 | 2018-07-20 | 河海大学 | A kind of Forecasting Flood method of combination hydrologic process data and history priori data |
CN108563681A (en) * | 2018-03-07 | 2018-09-21 | 阿里巴巴集团控股有限公司 | A kind of content recommendation method, device, electronic equipment and system |
CN108596679A (en) * | 2018-04-27 | 2018-09-28 | 中国联合网络通信集团有限公司 | Construction method, device, terminal and the computer readable storage medium of user's portrait |
CN108876509A (en) * | 2018-05-11 | 2018-11-23 | 上海赢科信息技术有限公司 | Utilize the method and system of POI analysis user tag |
CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
CN108960975A (en) * | 2018-06-15 | 2018-12-07 | 广州麦优网络科技有限公司 | Personalized Precision Marketing Method, server and storage medium based on user's portrait |
Non-Patent Citations (2)
Title |
---|
徐璐瑶;姜增祺;黄婷婷;刘云鹏;: "基于大数据的用户画像***概述", 电子世界, no. 02 * |
王高琴;沈炯;李益国;: "基于聚类和贝叶斯推断的市场出清电价离散概率分布预测", 中国电机工程学报, no. 34 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428087A (en) * | 2019-06-25 | 2019-11-08 | 万翼科技有限公司 | Business stability prediction technique, device, computer equipment and storage medium |
CN110427234A (en) * | 2019-06-27 | 2019-11-08 | 阿里巴巴集团控股有限公司 | The methods of exhibiting and device of the page |
CN110751168A (en) * | 2019-09-03 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
CN112133431A (en) * | 2020-08-27 | 2020-12-25 | 绿瘦健康产业集团有限公司 | Health information message pushing method, device, medium and terminal equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109902849B (en) | User behavior prediction method and device, and behavior prediction model training method and device | |
CN109767264A (en) | Product data method for pushing, device, computer equipment and storage medium | |
CN109829020A (en) | Place resource data push method, device, computer equipment and storage medium | |
CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
CN110245213A (en) | Questionnaire generation method, device, equipment and storage medium | |
CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
CN109493199A (en) | Products Show method, apparatus, computer equipment and storage medium | |
CN109345302A (en) | Machine learning model training method, device, storage medium and computer equipment | |
CN108090162A (en) | Information-pushing method and device based on artificial intelligence | |
CN109961080B (en) | Terminal identification method and device | |
CN110008397B (en) | Recommendation model training method and device | |
CN110910199A (en) | Item information sorting method and device, computer equipment and storage medium | |
CN109325118B (en) | Unbalanced sample data preprocessing method and device and computer equipment | |
CN109801101A (en) | Label determines method, apparatus, computer equipment and storage medium | |
CN108764319A (en) | A kind of sample classification method and apparatus | |
CN107203558B (en) | Object recommendation method and device, and recommendation information processing method and device | |
CN113379449B (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
CN115329204A (en) | Cloud business service pushing method and pushing processing system based on big data mining | |
CN109214904A (en) | Acquisition methods, device, computer equipment and the storage medium of financial fraud clue | |
CN113592535A (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
CN111768247A (en) | Order-placing rate prediction method, device and readable storage medium | |
CN111626767A (en) | Resource data distribution method, device and equipment | |
CN109377284B (en) | Method and electronic equipment for pushing information | |
CN112069269B (en) | Big data and multidimensional feature-based data tracing method and big data cloud server | |
CN110245571A (en) | Contract signature checking method, device, computer equipment and storage medium |
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 |