CN110334274A - Information-pushing method, device, computer equipment and storage medium - Google Patents
Information-pushing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110334274A CN110334274A CN201910463804.8A CN201910463804A CN110334274A CN 110334274 A CN110334274 A CN 110334274A CN 201910463804 A CN201910463804 A CN 201910463804A CN 110334274 A CN110334274 A CN 110334274A
- Authority
- CN
- China
- Prior art keywords
- user
- portrait
- data
- behavior data
- specified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
This application discloses a kind of information-pushing method, device, computer equipment and storage mediums, and wherein method includes: the crawler behavior data of each user in all specified App of acquisition；Crawler behavior data are uploaded to preset cloud storage platform in real time；It calls preset real-time analytical calculation engine to carry out real-time analysis processing to the crawler behavior data in cloud storage platform, obtains attribute tags corresponding with each crawler behavior data；According to attribute tags, user's portrait of each user corresponding with each attribute tags is constructed；It is drawn a portrait according to user, the specified App held to each user carries out information push.The application is handled by real-time analysis engine come the real-time analysis to crawler behavior data, to obtain user's portrait corresponding with crawler behavior data, effectively meets the business demand handled in real time the big data of magnanimity.Information corresponding with user's portrait is sent additionally by specified App, so as to accurately recommend suitable product to user.
Description
Technical field
This application involves information advancing technique fields, and in particular to a kind of information-pushing method, device, computer equipment and
Storage medium.
Background technique
User's portrait, i.e. user information labeling, refer to a person's identity data, consumption data, behavioral data, position
The user model data for the labeling that the data such as data and lifestyle data take out by data analysis.In current section
In the society that skill rapidly develops, enough Information bases are provided for company or enterprise since user draws a portrait, and can help
Enterprise is quickly found out the more extensive feedback information such as accurate user group and user demand, and user's portrait has become support
The basic mode for the big datas applications such as propertyization is recommended, automation is marketed.But existing financing corporation is all by the important of user
Information data is stored in traditional Database Systems, so that above-mentioned important information data summarize collection slowly, and these
Traditional Database Systems can't support the real-time calculation and analysis for important information data, lead to not complete to user's
The real-time building of user's portrait, so that the characteristics of financing corporation can not accurately understand user and demand, can not draw according to user
As accurately to recommend suitable financial product to user, the precision for selling development is low.
Summary of the invention
The main purpose of the application is to provide a kind of information-pushing method, device, computer equipment and storage medium, it is intended to
Solving existing financing corporation accurately cannot recommend suitable financial product to user according to user's portrait, sell development
The low technical problem of precision.
The application proposes a kind of information-pushing method, the method includes the steps:
The crawler behavior data of each user in all specified App are acquired, wherein the specified App is installed on each use
In the terminal device at family；
The crawler behavior data are uploaded to preset cloud storage platform in real time；
Preset real-time analytical calculation engine is called to carry out the crawler behavior data in the cloud storage platform real
When analysis handle, obtain attribute tags corresponding with each crawler behavior data；
According to the attribute tags, user's portrait of building each user corresponding with each attribute tags；
It is drawn a portrait according to the user, the specified App held to each user carries out information push.
Optionally, in all specified App of acquisition the step of the crawler behavior data of each user, comprising:
Obtain the journalizing data in each specified App；
Original active behavioral data is extracted from each journalizing data respectively；
Each original active behavioral data is formatted according to preset unified standard, it is identical to obtain format
Each crawler behavior data.
Optionally, the described the step of crawler behavior data are uploaded to preset cloud storage platform in real time, comprising:
Obtain the quantitative value of all specified App；
Multiple memory space buckets corresponding with the quantitative value of the specified App are created in the cloud storage platform,
Wherein the title of each bucket is corresponded with the title of each specified App respectively；
The crawler behavior data in each specified App are uploaded to each of the cloud storage platform correspondingly
It is stored in the bucket.
Optionally, described to call preset real-time analytical calculation engine to the crawler behavior in the cloud storage platform
The step of data carry out real-time analysis processing, obtain attribute tags corresponding with each crawler behavior data, comprising:
Distribute a random number for each bucket, wherein the integer that the number is 1-N, the N according to
The quantitative value value of the bucket；
Create multiple real-time analytical calculation engines that quantity is N；
The crawler behavior data under each bucket are obtained in real time respectively by each real-time analytical calculation engine, and
Data collection, data cleansing, model management and optimization are carried out to the crawler behavior data in each bucket, data are analyzed
Early warning and see clearly and the visualization output of data handle, obtain corresponding each attribute tags.
Optionally, the attribute tags include intrinsic identity attribute label and dynamic attribute label, described according to the category
Property label, the step of user's portrait of building each user corresponding with each attribute tags, comprising:
By all intrinsic identity attribute labelings at multiple specified build-in attribute labels, wherein described specified solid
Having attribute tags is the intrinsic identity attribute label that frequency of occurrence is greater than 1 in all intrinsic identity attribute labels；
It is extracted from all dynamic attribute labels and described specifies intrinsic identity attribute label corresponding with each
All specified dynamic attribute labels；
Respectively to it is each it is described specify the corresponding all specified dynamic attribute labels of intrinsic identity attribute label to be combined,
It obtains described intrinsic identity attribute label being specified respectively to combine text label correspondingly with each；
Intrinsic identity attribute label is specified to be associated with described correspondingly on each combine text label respectively,
Generate user's portrait of each user.
Optionally, described to be drawn a portrait according to the user, the specified App held to each user carries out the step of information push
Suddenly, comprising:
It is drawn a portrait according to the user, search and the corresponding recommendation information of each user's portrait；
Each recommendation information is sent to background server corresponding with the specified App；
Each recommendation information is pushed by the specified App that the background server is held to each user.
Optionally, described to be drawn a portrait according to the user, it searches and draws a portrait corresponding recommendation information with each user
Step, comprising:
Each user's portrait is input to preset recommended models；
It is filtered out from pre-stored resource by the recommended models corresponding described with each user's portrait
Recommendation information.
The application also provides a kind of information push-delivery apparatus, comprising:
Acquisition module, for acquiring the crawler behavior data of each user in all specified App, wherein the specified App
It is installed in the terminal device of each user；
Uploading module, for the crawler behavior data to be uploaded to preset cloud storage platform in real time；
Analysis module, for calling preset real-time analytical calculation engine to the movable row in the cloud storage platform
Real-time analysis processing is carried out for data, obtains attribute tags corresponding with each crawler behavior data；
Module is constructed, for according to the attribute tags, constructing each user's corresponding with each attribute tags
User's portrait；
Pushing module, for being drawn a portrait according to the user, the specified App held to each user carries out information push.
The application also provides a kind of computer equipment, including memory and processor, is stored with calculating in the memory
The step of machine program, the processor realizes the above method when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer journey
The step of above method is realized when sequence is executed by processor.
Information-pushing method, device, computer equipment and storage medium provided herein has following
The utility model has the advantages that
Information-pushing method, device, computer equipment and storage medium provided herein acquires all specified App
The crawler behavior data of interior each user, wherein the specified App is installed in the terminal device of each user；By the work
Dynamic behavioral data is uploaded to preset cloud storage platform in real time；Call preset real-time analytical calculation engine flat to the cloud storage
Crawler behavior data in platform carry out real-time analysis processing, obtain attribute corresponding with each crawler behavior data
Label；According to the attribute tags, user's portrait of building each user corresponding with each attribute tags；According to described
User's portrait, the specified App held to each user carry out information push.The application by preset real-time analysis engine come
It realizes that the real-time analysis to crawler behavior data is handled, and then obtains user's portrait corresponding with the crawler behavior data, effectively
Ground meets the business demand handled in real time the big data of magnanimity.In addition, being drawn a portrait according to the user of acquisition, by finger
Determine App and send information corresponding with user's portrait, accurately recommends suitable financial product to user to realize, improve finance
The precision of company's sale.
Detailed description of the invention
Fig. 1 is the flow diagram of the information-pushing method of one embodiment of the application；
Fig. 2 is the flow diagram of the information-pushing method of another embodiment of the application；
Fig. 3 is the flow diagram of the information-pushing method of the another embodiment of the application；
Fig. 4 is the structural schematic diagram of the information push-delivery apparatus of one embodiment of the application；
Fig. 5 is the structural schematic diagram of the computer equipment of one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It should be appreciated that specific embodiment described herein is used only for explaining the application, it is not used to limit the application.
It is to be appreciated that the directional instruction (such as up, down, left, right, before and after ...) of institute is only used in the embodiment of the present application
In explaining in relative positional relationship, the motion conditions etc. under a certain particular pose (as shown in the picture) between each component, if should
When particular pose changes, then directionality instruction also correspondingly changes correspondingly, and the connection, which can be, to be directly connected to,
It can be and be indirectly connected with.
Referring to Fig.1, the information-pushing method of one embodiment of the application, comprising:
S1: the crawler behavior data of each user in all specified App of acquisition, wherein the specified App is installed on each institute
It states in the terminal device of user；
S2: the crawler behavior data are uploaded to preset cloud storage platform in real time；
S3: preset real-time analytical calculation engine is called to carry out the crawler behavior data in the cloud storage platform
Real-time analysis processing obtains attribute tags corresponding with each crawler behavior data；
S4: according to the attribute tags, user's portrait of building each user corresponding with each attribute tags；
S5: drawing a portrait according to the user, and the specified App held to each user carries out information push.
As described in above-mentioned steps S1 and S2, the executing subject of this method embodiment is information push-delivery apparatus, and above- mentioned information push away
Device is sent to realize real-time perfoming pair to fetching by establishing with above-mentioned all specified finance App (Application, application program)
The acquisition of the crawler behavior data of all users in each specified finance App, later again uploads the crawler behavior data
It is stored to preset cloud storage platform.Wherein, above-mentioned specified App is installed in the terminal device of each user, the specified App
The financial App of implementation is issued by financing corporation, and all specified App are used in conjunction with a specified server and carry out data friendship
Mutually, above-mentioned cloud storage platform provides structuring or non-by the storage equipment of bottom and forming using access device for upper layer
The storage of structural data, and the maintenance management of data is provided, interface is provided for service application etc. and accesses data, and is easier to support
It can support the expansibility of laterally or longitudinally resource.The cloud storage platform of the present embodiment provides knot to above-mentioned crawler behavior data
The storage of structure data, structural data cloud storage, that is, distributed data base system support ODBC/JDBC (Open Database
Connectivity (Open Database Connection)/Java Database Connectivity (Java DataBase Connectivity)) interface；
Perfect SQL (Structured Query Language, structured query language) grammer is enriched in support；Support data compression
Storage；Support a variety of data distribution modes, and automatic implementation load balancing；Batch data importing/export function；Operation and Maintenance
With network management function (equipment management, fault management, performance statistics, log management, rights management, configuration management, RAID
(Redundant Arrays of Inexpensive Disks, Redundant Array of Inexpensive Disc) management etc.)；Whole process signaling with
Track, auxiliary user's observing system state and diagnosis problem.By by above-mentioned crawler behavior data be uploaded in cloud storage platform into
Row storage, so that cloud storage platform pair is able to maintain prolonged stability crawler behavior data of the number with TB.
As described in above-mentioned steps S3 to S5, value can as time goes by and reduces rapidly for the business of data, therefore
Data must be calculated and be handled to it as early as possible after occurring.And the big data tupe of traditional database is for data mart modeling
It follows and traditional day clear day finishes mode, i.e., even current data is added up and handled using day as calculating cycle using hour, shown
Right this kind of processing mode is unable to satisfy the demand that data calculate in real time.In such as real-time big data analysis, air control early warning, pre- in real time
Many business scenario fields such as survey, financial transaction, batch (offline in other words) processing want data processing time delay for above-mentioned
Asking for harsh application field is that can not be competent at its business demand completely.By the storage of above-mentioned crawler behavior data to can prop up
After holding the cloud storage platform calculated in real time, the present embodiment can call preset real-time analytical calculation engine to complete the work to magnanimity
The real-time analysis processing of dynamic behavioral data, and each user's portrait corresponding with each crawler behavior data is obtained, it is specifically, logical first
It crosses real-time analytical calculation engine and real-time analysis processing is carried out to above-mentioned crawler behavior data, obtain distinguishing with each crawler behavior data
Corresponding attribute tags construct user's portrait of each user corresponding with each attribute tags then according to above-mentioned attribute tags.Its
In, above-mentioned real-time analytical calculation engine is a kind of real-time Computational frame for stream data, it supports high-throughput, supports to hold
Wrong real-time streaming data processing, may be, for example, Teradata, ROLAP, ElasticSearch, Spark etc.；Above-mentioned attribute tags
For and to crawler behavior information analysis of the user in financial App come highly refined signature identification, above-mentioned attribute mark
Label may include the intrinsic identity attribute label and dynamic attribute label of user, which may include the surname of user
Name, age, gender, occupation, mailbox, telephone number etc., when which includes use time, the use using App
Long, browsing product, the content of search, the content of collection, deliver or content, the content of purchase of comment etc.；Above-mentioned user
Portrait is a kind of effective tool delineated target user, contact user's demand, therefore can be by the most plain and closeness to life language
By the attribute of user, behavior and expect that connection generates user's portrait.The virtual representations that user draws a portrait as actual user, are roots
Built according to product and market, reflect the feature and demand of real user, then construct user portrait core be then to
User labels " ", what user's portrait of the present embodiment was made of the attribute tags obtained, is obtaining above-mentioned each attribute mark
After label, user's portrait of each user comprising each above-mentioned attribute tags can be constructed, and further according to the user of generation
The specified App for drawing a portrait to hold to each user carries out information push.In the present embodiment, by calling real-time analytical calculation engine can
It realizes that the real-time analysis to above-mentioned crawler behavior data is handled, and obtains each user's portrait corresponding with each crawler behavior data,
It is final effectively to meet place in real time to effectively shorten full link data stream time delay, real time implementation calculating logic, divide calculating cost
Manage the business demand of big data (the crawler behavior data of magnanimity).In addition, after obtaining above-mentioned user's portrait, due to according to user
User's portrait can capture the current Some features of user and demand, to the product of financing corporation can be combined to carry out pair
The information recommendation answered, cocoa is by sending information corresponding with user's portrait to above-mentioned specified App, to realize accurately to difference
User recommend suitable financial product, improve the precision of financing corporation's sale.
Further, in one embodiment of the application, above-mentioned steps S1, comprising:
S100: the journalizing data in each specified App are obtained；
S101: original active behavioral data is extracted from each journalizing data respectively；
S102: each original active behavioral data is formatted according to preset unified standard, obtains format
Identical each crawler behavior data.
As described in above-mentioned steps S100 to S102, the source of above-mentioned crawler behavior information is the journalizing of each specified App
Data, but can believe comprising more noise rubbish since aforesaid operations daily record data type is relatively more, and in operation log data
Breath, it is therefore desirable to respective handling be carried out to the operation log data in all specified App to obtain above-mentioned crawler behavior information.
In the present embodiment, the operation log data in each specified App are obtained first, then the operation log data are carried out
Data scrubbing, to obtain above-mentioned original active behavioral data, wherein above-mentioned data scrubbing refers to one in operation log data
A little junk datas or attribute clean up, and only retain useful data.Finally by each above-mentioned original active behavioral data according to preset
Unified standard formats, and obtains the identical each crawler behavior data of format.Specifically, above-mentioned by each original active behavior
The step of data are formatted according to preset unified standard can include: set first according to above-mentioned original active behavioral data
Set unified standard form；Then each above-mentioned original active behavioral data is divided into independent data field, and filters and provides
Have the specified data field of specific meanings, wherein above-mentioned specified data field refer to it is some to formed user's portrait it is relevant important
Field corresponding to data；Category conversion processing is carried out to above-mentioned specified data field according to preset statement format later,
In above-mentioned statement format be the format for including the elements such as time, place, personage, object, cause and effect；Finally in category conversion
After the completion of processing, above-mentioned specified data field is filled into the data field with corresponding meaning in preset standard form,
To obtain each above-mentioned crawler behavior data.In the present embodiment, by carrying out data scrubbing to the journalizing data in specified App
Be conducive to the subsequent work for same user with the processing of data conversion to obtain that there is the crawler behavior information of unified format
The data of dynamic behavioural information merge.In addition, by by the crawler behavior information with unified format be uploaded to cloud storage platform into
Row storage is advantageously implemented the normalization and independent property that the corresponding crawler behavior data storage of App is specified to each.
Referring to Fig. 2, further, in one embodiment of the application, above-mentioned steps S2, comprising:
S200: the quantitative value of all specified App is obtained；
S201: multiple memory spaces corresponding with the quantitative value of the specified App are created in the cloud storage platform
Bucket, wherein the title of each bucket is corresponded with the title of each specified App respectively；
S202: the crawler behavior data in each specified App are uploaded to the cloud storage correspondingly and are put down
It is stored in each bucket of platform.
It is above-mentioned that crawler behavior data are uploaded to preset cloud storage platform in real time as described in above-mentioned steps S200 to S202
Process, specifically can include: obtain the quantity of all specified App first, and in advance in above-mentioned cloud storage platform setting and should
The corresponding multiple bucket of quantity of specified App are used for storage object wherein above-mentioned bucket refers to memory space
(Object) container, and all objects must all be under the jurisdiction of some memory space；In addition each bucket for creating with
Each specified App is one-to-one relationship, i.e., a specified App is only bound with a corresponding bucket, such as
It can be correspondingly arranged according to the Apply Names of each specified App containing multiple buckets identical with each Apply Names.Obtaining each finger
After determining the above-mentioned crawler behavior data in App, which can be uploaded to correspondingly in cloud storage platform
Bucket in deposited.In the present embodiment, by being corresponded to according to the quantity of specified App to be generated in the inside of cloud storage platform
Multiple bucket, and store by multiple bucket crawler behavior data of each specified App respectively so that each
The specified corresponding crawler behavior data of App can be uniformly distributed on each bucket of cloud storage platform, be realized to each
The effective differentiation for the crawler behavior data that a specified App is generated and uniform distribution storage.In addition be conducive to analyze in real time
Computing engines carry out to crawler behavior data carry out analytical calculation processing when, can according to business demand only to some or it is multiple
The crawler behavior data stored in specific bucket are analyzed and processed, or can also be simultaneously to storing in all bucket
Each crawler behavior data are analyzed and processed, to improve the processing flexibility ratio to crawler behavior data.
Further, in one embodiment of the application, above-mentioned steps S3, comprising:
S300: distributing a random number for each bucket, wherein the integer that the number is 1-N, the N
According to the quantitative value value of the bucket；
S301: multiple real-time analytical calculation engines that creation quantity is N；
S302: the crawler behavior number under each bucket is obtained by each real-time analytical calculation engine in real time respectively
According to, and data collection, data cleansing, model management and optimization, data are carried out to the crawler behavior data in each bucket
The early warning of analysis and see clearly and the visualization output of data handle, obtain corresponding each attribute tags.
As described in above-mentioned steps S300 to S302, above-mentioned real-time analytical calculation engine be may be implemented for above-mentioned crawler behavior
The real-time analytical calculation of data, wherein the quantity of above-mentioned real-time computing engines is not construed as limiting, the real-time analytical calculation engine
Quantity can improve for one or more, preferably settable multiple real-time analytical calculation engines to above-mentioned crawler behavior data
Processing speed.In the present embodiment, the above-mentioned preset real-time analytical calculation engine of calling is to the work in the cloud storage platform
The step of dynamic behavioral data carries out real-time analysis processing, obtains attribute tags corresponding with each crawler behavior data,
Specifically can include: first be each bucket distribute a random number, wherein number be 1-N integer, and N according to
Then the quantitative value value of bucket creates multiple real-time analytical calculation engines that quantity is N, passes through each real-time analysis meter later
It calculates engine and obtains the crawler behavior data under each bucket in real time respectively, and according to preset analysis model in each bucket
Crawler behavior data carry out real-time analysis and handle to obtain corresponding each attribute tags, wherein above-mentioned analysis model is set in real time
The inside of analysis engine is set, for executing the realization analysis processing for crawler behavior data, the creation method of the analysis model
The method that can refer to existing creation model, details are not described herein.In addition, the process of above-mentioned real-time analysis processing includes that data are received
Collection, data cleansing, model management and optimization, data analysis early warning and see clearly and the visualization of data export.The present embodiment
By creating multiple real-time analytical calculation engines corresponding with bucket quantity, may be implemented to call multiple real-time analysis meters simultaneously
It calculates engine to carry out real-time analysis processing to the behavioral activity data under each bucket, and then the behavior to magnanimity can be improved
The treatment effeciency of activity data, and improve to obtain the speed of corresponding attribute tags.
Further, in one embodiment of the application, the attribute tags include intrinsic identity attribute label and dynamic attribute
Label, above-mentioned steps S4, comprising:
S400: by all intrinsic identity attribute labelings at multiple specified build-in attribute labels, wherein the finger
Determining build-in attribute label is the intrinsic identity attribute label that frequency of occurrence is greater than 1 in all intrinsic identity attribute labels；
S401: it is extracted from all dynamic attribute labels and described specifies intrinsic identity attribute label right respectively with each
All specified dynamic attribute labels answered；
S402: described the corresponding all specified dynamic attribute label of intrinsic identity attribute label is specified to carry out to each respectively
Combination obtains described intrinsic identity attribute label being specified respectively to combine text label correspondingly with each；
S403: intrinsic identity attribute label is specified to carry out with described correspondingly on each combine text label respectively
Association generates user's portrait of each user.
As described in above-mentioned steps S401 to S403, due to specifying the quantity of App there are multiple, thus for constructing user's picture
The data source more than one of picture, the same user would generally produce crawler behavior data in different specified App, therefore
The corresponding a variety of dynamic attribute labels for needing to generate the same user in different specified App are bound, so that
Each dynamic attribute label after binding belongs to the same user, to guarantee the accurate of the user being subsequently generated portrait
Degree.Above-mentioned attribute tags include intrinsic identity attribute label and dynamic attribute label, and above-mentioned constructed according to each attribute tags corresponds to
Each user user portrait process, specifically can comprise the following steps that first will all intrinsic identity attribute labels divide
Class is at multiple specified build-in attribute labels, wherein above-mentioned specified build-in attribute label is in all above-mentioned intrinsic identity attribute marks
Frequency of occurrence is greater than 1 intrinsic identity attribute label in label, by filtering out repetition from all intrinsic identity attribute labels
The intrinsic identity attribute label occurred, and labeled as intrinsic identity attribute label is specified, to indicate that these repeat multiple
Intrinsic identity attribute label corresponds to the same designated user.Then from extracted in all above-mentioned dynamic attribute labels with it is each on
It states and specifies the corresponding specified dynamic attribute label of intrinsic identity attribute label, specify intrinsic identity attribute to each respectively later
The corresponding all specified dynamic attribute labels of label are combined, and obtain specifying intrinsic identity attribute label to correspond with each
Each combination text label, finally each said combination text label and intrinsic identity attribute label will be specified correspondingly respectively
It is associated, generates user's portrait of each user, so that can include the finger of corresponding designated user in user's portrait
Fixed intrinsic identity attribute label and the corresponding all specified dynamic attribute labels of intrinsic identity attribute label are specified with this, i.e.,
Corresponding combine text label, and intrinsic identity attribute label can be specified by this to characterize the institute of its corresponding user's portrait
The characteristics of belonging to, its corresponding user is characterized by combine text label and demand.In the present embodiment, to all intrinsic bodies
Part attribute is classified after obtaining multiple specified build-in attribute labels, by specifying intrinsic identity attribute label to each respectively
Corresponding all specified dynamic attribute labels are combined to obtain combine text label, and respectively by each combination text label
The user of each user portrait is generated with specifying intrinsic identity attribute label to be associated correspondingly, being conducive to will not
Summarize with the dynamic attribute label for belonging to same user in data source and be tied to the user, so that above-mentioned user portrait includes more
Add comprehensive user data, i.e. user's corresponding all dynamic attribute labels in different App, to effectively improve life
At user portrait accuracy, also improve indirectly according to user draw a portrait carry out information recommendation accuracy.
Referring to Fig. 3, further, in one embodiment of the application, above-mentioned steps S5, comprising:
S500: drawing a portrait according to the user, search and the corresponding recommendation information of each user's portrait；
S501: each recommendation information is sent to background server corresponding with the specified App；
S502: each recommendation information is pushed by the specified App that the background server is held to each user.
As described in above-mentioned steps S500 to S502, user's portrait refers to a person's identity data, consumption data, behavior
The user model number for the labeling that the data such as data, position data and lifestyle data take out by data analysis
According to.After having obtained user's portrait of each user corresponding with above-mentioned each crawler behavior data, according to each user
Portrait can search each recommendation information corresponding with each user's portrait, and each recommendation information is sent to and is specified with described
The corresponding background server of App pushes each above-mentioned recommendation with the specified App held by the background server to each user
Breath.Further, recommendation information corresponding with user object can be shown to user by specifying the predeterminated position of App at this,
Citing ground, when the terminal device of the first user shows certain specified App, at this, the designated position at certain specified interface App is for example pushed up
The key positions such as portion, bottom, intermediate both ends show the first recommendation information corresponding with the user of the first user portrait.The present embodiment
It is obtained and the corresponding recommendation information of user's portrait is sent to background server corresponding with specified App, then controlled by that will search
The background server sends recommendation message corresponding with respective user portrait come the specified App held to each user,
Accurately recommend suitable financial product to different users to realize, improves the accuracy of push recommendation information, also improve
The precision of financing corporation's sale.
Further, in one embodiment of the application, above-mentioned steps S500, comprising:
S5000: each user's portrait is input to preset recommended models；
S5001: it is filtered out from pre-stored resource by the recommended models and is respectively corresponded with each user's portrait
The recommendation information.
As described in above-mentioned steps S5000 and S5001, a recommended models can be pre-created, and by the recommended models come
Generate financial recommendation information corresponding with user's portrait.The process of above-mentioned recommended models is wherein created, specifically can include: acquisition refers to
The sample data of fixed number amount, wherein above-mentioned sample data is historical user's representation data, and historical user's representation data is specific
To be labeled with the corresponding Feature Words for recommending resource, such as the format of above-mentioned sample data are as follows: Feature Words+mark is corresponding to be pushed away
Resource is recommended, in addition above-mentioned specified quantity is not especially limited, can be determined according to the actual situation；Then above-mentioned sample data is defeated
Enter to preset specified neural network model and be trained, until above-mentioned specified neural network model convergence；It finally will be by instruction
Convergent above-mentioned specified neural network, is determined as above-mentioned recommended models after white silk.Wherein, to the concrete kind of specified neural network model
Type is not construed as limiting, which can be convolutional neural networks (CNN) model, Recognition with Recurrent Neural Network (RNN) mould
Any one in type, deep neural network (DNN) model or any number of combinations, but it is not limited to the above-mentioned nerve enumerated
Network model.Moreover, it is achieved that specified neural network convergence refers to: the accuracy of the output result of specified neural network is greater than default
Threshold value (such as 98% can be set as), citing ground, when specified neural network model is exported for a certain special characteristic word of input
Recommendation resource results, the error between the specific recommendations resource of special characteristic word mark is 1%, shows to export result
Accuracy is greater than preset threshold, then can determine that the specified neural network model has been restrained, and this can be specified to neural network mould
Type is determined as recommended models, and recommendation information corresponding with user's portrait is generated by the recommended models to realize.In addition, above-mentioned
Recommended models also have the function of self-learning optimization, and the model parameter of itself can be adjusted according to user's representation data of update,
The recommendation information obtained by the recommended models is enabled more to meet the preference of user.It is above-mentioned according to user in the present embodiment
Portrait, the step of search with each user portrait corresponding recommendation information can include: be first input to each user portrait default
Recommended models, then filtered out from pre-stored resource by above-mentioned recommended models and to be drawn a portrait corresponding recommendation with each user
Information.Wherein, the above-mentioned screening process to recommendation information, comprising: above-mentioned recommended models are in any one use for receiving input
After the portrait of family, it can draw a portrait to the user carry out keyword extraction first, and obtain the corresponding keyword of user portrait, then
Matching treatment is carried out to obtained above-mentioned keyword and internal pre-stored all Feature Words, obtains finger corresponding with the keyword
Determine Feature Words, finally filtering out from all resources of storage inside with the specific characteristic word is the recommendation for matching corresponding relationship
Breath.It is corresponding with user's portrait to be exported by recommended models by the way that user's portrait is input to recommended models in the present embodiment
Recommendation information be conducive to the accuracy for improving recommendation information push so that the recommendation information obtained more meets the preference of user.
Referring to Fig. 4, a kind of information push-delivery apparatus is additionally provided in one embodiment of the application, comprising:
Acquisition module 1, for acquiring the crawler behavior data of each user in all specified App, wherein the specified App
It is installed in the terminal device of each user；
Uploading module 2, for the crawler behavior data to be uploaded to preset cloud storage platform in real time；
Analysis module 3, for calling preset real-time analytical calculation engine to the activity in the cloud storage platform
Behavioral data carries out real-time analysis processing, obtains attribute tags corresponding with each crawler behavior data；
Module 4 is constructed, for according to the attribute tags, constructing each user's corresponding with each attribute tags
User's portrait；
Pushing module 5, for being drawn a portrait according to the user, the specified App held to each user carries out information push.
In the present embodiment, acquisition module, uploading module, analysis module in above- mentioned information driving means, building module with
The function of pushing module and the realization process of effect are specifically detailed in the realization that step S1-S5 is corresponded in above- mentioned information method for pushing
Journey, details are not described herein.
Further, in one embodiment of the application, above-mentioned acquisition module, comprising:
First acquisition unit, for obtaining the journalizing data in each specified App；
First extraction unit, for extracting original active behavioral data from each journalizing data respectively；
Converting unit, for each original active behavioral data to be formatted according to preset unified standard,
Obtain the identical each crawler behavior data of format.
In the present embodiment, the first acquisition unit that includes in the acquisition module in above- mentioned information driving means, first are extracted
Unit is specifically detailed in above- mentioned information method for pushing with the realization process of the function of converting unit and effect and corresponds to step S100-
The realization process of S102, details are not described herein.
Further, in one embodiment of the application, above-mentioned uploading module, comprising:
Second acquisition unit, for obtaining the quantitative value of all specified App；
First creating unit is corresponding more with the quantitative value of the specified App for creating in the cloud storage platform
A memory space bucket, wherein the title of each bucket is corresponded with the title of each specified App respectively；
Uploading unit, it is described for being uploaded to the crawler behavior data in each specified App correspondingly
It is stored in each bucket of cloud storage platform.
In the present embodiment, the second acquisition unit that includes in the uploading module in above- mentioned information driving means, the first creation
Unit is specifically detailed in above- mentioned information method for pushing with the realization process of the function of uploading unit and effect and corresponds to step S200-
The realization process of S202, details are not described herein.
Further, in one embodiment of the application, above-mentioned processing module, comprising:
Allocation unit, for distributing a random number for each bucket, wherein the number is the whole of 1-N
Number, the N is according to the quantitative value value of the bucket；
Second creating unit, for creating multiple real-time analytical calculation engines that quantity is N；
Processing unit, for obtaining the work under each bucket in real time respectively by each real-time analytical calculation engine
Dynamic behavioral data, and to the crawler behavior data in each bucket carry out data collection, data cleansing, model management with it is excellent
Change, data analysis early warning and see clearly and the visualization output of data handle, obtain corresponding each attribute tags.
In the present embodiment, the allocation unit, the second creating unit that include in the processing module in above- mentioned information driving means
It is specifically detailed in above- mentioned information method for pushing with the realization process of the function of processing unit and effect and corresponds to step S300-S302's
Realization process, details are not described herein.Further, in one embodiment of the application, above-mentioned attribute tags include intrinsic identity attribute
Label and dynamic attribute label, above-mentioned building module, comprising:
Taxon, for by all intrinsic identity attribute labelings at multiple specified build-in attribute labels,
In, the specified build-in attribute label is the intrinsic identity that frequency of occurrence is greater than 1 in all intrinsic identity attribute labels
Attribute tags；
Second extraction unit described specifies intrinsic identity category with each for extracting from all dynamic attribute labels
The property corresponding all specified dynamic attribute labels of label；
Assembled unit, for described specifying the corresponding all specified dynamic attributes of intrinsic identity attribute label to each respectively
Label is combined, and obtains described intrinsic identity attribute label being specified respectively to combine text label correspondingly with each；
Generation unit, for each combine text label to be specified intrinsic identity attribute with described correspondingly respectively
Label is associated, and generates user's portrait of each user.
In the present embodiment, the taxon that includes in the building module in above- mentioned information driving means, the second extraction unit,
Assembled unit is specifically detailed in above- mentioned information method for pushing with the realization process of the function of generation unit and effect and corresponds to step
The realization process of S400-S403, details are not described herein.
Further, in one embodiment of the application, above-mentioned pushing module, comprising:
Search unit, for being drawn a portrait according to the user, search and the corresponding recommendation information of each user's portrait；
Transmission unit, for each recommendation information to be sent to background server corresponding with the specified App；
Push unit, specified App push for being held by from the background server to each user is each described to be pushed away
Recommend information.
In the present embodiment, the search unit that includes in the pushing module in above- mentioned information driving means, transmission unit and push away
The realization process of the function and effect of sending unit is specifically detailed in the realization that step S500-S502 is corresponded in above- mentioned information method for pushing
Process, details are not described herein.
Further, in one embodiment of the application, above-mentioned search unit, comprising:
Subelement is inputted, for each user's portrait to be input to preset recommended models；
Subelement is screened, is drawn a portrait for being filtered out from pre-stored resource by the recommended models with each user
The corresponding recommendation information.
In the present embodiment, the input subelement and screening subelement that include in the search unit in above- mentioned information driving means
Function and the realization process of effect be specifically detailed in the realization that step S5000-S5001 is corresponded in above- mentioned information method for pushing
Journey, details are not described herein.
Referring to Fig. 5, a kind of computer equipment is also provided in the embodiment of the present application, which can be server,
Its internal structure can be as shown in Figure 5.The computer equipment includes processor, the memory, network connected by system bus
Interface and database.Wherein, the processor of computer equipment design is for providing calculating and control ability.The computer equipment
Memory include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer
Program and database.The built-in storage provides ring for the operation of operating system and computer program in non-volatile memory medium
Border.The database of the computer equipment is for storing the data such as crawler behavior data, attribute tags and user's portrait.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize information-pushing method shown by any of the above-described a exemplary embodiment.
Above-mentioned processor executes the step of above- mentioned information method for pushing:
The crawler behavior data of each user in all specified App are acquired, wherein the specified App is installed on each use
In the terminal device at family；
The crawler behavior data are uploaded to preset cloud storage platform in real time；
Preset real-time analytical calculation engine is called to carry out the crawler behavior data in the cloud storage platform real
When analysis handle, obtain attribute tags corresponding with each crawler behavior data；
According to the attribute tags, user's portrait of building each user corresponding with each attribute tags；
It is drawn a portrait according to the user, the specified App held to each user carries out information push.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction of the device, computer equipment that are applied thereon to application scheme.
One embodiment of the application also provides a kind of computer readable storage medium, is stored thereon with computer program, the meter
When calculation machine program is executed by one or more processors, so that realizing above- mentioned information push side when one or more processors execute
Step in method embodiment.
A kind of information-pushing method is realized when computer program is executed by processor, specifically:
The crawler behavior data of each user in all specified App are acquired, wherein the specified App is installed on each use
In the terminal device at family；
The crawler behavior data are uploaded to preset cloud storage platform in real time；
Preset real-time analytical calculation engine is called to carry out the crawler behavior data in the cloud storage platform real
When analysis handle, obtain attribute tags corresponding with each crawler behavior data；
According to the attribute tags, user's portrait of building each user corresponding with each attribute tags；
It is drawn a portrait according to the user, the specified App held to each user carries out information push.
In conclusion the information-pushing method provided in the embodiment of the present application, device, computer equipment and storage medium,
The crawler behavior data of each user in all specified App are acquired, wherein the specified App is installed on the terminal of each user
In equipment；The crawler behavior data are uploaded to preset cloud storage platform in real time；Preset real-time analytical calculation is called to draw
It holds up and real-time analysis processing is carried out to the crawler behavior data in the cloud storage platform, obtain and each crawler behavior number
According to corresponding attribute tags；According to the attribute tags, construct each user's corresponding with each attribute tags
User's portrait；It is drawn a portrait according to the user, the specified App held to each user carries out information push.The application passes through pre-
If real-time analysis engine realize the real-time analysis processing to crawler behavior data, and then obtain and the crawler behavior data pair
The user's portrait answered, effectively meets the business demand handled in real time the big data of magnanimity.In addition, according to acquisition
User's portrait accurately recommends suitable gold by sending information corresponding with user's portrait to specified App to realize to user
Melt product, improves the precision of financing corporation's sale.
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 store and 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,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
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 can by diversified forms
, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed are according to rate SDRAM (SSRSDRAM), increasing
Strong type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include the other elements being not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of information-pushing method characterized by comprising
The crawler behavior data of each user in all specified App are acquired, wherein the specified App is installed on each user's
In terminal device；
The crawler behavior data are uploaded to preset cloud storage platform in real time；
Preset real-time analytical calculation engine is called to divide the crawler behavior data in the cloud storage platform in real time
Analysis processing obtains attribute tags corresponding with each crawler behavior data；
According to the attribute tags, user's portrait of building each user corresponding with each attribute tags；
It is drawn a portrait according to the user, the specified App held to each user carries out information push.
2. information-pushing method according to claim 1, which is characterized in that each use in all specified App of acquisition
The step of crawler behavior data at family, comprising:
Obtain the journalizing data in each specified App；
Original active behavioral data is extracted from each journalizing data respectively；
Each original active behavioral data is formatted according to preset unified standard, obtains the identical each institute of format
State crawler behavior data.
3. information-pushing method according to claim 1, which is characterized in that it is described by the crawler behavior data it is real-time on
The step of reaching preset cloud storage platform, comprising:
Obtain the quantitative value of all specified App；
Multiple memory space buckets corresponding with the quantitative value of the specified App are created in the cloud storage platform, wherein
The title of each bucket is corresponded with the title of each specified App respectively；
The crawler behavior data in each specified App are uploaded to each described of the cloud storage platform correspondingly
It is stored in bucket.
4. information-pushing method according to claim 3, which is characterized in that described that preset real-time analytical calculation is called to draw
It holds up and real-time analysis processing is carried out to the crawler behavior data in the cloud storage platform, obtain and each crawler behavior number
The step of according to corresponding attribute tags, comprising:
A random number is distributed for each bucket, wherein the integer that the number is 1 to N, the N is according to
The quantitative value value of bucket；
Create multiple real-time analytical calculation engines that quantity is N；
The crawler behavior data under each bucket are obtained in real time respectively by each real-time analytical calculation engine, and to each
Crawler behavior data in the bucket carry out the early warning of data collection, data cleansing, model management and optimization, data analysis
With see clearly and the visualization output of data handle, obtain corresponding each attribute tags.
5. information-pushing method according to claim 1, which is characterized in that the attribute tags include intrinsic identity attribute
Label and dynamic attribute label, described according to the attribute tags, building each user corresponding with each attribute tags
User portrait the step of, comprising:
By all intrinsic identity attribute labelings at multiple specified build-in attribute labels, wherein the specified intrinsic category
Property label be in all intrinsic identity attribute labels frequency of occurrence be greater than 1 intrinsic identity attribute label；
It is extracted from all dynamic attribute labels and described specifies intrinsic identity attribute label corresponding specified with each
Dynamic attribute label；
Respectively to it is each it is described specify the corresponding all specified dynamic attribute labels of intrinsic identity attribute label to be combined, obtain
Described intrinsic identity attribute label is specified respectively to combine text label correspondingly with each；
It specifies intrinsic identity attribute label to be associated with described correspondingly on each combine text label respectively, generates
The user of each user draws a portrait.
6. information-pushing method according to claim 1, which is characterized in that described to be drawn a portrait according to the user, Xiang Gesuo
State the step of specified App that user holds carries out information push, comprising:
It is drawn a portrait according to the user, search and the corresponding recommendation information of each user's portrait；
Each recommendation information is sent to background server corresponding with the specified App；
Each recommendation information is pushed by the specified App that the background server is held to each user.
7. information-pushing method according to claim 6, which is characterized in that it is described according to the user draw a portrait, search with
The step of each user's portrait corresponding recommendation information, comprising:
Each user's portrait is input to preset recommended models；
It is filtered out from pre-stored resource by the recommended models and is drawn a portrait the corresponding recommendation with each user
Information.
8. a kind of information push-delivery apparatus characterized by comprising
Acquisition module, for acquiring the crawler behavior data of each user in all specified App, wherein the specified App installation
In in the terminal device of each user；
Uploading module, for the crawler behavior data to be uploaded to preset cloud storage platform in real time；
Analysis module, for calling preset real-time analytical calculation engine to the crawler behavior number in the cloud storage platform
According to real-time analysis processing is carried out, attribute tags corresponding with each crawler behavior data are obtained；
Module is constructed, for according to the attribute tags, constructing the user of each user corresponding with each attribute tags
Portrait；
Pushing module, for being drawn a portrait according to the user, the specified App held to each user carries out information push.
9. a kind of computer equipment, including memory and processor, it is stored with computer program in the memory, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is held by processor
The step of method described in any one of claims 1 to 7 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463804.8A CN110334274A (en) | 2019-05-30 | 2019-05-30 | Information-pushing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463804.8A CN110334274A (en) | 2019-05-30 | 2019-05-30 | Information-pushing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110334274A true CN110334274A (en) | 2019-10-15 |
Family
ID=68140516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910463804.8A Pending CN110334274A (en) | 2019-05-30 | 2019-05-30 | Information-pushing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110334274A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111030893A (en) * | 2019-12-31 | 2020-04-17 | 上海途鸽数据科技有限公司 | Method and device for analyzing user behaviors in cloud communication application scene |
| CN111143740A (en) * | 2019-12-14 | 2020-05-12 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN111223235A (en) * | 2019-12-27 | 2020-06-02 | 合肥美的智能科技有限公司 | Commodity putting method of unmanned cabinet, unmanned cabinet and control device of unmanned cabinet |
| CN111652735A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance product recommendation method based on user behavior label characteristics and commodity characteristics |
| CN112102956A (en) * | 2020-10-13 | 2020-12-18 | 杭州健海科技有限公司 | Method and system for improving compliance of diabetic patient |
| CN112508607A (en) * | 2020-12-02 | 2021-03-16 | 上海中商网络股份有限公司 | Data pushing method and device, computer equipment and readable storage medium |
| CN112613936A (en) * | 2020-12-04 | 2021-04-06 | 光大科技有限公司 | Message pushing method and device, storage medium and electronic device |
| CN112925815A (en) * | 2021-02-23 | 2021-06-08 | 四川享宇金信金融科技有限公司 | Automatic push information generation system with tracking function |
| CN113362117A (en) * | 2021-07-02 | 2021-09-07 | 柒久园艺科技(北京)有限公司 | Visual analysis method, system, equipment and storage medium for commodity data |
| WO2021175021A1 (en) * | 2020-03-06 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Product push method and apparatus, computer device, and storage medium |
| CN113449163A (en) * | 2021-06-29 | 2021-09-28 | 平安养老保险股份有限公司 | Customer mining method, device, equipment and storage medium based on artificial intelligence |
| CN114021175A (en) * | 2021-11-19 | 2022-02-08 | 深圳市电子商务安全证书管理有限公司 | User portrait configuration method and device, computer equipment and medium |
| CN115174514A (en) * | 2022-05-31 | 2022-10-11 | 青岛海尔科技有限公司 | Message pushing method and device, storage medium and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140122456A1 (en) * | 2012-03-30 | 2014-05-01 | Percolate Industries, Inc. | Interactive computing recommendation facility with learning based on user feedback and interaction |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| WO2017157146A1 (en) * | 2016-03-15 | 2017-09-21 | 平安科技（深圳）有限公司 | User portrait-based personalized recommendation method and apparatus, server, and storage medium |
| CN109493199A (en) * | 2019-01-04 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
-
2019
- 2019-05-30 CN CN201910463804.8A patent/CN110334274A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140122456A1 (en) * | 2012-03-30 | 2014-05-01 | Percolate Industries, Inc. | Interactive computing recommendation facility with learning based on user feedback and interaction |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| WO2017157146A1 (en) * | 2016-03-15 | 2017-09-21 | 平安科技（深圳）有限公司 | User portrait-based personalized recommendation method and apparatus, server, and storage medium |
| CN109493199A (en) * | 2019-01-04 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143740A (en) * | 2019-12-14 | 2020-05-12 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN111223235A (en) * | 2019-12-27 | 2020-06-02 | 合肥美的智能科技有限公司 | Commodity putting method of unmanned cabinet, unmanned cabinet and control device of unmanned cabinet |
| CN111030893A (en) * | 2019-12-31 | 2020-04-17 | 上海途鸽数据科技有限公司 | Method and device for analyzing user behaviors in cloud communication application scene |
| WO2021175021A1 (en) * | 2020-03-06 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Product push method and apparatus, computer device, and storage medium |
| CN111652735A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance product recommendation method based on user behavior label characteristics and commodity characteristics |
| CN112102956A (en) * | 2020-10-13 | 2020-12-18 | 杭州健海科技有限公司 | Method and system for improving compliance of diabetic patient |
| CN112508607A (en) * | 2020-12-02 | 2021-03-16 | 上海中商网络股份有限公司 | Data pushing method and device, computer equipment and readable storage medium |
| CN112613936A (en) * | 2020-12-04 | 2021-04-06 | 光大科技有限公司 | Message pushing method and device, storage medium and electronic device |
| CN112925815B (en) * | 2021-02-23 | 2023-08-08 | 四川享宇金信金融科技有限公司 | Push information automatic generation system with tracking function |
| CN112925815A (en) * | 2021-02-23 | 2021-06-08 | 四川享宇金信金融科技有限公司 | Automatic push information generation system with tracking function |
| CN113449163A (en) * | 2021-06-29 | 2021-09-28 | 平安养老保险股份有限公司 | Customer mining method, device, equipment and storage medium based on artificial intelligence |
| CN113362117A (en) * | 2021-07-02 | 2021-09-07 | 柒久园艺科技(北京)有限公司 | Visual analysis method, system, equipment and storage medium for commodity data |
| CN113362117B (en) * | 2021-07-02 | 2023-12-26 | 柒久园艺科技(北京)有限公司 | Visual analysis method, system, equipment and storage medium for commodity data |
| CN114021175B (en) * | 2021-11-19 | 2022-08-02 | 深圳市电子商务安全证书管理有限公司 | User portrait configuration method and device, computer equipment and medium |
| CN114021175A (en) * | 2021-11-19 | 2022-02-08 | 深圳市电子商务安全证书管理有限公司 | User portrait configuration method and device, computer equipment and medium |
| CN115174514A (en) * | 2022-05-31 | 2022-10-11 | 青岛海尔科技有限公司 | Message pushing method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334274A (en) | Information-pushing method, device, computer equipment and storage medium | |
| CN110796470B (en) | Data analysis system for market subject supervision and service | |
| AU2011239306B2 (en) | Digital analytics system | |
| US20080208661A1 (en) | Method and system of using anrtifacts to identify elements of a component business model | |
| CN107908606A (en) | Method and system based on different aforementioned sources automatic report generation | |
| CN107766402A (en) | A kind of building dictionary cloud source of houses big data platform | |
| CN106202566A (en) | A kind of magnanimity electricity consumption data mixing based on big data storage system and method | |
| CN112580914A (en) | Method and device for realizing enterprise-level data middling platform system for collecting multi-source data | |
| CN109656963A (en) | Metadata acquisition methods, device, equipment and computer readable storage medium | |
| CN103631922A (en) | Hadoop cluster-based large-scale Web information extraction method and system | |
| CN107103064A (en) | Data statistical approach and device | |
| CN111400288A (en) | Data quality inspection method and system | |
| CN115423289A (en) | Intelligent plate processing workshop data processing method and terminal | |
| CN106982251A (en) | Project field work data reporting method and system are reconnoitred based on mobile device | |
| US20080147457A1 (en) | Systems and methods for handling attributes used for assignment generation in a value flow environment | |
| CN113254630A (en) | Domain knowledge map recommendation method for global comprehensive observation results | |
| CN112527886A (en) | Data warehouse system based on urban brain | |
| CN107153702A (en) | A kind of data processing method and device | |
| CN116842055A (en) | System and method for integrated processing of internet of things data batch flow | |
| CN112817958A (en) | Electric power planning data acquisition method and device and intelligent terminal | |
| CN114756563A (en) | Data management system with multiple coexisting complex service lines of internet | |
| US10055469B2 (en) | Method and software for retrieving information from big data systems and analyzing the retrieved data | |
| CN112163017B (en) | Knowledge mining system and method | |
| CN107871055A (en) | A kind of data analysing method and device | |
| CN115329011A (en) | Data model construction method, data query method, data model construction device and data query device, 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 |