CN109408716A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN109408716A CN109408716A CN201811207503.0A CN201811207503A CN109408716A CN 109408716 A CN109408716 A CN 109408716A CN 201811207503 A CN201811207503 A CN 201811207503A CN 109408716 A CN109408716 A CN 109408716A
- Authority
- CN
- China
- Prior art keywords
- pushed information
- information
- pushed
- user
- recommended models
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for pushed information.If a specific embodiment of the method for pushed information includes: to receive the first pushed information, recommended models are obtained from the distributed account book based on block chain, wherein, the distributed account book based on block chain is for storing recommended models, and recommended models are for recommending push user；First pushed information is input to recommended models, determines the corresponding first push user of the first pushed information；First pushed information is pushed to the first push user.The embodiment is that pushed information recommends push user using the recommended models stored in the distributed account book based on block chain, improves the precision of information push.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for pushed information.
Background technique
Information push is also known as " Web broadcast " by certain technical standard or agreement, on the internet by pushing away
The information of user's needs is sent to reduce a technology of information overload.Information advancing technique by active push information to user,
User can be reduced the time spent in searching on network.It searches for according to the interest of user, filters information, and by its active
It is pushed to user, user is helped expeditiously to excavate valuable information.
Existing information push mode usually analyzes individual subscriber at one using upper behavioral data, and root
According to analysis result to user's pushed information.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for pushed information.
In a first aspect, some embodiments of the present application provide a kind of method for pushed information, comprising: if receiving
First pushed information obtains recommended models from the distributed account book based on block chain, wherein the distributed account based on block chain
This is for storing recommended models, and recommended models are for recommending push user；First pushed information is input to recommended models, and root
The corresponding first push user of the first pushed information is determined according to recommended models；First pushed information is pushed to the first push to use
Family.
In some embodiments, if receiving the behavioral data of the second push user, from the distributed account based on block chain
Recommended models are obtained in this；The behavioral data of second push user is input to recommended models, and determines the according to recommended models
Corresponding second pushed information of two push users, wherein recommended models are also used to recommend pushed information；Second pushed information is pushed away
Give the second push user.
In some embodiments, before the first pushed information is input to recommended models, further includes: obtain training sample
This, wherein training sample includes that sample pushed information, the behavioral data of sample push user and sample push user push away sample
The interested probability of breath of delivering letters；Using the behavioral data of sample pushed information and sample push user as input, sample is pushed
For user to the interested probability of sample pushed information as exporting, training obtains recommended models.
In some embodiments, this method further include: if receiving the generation of second the second pushed information of push user response
The second behavioral data, be updated using the recommended models of the second pushed information and the second behavioral data pair；It will be updated
Recommended models are stored into the distributed account book based on block chain.
In some embodiments, this method further include: if receiving the generation of first the first pushed information of push user response
The first behavioral data, recommended models are updated using the first pushed information and the first behavioral data；It is pushed away updated
Model storage is recommended into the distributed account book based on block chain.
In some embodiments, this method further include: the first pushed information is input to updated recommended models, is determined
The corresponding updated first push user of first pushed information；First pushed information is pushed to updated first push to use
Family.
In some embodiments, this method further include: if receiving the first pushed information, determine the pass of the first pushed information
Key information and upload information；The key message of first pushed information and upload information storage are arrived into the distributed account based on block chain
In this, wherein the distributed account book based on block chain is also used to store the key message and upload information of pushed information.
In some embodiments, this method further include: it is for statistical analysis to the first behavioral data, determine that the first push is believed
At least one in the classification information of the user of the first pushed information of the click volume of breath, the clicking rate of the first pushed information and click
?.
In some embodiments, this method further include: by the key message of the first pushed information and point based on block chain
The key message of the pushed information stored in cloth account book is matched, and determines to believe with the associated push of the first pushed information
Breath；The resource information of the clicking rate of click volume, the first pushed information based on the first pushed information and the first pushed information be with
At least one lower user distributes resource: uploading the user of the first pushed information, uploads and believe with the associated push of the first pushed information
The user of breath and the user for clicking the first pushed information.
Second aspect, some embodiments of the present application provide a kind of device for pushed information, comprising: obtain single
Member obtains recommended models from the distributed account book based on block chain if being configured to receive the first pushed information, wherein
Distributed account book based on block chain is for storing recommended models, and recommended models are for recommending push user；Determination unit is matched
It is set to and the first pushed information is input to recommended models, and determine corresponding first push of the first pushed information according to recommended models
User；Push unit is configured to for the first pushed information to be pushed to the first push user.
The third aspect, some embodiments of the present application provide a kind of computer equipment, which includes: one
Or multiple processors；Storage device stores one or more programs thereon；When one or more programs are handled by one or more
Device executes, so that one or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, some embodiments of the present application provide a kind of computer-readable medium, are stored thereon with computer
Program realizes the method as described in implementation any in first aspect when the computer program is executed by processor.
The method and apparatus provided by the above embodiment for pushed information of the application, if receiving the first push letter
Breath, obtains recommended models from the distributed account book based on block chain.Then, the first pushed information is input to recommended models,
To determine the corresponding first push user of the first pushed information.Finally, the first pushed information is pushed to the first push user.Phase
Than the information recommendation mode analyzed in the existing behavioral data based on user on single application, the application is utilized and is based on
The recommended models stored in the distributed account book of block chain are that pushed information recommends push user, due to the distribution based on block chain
The information content of formula account book storage is larger, improves the precision of information push.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that some embodiments of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the application；
Fig. 3 is the flow chart according to another embodiment of the method for pushed information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for pushed information of the application；
Fig. 5 is the flow chart according to the further embodiment of the method for pushed information of the application；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the computer equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the exemplary system architecture 100 of the method for pushed information of the application.
As shown in Figure 1, system architecture 100 may include equipment 101,102,103 and network 104.Network 104 is to set
The medium of communication link is provided between standby 101,102,103.Network 104 may include various connection types, such as wired, wireless
Communication link or fiber optic cables etc..
Equipment 101,102,103 can be support network connection to provide the hardware device or soft of various network services
Part.When equipment is hardware, can be various electronic equipments, including but not limited to smart phone, tablet computer, it is on knee just
Take computer, desktop computer and server etc..At this moment, as hardware device, multiple equipment composition may be implemented into
Distributed apparatus group, also may be implemented into individual equipment.When equipment is software, above-mentioned cited equipment may be mounted at
In.At this moment, it as software, may be implemented into for example for providing the multiple softwares or software module of Distributed Services, it can also
To be implemented as single software or software module.It is not specifically limited herein.
In practice, equipment can provide corresponding network by installing corresponding client application or server-side application
Service.Equipment can be presented as client after being mounted with client application in network communications.Correspondingly, it is installing
After server-side application, it can be presented as server-side in network communications.
As an example, equipment 101,102 is presented as client, and equipment 103 is presented as server-side in Fig. 1.Specifically
Ground, equipment 101,102 can be the client for being equipped with the application of information browse class, and equipment 103 can be information browse class application
Background server.The background server of information browse class application can be in the client (example for receiving the application of information browse class
Such as equipment 101) send the first pushed information in the case where, obtain recommended models from the distributed account book based on block chain；
First pushed information is input to recommended models, and determines that corresponding first push of the first pushed information is used according to recommended models
Family；First pushed information is pushed to the client (such as equipment 102) of the first push user.
It should be noted that the method provided by the embodiment of the present application for pushed information can be executed by equipment 103.
It should be understood that the number of network and equipment in Fig. 1 is only schematical.According to needs are realized, can have
Any number of network and equipment.
With continued reference to Fig. 2, it illustrates the processes according to one embodiment of the method for pushed information of the application
200.This for pushed information method the following steps are included:
Step 201, if receiving the first pushed information, recommended models are obtained from the distributed account book based on block chain.
In the present embodiment, user can be to executing subject (such as the equipment shown in FIG. 1 of the method for pushed information
103) the first pushed information is uploaded.If receiving the first pushed information, above-mentioned executing subject can be from the distribution based on block chain
Push model is obtained in formula account book.In general, the push model obtained from the distributed account book based on block chain is newest storage
Recommended models.Wherein, the recommended models of newest storage are deposited in the last one block in the distributed account book based on block chain
The recommended models of storage.
Here, the distributed account book based on block chain can be used for storing recommended models.Specifically, above-mentioned executing subject can
To create the block for storing recommended models in the distributed account book based on block chain, and block is written into recommended models
In.It, can be after the block for storing the recommended models if the parameter of recommended models is adjusted and generates new recommended models
Face creates a new block, and new recommended models are stored into new block.If the parameter of recommended models constantly by
It adjusts and constantly generates new recommended models, then can constantly create new area in the distributed account book based on block chain
Block, to store the new recommended models being continuously generated.Wherein, block chain is Distributed Storage, point-to-point transmission, common recognition machine
The new application mode of the computer technologies such as system, Encryption Algorithm.Block chain is a kind of database of decentralization, it includes one
The referred to as list of block has the record of sustainable growth and marshalling.Each block includes a timestamp and one
A linking with previous block, allowing for being recorded in the data in block in this way can not distort.Also, block chain includes multiple sections
Point, when new data is written in a node in block chain, the new data that the node can be written by common recognition mechanism is synchronous
Into other nodes of block chain, so that the data in the block chain that all nodes save are with uniformity.
Here, recommended models can be used for recommending to push user, the corresponding pass between characterization pushed information and push user
System.In some embodiments, the training sample for training recommended models may include that sample pushed information and sample push are used
The behavioral data at family.Wherein, sample pushed information can be in preset time period (such as in first trimester) and be pushed to user's
Pushed information.Sample push user can be the user that sample pushed information is received in preset time period.Sample pushes user
Behavioral data can be behavior caused by the sample pushed information that receives in sample push user response preset time period
Data.In general, can recorde corresponding behavioral data when user operates pushed information.Wherein, behavioral data can be with
Including but not limited at least one of following: mark, the pushed information of pushed information show time point on the terminal device, push
Information no longer shows time point on the terminal device, the browsing duration of pushed information etc..For example, when user opens push letter
When breath, pushed information can be shown on the terminal device of user, shown on the terminal device at this point it is possible to record pushed information
Time point.In another example pushed information is no longer shown on the terminal device of user when user closes pushed information, at this point it is possible to
Record pushed information no longer shows time point on the terminal device.At the same time it can also no longer be shown at end using pushed information
Time point in end equipment subtracts the time point of pushed information displaying on the terminal device, records the browsing duration of pushed information.
In some embodiments, recommended models can be using various machine learning methods and training sample to existing machine
Device learning model (such as various neural networks) carries out obtained from Training.In general, the input of training sample can wrap
Include the behavioral data of sample pushed information and sample push user.The output of training sample can be those skilled in the art to sample
The behavioral data of this push user is analyzed, so that it is determined that the sample push user gone out is interested to sample pushed information general
Rate.At this moment, recommended models can be trained as follows and be obtained:
Firstly, obtaining a large amount of training samples.
Wherein, each training sample may include that sample pushed information, the behavioral data of sample push user and sample push away
Send user to the interested probability of sample pushed information.Here, the behavioral data of sample push user, which can be, utilizes block chain
Intelligent protocol function access each different behavior numbers using acquired sample push user in each different application
According to.
Then, for each training sample in a large amount of training samples, by the training sample sample pushed information and
Sample pushes the behavioral data of user as input, and it is emerging to sample pushed information sense that the sample in the training sample is pushed user
The probability of interest is trained initial machine learning model as output, until training can be used in recommending push user's
Recommended models.
Here, the engineering that initial machine learning model can be unbred machine learning model or training is not completed
Model is practised, initial parameter (such as different small random numbers) can be set in initial machine learning model, and parameter is in recommended models
Training process in can be continuously adjusted.Until training the recommended models position that can be used in recommending push user.Example
Such as, BP (Back Propagation, backpropagation) algorithm or SGD (Stochastic Gradient can be used
Descent, stochastic gradient descent) algorithm adjusts the parameters of recommended models.
In some embodiments, recommended models can be those skilled in the art to great amount of samples pushed information and a large amount of samples
The behavioral data of this push user is for statistical analysis, and obtain be stored with multiple sample pushed informations and corresponding sample pushes away
Send the mapping table of the information of user.Specifically, for each sample pushed information, those skilled in the art can be to a large amount of
The behavioral data of sample push user is analyzed, so that it is determined that great amount of samples push user is emerging to the sample pushed information sense out
The probability of interest.Then the sample that the sample pushed information and interested probability are greater than predetermined probabilities threshold value (such as 0.7) is pushed away
The information of user is sent to be stored in mapping table, to generate recommended models.
In some embodiments, if receiving the first pushed information, above-mentioned executing subject can also determine that the first push is believed
The key message and upload information of breath, and by the key message of the first pushed information and upload information storage to based on block chain
In distributed account book.Here, the distributed account book based on block chain can be also used for the storage key message of pushed information and upper
Communication breath.Specifically, above-mentioned executing subject can create in the distributed account book based on block chain for storing pushed information
Key message and upload information block, and will store up pushed information key message and upload information write-in block in.Wherein,
The key message of first pushed information can characterize the main contents of the first pushed information, the usually mark to the first pushed information
Topic, summary info or detailed content are analyzed and are generated.The upload information of first pushed information may include but unlimited
In the mark (such as account) of user of the first pushed information of upload, the uplink time of the first pushed information, the first pushed information
Storage address etc..
Step 202, the first pushed information is input to recommended models, and determines the first pushed information pair according to recommended models
The the first push user answered.
In the present embodiment, the first pushed information can be input to recommended models by above-mentioned executing subject, so that it is determined that the
The corresponding first push user of one pushed information.
In some embodiments, if recommended models are using various machine learning methods and training sample to existing machine
Learning model carries out obtained from Training.At this point, the first pushed information can be input to recommendation by above-mentioned executing subject
Model, so that each sample exported in great amount of samples push user pushes user to the interested probability of the first pushed information.
At this point, above-mentioned executing subject can push each sample push user in user to the first pushed information sense according to great amount of samples
The probability of interest determines the first push user from great amount of samples push user.For example, interested probability is greater than default
The sample push user of probability threshold value is determined as the first push user.
In some embodiments, if recommended models are to be stored with multiple sample pushed informations and corresponding sample push user
Information mapping table.At this point, above-mentioned executing subject can calculate in the first pushed information and multiple sample pushed informations
Each sample pushed information between similarity, and based on similarity calculation as a result, from the mapping table determine first
Push user.For example, using the corresponding sample push user of the highest sample pushed information of similarity as the first push user.Again
For example, the corresponding sample push user of the sample pushed information that similarity is greater than similarity threshold (such as 70%) is as first
Push user.
Step 203, the first pushed information is pushed to the first push user.
In the present embodiment, the first pushed information can be pushed to the first push user by above-mentioned executing subject.
In some embodiments, after the first pushed information is pushed to the first push user, the first push user can
To be operated to the first pushed information.At this point, corresponding first behavioral data can be generated.First behavioral data can be sent
To above-mentioned executing subject, above-mentioned executing subject can be for statistical analysis to the first behavioral data, so that it is determined that the first push letter
At least one in the classification information of the user of the first pushed information of the click volume of breath, the clicking rate of the first pushed information and click
, it is checked for uploading the user of the first pushed information.Here, above-mentioned executing subject can count the first push user and click the
Click volume of the quantity of first behavioral data generated as the first pushed information when one pushed information.Above-mentioned executing subject is also
The ratio of the click volume and the quantity of the first push user of the first pushed information, the click as the first pushed information can be calculated
Rate.Above-mentioned executing subject can also to click the first pushed information user information it is for statistical analysis, so that it is determined that point out
Hit the classification information of the user of the first pushed information.It, can also be by here it is possible to divided according to classification of the age to user
It is divided according to classification of the gender to user, the present embodiment is to this without limiting.
In some embodiments, the key message of pushed information and upper is also stored in the distributed account book based on block chain
In the case that communication ceases, above-mentioned executing subject can also be by the key message of the first pushed information and the distribution based on block chain
The key message of the pushed information stored in account book is matched, and is determined and the associated pushed information of the first pushed information.Its
In, if the key message of the pushed information stored in the distributed account book based on block chain includes the pass of the first pushed information
Key information, it may be considered that the pushed information is associated with the first pushed information.Subsequently, based on the first pushed information click volume,
The resource information of the clicking rate of first pushed information and the first pushed information is that at least one following user distributes resource: uploading the
The user of one pushed information, the use for uploading with the user of the associated pushed information of the first pushed information and clicking the first pushed information
Family.Corresponding resource, above-mentioned executing subject can be brought for the first pushed information by clicking the first pushed information generally, due to user
It can be the user for uploading the first pushed information according to preset ratio, upload and the associated pushed information of the first pushed information
User and the user for clicking the first pushed information distribute resource.Wherein, resource can be the virtual objects by the Internet assigned,
For example, resource can include but is not limited to red packet, discount coupon, be of use certificate etc..Preset ratio can by above-mentioned executing subject and
The user for uploading the first pushed information adjusts jointly.It should be noted that if with the associated pushed information of the first pushed information
Uplink time is and at least partly identical as the content of the first pushed information earlier than the first pushed information, just can be to upload and the
The user of the associated pushed information of one pushed information distributes resource.
The method provided by the above embodiment for pushed information of the application, if receiving the first pushed information, from base
Recommended models are obtained in the distributed account book of block chain.Then, the first pushed information is input to recommended models, to determine the
The corresponding first push user of one pushed information.Finally, the first pushed information is pushed to the first push user.Compared to existing
The information recommendation mode analyzed based on behavioral data of the user on single application, the application utilize based on block chain
The recommended models stored in distributed account book are that pushed information recommends push user, since the distributed account book based on block chain is deposited
The information content of storage is larger, improves the precision of information push.
With further reference to Fig. 3, it illustrates according to another embodiment of the method for pushed information of the application
Process 300.This for pushed information method the following steps are included:
Step 301, if receiving the first pushed information, recommended models are obtained from the distributed account book based on block chain.
Step 302, the first pushed information is input to recommended models, and determines the first pushed information pair according to recommended models
The the first push user answered.
Step 303, the first pushed information is pushed to the first push user.
In the present embodiment, the behaviour of the concrete operations of step 301-303 and step 201-203 in embodiment shown in Fig. 2
Make essentially identical, details are not described herein.
Step 304, if receiving the first behavioral data of first the first pushed information of push user response generation, the is utilized
One pushed information and the first behavioral data are updated recommended models.
In the present embodiment, after the first pushed information is pushed to the first push user, the first push user can be with
First pushed information is operated.At this point, corresponding first behavioral data can be generated.First behavioral data can be sent to use
In the executing subject (such as equipment 103 shown in FIG. 1) of the method for pushed information, above-mentioned executing subject can use the first push
Information and the first behavioral data are updated recommended models.Specifically, those skilled in the art can be to the first behavioral data
It is analyzed, so that it is determined that the first push user is to the interested probability of the first pushed information out.At this point, above-mentioned executing subject can
As input, it is interested to the first pushed information general to be pushed user for first for the first pushed information and the first behavioral data
Rate is updated recommended models as output, to adjust the parameter of recommended models, to obtain updated recommended models.
Step 305, by the storage of updated recommended models into the distributed account book based on block chain.
In the present embodiment, above-mentioned executing subject can create a new area behind the block of storage recommended models
Block, and by the storage of updated recommended models into new block.At this point, updated recommended models just become newest storage
Recommended models.
Step 306, the first pushed information is input to updated recommended models, determines that the first pushed information is corresponding more
The first push user after new.
In the present embodiment, the first pushed information can be input to updated recommended models by above-mentioned executing subject, from
And determine the corresponding updated first push user of the first pushed information.In general, what updated recommended models were determined
Updated first push user is different from the first push user.
Step 307, the first pushed information is pushed to updated first push user.
In the present embodiment, the first pushed information can be pushed to updated first push and used by above-mentioned executing subject
Family.
In some embodiments, after the first pushed information to be pushed to updated first push user, after update
First push user the first pushed information can be operated, to generate corresponding first behavioral data.At this point, above-mentioned
Executing subject can also continue to update using this first behavioral data generated to updated recommended models, and continue
Recommend more first push users, to continue to push the first pushed information.It loops back and forth like this, the first pushed information
It is pushed to more to its interested user.
From figure 3, it can be seen that the method for pushed information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 300 increase step 304-307.The scheme of the present embodiment description can push user response first first as a result,
Continue to be updated recommended models when the first behavioral data that pushed information generates, to recommend out more to believe the first push
Interested first push user is ceased, in order to which the first pushed information to be pushed to more to its interested user.Especially,
For new pushed information, realize can be pushed in a short period of time it is more to its interested user,
Substantially reduce the duration of the Cold Start of new pushed information.
With continued reference to Fig. 4, it illustrates the streams according to another embodiment of the method for pushed information of the application
Journey 400.This for pushed information method the following steps are included:
Step 401, it if receiving the behavioral data of the second push user, is obtained from the distributed account book based on block chain
Recommended models.
In the present embodiment, user can be to executing subject (such as the equipment shown in FIG. 1 of the method for pushed information
103) behavioral data of the second push user is uploaded.If receiving the behavioral data of the second push user, above-mentioned executing subject can
To obtain recommended models from the distributed account book based on block chain.In general, being obtained from the distributed account book based on block chain
Push model be newest storage recommended models.Wherein, the recommended models of newest storage are the distributed accounts based on block chain
The recommended models stored in the last one block in this.It should be noted that behavioral data, block chain and recommended models are being joined
According to being described in detail in embodiment illustrated in fig. 2, details are not described herein.
Step 402, the behavioral data of the second push user is input to recommended models, and determines second according to recommended models
Push corresponding second pushed information of user.
In the present embodiment, the behavioral data of the second push user can be input to recommended models by above-mentioned executing subject,
So that it is determined that corresponding second pushed information of the second push user.Here, recommended models can be also used for recommending pushed information.
In some embodiments, if recommended models are using various machine learning methods and training sample to existing machine
Learning model carries out obtained from Training.At this point, above-mentioned executing subject can be by the behavioral data of the second push user
Recommended models are input to, so that the second push user of output is emerging to each sample pushed information sense in great amount of samples pushed information
The probability of interest.At this point, above-mentioned executing subject can be according to the second push user to each sample in great amount of samples pushed information
The interested probability of pushed information determines the second pushed information from great amount of samples pushed information.For example, by interested general
The sample pushed information that rate is greater than predetermined probabilities threshold value is determined as the second pushed information.
In some embodiments, if recommended models are to be stored with multiple sample pushed informations and corresponding sample push user
Information mapping table.At this point, above-mentioned executing subject can inquire sample identical with the second push information of user
The corresponding sample pushed information of information of user is pushed, and as the second pushed information.
Step 403, the second pushed information is pushed to the second push user.
In the present embodiment, the second pushed information can be pushed to the second push user by above-mentioned executing subject.Some
In embodiment, the case where the distributed account book based on block chain is also stored with the key message and upload information of pushed information
Under, above-mentioned executing subject can determine the key message of the second pushed information, and with deposited in the distributed account book based on block chain
The key message of the pushed information of storage is matched, if it exists the pass of the key message of pushed information and the second pushed information
Key information is identical, obtains the upload information of the key message of the pushed information, and download from the storage address in upload information
The pushed information, as the second pushed information.
The method provided by the above embodiment for pushed information of the application, if receiving the behavior of the second push user
Data obtain recommended models from the distributed account book based on block chain.Then, the behavioral data of the second push user is inputted
To recommended models, to determine corresponding second pushed information of the second push user.Finally, the second pushed information is pushed to second
Push user.Compared to the information recommendation mode that the existing behavioral data based on user on single application is analyzed, originally
Application recommends pushed information using the recommended models stored in the distributed account book based on block chain for push user, due to being based on
The information content of the distributed account book storage of block chain is larger, improves the precision of information push.
With further reference to Fig. 5, it illustrates according to the further embodiment of the method for pushed information of the application
Process 500.This for pushed information method the following steps are included:
Step 501, it if receiving the behavioral data of the second push user, is obtained from the distributed account book based on block chain
Recommended models.
Step 502, the behavioral data of the second push user is input to recommended models, and determines second according to recommended models
Push corresponding second pushed information of user.
Step 503, the second pushed information is pushed to the second push user.
In the present embodiment, the behaviour of the concrete operations of step 501-503 and step 401-403 in embodiment shown in Fig. 2
Make essentially identical, details are not described herein.
Step 504, if receiving the second behavioral data of second the second pushed information of push user response generation, the is utilized
Two pushed informations and the second behavioral data are updated recommended models.
In the present embodiment, after the second pushed information is pushed to the second push user, the second push user can be with
Second pushed information is operated.At this point, corresponding second behavioral data can be generated.Second behavioral data can be sent to use
In the executing subject (such as equipment 103 shown in FIG. 1) of the method for pushed information, above-mentioned executing subject can use the second push
Information and the second behavioral data are updated recommended models.Specifically, those skilled in the art can be to the second behavioral data
It is analyzed, so that it is determined that the second push user is to the interested probability of the second pushed information out.At this point, above-mentioned executing subject can
As input, it is interested to the second pushed information general to be pushed user for second for the second pushed information and the second behavioral data
Rate is updated recommended models as output, to adjust the parameter of recommended models, to obtain updated recommended models.
Step 505, by the storage of updated recommended models into the distributed account book based on block chain.
In the present embodiment, above-mentioned executing subject can create a new area behind the block of storage recommended models
Block, and by the storage of updated recommended models into new block.At this point, updated recommended models just become newest storage
Recommended models.
From figure 5 it can be seen that the method for pushed information compared with the corresponding embodiment of Fig. 4, in the present embodiment
Process 500 increase step 504-505.The scheme of the present embodiment description can push user response second second as a result,
Continue to be updated recommended models when the second behavioral data that pushed information generates, so that updated recommended models can push away
Recommend out more accurate pushed information or push user.
Below with reference to Fig. 6, it illustrates the computer equipments for being suitable for being used to realize the embodiment of the present application (such as shown in Fig. 1
Equipment 103) computer system 600 structural schematic diagram.Computer equipment shown in Fig. 6 is only an example, is not answered
Any restrictions are brought to the function and use scope of the embodiment of the present application.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable medium either the two any combination.Computer-readable medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable medium can include but is not limited to: electrical connection, portable meter with one or more conducting wires
Calculation machine disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable medium, which can be, any includes or storage program has
Shape medium, the program can be commanded execution system, device or device use or in connection.And in the application
In, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, wherein
Carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to electric
Magnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable Jie
Any computer-readable medium other than matter, the computer-readable medium can be sent, propagated or transmitted for being held by instruction
Row system, device or device use or program in connection.The program code for including on computer-readable medium
It can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any conjunction
Suitable combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object-oriented programming language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include acquiring unit, determination unit and push unit.Wherein, the title of these units is not constituted under certain conditions to the unit
The restriction of itself, for example, acquiring unit is also described as " if receiving the first pushed information, from point based on block chain
The unit of recommended models is obtained in cloth account book ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in computer equipment described in above-described embodiment；It is also possible to individualism, and is set without the computer is incorporated
In standby.Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the calculating
When machine equipment executes, so that the computer equipment: if receiving the first pushed information, from the distributed account book based on block chain
Obtain recommended models, wherein the distributed account book based on block chain is for storing recommended models, and recommended models are for recommending push
User；First pushed information is input to recommended models, determines the corresponding first push user of the first pushed information；First is pushed away
Breath of delivering letters is pushed to the first push user.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (11)
1. a kind of method for pushed information characterized by comprising
If receiving the first pushed information, recommended models are obtained from the distributed account book based on block chain, wherein described to be based on
The distributed account book of block chain is for storing the recommended models, and the recommended models are for recommending push user；
First pushed information is input to the recommended models, and determines that first push is believed according to the recommended models
Cease corresponding first push user；
First pushed information is pushed to the first push user.
2. the method according to claim 1, wherein the method also includes:
If receiving the behavioral data of the second push user, the recommendation is obtained from the distributed account book based on block chain
Model；
The behavioral data of the second push user is input to the recommended models, and according to recommended models determination
Corresponding second pushed information of second push user, wherein the recommended models are also used to recommend pushed information；
Second pushed information is pushed to the second push user.
3. according to the method described in claim 2, it is characterized in that, first pushed information is input to described push away described
Before recommending model, further includes:
Obtain training sample, wherein the training sample includes sample pushed information, the behavioral data of sample push user and institute
Sample push user is stated to the interested probability of sample pushed information；
Using the behavioral data of the sample pushed information and sample push user as input, the sample is pushed into user
To the interested probability of the sample pushed information as exporting, training obtains the recommended models.
4. according to the method described in claim 3, it is characterized in that, the method also includes:
If receiving the second behavioral data that the second pushed information described in the second push user response generates, described the is utilized
Two pushed informations and second behavioral data are updated the recommended models；
By the storage of updated recommended models into the distributed account book based on block chain.
5. method according to claim 1 to 4, which is characterized in that the method also includes:
If receiving the first behavioral data that the first pushed information described in the first push user response generates, described the is utilized
One pushed information and first behavioral data are updated the recommended models；
By the storage of updated recommended models into the distributed account book based on block chain.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
First pushed information is input to the updated recommended models, determines that first pushed information is corresponding more
The first push user after new；
First pushed information is pushed to updated first push user.
7. the method according to any one of claim 4 to 6, which is characterized in that the method also includes:
If receiving the first pushed information, the key message and upload information of first pushed information are determined；
By the key message of first pushed information and upload information storage into the distributed account book based on block chain,
Wherein, the distributed account book based on block chain is also used to store the key message and upload information of pushed information.
8. the method according to the description of claim 7 is characterized in that the method also includes:
It is for statistical analysis to first behavioral data, determine that the click volume of first pushed information, described first push
At least one of in the classification information of the user of the clicking rate and click first pushed information of information.
9. according to the method described in claim 8, it is characterized in that, the method also includes:
The pushed information that will be stored in the key message of first pushed information and the distributed account book based on block chain
Key message matched, determine and the associated pushed information of the first pushed information；
The clicking rate of click volume, first pushed information based on first pushed information and first pushed information
Resource information is that at least one following user distributes resource: uploading the user of first pushed information, uploads and described first
The user of the associated pushed information of pushed information and the user for clicking first pushed information.
10. a kind of computer equipment, comprising:
One or more processors；
Storage device stores one or more programs thereon；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-9.
11. a kind of computer readable storage medium, is stored thereon with computer program, the computer program is executed by processor
Method of the Shi Shixian as described in any in claim 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811207503.0A CN109408716B (en) | 2018-10-17 | 2018-10-17 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811207503.0A CN109408716B (en) | 2018-10-17 | 2018-10-17 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109408716A true CN109408716A (en) | 2019-03-01 |
| CN109408716B CN109408716B (en) | 2020-12-29 |
Family
ID=65468235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811207503.0A Active CN109408716B (en) | 2018-10-17 | 2018-10-17 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109408716B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931050A (en) * | 2020-08-02 | 2020-11-13 | 吕维东 | Information push method based on intelligent identification and big data and block chain financial platform |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915354A (en) * | 2014-03-12 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Multimedia file pushing method and device |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| US20180165585A1 (en) * | 2016-12-09 | 2018-06-14 | Cognitive Scale, Inc. | Method for Providing Procurement Related Cognitive Insights Using Blockchains |
| CN108491266A (en) * | 2018-03-09 | 2018-09-04 | 联想(北京)有限公司 | Data processing method, device based on block chain and electronic equipment |
| US20180285764A1 (en) * | 2017-03-29 | 2018-10-04 | Futurewei Technologies, Inc. | Knowledge network platform |
| CN108959642A (en) * | 2018-07-27 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | Method and apparatus for information to be written |
-
2018
- 2018-10-17 CN CN201811207503.0A patent/CN109408716B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915354A (en) * | 2014-03-12 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Multimedia file pushing method and device |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| US20180165585A1 (en) * | 2016-12-09 | 2018-06-14 | Cognitive Scale, Inc. | Method for Providing Procurement Related Cognitive Insights Using Blockchains |
| US20180285764A1 (en) * | 2017-03-29 | 2018-10-04 | Futurewei Technologies, Inc. | Knowledge network platform |
| CN108491266A (en) * | 2018-03-09 | 2018-09-04 | 联想(北京)有限公司 | Data processing method, device based on block chain and electronic equipment |
| CN108959642A (en) * | 2018-07-27 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | Method and apparatus for information to be written |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931050A (en) * | 2020-08-02 | 2020-11-13 | 吕维东 | Information push method based on intelligent identification and big data and block chain financial platform |
| CN111931050B (en) * | 2020-08-02 | 2021-06-25 | 优观融资租赁(中国)有限公司 | Information push method based on intelligent identification and big data and block chain financial server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109408716B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| CN108805594A (en) | Information-pushing method and device | |
| CN108491267A (en) | Method and apparatus for generating information | |
| CN109189938A (en) | Method and apparatus for updating knowledge mapping | |
| CN108989882A (en) | Method and apparatus for exporting the snatch of music in video | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN109981787B (en) | Method and device for displaying information | |
| CN109976997A (en) | Test method and device | |
| CN108520470A (en) | Method and apparatus for generating customer attribute information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN109862100B (en) | Method and device for pushing information | |
| CN109271556A (en) | Method and apparatus for output information | |
| CN109815365A (en) | Method and apparatus for handling video | |
| CN110020162A (en) | User identification method and device | |
| CN109495552A (en) | Method and apparatus for updating clicking rate prediction model | |
| CN108182472A (en) | For generating the method and apparatus of information | |
| CN108776692A (en) | Method and apparatus for handling information | |
| CN109859006A (en) | For determining method, system, electronic equipment and the computer-readable medium of user interest profile | |
| CN109582825A (en) | Method and apparatus for generating information | |
| CN110019263A (en) | Information storage means and device | |
| CN108629011A (en) | Method and apparatus for sending feedback information | |
| CN108959642A (en) | Method and apparatus for information to be written | |
| CN108737486A (en) | Information-pushing method and device | |
| CN108600329A (en) | For pushed information, the method and apparatus for showing information | |
| CN108549586A (en) | Information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200703 Address after: Room 909, No. 12, Huangshan Road, Jianye District, Nanjing City, Jiangsu Province Applicant after: Nanjing Shangwang Network Technology Co.,Ltd. Address before: 312599 B-2, 3 floor, Jiayi Plaza, 127 East Renmin Road, Nanming street, Xinchang, Shaoxing, Zhejiang Applicant before: LIANSHANG (XINCHANG) NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |