CN110247974A - Information-pushing method, device, computer and storage medium based on block chain - Google Patents
Information-pushing method, device, computer and storage medium based on block chain Download PDFInfo
- Publication number
- CN110247974A CN110247974A CN201910526939.4A CN201910526939A CN110247974A CN 110247974 A CN110247974 A CN 110247974A CN 201910526939 A CN201910526939 A CN 201910526939A CN 110247974 A CN110247974 A CN 110247974A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- pushed
- block chain
- block
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of information-pushing method based on block chain, device, computer equipment and storage mediums.Method includes: each block for obtaining block chain；The block chain is parsed, the multidimensional characteristic of the user recorded in each block on the block chain and the prediction probability of multiple information to be pushed corresponding with the multidimensional characteristic of the user are obtained；The information to be pushed is pushed to user according to the prediction probability.The operation information of user and the distributed storage of pushed information probability are realized by block chain, and the multidimensional characteristic of user and the probability of information to be pushed away are extracted accordingly, the calculating that cost source is compared in user preference feature extraction etc. is directly carried out in user terminal, and realize that distributed tracking stores, realize the decentralization of the calculating of Characteristic Contrast, the pressure of server end is greatly reduced, realization accurately pushes and excavate user demand, so that information push is more accurate and timely.
Description
Technical field
This application involves the information advancing technique fields based on block chain, more particularly to a kind of information based on block chain
Method for pushing, device, computer equipment and storage medium.
Background technique
With the high speed development of the development of the high speed of internet, especially mobile Internet, the various of mobile Internet are answered
With the free life of extreme enrichment people.People can do shopping, entertain and consume with staying indoors.
For the usual consumption habit of user, the main of the push of various applications is had become for user's push consumption information
Method, however when liking carrying out PUSH message, rely primarily on server end for user at present and the feature of user is solved
It analyses, and carries out the push of message with this, server end is caused to need to consume more computing resource and storage resource, so that service
Device pressure is larger, influences the computational efficiency and computational accuracy of server, cause that information pushes not in time and inaccurately.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind being capable of information-pushing method, dress based on block chain
It sets, computer equipment and storage medium.
A kind of information-pushing method based on block chain, which comprises
Obtain each block of block chain；
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic of user；
The information to be pushed is pushed to user according to the prediction probability.
In one of the embodiments, before the step of each block for obtaining block chain further include:
Obtain operation information；
Operation information described in each node broadcasts to the block chain.
In one of the embodiments, after the step of operation information described in each node broadcasts to the block chain
Further include:
Block is generated according to the operation information；
The block chain is updated according to the block.
The step of acquisition operation information includes: in one of the embodiments,
The operation information is obtained, operation information importing user model is learnt, the multidimensional for obtaining user is special
Sign；
The step of operation information described in each node broadcasts to the block chain includes:
To the multidimensional characteristic of each node broadcasts user of the block chain.
In one of the embodiments, before the step of each block for obtaining block chain further include:
Obtain information to be pushed；
The information to be pushed is parsed, the feature of the information to be pushed is obtained；
By the multidimensional characteristic of the feature of the information to be pushed and user, it is input to the deep neural network model constructed
In predicted, obtain the prediction probability of each information to be pushed；
To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
The prediction of each information to be pushed of each node broadcasts to the block chain in one of the embodiments,
After the step of probability further include:
Block is generated according to the prediction probability of each information to be pushed；
The block chain is updated according to the block.
The described the step of information to be pushed is pushed to user according to the prediction probability in one of the embodiments,
Include:
Detect whether the prediction probability is greater than preset threshold；
When the prediction probability is greater than or equal to the preset threshold, then according to the prediction probability to described in user's push
Information to be pushed.
A kind of information push-delivery apparatus based on block chain, described device include:
Block chain module is obtained, for obtaining each block of block chain；
Feature and probability obtain module and obtain and record in each block on the block chain for parsing the block chain
User multidimensional characteristic and multiple information to be pushed corresponding with the multidimensional characteristic of the user prediction probability；
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
Computer program, the processor perform the steps of when executing the computer program
Obtain each block of block chain；
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic of user；
The information to be pushed is pushed to user according to the prediction probability.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain each block of block chain；
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic of user；
The information to be pushed is pushed to user according to the prediction probability.
The above-mentioned information-pushing method based on block chain, device, computer equipment and storage medium, are realized by block chain
The operation information of user and the distributed storage of pushed information probability, and the multidimensional characteristic of extraction user and information to be pushed away accordingly
Probability, user preference feature extraction etc. is compared the calculating in cost source and is directly carried out in user terminal, and realizes that distributed tracking is deposited
Storage, realizes the decentralization of the calculating of Characteristic Contrast, greatly reduces the pressure of server end, realizes and accurately pushes and dig
User demand is dug, so that information push is more accurate and timely.
Detailed description of the invention
Fig. 1 is the applied environment figure of the information-pushing method based on block chain in one embodiment；
Fig. 2 is the flow diagram of the information-pushing method based on block chain in one embodiment；
Fig. 3 is the structural block diagram of the information push-delivery apparatus based on block chain in one embodiment；
Fig. 4 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Information-pushing method provided by the present application based on block chain, can be applied in application environment as shown in Figure 1.
Wherein, multiple terminals 102 are connected with each other by network, and are communicated between each other, and each terminal 102 also passes through network and server
104 connection, and with 104 connection communication of server.Each terminal 102 and the connection of server 104 form alliance's chain, each terminal 102
With the node that server 104 is in alliance's chain, each terminal 102 and server 104 can be as nodes into alliance's chain
Other node broadcasts, and each terminal 102 and server 104 can receive the broadcast of other nodes, and can be to reception
The information package arrived is block, and block chain is entered in block chain with more new block chain.Wherein, terminal 102 can be, but not limited to be
Various personal computers, laptop, smart phone, tablet computer and portable wearable device, server 104 can be used
The server cluster of independent server either multiple servers composition is realized.Each block of server acquisition block chain；
The block chain is parsed, obtains the multidimensional characteristic of the user recorded in each block on the block chain and with the user's
The prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic；The letter to be pushed is pushed to user according to the prediction probability
Breath.
In one embodiment, as shown in Fig. 2, providing a kind of information-pushing method based on block chain, in this way
Applied to being illustrated for the terminal in Fig. 1, comprising the following steps:
Step 210, each block of block chain is obtained.
Specifically, which is for recording user's operation information, information to be pushed and relevant to user behavior
The block chain of information, the block chain are successively linked by multiple blocks according to timestamp.Each block of the block chain is by each section
Point, which is packaged, to be generated, and chain enters into block chain.
In the present embodiment, as the terminal or server of node, block chain can be obtained, and get in block chain
Block.
Step 230, the block chain is parsed, the multidimensional characteristic of the user recorded in each block on the block chain is obtained
And the prediction probability of multiple information to be pushed corresponding with the multidimensional characteristic of the user.
In this step, block chain is parsed, the information recorded in each block in block chain can be obtained, the letter of these records
The prediction probability of multidimensional characteristic and multiple information to be pushed corresponding with the multidimensional characteristic of the user in breath comprising user.
Since the multidimensional characteristic of user and the prediction probability of information to be pushed are recorded in the block of block chain, and the block of block chain is
It is generated by each node being distributed in network, and the block of block chain is recorded and updated by each node in network, because
This, enables the multidimensional characteristic of user and the prediction probability of information to be pushed to realize distributed storage, and nothing by block chain
Need server to be stored, can be effectively reduced the occupancy to server resource, further, it is possible to make user multidimensional characteristic and
The prediction probability of information to be pushed can be more reliably recorded, and effectively avoid being tampered, and since each node can
Therefore enough separate storage block chains can effectively improve the reading of the multidimensional characteristic of user and the prediction probability of information to be pushed
Efficiency, to improve acquisition efficiency.
Specifically, the multidimensional characteristic of user is the characteristic information of multiple dimensions of user, and user is from multiple and different dimensions
Reflect the personal information of user or the feature of individual, which includes the feature of user behavior and the individual spy of user
Sign.For example, the multidimensional characteristic includes the age of user, the gender of user, the occupation of user, educational background of user etc., for example, this is more
Dimensional feature include user's payment amount, user browsing type of merchandize, user collection type of merchandize, collection Brand.
The multidimensional characteristic of the user is to constitute user behavior or the principal element of operation to obtain user according to the multidimensional characteristic
Usual consumption habit or consumption propensity.
The information to be pushed can be considered that the page or message to be pushed, the information to be pushed can be considered advertisement information.Value
One be mentioned that, information to be pushed can be one it is either multiple.It is noted that information to be pushed be it is multiple, it is multiple
Information to be pushed can be directed to different user or the same user.Different user behaviors are pushed respectively, improve push
Precision.In the present embodiment, which is multiple, and is directed to a user, which is above-mentioned multidimensional characteristic
Corresponding user, that is to say, that in the present embodiment, the information to be pushed same user corresponding with multidimensional characteristic parses block chain
The multidimensional characteristic and information to be pushed of the user of acquisition belongs to a user, which is the corresponding user of present node.One reality
Applying example is to parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of user of multidimensional characteristic.One embodiment is to parse the block chain, is obtained
The multidimensional characteristic of same user recorded in each block on the block chain and corresponding with multidimensional characteristic multiple wait push away
It delivers letters the prediction probability of breath.
The prediction probability can be considered as the matching degree of information to be pushed and multidimensional characteristic, or be considered as information to be pushed and use
The matching degree of the multidimensional characteristic at family is able to reflect the demand whether information to be pushed meets user by the prediction probability.
Step 250, the information to be pushed is pushed to user according to the prediction probability.
In this step, after obtaining prediction probability, information to be pushed corresponding with the prediction probability is pushed to user.By
In the corresponding prediction probability of each information to be pushed, therefore, can be pushed and the prediction probability pair according to prediction probability to user
The information to be pushed answered, and make the demand for meeting user to PUSH message.
In above-described embodiment, the operation information of user and the distributed storage of pushed information probability are realized by block chain,
And the calculating in cost source is compared in the multidimensional characteristic of extraction user and the probability of information to be pushed away, user preference feature extraction etc. accordingly
It is directly carried out in user terminal, and realizes that distributed tracking stores, realized the decentralization of the calculating of Characteristic Contrast, greatly reduce
The pressure of server end is realized and accurately pushes and excavate user demand, so that information push is more accurate and timely.
One embodiment is, according to the sequence of obtained prediction probability from large to small, pushes the letter to be pushed to user
Breath, that is to say, that preferentially by the larger corresponding information to be pushed of prediction probability to user.In the present embodiment, it is based on user behavior
It pushes to user in the larger corresponding information to be pushed of prediction probability, in such manner, it is possible to make the row of information to be pushed matching user
For, for example, user, in browsing, to user's PUSH message, for another example, user is in collection, to user's PUSH message, so that with
Family can receive PUSH message in browsing or collection, without receiving PUSH message when payment, forwarding, so that
PUSH message more meets the current behavior of user, and meets the identity characteristic of user, avoids impacting the operation of user,
So that the use perception of user is more preferably.
In one of the embodiments, before the step of each block for obtaining block chain further include: obtain operation letter
Breath；Operation information described in each node broadcasts to the block chain.
Specifically, which is the information of the operation of user, which is to record the information of user behavior.With
The operation behavior that family behavior, that is, user is carried out by the application program in terminal or terminal, for example, the operation behavior includes stepping on
Platform is recorded, for example, the operation includes click, sliding, fingerprint authentication, face verification, camera shooting etc..For example, clicking in application program
Icon, button, slide application program in sliding button.The user behavior is used to match the preset rules in application program,
And then obtain the default feedback of application program.For example, the application program is to consume the application in store, which be can be pair
Consume checking, collect, forwarding, paying the bill, buying for the commodity in store.
In the present embodiment, in order to enable each node obtains the operation information of user, as one of terminal of node,
After obtaining the operation of user on the terminal, the corresponding information of the operation, that is, operation information are obtained, by the operation information
It is broadcasted to other each nodes of block chain, so that each node receives the operation information, in this way, each node can be remembered
Operation information is recorded, and a node therein is possibly based on the operation information and generates new block, in this way, making that user's is every
The corresponding operation information of the operation of one step can be recorded, and be recorded in the node of block chain, to realize user
The occupancy to the storage resource of server is effectively reduced in the distributed storage of operation.
In one of the embodiments, after the step of operation information described in each node broadcasts to the block chain
Further include: block is generated according to the operation information；The block chain is updated according to the block.
It, can be based on this node or other node broadcasts for the node in block chain in the present embodiment
Operation information generates block, and updates the block chain according to the block, that is, the block chain is entered in block chain.This
Sample realizes distributed recording and storage to operation information.Also, it, can be effective since operation information is written in block chain
It avoids operation information from being tampered, and effectively avoids the loss of operation information.In addition, being made by the way that block is written in operation information
Operation information can distributed storage avoid multiple terminal concurrences from leading to server it is not necessary that individually server is written
Batch is written, and can effectively improve the storage efficiency of operation information.
It is noted that generating the node of block according to operation information, it can be present node, be also possible to block chain
In receive broadcast operation information other nodes.
It should be understood that for generating block, the block of realization principle and existing block chain according to operation information
Generation it is identical, for example, obtain block chain in newest block block head information, according to the block head information carry out Hash fortune
It calculates, obtains the block head information of current block, by the block body of operation information write-in block, generate block.Each node all will
The operation for generate block, for generating the node of current block earliest, then node success chain enters in block chain.In this way,
Each node all there will be an opportunity to the block chain of each self-generating entering block, be updated to block chain, to realize operation information
Distributed storage.
It is noted that in above-described embodiment, by the block of operation information write-in block chain, when needing pushed information
When, the operation information can be obtained from block chain, and the multidimensional characteristic of parsing acquisition user is carried out to the operation information, one
Embodiment is to obtain each block of block chain；The block chain is parsed, the use recorded in each block on the block chain is obtained
The prediction probability of the operation information at family and multiple information to be pushed corresponding with the user of the operation information, to the operation
Information carries out machine learning, obtains the multidimensional characteristic of user.In this way, can be obtained user multidimensional characteristic and it is corresponding it is multiple to
The prediction probability of pushed information.In a further embodiment, the multidimensional characteristic of the user can pass through engineering before block is written
It practises and obtaining, which is described below.
The step of acquisition operation information includes: to obtain the operation information in one of the embodiments, will be described
Operation information imports user model and is learnt, and obtains the multidimensional characteristic of user；Each node broadcasts to the block chain
The step of operation information includes: the multidimensional characteristic to each node broadcasts user of the block chain.It is described according to the behaviour
Making the step of information generates block, updates the block chain according to the block includes: the multidimensional characteristic generation area according to user
Block；The block chain is updated according to the block.
That is, obtaining the operation information in the present embodiment, the operation information is imported into user model
It practises, obtains the multidimensional characteristic of user；To the multidimensional characteristic of each node broadcasts user of the block chain；It is special according to the multidimensional of user
Sign generates block；The block chain is updated according to the block.
In the present embodiment, in order to obtain the multidimensional characteristic of user, and block is written into multidimensional characteristic, and chain enters block chain
In, operation information is directed into user model first and is learnt, which includes user's history data, that is, will be used
Family historical operating data is directed into user model and is learnt, which is the historical operation behavior number based on a large number of users
According to the model for being trained acquisition, training obtains the user model in advance.By the user model to user's history data
Study, the multidimensional characteristic of user can be obtained.The multidimensional characteristic includes user preference feature and the personal characteristics of user, than
Such as, the multidimensional characteristic include user's payment amount, user browsing type of merchandize, user collection type of merchandize, collection quotient
Product brand.The multidimensional characteristic of the user is that the principal element of composition user behavior can obtain user's according to the multidimensional characteristic
Usual consumption habit or consumption propensity.It realizes, is also possible in terminal side it is noted that the user model can be
It is realized in server side, for example, operation information is learnt by the user model that the terminal of user is sent to server.
In one embodiment, the operation information and user information are obtained, the operation information and user information are led
Access customer model is learnt, and the multidimensional characteristic of user is obtained；To the multidimensional characteristic of each node broadcasts user of the block chain；
Block is generated according to the multidimensional characteristic of user；The block chain is updated according to the block.
In the present embodiment, the multidimensional characteristic of user is also got by user information study, which is of user
People's information or identity information, for example, the age of user, gender, occupation and marital status etc..Learn to obtain by user information
User's multidimensional characteristic, more can adequately obtain the personal characteristics of user so that information push it is more accurate.
In the present embodiment, block is generated due to obtaining the multidimensional characteristic of user, and based on this, in this way, subsequent ought use
When family logs in, server can directly get the multidimensional characteristic of user from the block of block chain, and make server with this
The push for realizing information to be pushed parses without obtaining operation information or learns to obtain multidimensional characteristic, effectively increases
The acquisition efficiency of the multidimensional characteristic of user, improves the pushing efficiency of information to be pushed.
In order to avoid the terminal operation to user impacts, in one embodiment, the login of user is detected, detected
When being logged in user, user is obtained in the upper operation information once logged in, the operation information is imported into user model
It practises, obtains the multidimensional characteristic of user；To the multidimensional characteristic of each node broadcasts user of the block chain；It is special according to the multidimensional of user
Sign generates block；The block chain is updated according to the block.
In the present embodiment, due to operation information import user model study be user log in when progress, that is, by with
Family logs in and triggers, and what is learnt is the operation information for operating and generating when logging in the last time, in such manner, it is possible to which user is avoided to exist
Learnt when subsequent operation, terminal avoided to consume excessive resource due to the study of user model, avoids the Caton of terminal,
So that the experience of user's operation is more preferably.
In order to avoid the terminal operation to user impacts, in one embodiment, whether detection present terminal is in
Standby perhaps breath screen state obtains user in upper primary login when detecting that present terminal is in standby or ceases screen state
Operation information, by the operation information importing user model learn, obtain the multidimensional characteristic of user；To the block chain
Each node broadcasts user multidimensional characteristic；Block is generated according to the multidimensional characteristic of user；The area is updated according to the block
Block chain.
It is to shield Shi Jinhang in terminal standby or breath since operation information imports user model study in the present embodiment, this
Sample effectively can avoid user from learning in operation, and terminal is avoided to consume excessive money due to the study of user model
Source avoids the Caton of terminal, so that the experience of user's operation is more preferably.
In one embodiment, described to learn operation information importing user model, obtain the multidimensional of user
Feature includes: to learn operation information importing user model, obtains at least one multidimensional characteristic of user；It obtains
Incidence relation between multiple multidimensional characteristics；According between multiple multidimensional characteristics incidence relation and at least one
Multidimensional characteristic obtains multiple multidimensional characteristics of user.
Specifically, multidimensional characteristic refers to the feature of multiple dimensions, in the present embodiment, there is association between multidimensional characteristic,
Namely incidence relation.Incidence relation between multidimensional characteristic can be user model and learn to obtain.In the present embodiment, Yong Huhang
To learn in user model, it will a multidimensional characteristic is obtained, and according to the pass of this multidimensional characteristic and other multidimensional characteristics
Connection relationship can obtain the multidimensional characteristic being more associated, in such manner, it is possible to effectively improve being imitated for multiple multidimensional characteristics
Rate and accuracy.
According to other multidimensional characteristics that incidence relation obtains, user interest or consumption habit can be widely adapted to.
It should be understood that the acquisition about incidence relation, can be platform setting, for example, user setting quotient to be pushed
The relevance of product or information, such as articles for babies and baby milk are associated with, and if user buys articles for babies, then buy baby milk
A possibility that powder, is bigger, is also possible to what user model learnt, for example after push, user has purchase, then judges user
There is the demand of this respect；The preferential Securities of commodity for another example, for example may have demand, but user to certain commodity by other features of user
Point has been opened certain commodity and has but never been bought, or never searches for certain commodity, it may be possible to because price is higher than user's desired value,
Commodity coupon can be pushed, in the present embodiment, discount coupon is the multidimensional special medical treatment for having incidence relation with user's search commercial articles
It should；It then may be because commodity price is omited relative to the commodity price that other approach are bought if user has used discount coupon purchase
Height can continue to push the preferential Securities of commodity, or suitably do commercial activities and price adjustment；Additionally it is possible to which some marketing strategies are implanted into
Information characteristics model, then the marketing strategy is the multidimensional characteristic for having incidence relation with the multidimensional characteristic of user behavior.
In the present embodiment, it is based on artificial intelligence technology, the information of user preference is pushed to user, or user is lost interest in
Information by the implantation marketing methods of user demand test model, pushed information associated with user behavior is sent out
It send to user, participation or the consumption for transferring user are warm and sincere, more fully serve target user, more accurately push to user
Information can be used for electric business platform, information platform, or large-scale forum platform etc..
In one of the embodiments, before the step of each block for obtaining block chain further include: obtain wait push
Information；The information to be pushed is parsed, the feature of the information to be pushed is obtained；By the feature of the information to be pushed and user
Multidimensional characteristic, be input in the deep neural network model constructed and predicted, obtain the prediction of each information to be pushed
Probability；To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
In the present embodiment, in order to realize user multidimensional characteristic and information to be pushed comparison, and then obtain both
With degree, information to be pushed is parsed first, obtains the feature of information to be pushed, then by the feature of information to be pushed and use
The multidimensional characteristic at family, which is input in deep neural network model, to be predicted, and then the prediction for obtaining each information to be pushed is general
Rate, and the prediction probability of information to be pushed is corresponding with the multidimensional characteristic of user.
Specifically, the deep neural network model of the building is capable of the multidimensional characteristic of feature and user to information to be pushed
Matching degree predicted, so that the prediction probability of each information to be pushed be calculated.In the present embodiment, building one in advance
Deep neural network (DNN) model, is trained using deep neural network model of a large amount of sample data to building, training
An available trained deep neural network model after the completion.The sample data is user behavior or user
Historical data.The feature of information to be pushed includes that user group's feature, information (commodity) can dispense range, validity information, packet
Fill feature, unique identification, other information Relating Characteristic etc..
It is noted that building deep neural network model can be implemented by using the prior art, and the depth nerve net
The framework of network model can also use the prior art.For example, the deep neural network model can be used such as Chinese patent
Mode disclosed in 201611228253.X is constructed, and the structure of the deep neural network model can also be used as Chinese special
Framework disclosed in sharp 201611228253.X.Not burdensome description to this in the present embodiment.
In addition, it is noted that since terminal and server is the node of block chain, the depth nerve net
Network model can be server side realize, be also possible to terminal side realize, for example, server according to merchandise news more
Newly, corresponding information to be pushed is obtained, for example, information to be pushed is sent by server to the deep neural network model progress of terminal
Study.
After obtaining the prediction probability of information to be pushed, by the prediction probability of information to be pushed to the block chain
Each node broadcasts, so that other each nodes in block chain can receive the prediction probability of information to be pushed, in this way, each section
Point can record the prediction probability of information to be pushed, and a node therein is possibly based on the prediction of the information to be pushed
Probability generates new block, in this way, making the prediction probability of each information to be pushed can be recorded, and is recorded in block
In the node of chain, to realize the distributed storage of the prediction probability of information to be pushed, the storage to server is effectively reduced
The occupancy of resource.
In order to realize that the real-time update of the prediction probability of information to be pushed detects whether exist newly in one embodiment
The merchandise news of publication obtains letter to be pushed corresponding with the merchandise news when detecting the presence of the merchandise news newly issued
Breath；The information to be pushed is parsed, the feature of the information to be pushed is obtained；By the feature of the information to be pushed and user
Multidimensional characteristic is input in the deep neural network model constructed and is predicted, the prediction for obtaining each information to be pushed is general
Rate；To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
In the present embodiment, after commodity update, triggering obtains information to be pushed, and then carries out the calculating of predetermined probabilities, with
Corresponding prediction probability is calculated to newly generated information to be pushed in this.
It is noted that the information to be pushed is initiated by server platform side, sent to user, due to the present embodiment
In, the prediction probability of information to be pushed is stored in block chain, so that the prediction probability of information to be pushed realizes distribution
Storage, in order to realize the distributed storage of information to be pushed, in one embodiment, obtain information to be pushed, the area Xiang Suoshu
Information to be pushed described in each node broadcasts of block chain, in the present embodiment, server is by information to be pushed to each node of block chain
Broadcast, so that each node can receive information to be pushed, so that each information to be pushed can be by node institute
Record, realizes the distributed storage of information to be pushed.
In order to enable server can timely pushed information detect the login of user in one embodiment；It is detecting
When user logs in；Obtain each block of block chain；The block chain is parsed, obtains and records in each block on the block chain
The prediction probability of the multidimensional characteristic of user and multiple information to be pushed corresponding with the multidimensional characteristic of the user；According to described
Prediction probability pushes the information to be pushed to user.
In the present embodiment, server obtains block when detecting that user logs in from block chain, parsing block obtains
The prediction probability of the multidimensional characteristic of user and corresponding information to be pushed, in this way, enabling the server to be quickly obtained multidimensional spy
It seeks peace the prediction probability of information to be pushed, to realize the fast and accurate push of information to be pushed.
The prediction of each information to be pushed of each node broadcasts to the block chain in one of the embodiments,
After the step of probability further include: generate block according to the prediction probability of each information to be pushed；It is updated according to the block
The block chain.
In the present embodiment, the prediction probability node of the information to be pushed of broadcast is received, according to each information to be pushed
Prediction probability generate block, that is, by the prediction probability of information to be pushed write-in block, and block chain is entered to block
In chain.In this way, realizing the distributed recording and storage to the prediction probability of information to be pushed.Also, due to information to be pushed
Prediction probability write-in block chain in, effectively operation information can be avoided to be tampered, and effectively avoid the pre- of information to be pushed
Survey the loss of probability.In addition, by the way that block is written in the prediction probability of information to be pushed, without individually being write to server
Enter, the storage efficiency of the prediction probability of information to be pushed can be effectively improved.
In above-described embodiment, block not only is written into the multidimensional characteristic of user, also writes the prediction probability of information to be pushed
Enter block, effectively increase the storage efficiency of the multidimensional characteristic of user and the prediction probability of information to be pushed and reads effect
Rate, in addition, saving the storage resource of server.
For generating node according to operation information, realization principle is identical as the generation of block of existing block chain,
It has been illustrated in above-described embodiment, in the present embodiment, not burdensome description.
In one embodiment, the acquisition information to be pushed, wait push described in each node broadcasts of Xiang Suoshu block chain
After the step of information further include: generate block according to each information to be pushed；The block chain is updated according to the block.
In the present embodiment, the node of the information to be pushed of broadcast is received by information to be pushed and is written block, and by block
Chain enters in block chain, so that server i.e. the information to be pushed of platform side are able to record in block chain, realizes wait push away
It delivers letters the distributed storage of breath, saves the storage resource of server, and the push for effectively increasing information to be pushed is read
Efficiency.
The described the step of information to be pushed is pushed to user according to the prediction probability in one of the embodiments,
Include: whether the detection prediction probability is greater than preset threshold；When the prediction probability be greater than or equal to the preset threshold, then
The information to be pushed is pushed to user according to the prediction probability.
Specifically, since multiple information to be pushed have respectively corresponded prediction probability, in order to from multiple information to be pushed
It determines that one is pushed, whether the corresponding to determine whether to push of prediction threshold value is greater than according to prediction probability in the present embodiment
Information to be pushed shows the corresponding feature of information to be pushed and user when whether prediction probability is greater than or equal to preset threshold
Multidimensional characteristic matching degree it is higher.When multiple prediction probabilities be greater than preset threshold, then push multiple corresponding information to be pushed.
When there is no the prediction probability that prediction probability is greater than or equal to preset threshold, then the sequence according to prediction probability from large to small,
Successively push corresponding information to be pushed.
In the present embodiment, since information to be pushed is pushed according to prediction probability, information to be pushed and user
Demand matching degree it is higher, the corresponding information to be pushed of prediction probability is pushed to the terminal of user, is realized with this wait push
The accurate push of information.
In the following examples, the realization process to the information-pushing method based on block chain is specifically addressed:
In the present embodiment, user logs in terminal, and triggering terminal is obtained user behavior of the user in upper primary login
Corresponding operation information, user will largely use in the historical data that the operation information repeatedly logged in front of this is user, terminal
The historical data at family is directed into user model and is learnt, and obtains the multidimensional characteristic of user.Then, section of the terminal as block chain
Point broadcasts the multidimensional characteristic of the user, so that other nodes receive the multidimensional characteristic of the user.One of node pair
The multidimensional characteristic of the user, which be packaged, generates block, and block chain is entered in block chain, realizes the update to block chain.
It is noted that the corresponding operation information of operation that user is done in this login will be recorded, store, with
When user logs in next time, this operation information is directed into user model and is learnt, obtains the multidimensional characteristic of user.
In this way, user when logging in each time, such as produces new operation, then can accordingly learn to obtain new multidimensional characteristic, conversely, such as
User does not generate new operation after logging in, then new multidimensional characteristic will not be generated.
On the other hand, node obtains information to be pushed；The information to be pushed is parsed, the spy of the information to be pushed is obtained
Sign；By the multidimensional characteristic of the feature of the information to be pushed and user, be input in the deep neural network model constructed into
Row prediction, obtains the prediction probability of each information to be pushed, the prediction to other node broadcasts information to be pushed of block chain is general
Rate.The node for receiving the prediction probability of information to be pushed, which be packaged to the prediction probability of information to be pushed, generates block, will
Block chain enters in block chain, realizes the update to block chain.
When user logs in, server detects that user logs in, and server obtains block from block chain, parses block,
The multidimensional characteristic of the user and the prediction probability of multiple information to be pushed corresponding with the multidimensional characteristic of the user are obtained, is serviced
Information to be pushed is pushed to the terminal of user according to the prediction probability of information to be pushed by device.To realize information to be pushed
Push.
It should be understood that although each step in the flow chart of Fig. 2 is successively shown according to the instruction of arrow, this
A little steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, at least part in Fig. 2
Step may include that perhaps these sub-steps of multiple stages or stage are executed in synchronization to multiple sub-steps
It completes, but can execute at different times, the execution sequence in these sub-steps or stage, which is also not necessarily, successively to be carried out,
But it can be executed in turn or alternately at least part of the sub-step or stage of other steps or other steps.
Here is a specific embodiment:
1) the alliance's chain formed by Platform Server, each user of platform, platform administrator, each step of the user terminal in platform
Block is charged in operation, and to each node broadcasts of block chain, and each node receives information on chain, and block is written.
2) (including the information such as commodity, advertisement, article) after operators' publishing platform information such as platform user or administrator, it is
The feature (for example price, brand positioning dispense range, the characteristic informations such as activity time) for identification information of uniting, current operation node
Information and its characteristic information are charged into block, and to each node broadcasts of block chain, each node receives information, write area on chain
Block.
3) when user logs in platform, register is charged to block chain by user node, and to each node broadcasts of block chain,
Each node receives information on chain, and block is written.
4) the history click information of currently logged on user imports user's unique characteristics and extracts model, extracts itself spy of user
It levies (such as probability of high consumption group, the probability of male/female, the features such as fashion type/conservative probability), the user characteristics
Extraction extracted using machine learning mode, the machine learning that existing technology can be used is realized, currently logged on user's node to
Unique characteristics information is written in block, and to each node broadcasts of block chain, and each node receives information on chain, and block is written.
5) simultaneously, the history click information importing of currently logged on user is trained in advance with a large number of users history click data
User model, extract the operating characteristics of active user, by the operating characteristics and step 3) of currently logged on user extract wait push away
Information characteristics import deep neural network model (DNN), predict the prediction probability of information to be pushed away, and to distinguish, we are denoted as preference
The preference prediction probability of information to be pushed away is charged to block by prediction probability, active user's node, and to each node broadcasts of block chain, chain
Upper each node receives information, and block is written.
6) in currently logged on user's node from query steps 4 on block chain) in user's unique characteristics information and step 5)
The preference prediction probability of corresponding active user's information to be pushed away does not have re -training to cross or user as user's unique characteristics extract model
Model does not have the operation note that re -training is crossed and user is not new, then directly from query steps 4 on block chain after user logs in)
In user's unique characteristics and step 5) in correspond to active user information to be pushed away preference prediction probability, otherwise user log in after
Step 4) and step 5) must be re-started.
7) simultaneously from query steps 2 on block) in information characteristics to be pushed away in limited period, by user's unique characteristics information,
The preference prediction probability and information characteristics to be pushed away of the information to be pushed away of corresponding active user import user demand information excavating model.
Both 8) user information mining model thinking, first comparison user's unique characteristics information and information characteristics to be pushed away, such as
Feature meets, then predicts information prediction probability to be pushed away by the characteristic probability of user, to distinguish, is characterized prediction probability (ratio
Model such as is extracted by user's unique characteristics and obtains that user is fashion type and to like the probability of accessory be 60%, then the small decorations of fashion
Information characteristics prediction probability in product is 60%), thus to calculate all information to be pushed away for meeting active user's unique characteristics
Feature prediction probability.
The feature prediction probability of the corresponding information to be pushed away of active user is compared one by one with hobby prediction probability, is such as worked as
The information characteristics prediction probability to be pushed away of preceding comparison is greater than hobby prediction probability and hobby prediction probability is greater than 0, then the current letter of push
Associated other information is then purchased by group wait push away in information in breath, and the total prediction probability for spelling the information to be pushed away of preferential activity class such as single mentions
It rises, increases probability value 5%, other classes；As the information characteristics prediction probability to be pushed away currently compared is greater than hobby prediction probability and happiness
Good prediction probability is equal to 0, then to current with pushing currently information to be pushed away
The information characteristics prediction probability to be pushed away such as currently compared is greater than hobby prediction probability and preference prediction probability is equal to 0,
And preferential activity is not present in information to be pushed away, then pushes the preferential activity such as preferential Securities to improve user preference rate, push preferential activity
Push probability is characterized prediction probability, and recording the corresponding information marketing grade currently to be pushed away of active user is A grades；Letter such as to be pushed away
Have before breath there are preferential movable push and preference prediction probability be still 0, then illustrates that user does not have demand to current information,
Pushing probability is 0, and recording the corresponding information marketing grade currently to be pushed away of active user is 0 grade.
The information characteristics prediction probability to be pushed away such as currently compared is greater than hobby prediction probability and preference prediction probability is greater than 0,
Then information to be pushed away is by hobby prediction probability push, while the preferential strategy such as push preferential Securities to be to improve user preference rate, and records
The corresponding information marketing grade currently to be pushed away of active user is B grades；As the information characteristics prediction probability to be pushed away currently compared is less than
Like prediction probability, then by hobby prediction probability push, and recording the corresponding information marketing grade currently to be pushed away of active user is C
Grade；The above correlation ratio passes through user node to result information and charges to block, and to each node broadcasts of block chain, each node on chain
Information is received, block is written；In server end, receive user terminal transmission after the analysis of user demand mining model
Information to be pushed away is carried out the push of information by the sequence of push probability (being greater than 0) from big to small.Meanwhile as user is corresponding wait push away
The preferential activity (for example spelling list, purchase by group, the information such as display panic buying) that the information to be pushed away that information marketing grade is A grades starts then pushes
To corresponding user
In the present embodiment, realize that user's history clicks distributed storage and the user spy of behavior by block chain technology
Sign is extracted, and information characteristics to be pushed away extract, and the calculating that cost source is compared in user preference feature extraction etc. is directly carried out in user terminal, and
It realizes distributed tracking storage, greatly reduces the pressure of server end.Meanwhile using artificial intelligence technology, realize wait push away
The scientific analysis of information accurately pushes and excavates user demand, and the change of the historical operation information according to user, makees in time
Corresponding marketing strategy adjustment out.
In one embodiment, it as shown in figure 3, providing a kind of information push-delivery apparatus based on block chain, including obtains
Block chain module 310, feature and probability obtain module 330 and pushing module 350, in which:
Obtain each block that block chain module 310 is used to obtain block chain.
Feature and probability obtain module 330 for parsing the block chain, obtain and remember in each block on the block chain
The prediction probability of the multidimensional characteristic of the user of load and multiple information to be pushed corresponding with the multidimensional characteristic of the user.
Pushing module 350 is used to push the information to be pushed to user according to the prediction probability.
In one embodiment, the information push-delivery apparatus based on block chain further include:
Operation information acquisition module, for obtaining operation information.
Operation information broadcast module, for operation information described in each node broadcasts to the block chain.
In one embodiment, the information push-delivery apparatus based on block chain further include:
First block generation module, for generating block according to the operation information.
First update module, for updating the block chain according to the block.
In one embodiment, the operation information acquisition module is also used to obtain the operation information, by the operation
Information imports user model and is learnt, and obtains the multidimensional characteristic of user.
The operation information broadcast module is also used to the multidimensional characteristic to each node broadcasts user of the block chain.
In one embodiment, the information push-delivery apparatus based on block chain further include:
Information to be pushed obtains module, for obtaining information to be pushed.
Information to be pushed parsing module obtains the feature of the information to be pushed for parsing the information to be pushed.
Prediction probability obtains module, for being input to the multidimensional characteristic of the feature of the information to be pushed and user
It is predicted in the deep neural network model of building, obtains the prediction probability of each information to be pushed.
Prediction probability broadcast module, the prediction for each information to be pushed of each node broadcasts to the block chain are general
Rate.
In one embodiment, the information push-delivery apparatus based on block chain further include:
Second block generation module, for generating block according to the prediction probability of each information to be pushed.
Second update module, for updating the block chain according to the block.
In one embodiment, the pushing module includes:
Threshold detection unit, for detecting whether the prediction probability is greater than preset threshold.
Push unit, for being greater than or equal to the preset threshold when the prediction probability, then according to the prediction probability
The information to be pushed is pushed to user.
Specific restriction about the information push-delivery apparatus based on block chain may refer to above for based on block chain
The restriction of information-pushing method, details are not described herein.Modules in the above-mentioned information push-delivery apparatus based on block chain can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of calculating
In processor in machine equipment, it can also be stored in a software form in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, and can be
Terminal, as the node in block chain, internal structure chart can be as shown in Figure 4.The computer equipment includes passing through to be
Processor, memory, network interface and the database of bus of uniting connection.Wherein, the processor of the computer equipment is for providing
Calculating and control ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.This is non-volatile to deposit
Storage media is stored with operating system, computer program and database.The built-in storage is the operation in non-volatile memory medium
The operation of system and computer program provides environment.The database of the computer equipment is for storing user model, depth nerve
Network model.The network interface of the computer equipment is used to communicate with nodes such as external terminals by network connection.The calculating
To realize a kind of information-pushing method based on block chain when machine program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 4, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor perform the steps of when executing computer program
Obtain each block of block chain.
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic of user.
The information to be pushed is pushed to user according to the prediction probability.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain operation information.
Operation information described in each node broadcasts to the block chain.
In one embodiment, it is also performed the steps of when processor executes computer program
Block is generated according to the operation information.
The block chain is updated according to the block.
In one embodiment, it is also performed the steps of when processor executes computer program
The operation information is obtained, operation information importing user model is learnt, the multidimensional for obtaining user is special
Sign.
The step of operation information described in each node broadcasts to the block chain includes:
To the multidimensional characteristic of each node broadcasts user of the block chain.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain information to be pushed.
The information to be pushed is parsed, the feature of the information to be pushed is obtained.
By the multidimensional characteristic of the feature of the information to be pushed and user, it is input to the deep neural network model constructed
In predicted, obtain the prediction probability of each information to be pushed.
To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
In one embodiment, it is also performed the steps of when processor executes computer program
Block is generated according to the prediction probability of each information to be pushed.
The block chain is updated according to the block.
In one embodiment, it is also performed the steps of when processor executes computer program
Detect whether the prediction probability is greater than preset threshold.
When the prediction probability is greater than or equal to the preset threshold, then according to the prediction probability to described in user's push
Information to be pushed.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain each block of block chain.
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with institute
State the prediction probability of the corresponding multiple information to be pushed of multidimensional characteristic of user.
The information to be pushed is pushed to user according to the prediction probability.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain operation information.
Operation information described in each node broadcasts to the block chain.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Block is generated according to the operation information.
The block chain is updated according to the block.
In one embodiment, it is also performed the steps of when computer program is executed by processor
The operation information is obtained, operation information importing user model is learnt, the multidimensional for obtaining user is special
Sign.
The step of operation information described in each node broadcasts to the block chain includes:
To the multidimensional characteristic of each node broadcasts user of the block chain.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain information to be pushed.
The information to be pushed is parsed, the feature of the information to be pushed is obtained.
By the multidimensional characteristic of the feature of the information to be pushed and user, it is input to the deep neural network model constructed
In predicted, obtain the prediction probability of each information to be pushed.
To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Block is generated according to the prediction probability of each information to be pushed.
The block chain is updated according to the block.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Detect whether the prediction probability is greater than preset threshold.
When the prediction probability is greater than or equal to the preset threshold, then according to the prediction probability to described in user's push
Information to be pushed.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of information-pushing method based on block chain, which comprises
Obtain each block of block chain；
Parse the block chain, obtain the user recorded in each block on the block chain multidimensional characteristic and with the use
The prediction probability of the corresponding multiple information to be pushed of the multidimensional characteristic at family；
The information to be pushed is pushed to user according to the prediction probability.
2. the method according to claim 1, wherein also being wrapped before the step of each block for obtaining block chain
It includes:
Obtain operation information；
Operation information described in each node broadcasts to the block chain.
3. according to the method described in claim 2, it is characterized in that, being operated described in each node broadcasts to the block chain
After the step of information further include:
Block is generated according to the operation information；
The block chain is updated according to the block.
4. according to the method described in claim 2, it is characterized in that, the step of acquisition operation information include:
The operation information is obtained, operation information importing user model is learnt, the multidimensional characteristic of user is obtained；
The step of operation information described in each node broadcasts to the block chain includes:
To the multidimensional characteristic of each node broadcasts user of the block chain.
5. according to the method described in claim 4, it is characterized in that, it is described obtain block chain each block the step of before also wrap
It includes:
Obtain information to be pushed；
The information to be pushed is parsed, the feature of the information to be pushed is obtained；
By the multidimensional characteristic of the feature of the information to be pushed and user, be input in the deep neural network model constructed into
Row prediction, obtains the prediction probability of each information to be pushed；
To the prediction probability of each information to be pushed of each node broadcasts of the block chain.
6. according to the method described in claim 5, it is characterized in that, each node broadcasts to the block chain it is each it is described to
After the step of prediction probability of pushed information further include:
Block is generated according to the prediction probability of each information to be pushed；
The block chain is updated according to the block.
7. according to claim 1 to method described in 6 any one, which is characterized in that it is described according to the prediction probability to
Family push the information to be pushed the step of include:
Detect whether the prediction probability is greater than preset threshold；
It is when the prediction probability is greater than or equal to the preset threshold, then described wait push away to user's push according to the prediction probability
It delivers letters breath.
8. a kind of information push-delivery apparatus based on block chain, which is characterized in that described device includes:
Block chain module is obtained, for obtaining each block of block chain；
Feature and probability obtain module and obtain the use recorded in each block on the block chain for parsing the block chain
The prediction probability of the multidimensional characteristic at family and multiple information to be pushed corresponding with the multidimensional characteristic of the user；
Pushing module, for pushing the information to be pushed to user according to the prediction probability.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 7 institute when executing the computer program
The step of stating method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526939.4A CN110247974A (en) | 2019-06-18 | 2019-06-18 | Information-pushing method, device, computer and storage medium based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526939.4A CN110247974A (en) | 2019-06-18 | 2019-06-18 | Information-pushing method, device, computer and storage medium based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110247974A true CN110247974A (en) | 2019-09-17 |
Family
ID=67887762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910526939.4A Pending CN110247974A (en) | 2019-06-18 | 2019-06-18 | Information-pushing method, device, computer and storage medium based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110247974A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242678A (en) * | 2020-01-07 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN112070532A (en) * | 2020-08-27 | 2020-12-11 | 中国平安财产保险股份有限公司 | Information pushing method, device, equipment and storage medium |
| CN112348716A (en) * | 2020-11-25 | 2021-02-09 | 山东师范大学 | Block chain-based news data storage and release process and business operation mode thereof |
| CN112446812A (en) * | 2020-12-14 | 2021-03-05 | 恒瑞通（福建）信息技术有限公司 | Block chain based government affair information automatic pushing method and terminal |
| CN113609381A (en) * | 2021-07-13 | 2021-11-05 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
| CN108933819A (en) * | 2018-06-26 | 2018-12-04 | 尹煦 | A kind of information-pushing method based on block chain |
| 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 |
| US20190057164A1 (en) * | 2017-08-16 | 2019-02-21 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Search method and apparatus based on artificial intelligence |
| CN109523302A (en) * | 2018-10-19 | 2019-03-26 | 中链科技有限公司 | Advertisement sending method, device and calculating equipment based on block chain |
-
2019
- 2019-06-18 CN CN201910526939.4A patent/CN110247974A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
| US20190057164A1 (en) * | 2017-08-16 | 2019-02-21 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Search method and apparatus based on artificial intelligence |
| CN108933819A (en) * | 2018-06-26 | 2018-12-04 | 尹煦 | A kind of information-pushing method based on block chain |
| 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 |
| CN109523302A (en) * | 2018-10-19 | 2019-03-26 | 中链科技有限公司 | Advertisement sending method, device and calculating equipment based on block chain |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242678A (en) * | 2020-01-07 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN112070532A (en) * | 2020-08-27 | 2020-12-11 | 中国平安财产保险股份有限公司 | Information pushing method, device, equipment and storage medium |
| CN112348716A (en) * | 2020-11-25 | 2021-02-09 | 山东师范大学 | Block chain-based news data storage and release process and business operation mode thereof |
| CN112446812A (en) * | 2020-12-14 | 2021-03-05 | 恒瑞通（福建）信息技术有限公司 | Block chain based government affair information automatic pushing method and terminal |
| CN112446812B (en) * | 2020-12-14 | 2023-07-21 | 恒瑞通（福建）信息技术有限公司 | Automatic push method and terminal for government affair information based on blockchain |
| CN113609381A (en) * | 2021-07-13 | 2021-11-05 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
| CN113609381B (en) * | 2021-07-13 | 2023-12-12 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110247974A (en) | Information-pushing method, device, computer and storage medium based on block chain | |
| US11574139B2 (en) | Information pushing method, storage medium and server | |
| CN106446228B (en) | Method and device for collecting and analyzing WEB page data | |
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN103176982B (en) | The method and system that a kind of e-book is recommended | |
| US20160210657A1 (en) | Real-time marketing campaign stimuli selection based on user response predictions | |
| CN107851267A (en) | System and method for carrying out the synchronous data related to audio call via the virtual phone number of dynamically distributes | |
| CN110335100A (en) | Information-pushing method, device, computer and storage medium based on artificial intelligence | |
| CN108763502A (en) | Information recommendation method and system | |
| CN109840782B (en) | Click rate prediction method, device, server and storage medium | |
| CN109446302A (en) | Question and answer data processing method, device and computer equipment based on machine learning | |
| CN111538907B (en) | Object recommendation method, system and device | |
| CN111274501B (en) | Method, system and non-transitory storage medium for pushing information | |
| CN103177129B (en) | Internet real-time information recommendation prognoses system | |
| CN108460627A (en) | Marketing activity scheme method for pushing, device, computer equipment and storage medium | |
| KR102312735B1 (en) | Method for providing crowdfunding commercial service using influencer marketing | |
| CN109447685A (en) | Product data method for pushing, device and computer equipment based on machine learning | |
| CN109461043A (en) | Product method for pushing, device, computer equipment and storage medium | |
| CN112148992A (en) | Content pushing method and device, computer equipment and storage medium | |
| CN106503907A (en) | A kind of business assessment information determines method and server | |
| CN111291125A (en) | Data processing method and related equipment | |
| KR20220155946A (en) | Method and apparatus for providing a list of advertising companies related to a first terminal using a neural network | |
| CN113011886B (en) | Method and device for determining account type and electronic equipment | |
| CN112269943B (en) | Information recommendation system and method | |
| CN115730125A (en) | Object identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |
|
| RJ01 | Rejection of invention patent application after publication |