CN108491540A - Text message method for pushing, device and intelligent terminal - Google Patents
Text message method for pushing, device and intelligent terminal Download PDFInfo
- Publication number
- CN108491540A CN108491540A CN201810286984.2A CN201810286984A CN108491540A CN 108491540 A CN108491540 A CN 108491540A CN 201810286984 A CN201810286984 A CN 201810286984A CN 108491540 A CN108491540 A CN 108491540A
- Authority
- CN
- China
- Prior art keywords
- text message
- interest
- push
- target
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
Abstract
The application proposes a kind of text message method for pushing, device and intelligent terminal, wherein method includes:Calculate the interest degree of correlation of each candidate text message and the point of interest of target user;The interest coverage of each candidate text message is calculated according to interest coverage computation model;The scoring of push value is carried out to each candidate text message, and push is worth highest candidate text message as target text information deposit text message push collection;The operational factor of interest coverage computation model is updated according to the interest coverage of the target text information of newest deposit text message push collection;It concentrates each remaining candidate text message to carry out the scoring of push value candidate text message according to updated interest coverage computation model, and push is worth highest candidate text message as target text information deposit text message push collection;Text message push collection is pushed to target user.The diversity for improving information push as a result, increases the viscosity of user and product.
Description
Technical field
This application involves a kind of information advancing technique field more particularly to text message method for pushing, device and intelligence eventually
End.
Background technology
In general, in order to from a large amount of text message on internet, recommend the text in accordance with user interest point to user
Information, commending system need the different demands for meeting different user, to achieve the effect that thousand people, thousand face.
In the related technology, commending system is divided into two stages of recalling and sort, and the stage of recalling passes through user preference information etc.
Mode is coarse to recall text message, and the Candidate Set for recalling the stage is usually million ranks, and phase sorting is then to the text after recalling
Information calculates the marking between user and text message, this marking can be as the foundation of final output ranking results.
However, sort method in the related technology, gives a mark only according to the interest preference of user, although from single
Recommendation results see that accuracy is relatively high, but if from the point of view of the whole recommendation results of each user, diversity but cannot be guaranteed.With
It is for news is recommended, if target user likes seeing to recommend the scene of text message " the relevant news of Mei Xi " is new from single
From the perspective of news, own " Mei Xi " relevant news marking will necessarily be relatively high, to, have include largely " Mei Xi " it is new
News recommends user, and diversity is poor.
Apply for content
The application is intended to solve at least some of the technical problems in related technologies.
For this purpose, first purpose of the application is to propose a kind of text message method for pushing, information push is improved
Diversity increases the viscosity of user and product.
Second purpose of the application is to propose a kind of text message pusher.The third purpose of the application is
It is proposed a kind of intelligent terminal.
The 4th purpose of the application is to propose a kind of non-transitorycomputer readable storage medium.
The 5th purpose of the application is to propose a kind of computer program product.
In order to achieve the above object, the application first aspect embodiment proposes a kind of text message method for pushing, including it is following
Step:Obtain candidate text message collection;It is calculated according to preset user interest point correlation model and text interest point correlation model
Candidate's text message concentrates the interest degree of correlation of each candidate text message and the point of interest of target user;According to preset
Interest coverage computation model calculates each candidate text message and is pushed away respectively as target text information addition text message
When sending collection, the interest coverage of all target text information is concentrated in the text message push;According to the interest degree of correlation and
Interest coverage carries out each candidate text message the scoring of push value, and the push is worth highest candidate text
Information is stored in the text message push collection as target text information;According to the mesh of the newest deposit text message push collection
The interest coverage of mark text message updates the operational factor of the interest coverage computation model;According to the preset user
Point of interest correlation model, text interest point correlation model and the updated interest coverage computation model are to the candidate text
This information concentrates each remaining candidate text message to carry out the scoring of the push value, and the push is worth highest candidate
Text message is as target text information deposit text message push collection;Text message push collection is pushed to the target
User.
The text message method for pushing of the embodiment of the present application can be based on the basis of ensureing recommendation results accuracy
The diversity of point of interest carries out the push of text message, can effectively ensure the diversity for pushing result, to meet user
Individualized experience, improve the viscosity of user and product.
In order to achieve the above object, the application second aspect embodiment proposes a kind of text message pusher, including:It obtains
Module, for obtaining candidate text message collection;Computing module, for emerging according to preset user interest point correlation model and text
Interest point correlation model calculates the interest that the candidate text message concentrates each candidate text message and the point of interest of target user
The degree of correlation;The computing module is additionally operable to calculate each candidate text envelope according to preset interest coverage computation model
When text message push collection is added respectively as target text information in breath, all target text letters are concentrated in the text message push
The interest coverage of breath;Processing module is used for according to the interest degree of correlation and interest coverage to each candidate text
Information carries out the scoring of push value, and the highest candidate text message of push value is stored in text as target text information
Information push collection;Update module, the interest for the target text information according to the newest deposit text message push collection are covered
Cover degree updates the operational factor of the interest coverage computation model;The processing module is additionally operable to according to the preset use
Family point of interest correlation model, text interest point correlation model and the updated interest coverage computation model are to the candidate
Text message concentrates each remaining candidate text message to carry out the scoring of the push value, and the push is worth highest time
Select text message as target text information deposit text message push collection;Pushing module, for pushing the text message
Collection is pushed to the target user.
The text message pusher of the embodiment of the present application can be based on the basis of ensureing recommendation results accuracy
The diversity of point of interest carries out the push of text message, can effectively ensure the diversity for pushing result, to meet user
Individualized experience, improve the viscosity of user and product.In order to achieve the above object, the application third aspect embodiment proposes one
Kind intelligent terminal, including:Processor and memory;Wherein, the processor is held by what is stored in the reading memory
Line program code runs program corresponding with the executable program code, for realizing the text as described in above-described embodiment
This information-pushing method.
To achieve the goals above, the application fourth aspect embodiment proposes a kind of computer-readable storage of non-transitory
Medium realizes the text message method for pushing as described in above-described embodiment when the program is executed by processor.
To achieve the goals above, the 5th aspect embodiment of the application proposes a kind of computer program product, when described
When instruction processing unit in computer program product executes, the text message method for pushing as described in above-described embodiment is executed.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains obviously, or recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein:
Fig. 1 is the flow chart according to the text message method for pushing of the application one embodiment;
Fig. 2 is the update operation schematic diagram of a scenario according to the operational factor of the application one embodiment;
Fig. 3 is the flow chart according to the text message method for pushing of one specific embodiment of the application;
Fig. 4 is the structural schematic diagram according to the text message pusher of the application one embodiment;And
Fig. 5 is the block diagram for the exemplary computer device for realizing the application embodiment.
Specific implementation mode
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Below with reference to the accompanying drawings the text message method for pushing, device and intelligent terminal of the embodiment of the present application are described.
Wherein, the text message of the embodiment of the present application may include news information, and books recommendation information etc. is a variety of can be
The recommendation realized in commending system.
Fig. 1 is the flow chart according to the text message method for pushing of the application one embodiment.As shown in Figure 1, this method
Including:
Step 101, candidate text message collection is obtained.
Specifically, the method for determination of candidate text message included in candidate text message collection, with calling together for commending system
The mode of returning is related, in some possible examples, can be recalled according to geographical location, to which candidate text message is concentrated
Including candidate text message be matched with target user position, for example, to being in Pekinese user, the time of acquisition
It is Pekinese's news to select the news that text message is concentrated;Can be inclined according to the individual of user in some possible examples
What good information was slightly recalled, wherein the personal preference information of user can be determined according to the historical viewings of user record etc., from
And candidate text message, which concentrates the candidate text message for including, to be consistent with the personal preference information of user, for example, right
In the user of preference movement, the text message that the candidate text message of recommendation is concentrated includes to move and move periphery etc..
Step 102, candidate text is calculated according to preset user interest point correlation model and text interest point correlation model
Information concentrates the interest degree of correlation of each candidate text message and the point of interest of target user.
It is appreciated that user interest point correlation model is for portraying interest level of the user to point of interest, text interest
Correlation model user portrays satisfaction degree of the text message to point of interest, wherein according to the difference of application scenarios, user interest point
Correlation model and text interest point correlation model can be matrix model, neural network model etc..
Under no application scenarios, the mode of structure user interest point correlation model and text interest point correlation model is not
Together, as a kind of possible realization method, user information is obtained, wherein user information is with user to the journey interested of point of interest
It spends closely bound up, it may include it is one or more in search satisfaction feedback information, user's portrait information, user social contact information,
Wherein, user's portrait information includes identity information, occupational information, age information, gender information of user etc..
In turn, interest level of the user to multiple points of interest is analyzed according to user information, by taking user draws a portrait information as an example,
To the user of sportsman's identity, to the point of interest interest level highest of sport and its periphery, the sense to points for attention of competing
Level of interest is higher, more low to the interest level of the point of interest of makeup.According to user to the journey interested of multiple points of interest
Degree establishes user interest point correlation model, thus, it can be true according to the information of target user by user interest point correlation model
User set the goal to the interest levels of multiple points of interest.
In this example, user_attention_weight is established to the interest level of multiple points of interest according to user
Matrix, wherein interest level of the user to point of interest is featured in matrix.
In the present embodiment, text message is obtained, interest of the text message to multiple points of interest is analyzed according to text message
Coverage analyzes the covering of content and point of interest that text message is included for example, carrying out semantic analysis to text message
Degree for another example according to the number with the relevant keyword of point of interest that text message occurs, analyzes what text message was included
The coverage of content and point of interest establishes text interest point according to text message to the interest coverage of multiple points of interest in turn
Correlation model, to by interest coverage computation model according to acquisitions such as the information content, the information sources of candidate text message
Level of coverage of the text message to point of interest.
In this example, doc_attention_weight squares are established to the interest level of multiple points of interest according to user
Battle array, wherein level of coverage of the text message to point of interest is featured in matrix.
Specifically, candidate text envelope is calculated according to preset user interest point correlation model and text interest point correlation model
Breath concentrates the interest degree of correlation of each candidate text message and the point of interest of target user, wherein obtains the side of the interest degree of correlation
Formula can be different under different application scenarios, continue using user interest point correlation model and text interest point correlation model as square
For battle array, which is the product value of user interest point incidence matrix and text interest point incidence matrix.
It is emphasized that the candidate text message of each of the present embodiment is related to the interest of the point of interest of target user
Degree indicates the correlation in point of interest dimension between each candidate text message and the point of interest of target user, to ensure most
The candidate text message for being pushed to target user eventually is relatively uniform with user interest point, ensures the accurate of the text message of push
Property.
Step 103, each candidate text message is calculated respectively as target according to preset interest coverage computation model
When text message push collection is added in text message, the interest coverage of all target text information is concentrated in text message push.
Wherein, interest coverage indicates that the push of current text information concentrates all target text information to each point of interest
Level of coverage, interest coverage is higher, indicates that the interest covered in all target text information is concentrated in the push of current text information
Point is more and more to the degree of covering of each point of interest, and interest coverage is lower, indicates that institute is concentrated in the push of current text information
There is the point of interest covered in target text information fewer, and fewer to the degree of covering of each point of interest, alternatively, to a other several
The degree of covering of a point of interest is more etc..
If being appreciated that the point of interest for concentrating each candidate text message and target user only according to candidate text message
The interest degree of correlation, determine and be finally pushed to the target text information of target user, it is clear that the target text letter of push can be caused
Breath excessively concentrates on the higher point of interest of user interest degree, and the diversity of the target text information of push is inadequate, thus, in order to protect
The diversity of card text message push introduces preset interest coverage computation model, by this in embodiments herein
When interest-degree computation model calculates each candidate text message respectively as target text information addition text message push collection, text
The interest coverage of all target text information is concentrated in the push of this information, wherein all targets are concentrated in the push of current text information
Text message includes the target text information determined before, and current candidate text message to be scored, to be based on interest
The diversity dimension of point considers the candidate text message that candidate text message is concentrated.
Citing and for, it is assumed that current candidate text message concentration includes candidate text message 1 and 2, and text message pushes
It is 3 and 4 to concentrate the target text information having determined, then calculates and regard candidate text message 1 as target text information, text is added
After the push of this information is concentrated, the interest coverage that target text information is 1,3 and 4, and, it regard candidate text message 2 as mesh
Mark text message, be added text message push concentrate after, target text information be 2,3 and 4 interest coverage.
Step 104, the scoring of push value is carried out to each candidate text message according to the interest degree of correlation and interest coverage,
And push is worth highest candidate text message as target text information deposit text message push collection.
Specifically, the scoring of push value is carried out to each candidate text message according to the interest degree of correlation and interest coverage,
In turn, push is worth highest candidate text message as target text information deposit text message push collection, thereby it is ensured that
The target text information of text message push concentration is currently joined into i.e. with reference to the diversity dimension of point of interest, referring also to target
The dimension of the point of interest of user.
Wherein, according to the difference of application scenarios, according to the interest degree of correlation and interest coverage to each candidate text message
The mode for carrying out push value scoring is different, and example is as follows:
The first example:
In this example, preset interest coverage computation model, user interest point correlation model and text interest point close
Gang mould type is matrix, wherein interest coverage computation model is T matrixes, and user interest point correlation model is user_
Attention_weight matrixes, text interest point correlation model are doc_attention_weight matrixes, then can will be upper
The product value for stating three matrixes scores as push value, i.e. push value user_doc_score=user_attention_
weight*T*doc_attention_weigh。
Second of example:
In this example, the scoring of the interest degree of correlation and the scoring of interest coverage can be different, for example, emerging
The scoring of the interesting degree of correlation is hundred-mark system, and the scoring of interest coverage is ten point system, then can calculate separately out interest correlation
After degree and interest coverage, after the interest degree of correlation and interest coverage are normalized respectively, by the score value of the two and
Scoring as push value.
Certainly, in the present embodiment, in order to meet the needs under different application scene, interest correlation can also be assigned respectively
Degree weighted value corresponding with interest coverage is multiplied with corresponding weighted value respectively by the interest degree of correlation and interest coverage
Afterwards, by corresponding product value and as push value scoring.
Step 105, interest is updated according to the interest coverage of the target text information of newest deposit text message push collection
The operational factor of coverage computation model.
Step 106, according to preset user interest point correlation model, text interest point correlation model and updated interest
Coverage computation model concentrates each remaining candidate text message to carry out the scoring of push value candidate text message, and will push away
Send the highest candidate text message of value as target text information deposit text message push collection.
It should be understood that multifarious the considering of text message push, is not simply to individually pushing in fact
Target text information is considered, but the comprehensive consideration of all target text information to recommendation, thus, it is emerging in the application
Interesting coverage computation model calculates interest coverage, assumes that each candidate text message being separately added into corresponding text message
After push collection, according to currently selected all target text information to the level of coverage of each point of interest.
For example, if current selected all target text information to the level of coverage of point of interest A and B compared with
Height does not cover point of interest C and D, then it is during the determination of next target text information, to one comprising emerging
The candidate text message 1 of interesting point A, B, C and another include the candidate text message 2 of point of interest C and D, consider add respectively respectively
After entering text message push collection, the interest coverage of text message push collection, although at this point, candidate text message 1 cover it is more
Point of interest, but due to its covering point of interest A, B included largely in the target text information selected, thus, wait
The interest coverage that can be obtained after selecting text message 1 to be added is relatively low, although candidate text message 2 covers less point of interest,
It is that the point of interest C and D covered due to it does not include in the target text information selected, thus, candidate text message 2 is added
The interest coverage obtained afterwards is higher, and candidate text message 2 may bring actively impact to the diversity of text message.
Clearly as user interest point correlation model is according to current selected all target text information to each
What the level of coverage of a point of interest determined, thus, after determining newest target text information, selected target text
Information is due to being added new target text information, at this time, it may be necessary to be believed according to the target text of newest deposit text message push collection
Breath interest coverage update interest coverage computation model operational factor, with improve commending system practicability and flexibly
Property.
In turn, it is covered according to preset user interest point correlation model, text interest point correlation model and updated interest
Cover degree computation model concentrates each remaining candidate text message to carry out the scoring of push value candidate text message, and will push
It is worth highest candidate text message as target text information deposit text message push collection, often determines a target as a result,
After text message, i.e., according to the correlation model of its point of interest of the target text information update user of newest determination, it is ensured that under determining
The one target text information determined contributes the diversity for being pushed to the text message of user.
It should be noted that according to the difference of application scenarios, interest coverage computation model can be can arbitrarily reflect
The current text information push gone out is concentrated, and all target text information embody the form of point of interest coverage:
As a kind of possible realization method, interest coverage computation model is T matrixes, wherein the formula of T matrixes is T
=ealpha*count, wherein alpha is attenuation coefficient, and in some possible embodiments, alpha can be with value -0.32, count
It is to show number after text message push concentrates the target text information being stored in extensive to each point of interest, is covered according to interest
The formula of cover degree computation model it is found that with count values increase, the exponential damping of T matrixes represents the journey of diversity variation
Degree, that is to say, that when text message push concentrate the target text information that has been stored in each point of interest to show number higher,
After newly-increased target text information, may return causes interest coverage not promoted, to which diversity is poorer.
It in the present embodiment, can be according to the interest coverage of the target text information of newest deposit text message push collection
Update the count in T matrixes.
Certainly, in practical applications, it is contemplated that user has centainly amnestic to point of interest, for example, being used for target
The point of interest of family a, browsed target text information 1 include point of interest A, when its browsing equally includes the target of point of interest A
When text message 2, point of interest A browsed in target text information 1 may be forgotten, at this point, calculating target text
When the point of interest coverage of this information 2, determination in order to be more accurate, it should be taken into account that this forgetting to point of interest, thus,
Interest coverage computation model is updated in the interest coverage of the target text information according to newest deposit text message push collection
Operational factor when, further include:Obtain point of interest forgetting factor, wherein point of interest forgetting factor is indicating user to
The forgetting degree of browsed point of interest updates interest coverage computation model according to point of interest forgetting factor and interest coverage
In operational factor.
Clearer for description, still by taking operational factor is count as an example, in this example, count can be used to public affairs
Formula indicates:
Count=count*forgetting_factor+ Δs count
Wherein, forgetting_factor is forgetting factor, and in this example, forgetting_factor can be
0.98, indicate user to having seen the forgetting degree of point of interest, Δ count indicate that increasing target text information newly rolls over each point of interest
That calculates shows number, wherein Δ count can be calculated with following formula:
Wherein, i indicates that i-th of point of interest, j indicate to increase the point of interest that target text information is included, sim (i, j) table newly
Show the cosine similarity of i-th of point of interest and j-th of point of interest in newly-increased target text information.For example, in current text
The vector for showing number to each point of interest that information push is concentrated is expressed as { pony:1, Xiaobao:0, little Song 0 }, new gaining
Mark text message contains pony and Xiaobao the two points of interest, wherein the calculating of the Δ count in this implementation as shown in Fig. 2,
The vector of updated count is expressed as { pony:2, Xiaobao:1, little Song 0.7 }, updated count considers newly-increased target
Text shows number to point of interest, the multifarious influence on entire text message push collection.
Step 107, text message push collection is pushed to target user.
Specifically, it is determined that the target text information concentrated of text message push be according to each candidate text message and mesh
Mark the interest degree of correlation of the point of interest of user, and the interest coverage of each candidate text message is determined, this determination
Mode, on the one hand, consider the correlation of the point of interest of target user and the point of interest dimension of candidate text message, another party
Face, it is contemplated that the diversity of the point of interest of entire candidate's text set, the text message that text message push is concentrated as a result, both included
Meet the target text information of target user's point of interest, to also contain may not be the target for meeting very much target user's point of interest
Text message, the text message push pushed as a result, are concentrated, and the more interested target text information of target user had both been met
Recommendation excavate target user also to that can not be the target text information for meeting very much target user's point of interest based on other
Other points of interest, improve user experience of the target user to the push of the clicking rate and text message of text message, increase
The viscosity of user and product.
Wherein, in practical implementation, it can currently wait that text message push collection, which is pushed to the opportunity of target user,
When to select text message collection be empty, that is, traverse candidate text message and concentrate all candidate text messages, by all candidates
Text message screens one by one, and the opportunity that text message push collection is pushed to target user can also be the target letter filtered out
The number of informative text meets predetermined number, for example, for a single recommends the commending system of three text messages, works as screening
When the number of the target information text gone out is 3, then text message push collection is pushed to target user.
In addition, text message push collection is pushed to the form of target user, according to the difference of application scenarios, also include but
It is not limited to following manner:
The first example:
The target text information that text message push is concentrated generates text message and recommends according to the sequencing being stored into
List, and text message recommendation list is pushed to target user, improving target user as a result, expires text message push
Meaning degree.
Second of example:
The target text information that text message push is concentrated marks reading value according to the sequencing being stored into, wherein
Reading value can use digital representation, can also service rating indicate etc., first more be put onto text message push concentrate target text
The reading value of this information is higher, to provide reading order instruction to the user according to reading value, improve the browsing of target user
Experience.
In order to enable the description of the text message method for pushing of the embodiment of the present application is clearer, it is specific with reference to one
Embodiment under application scenarios illustrates:
In this example, the scoring of push value is indicated with the user_doc_score in above-described embodiment, interest coverage
Computation model is T matrixes, and user interest point correlation model and text interest point correlation model are respectively user_attention_
Weight matrixes and doc_attention_weight matrixes.
Specifically, as shown in figure 3, pre-establish user_attention_weight matrixes, and according to user_
Attention_weight matrixes primarily determine out candidate text message collection, if candidate text message collection is not sky, calculate
The scoring user_doc_score of recommendation, will score highest candidate text message deposit text message push collection, update T squares
After battle array, if candidate text message collection is not sky, continue to calculate remaining candidate text message according to updated T matrixes
Text message push collection is added in the scoring user_doc_score of recommendation, the highest candidate text message that will score, as a result, directly
It is sky to candidate text message collection, then the target text information that text message push is concentrated is sequentially generated text envelope according to deposit
Recommendation list is ceased, and text message recommendation list is pushed to target user.
In conclusion the text message method for pushing of the embodiment of the present application, it can be in the base for ensureing recommendation results accuracy
On plinth, the diversity based on point of interest carries out the push of text message, can effectively ensure the diversity for pushing result, to
The individualized experience for meeting user improves the viscosity of user and product.
In order to realize that above-described embodiment, the application also propose a kind of text message pusher.
Fig. 4 is the structural schematic diagram according to the text message pusher of the application one embodiment.
As shown in figure 4, text information push-delivery apparatus includes:Acquisition module 100, computing module 200, processing module 300,
Update module 400 and pushing module 500.
Wherein, acquisition module 100, for obtaining candidate text message collection.
Computing module 200, for being calculated according to preset user interest point correlation model and text interest point correlation model
Candidate text message concentrates the interest degree of correlation of each candidate text message and the point of interest of target user.
In one embodiment of the application, computing module 200 is additionally operable to according to preset interest coverage computation model
When calculating each candidate text message respectively as target text information addition text message push collection, text message push is concentrated
The interest coverage of all target text information.
Processing module 300, for being pushed to each candidate text message according to the interest degree of correlation and interest coverage
The scoring of value, and push is worth highest candidate text message as target text information deposit text message push collection.
Update module 400, the interest coverage of the target text information for being collected according to newest deposit text message push
Update the operational factor of interest coverage computation model.
In one embodiment of the application, processing module 300 is additionally operable to be associated with mould according to preset user interest point
Type, text interest point correlation model and updated interest coverage computation model concentrate candidate text message each remaining
Candidate text message carries out the scoring of push value, and push is worth highest candidate text message and is stored in as target text information
Text message push collection.
Pushing module 500, for text message push collection to be pushed to target user.
It should be noted that the aforementioned explanation to text message method for pushing embodiment is also applied for the embodiment
Text message pusher, details are not described herein again.
In conclusion the text message pusher of the embodiment of the present application, it can be in the base for ensureing recommendation results accuracy
On plinth, the diversity based on point of interest carries out the push of text message, can effectively ensure the diversity for pushing result, to
The individualized experience for meeting user improves the viscosity of user and product.
In order to realize that above-described embodiment, the application also propose a kind of intelligent terminal, including:Processor, wherein processor is logical
It crosses and reads in memory the executable program code that stores to run program corresponding with executable program code, for realizing
The text message method for pushing of above-described embodiment description.Wherein, which can be mobile phone, tablet computer, individual digital
It can be Intelligent bracelet, intelligent hand that assistant, Wearable etc., which have the hardware device of various operating systems, the Wearable,
Table, intelligent glasses etc..
In order to realize above-described embodiment, the application also proposes a kind of non-transitorycomputer readable storage medium, when described
Instruction in storage medium is performed by processor, enabling executes the text message push side shown in above-described embodiment
Method.
In order to realize that above-described embodiment, the application also propose a kind of computer program product, when the computer program produces
When instruction processing unit in product executes, the text message method for pushing shown in above-described embodiment is executed.
Fig. 5 shows the block diagram of the exemplary computer device suitable for being used for realizing the application embodiment.What Fig. 5 was shown
Computer equipment 12 is only an example, should not bring any restrictions to the function and use scope of the embodiment of the present application.
As shown in figure 5, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to:One or more processor or processing unit 16, system storage 28 connect different system component
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (Industry Standard
Architecture;Hereinafter referred to as:ISA) bus, microchannel architecture (Micro Channel Architecture;Below
Referred to as:MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association;Hereinafter referred to as:VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection;Hereinafter referred to as:PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (Random Access Memory;Hereinafter referred to as:RAM) 30 and/or cache memory 32.Computer equipment 12 can be with
Further comprise other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example,
Storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 5 do not show, commonly referred to as " hard drive
Device ").Although being not shown in Fig. 5, can provide for being driven to the disk for moving non-volatile magnetic disk (such as " floppy disk ") read-write
Dynamic device, and to removable anonvolatile optical disk (such as:Compact disc read-only memory (Compact Disc Read Only
Memory;Hereinafter referred to as:CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory;Hereinafter referred to as:DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program production
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can be stored in such as memory 28
In, such program module 42 include but not limited to operating system, one or more application program, other program modules and
Program data may include the realization of network environment in each or certain combination in these examples.Program module 42 is usual
Execute the function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, the equipment interacted with the computer system/server 12 can be also enabled a user to one or more to be communicated, and/
Or with any equipment (example that the computer system/server 12 is communicated with one or more of the other computing device
Such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, it calculates
Machine equipment 12 can also pass through network adapter 20 and one or more network (such as LAN (Local Area
Network;Hereinafter referred to as:LAN), wide area network (Wide Area Network;Hereinafter referred to as:WAN) and/or public network, example
Such as internet) communication.As shown, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.It answers
When understanding, although not shown in the drawings, other hardware and/or software module can not used in conjunction with computer equipment 12, including but not
It is limited to:Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, to perform various functions application and
Data processing, such as realize the method referred in previous embodiment.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discuss suitable
Sequence, include according to involved function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system of such as computer based system including processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicating, propagating or passing
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium includes following:Electricity with one or more wiring
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can be for example by carrying out optical scanner to paper or other media, then into edlin, interpretation or when necessary with it
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be executed with storage
Or firmware is realized.Such as, if realized in another embodiment with hardware, following skill well known in the art can be used
Any one of art or their combination are realized:With for data-signal realize logic function logic gates from
Logic circuit is dissipated, the application-specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, which includes the steps that one or a combination set of embodiment of the method when being executed.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, it can also
That each unit physically exists alone, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and when sold or used as an independent product, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, change, replace and become within the scope of application
Type.
Claims (10)
1. a kind of text message method for pushing, which is characterized in that include the following steps:
Obtain candidate text message collection;
The candidate text message is calculated according to preset user interest point correlation model and text interest point correlation model to concentrate
The interest degree of correlation of each candidate's text message and the point of interest of target user;
Each candidate text message is calculated respectively as target text information according to preset interest coverage computation model
When text message push collection is added, the interest coverage of all target text information is concentrated in the text message push;
The scoring of push value is carried out to each candidate text message according to the interest degree of correlation and interest coverage, and will
The highest candidate text message of push value is stored in the text message push collection as target text information;
The interest covering is updated according to the interest coverage of the target text information of the newest deposit text message push collection
Spend the operational factor of computation model;
According to the preset user interest point correlation model, text interest point correlation model and the updated interest covering
Degree computation model carries out candidate text message concentration each remaining candidate text message the scoring of the push value, and
Using the highest candidate text message of push value as target text information deposit text message push collection;
Text message push collection is pushed to the target user.
2. the method as described in claim 1, which is characterized in that the interest coverage computation model is T matrixes, wherein institute
The formula for stating T matrixes is:
T=ealpha*count
Wherein, alpha is attenuation coefficient, and count is that the text message push concentrates the target text information being stored in each
A point of interest it is extensive after show number;
The interest coverage of the target text information according to the newest deposit text message push collection updates the interest
The operational factor of coverage computation model, including:
The T matrixes are updated according to the interest coverage of the target text information of the newest deposit text message push collection
In count.
3. the method as described in claim 1, which is characterized in that the mesh according to the newest deposit text message push collection
The interest coverage of mark text message updates the operational factor of the interest coverage computation model, further includes:
Obtain point of interest forgetting factor;
The operation in the interest coverage computation model is updated according to the point of interest forgetting factor and the interest coverage
The factor.
4. the method as described in claim 1, which is characterized in that described according to preset user interest point correlation model and text
This point of interest correlation model calculates the candidate text message and concentrates each candidate text message and the point of interest of target user
Before the interest degree of correlation, further include:
User information is obtained, interest level of the user to multiple points of interest is analyzed according to the user information, wherein the use
Family information includes one or more in search satisfaction feedback information, user's portrait information, user social contact information;
The user interest point correlation model is established to the interest level of multiple points of interest according to the user;
Text message is obtained, interest coverage of the text message to multiple points of interest is analyzed according to the text message;
The text interest point correlation model is established to the interest coverage of multiple points of interest according to the text message.
5. the method as described in claim 1, which is characterized in that described that text message push collection is pushed to the target
User, including:
Judge whether the target text information recommendation number that the text message push is concentrated reaches predetermined number;
If reaching the predetermined number, according to the sequencing that the target text information is stored into, generates text message and push away
List is recommended, and the text message recommendation list is pushed to the target user.
6. the method as described in claim 1, which is characterized in that described that text message push collection is pushed to the target
User, including:
Judge whether the candidate text message collection is empty;
If it is empty, then the target text information that text message push is concentrated is pushed to the target user.
7. a kind of text message pusher, which is characterized in that including:
Acquisition module, for obtaining candidate text message collection;
Computing module, for calculating the candidate according to preset user interest point correlation model and text interest point correlation model
Text message concentrates the interest degree of correlation of each candidate text message and the point of interest of target user;
The computing module is additionally operable to calculate each candidate text message point according to preset interest coverage computation model
Not Zuo Wei target text information when text message push collection is added, all target text information are concentrated in text message push
Interest coverage;
Processing module, for being pushed to each candidate text message according to the interest degree of correlation and interest coverage
The scoring of value, and using the highest candidate text message of push value as target text information deposit text message push collection;
Update module, the interest coverage for the target text information according to the newest deposit text message push collection update
The operational factor of the interest coverage computation model;
The processing module, be additionally operable to according to the preset user interest point correlation model, text interest point correlation model and
The updated interest coverage computation model to the candidate text message concentrate each remaining candidate text message into
The scoring of the row push value, and the highest candidate text message of push value is stored in text envelope as target text information
Breath push collection;
Pushing module, for text message push collection to be pushed to the target user.
8. a kind of intelligent terminal, which is characterized in that including processor and memory;
Wherein, the processor can perform to run with described by reading the executable program code stored in the memory
The corresponding program of program code, for realizing the text message method for pushing as described in any in claim 1-6.
9. a kind of computer program product, which is characterized in that when the instruction processing unit in the computer program product executes
Realize the text message method for pushing as described in any in claim 1-6.
10. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the meter
The text message method for pushing as described in any in claim 1-6 is realized when calculation machine program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810286984.2A CN108491540B (en) | 2018-03-30 | 2018-03-30 | Text information pushing method and device and intelligent terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810286984.2A CN108491540B (en) | 2018-03-30 | 2018-03-30 | Text information pushing method and device and intelligent terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108491540A true CN108491540A (en) | 2018-09-04 |
CN108491540B CN108491540B (en) | 2022-02-22 |
Family
ID=63317786
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810286984.2A Active CN108491540B (en) | 2018-03-30 | 2018-03-30 | Text information pushing method and device and intelligent terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108491540B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134827A (en) * | 2019-03-28 | 2019-08-16 | 北京达佳互联信息技术有限公司 | A kind of determination method, apparatus, electronic equipment and storage medium for recommending video |
CN110866106A (en) * | 2019-10-10 | 2020-03-06 | 重庆金融资产交易所有限责任公司 | Text recommendation method and related equipment |
CN112163399A (en) * | 2020-10-12 | 2021-01-01 | 北京字跳网络技术有限公司 | Online document pushing method and device, electronic equipment and computer readable medium |
CN112256970A (en) * | 2020-10-28 | 2021-01-22 | 四川金熊猫新媒体有限公司 | News text pushing method, device, equipment and storage medium |
CN112633977A (en) * | 2020-12-22 | 2021-04-09 | 苏州斐波那契信息技术有限公司 | User behavior based scoring method, device computer equipment and storage medium |
CN113553421A (en) * | 2021-06-22 | 2021-10-26 | 北京百度网讯科技有限公司 | Comment text generation method and device, electronic equipment and storage medium |
CN117708439A (en) * | 2024-02-06 | 2024-03-15 | 每日互动股份有限公司 | Target text pushing method, device, medium and equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030204588A1 (en) * | 2002-04-30 | 2003-10-30 | International Business Machines Corporation | System for monitoring process performance and generating diagnostic recommendations |
US20030204789A1 (en) * | 2002-04-30 | 2003-10-30 | International Business Machines Corporation | Method and apparatus for generating diagnostic recommendations for enhancing process performance |
CN102360364A (en) * | 2011-09-30 | 2012-02-22 | 奇智软件(北京)有限公司 | Automatic application recommendation method and device |
CN103440341A (en) * | 2013-09-09 | 2013-12-11 | 广州品唯软件有限公司 | Information recommendation method and device |
CN105045858A (en) * | 2015-07-10 | 2015-11-11 | 湖南科技大学 | Voting based taxi passenger-carrying point recommendation method |
CN105404680A (en) * | 2015-11-25 | 2016-03-16 | 百度在线网络技术(北京)有限公司 | Searching recommendation method and apparatus |
CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术(北京)有限公司 | Information recommendation method and device |
CN106407364A (en) * | 2016-09-08 | 2017-02-15 | 北京百度网讯科技有限公司 | Information recommendation method and apparatus based on artificial intelligence |
-
2018
- 2018-03-30 CN CN201810286984.2A patent/CN108491540B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030204588A1 (en) * | 2002-04-30 | 2003-10-30 | International Business Machines Corporation | System for monitoring process performance and generating diagnostic recommendations |
US20030204789A1 (en) * | 2002-04-30 | 2003-10-30 | International Business Machines Corporation | Method and apparatus for generating diagnostic recommendations for enhancing process performance |
CN102360364A (en) * | 2011-09-30 | 2012-02-22 | 奇智软件(北京)有限公司 | Automatic application recommendation method and device |
CN103440341A (en) * | 2013-09-09 | 2013-12-11 | 广州品唯软件有限公司 | Information recommendation method and device |
CN105045858A (en) * | 2015-07-10 | 2015-11-11 | 湖南科技大学 | Voting based taxi passenger-carrying point recommendation method |
CN105404680A (en) * | 2015-11-25 | 2016-03-16 | 百度在线网络技术(北京)有限公司 | Searching recommendation method and apparatus |
CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术(北京)有限公司 | Information recommendation method and device |
CN106407364A (en) * | 2016-09-08 | 2017-02-15 | 北京百度网讯科技有限公司 | Information recommendation method and apparatus based on artificial intelligence |
Non-Patent Citations (5)
Title |
---|
AKITO NISHITARUMIZU 等: "Improving a News Recommendation System in Adapting to Interests of a User with Storage of a Constant Size", 《2010 12TH INTERNATIONAL ASIA-PACIFIC WEB CONFERENCE》 * |
林一 等: "一种增强现实分场景推送情景感知服务的方法", 《软件学报》 * |
沈阳: "基于网络阅读行为兴趣度模型的网摘推荐", 《情报杂志》 * |
蒋晶晶: "基于抽象状态机的位置服务推荐模型的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
阴红志: "社会化媒体中若干时空相关的推荐问题研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134827A (en) * | 2019-03-28 | 2019-08-16 | 北京达佳互联信息技术有限公司 | A kind of determination method, apparatus, electronic equipment and storage medium for recommending video |
CN110134827B (en) * | 2019-03-28 | 2021-07-09 | 北京达佳互联信息技术有限公司 | Method and device for determining recommended video, electronic equipment and storage medium |
CN110866106A (en) * | 2019-10-10 | 2020-03-06 | 重庆金融资产交易所有限责任公司 | Text recommendation method and related equipment |
CN112163399A (en) * | 2020-10-12 | 2021-01-01 | 北京字跳网络技术有限公司 | Online document pushing method and device, electronic equipment and computer readable medium |
CN112256970A (en) * | 2020-10-28 | 2021-01-22 | 四川金熊猫新媒体有限公司 | News text pushing method, device, equipment and storage medium |
CN112633977A (en) * | 2020-12-22 | 2021-04-09 | 苏州斐波那契信息技术有限公司 | User behavior based scoring method, device computer equipment and storage medium |
CN113553421A (en) * | 2021-06-22 | 2021-10-26 | 北京百度网讯科技有限公司 | Comment text generation method and device, electronic equipment and storage medium |
CN113553421B (en) * | 2021-06-22 | 2023-05-05 | 北京百度网讯科技有限公司 | Comment text generation method and device, electronic equipment and storage medium |
CN117708439A (en) * | 2024-02-06 | 2024-03-15 | 每日互动股份有限公司 | Target text pushing method, device, medium and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108491540B (en) | 2022-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491540A (en) | Text message method for pushing, device and intelligent terminal | |
CN108108451A (en) | The group of subscribers portrait acquisition methods and device of group | |
CN105493057B (en) | The content selection controlled using accuracy | |
US9401097B2 (en) | Method and apparatus for providing emotion expression service using emotion expression identifier | |
CN107330023A (en) | Content of text based on focus recommends method and apparatus | |
CN108550068A (en) | A kind of individual commodity recommendation method and system based on user behavior analysis | |
CN101458703A (en) | Resizing tag representations or tag group representations to control relative importance | |
CN108090211A (en) | Hot news method for pushing and device | |
CN111782947B (en) | Search content display method and device, electronic equipment and storage medium | |
CN108563655A (en) | Text based event recognition method and device | |
CN111429163A (en) | Outdoor advertisement delivery resource recommendation method and device and computer equipment | |
CN109977322A (en) | Trip mode recommended method, device, computer equipment and readable storage medium storing program for executing | |
CN107992602A (en) | Search result methods of exhibiting and device | |
EP3701395A1 (en) | Recommending entities based on interest indicators | |
JP2017054214A (en) | Determination device, learning device, information distribution device, determination method, and determination program | |
US20150142584A1 (en) | Ranking content based on member propensities | |
CN108647273A (en) | It makes friends and recommends method and device | |
CN109255070A (en) | Recommendation information processing method, device, computer equipment and storage medium | |
CN110070140A (en) | Method and device is determined based on user's similitude of multi-class information | |
US11249945B2 (en) | Cognitive data descriptors | |
CN108345700A (en) | Article represents the choosing method, device and computer equipment of picture | |
JP2017201535A (en) | Determination device, learning device, determination method, and determination program | |
CN108804491A (en) | item recommendation method, device, computing device and storage medium | |
CN116401420A (en) | Searching method, device, medium and equipment based on multi-mode feature fusion | |
CN116226537A (en) | Layout and display method, device, equipment and medium of page modules in page |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |