CN106021577A - Information pushing method and device and electronic equipment - Google Patents
Information pushing method and device and electronic equipment Download PDFInfo
- Publication number
- CN106021577A CN106021577A CN201610380433.3A CN201610380433A CN106021577A CN 106021577 A CN106021577 A CN 106021577A CN 201610380433 A CN201610380433 A CN 201610380433A CN 106021577 A CN106021577 A CN 106021577A
- Authority
- CN
- China
- Prior art keywords
- time
- historical information
- degree
- staying
- title
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The embodiment of the invention discloses a method and a device for pushing information and electronic equipment, relates to an information pushing technology, and can improve the information pushing efficiency. The information pushing method comprises the following steps: acquiring the staying time of a target user for browsing each historical information title; calculating the average staying time of each historical information title browsed by each user, and obtaining the implicit interest degree of each historical information title of the target user based on the average staying time of each historical information title and the staying time of the target user; and sequentially extracting keywords in the historical information titles of N top ranked implicit interestingness, and pushing information in an information set to be pushed, which is matched with the extracted keywords, to the target user. The method and the device are suitable for recommending the news content.
Description
Technical field
The present invention relates to information advancing technique, particularly relate to a kind of method of pushed information, device and electronics and set
Standby.
Background technology
Society, increasing user uses electronic equipment, the information needed for being obtained by internet,
Such as, by mobile phone, carry out cyber journalism, humors and jokes etc. and read, to understand based on oneself interest
The various current events of hobby are dynamic, so as to alleviating life and operating pressure.
As a example by news, owing to news substantial amounts, the news type occurred every day is various, user is from so
The news of magnanimity finds the news meeting oneself hobby, requires a great deal of time, cause news
Browse efficiency is relatively low.The efficiency of news is browsed, in prior art, it is proposed that a kind of news in order to promote user
Method for pushing, by statistics each user access behavioral parameters to each news, such as, browsing histories, comments
Discuss, share, search behavior, point are praised, collection etc., by each user to each news access behavior application
In the news weights mathematical model pre-set, such as, content-based recommendation mathematical model, collaborative filtering
Mathematical model, Knowledge based engineering is recommended to recommend mathematical model, recommendation mathematical model based on network structure, group
Close and recommend mathematical model etc., thus obtain the weights of each news, and be ranked up according to weights, the row of choosing
The news of sequence top N, as news collection to be recommended；Then, by user behavior, such as, user couple
The click of news, browse, collect, the behavior such as comment is added up, obtain the behavior characteristics of user, calculate
The behavior characteristics of user concentrates the matching degree of each news with news to be recommended, chooses the news that matching degree is forward,
Push to this user, so that user avoids searching required news from magnanimity news, it is not necessary to flower
The expense lookup time just can obtain required news, improves user and browses efficiency and user's lifting of news
Browse the experience of news content.
But this news method for pushing, when calculating news weights, for calculating the access of news weights
The macroscopic view access behavior ginsengs such as behavioral parameters is browsing histories, comment on, share, search behavior, point are praised, collection
Number, does not considers that user browses the microcosmic such as the time of headline and accesses behavioral parameters, especially for work now
Work, life joint gather for nervous user, browse headline by taking some time, can know this
The approximate contents of news, thus, it is possible to without going again to browse this news content, and this factor is the most existing
Technology considers so that the news accessing behavioral parameters propelling movement based on macroscopic view may not be inconsistent with user's expection, thus
Making user not go to browse the news of propelling movement, cause the news pushed inefficient, relative users browses news
Efficiency relatively low；Further, a lot of users, after browsing news, do not carry out commenting on, share, point
Praise, the behavior such as collection, also making to access, based on macroscopic view, the news that behavioral parameters pushes may expect not with user
Symbol, reduces the efficiency pushing news.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method of pushed information, device and electronic equipment, energy
Enough promote the efficiency of pushed information, to solve in the method for existing pushed information, access behavior based on macroscopic view
The information that parameter pushes may not be inconsistent with user's expection, thus does not go to browse pushed information so that information pushing
Inefficient problem.
First aspect, the embodiment of the present invention provides a kind of method of pushed information, including:
Obtain targeted customer and browse the time of staying of each historical information title；
Calculate each user and browse the mean residence time of each historical information title；
Mean residence time based on each historical information title and the time of staying of described targeted customer,
To described targeted customer to hidden interest-degree in each historical information title；
Key word in the historical information title of hidden interest-degree sequence top N in extracting successively, to described target
User pushes the information that the information to be pushed matched with the key word extracted is concentrated.
In conjunction with first aspect, in the first embodiment of first aspect, described acquisition targeted customer browses
The time of staying of each historical information title includes:
Arrange with the message header page that one or more message headers are a page；
Record user is in the page time of staying of the described message header page, if described message header page bag
Containing a message header, the time of staying of acquisition is the described page time of staying, if the described message header page
Comprising multiple message header, the time of staying of acquisition is that the described page time of staying is divided by described message header page
The message header number comprised in face.
In conjunction with first aspect, in the second embodiment of first aspect, following formula is utilized to calculate described interior hidden
Interest-degree:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
IAjiFor jth user to hidden interest-degree in i-th historical information title.
In conjunction with first aspect, the first or the second embodiment of first aspect, in the 3rd of first aspect
Plant in embodiment, use at described mean residence time based on each historical information title and described target
The time of staying at family, obtain described targeted customer to hidden interest-degree in each historical information title before, institute
Method of stating also includes:
The number of words that statistical history message header comprises, calculates the individual character mean residence time of described targeted customer；
During the stop of described mean residence time based on each historical information title and described targeted customer
Between, obtain described targeted customer and hidden interest-degree in each historical information title included:
Calculate the time of staying business divided by mean residence time of a historical information title, hidden emerging in obtaining first
Interest degree；
Obtaining the first number of words that a described historical information title comprises, the individual character calculating described targeted customer is average
The time of staying and the product of the first number of words；
Calculate the time of staying business divided by described product of a described historical information title, hidden emerging in obtaining second
Interest degree；
Calculate in described first hidden interest-degree in hidden interest-degree and described second and value, obtain described target and use
Family is to hidden interest-degree in a described historical information title.
In conjunction with the third embodiment of first aspect, in the 4th kind of embodiment of first aspect, described
The individual character mean residence time of targeted customer includes: all individual character mean residence times of described targeted customer with
And list title individual character mean residence time, the number of words that described statistical history message header comprises, calculate described mesh
The individual character mean residence time of mark user includes:
Concentrate from the message header of statistics, extract a historical information title, add up a described historical information title
The number of words comprised, calculates described targeted customer and browses the time of staying of a described historical information title and described word
The business of number, obtains single title individual character mean residence time；
The historical information title quantity comprised according to described message header collection, calculates each single title individual character and averagely stops
Stay the meansigma methods of time, obtain all individual character mean residence times of described targeted customer.
Second aspect, the embodiment of the present invention provides the device of a kind of pushed information, including: the time of staying obtains
Module, mean residence time acquisition module, interior hidden interest-degree module and pushing module, wherein,
Time of staying acquisition module, browses the time of staying of each historical information title for obtaining targeted customer；
Mean residence time acquisition module, browses averagely stopping of each historical information title for calculating each user
Stay the time；
Interior hidden interest-degree module, for mean residence time based on each historical information title and described mesh
The time of staying of mark user, obtain described targeted customer to hidden interest-degree in each historical information title；
Pushing module, the key in the historical information title of hidden interest-degree sequence top N in extracting successively
Word, pushes, to described targeted customer, the information that the information to be pushed matched with the key word extracted is concentrated.
In conjunction with second aspect, in the first embodiment of second aspect, described time of staying acquisition module
Including: message header page setup unit and residence Time Calculation unit, wherein,
Message header page setup unit, is used for arranging the information so that one or more message headers are a page
Title page；
Residence Time Calculation unit, for recording user's page time of staying at the described message header page,
If the described message header page comprises a message header, the time of staying of acquisition is the described page time of staying,
If the described message header page comprises multiple message header, when the time of staying of acquisition is the stop of the described page
Between divided by the message header number comprised in the described message header page.
In conjunction with second aspect, in the second embodiment of second aspect, described interior hidden interest-degree module profit
With following formula calculate described interior hidden interest-degree:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
IAjiFor jth user to hidden interest-degree in i-th historical information title.
In conjunction with second aspect, the first or the second embodiment of second aspect, in the 3rd of second aspect
In kind of embodiment, described interior hidden interest-degree module includes: individual character mean residence time computing unit, first
In hidden interest-degree computing unit, individual character grand mean residence Time Calculation unit, hidden interest-degree calculates single in second
First and interior hidden interest-degree computing unit, wherein,
Individual character mean residence time computing unit, the number of words comprised for statistical history message header, calculate institute
State the individual character mean residence time of targeted customer；
Hidden interest-degree computing unit in first, for calculating the time of staying of a historical information title divided by averagely
The business of the time of staying, hidden interest-degree in obtaining first；
Individual character grand mean residence Time Calculation unit, is used for obtaining first that a described historical information title comprises
Number of words, calculates individual character mean residence time and the product of the first number of words of described targeted customer；
Hidden interest-degree computing unit in second, for calculate time of staying of a described historical information title divided by
The business of described product, hidden interest-degree in obtaining second；
Interior hidden interest-degree computing unit, hidden interest in hidden interest-degree and described second in being used for calculating described first
Degree and value, obtain described targeted customer to hidden interest-degree in a described historical information title.
In conjunction with the third embodiment of second aspect, in the 4th kind of embodiment of second aspect, described
Individual character mean residence time computing unit includes: all individual character mean residence time computation subunit and single mark
Topic individual character mean residence time computation subunit, wherein,
Single title individual character mean residence time computation subunit, for concentrating from the message header of statistics, extracts
One historical information title, adds up the number of words that a described historical information title comprises, calculates described targeted customer clear
Look at the time of staying of a described historical information title and the business of described number of words, obtain single title individual character and averagely stop
Time；
All individual character mean residence time computation subunit, for the history comprised according to described message header collection
Message header quantity, calculates the meansigma methods of each single title individual character mean residence time, obtains described targeted customer
All individual character mean residence times.
The third aspect, the embodiment of the present invention provides a kind of electronic equipment, and described electronic equipment includes: housing,
Processor, memorizer, circuit board and power circuit, wherein, circuit board is placed in the space that housing surrounds
Portion, processor and memorizer are arranged on circuit boards；Power circuit, for for each of above-mentioned electronic equipment
Circuit or device are powered；Memorizer is used for storing executable program code；Processor is by reading in memorizer
The executable program code of storage runs the program corresponding with executable program code, is used for performing aforementioned
The method of the pushed information described in.
A kind of method of pushed information, device and the electronic equipment that the embodiment of the present invention provides, by obtaining mesh
Mark user browses the time of staying of each historical information title；Calculate each user and browse each historical information title
Mean residence time, mean residence time based on each historical information title and described targeted customer's
The time of staying, obtain described targeted customer to hidden interest-degree in each historical information title；In extracting successively
Key word in the historical information title of hidden interest-degree sequence top N, pushes to described targeted customer and extracts
To the information concentrated of the information to be pushed that matches of key word, it is possible to promote the efficiency of pushed information, to solve
Certainly in the method for existing pushed information, the information accessing behavioral parameters propelling movement based on macroscopic view may be pre-with user
Phase is not inconsistent, thus does not go to browse pushed information so that the problem that information pushing is inefficient.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement
In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the method flow schematic diagram of embodiments of the invention one pushed information；
Fig. 2 is the apparatus structure schematic diagram of embodiments of the invention two pushed information；
Fig. 3 is the structural representation of one embodiment of electronic equipment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the embodiment of the present invention is described in detail.
It will be appreciated that described embodiment be only the present invention a part of embodiment rather than whole realities
Execute example.Based on the embodiment in the present invention, those of ordinary skill in the art are not before making creative work
Put all other embodiments obtained, broadly fall into the scope of protection of the invention.
Embodiment one
Fig. 1 is the method flow schematic diagram of embodiments of the invention one pushed information, as it is shown in figure 1, this reality
The method executing example may include that
Step 101, obtains targeted customer and browses the time of staying of each historical information title；
In the present embodiment, information is when being presented on screen by electronic equipment, even if for the ease of user slightly
Slightly understanding information content, each information is both provided with a message header, user when browsing message header, base
In the hobby of oneself, different message headers has the different time of staying.Such as, user is felt
The message header of interest, has the longer time of staying, and for uninterested message header, during stop
Between can shorter, user's time of staying length when browsing message header, can intuitively react user to such
The interest of type information, thus, in the present embodiment, it is considered to by the time of staying of user's browsing histories message header
As user to the interest index potential to type information.
In the present embodiment, as an alternative embodiment, information includes but not limited to: news, make laughs, science and technology,
Health preserving etc..
In the present embodiment, as an alternative embodiment, described acquisition targeted customer browses each historical information mark
The time of staying of topic includes:
A11, is arranged with the message header page that one or more message headers are a page；
A12, record user is in the page time of staying of the described message header page, if described message header page
Bread contains a message header, and the time of staying of acquisition is the described page time of staying, if described message header
The page comprises multiple message header, and the time of staying of acquisition is that the described page time of staying is divided by described information mark
The message header number comprised in the topic page.
In the present embodiment, user, in the page time of staying of the message header page, can be from this message header
Page open is to the pent time, it is also possible to be to this message header page from this message header page open
It is switched to the time of out of Memory title page, it is also possible to be to produce from this message header page open to user
Time during raw sliding operation.
Step 102, calculates each user and browses the mean residence time of each historical information title；
Step 103, mean residence time based on each historical information title and the stop of described targeted customer
Time, obtain described targeted customer to hidden interest-degree in each historical information title；
In the present embodiment, as an alternative embodiment, following formula is utilized to calculate the average stop of historical information title
Time:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
N is the number of users browsing i-th historical information title.
As an alternative embodiment, hidden interest-degree in utilizing following formula to calculate:
In formula,
IAjiFor jth user to hidden interest-degree in i-th historical information title.
In the present embodiment, owing to the user of different age group is when the same message header of normal browsing, required
Time has larger difference, and such as, the time needed for Children Normal browses message header is noticeably greater than adult,
Thus, as another alternative embodiment, it is also possible to user was classified according to the age, according to targeted customer
Affiliated character classification by age, each user adding up this character classification by age browses the average stop of each historical information title
Time.
In the present embodiment, such as, as a example by headline, the number of users if carried out statistics is 2, user A
Browsing four headline of numbered x1, x2, x3, x4, wherein, user A is in the time of staying of x1
For the time of staying tail 1000ms of 1100ms, x2, the time of staying of x3 is the time of staying of 900ms, x4
For 1400ms.
User B is stopping of 1700ms, x3 in the time of staying that the time of staying is 1600ms, x2 at x1
The time of staying staying the time to be 1200ms, x4 is 1800ms.Then:
The mean residence time that each user browses each headline is as follows:
According to hidden interest-degree computing formula in above-mentioned, interior hidden interest-degree result of calculation is as follows:
User A is 0.8148 to interest-degree hidden in x1；
User A is 0.7407 to interest-degree hidden in x2；
User A is 0.8571 to interest-degree hidden in x3；
User A is 0.8750 to interest-degree hidden in x4；
User B is 1.1852 to interest-degree hidden in x1；
User B is 1.2593 to interest-degree hidden in x2；
User B is 1.1429 to interest-degree hidden in x3；
User B is 1.1250 to interest-degree hidden in x4.
In the present embodiment, user is the highest to interest-degree hidden in a certain message header, shows that user browses this letter
The breath time used by title is the longest, more pays close attention to this category information.
In the present embodiment, in order to promote each user data (time of staying) for calculating mean residence time
Reliability, as an alternative embodiment, browse the flat of each historical information title each user of described calculating
All after the time of staying, mean residence time based on each historical information title and described targeted customer's
Before the time of staying, the method also includes:
Calculate the mean square deviation browsing each historical information title, if a certain user's browsing histories message header
The time of staying is more than 3 times of described mean square deviations with the error of mean residence time, deletes described a certain user and browses
The time of staying of historical information title, perform each user of described calculating and browse the average of each historical information title
The step of the time of staying.
In the present embodiment, if the time of staying of each user's browsing histories message header and mean residence time
Error be not more than 3 times of described mean square deviations, perform each user of described calculating and browse each historical information title
The step of mean residence time.
In the present embodiment, owing to the number of words comprised in each message header is inconsistent, if a certain user browses two
Message header institute's time spent is the same, but first information title comprises 10 words, and the second message header comprises
20 words, it is clear that in the case of this class of subscriber is identical, this user concern to first information title
Degree is higher than the attention rate to the second message header.Thus, as an alternative embodiment, based on each user
Time different of reading ability institute browsing histories message header, in described calculating, each user browses each
The mean residence time of historical information title, mean residence time based on each historical information title and institute
Before the time of staying stating targeted customer, the method also includes:
The number of words that statistical history message header comprises, calculates the individual character mean residence time of described targeted customer.
In the present embodiment, individual character mean residence time includes: all individual characters of described targeted customer averagely stop
Time and single title individual character mean residence time, wherein, all individual characters of described targeted customer averagely stop
Time is that this user browses in the total number of word that all historical information titles are corresponding, each word corresponding when browsing
Between；Single title individual character mean residence time is that every word that user browses a historical information title corresponding averagely stops
Time.
As an alternative embodiment, the number of words that described statistical history message header comprises, calculate described target and use
The individual character mean residence time at family includes:
B11, concentrates from the message header of statistics, extracts a historical information title, add up a described historical information
The number of words that title comprises, calculates described targeted customer and browses the time of staying and the institute of a described historical information title
State the business of number of words, obtain single title individual character mean residence time；
B12, the historical information title quantity comprised according to described message header collection, calculate each single title individual character and put down
All the meansigma methods of the time of staying, obtains described target all individual characters mean residence time.
As another alternative embodiment, the number of words that described statistical history message header comprises, calculate described target
The individual character mean residence time of user includes:
Concentrate from the message header of statistics, extract a historical information title, add up a described historical information title
The number of words comprised, calculates described targeted customer and browses the time of staying of a described historical information title and described word
The business of number, obtains single title individual character mean residence time that a described historical information title is corresponding.
In the present embodiment, as an alternative embodiment, described average stop based on each historical information title
Time and the time of staying of described targeted customer, obtain described targeted customer to each historical information title
Interior hidden interest-degree includes:
C11, calculates the time of staying business divided by mean residence time of a historical information title, in obtaining first
Hidden interest-degree；
C12, obtains the first number of words that a described historical information title comprises, calculates the individual character of described targeted customer
Mean residence time and the product of the first number of words；
C13, calculates the time of staying business divided by described product of a described historical information title, in obtaining second
Hidden interest-degree；
C14, calculate in described first hidden interest-degree in hidden interest-degree and described second and value, obtain described mesh
Mark user is to hidden interest-degree in a described historical information title.
In the present embodiment, as a example by above-mentioned, targeted customer includes user A and user B, if x1, x2,
The number of words that x3, x4 comprise is respectively 5,10,15,20, and all individual characters of calculated each user are average
The time of staying is as follows:
All individual character mean residence times of user A:
TpA=(1100ms/5+1000ms/10+900ms/15+1400ms/20)/4=112.5ms/ word；
All individual character mean residence times of user B:
TpB=(1600ms/5+1700ms/10+1200ms/15+1800ms/20)/4=165ms/ word.
The most calculated targeted customer is as follows to hidden interest-degree in a described historical information title:
User A is to interest-degree=1100/1350+1100/ (5*112.5)=2.7704 hidden in x1；
User A is to interest-degree=1000/1350+1000/ (10*112.5)=1.6300 hidden in x2；
User A is to interest-degree=900/1050+900/ (15*112.5)=1.3905 hidden in x3；
User A is to interest-degree=1400/1600+1400/ (20*112.5)=1.4972 hidden in x4；
User B is to interest-degree=1600/1350+1600/ (5*165)=3.1246 hidden in x1；
User B is to interest-degree=1700/1350+1700/ (10*165)=2.2896 hidden in x2；
User B is to interest-degree=1200/1050+1200/ (15*165)=1.6277 hidden in x3；
User B is to interest-degree=1800/1600+1800/ (20*165)=1.6705 hidden in x4.
As another alternative embodiment, described mean residence time based on each historical information title and institute
State the time of staying of targeted customer, obtain described targeted customer to hidden interest-degree in each historical information title
Including:
D11, calculates the time of staying business divided by mean residence time of a historical information title, in obtaining first
Hidden interest-degree；
D12, hidden emerging in calculating the individual character mean residence time and described first that a described historical information title is corresponding
Interest degree and value, obtain described targeted customer to hidden interest-degree in a described historical information title.
Step 104, the key word in the historical information title of hidden interest-degree sequence top N in extracting successively,
The information that the information to be pushed matched with the key word extracted is concentrated is pushed to described targeted customer.
In the present embodiment, as an alternative embodiment, information to be pushed collection can use art methods to obtain
Take, such as, by statistics each user access behavioral parameters to each news, such as, browsing histories, comment
Discuss, share, search behavior, point are praised, collection etc., by each user to each news access behavior application
In the news weights mathematical model pre-set, such as, content-based recommendation mathematical model, collaborative filtering
Mathematical model, Knowledge based engineering is recommended to recommend mathematical model, recommendation mathematical model based on network structure, group
Close and recommend mathematical model etc., thus obtain the weights of each news, and be ranked up according to weights, the row of choosing
The news of sequence top N, as primary election news collection；Then, by user behavior, such as, user is to newly
The click heard, browse, collect, the behavior such as comment is added up, obtain the behavior characteristics of user, calculate and use
The behavior characteristics at family concentrates the matching degree of each news with primary election news, chooses the news that matching degree is forward,
Collect to news to be pushed (information).As another alternative embodiment, information to be pushed collection can also be by respectively
Operator is committed to the information composition of push server, and this is not construed as limiting by the present embodiment.
In the present embodiment, as an alternative embodiment, can be by hidden interest-degree sequence top N in extracting
Historical information title in a historical information title, extract each history keyword that this historical information title comprises
Word, then extract message header corresponding to an information that information to be pushed is concentrated comprises respectively push key word,
According to the matching degree algorithm pre-set, calculate the matching degree of each history keyword word and each propelling movement key word, as
The most calculated matching degree exceedes the matching degree threshold value pre-set, then the message header by extraction is corresponding
Information pushes to targeted customer；If calculated matching degree is not less than the matching degree threshold value pre-set,
Then concentrate from information to be pushed and extract next information, until the information that information to be pushed is concentrated is extracted complete.
Then, next historical information title in the historical information title of hidden interest-degree sequence top N in extracting.
The method of the embodiment of the present invention one pushed information, browses each historical information mark by obtaining targeted customer
The time of staying of topic；Calculate each user and browse the mean residence time of each historical information title, based on each
The mean residence time of historical information title and the time of staying of described targeted customer, obtain described target and use
Family is to hidden interest-degree in each historical information title；The history of hidden interest-degree sequence top N in extracting successively
Key word in message header, pushes to described targeted customer and waiting of matching of the key word extracted pushes
The information that information is concentrated.So, when carrying out information pushing, it is considered to when user browses the stop of message header
Between wait microcosmic access behavioral parameters, as auxiliary characteristics or the index of user interest degree so that the information of propelling movement
More can meet targeted customer's expection, thus promote the information efficiency of propelling movement, the information of propelling movement is browsed by user
Probability increases, and enhances user and browses the efficiency of information；Further, due to based on browsing message header
The interior hidden interest-degree of residence Time Calculation can characterize user's interest to information, even if user is browsing information
After do not carry out commenting on, share, the behavior such as point is praised, collection, the information pushed and user also can be made to expect kiss
Right height, the information browse improving user is experienced.
Embodiment two
Fig. 2 is the apparatus structure schematic diagram of embodiments of the invention two pushed information, as in figure 2 it is shown, this reality
Execute the device of example and may include that time of staying acquisition module 21, mean residence time acquisition module 22, interior hidden
Interest-degree module 23 and pushing module 24, wherein,
Time of staying acquisition module 21, during for obtaining stop that targeted customer browses each historical information title
Between；
In the present embodiment, as an alternative embodiment, information includes but not limited to: news, make laughs, science and technology,
Health preserving etc..
In the present embodiment, as an alternative embodiment, time of staying acquisition module 21 includes: message header page
Face arranges unit and residence Time Calculation unit (not shown), wherein,
Message header page setup unit, is used for arranging the information so that one or more message headers are a page
Title page；
Residence Time Calculation unit, for recording user's page time of staying at the described message header page,
If the described message header page comprises a message header, the time of staying of acquisition is the described page time of staying,
If the described message header page comprises multiple message header, when the time of staying of acquisition is the stop of the described page
Between divided by the message header number comprised in the described message header page.
Mean residence time acquisition module 22, browses the average of each historical information title for calculating each user
The time of staying；
In the present embodiment, as an alternative embodiment, following formula is utilized to calculate the average stop of historical information title
Time:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
N is the number of users browsing i-th historical information title.
As another alternative embodiment, it is also possible to user was classified according to the age, according to targeted customer institute
The character classification by age belonged to, each user adding up this character classification by age browses when averagely stopping of each historical information title
Between.
As an alternative embodiment, browse the mean residence time of each historical information title each user of calculating,
Before the time of staying of mean residence time based on each historical information title and described targeted customer, flat
All time of staying acquisition modules can be also used for calculating the mean square deviation browsing each historical information title, if certain
The time of staying of one user's browsing histories message header is described mean square more than 3 times with the error of mean residence time
Difference, deletes the time of staying of described a certain user's browsing histories message header, calculates each user and browse each going through
The mean residence time of history message header.
In hidden interest-degree module 23, for mean residence time based on each historical information title and described
The time of staying of targeted customer, obtain described targeted customer to hidden interest-degree in each historical information title；
In the present embodiment, as an alternative embodiment, utilize following formula calculate described interior hidden interest-degree:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
IAjiFor jth user to hidden interest-degree in i-th historical information title.
In the present embodiment, as an alternative embodiment, interior hidden interest-degree module 23 includes: individual character averagely stops
Time calculating unit, hidden interest-degree computing unit in first, individual character grand mean residence Time Calculation unit,
Hidden interest-degree computing unit and interior hidden interest-degree computing unit (not shown) in two, wherein,
Individual character mean residence time computing unit, the number of words comprised for statistical history message header, calculate institute
State the individual character mean residence time of targeted customer；
In the present embodiment, as an alternative embodiment, individual character mean residence time computing unit includes: all
Individual character mean residence time computation subunit and single title individual character mean residence time computation subunit, wherein,
Single title individual character mean residence time computation subunit, for concentrating from the message header of statistics, extracts
One historical information title, adds up the number of words that a described historical information title comprises, calculates described targeted customer's
User browses the time of staying of a described historical information title and the business of described number of words, obtains single title individual character and puts down
All time of staying；
All individual character mean residence time computation subunit, for the history comprised according to described message header collection
Message header quantity, calculates the meansigma methods of each single title individual character mean residence time, obtains described targeted customer
All individual character mean residence times.
Hidden interest-degree computing unit in first, for calculating the time of staying of a historical information title divided by averagely
The business of the time of staying, hidden interest-degree in obtaining first；
Individual character grand mean residence Time Calculation unit, is used for obtaining first that a described historical information title comprises
Number of words, calculates individual character mean residence time and the product of the first number of words of described targeted customer；
Hidden interest-degree computing unit in second, for calculate time of staying of a described historical information title divided by
The business of described product, hidden interest-degree in obtaining second；
Interior hidden interest-degree computing unit, hidden interest in hidden interest-degree and described second in being used for calculating described first
Degree and value, obtain described targeted customer to hidden interest-degree in a described historical information title.
Pushing module 24, the pass in the historical information title of hidden interest-degree sequence top N in extracting successively
Keyword, pushes, to described targeted customer, the information that the information to be pushed matched with the key word extracted is concentrated.
The device of the present embodiment, may be used for performing the technical scheme of embodiment of the method shown in Fig. 1, and it realizes
Principle is similar with technique effect, and here is omitted.
It should be noted that in this article, the relational terms of such as first and second or the like be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply these
Relation or the order of any this reality is there is between entity or operation.And, term " includes ", " bag
Contain " or its any other variant be intended to comprising of nonexcludability, so that include a series of key element
Process, method, article or equipment not only include those key elements, but also include being not expressly set out
Other key elements, or also include the key element intrinsic for this process, method, article or equipment.?
In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that at bag
Include and the process of described key element, method, article or equipment there is also other identical element.
Each embodiment in this specification all uses relevant mode to describe, phase homophase between each embodiment
As part see mutually, what each embodiment stressed is the difference with other embodiments.
For device embodiment, owing to it is substantially similar to embodiment of the method, so describe
Fairly simple, relevant part sees the part of embodiment of the method and illustrates.
Represent in flow charts or the logic described otherwise above at this and/or step, for example, it is possible to recognized
For being the sequencing list of executable instruction for realizing logic function, may be embodied in any computer
In computer-readable recording medium, (such as computer based system, include place for instruction execution system, device or equipment
The reason system of device or other can be from instruction execution system, device or equipment instruction fetch the system performing instruction)
Use, or combine these instruction execution systems, device or equipment and use.For the purpose of this specification, " calculate
Machine computer-readable recording medium " can be any can to comprise, store, communicate, propagate or transmission procedure performs for instruction
System, device or equipment or combine these instruction execution systems, device or equipment and the device that uses.Calculate
The more specifically example (non-exhaustive list) of machine computer-readable recording medium includes following: have one or more wiring
Electrical connection section (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM),
Read only memory (ROM), erasable edits read only memory (EPROM or flash memory), light
Fine device, and portable optic disk read only memory (CDROM).It addition, computer-readable medium is even
Can be paper or other the suitable media that can print described program thereon, because can be such as by paper
Or other media carry out optical scanning, then carry out editing, interpret or carrying out with other suitable methods if desired
Process and electronically obtain described program, be then stored in computer storage.
Should be appreciated that each several part of the present invention can realize by hardware, software, firmware or combinations thereof.
In the above-described embodiment, multiple steps or method can be with storing in memory and by suitably referring to
Software that execution system performs or firmware is made to realize.Such as, if realized with hardware and real at another
As executing in mode, can realize by any one in following technology well known in the art or their combination:
There is the discrete logic of logic gates for data signal realizes logic function, have suitably
The special IC of combination logic gate circuit, programmable gate array (PGA), field programmable gate array
(FPGA) etc..
The embodiment of the present invention also provides for a kind of electronic equipment, and described electronic equipment comprises aforementioned any embodiment institute
The device stated.
Fig. 3 is the structural representation of one embodiment of electronic equipment of the present invention, it is possible to achieve Fig. 1-2 of the present invention
The flow process of illustrated embodiment, as it is shown on figure 3, above-mentioned electronic equipment may include that housing 31, processor 32,
Memorizer 33, circuit board 34 and power circuit 35, wherein, circuit board 34 is placed in what housing 31 surrounded
Interior volume, processor 32 and memorizer 33 are arranged on circuit board 34；Power circuit 35, for for
Each circuit or the device of stating electronic equipment are powered；Memorizer 33 is used for storing executable program code；Process
Device 32 runs and executable program code pair by reading the executable program code of storage in memorizer 33
The program answered, for the method performing the pushed information described in aforementioned any embodiment.
Processor 32 to concrete process and the processor 32 of performing of above-mentioned steps by running executable program
The step that code performs further, may refer to the description of Fig. 1-2 illustrated embodiment of the present invention, at this no longer
Repeat.
This electronic equipment exists in a variety of forms, includes but not limited to:
(1) mobile communication equipment: the feature of this kind equipment is to possess mobile communication function, and with provide speech,
Data communication is main target.This Terminal Type includes: smart mobile phone (such as iPhone), multimedia handset,
Functional mobile phone, and low-end mobile phone etc..
(2) super mobile personal computer equipment: this kind equipment belongs to the category of personal computer, has calculating and place
Reason function, the most also possesses mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC set
Standby etc., such as iPad.
(3) portable entertainment device: this kind equipment can show and play content of multimedia.This kind equipment includes:
Audio frequency, video player (such as iPod), handheld device, e-book, and intelligent toy and portable
In-vehicle navigation apparatus.
(4) server: provide calculate service equipment, the composition of server include processor, hard disk, internal memory,
System bus etc., server is similar with general computer architecture, but owing to needing to provide highly reliable clothes
Business, therefore at aspects such as disposal ability, stability, reliability, safety, extensibility, manageabilitys
Require higher.
(5) other have the electronic equipment of data interaction function.
Those skilled in the art are appreciated that and realize the whole or portion that above-described embodiment method is carried
The program that can be by step by step completes to instruct relevant hardware, and described program can be stored in a kind of meter
In calculation machine readable storage medium storing program for executing, this program upon execution, including one or a combination set of the step of embodiment of the method.
For convenience of description, describing apparatus above is to be divided into various units/modules to be respectively described with function.When
So, can be the function of each unit/module in same or multiple softwares and/or hardware when implementing the present invention
Realize.
As seen through the above description of the embodiments, those skilled in the art is it can be understood that arrive this
Invention can add the mode of required general hardware platform by software and realize.Based on such understanding,
The part that prior art is contributed by technical scheme the most in other words can be with software product
Form embodies, and this computer software product can be stored in storage medium, such as ROM/RAM, magnetic
Dish, CD etc., including some instructions with so that a computer equipment (can be personal computer, take
Business device, or the network equipment etc.) perform described in some part of each embodiment of the present invention or embodiment
Method.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited to
This, any those familiar with the art, in the technical scope that the invention discloses, can readily occur in
Change or replacement, all should contain within protection scope of the present invention.Therefore, protection scope of the present invention
Should be as the criterion with scope of the claims.
Claims (10)
1. the method for a pushed information, it is characterised in that including:
Obtain targeted customer and browse the time of staying of each historical information title；
Calculate each user and browse the mean residence time of each historical information title；
Mean residence time based on each historical information title and the time of staying of described targeted customer,
To described targeted customer to hidden interest-degree in each historical information title；
Key word in the historical information title of hidden interest-degree sequence top N in extracting successively, to described target
User pushes the information that the information to be pushed matched with the key word extracted is concentrated.
The method of pushed information the most according to claim 1, it is characterised in that described acquisition target is used
Family browses the time of staying of each historical information title and includes:
Arrange with the message header page that one or more message headers are a page；
Record user is in the page time of staying of the described message header page, if described message header page bag
Containing a message header, the time of staying of acquisition is the described page time of staying, if the described message header page
Comprising multiple message header, the time of staying of acquisition is that the described page time of staying is divided by described message header page
The message header number comprised in face.
The method of pushed information the most according to claim 1, it is characterised in that utilize following formula to calculate institute
State interior hidden interest-degree:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
IAjiFor jth user to hidden interest-degree in i-th historical information title.
4. according to the method for the pushed information described in any one of claims 1 to 3, it is characterised in that in institute
State mean residence time based on each historical information title and the time of staying of described targeted customer, obtain
Before described targeted customer is to hidden interest-degree in each historical information title, described method also includes:
The number of words that statistical history message header comprises, calculates the individual character mean residence time of described targeted customer；
During the stop of described mean residence time based on each historical information title and described targeted customer
Between, obtain described targeted customer and hidden interest-degree in each historical information title included:
Calculate the time of staying business divided by mean residence time of a historical information title, hidden emerging in obtaining first
Interest degree；
Obtaining the first number of words that a described historical information title comprises, the individual character calculating described targeted customer is average
The time of staying and the product of the first number of words；
Calculate the time of staying business divided by described product of a described historical information title, hidden emerging in obtaining second
Interest degree；
Calculate in described first hidden interest-degree in hidden interest-degree and described second and value, obtain described target and use
Family is to hidden interest-degree in a described historical information title.
The method of pushed information the most according to claim 4, it is characterised in that described targeted customer's
Individual character mean residence time includes: all individual character mean residence times of described targeted customer and single title list
Word mean residence time, the number of words that described statistical history message header comprises, calculate the list of described targeted customer
Word mean residence time includes:
Concentrate from the message header of statistics, extract a historical information title, add up a described historical information title
The number of words comprised, calculates described targeted customer and browses the time of staying of a described historical information title and described word
The business of number, obtains single title individual character mean residence time；
The historical information title quantity comprised according to described message header collection, calculates each single title individual character and averagely stops
Stay the meansigma methods of time, obtain all individual character mean residence times of described targeted customer.
6. the device of a pushed information, it is characterised in that including: time of staying acquisition module, averagely stop
Stay time-obtaining module, interior hidden interest-degree module and pushing module, wherein,
Time of staying acquisition module, browses the time of staying of each historical information title for obtaining targeted customer；
Mean residence time acquisition module, browses averagely stopping of each historical information title for calculating each user
Stay the time；
Interior hidden interest-degree module, for mean residence time based on each historical information title and described mesh
The time of staying of mark user, obtain described targeted customer to hidden interest-degree in each historical information title；
Pushing module, the key in the historical information title of hidden interest-degree sequence top N in extracting successively
Word, pushes, to described targeted customer, the information that the information to be pushed matched with the key word extracted is concentrated.
The device of pushed information the most according to claim 6, it is characterised in that the described time of staying is obtained
Delivery block includes: message header page setup unit and residence Time Calculation unit, wherein,
Message header page setup unit, is used for arranging the information so that one or more message headers are a page
Title page；
Residence Time Calculation unit, for recording user's page time of staying at the described message header page,
If the described message header page comprises a message header, the time of staying of acquisition is the described page time of staying,
If the described message header page comprises multiple message header, when the time of staying of acquisition is the stop of the described page
Between divided by the message header number comprised in the described message header page.
The device of pushed information the most according to claim 5, it is characterised in that described interior hidden interest-degree
Module utilize following formula calculate described interior hidden interest-degree:
In formula,
TiMean residence time for i-th historical information title；
TjiThe time of staying of i-th historical information title is browsed for jth user；
IAjiFor jth user to hidden interest-degree in i-th historical information title.
9. according to the device of the pushed information described in any one of claim 6 to 8, it is characterised in that described
In hidden interest-degree module include: individual character mean residence time computing unit, hidden interest-degree computing unit in first,
Individual character grand mean residence Time Calculation unit, hidden interest-degree computing unit and interior hidden interest-degree calculate in second
Unit, wherein,
Individual character mean residence time computing unit, the number of words comprised for statistical history message header, calculate institute
State the individual character mean residence time of targeted customer；
Hidden interest-degree computing unit in first, for calculating the time of staying of a historical information title divided by averagely
The business of the time of staying, hidden interest-degree in obtaining first；
Individual character grand mean residence Time Calculation unit, is used for obtaining first that a described historical information title comprises
Number of words, calculates individual character mean residence time and the product of the first number of words of described targeted customer；
Hidden interest-degree computing unit in second, for calculate time of staying of a described historical information title divided by
The business of described product, hidden interest-degree in obtaining second；
Interior hidden interest-degree computing unit, hidden interest in hidden interest-degree and described second in being used for calculating described first
Degree and value, obtain described targeted customer to hidden interest-degree in a described historical information title.
10. an electronic equipment, it is characterised in that described electronic equipment includes: housing, processor, deposit
Reservoir, circuit board and power circuit, wherein, circuit board is placed in the interior volume that housing surrounds, processor
Arrange on circuit boards with memorizer；Power circuit, is used for each circuit for above-mentioned electronic equipment or device
Power supply；Memorizer is used for storing executable program code；Processor is by holding of storing in reading memorizer
Line program code runs the program corresponding with executable program code, is used for performing aforementioned any claim
The method of the pushed information described in 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610380433.3A CN106021577B (en) | 2016-06-01 | 2016-06-01 | Information pushing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610380433.3A CN106021577B (en) | 2016-06-01 | 2016-06-01 | Information pushing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106021577A true CN106021577A (en) | 2016-10-12 |
| CN106021577B CN106021577B (en) | 2019-07-23 |
Family
ID=57092826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610380433.3A Expired - Fee Related CN106021577B (en) | 2016-06-01 | 2016-06-01 | Information pushing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106021577B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844401A (en) * | 2017-11-07 | 2018-03-27 | 广州品唯软件有限公司 | Data monitoring method, device and computer-readable storage medium |
| CN109165974A (en) * | 2018-08-06 | 2019-01-08 | 深圳乐信软件技术有限公司 | A kind of commercial product recommending model training method, device, equipment and storage medium |
| CN109815409A (en) * | 2019-02-02 | 2019-05-28 | 北京七鑫易维信息技术有限公司 | A kind of method for pushing of information, device, wearable device and storage medium |
| CN110110203A (en) * | 2018-01-11 | 2019-08-09 | 腾讯科技（深圳）有限公司 | Resource information method for pushing and server, resource information methods of exhibiting and terminal |
| CN110889031A (en) * | 2018-09-06 | 2020-03-17 | 北京奇元科技有限公司 | Recommended content display method and device |
| CN111046222A (en) * | 2019-04-29 | 2020-04-21 | 广东小天才科技有限公司 | Dictation list generation method and electronic equipment |
| WO2020088058A1 (en) * | 2018-10-31 | 2020-05-07 | 北京字节跳动网络技术有限公司 | Information generating method and device |
| WO2020088050A1 (en) * | 2018-10-31 | 2020-05-07 | 北京字节跳动网络技术有限公司 | Information generation method and device |
| CN112287221A (en) * | 2020-10-29 | 2021-01-29 | 恒瑞通（福建）信息技术有限公司 | Government affair information differentiation disclosure method, electronic device and storage medium |
| CN112764855A (en) * | 2021-01-20 | 2021-05-07 | 恒瑞通（福建）信息技术有限公司 | Block chain based government affair information automatic display method, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| US8442973B2 (en) * | 2006-05-02 | 2013-05-14 | Surf Canyon, Inc. | Real time implicit user modeling for personalized search |
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| CN104636406A (en) * | 2013-11-15 | 2015-05-20 | 华为技术有限公司 | Method and device for pushing information according to user behaviors |
-
2016
- 2016-06-01 CN CN201610380433.3A patent/CN106021577B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8442973B2 (en) * | 2006-05-02 | 2013-05-14 | Surf Canyon, Inc. | Real time implicit user modeling for personalized search |
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| CN104636406A (en) * | 2013-11-15 | 2015-05-20 | 华为技术有限公司 | Method and device for pushing information according to user behaviors |
Non-Patent Citations (1)
| Title |
|---|
| 南智敏 等: "网页兴趣度度量方法及其在兴趣模型中的应用研究", 《微型电脑应用》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844401A (en) * | 2017-11-07 | 2018-03-27 | 广州品唯软件有限公司 | Data monitoring method, device and computer-readable storage medium |
| CN110110203A (en) * | 2018-01-11 | 2019-08-09 | 腾讯科技（深圳）有限公司 | Resource information method for pushing and server, resource information methods of exhibiting and terminal |
| CN110110203B (en) * | 2018-01-11 | 2023-04-28 | 腾讯科技（深圳）有限公司 | Resource information pushing method, server, resource information display method and terminal |
| CN109165974A (en) * | 2018-08-06 | 2019-01-08 | 深圳乐信软件技术有限公司 | A kind of commercial product recommending model training method, device, equipment and storage medium |
| CN110889031A (en) * | 2018-09-06 | 2020-03-17 | 北京奇元科技有限公司 | Recommended content display method and device |
| WO2020088058A1 (en) * | 2018-10-31 | 2020-05-07 | 北京字节跳动网络技术有限公司 | Information generating method and device |
| WO2020088050A1 (en) * | 2018-10-31 | 2020-05-07 | 北京字节跳动网络技术有限公司 | Information generation method and device |
| CN109815409A (en) * | 2019-02-02 | 2019-05-28 | 北京七鑫易维信息技术有限公司 | A kind of method for pushing of information, device, wearable device and storage medium |
| CN111046222A (en) * | 2019-04-29 | 2020-04-21 | 广东小天才科技有限公司 | Dictation list generation method and electronic equipment |
| CN112287221A (en) * | 2020-10-29 | 2021-01-29 | 恒瑞通（福建）信息技术有限公司 | Government affair information differentiation disclosure method, electronic device and storage medium |
| CN112764855A (en) * | 2021-01-20 | 2021-05-07 | 恒瑞通（福建）信息技术有限公司 | Block chain based government affair information automatic display method, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106021577B (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106021577A (en) | Information pushing method and device and electronic equipment | |
| Takagi | Analysis of polling systems | |
| CN101984423B (en) | Hot-search word generation method and system | |
| CN103258000B (en) | Method and device for clustering high-frequency keywords in webpages | |
| CN103020845A (en) | Mobile application pushing method and system | |
| Gupta et al. | An overview of social tagging and applications | |
| CN104462113A (en) | Search method and device and electronic equipment | |
| US20150205580A1 (en) | Method and System for Sorting Online Videos of a Search | |
| CN105095433A (en) | Recommendation method and device for entities | |
| CN103902535A (en) | Method, device and system for obtaining associational word | |
| CN104376083B (en) | It is a kind of that method is recommended based on concern relation and the figure of multi-user's behavior | |
| CN103023714A (en) | Activeness and cluster structure analyzing system and method based on network topics | |
| CN103064880A (en) | Method, device and system based on searching information for providing users with website choice | |
| CN103020295A (en) | Problem label marking method and device | |
| CN108416627A (en) | A kind of brand influence force monitoring method and system based on internet data | |
| Xue et al. | Ontology alignment based on instance using NSGA-II | |
| US20160048575A1 (en) | System and method for topics extraction and filtering | |
| CN104951560A (en) | Knowledge point structure based searcher | |
| CN104503988A (en) | Searching method and device | |
| CN104050243A (en) | Network searching method and system combined with searching and social contact | |
| Kim | Recommender system based on product taxonomy in e-commerce sites. | |
| Zhu et al. | Finding experts in tag based knowledge sharing communities | |
| CN103399879B (en) | The interested entity preparation method and device of daily record are searched for based on user | |
| CN107463679A (en) | A kind of information recommendation method and device | |
| CN102915312A (en) | Method and system for issuing information on websites |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190723 |