CN107784092A - A kind of method, server and computer-readable medium for recommending hot word - Google Patents
A kind of method, server and computer-readable medium for recommending hot word Download PDFInfo
- Publication number
- CN107784092A CN107784092A CN201710949851.4A CN201710949851A CN107784092A CN 107784092 A CN107784092 A CN 107784092A CN 201710949851 A CN201710949851 A CN 201710949851A CN 107784092 A CN107784092 A CN 107784092A
- Authority
- CN
- China
- Prior art keywords
- information
- terminal
- target
- hot word
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of method, server and computer-readable medium for recommending hot word, wherein this method includes:If detecting, first terminal starts intended application, obtains the target property information of the user of the first terminal;The corresponding target interest point information of the target property information is determined according to attribute information and the default corresponding relation of interest point information;Target hot word collection to be recommended is determined from default lexicon according to the target interest point information;The target hot word collection is pushed into the first terminal.The embodiment of the present invention speculates the interest characteristics of user by the attribute information of terminal user and actively pushes the possible target hot word interested of user to terminal according to interest characteristics, the interest characteristics of user can be predicted and hot word interested is pushed to user, so that user recognizes possible relevant information interested but not knowing search entry, the convenience for obtaining information is improved.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of method for recommending hot word, server and computer-readable
Medium.
Background technology
Search entry is the high level overview of today's society hot news event and domain knowledge, be understand news things,
Explore the main entrance of knowledge.As the development of development of Mobile Internet technology is with ripe, people can whenever and wherever possible conveniently and efficiently
The information wanted to know about by mobile terminal to search to oneself, search entry turn into a kind of knowledge resource of people, make people can
Go to understand the information wanted to know about with the time using more fragmentation.
In the prior art, when user searches for some vocabulary by search engine, drop-down list of the mobile terminal in input frame
Middle can show recommends the associational word related to vocabulary.
However, people can only initiate the search for having potential cognition in oneself limited cognitive range, people can not understand
To possible part information interested but not knowing search entry.
The content of the invention
The embodiment of the present invention provides a kind of method, server and computer-readable medium for recommending hot word, can predict use
The interest characteristics at family simultaneously pushes hot word interested to user, so that user recognizes possible interested but do not know search term
The relevant information of bar, improve the convenience for obtaining information.
In a first aspect, the embodiments of the invention provide a kind of method for recommending hot word, this method includes:
If detecting, first terminal starts intended application, obtains the target property information of the user of the first terminal;
The corresponding target of the target property information is determined according to attribute information and the default corresponding relation of interest point information
Interest point information;
Target hot word collection to be recommended is determined from default lexicon according to the target interest point information;
The target hot word collection is pushed into the first terminal.
Second aspect, the embodiments of the invention provide a kind of server, the server includes being used to perform above-mentioned first party
The unit of the method in face.
The third aspect, the embodiments of the invention provide another server, including processor, input equipment, output equipment
And memory, the processor, input equipment, output equipment and memory are connected with each other, wherein, the memory is used to store
Terminal is supported to perform the computer program of the above method, the computer program includes programmed instruction, and the processor is configured
For calling described program to instruct, the method that performs above-mentioned first aspect.
Fourth aspect, the embodiments of the invention provide a kind of computer-readable recording medium, the computer-readable storage medium
Computer program is stored with, the computer program includes programmed instruction, and described program instruction makes institute when being executed by a processor
The method for stating the above-mentioned first aspect of computing device.
If the embodiment of the present invention obtains the user of the first terminal by detecting that first terminal starts intended application
Target property information;Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information;Target hot word to be recommended is determined from default lexicon according to the target interest point information
Collection;The target hot word collection is pushed into the first terminal.Server speculates user's by the attribute information of terminal user
Interest characteristics simultaneously actively pushes the possible target hot word interested of user according to interest characteristics to terminal, can predict that user's is emerging
Interesting feature simultaneously pushes hot word interested to user, so that user recognizes possible phase interested but not knowing search entry
Information is closed, improves the convenience for obtaining information.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it is required in being described below to embodiment to use
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow diagram of the method for recommendation hot word provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic flow diagram of the method for recommendation hot word that another embodiment of the present invention provides;
Fig. 3 is a kind of schematic block diagram of server provided in an embodiment of the present invention;
Fig. 4 is a kind of server schematic block diagram that another embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
It should be appreciated that ought be in this specification and in the appended claims in use, term " comprising " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but it is not precluded from one or more of the other feature, whole
Body, step, operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more of the associated item listed and be possible to combine, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In the specific implementation, the terminal described in the embodiment of the present invention is including but not limited to such as with touch sensitive surface
The mobile phone, laptop computer or tablet PC of (for example, touch-screen display and/or touch pad) etc it is other just
Portable device.It is to be further understood that in certain embodiments, the equipment is not portable communication device, but with tactile
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, the terminal including display and touch sensitive surface is described.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
Terminal supports various application programs, such as one or more of following:Drawing application program, demonstration application journey
Sequence, word-processing application, website create application program, disk imprinting application program, spreadsheet applications, game application
Program, telephony application, videoconference application, email application, instant messaging applications, exercise
Support application program, photo management application program, digital camera application program, digital camera application program, web-browsing application
Program, digital music player application and/or video frequency player application program.
The various application programs that can be performed in terminal can use at least one public of such as touch sensitive surface
Physical user-interface device.It can adjust and/or change among applications and/or in corresponding application programs and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch
Sensing surface) the various application programs with user interface directly perceived and transparent for a user can be supported.
Fig. 1 is referred to, Fig. 1 is a kind of schematic flow diagram of the method for recommendation hot word provided in an embodiment of the present invention.This reality
The executive agent for applying the method for recommending hot word in example is server.It may include as depicted in the method for recommendation hot word:
S101:If detecting, first terminal starts intended application, obtains the objective attribute target attribute of the user of the first terminal
Information.
When first terminal detects that user clicks on the application icon startup intended application of intended application, first terminal request
Establish and communicate to connect with server.Wherein, first terminal is any terminal that intended application has been installed and activated, and intended application is
The application of server admin.It is understood that the terminal mentioned in various embodiments of the present invention is smart mobile phone, tablet personal computer
Deng mobile terminal.
For server when detecting that first terminal starts intended application, being identified as first terminal needs acquisition user interested
Hot word, server response first terminal send connection request simultaneously with first terminal establish communicate to connect, obtain first terminal
User target property information.
The target property information of the user of first terminal can be extracted from the basic document of the user of first terminal.First
The basic document of the user of terminal may be embodied in intended application, and it is local or included in the can also to be included in first terminal
In the other application in addition to intended application of one terminal built-in.When the basic document of the user of first terminal is included in first eventually
When in the built-in other application in addition to intended application in end, server needs the mandate for obtaining the other application to enter to it
Row is accessed to obtain the basic document of the user of first terminal.
Target property information can include sex, age, occupation, schooling etc., can also include income, constellation,
The information such as job site.
S102:Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information.
Server is when getting the target property information of user of first terminal, according to the attribute prestored in terminal
Information and the default corresponding relation of interest point information determine the corresponding target interest point information of target property information, so that it is determined that
The point of interest of the user of one terminal.Point of interest is user's information interested or interest characteristics, such as tourism, cuisines, military affairs, vapour
Car, dress ornament etc..Attribute information can include sex, age, occupation, schooling etc., can also include income, constellation, work
Make the information such as place.
Server can use the form record attribute information of form and the default corresponding relation of interest point information, can also
Using user's portrait record attribute information and the default corresponding relation of interest point information.
When server draws a portrait using user the default corresponding relation of record attribute information and interest point information, S102 can be with
Specially:The target of the user for user's portrait prediction first terminal that server is built according to target property information and in advance is emerging
Interesting point;Wherein, user draws a portrait for portraying user characteristics.
User draw a portrait, be it is a kind of be used for delineate targeted customer, contact user's demand and design direction effective tool, its
Each field is widely used.User draws a portrait to be gathered for portraying the label (tag) of user characteristics, the mark of user characteristics
Label set include the static attribute information such as age, sex, include the interest characteristics of user, as tourism, cuisines, military affairs, automobile,
Dress ornament etc..
S103:Target hot word collection to be recommended is determined from default lexicon according to the target interest point information.
Server is it is determined that during target interest point information corresponding to the user of first terminal, from default lexicon really
The target hot word collection to be recommended to set the goal corresponding to point of interest.Hot word collection is the set of hot word.Hot word is popular vocabulary.Hot word
As a kind of vocabulary phenomenon, a country, an area are reflected in period people's question of common concern and things.Tool
There are characteristics of the times, reflect the much-talked-about topic and livelihood issues in a period.Its main expression-form has language, word and network
Picture.It can be one that target hot word to be recommended, which concentrates the quantity included, or at least two, such as 6, but not
It is limited to this.Target hot word concentrates the hot word included can be with different.
Wherein, the vocabulary included in default lexicon can be sorted out or be clustered by point of interest.Server is it is determined that mesh
When marking interest point information, a kind of vocabulary corresponding to target point of interest can be obtained, and show number by vocabulary or be clicked secondary
The frequency of occurrences in several or default measurement period, a kind of vocabulary corresponding to target point of interest is ranked up, and therefrom determined
Target hot word to be recommended.Or server can also be with reference to the hot word ranking list for counting to obtain by big data, from target interest
Target hot word to be recommended is determined in the corresponding a kind of vocabulary of point.
Order of the server by displaying number or the frequency of occurrences being clicked in number or default measurement period from high to low
The target hot word to be recommended of preset number is determined successively, or preset number is determined according to hot word ranking list successively from high to low
Target vocabulary to be recommended.Preset number is greater than or equal to 1 integer.
For example, when target hot word to be recommended concentrates the quantity of the hot word included to be 1, displaying number corresponding to the hot word
Or the frequency of occurrences highest in number or default measurement period is clicked, or the hot word is in the first place of ranking list.
S104:The target hot word collection is pushed into the first terminal.
Server pushes to target hot word collection according to the mark of first terminal it is determined that during target hot word collection to be recommended
First terminal, so that first terminal display target hot word collection in the interactive interface of intended application.Specifically, first terminal can be with
In the target hot word collection of the predeterminable area display server push for being used to show PUSH message of the main interface of intended application, also may be used
With the target hot word collection that display server pushes in intended application other interactive interfaces.
Such scheme, if server detects that first terminal starts intended application, obtain the user of the first terminal
Target property information;Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information;Target hot word to be recommended is determined from default lexicon according to the target interest point information
Collection;The target hot word collection is pushed into the first terminal.Server speculates user's by the attribute information of terminal user
Interest characteristics simultaneously actively pushes the possible target hot word interested of user according to interest characteristics to terminal, can predict that user's is emerging
Interesting feature simultaneously pushes hot word interested to user, so that user recognizes possible phase interested but not knowing search entry
Information is closed, improves the convenience for obtaining information.
Fig. 2 is referred to, Fig. 2 is a kind of schematic flow diagram of the method for recommendation hot word that another embodiment of the present invention provides.
The executive agent for recommending the method for hot word in the present embodiment is server.It may include as depicted in the method for recommendation hot word:
S201:Internet data is captured using web crawlers technology, extracts hot word from the internet data, and by institute
The hot word for stating extraction forms the default lexicon.
Server uses natural language recognition using web crawlers technology crawl internet data (such as web page contents)
Technology and participle technique are to carrying out cutting word processing and data cleansing processing to the internet data of crawl, to extract effectively
Information, and hot word is extracted from effective information.
For example, server crawls focus article using web crawlers technology from each website, extract and close from focus article
As hot word, the hot word extracted forms default lexicon for key word or keyword.Such as using semantic analysis technology from focus
The title or abstract extraction keyword or keyword of article determine extraction as hot word, and according to the affiliated classification of focus article
Tag along sort corresponding to hot word.Tag along sort can include:Science and technology, automobile, house property, health, tourism etc..
Or server can also crawl hot word using web crawlers technology from internet.It is it is understood that default
Lexicon in hot word can also be manually entered.
Web crawlers (be otherwise known as webpage spider, network robot) is a kind of according to certain rule, automatically crawl
The program or script of web message, can be accessed with system and analysing content and its attribute (sometimes referred to as " metadata ") so as to
Establish the process for the content indexing that search inquiry service can be provided.
Hot word reflects a country, an area in period people's common concern as a kind of vocabulary phenomenon
Problem and things.With characteristics of the times, the much-talked-about topic and livelihood issues in one period of reflection.Its main expression-form has language
Speech, word and network picture.
In another way of example, server does not include theme in the web page contents crawled using web crawlers technology
When, web page contents can be carried out with cutting word processing, and delete and pair determine that a theme for the web page contents and contributive should not delete word
(e.g., "Yes", " and ", " in ", " ", " ", " obtaining ", " " " " etc.) is so as to obtaining lexical item collection corresponding to the web page contents.
Lexical item, which is concentrated, includes at least two lexical items.Wherein, a webpage can correspond to a lexical item collection.
Server calculates each self-corresponding word frequency (Term of the lexical item included in effective word set corresponding to the webpage
Frequency, TF) and inverse document frequency (Inverse Document Frequency, IDF), and calculate each lexical item pair
The word frequency and the product of inverse document frequency answered, obtain the first term frequency-inverse document frequency values TF-IDF of each lexical item.Each terminal
The keyword or keyword that corresponding historical search record includes can be used as a lexical item collection.One lexical item can be a key
Word or keyword.
Wherein, word frequency TF represents that the lexical item concentrates the frequency occurred, word frequency in the first lexical itemTFi,jRepresent jth
Individual lexical item concentrates the word frequency of i-th of lexical item, niThe number that j-th of lexical item concentrates i-th of lexical item to occur is represented, m represents j-th of word
The lexical item sum included in item collection.
We are very easy to find, if a keyword only occurs in seldom webpage, we are easy for locking by it
Surely target is searched for, its weight also just should be big.If instead a word occurs in a large amount of webpages, it is seen that it is still not
Will be apparent that what content looked for, therefore it should be small.Generally, it is assumed that a keyword w occurred in Dw webpage, that
Dw is bigger, and w weight is smaller, and vice versa.In information retrieval, most commonly used weight is inverse document frequency IDF.
Inverse document frequency IDF refers to that IDF is bigger if the webpage number comprising the lexical item is fewer, then illustrates that the lexical item has
There is good class discrimination ability.If a lexical item is concentrated in a lexical item and frequently occurred, illustrate that the lexical item can be fine
The feature of the text of this lexical item collection is represented, such lexical item should assign higher weight to them, and select and be used as the word
The Feature Words of the text of item collection are to distinguish and other class lexical item collection.Wherein,|D|、|{j:ti∈dj}
| it is positive integer.
IDFiRepresent that j-th of lexical item concentrates the inverse document frequency of i-th of lexical item, | D | represent the webpage number in corpus
Sum, { j:ti∈djRepresent to include lexical item tiWebpage number.
J-th of lexical item concentrates the term frequency-inverse document frequency values TF-IDF of i-th of lexical itemi,j=TFi,j*IDFi。
For example, the lexical item sum that the first lexical item collection obtained by the first webpage includes is 1000, lexical item " robot " goes out
Existing number is 20 times, then " robot " this lexical item concentrates the word frequency TF=20/1000=of " robot " in the first lexical item
0.02。
If the sum of webpage is N, there are 100 webpages to include " robot " this lexical item in each webpages of N, then the first word
The inverse document frequency IDF=log ((N)/(100)) of " robot " in item collection.
First lexical item concentrate " robot " term frequency-inverse document frequency values TF-IDF=TF*IDF=0.02*log ((N)/
(100))。
Terminal calculates each lexical item and concentrates term frequency-inverse document frequency corresponding to each lexical item respectively after the same method
Value.
If an inquiry includes keyword w1,w2,...,wN, their word frequency in a particular webpage are respectively:
TF1,TF2,...,TFN, then, the correlation of this inquiry and the webpage is exactly:TF1*IDF1+TF2*IDF2+...+TFN*
IDFN。TF1For TF1The weight of corresponding lexical item, TF2For TF1The weight of corresponding lexical item, TFNFor TFNThe power of corresponding lexical item
Weight.Lexical item TFNPredict that theme ability is stronger, IDFNWeight is bigger, and lexical item prediction theme ability is weaker, and weight is with regard to smaller.
S202:Obtain the historical search record that terminal uploads;Wherein, the historical search record includes index information.
Server obtains the historical search record for being mounted with that the terminal of intended application uploads, and historical search record is user
Caused search record is scanned for using intended application and/or the other application in addition to intended application.Wherein, history is searched
Suo Jilu includes index information, and index information includes keyword, keyword or sentence etc..When index information includes sentence,
Retrieval information server can extract keyword or keyword from index information.
The unique mark of terminal and each self-corresponding historical search of terminal can be associated preservation by server.Terminal is only
One mark can be international mobile equipment identification number (International Mobile Equipment Identity, IMEI),
Can also be other unique marks, such as, MAC Address etc..
Alternatively, the historical search record also includes search time and positional information.
Historical search search time for including of record refers at the time of terminal performs search operation or time point, historical search
When the positional information that record includes is that terminal performs search operation, the current positional information of terminal.
S203:Obtain the attribute information of terminal user;Wherein, the attribute information comprises at least age, sex, occupation letter
Breath.
The attribute information of terminal user is obtained in the user basic information that server can store from manufacturer terminal community.Category
Property information can at least include sex, age, occupation etc., schooling, income, constellation, job site etc. can also be included
Information.
The attribute information of the unique mark of terminal and terminal user can be associated preservation by server.
S201, S202, S203 can be performed sequentially in no particular order, can also be performed simultaneously.
S204:According to the historical search of the acquisition record and the acquisition attribute information establish attribute information with it is emerging
The default corresponding relation of interest point information.
Server can tentatively be modeled using machine learning algorithm, and historical search corresponding to each terminal is recorded
And the touch model that the attribute information input of each terminal user is established is trained to obtain point of interest forecast model, the interest
The default corresponding relation of attribute information and interest point information is contained in point prediction model.
For example server historical search record and the attribute of each terminal user can be believed according to corresponding to each terminal
Training Support Vector Machines (Support Vector Machine, SVM) grader is ceased, now SVM classifier is that point of interest is pre-
Survey model.The training method of SVM classifier refers to concrete methods of realizing of the prior art, does not repeat herein.Server exists
When needing to predict the point of interest of terminal user, attribute information corresponding to terminal user to be predicted, SVM are inputted to SVM classifier
Grader is its exportable corresponding point of interest.
Alternatively, when historical search record also includes search time and positional information, S204 includes:Obtained according to described
The historical search record and the attribute information of the acquisition taken, on a time period, city, the age, sex, occupation is by terminal user
Multiple crowds are divided into, and build each self-corresponding user's portrait of the multiple crowd.
The search time and positional information that server includes in being recorded according to the historical search of each terminal user, and often
The attribute information of individual terminal user, terminal user is divided into from period, city, age, sex, these professional dimensions multiple
Crowd, and searched according to each crowd of index information statistic of classification that includes of the historical search of each terminal user record is interested
Rope word (can also be keyword or keyword), and then build each crowd each corresponding user's portrait.Period is search
Period corresponding to time.
Label (tag) set for the user characteristics that user draws a portrait for portraying the crowd, the tag set bag of user characteristics
Include the static attribute information such as search time section, residing city, age, sex, include interest characteristics (or the interest of customer group
Point), interest characteristics includes interest pattern (or point of interest), can also include the search term for reflecting the interest pattern.Interest pattern
Such as travel, play, science and technology, cuisines, military affairs, automobile, shopping, dress ornament, animation, education.Interest pattern corresponding to one crowd
Number can be one or at least two.Interest pattern corresponding to different crowd can be with identical, can also be different.
For example the crowd of server division is as follows:
Crowd one:18:00~00:00, Shenzhen male programmer of 25~30 years old, Capricorn
Crowd two:14:00~18:00, the Shanghai schoolboy of 12~18 years old, Gemini
Crowd three:18:00~00:00, Beijing female model of 18~25 years old, Taurus
Search term interested is as shown in the table corresponding to user's portrait of each crowd:
When the historical search record obtained in S202 includes index information, server performs S205 after S204 is performed;
When the historical search record obtained in S202 also includes search time and positional information, server performs after S204 is performed
S206。
S205:If detecting, first terminal starts intended application, obtains the objective attribute target attribute of the user of the first terminal
Information.
When first terminal detects that user clicks on the application icon startup intended application of intended application, first terminal request
Establish and communicate to connect with server.Wherein, first terminal is any terminal that intended application has been installed and activated, and intended application is
The application of server admin.Target property information can include sex, age, occupation, schooling etc., can also include receiving
Enter, constellation, the information such as job site.
For server when detecting that first terminal starts intended application, being identified as first terminal needs acquisition user interested
Hot word, server response first terminal send connection request simultaneously with first terminal establish communicate to connect, obtain first terminal
User target property information.
The target property information of the user of first terminal can be extracted from the basic document of the user of first terminal.First
The basic document of the user of terminal may be embodied in intended application, and it is local or included in the can also to be included in first terminal
In the other application in addition to intended application of one terminal built-in.When the basic document of the user of first terminal is included in first eventually
When in the built-in other application in addition to intended application in end, server needs the mandate for obtaining the other application to enter to it
Row is accessed to obtain the basic document of the user of first terminal.
Server performs S207 after S205 is performed.
Alternatively, when historical search record also includes search time and positional information, S204 includes:According to the acquisition
Historical search record and the acquisition attribute information, on a time period, city, the age, sex, occupation by terminal user draw
When being divided into multiple crowds, and building each self-corresponding user portrait of the multiple crowd, recommending the method for hot word can also include
S206:If detecting, first terminal starts intended application, and it is current to obtain current temporal information and the first terminal
Positional information.
The current positional information of current temporal information and first terminal is used to obtain and current time and present bit
Put the interest characteristics or point of interest met.
Server can perform S2071~S2072 after S206 is performed;Can also execute server according to target category
Property information and the user that builds in advance draw a portrait prediction first terminal user target point of interest.
S207:Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information.
Server is when getting the target property information of user of first terminal, according to the attribute prestored in terminal
Information and the default corresponding relation of interest point information determine the corresponding target interest point information of target property information, so that it is determined that
The point of interest of the user of one terminal.Point of interest is user's information interested or interest characteristics, such as travels, plays, be scientific and technological, be beautiful
Food, military affairs, automobile, shopping, dress ornament, animation, education etc..Attribute information can include sex, age, occupation, schooling
Deng the information such as income, constellation, job site can also be included.
Server can use the form record attribute information of form and the default corresponding relation of interest point information, can also
Using user's portrait record attribute information and the default corresponding relation of interest point information.
When server according to the historical search of acquisition record and obtain attribute information, on a time period, city, the age,
Terminal user is divided into multiple crowds by sex, occupation, and when building each self-corresponding user's portrait of multiple crowds, and S207 can be with
Specially:The target of the user for user's portrait prediction first terminal that server is built according to target property information and in advance is emerging
Interesting point;Wherein, user draws a portrait for portraying user characteristics.
Target person of the server according to belonging to the target property information of the user of first terminal determines the user of first terminal
Group, and the target property information of the user of first terminal is inputted into user's portrait model corresponding to target group, to pass through the use
The target point of interest of the user of family portrait prediction first terminal.
Target point of interest can be tourism, game, science and technology, cuisines, military affairs, automobile, shopping, dress ornament, animation, education etc. its
One of or at least two any combination, be not limited herein.
Alternatively, when according to the historical search of acquisition record and obtain attribute information, on a time period, city, the age,
Terminal user is divided into multiple crowds by sex, occupation, and builds each self-corresponding user's portrait of multiple crowds, and recommends hot word
Method when including S206, S207 is specifically included:
S2071:According to the current temporal information, the current positional information and the target property information,
Targeted customer's portrait is determined from the user's portrait built in advance.
Multiple crowds are divided into terminal user from period, city, age, sex, these professional dimensions
Because the tag set of user characteristics that the user's portrait pre-established is portrayed includes search time section, residing city
The static attribute information such as city, age, sex, therefore, server can according to current temporal information, current positional information with
It is each self-corresponding from the multiple crowds built in advance and target property information determines the target group belonging to the user of first terminal
Determine that targeted customer corresponding to the target group draws a portrait in user's portrait.
Interest pattern is such as traveled, played, science and technology, cuisines, military affairs, automobile, shopping, dress ornament, animation, education.
S2072:The target interest point information of the user of the first terminal is predicted according to targeted customer portrait.
It is emerging because the tag set of user characteristics that user's portrait is portrayed includes the interest characteristics (or point of interest) of customer group
Interesting feature includes interest pattern (or point of interest), and therefore, server is it is determined that targeted customer corresponding to the user of first terminal
During portrait, target interest point information corresponding to targeted customer's portrait can be obtained.
Server performs S208 after S207 or S2072 is performed.
S208:Target hot word collection to be recommended is determined from default lexicon according to the target interest point information.
Server is it is determined that during target interest point information corresponding to the user of first terminal, from default lexicon really
The target hot word collection to be recommended to set the goal corresponding to point of interest.Hot word collection is the set of hot word.Hot word is popular vocabulary.Wait to push away
It can be one that the target hot word recommended, which concentrates the quantity included, or at least two, such as 6, but it is not limited to this.
Wherein, the vocabulary included in default lexicon can be sorted out or be clustered by point of interest.Server is it is determined that mesh
When marking interest point information, a kind of vocabulary corresponding to target point of interest can be obtained, and show number by vocabulary or be clicked secondary
The frequency of occurrences in several or default measurement period, a kind of vocabulary corresponding to target point of interest is ranked up, and therefrom determined
Target hot word to be recommended.Or server can also be with reference to the hot word ranking list for counting to obtain by big data, from target interest
Target hot word to be recommended is determined in the corresponding a kind of vocabulary of point.
Order of the server by displaying number or the frequency of occurrences being clicked in number or default measurement period from high to low
The target hot word to be recommended of preset number is determined successively, or preset number is determined according to hot word ranking list successively from high to low
Target vocabulary to be recommended.Preset number is greater than or equal to 1 integer.
For example, when target hot word to be recommended concentrates the quantity of the hot word included to be 1, displaying number corresponding to the hot word
Or the frequency of occurrences highest in number or default measurement period is clicked, or the hot word is in the first place of ranking list.
Alternatively, S208 can include:
S2081:Hot word to be recommended is determined from default lexicon according to the target point of interest.
Server screens and the heat to be recommended of target interest points matching according to target point of interest from default lexicon
Word.
S2082:Calculate each self-corresponding weight of the hot word to be recommended and the degree of correlation.
Server can use semantic analysis technology to calculate the degree of correlation between hot word to be recommended, specifically, server
It can first determine to refer to hot word corresponding to target point of interest, and calculate the degree of correlation between hot word to be recommended and reference hot word.Ginseng
It can be the hot word that target point of interest corresponds to the temperature highest (as the first in temperature ranking list) in hot word to examine hot word;Can also
Determine from search term interested corresponding to user's portrait, be not limited herein.
Server can count the number being pushed corresponding to hot word to be recommended in default measurement period or be clicked
Number, and the number being pushed or the number being clicked calculate according to corresponding to hot word to be recommended in default measurement period
Each self-corresponding weight of hot word to be recommended.Default measurement period can be one week or one month, but be not limited to
This, can also be configured according to being actually needed, not be limited herein.The weight can be the number being pushed or be clicked
The business of number and default measurement period.
S2083:Target hot word collection is determined according to each self-corresponding weight of the hot word to be recommended and the degree of correlation, its
In, the target hot word concentrates the hot word included different.
Server filters out with reference to hot word from hot word to be recommended and is less than default phase with the degree of correlation with reference to hot word
The hot word of pass degree threshold value, candidate's hot word collection is formed, and each each self-corresponding weight of hot word is concentrated according to candidate's hot word, by weight
Order from high to low is concentrated from candidate's hot word and filters out the different target hot word of preset number, the target filtered out successively
Hot word forms target hot word collection.Default relevance threshold can be 50%, and preset number can be 3, or 6, but not
It is limited to this, can be specifically configured according to being actually needed.
S209:The target hot word collection is pushed into the first terminal.
Server pushes to target hot word collection according to the mark of first terminal it is determined that during target hot word collection to be recommended
First terminal, so that first terminal display target hot word collection in the interactive interface of intended application.Specifically, first terminal can be with
In the target hot word collection of the predeterminable area display server push for being used to show PUSH message of the main interface of intended application, also may be used
With the target hot word collection that display server pushes in intended application other interactive interfaces.
Such scheme, if server detects that first terminal starts intended application, obtain the user of the first terminal
Target property information;Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information;Target hot word to be recommended is determined from default lexicon according to the target interest point information
Collection;The target hot word collection is pushed into the first terminal.Server speculates user's by the attribute information of terminal user
Interest characteristics simultaneously actively pushes the possible target hot word interested of user according to interest characteristics to terminal, can predict that user's is emerging
Interesting feature simultaneously pushes hot word interested to user, so that user recognizes possible phase interested but not knowing search entry
Information is closed, improves the convenience for obtaining information, and the personalized hot word for meeting user's request can be pushed to user, without
It is as pushing identical content to all users in the prior art.
Server is according to customer attribute information, historical search record, search time and positional information, on a time period, city
Terminal user is divided into multiple crowds by city, age, sex, occupation, and builds each self-corresponding user's portrait of multiple crowds, energy
It is enough to improve the degree of accuracy for determining target point of interest, further improve the hot word of push and the matching degree of user's request.
The hot word that server includes to the target hot word collection that first terminal pushes is different, can avoid information redundancy,
The time of filter information is reduced, improves the efficiency that user obtains target data.
The embodiment of the present invention also provides a kind of server, and server is the server for recommending hot word, the server bag
Include for perform the recommendation hot word described in foregoing any embodiment method in each step unit.Specifically, referring to figure
3, Fig. 3 be a kind of schematic block diagram of server provided in an embodiment of the present invention.The server 3 of the present embodiment includes:First obtains
Unit 310, the first determining unit 320, the second determining unit 330 and push unit 340.
First acquisition unit 310, if for detecting that first terminal starts intended application, obtain the first terminal
The target property information of user.
Alternatively, server also includes:
First pretreatment unit 3011, for obtaining the historical search record of terminal upload;Wherein, the historical search note
Record includes index information;
Second pretreatment unit 3012, for obtaining the attribute information of terminal user;Wherein, the attribute information at least wraps
Include age, sex, occupational information;
3rd pretreatment unit 3013, for being believed according to the attribute of the historical search of acquisition record and the acquisition
Breath establishes the default corresponding relation of attribute information and interest point information.
Further, the historical search record also includes search time and positional information;
Further, when historical search record also includes search time and positional information, the 3rd pretreatment unit
3013 are specifically used for:According to the historical search of the acquisition record and the acquisition attribute information, on a time period, city,
Terminal user is divided into multiple crowds by age, sex, occupation, and builds each self-corresponding user's portrait of the multiple crowd.
Alternatively, server also includes:
4th pretreatment unit 3014, for capturing internet data using web crawlers technology, from the interconnection netting index
The default lexicon is formed according to middle extraction hot word, and by the hot word of the extraction.
First determining unit 320, for the pre- of the attribute information that is obtained according to first acquisition unit 310 and interest point information
If corresponding relation determines target interest point information corresponding to the target property information.
Second determining unit 330, for according to the target interest point information that the first determining unit 320 determines from default
Lexicon in determine target hot word collection to be recommended.
Push unit 340, the target hot word collection for the second determining unit 330 to be determined push to described first eventually
End.
Alternatively, server also includes:
Second acquisition unit 350, if for detecting that first terminal starts intended application, obtain current temporal information
And the positional information that the first terminal is current;
First determining unit 320 includes:
User draw a portrait determining unit 321, for according to the current temporal information, the current positional information and
The target property information, targeted customer's portrait is determined from the user's portrait built in advance;
Point of interest determining unit 322, the mesh for the user for predicting the first terminal that drawn a portrait according to the targeted customer
Mark interest point information.
Further, point of interest determining unit 322 is specifically used for:
Hot word to be recommended is determined from default lexicon according to the target point of interest;
Calculate each self-corresponding weight of the hot word to be recommended and the degree of correlation;
Target hot word collection is determined according to each self-corresponding weight of the hot word to be recommended and the degree of correlation, wherein, it is described
Target hot word concentrates the hot word included different.
Such scheme, if server detects that first terminal starts intended application, obtain the user of the first terminal
Target property information;Determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information;Target hot word to be recommended is determined from default lexicon according to the target interest point information
Collection;The target hot word collection is pushed into the first terminal.Server speculates user's by the attribute information of terminal user
Interest characteristics simultaneously actively pushes the possible target hot word interested of user according to interest characteristics to terminal, can predict that user's is emerging
Interesting feature simultaneously pushes hot word interested to user, so that user recognizes possible phase interested but not knowing search entry
Information is closed, improves the convenience for obtaining information, and the personalized hot word for meeting user's request can be pushed to user, without
It is as pushing identical content to all users in the prior art.
Server is according to customer attribute information, historical search record, search time and positional information, on a time period, city
Terminal user is divided into multiple crowds by city, age, sex, occupation, and builds each self-corresponding user's portrait of multiple crowds, energy
It is enough to improve the degree of accuracy for determining target point of interest, further improve the hot word of push and the matching degree of user's request.
The hot word that server includes to the target hot word collection that first terminal pushes is different, can avoid information redundancy,
The time of filter information is reduced, improves the efficiency that user obtains target data.
Referring to Fig. 4, Fig. 4 is a kind of server schematic block diagram that another embodiment of the present invention provides.This reality as depicted
The server 4 applied in example can include:One or more processors 401;One or more input equipments 402, it is one or more
Output equipment 403 and memory 404.Above-mentioned processor 401, input equipment 402, output equipment 403 and memory 404 are by total
Line 405 connects.Memory 404 is used to store computer program, and the computer program includes programmed instruction, and processor 401 is used
In the programmed instruction for performing the storage of memory 404.Wherein, processor 401 is arranged to call described program instruction to perform:
If detecting, first terminal starts intended application, obtains the target property information of the user of the first terminal;
The corresponding target of the target property information is determined according to attribute information and the default corresponding relation of interest point information
Interest point information;
Target hot word collection to be recommended is determined from default lexicon according to the target interest point information;
The target hot word collection is pushed into the first terminal.
Alternatively, if detecting, first terminal starts intended application, obtains the target category of the user of the first terminal
Property information before, processor 401 be additionally configured to call described program instruction perform:
Obtain the historical search record that terminal uploads;Wherein, the historical search record includes index information;
Obtain the attribute information of terminal user;Wherein, the attribute information comprises at least age, sex, occupational information.
Alternatively, the historical search record also includes search time and positional information.
Alternatively, when historical search record also includes search time and positional information, the specific quilt of processor 401
It is configured to call described program instruction to perform:
According to the historical search of the acquisition record and the acquisition attribute information, on a time period, city, the age,
Terminal user is divided into multiple crowds by sex, occupation, and builds each self-corresponding user's portrait of the multiple crowd.
Alternatively, processor 401 is additionally configured to call described program instruction to perform:
If detecting, first terminal starts intended application, obtains current temporal information and the first terminal is current
Positional information;
It is described to determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information, including:
According to the current temporal information, the current positional information and the target property information, from advance
Targeted customer's portrait is determined in user's portrait of structure;
The target interest point information of the user of the first terminal is predicted according to targeted customer portrait.
Alternatively, processor 401 is specific is arranged to call described program instruction to perform:
Hot word to be recommended is determined from default lexicon according to the target point of interest;
Calculate each self-corresponding weight of the hot word to be recommended and the degree of correlation;
Target hot word collection is determined according to each self-corresponding weight of the hot word to be recommended and the degree of correlation, wherein, it is described
Target hot word concentrates the hot word included different.
Alternatively, if detecting, first terminal starts intended application, obtains the target category of the user of the first terminal
Property information before, processor 401 be additionally configured to call described program instruction perform:
Internet data is captured using web crawlers technology, hot word is extracted from the internet data, and carry described
The hot word taken forms the default lexicon.
It should be appreciated that in embodiments of the present invention, alleged processor 401 can be CPU (Central
Processing Unit, CPU), the processor can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other FPGAs
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
It can also be any conventional processor etc. to manage device.
Input equipment 402 can include Trackpad, fingerprint adopt sensor (finger print information that is used to gathering user and fingerprint
Directional information), microphone etc., output equipment 403 can include display (LCD etc.), loudspeaker etc..
The memory 404 can include read-only storage and random access memory, and to processor 401 provide instruction and
Data.The a part of of memory 404 can also include nonvolatile RAM.For example, memory 404 can also be deposited
Store up the information of device type.
In the specific implementation, processor 401, input equipment 402, the output equipment 403 described in the embodiment of the present invention can
Perform the realization side described in the first embodiment and second embodiment of the method for recommendation hot word provided in an embodiment of the present invention
Formula, the implementation of the server described by the embodiment of the present invention is also can perform, will not be repeated here.
A kind of computer-readable recording medium, the computer-readable storage medium are provided in another embodiment of the invention
Matter is stored with computer program, and the computer program includes programmed instruction, and described program instruction is realized when being executed by processor:
If detecting, first terminal starts intended application, obtains the target property information of the user of the first terminal;
The corresponding target of the target property information is determined according to attribute information and the default corresponding relation of interest point information
Interest point information;
Target hot word collection to be recommended is determined from default lexicon according to the target interest point information;
The target hot word collection is pushed into the first terminal.
Alternatively, if described detect that first terminal starts intended application, the mesh of the user of the first terminal is obtained
Before marking attribute information, described program instruction is also realized when being executed by processor:
Obtain the historical search record that terminal uploads;Wherein, the historical search record includes index information;
Obtain the attribute information of terminal user;Wherein, the attribute information comprises at least age, sex, occupational information;
Attribute information and point of interest are established according to the attribute information of the historical search of acquisition record and the acquisition
The default corresponding relation of information.
Alternatively, the historical search record also includes search time and positional information.
Alternatively, when historical search record also includes search time and positional information, described program instruction quilt
Implemented during computing device:According to the historical search of the acquisition record and the acquisition attribute information, temporally
Terminal user is divided into multiple crowds, and builds each self-corresponding use of the multiple crowd by section, city, age, sex, occupation
Draw a portrait at family.
Alternatively, also realized when described program instruction is executed by processor:
If detecting, first terminal starts intended application, obtains current temporal information and the first terminal is current
Positional information;
It is described to determine that the target property information is corresponding with the default corresponding relation of interest point information according to attribute information
Target interest point information, including:
According to the current temporal information, the current positional information and the target property information, from advance
Targeted customer's portrait is determined in user's portrait of structure;
The target interest point information of the user of the first terminal is predicted according to targeted customer portrait.
Alternatively, implemented when described program instruction is executed by processor:
Hot word to be recommended is determined from default lexicon according to the target point of interest;
Calculate each self-corresponding weight of the hot word to be recommended and the degree of correlation;
Target hot word collection is determined according to each self-corresponding weight of the hot word to be recommended and the degree of correlation, wherein, it is described
Target hot word concentrates the hot word included different.
Alternatively, if described detect that first terminal starts intended application, the mesh of the user of the first terminal is obtained
Before marking attribute information, described program instruction is also realized when being executed by processor:
Internet data is captured using web crawlers technology, hot word is extracted from the internet data, and carry described
The hot word taken forms the default lexicon.
The computer-readable recording medium can be the internal storage unit of the server described in foregoing any embodiment,
Such as the hard disk or internal memory of server.The computer-readable recording medium can also be the External memory equipment of the terminal,
Such as the plug-in type hard disk being equipped with the server, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) blocks, flash card (Flash Card) etc..Further, the computer-readable recording medium is also
The internal storage unit of the server can both be included or including External memory equipment.The computer-readable recording medium is used
In other programs and data needed for the storage computer program and the terminal.The computer-readable recording medium is also
It can be used for temporarily storing the data that has exported or will export.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, the composition and step of each example are generally described according to function in the above description.This
A little functions are performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specially
Industry technical staff can realize described function using distinct methods to each specific application, but this realization is not
It is considered as beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience of description and succinctly, the end of foregoing description
End and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed terminal and method, it can be passed through
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed phase
Coupling or direct-coupling or communication connection between mutually can be INDIRECT COUPLING or the communication by some interfaces, device or unit
Connection or electricity, the connection of mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
It is that unit is individually physically present or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art, or all or part of the technical scheme can be in the form of software product
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or substitutions should be all included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (10)
- A kind of 1. method for recommending hot word, it is characterised in that including:If detecting, first terminal starts intended application, obtains the target property information of the user of the first terminal;The corresponding target interest of the target property information is determined according to attribute information and the default corresponding relation of interest point information Point information;Target hot word collection to be recommended is determined from default lexicon according to the target interest point information;The target hot word collection is pushed into the first terminal.
- 2. according to the method for claim 1, it is characterised in that if described detect that first terminal starts intended application, Before the target property information for obtaining the user of the first terminal, in addition to:Obtain the historical search record that terminal uploads;Wherein, the historical search record includes index information;Obtain the attribute information of terminal user;Wherein, the attribute information comprises at least age, sex, occupational information;Attribute information and interest point information are established according to the attribute information of the historical search of acquisition record and the acquisition Default corresponding relation.
- 3. according to the method for claim 2, it is characterised in that the historical search record also includes search time and position Confidence ceases.
- 4. according to the method for claim 3, it is characterised in that described according to the historical search of acquisition record and institute The attribute information for stating acquisition is established attribute information and the default corresponding relation of interest point information and included:According to the historical search of the acquisition record and the acquisition attribute information, on a time period, city, the age, sex, Terminal user is divided into multiple crowds by occupation, and builds each self-corresponding user's portrait of the multiple crowd.
- 5. according to the method for claim 4, it is characterised in that methods described also includes:If detecting, first terminal starts intended application, obtains current temporal information and the current position of the first terminal Confidence ceases;It is described that the corresponding target of the target property information is determined according to attribute information and the default corresponding relation of interest point information Interest point information, including:According to the current temporal information, the current positional information and the target property information, from advance structure User portrait in determine targeted customer portrait;The target interest point information of the user of the first terminal is predicted according to targeted customer portrait.
- 6. according to the method for claim 1, it is characterised in that it is described according to the target point of interest from default lexicon It is middle to determine that target hot word collection to be recommended includes:Hot word to be recommended is determined from default lexicon according to the target point of interest;Calculate each self-corresponding weight of the hot word to be recommended and the degree of correlation;Target hot word collection is determined according to each self-corresponding weight of the hot word to be recommended and the degree of correlation, wherein, the target Hot word concentrates the hot word included different.
- 7. according to the method described in any one of claim 1 to 6, it is characterised in that if described detect that first terminal starts mesh Mark is applied, then before the target property information for the user for obtaining the first terminal, in addition to:Internet data is captured using web crawlers technology, extracts hot word from the internet data, and by the extraction Hot word forms the default lexicon.
- 8. a kind of server, it is characterised in that including the unit for performing the method as described in claim any one of 1-7.
- A kind of 9. server, it is characterised in that including processor, input equipment, output equipment and memory, the processor, Input equipment, output equipment and memory are connected with each other, wherein, the memory is used to store computer program, the calculating Machine program includes programmed instruction, and the processor is arranged to call described program instruction, performed as claim 1-7 is any Method described in.
- A kind of 10. computer-readable recording medium, it is characterised in that the computer-readable storage medium is stored with computer program, The computer program includes programmed instruction, and described program instruction makes the computing device such as right when being executed by a processor It is required that the method described in any one of 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710949851.4A CN107784092A (en) | 2017-10-11 | 2017-10-11 | A kind of method, server and computer-readable medium for recommending hot word |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710949851.4A CN107784092A (en) | 2017-10-11 | 2017-10-11 | A kind of method, server and computer-readable medium for recommending hot word |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107784092A true CN107784092A (en) | 2018-03-09 |
Family
ID=61433716
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710949851.4A Withdrawn CN107784092A (en) | 2017-10-11 | 2017-10-11 | A kind of method, server and computer-readable medium for recommending hot word |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107784092A (en) |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446385A (en) * | 2018-03-21 | 2018-08-24 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108550050A (en) * | 2018-03-27 | 2018-09-18 | 昆山和君纵达数据科技有限公司 | A kind of user's portrait method based on call center data |
CN109299367A (en) * | 2018-09-28 | 2019-02-01 | 中国平安财产保险股份有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN109376295A (en) * | 2018-08-24 | 2019-02-22 | 北京达佳互联信息技术有限公司 | A kind of hot word collects method for pushing, device and network server |
CN109597874A (en) * | 2018-10-23 | 2019-04-09 | 重庆邂智科技有限公司 | Information recommendation method, device and server |
CN109657129A (en) * | 2018-12-26 | 2019-04-19 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
CN109993649A (en) * | 2019-03-13 | 2019-07-09 | 王亚萍 | A kind of pilot-operated type consultancy relating to payment of tax method for pushing |
CN109993507A (en) * | 2019-04-17 | 2019-07-09 | 王亚萍 | A kind of pilot-operated type service system of paying taxes |
CN110222021A (en) * | 2019-05-20 | 2019-09-10 | 中国平安财产保险股份有限公司 | A kind of data processing method, equipment, server and computer readable storage medium |
CN110263248A (en) * | 2019-05-21 | 2019-09-20 | 平安科技(深圳)有限公司 | A kind of information-pushing method, device, storage medium and server |
CN110598100A (en) * | 2019-09-04 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Hot word recommendation method, device, equipment and storage medium |
CN110633411A (en) * | 2019-07-18 | 2019-12-31 | 北京无限光场科技有限公司 | Method and device for screening house resources, electronic equipment and storage medium |
CN110750706A (en) * | 2018-07-19 | 2020-02-04 | 阿里巴巴集团控股有限公司 | Method, device and system for determining search hot words and electronic equipment |
CN110765348A (en) * | 2019-09-17 | 2020-02-07 | 五八有限公司 | Hot word recommendation method and device, electronic equipment and storage medium |
CN110781283A (en) * | 2019-09-16 | 2020-02-11 | 腾讯大地通途(北京)科技有限公司 | Chain brand word bank generation method and device and electronic equipment |
CN110929138A (en) * | 2018-09-04 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Recommendation information generation method, device, equipment and storage medium |
CN110941766A (en) * | 2019-12-10 | 2020-03-31 | 北京字节跳动网络技术有限公司 | Information pushing method and device, computer equipment and storage medium |
CN111078998A (en) * | 2019-11-19 | 2020-04-28 | Oppo(重庆)智能科技有限公司 | Information retrieval method, information retrieval device, storage medium and server |
CN111125344A (en) * | 2019-12-23 | 2020-05-08 | 北大方正集团有限公司 | Related word recommendation method and device |
CN111126912A (en) * | 2019-12-23 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Freight type identification method and device, storage medium and terminal for truck |
CN111291258A (en) * | 2020-01-20 | 2020-06-16 | 北京无限光场科技有限公司 | Recommendation method and device for searching hot words, electronic equipment and readable medium |
CN111310019A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Information recommendation method, information processing method, system and equipment |
CN111339741A (en) * | 2020-02-26 | 2020-06-26 | 腾讯科技(深圳)有限公司 | Account application method and device, computer readable storage medium and electronic equipment |
CN111368025A (en) * | 2020-02-24 | 2020-07-03 | 百度在线网络技术(北京)有限公司 | Hot word recommendation method and device for intelligent voice device and storage medium |
CN111444429A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技(深圳)有限公司 | Information pushing method and device and server |
CN111831899A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Navigation interest point recommendation method and device and server |
CN111989664A (en) * | 2018-04-18 | 2020-11-24 | 北京嘀嘀无限科技发展有限公司 | System and method for improving online platform user experience |
CN112000865A (en) * | 2020-07-22 | 2020-11-27 | 北京达佳互联信息技术有限公司 | Hot word generation method, device, server and storage medium |
CN112182378A (en) * | 2020-09-28 | 2021-01-05 | 厦门美柚股份有限公司 | Message pushing method, device, terminal and medium |
CN112488650A (en) * | 2020-11-26 | 2021-03-12 | 万翼科技有限公司 | Conference atmosphere adjusting method, electronic equipment and related products |
WO2021114279A1 (en) * | 2019-12-13 | 2021-06-17 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining restriction attribute of area of interset |
CN113256441A (en) * | 2021-06-03 | 2021-08-13 | 探探文化发展(北京)有限公司 | User recommendation method, device, equipment and storage medium in social scene |
CN113407821A (en) * | 2021-05-30 | 2021-09-17 | 咸宁方片互娱网络有限公司 | Method and system for recommending dynamic content of cell, intelligent terminal and server |
CN114223011A (en) * | 2019-10-23 | 2022-03-22 | 深圳市欢太科技有限公司 | Entry pushing method and device, electronic equipment and storage medium |
CN114880713A (en) * | 2022-06-30 | 2022-08-09 | 深圳红途科技有限公司 | User behavior analysis method, device, equipment and medium based on data link |
WO2022199494A1 (en) * | 2021-03-23 | 2022-09-29 | 华为技术有限公司 | User interest-based content recommendation method, and terminal device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104166700A (en) * | 2014-08-01 | 2014-11-26 | 百度在线网络技术(北京)有限公司 | Search term recommendation method and device |
CN104572889A (en) * | 2014-12-24 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method, device and system for recommending search terms |
CN107229654A (en) * | 2016-03-25 | 2017-10-03 | 北大方正集团有限公司 | A kind of heat searches word acquisition methods and system |
-
2017
- 2017-10-11 CN CN201710949851.4A patent/CN107784092A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104166700A (en) * | 2014-08-01 | 2014-11-26 | 百度在线网络技术(北京)有限公司 | Search term recommendation method and device |
CN104572889A (en) * | 2014-12-24 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method, device and system for recommending search terms |
CN107229654A (en) * | 2016-03-25 | 2017-10-03 | 北大方正集团有限公司 | A kind of heat searches word acquisition methods and system |
Cited By (53)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446385A (en) * | 2018-03-21 | 2018-08-24 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108550050A (en) * | 2018-03-27 | 2018-09-18 | 昆山和君纵达数据科技有限公司 | A kind of user's portrait method based on call center data |
CN111989664A (en) * | 2018-04-18 | 2020-11-24 | 北京嘀嘀无限科技发展有限公司 | System and method for improving online platform user experience |
CN110750706A (en) * | 2018-07-19 | 2020-02-04 | 阿里巴巴集团控股有限公司 | Method, device and system for determining search hot words and electronic equipment |
CN110750706B (en) * | 2018-07-19 | 2023-04-28 | 阿里巴巴集团控股有限公司 | Search hotword determining method, device and system and electronic equipment |
CN109376295A (en) * | 2018-08-24 | 2019-02-22 | 北京达佳互联信息技术有限公司 | A kind of hot word collects method for pushing, device and network server |
CN110929138A (en) * | 2018-09-04 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Recommendation information generation method, device, equipment and storage medium |
CN110929138B (en) * | 2018-09-04 | 2024-03-29 | 阿里巴巴集团控股有限公司 | Recommendation information generation method, device, equipment and storage medium |
CN109299367A (en) * | 2018-09-28 | 2019-02-01 | 中国平安财产保险股份有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN109597874A (en) * | 2018-10-23 | 2019-04-09 | 重庆邂智科技有限公司 | Information recommendation method, device and server |
CN109597874B (en) * | 2018-10-23 | 2023-05-23 | 重庆邂智科技有限公司 | Information recommendation method, device and server |
CN111310019B (en) * | 2018-12-11 | 2023-10-20 | 阿里巴巴集团控股有限公司 | Information recommendation method, information processing method, system and equipment |
CN111310019A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Information recommendation method, information processing method, system and equipment |
CN109657129A (en) * | 2018-12-26 | 2019-04-19 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
CN109657129B (en) * | 2018-12-26 | 2023-04-18 | 北京百度网讯科技有限公司 | Method and device for acquiring information |
CN109993649A (en) * | 2019-03-13 | 2019-07-09 | 王亚萍 | A kind of pilot-operated type consultancy relating to payment of tax method for pushing |
CN109993507A (en) * | 2019-04-17 | 2019-07-09 | 王亚萍 | A kind of pilot-operated type service system of paying taxes |
CN110222021A (en) * | 2019-05-20 | 2019-09-10 | 中国平安财产保险股份有限公司 | A kind of data processing method, equipment, server and computer readable storage medium |
CN110222021B (en) * | 2019-05-20 | 2024-02-09 | 中国平安财产保险股份有限公司 | Data processing method, device, server and computer readable storage medium |
CN110263248A (en) * | 2019-05-21 | 2019-09-20 | 平安科技(深圳)有限公司 | A kind of information-pushing method, device, storage medium and server |
CN110263248B (en) * | 2019-05-21 | 2023-11-28 | 平安科技(深圳)有限公司 | Information pushing method, device, storage medium and server |
CN110633411A (en) * | 2019-07-18 | 2019-12-31 | 北京无限光场科技有限公司 | Method and device for screening house resources, electronic equipment and storage medium |
CN110598100A (en) * | 2019-09-04 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Hot word recommendation method, device, equipment and storage medium |
CN110598100B (en) * | 2019-09-04 | 2021-06-11 | 腾讯科技(深圳)有限公司 | Hot word recommendation method, device, equipment and storage medium |
CN110781283A (en) * | 2019-09-16 | 2020-02-11 | 腾讯大地通途(北京)科技有限公司 | Chain brand word bank generation method and device and electronic equipment |
CN110781283B (en) * | 2019-09-16 | 2023-12-08 | 腾讯大地通途(北京)科技有限公司 | Chain brand word stock generation method and device and electronic equipment |
CN110765348A (en) * | 2019-09-17 | 2020-02-07 | 五八有限公司 | Hot word recommendation method and device, electronic equipment and storage medium |
CN110765348B (en) * | 2019-09-17 | 2024-01-05 | 五八有限公司 | Hot word recommendation method and device, electronic equipment and storage medium |
CN111831899A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Navigation interest point recommendation method and device and server |
CN111831899B (en) * | 2019-09-24 | 2023-11-24 | 北京嘀嘀无限科技发展有限公司 | Navigation interest point recommendation method, device, server and readable storage medium |
CN114223011A (en) * | 2019-10-23 | 2022-03-22 | 深圳市欢太科技有限公司 | Entry pushing method and device, electronic equipment and storage medium |
CN111078998A (en) * | 2019-11-19 | 2020-04-28 | Oppo(重庆)智能科技有限公司 | Information retrieval method, information retrieval device, storage medium and server |
CN111078998B (en) * | 2019-11-19 | 2024-03-12 | Oppo(重庆)智能科技有限公司 | Information retrieval method, device, storage medium and server |
CN110941766A (en) * | 2019-12-10 | 2020-03-31 | 北京字节跳动网络技术有限公司 | Information pushing method and device, computer equipment and storage medium |
CN110941766B (en) * | 2019-12-10 | 2023-10-20 | 北京字节跳动网络技术有限公司 | Information pushing method, device, computer equipment and storage medium |
WO2021114279A1 (en) * | 2019-12-13 | 2021-06-17 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining restriction attribute of area of interset |
CN111126912A (en) * | 2019-12-23 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Freight type identification method and device, storage medium and terminal for truck |
CN111125344A (en) * | 2019-12-23 | 2020-05-08 | 北大方正集团有限公司 | Related word recommendation method and device |
CN111125344B (en) * | 2019-12-23 | 2023-09-05 | 新方正控股发展有限责任公司 | Related word recommendation method and device |
CN111291258A (en) * | 2020-01-20 | 2020-06-16 | 北京无限光场科技有限公司 | Recommendation method and device for searching hot words, electronic equipment and readable medium |
CN111368025A (en) * | 2020-02-24 | 2020-07-03 | 百度在线网络技术(北京)有限公司 | Hot word recommendation method and device for intelligent voice device and storage medium |
CN111339741A (en) * | 2020-02-26 | 2020-06-26 | 腾讯科技(深圳)有限公司 | Account application method and device, computer readable storage medium and electronic equipment |
CN111444429B (en) * | 2020-03-27 | 2023-04-07 | 腾讯科技(深圳)有限公司 | Information pushing method and device and server |
CN111444429A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技(深圳)有限公司 | Information pushing method and device and server |
CN112000865B (en) * | 2020-07-22 | 2024-01-23 | 北京达佳互联信息技术有限公司 | Hotword generation method, device, server and storage medium |
CN112000865A (en) * | 2020-07-22 | 2020-11-27 | 北京达佳互联信息技术有限公司 | Hot word generation method, device, server and storage medium |
CN112182378A (en) * | 2020-09-28 | 2021-01-05 | 厦门美柚股份有限公司 | Message pushing method, device, terminal and medium |
CN112488650A (en) * | 2020-11-26 | 2021-03-12 | 万翼科技有限公司 | Conference atmosphere adjusting method, electronic equipment and related products |
WO2022199494A1 (en) * | 2021-03-23 | 2022-09-29 | 华为技术有限公司 | User interest-based content recommendation method, and terminal device |
CN113407821A (en) * | 2021-05-30 | 2021-09-17 | 咸宁方片互娱网络有限公司 | Method and system for recommending dynamic content of cell, intelligent terminal and server |
CN113256441A (en) * | 2021-06-03 | 2021-08-13 | 探探文化发展(北京)有限公司 | User recommendation method, device, equipment and storage medium in social scene |
CN114880713B (en) * | 2022-06-30 | 2022-09-27 | 深圳红途科技有限公司 | User behavior analysis method, device, equipment and medium based on data link |
CN114880713A (en) * | 2022-06-30 | 2022-08-09 | 深圳红途科技有限公司 | User behavior analysis method, device, equipment and medium based on data link |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107784092A (en) | A kind of method, server and computer-readable medium for recommending hot word | |
Heidari et al. | Using transfer learning approach to implement convolutional neural network model to recommend airline tickets by using online reviews | |
CN103339623B (en) | It is related to the method and apparatus of Internet search | |
CN106599022B (en) | User portrait forming method based on user access data | |
US8676730B2 (en) | Sentiment classifiers based on feature extraction | |
US20090265338A1 (en) | Contextual ranking of keywords using click data | |
US20130060769A1 (en) | System and method for identifying social media interactions | |
US10152478B2 (en) | Apparatus, system and method for string disambiguation and entity ranking | |
JP2011154668A (en) | Method for recommending the most appropriate information in real time by properly recognizing main idea of web page and preference of user | |
CN105843796A (en) | Microblog emotional tendency analysis method and device | |
Raghuvanshi et al. | A brief review on sentiment analysis | |
CN107506472A (en) | A kind of student browses Web page classification method | |
Kiran et al. | User specific product recommendation and rating system by performing sentiment analysis on product reviews | |
JP6130270B2 (en) | Comment list public server, program and method for sorting and specifying comment sets corresponding to media contents | |
Anh et al. | Extracting user requirements from online reviews for product design: A supportive framework for designers | |
KR101543680B1 (en) | Entity searching and opinion mining system of hybrid-based using internet and method thereof | |
RU2683482C2 (en) | Method of displaying relevant contextual information | |
Bach et al. | Big data text mining in the financial sector | |
CN107908749B (en) | Character retrieval system and method based on search engine | |
Luo et al. | Product review information extraction based on adjective opinion words | |
AleEbrahim et al. | Summarising customer online reviews using a new text mining approach | |
Wu et al. | Understanding customers using Facebook Pages: Data mining users feedback using text analysis | |
JP6152333B2 (en) | Apparatus, server, program, and method for specifying summary word corresponding to media content | |
US8195458B2 (en) | Open class noun classification | |
KR101265467B1 (en) | Method for extracting experience and classifying verb in blog |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180309 |
|
WW01 | Invention patent application withdrawn after publication |