CN108280200A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN108280200A CN108280200A CN201810085111.5A CN201810085111A CN108280200A CN 108280200 A CN108280200 A CN 108280200A CN 201810085111 A CN201810085111 A CN 201810085111A CN 108280200 A CN108280200 A CN 108280200A
- Authority
- CN
- China
- Prior art keywords
- text
- label
- user
- search term
- access request
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
Abstract
The embodiment of the present application discloses the method and apparatus for pushed information.One specific implementation mode of this method includes：It is directed to the access request of targeted sites in response to receiving user, determines whether access request includes the search term of user；In response to determining that access request includes the search term of user, following steps are executed：By search term input tag recognition model trained in advance, the label of the user property for characterizing user is obtained, wherein tag recognition model is used to characterize the correspondence of the search term and the label of the user property for characterizing user of user；Matching relationship based on obtained label and pre-set label and text, matches the first text from preset text collection；The first text matched is pushed.This embodiment improves the diversity of information push.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for being used for pushed information.
Background technology
Information pushes, and is exactly " web broadcast ", is by certain technical standard or agreement, on the internet by regular
The information that user needs is transmitted to reduce a new technology of information overload.The information for being presently used for pushing generally comprises following
Two kinds of set-up modes：The first is that different information is arranged according to different websites (page) by technical staff, when user's initiation pair
When the operation requests of specific webpage, then presupposed information corresponding with the page is shown；Second is that technical staff pre-sets system
One for website information (such as：You are good, and today, weather was * * *).
Invention content
The embodiment of the present application proposes the method and apparatus for pushed information.
In a first aspect, the embodiment of the present application provides a kind of method for pushed information, this method includes：In response to connecing
The access request that user is directed to targeted sites is received, determines whether access request includes the search term of user；It is visited in response to determining
It asks that request includes the search term of user, executes following steps：By search term input tag recognition model trained in advance, used
In the label for the user property for characterizing the user, wherein tag recognition model is used to characterize the search term of user and is used for table
Take over the correspondence of the label of the user property at family for use；Based on obtained label and pre-set label and text
With relationship, the first text is matched from preset text collection；The first text matched is pushed.
In some embodiments, this method further includes：In response to determining that access request does not include the search term of user, execute
Following steps：Obtain pre-stored, user historical search set of words；By the historical search word in historical search set of words point
Other input label identification model obtains the tag set of the user property for characterizing user；Based on obtained tag set
In label and pre-set label and text matching relationship, the second text is matched from preset text collection；
The second text matched is pushed.
In some embodiments, based on the label and pre-set label and text in obtained tag set
Matching relationship matches the second text from preset text collection, including：Determine in tag set whether include at least two
Sub-set of tags is closed, wherein sub-set of tags conjunction includes at least two labels and included label is identical；In response to determining tally set
Conjunction includes that at least two sub-set of tags are closed, and executes following steps：Each label in being closed at least two sub-set of tags
Set determines the quantitative value of the label during the sub-set of tags is closed；Maximum quantitative value institute in identified each quantitative value is right
The label answered is determined as target labels；It is closed based on the matching of identified target labels and pre-set label and text
System, matches the second text from preset text collection.
In some embodiments, the text in text collection has preset text priority；And based on obtained
The matching relationship of label and pre-set label and text matches the first text from preset text collection, including：
Matching relationship based on obtained label and pre-set label and text, mesh is matched from preset text collection
Mark text collection；Based on the text priority of each text in target text set, first is chosen from target text set
Text.
In some embodiments, training obtains tag recognition model as follows：Obtain multiple sample searches words with
And the label corresponding to each sample searches word demarcate in advance, in multiple sample searches words；It, will using machine learning method
Each sample searches word in multiple sample searches words is as input, by each of sample searches words demarcate in advance, multiple
For label corresponding to sample searches word as output, training obtains tag recognition model.
Second aspect, the embodiment of the present application provide a kind of device for pushed information, which includes：It determines single
Member is configured to be directed to the access request of targeted sites in response to receiving user, determines whether access request includes user's
Search term；First execution unit is configured to, in response to determining that access request includes the search term of user, execute following steps：
By search term input tag recognition model trained in advance, the label of the user property for characterizing user is obtained, wherein label
Identification model is used to characterize the correspondence of the search term and the label of the user property for characterizing user of user；Based on gained
The matching relationship of the label and pre-set label and text that arrive, matches the first text from preset text collection；
The first text matched is pushed.
In some embodiments, which further includes：Second execution unit is configured in response to determining access request not
Search term including user executes following steps：Obtain pre-stored, user historical search set of words；By historical search
Historical search word in set of words distinguishes input label identification model, obtains the tally set of the user property for characterizing user
It closes；Based on the matching relationship of label and pre-set label and text in obtained tag set, from preset text
The second text is matched in this set；The second text matched is pushed.
In some embodiments, the second execution unit includes：Determining module is configured to determine whether wrap in tag set
Include the conjunction of at least two sub-set of tags, wherein sub-set of tags conjunction includes at least two labels and included label is identical；Execute mould
Block is configured to, in response to determining that tag set includes that at least two sub-set of tags are closed, execute following steps：For at least two
Each sub-set of tags during a sub-set of tags is closed is closed, and determines the quantitative value of the label during the sub-set of tags is closed；It will be identified each
Label in a quantitative value corresponding to maximum quantitative value is determined as target labels；Based on identified target labels and in advance
The label of setting and the matching relationship of text, match the second text from preset text collection.
In some embodiments, the text in text collection has preset text priority；And first execution unit
Including：Matching module is configured to the matching relationship based on obtained label and pre-set label and text, from pre-
If text collection in match target text set；Module is chosen, is configured to based on each text in target text set
This text priority, chooses the first text from target text set.
In some embodiments, training obtains tag recognition model as follows：Obtain multiple sample searches words with
And the label corresponding to each sample searches word demarcate in advance, in multiple sample searches words；It, will using machine learning method
Each sample searches word in multiple sample searches words is as input, by each of sample searches words demarcate in advance, multiple
For label corresponding to sample searches word as output, training obtains tag recognition model.
The third aspect, the embodiment of the present application provide a kind of server, including：One or more processors；Storage device,
For storing one or more programs, when one or more programs are executed by one or more processors so that one or more
The method that processor realizes any embodiment in the above-mentioned method for pushed information.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, which realizes any embodiment in the above-mentioned method for pushed information method when being executed by processor.
Method and apparatus provided by the embodiments of the present application for pushed information, by being directed to mesh in response to receiving user
The access request of labeling station point, determines whether access request includes the search term of user；In response to determining that access request includes user
Search term, execute following steps：By search term input tag recognition model trained in advance, the use for characterizing user is obtained
The label of family attribute；Matching relationship based on obtained label and pre-set label and text, from preset text
The first text is matched in set；The first text matched is pushed, so as in response to getting searching for user
Search term is identified as label by the model pre-established, and then text corresponding with the label identified is pushed away by rope word
User is given, the diversity of information push is improved.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for pushed information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for pushed information of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for pushed information of the application；
Fig. 6 is adapted for the structural schematic diagram of the computer system of the server for realizing the embodiment of the present application.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the implementation of the method for pushed information or the device for pushed information that can apply the application
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with server 105 with using terminal equipment 101,102,103, to receive or send out
Send message etc..Various client applications, such as web browser applications, purchase can be installed on terminal device 101,102,103
Species application, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) it is player, on knee portable
Computer and desktop computer etc..
Server 105 can be to provide the server of various services, such as to being shown on terminal device 101,102,103
Webpage provides the backstage web page server supported.Backstage web page server can to the data such as the web access requests that receive into
The processing such as row analysis, and handling result (such as first text) is fed back into terminal device.
It should be noted that the method for pushed information that the embodiment of the present application is provided generally is held by server 105
Row, correspondingly, the device for pushed information is generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow of one embodiment of the method for pushed information according to the application is shown
200.This is used for the method for pushed information, includes the following steps：
Step 201, it is directed to the access request of targeted sites in response to receiving user, determines whether access request includes using
The search term at family.
In the present embodiment, it is used for electronic equipment (such as the service shown in FIG. 1 of the method operation of pushed information thereon
Device) it can be asked for the access of targeted sites by wired connection mode or radio connection in response to receiving user
It asks, determines whether access request includes the search term of user.Wherein, targeted sites can be being accessed for user of pre-establishing
Website, and be directed to targeted sites pre-sets and needs to be pushed to the text of user (such as " you are good, wishes that your kind today
Feelings ").Specifically, above-mentioned electronic equipment can receive user by client (such as terminal device shown in FIG. 1 101,102,
103) access request for targeted sites sent.Access request can be inbound request or searching request of user etc..
Search term is specifically as follows vocabulary, sentence or voice input by user etc., such as " A mobile phones how much ".Herein, access is asked
It may include search term input by user to ask, and may also be only the inbound request of user without including search term input by user.
Step 202, in response to determining that access request includes the search term of user, following steps are executed：Search term is inputted
Trained tag recognition model in advance, obtains the label of the user property for characterizing user；Based on obtained label and
The matching relationship of pre-set label and text matches the first text from preset text collection；Will matched
One text is pushed.
In the present embodiment, being used for the electronic equipment of the method operation of pushed information thereon can access in response to determining
Request includes the search term of user, executes following steps：
Step 2021, it by search term input tag recognition model trained in advance, obtains the user for characterizing user and belongs to
The label of property.
Wherein, user property may include the natural qualities such as the gender of user, age, can also include occupation, birthplace
Etc. social properties, can also include the personal attributes such as interest, hobby.Label can include but is not limited at least one of following：Text
Word, number, vocabulary, phrase.Illustratively, the label at the age for characterizing user may include number, such as " 18 years old with
Under "；The label of occupation for characterizing user may include vocabulary, such as " engineer ".Obtained label can be one
Or it is multiple.Tag recognition model can be used for characterizing pair of the search term and the label of the user property for characterizing user of user
It should be related to.
Specifically, as an example, tag recognition model can be technical staff based on to a large amount of user search term and
The statistics of the label of user property for characterizing user and pre-establish, be stored with multiple search terms with for characterizing user
User property label correspondence mapping table；Can also be technical staff based on the statistics to mass data and
It pre-sets and stores into above-mentioned electronic equipment, similar to the label progress in multiple search terms and default tag set
Degree calculates the calculation formula to obtain.The result of calculation of the calculation formula is determined for each search in multiple search terms
Label corresponding to word.Specifically, for each search term in multiple search terms, can will be calculated and the search term
The highest label of similarity is determined as the label corresponding to the search term.
In some optional realization methods of the present embodiment, above-mentioned tag recognition model can train as follows
It obtains：
First, above-mentioned electronic equipment can obtain multiple sample searches words and demarcate in advance, multiple sample searches words
In each sample searches word corresponding to label.
Then, above-mentioned electronic equipment can utilize machine learning method, and each sample in multiple sample searches words is searched
Rope word is as input, using the label corresponding to each sample searches word in sample searches words demarcate in advance, multiple as defeated
Go out, training obtains tag recognition model.Specifically, above-mentioned electronic equipment can use model-naive Bayesian (Naive
Bayesian Model, NBM) or the model for classification such as support vector machines (Support Vector Machine, SVM),
Using above-mentioned multiple sample searches words as the input of model, by each sample in above-mentioned sample searches word demarcating in advance, multiple
Label corresponding to this search term is as output, and using machine learning method, training obtains tag recognition model.
Particularly, above-mentioned before by search term input label identification model when search term input by user is sentence
Electronic equipment can also carry out search term cutting word processing, and will treated search term input label identification model.As showing
" A mobile phones how much " example, search term are, it may include " A mobile phones " and " how much " to carry out cutting word treated search term, into
And the label identified may include " mobile phone " and " money is sensitive ".It should be noted that cutting word is to study and answer extensively at present
Known technology, details are not described herein.
Step 2022, the matching relationship based on obtained label and pre-set label and text, from preset
The first text is matched in text collection.
Wherein, preset text collection may include that technical staff waits for push text by what above-mentioned electronic equipment pre-entered
This.First text can be text in preset text collection, being matched by above-mentioned search term input by user.In advance
The matching relationship of setting can be the correspondence of the pre-set label of technical staff and the text in above-mentioned text collection.Tool
Body, as an example, matching relationship, which can be a label, corresponds to a text in text collection；Or it is a label pair
Answer multiple texts in text collection.For example, obtained label is " nutritionist ", preset text corresponding with the label can
Think that " you are good, and the technical ability that nutritionist should have is as follows：……”；Alternatively, obtained label is " film ", the preset and mark
It may include " you are good, and A cin positive films are being shown " and " you are good, recommends the A films that highest scores for you " to sign corresponding text.It needs
It is noted that when going out multiple texts by tag match, it can be using multiple texts as the first text.
In some optional realization methods of the present embodiment, the text in above-mentioned text collection has preset text excellent
First grade, text priority are used to characterize the push sequence of the text in text collection.Specifically, text priority can use number
The expressions such as word, word, symbol.For example, the height of priority can be characterized with the size of number, number is smaller, and priority is got over
It is high.Herein, the matching relationship based on obtained label and pre-set label and text, above-mentioned electronic equipment can be with
The first text is matched from preset text collection as follows：
First, the matching relationship based on obtained label and pre-set label and text, above-mentioned electronic equipment
Target text set can be matched from preset text collection.Wherein, target text set may include at least two texts
This.Herein, obtained label can be one or more.The matching relationship of label and text can be a label pair
Multiple texts or a label are answered to correspond to a text.In turn, when obtained label is multiple or label and text
Matching relationship is a label when corresponding to multiple texts, above-mentioned electronic equipment can be matched from preset text collection including
The target text set of at least two texts.
Then, the text priority based on each text in target text set, above-mentioned electronic equipment can be from targets
The first text is chosen in text collection.Specifically, above-mentioned electronic equipment can be by text highest priority in target text set
Text be determined as the first text.
Step 2023, the first text matched is pushed.
Specifically, above-mentioned electronic equipment the first text matched can be pushed to where user client (such as
Terminal device shown in FIG. 1 101,102,103).
It is a signal according to the application scenarios of the method for pushed information of the present embodiment with continued reference to Fig. 3, Fig. 3
Figure.In the application scenarios of Fig. 3, server 301 can be directed to the access request 302 of targeted sites in response to receiving user
(such as the access request 302 that can be sent by terminal device 303 in response to receiving user), determines that access request 302 is
The no search term 3021 including user；Then, server 301 can be in response to determining that access request 302 includes the search of user
Word 3021 (such as " A films ") executes following steps：Search term 3021 is inputted to tag recognition model trained in advance, is obtained
The label 304 (such as " film ") of user property for characterizing user, wherein tag recognition model can be used for characterizing user
Search term with for characterize user user property label correspondence；Based on obtained label and pre-set
Label and text matching relationship, the first text 305 is matched from preset text collection, and (such as " you are good, is showing
Film include：A；B；C”)；Finally, server 301 can push the first text 305 matched.Specifically, such as
Shown in Fig. 3, the first text 305 can be pushed to terminal device 303 by server 301.
The method that above-described embodiment of the application provides in response to receiving user for the access of targeted sites by asking
It asks, determines whether access request includes the search term of user；In response to determine access request include user search term, execute with
Lower step：By search term input tag recognition model trained in advance, the label of the user property for characterizing user is obtained；Base
In obtained label and the matching relationship of pre-set label and text, first is matched from preset text collection
Text；The first text matched is pushed, so as in response to the search term for getting user, by pre-establishing
Model search term is identified as label, and then text corresponding with the label identified is pushed to user, improves letter
Cease the diversity of push.
With further reference to Fig. 4, it illustrates the flows 400 of another embodiment of the method for pushed information.The use
In the flow 400 of the method for pushed information, include the following steps：
Step 401, it is directed to the access request of targeted sites in response to receiving user, determines whether access request includes using
The search term at family.
In the present embodiment, it is used for electronic equipment (such as the service shown in FIG. 1 of the method operation of pushed information thereon
Device) it can be asked for the access of targeted sites by wired connection mode or radio connection in response to receiving user
It asks, determines whether access request includes the search term of user.Wherein, targeted sites can be being accessed for user of pre-establishing
Website, and targeted sites are directed to, pre-set the text for needing to be pushed to user.Specifically, above-mentioned electronic equipment can connect
Receive the access request for targeted sites that user is inputted by client.Access request can be user inbound request or
Searching request etc..Search term is specifically as follows vocabulary, sentence or voice input by user etc..Herein, access request can be with
Including search term input by user, the inbound request of user is may also be only without including search term input by user.
Step 402, in response to determining that access request does not include the search term of user, following steps are executed：Acquisition is deposited in advance
Storage, user historical search set of words；Historical search word in historical search set of words is distinguished into input label identification model,
Obtain the tag set of the user property for characterizing user；Based in obtained tag set label and pre-set
Label and text matching relationship, the second text is matched from preset text collection；By the second text matched into
Row push.
In the present embodiment, being used for the electronic equipment of the method operation of pushed information thereon can access in response to determining
Request does not include the search term of user, executes following steps：
Step 4021, pre-stored, user historical search set of words is obtained.
Wherein, historical search word can be that user passes through client (such as terminal shown in FIG. 1 in default historical time section
Equipment 101,102,103) input search term.It is understood that in above-mentioned default historical time section, above-mentioned electronic equipment
Search term input by user can be received and search term input by user is stored.
Step 4022, the historical search word in historical search set of words is inputted into above-mentioned tag recognition model respectively, obtained
Tag set for the user property for characterizing user.
It should be noted that may include identical search term in historical search set of words；May include in tag set
Identical label.For example, user is in default historical time section " 0:00-24:10 in 00 ":00 and 22:00 has input " A
Film ", then historical search set of words may include two search terms " A film ", and tag set may include two labels " electricity
Shadow ".
Step 4023, the matching based on label and pre-set label and text in obtained tag set is closed
System, matches the second text from preset text collection.
Wherein, the label included by tag set can be one or more.Preset text collection may include technology
The text to be pushed that personnel are pre-entered by above-mentioned electronic equipment.Second text can be the historical search by above-mentioned user
Text in the preset text collection that word matches.Pre-set matching relationship can be the pre-set mark of technical staff
The correspondence of label and the text in above-mentioned text collection.It should be noted that when going out multiple texts by tag match, it can
Using by multiple texts as the second text.
In some optional realization methods of the present embodiment, based in obtained tag set label and in advance
The label of setting and the matching relationship of text, above-mentioned electronic equipment can be matched from preset text collection as follows
Go out the second text：
First, whether it includes that at least two sub-set of tags are closed that above-mentioned electronic equipment can determine in tag set, wherein mark
Bamboo slips used for divination or drawing lots set may include at least two labels and included label is identical.For example, the label included by tag set is " electricity
Shadow；Film；Film；Books ", then can be by " film；Film；Film " is determined as a sub-set of tags and closes, due to above-mentioned label
Only include " books " label in set, therefore above-mentioned tag set " film；Film；Film；Books " do not include at least two
Sub-set of tags is closed.
Then, above-mentioned electronic equipment can be executed in response to determining that tag set includes that at least two sub-set of tags are closed
Following steps：
Step 40231, each sub-set of tags in being closed at least two sub-set of tags is closed, in determining that the sub-set of tags is closed
Label quantitative value.
As an example, tag set is " film；Film；Film；Books；Books ".Sub-set of tags is combined into " film；Film；
Film " and " books；Books ".Above-mentioned electronic equipment can determine that sub-set of tags closes " film；Film；The number of label in film "
Magnitude is " 3 "；Sub-set of tags closes " books；The quantitative value of label in books " is " 2 ".
Step 40232, the label corresponding to maximum quantitative value in identified each quantitative value is determined as target mark
Label.
For example, closing " film for sub-set of tags determined by above-mentioned electronic equipment；Film；The quantity of label in film "
Value is " 3 " and sub-set of tags closes " books；The quantitative value of label in books " is " 2 ", since numerical value " 3 " is more than numerical value " 2 ",
Therefore the label " film " corresponding to numerical value " 3 " can be determined as target labels by above-mentioned electronic equipment.
Step 40233, based on identified target labels and the matching relationship of pre-set label and text, from pre-
If text collection in match the second text.
Wherein, pre-set matching relationship can be in the pre-set label of technical staff and above-mentioned text collection
The correspondence of text.Specifically, as an example, matching relationship, which can be a label, corresponds to a text in text collection
This；Or multiple texts in text collection are corresponded to for a label.For example, target labels are " film ", the preset and mesh
It can be that " you are good, and the film shown includes to mark the corresponding text of label：A；B；C”.It should be noted that when passing through target
It, can be using multiple texts as the second text when tag match goes out multiple texts.
Step 4024, the second text matched is pushed.
Specifically, above-mentioned electronic equipment the second text matched can be pushed to where user client (such as
Terminal device shown in FIG. 1 101,102,103).
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the method for pushed information in the present embodiment
Flow 400 highlight the performed step when access request does not include the search term of user.The present embodiment describes as a result,
Scheme can introduce the historical search word of user, to improve the flexibility of information push, and further improve letter
Cease the diversity of push.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for pushing letter
One embodiment of the device of breath, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 for pushed information of the present embodiment includes：Determination unit 501 and first executes list
Member 502.Wherein it is determined that unit 501 is configured to be directed to the access request of targeted sites in response to receiving user, determines and access
Whether request includes the search term of user；First execution unit 502 is configured in response to determining that access request includes user's
Search term executes following steps：By search term input tag recognition model trained in advance, the user for characterizing user is obtained
The label of attribute, wherein the search term and the user property for characterizing user that tag recognition model can be used for characterizing user
Label correspondence；Matching relationship based on obtained label and pre-set label and text, from preset
The first text is matched in text collection；The first text matched is pushed.
In the present embodiment, determination unit 501 can be by wired connection mode or radio connection in response to connecing
The access request that user is directed to targeted sites is received, determines whether access request includes the search term of user.Wherein, targeted sites
It can be the website accessed for user pre-established, and be directed to targeted sites, pre-set the text for needing to be pushed to user
This (such as " you are good, wish your good mood today ").(such as schemed by client specifically, determination unit 501 can receive user
Terminal device 101 shown in 1,102,103) input the access request for targeted sites.Access request can be user's
Inbound request or searching request etc..Search term is specifically as follows vocabulary, sentence or voice input by user etc..Herein,
Access request may include search term input by user, may also be only the inbound request of user without including input by user search
Rope word.
In the present embodiment, the first execution unit 502 can be held in response to determining that access request includes the search term of user
Row following steps：
Step 5021, it by search term input tag recognition model trained in advance, obtains the user for characterizing user and belongs to
The label of property.
Wherein, user property may include the natural qualities such as the gender of user, age, can also include occupation, birthplace
Etc. social properties, can also include the personal attributes such as interest, hobby.Label can include but is not limited at least one of following：Text
Word, number, vocabulary, phrase.Obtained label can be one or more.Tag recognition model can be used for characterizing user's
The correspondence of search term and the label of the user property for characterizing user.
Step 5022, the matching relationship based on obtained label and pre-set label and text, from preset
The first text is matched in text collection.
Wherein, preset text collection may include that technical staff waits for push text by what above-mentioned electronic equipment pre-entered
This.First text can be the text matched by above-mentioned search term input by user.Pre-set matching relationship can be with
For the correspondence of the text in the pre-set label of technical staff and above-mentioned text collection.
Step 5023, the first text matched is pushed.
Specifically, the first text matched can be pushed to the client (example where user by the first execution unit 502
Terminal device 101 as shown in Figure 1,102,103).
In some optional realization methods of the present embodiment, the device 500 for pushed information can also include：Second
Execution unit (not shown) is configured to, in response to determining that access request does not include the search term of user, execute following step
Suddenly：Obtain pre-stored, user historical search set of words；Historical search word in historical search set of words is inputted respectively
Tag recognition model obtains the tag set of the user property for characterizing user；Based on the mark in obtained tag set
The matching relationship of label and pre-set label and text, matches the second text from preset text collection；It will matching
The second text gone out is pushed.
In some optional realization methods of the present embodiment, the second execution unit may include：Determining module is (in figure not
Show), it is configured to determine in tag set whether include that at least two sub-set of tags are closed, wherein sub-set of tags conjunction can wrap
It includes at least two labels and included label is identical；Execution module (not shown) is configured in response to determining label
Set includes that at least two sub-set of tags are closed, and executes following steps：Each label in being closed at least two sub-set of tags
Subclass determines the quantitative value of the label during the sub-set of tags is closed；By maximum quantitative value institute in identified each quantitative value
Corresponding label is determined as target labels；It is closed based on the matching of identified target labels and pre-set label and text
System, matches the second text from preset text collection.
In some optional realization methods of the present embodiment, the text in text collection can have preset text excellent
First grade；And first execution unit 502 may include：Matching module (not shown) is configured to be based on obtained mark
The matching relationship of label and pre-set label and text, matches target text set from preset text collection；Choosing
Modulus block (not shown) is configured to the text priority based on each text in target text set, from target text
The first text is chosen in this set.
In some optional realization methods of the present embodiment, tag recognition model can be trained as follows
It arrives：Obtain multiple sample searches words and each sample searches word demarcate in advance, in multiple sample searches words corresponding to
Label；It will be demarcated in advance using each sample searches word in multiple sample searches words as input using machine learning method
, label corresponding to each sample searches word in multiple sample searches words as output, training obtains tag recognition model.
The device that above-described embodiment of the application provides is directed to Target Station by determination unit 501 in response to receiving user
The access request of point, determines whether access request includes the search term of user；Then the first execution unit 502 is visited in response to determining
It asks that request includes the search term of user, executes following steps：By search term input tag recognition model trained in advance, used
In the label of the user property of characterization user；Matching based on obtained label and pre-set label and text is closed
System, matches the first text from preset text collection；The first text matched is pushed, so as in response to
Search term is identified as label by the search term for getting user by the model that pre-establishes, so by with the label that identifies
Corresponding text is pushed to user, improves the diversity of information push.
Below with reference to Fig. 6, it illustrates the computer systems 600 suitable for the server for realizing the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various actions appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
It is connected to I/O interfaces 605 with lower component：Importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 610, as needed in order to be read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two arbitrarily combines.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.
The more specific example of computer readable storage medium can include but is not limited to：Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media may include the data letter propagated in a base band or as a carrier wave part
Number, wherein carrying computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses
The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet
Include determination unit and the first execution unit.Wherein, the title of these units is not constituted to the unit itself under certain conditions
Restriction, for example, determination unit is also described as " determining whether access request includes the unit of search term ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should
Device：It is directed to the access request of targeted sites in response to receiving user, determines whether access request includes the search term of user；
In response to determining that access request includes the search term of user, following steps are executed：Search term input label trained in advance is known
Other model obtains the label of the user property for characterizing user, wherein tag recognition model is used to characterize the search term of user
With the correspondence of the label of the user property for characterizing user；Based on obtained label and pre-set label with
The matching relationship of text matches the first text from preset text collection；The first text matched is pushed.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for pushed information, including：
It is directed to the access request of targeted sites in response to receiving user, determines whether the access request includes the user's
Search term；
Include the search term of the user in response to the determination access request, executes following steps：Described search word is inputted
Trained tag recognition model in advance, obtains the label of the user property for characterizing the user, wherein the tag recognition
Model is used to characterize the correspondence of the search term and the label of the user property for characterizing user of user；Based on obtained
The matching relationship of label and pre-set label and text matches the first text from preset text collection；General
The first text allotted is pushed.
2. according to the method described in claim 1, wherein, the method further includes：
Do not include the search term of the user in response to the determination access request, executes following steps：Obtain it is pre-stored,
The historical search set of words of the user；Historical search word in the historical search set of words is inputted the label respectively to know
Other model obtains the tag set of the user property for characterizing the user；Based on the label in obtained tag set
And the matching relationship of pre-set label and text, the second text is matched from preset text collection；It will match
The second text pushed.
3. according to the method described in claim 2, wherein, the label based in obtained tag set and set in advance
The matching relationship of the label and text set matches the second text from preset text collection, including：
Determine in the tag set whether include that at least two sub-set of tags are closed, wherein sub-set of tags conjunction includes at least two
Label and included label is identical；
Include that at least two sub-set of tags are closed in response to the determination tag set, executes following steps：For it is described at least
Each sub-set of tags during two sub-set of tags are closed is closed, and determines the quantitative value of the label during the sub-set of tags is closed；It will be identified
Label in each quantitative value corresponding to maximum quantitative value is determined as target labels；Based on identified target labels and in advance
The matching relationship of the label and text that are first arranged matches the second text from preset text collection.
4. according to the method described in claim 1, wherein, the text in the text collection has preset text priority；
And
The matching relationship based on obtained label and pre-set label and text, from preset text collection
The first text is matched, including：
Matching relationship based on obtained label and pre-set label and text, matches from preset text collection
Go out target text set；
Based on the text priority of each text in the target text set, first is chosen from the target text set
Text.
5. according to the method described in one of claim 1-4, wherein the tag recognition model is trained as follows
It arrives：
It obtains multiple sample searches words and each sample searches word demarcate in advance, in the multiple sample searches word institute is right
The label answered；
It will be marked in advance using each sample searches word in the multiple sample searches word as input using machine learning method
For the label corresponding to each sample searches word in fixed, the multiple sample searches word as output, training obtains label knowledge
Other model.
6. a kind of device for pushed information, including：
Determination unit is configured to be directed to the access request of targeted sites in response to receiving user, determines the access request
Whether the search term of the user is included；
First execution unit, be configured to include in response to the determination access request user search term, execute following
Step：By described search word input tag recognition model trained in advance, the user property for characterizing the user is obtained
Label, wherein the tag recognition model is used to characterize the label of the search term and the user property for characterizing user of user
Correspondence；Matching relationship based on obtained label and pre-set label and text, from preset text set
The first text is matched in conjunction；The first text matched is pushed.
7. device according to claim 6, wherein described device further includes：
Second execution unit is configured to not include the search term of the user in response to the determination access request, execute with
Lower step：Obtain the historical search set of words of pre-stored, the described user；History in the historical search set of words is searched
Rope word inputs the tag recognition model respectively, obtains the tag set of the user property for characterizing the user；Based on institute
The matching relationship of label and pre-set label and text in obtained tag set, from preset text collection
Allot the second text；The second text matched is pushed.
8. device according to claim 7, wherein second execution unit includes：
Determining module is configured to determine in the tag set whether include that at least two sub-set of tags are closed, wherein label
Set includes at least two labels and included label is identical；
Execution module is configured in response to the determination tag set include that at least two sub-set of tags are closed, execute following
Step：Each sub-set of tags in being closed at least two sub-set of tags is closed, and determines the label during the sub-set of tags is closed
Quantitative value；Label corresponding to maximum quantitative value in identified each quantitative value is determined as target labels；Based on really
The matching relationship of fixed target labels and pre-set label and text matches the second text from preset text collection
This.
9. device according to claim 6, wherein the text in the text collection has preset text priority；
And
First execution unit includes：
Matching module is configured to the matching relationship based on obtained label and pre-set label and text, from pre-
If text collection in match target text set；
Module is chosen, the text priority based on each text in the target text set is configured to, from the target
The first text is chosen in text collection.
10. according to the device described in one of claim 6-9, wherein the tag recognition model is trained as follows
It arrives：
It obtains multiple sample searches words and each sample searches word demarcate in advance, in the multiple sample searches word institute is right
The label answered；
It will be marked in advance using each sample searches word in the multiple sample searches word as input using machine learning method
For the label corresponding to each sample searches word in fixed, the multiple sample searches word as output, training obtains label knowledge
Other model.
11. a kind of server, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-5.
12. a kind of computer readable storage medium, is stored thereon with computer program, wherein when the program is executed by processor
Realize the method as described in any in claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085111.5A CN108280200B (en) | 2018-01-29 | 2018-01-29 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085111.5A CN108280200B (en) | 2018-01-29 | 2018-01-29 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108280200A true CN108280200A (en) | 2018-07-13 |
| CN108280200B CN108280200B (en) | 2021-11-09 |
Family
ID=62805587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810085111.5A Active CN108280200B (en) | 2018-01-29 | 2018-01-29 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280200B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255036A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109472028A (en) * | 2018-10-31 | 2019-03-15 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109977319A (en) * | 2019-04-04 | 2019-07-05 | 睿驰达新能源汽车科技（北京）有限公司 | A kind of method and device of generation behavior label |
| CN110321544A (en) * | 2019-07-08 | 2019-10-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN111125566A (en) * | 2019-12-11 | 2020-05-08 | 贝壳技术有限公司 | Information acquisition method and device, electronic equipment and storage medium |
| CN112348614A (en) * | 2019-11-27 | 2021-02-09 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
| CN112860995A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Interaction method, device, client, server and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020107853A1 (en) * | 2000-07-26 | 2002-08-08 | Recommind Inc. | System and method for personalized search, information filtering, and for generating recommendations utilizing statistical latent class models |
| US20090077057A1 (en) * | 2007-09-18 | 2009-03-19 | Palo Alto Research Center Incorporated | mixed-model recommender for leisure activities |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
| CN103870505A (en) * | 2012-12-17 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Query term recommending method and query term recommending system |
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
| CN104239458A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Method and device for representing search results |
| CN104866474A (en) * | 2014-02-20 | 2015-08-26 | 阿里巴巴集团控股有限公司 | Personalized data searching method and device |
| CN105045889A (en) * | 2015-07-29 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Information pushing method and apparatus |
| CN105095406A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for voice search based on user feature |
| CN105095286A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Page recommendation method and device |
| CN105893440A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Associated application recommendation method and apparatus |
| CN107590255A (en) * | 2017-09-19 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
-
2018
- 2018-01-29 CN CN201810085111.5A patent/CN108280200B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020107853A1 (en) * | 2000-07-26 | 2002-08-08 | Recommind Inc. | System and method for personalized search, information filtering, and for generating recommendations utilizing statistical latent class models |
| US20090077057A1 (en) * | 2007-09-18 | 2009-03-19 | Palo Alto Research Center Incorporated | mixed-model recommender for leisure activities |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
| CN103870505A (en) * | 2012-12-17 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Query term recommending method and query term recommending system |
| CN104866474A (en) * | 2014-02-20 | 2015-08-26 | 阿里巴巴集团控股有限公司 | Personalized data searching method and device |
| CN105095286A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Page recommendation method and device |
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
| CN104239458A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Method and device for representing search results |
| CN105095406A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for voice search based on user feature |
| CN105045889A (en) * | 2015-07-29 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Information pushing method and apparatus |
| CN105893440A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Associated application recommendation method and apparatus |
| CN107590255A (en) * | 2017-09-19 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255036A (en) * | 2018-08-31 | 2019-01-22 | 北京字节跳动网络技术有限公司 | Method and apparatus for output information |
| CN109472028A (en) * | 2018-10-31 | 2019-03-15 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109472028B (en) * | 2018-10-31 | 2023-12-15 | 北京字节跳动网络技术有限公司 | Method and device for generating information |
| CN109977319A (en) * | 2019-04-04 | 2019-07-05 | 睿驰达新能源汽车科技（北京）有限公司 | A kind of method and device of generation behavior label |
| CN110321544A (en) * | 2019-07-08 | 2019-10-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN112348614A (en) * | 2019-11-27 | 2021-02-09 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
| CN111125566A (en) * | 2019-12-11 | 2020-05-08 | 贝壳技术有限公司 | Information acquisition method and device, electronic equipment and storage medium |
| CN112860995A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Interaction method, device, client, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108280200B (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280200A (en) | Method and apparatus for pushed information | |
| CN107577807B (en) | Method and device for pushing information | |
| CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
| CN107105031A (en) | Information-pushing method and device | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN106845999A (en) | Risk subscribers recognition methods, device and server | |
| CN108805594A (en) | Information-pushing method and device | |
| CN107295095A (en) | The method and apparatus for pushing and showing advertisement | |
| CN107731229A (en) | Method and apparatus for identifying voice | |
| CN109325213A (en) | Method and apparatus for labeled data | |
| CN107992554A (en) | The searching method and device of the polymerization result of question and answer information are provided | |
| CN109389182A (en) | Method and apparatus for generating information | |
| CN108900612A (en) | Method and apparatus for pushed information | |
| CN107943895A (en) | Information-pushing method and device | |
| CN107360243A (en) | Information-pushing method and device | |
| CN109036397A (en) | The method and apparatus of content for rendering | |
| CN108924218A (en) | Method and apparatus for pushed information | |
| CN108959087A (en) | test method and device | |
| CN106919711A (en) | The method and apparatus of the markup information based on artificial intelligence | |
| CN107451785A (en) | Method and apparatus for output information | |
| CN109684624A (en) | A kind of method and apparatus in automatic identification Order Address road area | |
| CN109214501A (en) | The method and apparatus of information for identification | |
| CN109873756A (en) | Method and apparatus for sending information | |
| CN108629011A (en) | Method and apparatus for sending feedback information | |
| CN109255036A (en) | Method and apparatus for output information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |