CN110110219A - The method and device of user preference is determined according to network behavior - Google Patents
The method and device of user preference is determined according to network behavior Download PDFInfo
- Publication number
- CN110110219A CN110110219A CN201810108024.7A CN201810108024A CN110110219A CN 110110219 A CN110110219 A CN 110110219A CN 201810108024 A CN201810108024 A CN 201810108024A CN 110110219 A CN110110219 A CN 110110219A
- Authority
- CN
- China
- Prior art keywords
- user
- webpage
- category
- access
- class
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012937 correction Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 description 31
- 239000011159 matrix material Substances 0.000 description 14
- 238000011835 investigation Methods 0.000 description 7
- 230000007774 longterm Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 244000089409 Erythrina poeppigiana Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 235000007926 Craterellus fallax Nutrition 0.000 description 1
- 240000007175 Datura inoxia Species 0.000 description 1
- 244000097202 Rathbunia alamosensis Species 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of method and device that user preference is determined according to network behavior.Method includes: to obtain the access information of user, wherein access information includes webpage information, access time;Classification belonging to the webpage for determining user's access according to webpage information;According to classification belonging to access time, webpage, the determining user in predetermined period accesses the number of every class webpage daily;According to number, determine that user accesses the average time of every class webpage and the number variance yields of the every class webpage of access;According to average time, the number variance yields for accessing every class webpage, the preference of the user in predetermined period is determined.Scheme provided by the invention can make full use of the access information generated when user's online, determine user preference, so that network operator be enable adequately to understand user preferences, and then can targetedly provide a user better service.
Description
Technical field
The present invention relates to Internet technology more particularly to a kind of methods and dress that user preference is determined according to network behavior
It sets.
Background technique
Currently, with the development of internet technology, demand of the user to network service is also higher and higher.For network operation
For quotient, it is to be understood that the preference of user is transformed network further according to user preference, optimizes network, designs precision marketing set meal,
And then service level is promoted, to meet increasing user demand.
Inventors have found that user, when accessing to network, bandwidth operator is able to record the internet information of user, and
In the database by these information record.And how to use such information for determining the preference of user, it is those skilled in the art
The technical issues of urgent need to resolve.
Summary of the invention
The present invention provides a kind of method and device that user preference is determined according to network behavior, by the access for obtaining user
Information, according to the Information Statistics of acquisition, user accesses the number of every class webpage in predetermined period, further according to the access time of statistics
Number calculates user and accesses the average time of every class webpage and the number variance yields of the every class webpage of access, ties further according to calculating
Fruit determines that the preference of user in predetermined period, scheme provided by the invention can make full use of the access generated when user's online
Information determines user preference, so that network operator be enable adequately to understand user preferences, and then can targetedly to
User provides preferably service.
The first aspect of the invention is to provide a kind of method for determining user preference according to network behavior, comprising:
Obtain the access information of user, wherein the access information includes webpage information, access time;
Classification belonging to the webpage for determining user's access according to the webpage information;
According to classification belonging to the access time, the webpage, determine that the user described in predetermined period accesses daily
The number of every class webpage;
According to the number, determine that the user accesses the average time of every class webpage and the number of the every class webpage of access
Variance yields;
According to the average time, the number variance yields for accessing every class webpage, the institute in the predetermined period is determined
State the preference of user.
Another aspect of the present invention is to provide a kind of device that user preference is determined according to network behavior, comprising:
Module is obtained, for obtaining the access information of user, wherein when the access information includes webpage information, access
Between;
Category determination module, for according to the webpage information determine webpage that the user accesses belonging to classification;
Number determining module determines in predetermined period for the classification according to belonging to the access time, the webpage
The user accesses the number of every class webpage daily;Computing module, for determining that the user accesses every class according to the number
The average time of webpage and the number variance yields of the every class webpage of access;
Preference determining module, for determining according to the average time, the number variance yields for accessing every class webpage
The preference of the user in the predetermined period.
The method and device provided by the invention that user preference is determined according to network behavior has the technical effect that
The method and device provided in this embodiment that user preference is determined according to network behavior, including obtain user and access net
The access information of page, wherein access information includes webpage information, access time;The net of user's access is determined according to webpage information
Classification belonging to page;According to classification belonging to access time, webpage, determine that user accesses every class webpage daily within a preset time
Number;According to number, determine that user accesses the average time of every class webpage and the number variance yields of the every class webpage of access;Root
According to average time, the number variance yields for accessing every class webpage, the preference of the user in predetermined period is determined.Using the present embodiment institute
The method and device of offer can make full use of the access information that user generates when browsing webpage, accurately determine user's
Preference so as to make Network Provider understand the preference of user, and then promotes service level.
Detailed description of the invention
Fig. 1 is the process of the method that user preference is determined according to network behavior shown in an exemplary embodiment of the invention
Figure;
Fig. 2 is the process of the method that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure;
Fig. 3 is the process of the method that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure;
Fig. 4 is the process of the method that user preference is determined according to network behavior shown in the another exemplary embodiment of the present invention
Figure;
Fig. 5 is the structure of the device that user preference is determined according to network behavior shown in an exemplary embodiment of the invention
Figure;
Fig. 6 is the structure of the device that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure.
Specific embodiment
Fig. 1 is the process of the method that user preference is determined according to network behavior shown in an exemplary embodiment of the invention
Figure.
As shown in Figure 1, the method provided in this embodiment for determining user preference according to network behavior includes:
Step 101, the access information of user is obtained, wherein access information includes webpage information, access time.
Specifically, user when surfing the web webpage, can generate many access informations.What usual user browsed in online
Content is all oneself interested content, and therefore, the access information generated when can be surfed the Internet according to user determines user preferences.
The access information of user can be can recorde in width carrier side, then database is recorded in these access informations
In, browser used by a user also available user access information, then the information that will acquire are sent to the backstage of browser
In database, so that background data base can store the access information of user.The data of record may include surf time, user
ID, source IP address, Target IP, url inventory, access terminals type etc..It, can be direct when needing to carry out preference analysis to user
These information are read from database.Furthermore it is also possible to method provided in this embodiment is stored in the memory of server, and
The processor in server is set to run method provided in this embodiment, to enable the server to execute side provided in this embodiment
Method.Method provided in this embodiment can also be encapsulated into application program, be installed in server, so that server energy
Enough run method provided in this embodiment.
Further, the access information that user accesses webpage can be obtained from the data of acquisition, wherein available complete
The user access information in portion, the also access information of available needs.Meanwhile access information should also be carried out according to user identifier
Classification, to determine the preference of the user according to access information corresponding with user identifier.User identifier can be user mobile phone
Number, account, ip etc..
When practical application, webpage information, the access time that user generates when accessing webpage can be only obtained.Webpage information
It specifically includes: url, web page contents etc..For example, url is http://games.sina.com.Access time refers to that user accesses
The time of webpage, for example, user has accessed the webpage of Sina's game on November 23rd, 2017.
Wherein, user access information can also be daily obtained, the access information of daily user, and the access to acquisition are obtained
Information is analyzed.
Step 102, the classification according to belonging to the webpage that webpage information determines user's access.
Wherein it is possible to the webpage information to acquisition parses, it, can be according to preset rules if webpage information is url
The keyword in url is extracted, webpage classification is determined according to keyword.For example, the symbol such as " " in url, " // " can be removed first
Number, word combination { http games sina com } is obtained, then in preset class library, determination is corresponding with word combination
Classification is game, so that it is determined that classification belonging to the webpage of user's access.
All or part of webpage classifications can be set in class library, such as only storage needs the webpage classification investigated.If
When parsing to webpage information, corresponding webpage classification can not be determined in class library, then can abandon access letter
Data are ceased, abnormal data can also be stored as, it is handled by maintenance personnel.If storing current energy in class library
All webpage classifications enough determined and its corresponding keyword, then webpage classification corresponding with webpage can not be determined at this time, it can
It can be since the data in class library are abundant caused not enough, then can be abnormal number by this visit information data storing
According to by maintenance personnel according to the webpage classification or keyword in abnormal data supplement class library, it can according to the visit of acquisition
Ask the content of abundant information class library.In addition, if what is stored in class library is the webpage classification for needing to investigate and its corresponding pass
Keyword, then when webpage information occur and can not be matched to its corresponding webpage classification, it may be considered that the access of the webpage is believed
Breath is not the range this time investigated, then can not count this visit information.
Step 103, the classification according to belonging to access time, webpage determines that user accesses every class daily in predetermined period
The number of webpage.
Specifically, can all be screened user in the webpage information accessed on the same day according to access time, further according to
Step 102 as a result, determine the corresponding webpage classification of webpage information that filters out, and calculate the number that every class webpage occurs,
It is exactly the number that user accessed such webpage within one day time.If user has browsed multiple webpages in one day,
Multiple type of webpage can be determined within one day.If user's no browsing webpage in one day, intraday at this
Data can use 0 substitution.For example, accessing game class in second day user in the website 5 times that first day user accesses game classification
Other website 0 time.
Further, it can be traversed with traverse user classification corresponding to the webpage information accessed on the same day when first time
As soon as will access the other access times of the web page class when to webpage classification and be set as 1, when traversing the webpage classification for the second time
When, increase by 1 on this basis.The other access times of each web page class can also be initialized as 0, traverse one of net
When page classification, 1 is superimposed in the other access times of the web page class.Webpage can also be accessed using other modes counting user daily
The number of classification, herein with no restrictions.
Wherein it is possible to preset predetermined period according to demand, such as five days, one week, one month etc..Again with default week
Phase is unit, determines that user in predetermined period accesses the number of every class webpage daily.For example, being determined continuous as unit of five days
Five days in, user accesses the number of every class webpage daily.
Specifically, for the ease of being calculated or being analyzed according to statistical result first can be established according to determining data
Matrix:
Wherein, aijThe number of the i-th class webpage is accessed in jth day for user.
Specifically, each row of data represents the number that user accesses classification webpage corresponding to the row daily, i.e., every row in matrix A
The corresponding webpage classification of data be it is identical, as the first row represents the related data of first category webpage.Every columns in matrix A
According to representing on the same day, user accesses every other number of class web page class, the date that every column data generates be it is identical, such as first
Column represent in the predetermined period, the number of every class webpage of first day user access.It altogether include m class webpage in matrix A,
Predetermined period is n days.
Further, the type of webpage that can according to need investigation determines m value, for example, needing to investigate 5 class webpages altogether, then
M can be set to 5, and in each predetermined period, m is equal to 5.
Step 104, according to number, determine that user accesses the average time of every class webpage and the number of the every class webpage of access
Variance yields.
Wherein, the calculation method that user accesses the average time of every class webpage can be with are as follows:
Namely by user, the number of the i-th class webpage of access is added in n days, then divided by n, so that it is determined that user is daily out
Access the average time of the i-th class webpage.
Specifically, the calculation method that user accesses the number variance yields of every class webpage can be with are as follows:
Wherein,Indicate that user accesses the number variance yields of the i-th class webpage
By calculating varianceUser can further be understood and access the number of the i-th class webpage daily for visiting daily
Ask the departure degree of the average time of such webpage.
For the ease of statistics, the second matrix can also be established according to determining average time and number variance yields:
Wherein, average time and the number side of every class webpage are accessed in the second matrix in a predetermined period for user
Difference.
Step 105, according to average time, the number variance yields for accessing every class webpage, the user in predetermined period is determined
Preference.
Wherein it is possible to which continue counting user accesses the number of every class webpage daily, and calculates user's access and do not have class webpage
Total degree determines the forward webpage classification of access total degree, and as user preference.It can also be every by calculating user
It accesses the average value of every class webpage number, is ranked up to webpage classification.When using above-mentioned method of determination, it can count
It is normal to handle the access information stored in database after complete user accesses the number of every class webpage daily, it such as covers, empty
Deng these information capable of being made full use of to carry out user before access information is processed using method provided in this embodiment
Preference analysis, and after access information is processed, it will not influence the analysis result to user.
Specifically, the number that can also access daily each classification webpage according to user in predetermined period determines that user is inclined
It is good, further according to being determined in multiple predetermined periods as a result, further determining user preference.
Further, in scheme provided in this embodiment, average time, the number of every class webpage can be accessed according to user
Variance yields determines the preference of the user in predetermined period.
Average time can intuitively characterize the number that user accesses all kinds of webpages, if user accesses being averaged for certain class webpage
Number is more, it may be considered that user relatively pays close attention to the content of this kind of webpage.It is used furthermore it is also possible to be determined according to number variance yields
The preference at family.When the number that user accesses the i-th class webpage daily is relatively average, stable, σiWill be smaller, on the contrary, if user is every
The number of its i-th class webpage of access is unequal, such as has accessed within first day 40 the i-th webpages, but in other days, does not see
The i-th class webpage is seen, at this point, σiIt will be larger.Therefore, average time and number variance yields can be comprehensively considered, determine user
Whether the content of this kind of webpage is relatively paid close attention to.For example, frequency threshold value can be greater than in average time, and number variance yields is less than side
When poor threshold value, determine that user is interested in this kind of web page contents, so that it is determined that the preference of user.
When practical application, in the webpage for numerous types that user accessed in predetermined period, it may be possible to determine more
A interested webpage classification of user, at this point it is possible to obtain multiple user preferences.For example, user is simultaneously to sport and house property
It is interested.
The method provided in this embodiment for determining user preference according to network behavior accesses the visit of webpage including obtaining user
Ask information, wherein access information includes webpage information, access time;Belonging to the webpage for determining user's access according to webpage information
Classification;According to classification belonging to access time, webpage, determine that user accesses the secondary of every class webpage daily in predetermined period
Number;According to number, determine that user accesses the average time of every class webpage and the number variance yields of the every class webpage of access;According to visit
It asks average time, the number variance yields of every class webpage, determines the preference for determining user in predetermined period.Using the present embodiment institute
The method of offer can make full use of the access information that user generates when browsing webpage, and true according to the access information of user
Determine user and access the average time and variance yields of every class webpage, to comprehensively consider average time and number variance yields is more quasi-
The preference of true determination user, and then Network Provider can be made to understand the preference of user, and then promote service level.
Fig. 2 is the process of the method that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure.
As shown in Fig. 2, the method provided in this embodiment for determining user preference according to network behavior, comprising:
Step 201, the access information that user accesses webpage is obtained, wherein when access information includes webpage information, access
Between.
The concrete principle and implementation of step 201 and step 101 are all the same, and details are not described herein.
Step 202, keyword is extracted in the content of the uniform resource locator url of webpage and/or webpage.
Wherein it is possible to determine the keyword of the webpage according to the url of webpage.The uniform resource locator url of webpage refers to
The position for the resource that can be obtained from internet and a kind of succinct expression of access method, are standard resources on internet
Address.The part mode/agreement (scheme) is included at least in url and has the host IP address of the resource.It can be according to pre-
If rule handles the url of acquisition, for example, preset rules can be removal including " ", the symbols such as " // ", also
Can remove including mode, protocol section, such as " http ", " https ", " ftp " can also remove general domain name
Format and WWW mark, such as " com ", " cn ", " www ", to obtain useful information from url.For example, http: //
Www.iqiyi.com/, after getting rid of Versatile content according to preset rules, obtained vocabulary is " iqiyi ", then can be made
For the keyword of webpage.
Specifically, can also be according to the keyword of the contents extraction webpage of webpage.It in general, all include website in webpage
Title, the web site name in available webpage, and as the keyword of webpage.Such as all webpages in youku.com website
In, top all includes the mark of youku.com, can identify the mark, determines the keyword of the webpage.
Step 203, classification belonging to webpage is determined in preset class library according to keyword, and/or, keyword is made
For classification belonging to webpage.
Further, class library can be preset, includes keyword and the other corresponding relationship of web page class in class library.Example
Such as, a kind of webpage classification may include multiple keywords.For the ease of being safeguarded to class library, can also be arranged keyword with
The other corresponding table of web page class, for storing keyword and the other corresponding relationship of web page class, such as table 1.
Table 1
It is the line number being arranged by the number of url keyword in table 1, i.e. url keyword a line can also be by web page class
Line number is arranged in other quantity, i.e. a webpage classification corresponds to a line, correspondingly, can will belong to the other url of the same web page class
Keyword is placed in a box.
When practical application, table 1 can be safeguarded, delete, increase, modifying url keyword therein and webpage classification,
It can also delete, increase, modifying corresponding relationship therein.For example, the webpage classification for needing to investigate can be added in corresponding table
And its corresponding url keyword.When not parsing keyword included in corresponding table in the access information of user, then do not record
This visit situation.The data in class library can be made less using this embodiment, it is convenient for safeguarding.
If desired class library is preset, then method provided in this embodiment can also include:
The corresponding relationship of keyword and classification is received, and by corresponding relationship storage into pre-set categories library.
Wherein, keyword and the corresponding relationship of classification can be user's active upload, receive the correspondence of user's upload
After relationship, it can save it in preset class library.
Specifically, the corresponding relationship of keyword and classification can also be determined by the method for machine learning.In counting user
Whether when access information, can detecte in pre-set categories library includes Web Page Key Words, is calculated if it is not, keyword can then be imported
The self learning system of machine makes computer automatically determine classification corresponding to keyword, and the two corresponding relationship is stored in default
In class library.Wherein it is possible to realize above-mentioned function using machine learning frame in the prior art.
Furthermore it is also possible to which whether detect in pre-set categories library includes keyword, closed if it is not, then being added in pre-set categories library
Keyword, and the classification of keyword is determined as keyword itself.
Wherein it is possible to directly using keyword as webpage classification, when extracting Web Page Key Words, and in pre-set categories library
Do not include the keyword, can directly be saved into class library, and using keyword as classification.
If class library directly can be arranged in table form using keyword as classification belonging to webpage, such as 2 institute of table
Show.
Table 2
All webpage classifications can be covered when using this embodiment, in class library, data are compared with horn of plenty.
It is similar, when classifying according to the keyword extracted from web page contents to webpage, above-mentioned side can also be used
Formula is only that the class library of maintenance is different, and details are not described herein.
Step 204, the classification according to belonging to access time, webpage determines that user accesses every class daily in predetermined period
The number of webpage.
The concrete principle and implementation of step 204 and step 103 are all the same, and details are not described herein.
Step 205, according to number, determine that user accesses the average time of every class webpage and the number of the every class webpage of access
Variance yields.
The concrete principle and implementation of step 205 and step 104 are all the same, and details are not described herein.
Step 206, according in predetermined period, user accesses the average time of every class webpage, number variance yields determines user
Affiliated first category.
Specifically, the average time that according to user in predetermined period, can access every class webpage determines belonging to it
The most type of webpage of user's Average visits can be determined as first category belonging to the user, for example, μ by one classification2
It is larger in multiple average values, and webpage classification corresponding with the 2nd class webpage is News class, then being assured that user belongs to
News, preference are news.
Further, can also determine first category belonging to multiple users, for example, user simultaneously belong to News class,
Videos class.
When practical application, there is also user only due to certain reason, the webpage for browsing a type on the same day compared with
The case where more, and other times do not browse such webpage, causes user to access such webpage due to the access times of this day
Average time it is more, in such a scenario, directly determine the affiliated first category of user according to Average visits, it will cause
The problem for inaccuracy of classifying.
And hence it is also possible to consider according to number variance yields determine user belonging to first category.When user accesses i-th daily
When the number of class webpage is relatively average, stable, σiWill be smaller, on the contrary, if user accesses the number injustice of the i-th class webpage daily
, such as 40 the i-th webpages are had accessed within first day, but in other days, without the i-th class webpage of viewing, at this point, σiIt will be compared with
Greatly.It therefore, can be by comparing σiIt is further to determine whether user belongs to first category with preset value.
In addition, the present embodiment also provides first kind method for distinguishing belonging to another determining user.
It may determine that μiWhether it is greater thanIf so, determining that user belongs to first category i.
Wherein, a is preset correction value, and being usually arranged as 0.5, m is the other sum of web page class.μiThe flat of the i-th class webpage is accessed for user
Equal number;μkFor the average time for accessing kth class webpage, σkFor the root of the number variance yields of the every k class webpage of access.
The access average value of all webpages after the i-th class webpage of removing and variance root are added, then divided by webpage classification
Quantity m-1 can obtain the mean value of (μ+σ), multiplied by correction value 0.5, can obtain the mean value of μ, σ.By removing all nets
The parameter of the i-th class webpage, reuses μ in pageiIt is compared with the mean value of μ, σ of other webpages, if μiIt is equal greater than what is finally calculated
Value is as a result, it may be considered that user belongs to first category i.By above-mentioned method of determination, user can be accessed the i-th class webpage
Situation is compared with whole access situation, then determines whether user belongs to first category i, to make the result of classification more
Accurately.
Step 207, the preference of user is determined according to first category.
After determining first category belonging to user, the preference of user is determined further according to first category.For example, user belongs to
News class, Videos class can then determine that the preference of the user is news, video display class.
Method provided in this embodiment can determine user in a predetermined period according to the access situation of user
The average time and number variance yields for accessing every class webpage can be accurate further according to determining average time and variance yields
Determine user's generic, and then can accurately determine user preference.
Fig. 3 is the process of the method that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure.
Method provided in this embodiment can determine that user's is inclined according to the access information of user in multiple predetermined periods
It is good.
As shown in figure 3, the method provided in this embodiment for determining user preference according to network behavior, comprising:
Step 301, the first category that user belongs in each predetermined period in P predetermined period, the every class net of access are determined
The average time and number variance yields of page.
Wherein, the predetermined predetermined period number P for needing to investigate, for example, 10 periods, 15 periods etc. are investigated, it can also
With the preference of long-term investigation user according to demand.Due to user access information can not it is permanent storage in the database, because
This can be after generating access information, just according to access information record access number, and one when predetermined period P is larger
After a predetermined period, according to the data in the predetermined period determine user belonging to first category.To avoid database
In data be disposed off, be but not based on these data to user carry out preference analysis the case where generation.In addition, working as long-term investigation
When the preference of user, P can also be set to dynamic value, i.e., whenever a predetermined period terminates, then on the basis of current P value
Superposition 1.First category is determined further according to the predetermined period newly increased, is determined in the predetermined period of comprehensive basis before this
First category therefrom determines second category.
Specifically, can also determine to access the average time and number variance of every class webpage in each predetermined period
Value, specific to determine that method is referred to step 201~step 206 in embodiment shown in Fig. 2, details are not described herein.
Step 302, according to the average time and number variance of the every class webpage of access determined in each predetermined period
Value, determines the second category that user belongs in multiple first category.
Further, due to that can determine at least one first category in each predetermined period, then pre- at P
If in the period, it will be able to determine multiple first category.For example, in first predetermined period determine first category be the 1st,
3 classes, the first category determined in second predetermined period are the 1st, 4 classes, the first kind determined in third predetermined period
It Wei not the 1st, 5 classes.
Since the first category determined according to a predetermined period is that short-term determine will be as a result, namely this default week
The more interested content of user in phase.It is, however, possible to which it is emerging that user's content a kind of to certain compares sense in this predetermined period
Interest, but after a period of time, user is interested in other content.Therefore, determine that user is inclined according only to a predetermined period
Well can not long-term investigation user hobby.Based on this, the present embodiment is in order to the investigation user in one section of longer time
Preference comprehensively considers the average time generated when accessing every class webpage in multiple predetermined periods and number variance yields, in determination
First category in filter out second category.
When practical application, average time corresponding to first category webpage can be accessed in obtaining each predetermined period
And the number variance yields, determine whether the first category meets the requirement of second category further according to the size of each value.Example
Such as, P=3, the first category determined in first predetermined period are the 1st, 3 classes, first determined in second predetermined period
Classification is the 1st, 4 classes, and the first category determined in third predetermined period is the 1st, 5 classes.Then available first arrive third
In predetermined period, access the 1st, 3,4, the average time of 5 classes and number variance yields, then compare any one first category net
Whether the average time and number variance yields of page are all larger than its corresponding default value, if so, the first category can be with
It is confirmed as the second category that user belongs to.
All first category can be traversed, the second category of the condition of satisfaction is screened out from it.
If the preference of long-term investigation user, that is, P value are increased according to time change situation, then whenever P value becomes
After change, the average time of the first category, the every class webpage of access that can also include in the predetermined period according to newest determination and
Number variance yields redefines the second category that user belongs to, so that second category be enable to be updated according to the variation of P value.
Step 303, the preference of user is determined according to second category.
Step 303 is similar to the implementation of step 208, and details are not described herein.
It should be noted that the user preference determined can change with the variation of second category.
The method provided in this embodiment for determining user preference according to network behavior produces when can access webpage according to user
Raw access information, the preference of long-term investigation user, so as to understand for a long time user preference and preference variation, in turn
Personalized service is provided a user according to the hobby of user.
Fig. 4 is the process of the method that user preference is determined according to network behavior shown in the another exemplary embodiment of the present invention
Figure.
As shown in figure 4, provided in this embodiment determine user preference method according to network behavior, comprising:
Step 401, the first category that user belongs in each predetermined period in P predetermined period, the every class net of access are determined
The average time and number variance yields of page.
Step 401 is identical as the realization principle of step 301 and mode, and details are not described herein.
Step 402, the first category i in each predetermined period is obtained, determines classification i being determined as the pre- of first category
If amount of cycles P '.
Since access information of the user in each predetermined period is not quite similar, it is determined in each predetermined period
First category also can be different.First category i in available each predetermined period, for example, P=3, first default week
In phase, first category i is webpage classification 1,3;In second predetermined period, first category i is webpage classification 1,4;In third
In a predetermined period, first category i is webpage classification 1,5.The default week that each classification i is determined as to first category is determined again
Issue amount P '.For example, it is 3 that webpage classification 1, which is confirmed as the predetermined period quantity of the first category for first category, by webpage
The predetermined period quantity that classification 3,4,5 is confirmed as the first category for first category is 1.
For the ease of statistical magnitude P ', set C ' can be established according to the first category determined in each predetermined period.Tool
Body mode are as follows:
Subclass C ' is established according to the first category i determined in each predetermined periodn.Wherein, subclass C 'nIn include should
All first category i determined in predetermined period.N indicates predetermined period mark, such as first predetermined period, then n=1.By
In altogether including P predetermined period, therefore, available P subclass:
C′1=...e … Cf …}1
C′2=... Cg … Ch …}2
……
C′P=... Cc … Cd …}P
Wherein, Ce、Cf、Cg、ChDeng for first category that in each predetermined period, user belongs to.
Set C ' is determined according to multiple subclass:
C '=
{{… Ce … Cf …}1{… Cg … Ch …}2…{… Cc … Cd …}P}。
Further, since in each predetermined period, each classification i can only at most be confirmed as a first category,
It is exactly can only at most occur a classification i in each subclass in above-mentioned set, then can be according to each first category i
The number of appearance determines the predetermined period number P ' that classification i is determined as to first category.
Step 403, determine whether first category i meets first condition according to quantity P ', predetermined period quantity P.
Further, preset rules can be set, if determining that first category i meets the default rule according to quantity P ' and P
Then, it is determined that first category i meets first condition.
When practical application, it can be determined that whether quantity P ' is greater thanIf so, judgement meets preset rules, otherwise sentence
It is disconnected to be unsatisfactory for preset rules.
Wherein,It for correction value, can be configured according to demand, for example, willIt is set as 1/3.
If first category i meets the requirement of first condition, 404 are thened follow the steps.Otherwise, continue to determine next first kind
The requirement of first condition whether is not met.
Step 404, it determines in P predetermined period, the overall average number of the webpage of user's access level i.
Specifically, recording the number a for thering is user to access every class webpage daily in each predetermined periodij(being detailed in matrix A),
It can be determined in P predetermined period, total access times of the webpage of user's access level i according to these numerical value, then be visited with total
Number is asked divided by total number of days of P predetermined period, to obtain the overall average number μ of the webpage of access level ii', wherein total
Number of days is predetermined period number of days multiplied by P, for example, each predetermined period is 5 days, then total number of days is then 5 × P.
Step 405, according to the average time and number variance for accessing every class webpage in quantity P ', each predetermined period
Value, overall average number determine whether first category i meets second condition, if so, determining that first category i is second category.
Further, can first to the average time and number variance yields that every class webpage is accessed in each predetermined period into
Row processing.When with P predetermined period, available P matrix A, correspondingly, one can be obtained according to each matrix A
Therefore a matrix B can obtain P matrix B, it may be assumed that
P matrix B can be handled, obtain third matrix Bi:
Further according to third matrix BjIn include μij、σij, quantity P ', overall average number μi' determines whether first category i is full
Sufficient second condition, specific determining method, which can be, judges overall average number μiWhether ' meets:
If so, judging that classification i meets second condition.
If classification i meets first condition and second condition, judge that classification i presets for second category, that is, multiple
In the multiple first category generated in period, according to the long-term access data of user, then the second category that user belongs to is determined,
To keep the result finally determined more accurate.
After having determined whether classification i meets first condition and second condition, it can continue to determine that others classification i is
It is no to meet first condition and second condition.
Step 406, the preference of user is determined according to second category.
Step 406 is similar to the implementation of step 208, and details are not described herein.
Step 407, however, it is determined that first category i is second category, then determines that user belongs to the general of classification i according to preset algorithm
Rate, and output probability;
Wherein, preset algorithm are as follows:
Wherein, P ' refers to the predetermined period number that classification i is determined as to first category, that is, classification i is in set C '
Frequency of occurrence.P ' is calculated again and obtains q divided by P, that is, calculates classification i within P period, is confirmed as the general of first category
Therefore rate can indicate the probability that user is determined as to classification i by q value.
Wherein, the execution sequence of step 406 and step 407 with no restrictions, can first carry out step 406, can also first hold
Row step 407, may also be performed simultaneously step 406 and 407.
The method provided in this embodiment for determining user preference according to network behavior, is used in determining each predetermined period
On the basis of first category belonging to family, according to the data in each predetermined period, determine P predetermined period this it is longer when
In, second category belonging to user, so as to classify in one section of longer time to user.Also, pass through
The mean value and variance yields in multiple predetermined periods are introduced, user can be investigated in the stationarity for accessing the i-th class webpage, thus more
Accurately classify to user, and then more accurately the preference of user is analyzed.
Fig. 5 is the structure of the device that user preference is determined according to network behavior shown in an exemplary embodiment of the invention
Figure.
As shown in figure 5, the device provided in this embodiment for determining user preference according to network behavior, comprising:
Module 51 is obtained, for obtaining the access information of user, wherein the access information includes webpage information, access
Time;
Category determination module 52, for according to the webpage information determine webpage that the user accesses belonging to classification;
Number determining module 53 is determined for the classification according to belonging to the access time, the webpage in predetermined period
Interior user accesses the number of every class webpage daily;
Computing module 54, for determining that the user accesses average time and the visit of every class webpage according to the number
Ask the number variance yields of every class webpage;
Preference determining module 55, the number for accessing every class webpage daily according to the user determine that the user is inclined
It is good.
The device provided in this embodiment that user preference is determined according to network behavior accesses the visit of webpage including obtaining user
Ask information, wherein access information includes webpage information, access time;Belonging to the webpage for determining user's access according to webpage information
Classification;According to classification belonging to access time, webpage, determine that user accesses the secondary of every class webpage daily in predetermined period
Number;According to number, determine that user accesses the average time of every class webpage and the number variance yields of the every class webpage of access;According to visit
It asks average time, the number variance yields of every class webpage, determines and determine user preference in predetermined period.It is mentioned using the present embodiment
The device of confession can make full use of the access information that user generates when browsing webpage, and be determined according to the access information of user
User accesses the average time and variance yields of every class webpage, to comprehensively consider average time and number variance yields is more acurrate
Determination user preference, and then can make Network Provider understand user preference, and then promoted service level.
The concrete principle and implementation of the device provided in this embodiment that user preference is determined according to network behavior with
Embodiment shown in FIG. 1 is similar, and details are not described herein again.
Fig. 6 is the structure of the device that user preference is determined according to network behavior shown in another exemplary embodiment of the present invention
Figure.
As shown in fig. 6, on the basis of the above embodiments, it is provided in this embodiment that user preference is determined according to network behavior
Device,
The preference determining module 55, comprising:
First category determination unit 551, for according to the average time, the number variance yields for accessing every class webpage
Determine first category belonging to the user;
Preference determination unit 552, for determining the preference of the user according to the first category.
Wherein, first category determination unit 551 is specifically used for:
Judge μiWhether it is greater than
If so, determining that the user belongs to first category i;
Wherein, m is the other sum of the web page class, and a is preset correction value, μiThe i-th class webpage is accessed for the user
Average time;μkFor the average time for accessing kth class webpage, σkFor the root of the number variance yields of the every k class webpage of access.
Specifically, device provided in this embodiment further include: multicycle determining module 56 is used for:
The determining first category that in the P predetermined periods, user described in each predetermined period belongs to,
Access the average time and the number variance yields of every class webpage;
According to the average time and the number of the every class webpage of access determined in each predetermined period
Variance yields determines the second category that user belongs in multiple first category;
The preference of the user is determined according to the second category.
Optionally, the multicycle determining module 56, comprising:
Acquiring unit 561 is determined for obtaining the first category i in each predetermined period by the class
Other i is determined as the predetermined period quantity P ' of first category;
First determination unit 562, for whether determining the first category i according to quantity P ', predetermined period quantity P
Meet first condition;
If so, the first determination unit 562 determines in the P predetermined periods that the user accesses the net of the classification i
The overall average number of page;
First determination unit 562 is also used to access every class net according in quantity P ', each predetermined period
The average time and the number variance yields, the overall average number of page determine whether the first category i meets the
Two conditions, if so, determining that the first category i is the second category.
Optionally, device provided in this embodiment further includes probability output module 57, is used for:
If it is determined that the first category i is the second category, then determine that the user belongs to classification i according to preset algorithm
Probability, and export the probability;
Wherein, the preset algorithm are as follows:
Wherein, q is the probability.
In addition, category determination module 52 can also include:
Extraction unit 521 extracts keyword in the url of the webpage and/or the content of the webpage;
Second determination unit 522, for being determined belonging to the webpage in preset class library according to the keyword
Classification, and/or, using the keyword as classification belonging to the webpage.
It optionally, include the corresponding relationship of the keyword and the classification in the pre-set categories library;
Correspondingly, the category determination module 52 further include:
Receiving unit 523 is deposited for receiving the corresponding relationship of the keyword Yu the classification, and by the corresponding relationship
It stores up in the pre-set categories library;
And/or adding unit 524, for detecting whether including the keyword in the pre-set categories library, if it is not, then
The keyword is added in the pre-set categories library, and the classification of the keyword is determined as described keyword itself.
The concrete principle and implementation of the device provided in this embodiment that user preference is determined according to network behavior with
Embodiment shown in Fig. 2~4 is similar, and details are not described herein again.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (11)
1. a kind of method for determining user preference according to network behavior characterized by comprising
Obtain the access information of user, wherein the access information includes webpage information, access time;
Classification belonging to the webpage for determining user's access according to the webpage information;
According to classification belonging to the access time, the webpage, determine that the user described in predetermined period accesses every class daily
The number of webpage;
According to the number, determine that the user accesses the average time of every class webpage and the number variance of the every class webpage of access
Value;
According to the average time, the number variance yields for accessing every class webpage, the use described in the predetermined period is determined
The preference at family.
2. the method according to claim 1, wherein it is described according to access every class webpage the average time,
The number variance yields determines the preference of the user described in the predetermined period, comprising:
According in the predetermined period, the user accesses the average time of every class webpage, the number variance yields determines
First category belonging to the user;
The preference of the user is determined according to the first category.
3. according to the method described in claim 2, the user accesses it is characterized in that, described according in the predetermined period
The average time of every class webpage, the number variance yields determine first category belonging to the user, comprising:
Judge μiWhether it is greater than
If so, determining that the user belongs to first category i;
Wherein, m is the other sum of the web page class, and a is preset correction value, μiAverage time for accessing the i-th class webpage for the user
Number;μkFor the average time for accessing kth class webpage, σkFor the root of the number variance yields of the every k class webpage of access.
4. according to the method in claim 2 or 3, which is characterized in that further include:
The determining first category that in the P predetermined periods, user described in each predetermined period belongs to, access
The average time of every class webpage and the number variance yields;
According to the average time of the every class webpage of access determined in each predetermined period and the number variance
Value, determines the second category that user belongs in multiple first category;
The preference of the user is determined according to the second category.
5. according to the method described in claim 4, it is characterized in that, the visit that the basis determines in each predetermined period
The average time and the number variance yields for asking every class webpage, determine the user in multiple first category
The second category belonged to, comprising:
The first category i in each predetermined period is obtained, determines the classification i being determined as the pre- of first category
If amount of cycles P ';
Determine whether the first category i meets first condition according to quantity P ', predetermined period quantity P;
If so, determining in the P predetermined periods, the user accesses the overall average number of the webpage of the classification i;
According to the average time and the number side for accessing every class webpage in quantity P ', each predetermined period
Difference, the overall average number determine whether the first category i meets second condition, if so, determining the first category i
For the second category.
6. according to the method described in claim 5, it is characterized in that, however, it is determined that the first category i be the second category, then
It determines that the user belongs to the probability of classification i according to preset algorithm, and exports the probability;
Wherein, the preset algorithm are as follows:
Wherein, q is the probability.
7. according to claim 1~3,5,6 described in any item methods, which is characterized in that described true according to the webpage information
Classification belonging to the webpage of fixed user's access, comprising:
Keyword is extracted in the uniform resource locator url of the webpage and/or the content of the webpage;
Classification belonging to the webpage is determined in pre-set categories library according to the keyword, and/or, using the keyword as
Classification belonging to the webpage.
8. the method according to the description of claim 7 is characterized in that in the pre-set categories library include the keyword with it is described
The corresponding relationship of classification;
The method also includes:
The corresponding relationship of the keyword Yu the classification is received, and the corresponding relationship is stored to the pre-set categories library
In;
And/or whether detect in the pre-set categories library includes the keyword, if it is not, then adding in the pre-set categories library
Add the keyword, and the classification of the keyword is determined as described keyword itself.
9. a kind of device for determining user preference according to network behavior characterized by comprising
Module is obtained, for obtaining the access information of user, wherein the access information includes webpage information, access time;
Category determination module, for according to the webpage information determine webpage that the user accesses belonging to classification;
Number determining module determines described in predetermined period for the classification according to belonging to the access time, the webpage
User accesses the number of every class webpage daily;Computing module, for determining that the user accesses every class webpage according to the number
Average time and the every class webpage of access number variance yields;
Preference determining module, for determining described according to the average time, the number variance yields for accessing every class webpage
The preference of the user in predetermined period.
10. device according to claim 9, which is characterized in that the preference determining module, comprising:
First category determination unit, for determining institute according to the average time, the number variance yields that access every class webpage
State first category belonging to user;
Preference determination unit, for determining the preference of the user according to the first category.
11. device according to claim 10, which is characterized in that further include: multicycle determining module is used for:
The determining first category that in the P predetermined periods, user described in each predetermined period belongs to, access
The average time of every class webpage and the number variance yields;
According to the average time of the every class webpage of access determined in each predetermined period and the number variance
Value, determines the second category that user belongs in multiple first category;
The preference of the user is determined according to the second category.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810108024.7A CN110110219B (en) | 2018-02-02 | 2018-02-02 | Method and device for determining user preference according to network behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810108024.7A CN110110219B (en) | 2018-02-02 | 2018-02-02 | Method and device for determining user preference according to network behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110110219A true CN110110219A (en) | 2019-08-09 |
CN110110219B CN110110219B (en) | 2022-02-18 |
Family
ID=67483141
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810108024.7A Expired - Fee Related CN110110219B (en) | 2018-02-02 | 2018-02-02 | Method and device for determining user preference according to network behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110219B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110650161A (en) * | 2019-10-30 | 2020-01-03 | 华南师范大学 | Safe website and working method thereof |
CN112131561A (en) * | 2020-09-11 | 2020-12-25 | 北京北信源软件股份有限公司 | Access boundary determination method, device, electronic device and storage medium |
CN114780882A (en) * | 2022-03-26 | 2022-07-22 | 武汉楷瀚文化传媒有限公司 | Internet webpage display management method, equipment and computer storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077714A (en) * | 2014-06-16 | 2014-10-01 | 微梦创科网络科技(中国)有限公司 | Method and system for acquiring preference of user visiting website and pushing advertisements to user visiting website |
CN104217091A (en) * | 2013-06-05 | 2014-12-17 | 北京齐尔布莱特科技有限公司 | Website page view prediction method based on historical tendency weights |
-
2018
- 2018-02-02 CN CN201810108024.7A patent/CN110110219B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217091A (en) * | 2013-06-05 | 2014-12-17 | 北京齐尔布莱特科技有限公司 | Website page view prediction method based on historical tendency weights |
CN104077714A (en) * | 2014-06-16 | 2014-10-01 | 微梦创科网络科技(中国)有限公司 | Method and system for acquiring preference of user visiting website and pushing advertisements to user visiting website |
Non-Patent Citations (2)
Title |
---|
杨持: "《生物统计学》", 31 May 1996, 《呼和浩特:内蒙古大学出版社》 * |
韩文玲等: "青海省雷暴日数对防雷等级划分的影响分析", 《现代农业科技》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110650161A (en) * | 2019-10-30 | 2020-01-03 | 华南师范大学 | Safe website and working method thereof |
CN110650161B (en) * | 2019-10-30 | 2021-09-24 | 华南师范大学 | Safe website and working method thereof |
CN112131561A (en) * | 2020-09-11 | 2020-12-25 | 北京北信源软件股份有限公司 | Access boundary determination method, device, electronic device and storage medium |
CN114780882A (en) * | 2022-03-26 | 2022-07-22 | 武汉楷瀚文化传媒有限公司 | Internet webpage display management method, equipment and computer storage medium |
CN114780882B (en) * | 2022-03-26 | 2023-12-05 | 深圳市安睿信科技有限公司 | Internet webpage display management method, equipment and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110110219B (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108197331B (en) | User interest exploration method and device | |
JP5802745B2 (en) | Intelligent navigation method, apparatus and system | |
CN110489633B (en) | Intelligent brain service system based on library data | |
CN106503014B (en) | Real-time information recommendation method, device and system | |
US7610276B2 (en) | Internet site access monitoring | |
CN106504099A (en) | A kind of system for building user's portrait | |
CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
US10776431B2 (en) | System and method for recommending content based on search history and trending topics | |
US8990241B2 (en) | System and method for recommending queries related to trending topics based on a received query | |
CN109190024A (en) | Information recommendation method, device, computer equipment and storage medium | |
US20100100537A1 (en) | System and method for identifying trends in web feeds collected from various content servers | |
CN107707545A (en) | A kind of abnormal web page access fragment detection method, device, equipment and storage medium | |
CN111008265A (en) | Enterprise information searching method and device | |
CN105930507B (en) | A kind of method and device for the web browsing interest obtaining user | |
CN102890689A (en) | Method and system for building user interest model | |
CN106776860A (en) | One kind search abstraction generating method and device | |
JP2013125468A (en) | Advertisement distribution device | |
CN110110219A (en) | The method and device of user preference is determined according to network behavior | |
US20170228378A1 (en) | Extracting topics from customer review search queries | |
US9830344B2 (en) | Evaluation of nodes | |
JP2011227721A (en) | Interest extraction device, interest extraction method, and interest extraction program | |
CN117235586B (en) | Hotel customer portrait construction method, system, electronic equipment and storage medium | |
CN110795613A (en) | Commodity searching method, device and system and electronic equipment | |
Antoniou et al. | A Semantic Web Personalizing Technique: The Case of Bursts in Web Visits | |
CN111178421A (en) | Method, device, medium and electronic equipment for detecting user state |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220218 |
|
CF01 | Termination of patent right due to non-payment of annual fee |