CN110222191B - User interest portrait construction method, device, computer equipment and computer storage medium - Google Patents
User interest portrait construction method, device, computer equipment and computer storage medium Download PDFInfo
- Publication number
- CN110222191B CN110222191B CN201910319421.3A CN201910319421A CN110222191B CN 110222191 B CN110222191 B CN 110222191B CN 201910319421 A CN201910319421 A CN 201910319421A CN 110222191 B CN110222191 B CN 110222191B
- Authority
- CN
- China
- Prior art keywords
- user
- ontology concept
- interest
- words
- word
- 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.)
- Active
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses a method and a device for constructing user interest portraits and a computer storage medium, relates to the technical field of data analysis, and can eliminate interference information contained in webpage texts and improve the accuracy of user interest portraits construction. The method comprises the following steps: acquiring ontology concept words for reflecting each interest point; when the behavior operation of browsing the webpage by the user is monitored, mapping the webpage text word of the webpage browsed by the user to the ontology concept word for reflecting the corresponding interest point to obtain the interest value of the user on each ontology concept word; screening interest values of the user on each ontology concept word by analyzing webpage text words mapped to the same ontology concept word in a preset time period to obtain effective interest values of the user on each ontology concept word; and constructing user interest portraits according to the effective interest values of the users on each ontology concept word.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a method and apparatus for constructing a user interest portrait, a computer device, and a computer storage medium.
Background
With the development of big data, the explosive growth of data volume and the maturity of big data analysis technology enable behavior data that users can capture to be more and more, user portraits are more and more abundant and finer along with the proliferation of information, and the method can be applied to the self-client marketing of certain industries.
By collecting the behavior of the user browsing the web page, a user interest portrait can be constructed, wherein the user interest portrait comprises a plurality of interest point labels and the preference degree of the user for each interest point, for example, the preference degree of the user for sports is 60, the preference degree of the user for music is 20, and the like. In the prior art, a plurality of interest points are usually preset in the process of constructing the user interest portrait, and when the browsing behavior of the user is generated in the website, the webpage text in the website browsed by the user is mapped to the ontology concept representing different interest points, for example, football is mapped to interest points such as balls, sports and the like.
However, in the prior art, the user interest portrait is generally constructed by directly mapping the web page text browsed by the user to the ontology concept representing the corresponding interest point, and because a large amount of interference information such as advertisement, navigation bar, misoperation of the user and the like is contained in the web page text, a large amount of interference information is recorded in the interest point label in the constructed user interest portrait, so that the user interest portrait is inaccurate.
Disclosure of Invention
In view of this, the invention provides a method, a device, a computer device and a computer storage medium for constructing a user interest portrait, which mainly aims to solve the problem that the user interest portrait is inaccurate because a great amount of interference information is recorded by interest point labels in the user interest portrait constructed at present.
According to one aspect of the present invention, there is provided a method of constructing a user interest portrait, the method comprising:
acquiring ontology concept words for reflecting each interest point;
when the behavior operation of browsing the webpage by the user is monitored, mapping the webpage text word of the webpage browsed by the user to the ontology concept word for reflecting the corresponding interest point to obtain the interest value of the user on each ontology concept word;
screening interest values of the user on each ontology concept word by analyzing webpage text words mapped to the same ontology concept word in a preset time period to obtain effective interest values of the user on each ontology concept word;
and constructing user interest portraits according to the effective interest values of the users on each ontology concept word.
Further, the mapping the webpage text word of the webpage browsed by the user to the ontology concept word for reflecting the corresponding interest point, and obtaining the interest value of the user on each ontology concept word comprises the following steps:
Performing similarity calculation on webpage text words of a webpage browsed by a user and ontology concept words used for reflecting all interest points to obtain similarity between the webpage text words and all the ontology concept words;
and accumulating the similarity between the webpage text words and each ontology concept word which is larger than a preset threshold value, and dividing the similarity by the number of the webpages browsed by the user to obtain the interest value of the user on each ontology concept word.
Further, the step of screening the interest value of the user on each ontology concept word by analyzing the webpage text word mapped to the same ontology concept word in the preset time period, and the step of obtaining the effective interest value of the user on each ontology concept word includes:
counting the number of web pages browsed by a user to which the web page text words mapped to the same ontology concept words belong in a preset time period, and obtaining the number of web pages distributed around the same ontology concept words;
and screening the interest values of the user on each ontology concept word according to the webpage quantity distributed around the same ontology concept word to obtain the effective interest values of the user on each ontology concept word.
Further, the screening the interest value of the user on each ontology concept word according to the number of the web pages distributed around the same ontology concept word, and obtaining the effective interest value of the user on each ontology concept word includes:
Based on a preset webpage quantity threshold value distributed around the same ontology concept words, the quantity of which is larger than the webpage quantity threshold value, distributed around the same ontology concept words are screened out from all the ontology concept words;
and obtaining interest values of the user on the ontology concept words with the quantity of the webpages distributed around the same ontology concept words being larger than the webpage quantity threshold value, and obtaining effective interest values of the user on each ontology concept word.
Further, the step of screening the interest value of the user on each ontology concept word by analyzing the webpage text word mapped to the same ontology concept word in the preset time period, and the step of obtaining the effective interest value of the user on each ontology concept word includes:
according to the number of the user browsing webpages to which the webpage text words mapped to the same ontology concept words in a preset time period belong and the interest value of the user on the same ontology concept words, calculating the weight value of the user browsing webpages mapped to the same ontology concept words;
and screening the interest values of the user on each ontology concept word according to the weight values of the user browsing web pages mapped to the same ontology concept word, so as to obtain the effective interest values of the user on each ontology concept word.
Further, the filtering the interest value of the user on each ontology concept word according to the weight value of the user browsing web page mapped to the same ontology concept word, to obtain the effective interest value of the user on each ontology concept word includes:
based on a preset weight value threshold value of mapping the user browsing webpage onto the same ontology concept words, the ontology concept words with the weight value larger than the weight value threshold value of mapping the user browsing webpage onto the same ontology concept words are screened out from all the ontology concept words;
and obtaining interest values of the user on the ontology concept words with the weight values which are larger than the weight value threshold and mapped to the same ontology concept words by the user browsing web pages, and obtaining effective interest values of the user on each ontology concept word.
Further, the filtering the interest value of the user on each ontology concept word according to the weight value of the user browsing web page mapped to the same ontology concept word, to obtain the effective interest value of the user on each ontology concept word includes:
the weight values mapped to the same ontology concept words by the user browsing web pages are ranked from large to small, and the weight value ranking corresponding to each ontology concept word is obtained;
And screening the interest values of the users on the ontology concept words, which are ranked before the preset value, from the interest values of the users on the ontology concept words to obtain the effective interest values of the users on the ontology concept words.
According to another aspect of the present invention, there is provided an apparatus for constructing a user interest portrait, the apparatus comprising:
an acquisition unit for acquiring ontology concept words for reflecting each interest point;
the mapping unit is used for mapping the webpage text words of the webpage browsed by the user onto the ontology concept words for reflecting the corresponding interest points when the behavior operation of the webpage browsed by the user is monitored, so as to obtain the interest values of the user on each ontology concept word;
the screening unit is used for screening the interest values of the user on each ontology concept word by analyzing the webpage text words mapped to the same ontology concept word in a preset time period to obtain the effective interest values of the user on each ontology concept word;
and the construction unit is used for constructing the user interest portrait according to the effective interest values of the user on each ontology concept word.
Further, the mapping unit includes:
the first calculation module is used for carrying out similarity calculation on the webpage text words of the webpage browsed by the user and the ontology concept words used for reflecting the interest points to obtain similarity between the webpage text words and the ontology concept words;
And the accumulation module is used for accumulating the similarity between the webpage text words and each ontology concept word which is larger than a preset threshold value and dividing the similarity by the number of the webpages browsed by the user to obtain the interest value of the user on each ontology concept word.
Further, the screening unit includes:
the statistics module is used for counting the number of web pages browsed by the user to which the web page text words mapped to the same ontology concept words belong in a preset time period, and obtaining the number of web pages distributed around the same ontology concept words;
and the first screening module is used for screening the interest values of the user on each ontology concept word according to the webpage quantity distributed around the same ontology concept word to obtain the effective interest values of the user on each ontology concept word.
Further, the first screening module is specifically configured to screen, from among the ontology concept words, based on a preset threshold value of the number of web pages distributed around the same ontology concept word, where the number of web pages distributed around the same ontology concept word is greater than the threshold value of the number of web pages;
the first filtering module is specifically further configured to obtain interest values of the user on the ontology concept words with the number of web pages distributed around the same ontology concept word being greater than the threshold value of the number of web pages, and obtain effective interest values of the user on each ontology concept word.
Further, the screening unit includes:
the second calculation module is used for calculating the weight value of the user browsing webpage mapped to the same ontology concept word according to the number of the user browsing webpages to which the webpage text word mapped to the same ontology concept word belongs in a preset time period and the interest value of the user on the same ontology concept word;
and the second screening module is used for screening the interest value of the user on each ontology concept word according to the weight value of the user browsing webpage mapped to the same ontology concept word, so as to obtain the effective interest value of the user on each ontology concept word.
Further, the second screening module is specifically configured to screen, from among the ontology concept words, where a weight value of the user browsing webpage mapped to the same ontology concept word is greater than a weight value threshold, based on a preset weight value threshold of the user browsing webpage mapped to the same ontology concept word;
the second filtering module is specifically further configured to obtain an interest value of the user on the ontology concept words, where the weight value of the ontology concept words mapped to the same ontology concept words by the user browsing web page is greater than the weight value threshold, and obtain an effective interest value of the user on each ontology concept word.
Further, the second filtering module is specifically configured to sort the weight values mapped to the same ontology concept words by the user browsing web page from big to small, so as to obtain a weight value ranking corresponding to each ontology concept word;
the second screening module is specifically further configured to screen, from the interest values of the user on each ontology concept word, the interest values of the user on the ontology concept word, which are ranked before the preset value, of the weight values, so as to obtain effective interest values of the user on each ontology concept word.
According to yet another aspect of the present invention, there is provided a computer device comprising a memory storing a computer program and a processor implementing the steps of a method of constructing a user interest image when the computer program is executed by the processor.
According to still another aspect of the present invention, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method of constructing a representation of a user's interest.
By means of the technical scheme, the method and the device for constructing the user interest portrait are provided, the ontology concept words used for reflecting all the interest points are obtained, when the behavior operation of browsing the webpage by the user is monitored, the webpage text words of the webpage browsed by the user are mapped to the ontology concept words used for reflecting the corresponding interest points, the webpage text words mapped to the same ontology concept words in a preset time period are analyzed, the interest values of the user on all the ontology concept words are screened, the effective interest values of the user on all the ontology concept words are obtained, and therefore the user interest portrait is constructed based on the effective interest values. Compared with the construction mode of directly mapping the webpage text browsed by the user to the ontology concept of the corresponding interest point in the prior art, the method has the advantages that the existing webpage contains a large amount of interference information, the text in the interference information is usually on one webpage and can be mapped to the same ontology concept word, and the interest value of the user on each ontology concept word is screened by analyzing the webpage text word mapped to the same ontology concept word in a preset time period, so that the effective interest value of the user on each ontology concept word is obtained, the interference information contained in the webpage text can be eliminated, the effective interest value is reserved, and the constructed user interest figure is more accurate.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a schematic flow chart of a method for constructing a user interest image according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating another method for constructing a user interest image according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of screening interest values of users on concept words of various ontologies according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of screening interest values of users on various ontology concept words according to another embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a device for constructing a user interest image according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another apparatus for constructing a user interest image according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention provides a method for constructing a user interest image, which can eliminate interference information contained in a webpage text and improve the accuracy of user interest image construction, as shown in fig. 1, and comprises the following steps:
101. an ontology concept word for reflecting each point of interest is acquired.
Wherein the ontology concept words are words in the ontology table representing the concept of interest points, such as entertainment, politics, sports, music, etc., without limitation, and each ontology concept word may be specifically identified by a word vector due to its different characteristics, context features, etc.
It should be noted that, although each ontology concept word may include sub-category relationships, for example, entertainment includes movies, sports, etc., sports includes football, basketball, etc., where the ontology concept words are juxtaposed with each other, and each ontology concept word is used as a separate word vector.
102. When the behavior operation of the user for browsing the webpage is monitored, mapping the webpage text word of the user for browsing the webpage to the ontology concept words for reflecting the corresponding interest points, and obtaining the interest value of the user on each ontology concept word.
In the process of browsing the web pages, the user browses the web pages interested by the user, for example, the user likes cosmetics, frequently browses or searches the cosmetic web pages, the user likes sports, and frequently browses or searches the sports web pages, and the specific searching process can be through jumping among other web pages or searching directly through a search bar.
The action of the user for browsing the webpage is generally a webpage browsing action generated by clicking the webpage by the user, and jumps to different display pages by clicking different areas of the webpage. When the webpage browsing behavior of the user is generated, the behavior data corresponding to the webpage browsing behavior of the user can be obtained by burying the point at the front end or analyzing the log data at the rear end, the webpage text is extracted from the behavior data corresponding to the webpage browsing behavior of the user, the webpage text is processed to obtain webpage text words, further, similarity calculation is carried out on word vectors corresponding to the webpage text words and word vectors corresponding to the ontology concept words used for reflecting all interest points respectively to obtain the similarity between each webpage text word and each ontology concept word, the similarity larger than a preset threshold value is reserved, and the similarity between the webpage text words and each ontology concept word is accumulated and divided by the number of the webpage browsed by the user to obtain the interest value of the user under each ontology concept word.
For the embodiment of the invention, particularly in the process of extracting the webpage text from the behavior data corresponding to the webpage browsing behavior of the user, the text structure in the webpage can be utilized to extract the webpage text in different areas in the webpage, so that the webpage text can be extracted rapidly and accurately. In general, text blocks are stored in a web page, for example, topic text blocks, directory text blocks, picture text blocks, and the like, so as to further extract web page text in different text blocks in the web page.
103. And screening the interest value of the user on each ontology concept word by analyzing the webpage text words mapped to the same ontology concept word in a preset time period to obtain the effective interest value of the user on each ontology concept word.
For the embodiment of the invention, the user browses each webpage and has webpage text words, each webpage text word is mapped to a corresponding ontology concept word, and the interest value of the user on each ontology concept word is obtained, but the obtained interest value of the user on each ontology concept word is not accurate because of possible interference information such as advertisements and the like in the webpage, and it can be understood that if the interference information such as advertisements and the like exists, the webpage text words in the webpage browsed by the user are usually concentrated, the ontology concept words mapped to by the webpage text words are correspondingly concentrated and are usually distributed in a small amount of webpages; the web page text words in the web page of interest to the user are generally more dispersed, the ontology concept words mapped to the web page text words are correspondingly more dispersed and are generally distributed in a large number of web pages, and particularly, the interest values of the user on each ontology concept word can be screened by knowing the condition of web page text word distribution web pages mapped to the same ontology concept word in a preset time period, the interest values of the web page text words mapped to the same ontology concept word distributed on the ontology concept word of fewer pages are deleted and used as invalid interest values, and the interest values of the web page text word distribution sub-mapped to the same ontology concept word on the ontology word of more pages are reserved and used as valid interest values.
The user browses web pages a with web page text words a1, a2, a3, a4 and a5, the web page text words a1, a2 and a3 are mapped to ontology concept words M1, a4 and a5 are mapped to ontology concept words M2, the user browses web pages B with web page text words B1, B2 and B3, the web page text words B1 and B2 are mapped to ontology concept words M2, the user browses web pages C with web page text words C1, C2 and C3, the web page text words C1 and C2 are mapped to ontology concept words M1, C3 are mapped to ontology concept words M3, interest values of the user on the ontology concept words M1, M2 and M3 can be obtained through step 102, the web page text words mapped to the ontology concept words M1, a2, a4, B3, C1 and C2 are mapped to the ontology concept words M2, the web page text words a4, a2 and B3 and C1 and C2 are distributed as the interest values of the ontology concept words M2, the user is distributed on the web page words M1, the interest values of the ontology concept words M2 and the web page words M2 are distributed as the values of the web page words M2 and the web page text words M2 are distributed.
104. And constructing user interest portraits according to the effective interest values of the users on each ontology concept word.
As the effective interest value under each ontology concept word is the more accurate preference of the user in browsing behavior after the web page interference information is removed, the user interest portraits recorded with each interest point are further formed according to the effective interest value of the user on each ontology concept word.
For the embodiment of the invention, the construction of the user interest portrait is equivalent to the process of labeling the user, and particularly in the process of constructing the user interest portrait, the effective value of the user on each ontology concept word possibly changes along with the browsing of the webpage content by the user, the effective value of the user on each ontology concept word is used as dynamic data to label the user, and in order to precisely label the user interest portrait, the user is required to be labeled by combining attribute data such as the name, the sex, the age and the like of the user as static data on the basis of the effective value of the user on each ontology concept word, so that the user interest portrait is constructed.
The embodiment of the invention provides a construction method of a user interest portrait, which comprises the steps of obtaining ontology concept words for reflecting all interest points, mapping webpage text words of a user browsing webpage onto the ontology concept words for reflecting corresponding interest points when the behavior operation of the user browsing webpage is monitored, analyzing the webpage text words mapped onto the same ontology concept words within a preset time period, screening interest values of the user on all the ontology concept words, and obtaining effective interest values of the user on all the ontology concept words, so that the user interest portrait is constructed based on the effective interest values. Compared with the construction mode of directly mapping the webpage text browsed by the user to the ontology concept of the corresponding interest point in the prior art, the method has the advantages that the existing webpage contains a large amount of interference information, the text in the interference information is usually on one webpage and can be mapped to the same ontology concept word, and the interest value of the user on each ontology concept word is screened by analyzing the webpage text word mapped to the same ontology concept word in a preset time period, so that the effective interest value of the user on each ontology concept word is obtained, the interference information contained in the webpage text can be eliminated, the effective interest value is reserved, and the constructed user interest figure is more accurate.
The embodiment of the invention provides another method for constructing user interest images, which eliminates interference information contained in webpage text and improves the accuracy of user interest image construction, as shown in fig. 2, and comprises the following steps:
201. an ontology concept word for reflecting each point of interest is acquired.
For the embodiment of the present invention, the specific process of specifically obtaining the ontology concept words for reflecting each interest point is the same as that described in step 101, and will not be described herein.
202. When the behavior operation of browsing the webpage by the user is monitored, similarity calculation is carried out on the webpage text words browsed by the user and the ontology concept words used for reflecting the interest points, so that the similarity between the webpage text words and the ontology concept words is obtained.
It should be noted that, in order to prevent the web browsing behavior generated by the false clicking, when the web browsing behavior of the user is generated, the web browsing behavior of the user may be screened, and the web browsing behavior that the stay time of the user on the browsed page exceeds the preset time is reserved.
For the embodiment of the invention, the webpage text word browsed by the user and the ontology concept word for reflecting each interest point are respectively expressed as the word vector corresponding to the webpage text word and the word vector corresponding to the ontology concept word for reflecting each interest point, and the similarity between the webpage text word and each ontology concept word is obtained by calculating the similarity between the word vector corresponding to the webpage text word and the word vector corresponding to the ontology concept word for reflecting each interest point. For example, the similarity between words may be measured by calculating the cosine value of the angle between two word vectors, which is not limited herein.
203. And accumulating the similarity between the webpage text words and each ontology concept word which is larger than a preset threshold value, and dividing the similarity by the number of the webpages browsed by the user to obtain the interest value of the user on each ontology concept word.
For the embodiment of the invention, as the similarity between the webpage text word and each ontology concept word is larger than the preset threshold value, the similarity between the webpage text word and each ontology concept word can be reflected, the higher the similarity is, the higher the interest of the user on the ontology concept word is, in the webpage browsing process, the user can jump a plurality of webpages, each webpage can extract a plurality of webpage text words, and the interest value of the user on the ontology concept word is obtained by dividing the accumulated similarity between the webpage text word and each ontology concept word larger than the preset threshold value by the number of webpages browsed by the user.
For example, there are a, b, c, d, e, f, g web text words extracted from behavior data corresponding to a web behavior browsed by a user, the similarity between a, b, c, d, e, f, g and each ontology concept is calculated respectively, the similarity reserved to be greater than 0.7 is a and sports ontology concept words are 0.8, b and music ontology concept words are 0.7, d and sports ontology concept words are 0.9, f and sports ontology concept words are 0.8, and since the number of web pages browsed by the user is 1, the interest value of the user under the music ontology concept is calculated to be 0.7, and the interest value under the sports ontology concept is calculated to be 0.8+0.9+0.8=2.5.
204. And screening the interest value of the user on each ontology concept word by analyzing the webpage text words mapped to the same ontology concept word in a preset time period to obtain the effective interest value of the user on each ontology concept word.
Since the user does not need to be limited to a single browsing operation during the action of browsing the web page, the user can stay on the interested page and jump to the next interested page even through the links provided by the interested page, and certainly, the user may also misoperate to click on some disturbed links. For a page of interest to a user, there should be a greater number of user-browsed pages, and the ontology concept words to which the web text words of the user-browsed web pages are mapped are indeed of interest to the user; for the interference page, a small number of user browsing pages should exist, and the ontology concept words mapped to the webpage text words of the user browsing webpages are not interesting to the user, so that the embodiment of the invention screens the number of the user browsing webpages and the ontology concept words mapped to the webpage text words of the user browsing webpages by analyzing the webpage text words mapped to the same ontology concept words in a preset time period, can discharge the influence of the interference information on the ontology concept words which are interesting to the user, and further keeps the effective interest value of the user on each ontology concept word.
In this step, if each web page text word mapped to the same ontology concept word in the preset time period is distributed in the same page or a few pages, the ontology concept word may be interference information such as advertisement words, and if each web page text word mapped to the same ontology concept word in the preset time period is distributed in the same plurality of pages, the ontology concept word is effective information, so, as shown in fig. 3, specifically, by analyzing web page text words mapped to the same ontology concept word in the preset time period, the interest value of the user on each ontology concept word is screened, and the effective interest value of the user on each ontology concept word can be obtained by adopting the following implementation manner:
2041. and counting the number of web pages browsed by the user to which the web page text words mapped to the same ontology concept words belong in a preset time period, and obtaining the number of web pages distributed around the same ontology concept words.
For the embodiment of the invention, the web pages are limited to be browsed by the user at a single time point, if errors are generated when the ontology concept words interested by the user are determined from a small number of user browses, the number of the web pages browsed by the user in a preset time period is large, and the method has higher reference value for determining the ontology concept words interested by the user. The preset period of time of the web page is a time range of the web page browsing behavior of the user, for example, 12:10 to 12:30, 8:00 to 10:00, the limitation is not limited herein.
In the process of counting the number of the web pages browsed by the user to which the web page text words mapped to the same ontology concept word belong in a preset time period, because each web page text word has a web page source identifier when mapped to the ontology concept word corresponding to the corresponding interest point, the number of the web pages distributed around the same ontology concept word is recorded by counting the web page browsed by the user to which the web page text word mapped to the same ontology concept word belongs through the web page source identifier.
2042. And screening the interest values of the user on each ontology concept word according to the webpage quantity distributed around the same ontology concept word to obtain the effective interest values of the user on each ontology concept word.
For the embodiment of the invention, the threshold value of the webpage quantity distributed around the same ontology concept word can be preset, the threshold value of the webpage quantity can indicate the webpage quantity of the source of the ontology concept word, if the webpage quantity of the source of the ontology concept word is more, the higher the interest degree of the user on the ontology concept word is indicated, and the interest value of the user on the ontology concept word is taken as the effective interest value, otherwise, if the webpage quantity of the source of the ontology concept word is less, the lower the interest degree of the user on the ontology concept word is indicated. Specifically, based on preset webpage quantity threshold values distributed around the same ontology concept words, the ontology concept words with the webpage quantity larger than the webpage quantity threshold values distributed around the same ontology concept words are screened out from all the ontology concept words, and interest values of users on the ontology concept words with the webpage quantity larger than the webpage quantity threshold values distributed around the same ontology concept words are obtained, so that effective interest values of the users on all the ontology concept words are obtained.
In this step, based on the page of each web page text word distribution mapped to the same ontology concept word, the weight value of the user browsing the web page mapped to the same ontology concept word can be calculated, and for the ontology concept word with a larger weight value, the probability that the ontology concept word is effective information is larger, so, as shown in fig. 4, specifically, by analyzing the web page text word mapped to the same ontology concept word in a preset time period, the interest value of the user on each ontology concept word is screened, and the following implementation manner can be adopted to obtain the effective interest value of the user on each ontology concept word:
2043. and calculating the weight value of the user browsing webpage mapped to the same ontology concept word according to the number of the user browsing webpages to which the webpage text word mapped to the same ontology concept word belongs and the interest value of the user on the same ontology concept word in a preset time period.
For the embodiment of the invention, the weight value of the user browsing webpage mapped to the same ontology concept word can be calculated based on the number of the user browsing webpages to which the webpage text word mapped to the same ontology concept word belongs in a preset time period and the number of the user browsing webpages to which the user browsing webpages are multiplied by the interest value of the user on the ontology concept word.
2044. And screening the interest values of the user on each ontology concept word according to the weight values of the user browsing web pages mapped to the same ontology concept word, so as to obtain the effective interest values of the user on each ontology concept word.
For the embodiment of the invention, a weight value threshold value of mapping the user browsing webpage onto the same ontology concept word can be set, wherein the weight value threshold value can indicate the interest degree of the user on the ontology concept word, if the weight value of mapping the user browsing webpage onto the same ontology concept word is higher, the interest degree of the user on the ontology concept word is higher, the interest value of the user on the ontology concept word is taken as an effective interest value, and conversely, if the weight value of mapping the user browsing webpage onto the same ontology concept word is lower, the interest of the user on the ontology concept word is not indicated. Specifically, based on a preset weight value threshold value of mapping the user browsing webpage onto the same ontology concept words, the ontology concept words with weight values larger than the weight value threshold value of mapping the user browsing webpage onto the same ontology concept words are screened out from the ontology concept words, and interest values of the user on the ontology concept words with weight values larger than the weight value threshold value of mapping the user browsing webpage onto the same ontology concept words are obtained, so that effective interest values of the user on the ontology concept words are obtained.
For the embodiment of the invention, besides setting the weight value threshold value of the user browsing webpage mapped to the same ontology concept word, the weight values of the user browsing webpage mapped to the same ontology concept word can be sequenced from large to small to obtain the weight value ranking corresponding to each ontology concept word, and the interest value of the user, before the weight value ranking is preset, on the ontology concept word is screened from the interest values of the user on each ontology concept word to obtain the effective interest value of the user on each ontology concept word
205. And constructing user interest portraits according to the effective interest values of the users on each ontology concept word.
For the embodiment of the invention, the user interest portrait further comprises attribute data of the user, and the user attribute data such as birthday, gender, address, hobbies and the like can be obtained through the registration information of the user logging in the website, and the user interest portrait is constructed by combining the attribute data of the user and the effective interest values of the user on each ontology concept word.
As practical application, the user interest portrayal can be used as a recommendation system, related content is pushed to the user according to the interest value of the user on each body concept, for example, the user interest portrayal is constructed to show that the interest value of the user on makeup is high, and makeup products such as skin care products are pushed to the user.
Further, as a specific implementation of the method shown in fig. 1, an embodiment of the present invention provides a device for constructing a user interest portrait, as shown in fig. 5, where the device includes: an acquisition unit 31, a mapping unit 32, a screening unit 33, a construction unit 34.
An acquisition unit 31 operable to acquire an ontology concept word for reflecting each point of interest;
the mapping unit 32 is configured to map, when a behavior operation of browsing a web page by a user is monitored, a web page text word of the web page browsed by the user onto an ontology concept word for reflecting a corresponding interest point, so as to obtain an interest value of the user on each ontology concept word;
the screening unit 33 may be configured to screen the interest value of the user on each ontology concept word by analyzing the webpage text word mapped to the same ontology concept word in a preset time period, so as to obtain an effective interest value of the user on each ontology concept word;
the construction unit 34 may be configured to construct a user interest portrait based on the effective interest values of the user on each ontology concept.
According to the construction device for the user interest image, provided by the invention, the ontology concept words used for reflecting the interest points are obtained, when the behavior operation of the user for browsing the webpage is monitored, the webpage text words of the user for browsing the webpage are mapped onto the ontology concept words used for reflecting the corresponding interest points, the interest values of the user on the ontology concept words are screened by analyzing the webpage text words mapped onto the same ontology concept words within a preset time period, so that the effective interest values of the user on the ontology concept words are obtained, and the user interest image is constructed based on the effective interest values. Compared with the construction mode of directly mapping the webpage text browsed by the user to the ontology concept of the corresponding interest point in the prior art, the method has the advantages that the existing webpage contains a large amount of interference information, the text in the interference information is usually on one webpage and can be mapped to the same ontology concept word, and the interest value of the user on each ontology concept word is screened by analyzing the webpage text word mapped to the same ontology concept word in a preset time period, so that the effective interest value of the user on each ontology concept word is obtained, the interference information contained in the webpage text can be eliminated, the effective interest value is reserved, and the constructed user interest figure is more accurate.
As a further explanation of the apparatus for constructing a user interest image shown in fig. 5, fig. 6 is a schematic structural diagram of another apparatus for constructing a user interest image according to an embodiment of the present invention, as shown in fig. 6, the mapping unit 32 includes:
the first calculation module 321 may be configured to perform similarity calculation on a webpage text word of a webpage browsed by a user and an ontology concept word for reflecting each interest point, so as to obtain similarity between the webpage text word and each ontology concept word;
the accumulating module 322 may be configured to accumulate the similarity between the text word of the web page and each of the ontology concept words greater than a preset threshold value, and divide the similarity by the number of web pages browsed by the user, so as to obtain the interest value of the user on each of the ontology concept words.
Further, the screening unit 33 includes:
the statistics module 331 may be configured to count the number of web pages browsed by the user to which the web page text word mapped to the same ontology concept word belongs in a preset period of time, so as to obtain the number of web pages distributed around the same ontology concept word;
the first filtering module 332 may be configured to filter the interest values of the user on each ontology concept word according to the number of web pages distributed around the same ontology concept word, so as to obtain effective interest values of the user on each ontology concept word.
Further, the first filtering module 332 may be specifically configured to, based on preset thresholds of number of web pages distributed around the same ontology concept word, screen the ontology concept words from each ontology concept word, where the number of web pages distributed around the same ontology concept word is greater than the thresholds of number of web pages;
the first filtering module 332 may be further specifically configured to obtain interest values of the user on the ontology concept words with the number of web pages distributed around the same ontology concept word being greater than the threshold of the number of web pages, so as to obtain effective interest values of the user on each ontology concept word.
Further, the screening unit 33 includes:
the second calculating module 333 may be configured to calculate, according to the number of web pages browsed by the user to which the web page text word mapped to the same ontology concept word belongs and the interest value of the user on the same ontology concept word within a preset period of time, a weight value of the web pages browsed by the user mapped to the same ontology concept word;
the second filtering module 334 may be configured to filter the interest value of the user on each ontology concept word according to the weight value of the user browsing the web page mapped to the same ontology concept word, so as to obtain the effective interest value of the user on each ontology concept word.
Further, the second filtering module 334 may be specifically configured to, based on a preset weight value threshold value of mapping the user browsing web page onto the same ontology concept word, screen the ontology concept word with a weight value greater than the weight value threshold value of mapping the user browsing web page onto the same ontology concept word from the ontology concept words;
the second filtering module 334 may be further specifically configured to obtain an interest value of the user on the ontology concept words mapped to the same ontology concept words by the user browsing web page, where the weight value of the ontology concept words is greater than the weight value threshold, so as to obtain an effective interest value of the user on each ontology concept word.
Further, the second filtering module 334 may be specifically configured to sort the weight values mapped to the same ontology concept words by the user browsing web page from big to small, so as to obtain a weight value ranking corresponding to each ontology concept word;
the second filtering module 334 may be further specifically configured to filter, from the interest values of the user on each ontology concept word, the interest values of the user on the ontology concept word, which are ranked before the preset value, of the weight value, so as to obtain effective interest values of the user on each ontology concept word.
It should be noted that, in the other corresponding descriptions of the functional units related to the apparatus for constructing a user interest image provided in this embodiment, reference may be made to the corresponding descriptions in fig. 1 and fig. 2, and no further description is given here.
Based on the above-mentioned methods shown in fig. 1 and 2, correspondingly, the present embodiment further provides a storage medium, on which a computer program is stored, which when executed by a processor, implements the above-mentioned method for constructing a user interest portrait shown in fig. 1 and 2.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
Based on the methods shown in fig. 1 and fig. 2 and the virtual device embodiments shown in fig. 5 and fig. 6, in order to achieve the above objects, the embodiments of the present application further provide a computer device, which may specifically be a personal computer, a server, a network device, etc., where the entity device includes a storage medium and a processor; a storage medium storing a computer program; a processor for executing a computer program to implement the method for constructing a user interest portrait as shown in fig. 1 and 2.
Optionally, the computer device may also include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., bluetooth interface, WI-FI interface), etc.
It will be appreciated by those skilled in the art that the physical device structure of the apparatus for constructing a user interest image provided in this embodiment is not limited to the physical device, and may include more or fewer components, or may combine some components, or may be different in arrangement of components.
The storage medium may also include an operating system, a network communication module. An operating system is a program that manages the computer device hardware and software resources described above, supporting the execution of information handling programs and other software and/or programs. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the entity equipment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. By applying the technical scheme of the application, compared with the prior art, the method and the device have the advantages that through analyzing the webpage text words mapped to the same ontology concept words in the preset time period, the effective interest values of the user on each ontology concept word are obtained after the interest values of the user on each ontology concept word are screened, interference information contained in the webpage text can be eliminated, the effective interest values are reserved, and the constructed user interest image is more accurate.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of a preferred implementation scenario and that the modules or flows in the drawing are not necessarily required to practice the application. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely illustrative of some embodiments of the application, and the application is not limited thereto, as modifications may be made by those skilled in the art without departing from the scope of the application.
Claims (8)
1. A method for constructing a representation of a user's interest, the method comprising:
acquiring ontology concept words for reflecting each interest point;
when the behavior operation of browsing the webpage by the user is monitored, mapping the webpage text word of the webpage browsed by the user to the ontology concept word for reflecting the corresponding interest point to obtain the interest value of the user on each ontology concept word;
screening interest values of the user on each ontology concept word by analyzing the webpage text words mapped to the same ontology concept word in a preset time period, wherein obtaining effective interest values of the user on each ontology concept word comprises calculating weight values of the user browsing webpages mapped to the same ontology concept word according to the number of the user browsing webpages to which the webpage text words mapped to the same ontology concept word belong in the preset time period and the interest values of the user on the same ontology concept word; screening interest values of the user on each ontology concept word according to the weight values of the user browsing webpages mapped to the same ontology concept word to obtain effective interest values of the user on each ontology concept word, and specifically screening the ontology concept words, of which the weight values of the user browsing webpages mapped to the same ontology concept word are larger than the weight value threshold, from each ontology concept word based on preset weight value threshold of the user browsing webpages mapped to the same ontology concept word; obtaining interest values of the user on the ontology concept words with the weight values which are larger than the weight value threshold and mapped on the same ontology concept words by the user browsing web pages, and obtaining effective interest values of the user on each ontology concept word, wherein the weight values are obtained by multiplying the number of the affiliated user browsing web pages with the interest values of the user on the same ontology concept words;
And constructing user interest portraits according to the effective interest values of the users on each ontology concept word.
2. The method of claim 1, wherein mapping the web text words of the web page browsed by the user onto the ontology concept words reflecting the corresponding points of interest, and obtaining the interest values of the user on each ontology concept word comprises:
performing similarity calculation on the webpage text words of the webpage browsed by the user and the ontology concept words for reflecting the interest points to obtain similarity between the webpage text words and the ontology concept words;
and accumulating the similarity between the webpage text words and each ontology concept word which is larger than a preset threshold value, and dividing the similarity by the number of the webpages browsed by the user to obtain the interest value of the user on each ontology concept word.
3. The method of claim 1, wherein the filtering the interest value of the user on each ontology concept word by analyzing the web text word mapped to the same ontology concept word in the preset time period to obtain the effective interest value of the user on each ontology concept word comprises:
counting the number of web pages browsed by a user to which the web page text words mapped to the same ontology concept words belong in a preset time period, and obtaining the number of web pages distributed around the same ontology concept words;
And screening the interest values of the user on each ontology concept word according to the webpage quantity distributed around the same ontology concept word to obtain the effective interest values of the user on each ontology concept word.
4. The method of claim 3, wherein the filtering the interest value of the user on each ontology concept word according to the number of web pages distributed around the same ontology concept word to obtain the effective interest value of the user on each ontology concept word comprises:
based on a preset webpage quantity threshold value distributed around the same ontology concept words, the quantity of which is larger than the webpage quantity threshold value, distributed around the same ontology concept words are screened out from all the ontology concept words;
and obtaining interest values of the user on the ontology concept words with the quantity of the webpages distributed around the same ontology concept words being larger than the webpage quantity threshold value, and obtaining effective interest values of the user on each ontology concept word.
5. The method of claim 1, wherein the filtering the interest values of the user on the respective ontology concept words according to the weight values of the user browsing the web page mapped to the same ontology concept words to obtain the effective interest values of the user on the respective ontology concept words comprises:
The weight values mapped to the same ontology concept words by the user browsing web pages are ranked from large to small, and the weight value ranking corresponding to each ontology concept word is obtained;
and screening the interest values of the users on the ontology concept words, which are ranked before the preset value, from the interest values of the users on the ontology concept words to obtain the effective interest values of the users on the ontology concept words.
6. A device for constructing a user interest image, the device comprising:
an acquisition unit for acquiring ontology concept words for reflecting each interest point;
the mapping unit is used for mapping the webpage text words of the webpage browsed by the user onto the ontology concept words for reflecting the corresponding interest points when the behavior operation of the webpage browsed by the user is monitored, so as to obtain the interest values of the user on each ontology concept word;
the screening unit is used for screening the interest value of the user on each ontology concept word by analyzing the webpage text words mapped to the same ontology concept word in a preset time period, wherein the obtaining of the effective interest value of the user on each ontology concept word comprises calculating the weight value of the user browsing webpage mapped to the same ontology concept word according to the number of the user browsing webpages to which the webpage text words mapped to the same ontology concept word belong in the preset time period and the interest value of the user on the same ontology concept word; screening interest values of the user on each ontology concept word according to the weight values of the user browsing webpages mapped to the same ontology concept word to obtain effective interest values of the user on each ontology concept word, and specifically screening the ontology concept words, of which the weight values of the user browsing webpages mapped to the same ontology concept word are larger than the weight value threshold, from each ontology concept word based on preset weight value threshold of the user browsing webpages mapped to the same ontology concept word; obtaining interest values of the user on the ontology concept words with the weight values which are larger than the weight value threshold and mapped on the same ontology concept words by the user browsing web pages, and obtaining effective interest values of the user on each ontology concept word, wherein the weight values are obtained by multiplying the number of the affiliated user browsing web pages with the interest values of the user on the same ontology concept words;
And the construction unit is used for constructing the user interest portrait according to the effective interest values of the user on each ontology concept word.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319421.3A CN110222191B (en) | 2019-04-19 | 2019-04-19 | User interest portrait construction method, device, computer equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319421.3A CN110222191B (en) | 2019-04-19 | 2019-04-19 | User interest portrait construction method, device, computer equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222191A CN110222191A (en) | 2019-09-10 |
| CN110222191B true CN110222191B (en) | 2023-08-22 |
Family
ID=67819941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910319421.3A Active CN110222191B (en) | 2019-04-19 | 2019-04-19 | User interest portrait construction method, device, computer equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222191B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235824A (en) * | 2013-05-06 | 2013-08-07 | 上海河广信息科技有限公司 | Method and system for determining web page texts users interested in according to browsed web pages |
| CN103853831A (en) * | 2014-03-10 | 2014-06-11 | 中国电子科技集团公司第二十八研究所 | Personalized searching realization method based on user interest |
| WO2017106051A1 (en) * | 2015-12-16 | 2017-06-22 | Alibaba Group Holding Limited | Method, system, and device for providing item information |
| CN108920521A (en) * | 2018-06-04 | 2018-11-30 | 上海财经大学 | User's portrait-item recommendation system and method based on pseudo- ontology |
| CN109325179A (en) * | 2018-09-17 | 2019-02-12 | 青岛海信网络科技股份有限公司 | A kind of method and device that content is promoted |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10019419B2 (en) * | 2013-06-06 | 2018-07-10 | Tencent Technology (Shenzhen) Company Limited | Method, server, browser, and system for recommending text information |
-
2019
- 2019-04-19 CN CN201910319421.3A patent/CN110222191B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235824A (en) * | 2013-05-06 | 2013-08-07 | 上海河广信息科技有限公司 | Method and system for determining web page texts users interested in according to browsed web pages |
| CN103853831A (en) * | 2014-03-10 | 2014-06-11 | 中国电子科技集团公司第二十八研究所 | Personalized searching realization method based on user interest |
| WO2017106051A1 (en) * | 2015-12-16 | 2017-06-22 | Alibaba Group Holding Limited | Method, system, and device for providing item information |
| CN108920521A (en) * | 2018-06-04 | 2018-11-30 | 上海财经大学 | User's portrait-item recommendation system and method based on pseudo- ontology |
| CN109325179A (en) * | 2018-09-17 | 2019-02-12 | 青岛海信网络科技股份有限公司 | A kind of method and device that content is promoted |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222191A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10277480B2 (en) | Method, apparatus, and system for determining a location corresponding to an IP address | |
| CN109697629B (en) | Product data pushing method and device, storage medium and computer equipment | |
| JP6494061B2 (en) | Advertisement information push method, apparatus, system, server, and computer-readable medium | |
| CN106940705B (en) | Method and equipment for constructing user portrait | |
| US10423648B2 (en) | Method, system, and computer readable medium for interest tag recommendation | |
| CN109325179B (en) | Content promotion method and device | |
| CN105989004B (en) | Information delivery preprocessing method and device | |
| CN102855256B (en) | For determining the method, apparatus and equipment of Website Evaluation information | |
| CN106919611B (en) | Product information pushing method and device | |
| CN104899220A (en) | Application program recommendation method and system | |
| CN104462336A (en) | Information pushing method and device | |
| US20170046447A1 (en) | Information Category Obtaining Method and Apparatus | |
| CN103870553B (en) | A kind of input resource supplying method and system | |
| CN111159563B (en) | Method, device, equipment and storage medium for determining user interest point information | |
| US20210097045A1 (en) | Object identifier index | |
| CN111782953A (en) | Recommendation method, device, equipment and storage medium | |
| CN107748801B (en) | News recommendation method and device, terminal equipment and computer readable storage medium | |
| CN108804491A (en) | item recommendation method, device, computing device and storage medium | |
| CN110569447B (en) | Network resource recommendation method and device and storage medium | |
| CN110222191B (en) | User interest portrait construction method, device, computer equipment and computer storage medium | |
| CN111353836B (en) | Commodity recommendation method, device and equipment | |
| CN110209908A (en) | Application recommended method, device, computer equipment and computer storage medium based on user interest portrait | |
| CN110955845A (en) | User interest identification method and device, and search result processing method and device | |
| KR20200029822A (en) | Providing Method of parameter for advertisement and server device supporting the same | |
| CN111914199B (en) | Page element filtering method, device, equipment and storage medium |
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 |