CN110222191A - Construction method, device, computer equipment and the computer storage medium of user interest portrait - Google Patents
Construction method, device, computer equipment and the computer storage medium of user interest portrait Download PDFInfo
- Publication number
- CN110222191A CN110222191A CN201910319421.3A CN201910319421A CN110222191A CN 110222191 A CN110222191 A CN 110222191A CN 201910319421 A CN201910319421 A CN 201910319421A CN 110222191 A CN110222191 A CN 110222191A
- Authority
- CN
- China
- Prior art keywords
- user
- ontological concept
- word
- concept word
- webpage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
This application discloses construction method, device and the computer storage mediums of a kind of user interest portrait, are related to data analysis technique field, can exclude the interference information contained in web page text, improve the accuracy of user interest portrait construction.The described method includes: obtaining the Ontological concept word for reflecting each point of interest;When monitoring the behavior operation of user's browsing webpage, the web page text word that user browses webpage is mapped to the Ontological concept word for being used to reflect corresponding point of interest, obtains interest value of the user on each Ontological concept word;By webpage this cliction being mapped in analysis preset time period on identical Ontological concept word, interest value of the user on each Ontological concept word is screened, effective interest value of the user on each Ontological concept word is obtained;According to effective interest value of the user on each Ontological concept word, user interest portrait is constructed.
Description
Technical field
The present invention relates to data analysis technique fields, construction method, device, meter particularly with regard to user interest portrait
Calculate machine equipment and computer storage medium.
Background technique
With the development of big data, the explosive growth of data volume and the maturation of big data analysis technology catch user
The behavioral data caught is more and more, and user's portrait is also more and more abundant with the surge of information, more and more finely, can be applied
Into client's marketing of certain industries itself.
The behavior that webpage is browsed by collecting user can construct user interest portrait, and user interest portrait includes more
A point of interest label and user are to the fancy grade of each point of interest, for example, user is 60, user to the fancy grade of sport
Fancy grade to music is 20 etc..The prior art is during constructing user interest portrait, it will usually preset multiple
Point of interest, when generating the browsing behavior of user in website, by user browse web sites in web page text to be mapped to characterization different
On the Ontological concept of point of interest, such as football is mapped to the points of interest such as ball, sport.
However, the user interest portrait of prior art building is usually that the web page text that user browses directly is mapped to table
On the Ontological concept for levying corresponding point of interest, due to containing a large amount of interference information in web page text, such as advertisement, navigation bar and
User misoperation etc., so that a large amount of interference information of point of interest label record in the user interest portrait of construction, leads to user
Interest portrait inaccuracy.
Summary of the invention
In view of this, the present invention provides construction method, device, computer equipment and the calculating of a kind of user interest portrait
Machine storage medium, main purpose are in the user interest for solving to construct at present portrait that point of interest label also has recorded a large amount of dry
Information is disturbed, the problem of user interest portrait inaccuracy is caused.
According to the present invention on one side, a kind of construction method of user interest portrait is provided, this method comprises:
Obtain the Ontological concept word for reflecting each point of interest;
When monitoring the behavior operation of user's browsing webpage, the web page text word that user browses webpage is mapped to and is used for
Reflect on the Ontological concept word of corresponding point of interest, obtains interest value of the user on each Ontological concept word;
By webpage this cliction being mapped in analysis preset time period on identical Ontological concept word, to user at each
Interest value on body notional word is screened, and effective interest value of the user on each Ontological concept word is obtained;
According to effective interest value of the user on each Ontological concept word, user interest portrait is constructed.
Further, the web page text word that user is browsed webpage is mapped to the ontology for being used to reflect corresponding point of interest
On notional word, obtaining interest value of the user on each Ontological concept word includes:
This cliction of webpage that user browses webpage is subjected to similarity with the Ontological concept word for being used to reflect each point of interest
It calculates, obtains the similarity between web page text word and each Ontological concept word;
It is browsed after being greater than the similarity of preset threshold between cumulative web page text word and each Ontological concept word divided by user
Webpage quantity obtains interest value of the user on each Ontological concept word.
Further, described webpage this cliction by being mapped in analysis preset time period on identical Ontological concept word,
Interest value of the user on each Ontological concept word is screened, effective interest of the user on each Ontological concept word is obtained
Value includes:
The web page text word owning user browsing webpage on identical Ontological concept word is mapped in statistics preset time period
Quantity obtains the webpage quantity around the distribution of identical Ontological concept word;
It is emerging on each Ontological concept word to user according to the webpage quantity around the distribution of identical Ontological concept word
Interesting value is screened, and effective interest value of the user on each Ontological concept word is obtained.
Further, the webpage quantity being distributed according to around identical Ontological concept word, to user at each
Interest value on body notional word is screened, and is obtained effective interest value of the user on each Ontological concept word and is included:
Based on the webpage amount threshold preset around the distribution of identical Ontological concept word, sieved from each Ontological concept word
Select the Ontological concept word that the webpage quantity around the distribution of identical Ontological concept word is greater than the webpage amount threshold;
It obtains user and is greater than the webpage amount threshold in the webpage quantity around the distribution of identical Ontological concept word
Interest value on Ontological concept word obtains effective interest value of the user on each Ontological concept word.
Further, described webpage this cliction by being mapped in analysis preset time period on identical Ontological concept word,
Interest value of the user on each Ontological concept word is screened, effective interest of the user on each Ontological concept word is obtained
Value includes:
According to the web page text word owning user browsing webpage being mapped in preset time period on identical Ontological concept word
Interest value of the quantity with user on identical Ontological concept word calculates user's browsing webpage and is mapped on identical Ontological concept word
Weighted value;
Webpage, which is browsed, according to the user is mapped to the weighted value on identical Ontological concept word, it is general in each ontology to user
The interest value read on word is screened, and effective interest value of the user on each Ontological concept word is obtained.
Further, it is described according to the user browse webpage be mapped to the weighted value on identical Ontological concept word, to
Interest value of the family on each Ontological concept word is screened, and effective interest value packet of the user on each Ontological concept word is obtained
It includes:
The weighted value threshold value that webpage is mapped on identical Ontological concept word is browsed based on user is preset, from each ontology
The weighted value that user's browsing webpage is mapped on identical Ontological concept word is filtered out in notional word is greater than the weighted value threshold
The Ontological concept word of value;
It obtains user and is mapped to the weighted value on identical Ontological concept word greater than the weight in user browsing webpage
The interest value being worth on the Ontological concept word of threshold value, obtains effective interest value of the user on each Ontological concept word.
Further, it is described according to the user browse webpage be mapped to the weighted value on identical Ontological concept word, to
Interest value of the family on each Ontological concept word is screened, and effective interest value packet of the user on each Ontological concept word is obtained
It includes:
The weighted value that webpage is mapped on identical Ontological concept word is browsed to the user to be ranked up from large to small, is obtained
The corresponding weighted value ranking of each Ontological concept word;
Screened in the interest value on each Ontological concept word from the user weighted value ranking default value it
Interest value of the preceding user on Ontological concept word obtains effective interest value of the user on each Ontological concept word.
According to the present invention on the other hand, a kind of construction device of user interest portrait is provided, described device includes:
Acquiring unit, for obtaining the Ontological concept word for reflecting each point of interest;
Map unit, for when monitoring the behavior operation of user's browsing webpage, user to be browsed to the webpage text of webpage
This word is mapped to the Ontological concept word for reflecting corresponding point of interest, obtains interest of the user on each Ontological concept word
Value;
Screening unit, for webpage this cliction by being mapped in analysis preset time period on identical Ontological concept word,
Interest value of the user on each Ontological concept word is screened, effective interest of the user on each Ontological concept word is obtained
Value;
Construction unit constructs user interest for effective interest value according to the user on each Ontological concept word
Portrait.
Further, the map unit includes:
First computing module, for user to be browsed to this cliction of webpage of webpage and is used to reflect the ontology of each point of interest
Notional word carries out similarity calculation, obtains the similarity between web page text word and each Ontological concept word;
Accumulator module, for add up between web page text word and each Ontological concept word greater than preset threshold similarity after
Webpage quantity is browsed divided by user, obtains interest value of the user on each Ontological concept word.
Further, the screening unit includes:
Statistical module is used belonging to the web page text word being mapped on identical Ontological concept word in preset time period for counting
Family browses the quantity of webpage, obtains the webpage quantity around the distribution of identical Ontological concept word;
First screening module, the webpage quantity for being distributed according to around identical Ontological concept word, to user each
Interest value on a Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained.
Further, first screening module is distributed specifically for being based on presetting around identical Ontological concept word
Webpage amount threshold, it is big that the webpage quantity around the distribution of identical Ontological concept word is filtered out from each Ontological concept word
In the Ontological concept word of the webpage amount threshold;
First screening module is specifically also used to obtain user in the webpage around the distribution of identical Ontological concept word
Quantity is greater than the interest value on the Ontological concept word of the webpage amount threshold, obtains user's having on each Ontological concept word
Imitate interest value.
Further, the screening unit includes:
Second computing module, for according to the web page text word institute being mapped in preset time period on identical Ontological concept word
Belong to user and browse interest value of the quantity of webpage with user on identical Ontological concept word, calculates user's browsing webpage and be mapped to phase
With the weighted value on Ontological concept word;
Second screening module is mapped to the weighted value on identical Ontological concept word for browsing webpage according to the user,
Interest value of the user on each Ontological concept word is screened, effective interest of the user on each Ontological concept word is obtained
Value.
Further, second screening module, specifically for based on preset user browse webpage be mapped to it is identical
Weighted value threshold value on Ontological concept word filters out user's browsing webpage from each Ontological concept word and is mapped to identical
Weighted value on body notional word is greater than the Ontological concept word of the weighted value threshold value;
Second screening module is specifically also used to obtain user and in the user browses webpage to be mapped to identical ontology general
The interest value that the weighted value on word is greater than on the Ontological concept word of the weighted value threshold value is read, obtains user in each Ontological concept
Effective interest value on word.
Further, second screening module, it is general specifically for being mapped to identical ontology to user browsing webpage
The weighted value read on word is ranked up from large to small, obtains the corresponding weighted value ranking of each Ontological concept word;
Second screening module is specifically also used to screen in the interest value on each Ontological concept word from the user
Interest value of the weighted value ranking in the user before default value on Ontological concept word, it is general in each ontology to obtain user
Read effective interest value on word.
Another aspect according to the present invention provides a kind of computer equipment, including memory and processor, the storage
Device is stored with computer program, and the processor realizes the construction method of user interest portrait when executing the computer program
Step.
Another aspect according to the present invention provides a kind of computer storage medium, is stored thereon with computer program, institute
The step of stating the construction method that user interest portrait is realized when computer program is executed by processor.
By above-mentioned technical proposal, the present invention provides the construction method and device of a kind of user interest portrait, passes through acquisition
For reflecting the Ontological concept word of each point of interest, and when monitoring the behavior operation of user's browsing webpage, user is browsed
The web page text word of webpage is mapped to the Ontological concept word for reflecting corresponding point of interest, by reflecting in analysis preset time period
The web page text word being mapped on identical Ontological concept word screens interest value of the user on each Ontological concept word, obtains
To effective interest value of the user on each Ontological concept word, thus based on effective interest value building user interest portrait.With it is existing
Have directly to be mapped on the Ontological concept of corresponding point of interest by the web page text for browsing user in technology and carries out user interest
The building mode of portrait is compared, and due to containing a large amount of interference informations in existing webpage, and text would generally be one in interference information
It on a webpage, and can be mapped on identical Ontological concept word, the present invention is by being mapped to identical in analysis preset time period
Web page text word on body notional word obtains user and exists to user after the interest value on each Ontological concept word is screened
Effective interest value on each Ontological concept word can exclude the interference information contained in web page text, retain effective emerging
Interest value, so that the user interest portrait of building is more acurrate.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of the construction method of user interest portrait provided in an embodiment of the present invention;
Fig. 2 shows the flow diagrams of the construction method of another user interest portrait provided in an embodiment of the present invention;
Fig. 3 shows interest value of a kind of couple of user provided in an embodiment of the present invention on each Ontological concept word and sieves
The flow diagram of choosing;
Fig. 4 shows another interest value to user on each Ontological concept word provided in an embodiment of the present invention and carries out
The flow diagram of screening;
Fig. 5 shows a kind of structural schematic diagram of the construction device of user interest portrait provided in an embodiment of the present invention;
Fig. 6 shows the structural schematic diagram of the construction device of another user interest portrait provided in an embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
The embodiment of the invention provides a kind of construction method of user interest portrait, can exclude to contain in web page text
Interference information improves the accuracy of user interest portrait construction, as shown in Figure 1, this method comprises:
101, the Ontological concept word for reflecting each point of interest is obtained.
Wherein, Ontological concept word is the word that point of interest concept is indicated in this body surface, for example, amusement, politics, sport, sound
It is happy etc., it, specifically can be with word since each Ontological concept word has different characterizations, contextual feature etc. here without limiting
The each Ontological concept word of vectorial.
It should be noted that, although may include subclass relation in each Ontological concept word, for example, including shadow in amusement
Depending on, movement etc., football included below, basketball etc. are moved, is mutually juxtaposed between Ontological concept word here, each ontology is general
Word is read as individual term vector.
102, when monitoring the behavior operation of user's browsing webpage, the web page text word that user browses webpage is mapped to
For reflecting the Ontological concept word of corresponding point of interest, interest value of the user on each Ontological concept word is obtained.
During browsing webpage, user can browse user for oneself interested webpage, for example, user compares
Like making up, then often can browse or search for makeups class webpage, user likes sport, then often can browse or search for sport
Class webpage, the process specifically searched for can be by jumping in other webpages, can also be and directly scanned for by search column.
Wherein, it is usually that user clicks the web page browsing behavior that the page generates, and passes through that user, which browses the behavior of webpage,
It clicks the different region of the page and jumps to the different display pages.When generating user's browsing webpage behavior, can specifically pass through
It is buried a little in front end or the daily record data of parsing rear end, the corresponding behavioral data of acquisition user's browsing webpage behavior is clear from user
It lookes in the corresponding behavioral data of webpage behavior and extracts web page text, and web page text is handled, obtain web page text word,
Further respectively by the corresponding term vector of web page text word word corresponding with being used to reflect the Ontological concept word of each point of interest to
Amount carries out similarity calculation, obtains the similarity between each web page text word and each Ontological concept word, and remain larger than pre-
If the similarity of threshold value, the similarity between web page text word and each Ontological concept word browse after adding up divided by user
Webpage quantity obtains interest value of the user under each Ontological concept word.
For the embodiment of the present invention, webpage text specifically is being extracted from the corresponding behavioral data of user's browsing webpage behavior
During this, text structure in webpage can use, the web page text in webpage in different zones is extracted, thus quick and precisely
Ground extracts web page text.Under normal conditions, text sections can be saved in webpage, for example, theme type text block, catalogue
Type text block, picture type text block etc. further extract the web page text in webpage in different text blocks.
103, by webpage this cliction being mapped in analysis preset time period on identical Ontological concept word, to user each
Interest value on a Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained.
For the embodiment of the present invention, there are web page text words in each webpage of user's browsing, and each webpage is literary
This word can all be mapped to corresponding Ontological concept word, and obtain interest value of the user on each Ontological concept word, but by
There may be the interference informations such as advertisement in webpage, so that interest value of the obtained user on each Ontological concept word is not
Accurately, it is to be understood that if there is interference informations such as advertisements, the web page text word that user browses in webpage usually compares
It concentrates, the Ontological concept word which be mapped to accordingly compares concentration, is typically distributed in a small amount of webpage;And user
Web page text word in webpage interested is usually more dispersed, and the Ontological concept word which be mapped to accordingly compares
Dispersion, is typically distributed in a large amount of webpages, can be specifically mapped on identical Ontological concept word by understanding in preset time period
Web page text word be distributed webpage the case where, interest value of the user on each Ontological concept word is screened, will be mapped to
Web page text word on identical Ontological concept word is distributed in the deletion of the interest value on the Ontological concept word of the less page, as invalid
Interest value will be mapped to interest value of web page text word distribution on this pronouns, general term for nouns, numerals and measure words compared with multi-page on identical Ontological concept word
Retain, as effective interest value.
Illustratively, user browses in webpage A there are web page text word a1, a2, a3, a4, a5, web page text word a1, a2,
A3 is mapped to Ontological concept word M1, and a4, a5 are mapped to Ontological concept word M2, user browse in webpage B there are web page text word b1,
B2, b3, web page text word b1, b2 are mapped to Ontological concept word M2, and web page text word b3 is mapped to Ontological concept word M1, and user is clear
Look in webpage C that there are web page text word c1, c2, c3, web page text word c1, c2 to be mapped to Ontological concept word M1, c3 is mapped to this
Body notional word M3 passes through statistics by the available user of step 102 interest value on Ontological concept word M1, M2, M3 respectively
The web page text word being mapped on identical Ontological concept word, the web page text word being mapped on Ontological concept word M1 have a1, a2,
A4, b3, c1, c2, the web page text word being mapped on Ontological concept word M2 have a4, a5, b1, b2, are mapped to Ontological concept word M3
On web page text word have c3, so, the webpage that the web page text word being mapped on Ontological concept word M1, M2 is distributed compares point
It dissipates, retains interest value of the user on Ontological concept word M1, M2, as effective interest value, and be mapped on Ontological concept word M3
The webpage that is distributed of web page text word compare concentration, interest value of the user on Ontological concept word M2 is deleted, as invalid emerging
Interest value.
104, effective interest value according to the user on each Ontological concept word, building user interest portrait.
Since effective interest value under each Ontological concept word is more accurate user after removal webpage interference information clear
The preference profile look in behavior, further effective interest value according to user on each Ontological concept word, being formed in record has
The user interest of each point of interest is drawn a portrait.
For the embodiment of the present invention, constructs user interest portrait and be equivalent to the process to label to user, specifically exist
Construct user interest portrait during, due to user the virtual value on each Ontological concept word with user browse webpage in
Appearance may be variation, by the way that virtual value of the user on each Ontological concept word is carried out mark to user as dynamic data
Label label to user based on virtual value of the user on each Ontological concept word for accurate user interest portrait
On the basis of, it needs to label to user as static data in conjunction with attribute datas such as name, gender, the ages of user,
To construct user interest portrait.
The embodiment of the present invention provides a kind of construction method of user interest portrait, by obtaining for reflecting each point of interest
Ontological concept word, and when monitor user browse webpage behavior operation when, by user browse webpage web page text word reflect
It is mapped to the Ontological concept word for reflecting corresponding point of interest, by being mapped to identical Ontological concept word in analysis preset time period
On web page text word, interest value of the user on each Ontological concept word is screened, it is general in each ontology to obtain user
Effective interest value on word is read, thus based on effective interest value building user interest portrait.With directly pass through in the prior art by
The building mode that the web page text of user's browsing is mapped to progress user interest portrait on the Ontological concept of corresponding point of interest is compared,
Due to containing a large amount of interference informations in existing webpage, and text would generally be on a webpage in interference information, and can map
Onto identical Ontological concept word, the present invention is by analyzing the web page text being mapped on identical Ontological concept word in preset time period
Word obtains user's having on each Ontological concept word to user after the interest value on each Ontological concept word is screened
Interest value is imitated, the interference information contained in web page text can be excluded, retain effective interest value, so that the user of building is emerging
Interest portrait is more acurrate.
The embodiment of the invention provides the construction method of another user interest portrait, exclude to contain in web page text dry
Information is disturbed, improves the accuracy of user interest portrait construction, as shown in Figure 2, which comprises
201, the Ontological concept word for reflecting each point of interest is obtained.
For the embodiment of the present invention, detailed process and step for reacting the Ontological concept word of each point of interest are specifically obtained
Content described in rapid 101 is identical, herein without repeating.
202, when monitor user browse webpage behavior operation when, by user browse webpage this cliction of webpage be used for
Reflect that the Ontological concept word of each point of interest carries out similarity calculation, obtains between web page text word and each Ontological concept word
Similarity.
It should be noted that the overdue web page browsing behavior for hitting generation in order to prevent, can browse webpage generating user
When behavior, webpage behavior can be browsed to user and screened, retaining user in the browsing pages residence time is more than preset time
Web page browsing behavior.
For the embodiment of the present invention, specifically can by by user browse webpage this cliction of webpage be used to reflect it is each emerging
The Ontological concept word of interest point is expressed as the corresponding term vector of web page text word and is used to reflect that the ontology of each point of interest to be general
The corresponding term vector of word is read, the Ontological concept for calculating the corresponding term vector of web page text word with being used to reflect each point of interest is passed through
Similarity between the corresponding term vector of word obtains the similarity between web page text word and each Ontological concept word.For example, can
To measure the similarity between word by calculating the included angle cosine value between two term vectors, here without limiting.
203, divided by user after the similarity for being greater than preset threshold between web page text word and each Ontological concept word that adds up
Webpage quantity is browsed, interest value of the user on each Ontological concept word is obtained.
For the embodiment of the present invention, due to being greater than the similar of preset threshold between web page text word and each Ontological concept word
Degree is able to reflect the similarity degree between web page text word and Ontological concept word, and similarity degree is higher, shows user to the ontology
Interest on notional word is higher, and user may jump multiple webpages during browsing webpage, and each webpage can mention
Multiple web page text words are taken, after being greater than the similarity of preset threshold between cumulative web page text word and each Ontological concept word
Webpage quantity is browsed divided by user, obtains interest value of the user on Ontological concept word.
For example, from user browse the web page text word extracted in the corresponding behavioral data of a certain webpage behavior have a, b, c, d,
E, f, g calculate separately the similarity between a, b, c, d, e, f, g and each Ontological concept, remain larger than 0.7 similarity and have a
With sport Ontological concept word be 0.8, b and music Ontological concept word is 0.7, d and sport Ontological concept word is 0.9, f and sport sheet
Body notional word is 0.8, is 1 since user browses webpage quantity, and calculating interest value of the user under music Ontological concept is 0.7,
Interest value under sport Ontological concept is 0.8+0.9+0.8=2.5.
204, by webpage this cliction being mapped in analysis preset time period on identical Ontological concept word, to user each
Interest value on a Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained.
Since user is in the behavior operating process of browsing webpage, it is not limited to single browse operation, but it is emerging feeling
The link that the interesting page can be stopped or even can be provided by the page interested, jumps to next interested page, also has certainly
The link of some interference is clicked in possible maloperation.The page interested in user, it should can have greater number of user's browsing
The page, and the Ontological concept word that the web page text word of user's browsing webpage is mapped to is strictly interested to user;And it is right
In the interference page, it should which there are a small amount of user's browsing pages, and user browses the ontology that the web page text word of webpage is mapped to
Notional word is not interested to user, so the embodiment of the present invention is by being mapped to identical ontology in analysis preset time period
Webpage this cliction on notional word, browses webpage quantity to user and user browses the sheet that the web page text word of webpage is mapped to
Body notional word is screened, and influence of the interference information to the interested Ontological concept word of user is determined can be discharged, further protect
Continue to employ effective interest value of the family on each Ontological concept word.
In this step, if each web page text word distribution being mapped in preset time period on identical Ontological concept word
In the same page or the few page, then the Ontological concept word may be the interference informations such as advertising words, if preset time period
The each web page text word being inside mapped on identical Ontological concept word is distributed in multiple pages, then the Ontological concept word is effective
Information, so, as shown in figure 3, herein especially by the webpage being mapped in analysis preset time period on identical Ontological concept word
Word screens interest value of the user on each Ontological concept word, it is effective on each Ontological concept word to obtain user
Interest value can use following implementation:
2041, the web page text word owning user browsing net being mapped on identical Ontological concept word in preset time period is counted
The quantity of page obtains the webpage quantity around the distribution of identical Ontological concept word.
For the embodiment of the present invention, it is limited that upper user of single time point browses webpage, if come from a small amount of user browsing true
Error can be generated by determining the interested Ontological concept word of user, and user's browsing webpage quantity is more within a preset period of time, for
Determine that the interested Ontological concept word of user has higher reference value.Here webpage preset time period is that user browses net
The time range that page line is, for example, between 12:10 to 12:30, between 8:00 to 10:00, here without limiting.
The web page text word owning user browsing being specifically mapped in statistics preset time period on identical Ontological concept word
During the quantity of webpage, since each web page text word is being mapped to the Ontological concept for being mutually applied to the corresponding point of interest of reflection
All there is web page source mark when word, statistics can be identified by the web page source and is mapped to webpage text on identical Ontological concept word
This word owning user browses webpage, thus webpage quantity of the record around the distribution of identical Ontological concept word.
2042, according to the webpage quantity around the distribution of identical Ontological concept word, to user in each Ontological concept word
On interest value screened, obtain effective interest value of the user on each Ontological concept word.
For the embodiment of the present invention, the webpage quantity threshold preset around the distribution of identical Ontological concept word can be set
Value, which can show that the webpage quantity in Ontological concept word source, if Ontological concept word source page quantity
It is more, then illustrate that user is higher to the Ontological concept word interest level, and the interest value by user on the Ontological concept word
As effective interest value, on the contrary, illustrating user to the Ontological concept word sense if Ontological concept word source page negligible amounts
Level of interest is lower.It specifically can be based on the webpage amount threshold preset around the distribution of identical Ontological concept word, from each
The Ontological concept for being greater than webpage amount threshold around the webpage quantity of identical Ontological concept word distribution is filtered out in Ontological concept word
Word, and obtain user and be greater than on the Ontological concept word of webpage amount threshold in the webpage quantity around the distribution of identical Ontological concept word
Interest value, obtain effective interest value of the user on each Ontological concept word.
In this step, the page based on each web page text word distribution being mapped on identical Ontological concept word, can be with
It calculates user's browsing webpage and is mapped to the weighted value on identical Ontological concept word, the Ontological concept word bigger for weighted value should
Ontological concept word is bigger for the probability of effective information, so, as shown in figure 4, especially by being mapped in analysis preset time period
Webpage this cliction on identical Ontological concept word, screens interest value of the user on each Ontological concept word, is used
Effective interest value of the family on each Ontological concept word can use following implementation:
2043, net is browsed according to the web page text word owning user being mapped on identical Ontological concept word in preset time period
Interest value of the quantity of page with user on identical Ontological concept word calculates user's browsing webpage and is mapped to identical Ontological concept word
On weighted value.
It, specifically can be based on the webpage being mapped in preset time period on identical Ontological concept word for the embodiment of the present invention
Text word owning user browses the quantity of webpage, and by the quantity of owning user browsing webpage and user on the Ontological concept word
Interest value be multiplied, user be calculated browse webpage and be mapped to weighted value on identical Ontological concept word.
2044, webpage is browsed according to the user and is mapped to the weighted value on identical Ontological concept word, to user each
Interest value on Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained.
For the embodiment of the present invention, user can be set and browse the weighted value threshold that webpage is mapped on identical Ontological concept word
Value, the weighted value threshold value can show that user to Ontological concept word interest level, if user browse webpage be mapped to it is identical
Weighted value value on Ontological concept word is higher, then illustrates that user is higher to the Ontological concept word interest level, and user is existed
Interest value on the Ontological concept word is as effective interest value, on the contrary, if user browses webpage and is mapped to identical Ontological concept
Weighted value on word is lower, then illustrates that user loses interest in the Ontological concept word.It specifically can be clear based on user is preset
Webpage of looking at is mapped to the weighted value threshold value on identical Ontological concept word, and user is filtered out from each Ontological concept word and browses webpage
The weighted value being mapped on identical Ontological concept word is greater than the Ontological concept word of weighted value threshold value, and obtains user and browse in user
Webpage is mapped to the weighted value on identical Ontological concept word greater than the interest value on the Ontological concept word of weighted value threshold value, is used
Effective interest value of the family on each Ontological concept word.
For the embodiment of the present invention, the weighted value threshold on identical Ontological concept word is mapped in addition to setting user browses webpage
Except value, can also specifically the weighted value that webpage is mapped on identical Ontological concept word be browsed to user and arranged from large to small
Sequence obtains the corresponding weighted value ranking of each Ontological concept word, and sieves in the interest value on each Ontological concept word from user
Interest value of the weighted value ranking in the user before default value on Ontological concept word is selected, obtains user in each ontology
Effective interest value on notional word
205, effective interest value according to the user on each Ontological concept word, building user interest portrait.
Further include the attribute data of user for the embodiment of the present invention, in user interest portrait, can specifically pass through user
The registration information of Website login is available to arrive such as birthday, gender, address, hobby user attribute data, in conjunction with the category of user
Property data and user on each Ontological concept word effective interest value building user interest portrait.
As practical application, user interest portrait can do recommender system, according to user on each Ontological concept
Related content is pushed to user by interest value, for example, building user interest portrait shows that interest value of the user in makeups is very high,
The makeups product of skin care item etc is then pushed to user.
Further, the specific implementation as Fig. 1 the method, the embodiment of the invention provides a kind of user interest portraits
Construction device, as shown in figure 5, described device includes: acquiring unit 31, map unit 32, screening unit 33, construction unit
34。
Acquiring unit 31 can be used for obtaining the Ontological concept word for reflecting each point of interest;
Map unit 32, for when monitoring the behavior operation of user's browsing webpage, user to be browsed to the webpage of webpage
Text word is mapped to the Ontological concept word for reflecting corresponding point of interest, obtains interest of the user on each Ontological concept word
Value;
Screening unit 33 can be used for the webpage sheet by being mapped on identical Ontological concept word in analysis preset time period
Cliction screens interest value of the user on each Ontological concept word, obtains user's having on each Ontological concept word
Imitate interest value;
Construction unit 34, can be used for effective interest value according to the user on each Ontological concept word, and building is used
Family interest portrait.
The construction device of a kind of user interest portrait provided by the invention, by obtaining the sheet for reflecting each point of interest
Body notional word, and when monitoring the behavior operation of user's browsing webpage, the web page text word that user browses webpage is mapped to
For reflecting the Ontological concept word of corresponding point of interest, by being mapped on identical Ontological concept word in analysis preset time period
Web page text word screens interest value of the user on each Ontological concept word, obtains user in each Ontological concept word
On effective interest value, thus based on effective interest value building user interest portrait.With in the prior art directly by by user
The building mode that the web page text of browsing is mapped to progress user interest portrait on the Ontological concept of corresponding point of interest is compared, due to
Contain a large amount of interference informations in existing webpage, and text would generally be on a webpage in interference information, and can be mapped to phase
With on Ontological concept word, the present invention passes through the web page text word being mapped on identical Ontological concept word in analysis preset time period,
To user after the interest value on each Ontological concept word is screened, it is effective emerging on each Ontological concept word to obtain user
Interest value, can exclude the interference information contained in web page text, retain effective interest value, so that the user interest of building is drawn
As more acurrate.
The further explanation of construction device as the portrait of user interest shown in Fig. 5, Fig. 6 is according to embodiments of the present invention
The structural schematic diagram of the construction device of another user interest portrait, as shown in fig. 6, the map unit 32 includes:
First computing module 321 can be used for browsing user into this cliction of webpage of webpage and be used to reflect each interest
The Ontological concept word of point carries out similarity calculation, obtains the similarity between web page text word and each Ontological concept word;
Accumulator module 322 can be used for being greater than preset threshold between cumulative web page text word and each Ontological concept word
Webpage quantity is browsed divided by user after similarity, obtains interest value of the user on each Ontological concept word.
Further, the screening unit 33 includes:
Statistical module 331 can be used for counting the web page text being mapped on identical Ontological concept word in preset time period
Word owning user browses the quantity of webpage, obtains the webpage quantity around the distribution of identical Ontological concept word;
First screening module 332, can be used for according to the webpage quantity around the distribution of identical Ontological concept word, to
Interest value of the family on each Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained.
Further, first screening module 332 specifically can be used for being based on presetting around identical Ontological concept
The webpage amount threshold of word distribution filters out the webpage around the distribution of identical Ontological concept word from each Ontological concept word
Quantity is greater than the Ontological concept word of the webpage amount threshold;
First screening module 332 specifically can be also used for obtaining user described around identical Ontological concept word point
The webpage quantity of cloth is greater than the interest value on the Ontological concept word of the webpage amount threshold, obtains user in each Ontological concept
Effective interest value on word.
Further, the screening unit 33 includes:
Second computing module 333 can be used for according to the webpage being mapped on identical Ontological concept word in preset time period
Text word owning user browses interest value of the quantity of webpage with user on identical Ontological concept word, calculates user and browses webpage
The weighted value being mapped on identical Ontological concept word;
Second screening module 334 can be used for being mapped on identical Ontological concept word according to user browsing webpage
Weighted value screens interest value of the user on each Ontological concept word, obtains user on each Ontological concept word
Effective interest value.
Further, second screening module 334 specifically can be used for being based on presetting user and browse webpage mapping
Weighted value threshold value onto identical Ontological concept word filters out user's browsing webpage from each Ontological concept word and is mapped to
Weighted value on identical Ontological concept word is greater than the Ontological concept word of the weighted value threshold value;
Second screening module 334 specifically can be also used for acquisition user in user browsing webpage and be mapped to phase
The interest value being greater than on the Ontological concept word of the weighted value threshold value with the weighted value on Ontological concept word, obtains user each
Effective interest value on Ontological concept word.
Further, second screening module 334 specifically can be used for being mapped to user browsing webpage identical
Weighted value on Ontological concept word is ranked up from large to small, obtains the corresponding weighted value ranking of each Ontological concept word;
Second screening module 334 specifically can be also used for the interest from the user on each Ontological concept word
Interest value of the weighted value ranking in the user before default value on Ontological concept word is screened in value, obtains user each
Effective interest value on a Ontological concept word.
It should be noted that each functional unit involved by a kind of construction device of user interest portrait provided in this embodiment
Other it is corresponding describe, can be with reference to the corresponding description in Fig. 1 and Fig. 2, details are not described herein.
It is deposited thereon based on above-mentioned method as depicted in figs. 1 and 2 correspondingly, the present embodiment additionally provides a kind of storage medium
Computer program is contained, which realizes the building of above-mentioned user interest portrait as depicted in figs. 1 and 2 when being executed by processor
Method.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which produces
Product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is each
Method described in implement scene.
Based on above-mentioned method as shown in Figure 1 and Figure 2 and Fig. 5, virtual bench embodiment shown in fig. 6, in order to realize
Above-mentioned purpose, the embodiment of the present application also provides a kind of computer equipments, are specifically as follows personal computer, server, network
Equipment etc., the entity device include storage medium and processor;Storage medium, for storing computer program;Processor is used for
Computer program is executed to realize the construction method of above-mentioned user interest portrait as depicted in figs. 1 and 2.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as blue tooth interface, WI-FI interface).
It will be understood by those skilled in the art that the entity device of the construction device of user interest portrait provided in this embodiment
Structure does not constitute the restriction to the entity device, may include more or fewer components, perhaps combine certain components or
Different component layouts.
It can also include operating system, network communication module in storage medium.Operating system is that the above-mentioned computer of management is set
The program of standby hardware and software resource, supports the operation of message handling program and other softwares and/or program.Network communication mould
Block leads to for realizing the communication between each component in storage medium inside, and between other hardware and softwares in the entity device
Letter.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Pass through the skill of application the application
Art scheme, compared with currently available technology, the present invention in analysis preset time period by being mapped on identical Ontological concept word
Web page text word obtains user in each Ontological concept to user after the interest value on each Ontological concept word is screened
Effective interest value on word, can exclude the interference information contained in web page text, retain effective interest value, so that building
User interest portrait it is more acurrate.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of construction method of user interest portrait, which is characterized in that the described method includes:
Obtain the Ontological concept word for reflecting each point of interest;
When monitoring the behavior operation of user's browsing webpage, the web page text word that user browses webpage is mapped to and is used to reflect
On the Ontological concept word of corresponding point of interest, interest value of the user on each Ontological concept word is obtained;
It is general in each ontology to user by webpage this cliction being mapped in analysis preset time period on identical Ontological concept word
The interest value read on word is screened, and effective interest value of the user on each Ontological concept word is obtained;
According to effective interest value of the user on each Ontological concept word, user interest portrait is constructed.
2. the method according to claim 1, wherein the web page text word that user is browsed webpage is mapped to
For reflecting the Ontological concept word of corresponding point of interest, obtaining interest value of the user on each Ontological concept word includes:
This cliction of webpage that user browses webpage is subjected to similarity calculation with the Ontological concept word for being used to reflect each point of interest,
Obtain the similarity between web page text word and each Ontological concept word;
It is greater than after the similarity of preset threshold between cumulative web page text word and each Ontological concept word and browses webpage divided by user
Quantity obtains interest value of the user on each Ontological concept word.
3. the method according to claim 1, wherein described by being mapped to identical in analysis preset time period
Webpage this cliction on body notional word, screens interest value of the user on each Ontological concept word, obtains user each
Effective interest value on a Ontological concept word includes:
The quantity of the web page text word owning user browsing webpage on identical Ontological concept word is mapped in statistics preset time period,
Obtain the webpage quantity around the distribution of identical Ontological concept word;
According to the webpage quantity around the distribution of identical Ontological concept word, to interest value of the user on each Ontological concept word
It is screened, obtains effective interest value of the user on each Ontological concept word.
4. according to the method described in claim 3, it is characterized in that, described surround what identical Ontological concept word was distributed according to
Webpage quantity screens interest value of the user on each Ontological concept word, obtains user on each Ontological concept word
Effective interest value include:
Based on the webpage amount threshold preset around the distribution of identical Ontological concept word, filtered out from each Ontological concept word
The webpage quantity around the distribution of identical Ontological concept word is greater than the Ontological concept word of the webpage amount threshold;
Obtain the ontology that user is greater than the webpage amount threshold in the webpage quantity around the distribution of identical Ontological concept word
Interest value on notional word obtains effective interest value of the user on each Ontological concept word.
5. the method according to claim 1, wherein described by being mapped to identical in analysis preset time period
Webpage this cliction on body notional word, screens interest value of the user on each Ontological concept word, obtains user each
Effective interest value on a Ontological concept word includes:
According to the quantity for the web page text word owning user browsing webpage being mapped in preset time period on identical Ontological concept word
With interest value of the user on identical Ontological concept word, calculates user's browsing webpage and be mapped to the weight on identical Ontological concept word
Value;
Webpage is browsed according to the user and is mapped to the weighted value on identical Ontological concept word, to user in each Ontological concept word
On interest value screened, obtain effective interest value of the user on each Ontological concept word.
6. according to the method described in claim 5, it is characterized in that, described be mapped to identical according to user browsing webpage
Weighted value on body notional word screens interest value of the user on each Ontological concept word, obtains user at each
Effective interest value on body notional word includes:
The weighted value threshold value that webpage is mapped on identical Ontological concept word is browsed based on user is preset, from each Ontological concept
The weighted value that user's browsing webpage is mapped on identical Ontological concept word is filtered out in word is greater than the weighted value threshold value
Ontological concept word;
It obtains user and is mapped to the weighted value on identical Ontological concept word greater than the weighted value threshold in user browsing webpage
Interest value on the Ontological concept word of value obtains effective interest value of the user on each Ontological concept word.
7. according to method described in right 5, which is characterized in that described according to the user to browse webpage to be mapped to identical ontology general
The weighted value on word is read, interest value of the user on each Ontological concept word is screened, it is general in each ontology to obtain user
The effective interest value read on word includes:
The weighted value that webpage is mapped on identical Ontological concept word is browsed to the user to be ranked up from large to small, is obtained each
The corresponding weighted value ranking of Ontological concept word;
The weighted value ranking is screened in the interest value on each Ontological concept word from the user before default value
Interest value of the user on Ontological concept word obtains effective interest value of the user on each Ontological concept word.
8. a kind of construction device of user interest portrait, which is characterized in that described device includes:
Acquiring unit, for obtaining the Ontological concept word for reflecting each point of interest;
Map unit, for when monitoring the behavior operation of user's browsing webpage, user to be browsed to the web page text word of webpage
It is mapped to the Ontological concept word for reflecting corresponding point of interest, obtains interest value of the user on each Ontological concept word;
Screening unit, for webpage this cliction by being mapped in analysis preset time period on identical Ontological concept word, to
Interest value of the family on each Ontological concept word is screened, and effective interest value of the user on each Ontological concept word is obtained;
Construction unit constructs user interest portrait for effective interest value according to the user on each Ontological concept word.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is located
The step of reason device realizes method described in any one of claims 1 to 7 when executing.
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 true CN110222191A (en) | 2019-09-10 |
CN110222191B 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 (6)
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 |
US20140365868A1 (en) * | 2013-06-06 | 2014-12-11 | Tencent Technology (Shenzhen) Company Limited | Method, server, browser, and system for recommending text information |
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 |
-
2019
- 2019-04-19 CN CN201910319421.3A patent/CN110222191B/en active Active
Patent Citations (6)
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 |
US20140365868A1 (en) * | 2013-06-06 | 2014-12-11 | Tencent Technology (Shenzhen) Company Limited | Method, server, browser, and system for recommending text information |
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 |
---|---|
CN110222191B (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6494061B2 (en) | Advertisement information push method, apparatus, system, server, and computer-readable medium | |
CN110020188A (en) | Recommended based on the Global Vector of implicit interactions and profile data | |
US20110258149A1 (en) | Ranking search results using click-based data | |
JP5357432B2 (en) | Information processing apparatus, information processing method, and program | |
CN106919611B (en) | Product information pushing method and device | |
CN109753601B (en) | Method and device for determining click rate of recommended information and electronic equipment | |
CN109447713A (en) | A kind of recommended method and device of knowledge based map | |
EP3129938A1 (en) | Customizing evaluation information presentation | |
WO2008095034A1 (en) | Content identification expansion | |
CN103646341B (en) | A kind of website provides the recommendation method and apparatus of object | |
US9330071B1 (en) | Tag merging | |
KR101562279B1 (en) | Mobile device based on inference of user intent and content recommending method using the same | |
CN110275952A (en) | News recommended method, device and medium based on user's short-term interest | |
US10762122B2 (en) | Method and device for assessing quality of multimedia resource | |
CN109064293A (en) | Method of Commodity Recommendation, device, computer equipment and storage medium | |
JP6405343B2 (en) | Information processing apparatus, information processing method, and program | |
CN109711931A (en) | Method of Commodity Recommendation, device, equipment and storage medium based on user's portrait | |
CN110223186A (en) | User's similarity determines method and information recommendation method | |
CN111967914A (en) | User portrait based recommendation method and device, computer equipment and storage medium | |
CN107103028A (en) | A kind of information processing method and device | |
KR100987330B1 (en) | A system and method generating multi-concept networks based on user's web usage data | |
CN106156351B (en) | Multimedia resource recommendation information generation method and device | |
CN110209908A (en) | Application recommended method, device, computer equipment and computer storage medium based on user interest portrait | |
JP6165812B2 (en) | Advertisement device, advertisement extraction method, advertisement extraction program, terminal device, and terminal control program | |
US20150154683A1 (en) | Product search support server, product search support method, and product search support program |
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 |