CN106372128A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN106372128A CN106372128A CN201610716251.9A CN201610716251A CN106372128A CN 106372128 A CN106372128 A CN 106372128A CN 201610716251 A CN201610716251 A CN 201610716251A CN 106372128 A CN106372128 A CN 106372128A
- Authority
- CN
- China
- Prior art keywords
- user
- default
- record
- classification
- field
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000001105 regulatory effect Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data processing method and a device, wherein the method comprises the following steps: acquiring an access record of a user i in a target website; according to the aboveAccessing records to determine a domain interest value E of the user i to a preset domain AiAAnd a classification attention value P of a preset classification j in the preset field Aij(ii) a According to the formula Wij＝αEiAPijObtaining the preference value W of the user i to the preset classification jijα is an adjustment factor, wherein the α is determined by the total number N of the users visiting the target website and the attribute dimension M of the category j, the scheme realizes the direct and efficient determination of the preference degree of the users to a specific category in a certain field, and further can provide reasonable and effective reference data for the decision maker in the field.
Description
Technical field
The present embodiments relate to data processing technique, more particularly, to a kind of data processing method and device.
Background technology
Data mining obtains tremendous development in recent years as the major technique of analysis user behavior.Data mining refers generally to
It is hidden in the process of wherein information by algorithm search from substantial amounts of data.It is generally associated with computer science, and lead to
Cross all multi-methods such as statistics, Data Environments, information retrieval, machine learning, specialist system and pattern recognition come to realize to
The analysis of family behavior.
Cannot directly, efficiently determine in existing data mining and processing method user under a certain field to specific
The preference of classification, and then reasonable, effective reference data cannot be provided for the policymaker in this field.
Content of the invention
The present invention provides a kind of data processing method and device, with realize direct, efficiently determine user in a certain neck
Preference to specific classification under domain, and then reasonable, effective reference data can be provided for the policymaker in this field.
In a first aspect, embodiments providing a kind of data processing method, comprising:
Obtain the access record in targeted website for the user i；
Concern value e in field to default field a for the described user i is determined according to the described record that accessesiaAnd to described default
Classification concern value p of the default classification j under a of fieldij；
According to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein α is to adjust
The factor, described α is determined by total amount n of the access user in described targeted website and attribute dimensions m of described classification j.
Second aspect, the embodiment of the present invention additionally provides a kind of data processing equipment, comprising:
Access record determining module, for obtaining the access record in targeted website for the user i；
According to the described record that accesses, concern value determining module, for determining that described user i pays close attention to the field of default field a
Value eiaAnd classification concern value p to the default classification j under described default field aij；
Preference value determining module, for according to formula wij=α eiapijObtain described user i inclined to described default classification j
Value w wellij, wherein α is regulatory factor, and described α is by access total amount n of user in described targeted website and the genus of described classification j
Property dimension m determine.
The present invention passes through to obtain the access record in targeted website for the user i；Described user i is determined according to the described record that accesses
Field concern value e to default field aiaAnd classification concern value p to the default classification j under described default field aij；According to
Formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein α be regulatory factor, described α by
Attribute dimensions m of access total amount n of user in described targeted website and described classification j determine it is achieved that directly, efficiently really
Make the preference to specific classification under a certain field for the user, and then can provide rationally, effectively for the policymaker in this field
Reference data.
Brief description
The flow chart of the data processing method that Fig. 1 provides for the embodiment of the present invention one；
Fig. 2 is the schematic diagram of the preference value of the user being determined according to the data processing method that embodiment one provides；
The flow chart of the data processing method that Fig. 3 provides for the embodiment of the present invention two；
The flow chart of the data processing method that Fig. 4 provides for the embodiment of the present invention three；
The structure chart of the data processing equipment that Fig. 5 provides for the embodiment of the present invention four.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure is illustrate only in description, accompanying drawing.
Embodiment one
The flow chart of the data processing method that Fig. 1 provides for the embodiment of the present invention one, the present embodiment is applicable to user
Online accesses the situation that record was analyzed and then determined user preference, and the method can be by computing device such as desktop computer, pen
Remember this computer to execute, specifically include following steps:
Step 101, the acquisition access record in targeted website for the user i.
Exemplary, this access record can be obtained by statistical tool, and targeted website refers to need to carry out user preference
The specific website of demand analyses.Exemplary, when the house-purchase Demand perference needing to analyze user, search the nets such as room net, the visitor that lives in peace
Stand and can be targeted website；When certain the class shopping need needing to analyze user, the website such as sky cat, Jingdone district can be confirmed as
Targeted website.The access record in targeted website for the user i is obtained, wherein user i is numerous access target website in this step
Any one in user.
Step 102, according to described access record determine concern value e in field to default field a for the described user iiaAnd to
Classification concern value p of the default classification j under described default field aij.
Wherein, this default field can be that house property buys field, furniture shopping area or sports goods field etc., presets neck
Domain a is any one in default field, exemplary, can be that house property buys field.
Optionally,Wherein, belong to default field in the access record for user i for the freq (i)
A access times,For belonging to default field a access times in the access record of n user, wherein n is target
The sum of the access user of website.
Exemplary, if default field a buys field for house property, this default classification j can be location, price and room
Type.
Optionally,Wherein, k represents the attribute in default classification j, exemplary, taking Shenzhen as a example,
Attribute in the classification of location can be Nanshan District, Baoan District and Futian District；Attribute in price category can be less than 4,000,000,
400 to 1,000 ten thousand and more than 10,000,000, the attribute in house type classification can be that a Room one Room, two Room one Room two are defended and three living rooms and one sitting room
Deng.By formulaCan determine that classification concern value p in default classification j for the userij.
Optionally,Wherein β
It is preferably 0.9, wherein freq (ijk) it is the access times to k-th attribute in default classification j for the user i.Pass through in the program to take
Logarithm improves to simple multiple proportion, it is to avoid the value occurring during normalization is the 0 follow-up preference value causing
Calculate and produce insignificant data in a large number.
Step 103, according to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij.
Wherein, α is regulatory factor, and described α is by access total amount n of user in described targeted website and described classification j
Attribute dimensions m determine.Exemplary, as it was previously stated, the attribute in the classification of location can be Nanshan District, Baoan District and Futian District,
Then the attribute dimensions of this location classification are 3.
Wherein α as regulatory factor, to avoid preference value w under data sample changesijOverall variation, optionally, α's
It is worth for 1 divided by desired meansigma methodss, that is,
It is exemplary that it is assumed that having the access record of 6 users, this 6 users are expressed as { u1, u2 ..., u6 },
It is assumed that default field a buys field for house property, the corresponding relation of the attribute k under default classification j and this default classification is as follows:
Access under this house property purchase field for the corresponding user getting records as shown in the table:
Fig. 2 is the schematic diagram of the preference value of the user being determined according to the data processing method that embodiment one provides.Wherein,
Each default following combination all including three attributes, being made up of the attribute chosen under wherein each default classification of classifying
Have 27 kinds.As shown in Fig. 2 the preference that wherein " { 1 } { 1 } { 1 } " represents is " { Nanshan District } { less than 4,000,000 } { Room one
The Room } ", the preference that " { 2 } { 1 } { 1 } " represents is " { Baoan District } { less than 4,000,000 } { Room one Room } ", where each row
The corresponding data of gauge outfit is respectively the preference value to the preference representated by this gauge outfit for 6 users.Under " { 1 } { 1 } { 1 } " preference value
The preference value of corresponding { u1, u2 ..., u6 } this 6 users is followed successively by " 0.1328 " " 3.9403 " " 6.4478 " " 1.9076 "
" 0.1099 " and " 0.0000 ".
The technical scheme of the present embodiment, carries out the entirety in default field and the office of default classification by user is accessed with record
The analysis in portion, and the introducing of regulatory factor rationally efficiently determines the preference journey to specific classification under a certain field for the user
Degree, and then reasonable, effective reference data can be provided for the policymaker in this field.
On the basis of technique scheme, obtained user i before the access record of targeted website, also include:
Attribute dimensions m accessing default classification j under described default field a for the record determination according to targeted website.Show
Example property, by carrying out classifying, counting attribute dimensions m obtaining default classification j to the record that accesses of all users.
Embodiment two
The flow chart of the data processing method that Fig. 3 provides for the embodiment of the present invention two, the present embodiment is in the base of embodiment one
On plinth, different classes of segmenting and distribute with different weights is carried out to the record that accesses of user, has specifically included:
Step 201, the acquisition access record in targeted website for the user i, parse to the access record of described user i,
Determine that the typing search access record accessing in record of described user i and non-typing search access and record, be that described typing is searched
Rope accesses record and described non-typing search accesses record and distributes default weights.
In this step, it is mainly in view of the active behavior of user and common behavior is portrayed importance and existed not to user's request
With it is considered that user's active behavior more embodies the demand of the current urgent need to resolve of user, therefore access record is parsed,
Access record for typing search and access the different default weights of record distribution with non-typing search, exemplary, typing is searched for
It can be 3 that access records corresponding preset weights, and it can be 1 that non-typing search access records corresponding weights.
Step 202, access record according to described typing search and described non-typing search accesses record and each self-corresponding
Weights determine concern value e in field to default field a for the described user iiaAnd to the default classification j's under described default field a
Classification concern value pij.
Exemplary, p in this stepijComputational methods beWherein, γkFor in default classification j
K-th attribute jkThe weights being endowed.
Step 203, according to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein
α is regulatory factor, and described α is determined by total amount n of the access user in described targeted website and attribute dimensions m of described classification j.
The technical scheme of the present embodiment, by parsing to access record, determines the typing search visit accessing in record
Ask that record and non-typing search access record, be that typing search accesses record and non-typing search accesses record and distributes default power
Value, so that the user preference value finally giving is more reasonable, more reflects the real demand of user.
Embodiment three
The flow chart that Fig. 4 show the data processing method of the embodiment of the present invention three offer, the present embodiment is in above-mentioned each reality
On the basis of applying example, the access record of user is carried out updating optimization, has specifically included:
Step 301, the acquisition access record in targeted website for the user i, and access note according to default more new formula to described
Record carries out real-time update.
Consider in this step to access the concept drift characteristic and ageing of record, accessing the knowledge containing in record will hold
Continue and change, the importance of knowledge is also constantly decayed simultaneously.It is thus desirable to Current transaction and history thing can be distinguished
Business, and constantly weaken the impact that historical transactions produce to Result.
Exemplary, for different default fields, different attenuation functions can be taken, by selecting different θ values to visit
Ask that record decay is controlled, generally, access with the resistance to user disappearing condition pass and record user's access note that the product that comparatively fast disappear are comprised
Record more longer analytical cycle.In this step, with attenuation function f (t)=2 under time attenuation model-θtDecayed, its
Middle θ > 0.Cut-off current time tc(as 10 points of August in 2016 4 days), is located at the time that in pattern p, different access record occurs
Collection is combined into timewP (), specific access records the corresponding time and is set to tj(when recording corresponding access as the 200th article of access
Between for 10 points of on May 5th, 2016, then t200The corresponding time is 10 points of on May 5th, 2016), corresponding complete attenuation supports numberAccordingly, number d (p, t are supported according to this complete attenuationc) the more new formula that obtains isIt is that the real time access record of each user is updated according to this formula.
Step 302, according to after real-time update access record determine the concern value in field to default field a for the described user i
eiaAnd classification concern value p to the default classification j under described default field aij.
Step 303, according to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein
α is regulatory factor, and described α is determined by total amount n of the access user in described targeted website and attribute dimensions m of described classification j.
The technical scheme of the present embodiment, carries out real-time update according to default more new formula to described access record, improves
User preference value calculate when ageing it is ensured that output preference value result more reasonable.
On the basis of the various embodiments described above, obtain preference value w to described default classification j for the described user iijAfterwards, also wrap
Include: determine the preference value to described default classification j for each user in described n user successively, and by described preference value by big
It is ranked up to little；Or determine the preference value to described default classification j for each user in described n user successively, and screen
Go out the user that described preference value is more than or equal to 1.Exemplary, when the number of users to screening is restricted, can be using successively
Determine the preference value to described default classification j for each user in described n user, and carry out descending for described preference value
Sequence, is screened according to clooating sequence；When not limiting the number of users of screening, can be used using determining described n successively
The preference value to described default classification j for each user in family, and filter out the user that described preference value is more than or equal to 1.We
In case, according to the preference value of each user determining, can intuitively, easily carry out user's screening, the policymaker for this field carries
For reasonable, effective reference data.
Example IV
The structural representation of the data processing equipment that Fig. 5 provides for the embodiment of the present invention four, specifically includes as described in Figure:
Access record determining module 1, for obtaining the access record in targeted website for the user i；
According to the described record that accesses, concern value determining module 2, for determining that described user i closes to the field of default field a
Note value eiaAnd classification concern value p to the default classification j under described default field aij；
Preference value determining module 3, for according to formula wij=α eiapijObtain described user i to described default classification j's
Preference value wij, wherein α is regulatory factor, and described α is by access total amount n of user in described targeted website and described classification j
Attribute dimensions m determine.
The technical scheme of the present embodiment, by obtaining the access record in targeted website for the user i；Access record according to described
Determine concern value e in field to default field a for the described user iiaAnd the classification to the default classification j under described default field a
Concern value pij；According to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein α is to adjust
The section factor, described α is determined by total amount n of the access user in described targeted website and attribute dimensions m of described classification j, realizes
Directly, efficiently determine the preference to specific classification under a certain field for the user, and then can be the decision-making in this field
Person provides reasonable, effective reference data.
On the basis of technique scheme, also include:
Attribute dimensions determining module, pre- under described default field a for being determined according to the access record of targeted website
If attribute dimensions m of classification j.
On the basis of technique scheme, also include:
Weights module, for parsing to the access record of described user i, determines in the access record of described user i
Typing search access record and non-typing search accesses record, be that described typing search accesses record and described non-typing search
Access record and distribute default weights；
Described concern value determining module 2 specifically for:
Record is accessed according to described typing search and described non-typing search accesses record and each self-corresponding weights determine
Concern value e in field to default field a for the described user iiaAnd the classification concern to the default classification j under described default field a
Value pij.
On the basis of technique scheme, described access record determining module 1 specifically for:
Obtain the access record in targeted website for the user i, and according to default more new formula, reality is carried out to described access record
Shi Gengxin:
Described concern value determining module 2 specifically for:
Concern value e in field to default field a for the described user i is determined according to the record that accesses after real-time updateiaAnd to
Classification concern value p of the default classification j under described default field aij.
On the basis of technique scheme, also include:
Screening module, for determining the preference value to described default classification j for each user in described n user successively,
And be ranked up descending for described preference value；Or
Determine the preference value to described default classification j for each user in described n user successively, and filter out described inclined
The user more than or equal to 1 for the good value.
Above-mentioned classification can perform the method that any embodiment of the present invention is provided, and possesses the corresponding functional module of execution method
And beneficial effect.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other Equivalent embodiments more can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of data processing method is it is characterised in that include:
Obtain the access record in targeted website for the user i；
Concern value e in field to default field a for the described user i is determined according to the described record that accessesiaAnd in described default field a
Under default classification j classification concern value pij；
According to formula wij=α eiapijObtain preference value w to described default classification j for the described user iij, wherein α is regulatory factor,
Described α is determined by total amount n of the access user in described targeted website and attribute dimensions m of described classification j.
2. method according to claim 1 is it is characterised in that obtained user i before the access record of targeted website, also
Including:
Attribute dimensions m accessing default classification j under described default field a for the record determination according to targeted website.
3. method according to claim 1, it is characterised in that obtaining user i after the access record of targeted website, is also wrapped
Include:
The access record of described user i is parsed, determines that the typing search accessing in record of described user i accesses record
Access record with non-typing search, be described typing search access record and described non-typing search to access record distribution default
Weights；
Concern value e in field to default field a for the described user i is determined according to the described record that accessesiaAnd in described default field a
Under default classification j classification concern value pijIncluding:
Access to record according to described typing search and access described in record and each self-corresponding weights determination with described non-typing search
Concern value e in field to default field a for the user iiaAnd the classification concern value to the default classification j under described default field a
pij.
4. method according to claim 1 includes it is characterised in that obtaining the access record in targeted website for the user i:
Obtain the access record in targeted website for the user i, and according to default more new formula, described access record is carried out in real time more
New:
Concern value e in field to default field a for the described user i is determined according to the described record that accessesiaAnd in described default field a
Under default classification j classification concern value pijIncluding:
Concern value e in field to default field a for the described user i is determined according to the record that accesses after real-time updateiaAnd to described
Classification concern value p of the default classification j under default field aij.
5. the method according to any one of claim 1-4 is it is characterised in that obtain described user i to described default classification j
Preference value wijAfterwards, also include:
Determine the preference value to described default classification j for each user in described n user successively, and by described preference value by big
It is ranked up to little；Or
Determine the preference value to described default classification j for each user in described n user successively, and filter out described preference value
User more than or equal to 1.
6. a kind of data processing equipment is it is characterised in that include:
Access record determining module, for obtaining the access record in targeted website for the user i；
Concern value determining module, for determining concern value e in field to default field a for the described user i according to the described record that accessesia
And classification concern value p to the default classification j under described default field aij；
Preference value determining module, for according to formula wij=α eiapijObtain the preference value to described default classification j for the described user i
wij, wherein α is regulatory factor, and described α is by access total amount n of user in described targeted website and the attribute dimension of described classification j
Degree m determines.
7. device according to claim 6 is it is characterised in that also include:
Attribute dimensions determining module, determines default point under described default field a for the record that accesses according to targeted website
Attribute dimensions m of class j.
8. device according to claim 6 is it is characterised in that also include:
Weights module, for parsing to the access record of described user i, determines the record accessing in record of described user i
Enter search access record and non-typing search accesses and records, be that described typing search accesses record and described non-typing is searched for and accessed
Record distributes default weights；
Described concern value determining module specifically for:
Access to record according to described typing search and access described in record and each self-corresponding weights determination with described non-typing search
Concern value e in field to default field a for the user iiaAnd the classification concern value to the default classification j under described default field a
pij.
9. device according to claim 6 it is characterised in that described access record determining module specifically for:
Obtain the access record in targeted website for the user i, and according to default more new formula, described access record is carried out in real time more
New:
Described concern value determining module specifically for:
Concern value e in field to default field a for the described user i is determined according to the record that accesses after real-time updateiaAnd to described
Classification concern value p of the default classification j under default field aij.
10. the device according to any one of claim 6-9 is it is characterised in that also include:
Screening module, for determining the preference value to described default classification j for each user in described n user successively, and will
Described preference value is descending to be ranked up；Or
Determine the preference value to described default classification j for each user in described n user successively, and filter out described preference value
User more than or equal to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610716251.9A CN106372128A (en) | 2016-08-24 | 2016-08-24 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610716251.9A CN106372128A (en) | 2016-08-24 | 2016-08-24 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106372128A true CN106372128A (en) | 2017-02-01 |
Family
ID=57878289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610716251.9A Pending CN106372128A (en) | 2016-08-24 | 2016-08-24 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372128A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
| CN104102648A (en) * | 2013-04-07 | 2014-10-15 | 腾讯科技（深圳）有限公司 | User behavior data based interest recommending method and device |
| CN105574159A (en) * | 2015-12-16 | 2016-05-11 | 浙江汉鼎宇佑金融服务有限公司 | Big data-based user portrayal establishing method and user portrayal management system |
| CN105653693A (en) * | 2015-12-30 | 2016-06-08 | 东软集团股份有限公司 | Individualization recommendation method and apparatus |
-
2016
- 2016-08-24 CN CN201610716251.9A patent/CN106372128A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
| CN104102648A (en) * | 2013-04-07 | 2014-10-15 | 腾讯科技（深圳）有限公司 | User behavior data based interest recommending method and device |
| CN105574159A (en) * | 2015-12-16 | 2016-05-11 | 浙江汉鼎宇佑金融服务有限公司 | Big data-based user portrayal establishing method and user portrayal management system |
| CN105653693A (en) * | 2015-12-30 | 2016-06-08 | 东软集团股份有限公司 | Individualization recommendation method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104090919B (en) | Advertisement recommending method and advertisement recommending server | |
| CN101364239B (en) | Method for auto constructing classified catalogue and relevant system | |
| US9858308B2 (en) | Real-time content recommendation system | |
| CN106339502A (en) | Modeling recommendation method based on user behavior data fragmentation cluster | |
| CN105989082B (en) | Tabular views generation method and device | |
| CN106682144A (en) | Page display method and device | |
| CN106056407A (en) | Online banking user portrait drawing method and equipment based on user behavior analysis | |
| CN106339393A (en) | Information push method and device | |
| CN106504099A (en) | A kind of system for building user's portrait | |
| CN104216881A (en) | Method and device for recommending individual labels | |
| CN104462385A (en) | Personalized movie similarity calculation method based on user interest model | |
| CN105302810A (en) | Information search method and apparatus | |
| CN107133362A (en) | Commodity Information Search method, system, computer program and electronic equipment | |
| CN102053983A (en) | Method, system and device for querying vertical search | |
| CN101346720A (en) | A method and data processing system for restructuring web content | |
| CN104050240A (en) | Method and device for determining categorical attribute of search query word | |
| CN104156356B (en) | Personalized Navigation page generation method and device | |
| CN103353880B (en) | A kind of utilization distinctiveness ratio cluster and the data digging method for associating | |
| CN1983255A (en) | Internet searching method | |
| CN111291191B (en) | Broadcast television knowledge graph construction method and device | |
| US10552996B2 (en) | Systems and techniques for determining associations between multiple types of data in large data sets | |
| CN105095281A (en) | Website classification catalogue optimization analysis method based on log mining | |
| CN111967914A (en) | User portrait based recommendation method and device, computer equipment and storage medium | |
| CN105930507A (en) | Method and apparatus for obtaining Web browsing interest of user | |
| CN107908616A (en) | The method and apparatus of anticipation trend word |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170201 |