CN101625687A - Group interest data acquisition method and device supporting self-adaptive service - Google Patents
Group interest data acquisition method and device supporting self-adaptive service Download PDFInfo
- Publication number
- CN101625687A CN101625687A CN200810150317A CN200810150317A CN101625687A CN 101625687 A CN101625687 A CN 101625687A CN 200810150317 A CN200810150317 A CN 200810150317A CN 200810150317 A CN200810150317 A CN 200810150317A CN 101625687 A CN101625687 A CN 101625687A
- Authority
- CN
- China
- Prior art keywords
- data
- interest
- row
- group
- individual
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a group interest data acquisition method and a device supporting self-adaptive service. The method is characterized by including the following steps: collecting the data relevant to an individual user and data relevant to a project, mapping the care weight value w of the project to an interest key word, aggregating the interest data of individuals to form an interest knowledge base of group members and processing the interest knowledge base of group members generated in the aggregating step to obtain the group interest data. The device for realizing the method comprises a collector, a converter, an aggregator, a processor and a memory. The method and the device provided by the invention are suitable for groups with a plurality of structures and composition, rapidly collect the individual interest data of group members and generate the group interest data by processing. And the method is simple for operation and effectively provides the support of the group interest data for the self-adaptive service.
Description
Technical field
The present invention relates to a kind of group interest data acquisition method and device of supporting the self-adaptation service, relate to a kind of data and support method and apparatus, relate in particular to a kind of group interest data acquisition method and device towards the self-adaptation service.
Background technology
Along with developing rapidly of the communication technology and electronic technology, computation schema by traditional with computing machine be middle mind-set focus be put on man shifts, new computation schema is emphasized the importance of user in information service more.The self-adaptation service can provide the service content that adapts to user's request according to user's environment of living in or user interest hobby; Therefore, in the self-adaptation service, the interesting data that obtains the user just becomes the prerequisite that the self-adaptation service is provided, and also is one of core of self-adaptation Service Management.The user is divided into individual consumer and the user of colony, in many environment such as meeting room and museum, is used for day by day occurring with the form of group; Therefore, how providing towards the user's of colony self-adaptation service just to become more and more important, how to obtain the group interest data effectively, is the significant data support of colony being carried out the self-adaptation service.
Patented claim 200680002784.5 relates to a kind of method and device that obtains a customer group common interest-degree at it, its technological means mainly is according to compromise index and the user weight of user to program content characteristics, adjust fancy grade, to obtain the common interest-degree of customer group to program, by relatively this common interest-degree value and certain threshold level, whether decision recommends this program to customer group.
The described method of above-mentioned patent mainly is to treat programs recommended common interest-degree by calculating customer group, customer group to the value of this one dimension of common interest-degree of certain program as the factor of weighing the whole interest of customer group, do not obtain the whole interesting data of colony, and user's interesting data is key factor that need are considered in the self-adaptation service, and the description of group interest data should be a series of keyword of multidimensional.
Summary of the invention
The technical matters that solves
For fear of the deficiencies in the prior art part, the present invention proposes a kind of group interest data acquisition method and device of supporting the self-adaptation service, for the self-adaptation service provides quicker, more effective data support, the invention provides a kind of method and device, gather the individual interesting data of group member, obtain a cohort body interesting data through handling, and store for self-adaptation service use.
Technical scheme
A kind of group interest data acquisition method of supporting the self-adaptation service is characterized in that step is as follows:
Step 1 is gathered the data data relevant with project that the individual consumer is correlated with: the user obtains paying close attention to weight w=s+t/t to the evaluation of estimate s and the concern time t of browsing project on the collection individual consumer hand-held electronic devices
MaxThe value of s from 1 to 5, t and t
MaxUnit be second t
MaxIt is individual consumer's the longest current concern time;
Step 2 is mapped to the concern weight w of project on the interest keyword: overlapping if the interest keyword occurs, the mean value of then getting the concern weights obtains gathering the individual interesting data of formal description: { (keyword 1 as new concern weights, w1), (keyword 2, w2) ...; Described interest keyword is a characteristic key words of obtaining project that the user browses from project database;
The individual interesting data of step 3 polymerization forms group member interest knowledge base: with the set form of individual interesting data represent further abstract for vector representation be individual interesting data: (w1, w2, w3 ...); The individual interesting data of all members in the colony is integrated, form the group member interest knowledge base W of two-dimensional array; W can use matrix representation, and the element wij in the matrix represents the concern weights of i group member on j interest keyword;
The step 4 pair group member interest knowledge base that polymerization procedure produced is handled, and obtains the group interest data:
A) to each column element of matrix W,, then do not consider these row if exist the value of certain row element to be lower than 3.0 in these row; Otherwise, calculate all element value sums of going in these row, extract and be worth the subscripts of the highest 2 row;
B) each column element intermediate value of statistical matrix W is got the maximum row of number greater than 5.0 element number, if number surpasses the line number value half, then extracts this row subscript;
C) be lower than 3.0 element if in last step, contained value in the row of the subscript correspondence of extracting, be listed as under then from then on getting the mxm. element in the row at element place, occurred, then get inferior high value institute respective column subscript if this row subscript has gone on foot in the results last two;
D) the pairing interest keyword of row subscript result that 3 steps of front are produced joins in the group interest data.
A kind of device of realizing supporting the group interest data acquisition method of self-adaptation service is characterized in that comprising: collector, converter, polymerizer, processor and storer; Collector will be gathered the data data relevant with project that the individual consumer is correlated with and export converter to, converter is handled the data that collector obtains, and export the data of handling to polymerizer, the individual interesting data of polymerizer polymerization forms group member interest knowledge base, provide processor processing to obtain the group interest data this database, and be delivered to storer and store.
Beneficial effect
A kind of group interest data acquisition method and device of supporting the self-adaptation service proposed by the invention, it is the colony that is applicable to multiple structure and composition, gather the individual interesting data of group member apace, handle and generate colony's interesting data, and method is simple, and service provides the support of group interest data to self-adaptation effectively.
Description of drawings
Fig. 1: the structural representation of group interest data acquisition facility
Fig. 2: the method flow diagram that the group interest data are obtained
Embodiment
Now in conjunction with the embodiments, accompanying drawing is further described the present invention:
Fig. 1 is the structural representation of group interest data-acquisition system, mainly by collector, converter, polymerizer, processor, storer are formed, description is in order to provide the data support to colony's self-adaptation service, the transmission course of the how process that the user interest data are collected, handled and store, and data stream between each device.
110 is collector, and the function of two aspects is arranged: the one, and by gathering the data that the individual consumer is correlated with, promptly the user is to the evaluation of estimate and the concern time of concern project, and the user who obtains this project pays close attention to weights.The 2nd, from project database, obtain the characteristic key words of project, as individual consumer's interest keyword.
Wherein, the content characteristic of characteristic key words reflection project that the user browses for example for the showpiece in museum, can have characteristic key words such as type, age; For TV programme, characteristic key words such as literature and art, war, actor name can be arranged; And these characteristic key words can be used for reflecting user's interest place, and interest keyword of the present invention is used in reference to and substitutes family interest.
120 is converter, and its function is to receive after collector passes the interest keyword come, pays close attention to data such as weights, is responsible for paying close attention to weights to be mapped on the interest keyword, obtains gathering the individual interesting data of formal description.If overlapping phenomenon appears in the interest keyword, the mean value of then getting their concern weights is as new concern weights.
130 is polymerizer, and its function is the resulting individual interesting data of polymerization, finally forms group member interest knowledge base.Its operation was divided into for two steps, at first, the set form of individual interesting data was represented the further abstract vector representation that is; Then, the vector representation of the individual interesting data of all members in the colony is integrated, obtain group member interest knowledge base.
All group members of storage are to the concern weights of each interest keyword in the interest knowledge base of group member, and weights are big more, represent big more to the degree of concern of this interest keyword to the user, also promptly interested more.Its example sees Table 1, is applied as example with the museum, and wherein P1 refers to interest keyword pottery, jadeware etc. to P7, and P1 is user's concern weights to the value on the P7, and each row is represented a user's individual interesting data in the table.
140 is processor, and major function is that group member interest knowledge base is handled, and obtains the group interest data.
Wherein, the group interest data are meant the acceptable interest keyword of all members in the colony, have described the interest place of colony's integral body, specifically are one group of interest keywords.
150 is storer, and the data result that responsible storage of processor obtains is promptly stored the group interest data, to satisfy the data needs of colony's self-adaptation service.
Fig. 2 is the method flow diagram that the group interest data are obtained, and hereinafter in conjunction with application example and Fig. 2 the present invention is further elaborated.
The first step is gathered user-dependent data and is browsed the relevant data of project (step S210) with the user.User-dependent data owner will refer to evaluation of estimate, the concern time of user to the concern project, and the longest current concern time; The project related data refers to the characteristic key words of project, and browsing showpiece in the museum with the user is example, and the characteristic key words of showpiece has " pottery ", " jadeware ", " Song dynasty " etc.
In second step, calculate the concern weights (step S220) of user to project according to user related data.For example, evaluation of user value s is 4, and paying close attention to time t is 300 seconds, the longest current concern time t
MaxBe 600 seconds, calculate concern weight w=s+t/t of user
Max=4.5.
In the 3rd step,, combine with the interest keyword and obtain to gather the individual interesting data (step S230) of formal description with paying close attention to weights with the characteristic key words of project interest keyword as the user.If the overlapping phenomenon of interest keyword, the mean value of then getting their concern weights is as new concern weights.
Certain showpiece 1 of browsing in the museum with the user is an example, and its characteristic key words has a) pottery, b) Song dynasty.Then can be with the interest keyword of " pottery " " Song dynasty " two characteristic key words as the user.Suppose that the pairing concern weights of this showpiece are 4.5, obtain so individual interesting data (pottery, 4.5), and (Song dynasty, 4.5) ... }.If the showpiece 2 that have the user to browse this moment again, its characteristic key words has a) painting and calligraphy, and the b) Song dynasty, paying close attention to weights is 4.9.Occurred overlappingly on " Song dynasty " this keyword, got 4.5 and 4.9 evaluation of estimate 4.7 so as new concern weights.The individual interesting data that obtains after the processing for (pottery, 4.5), (Song dynasty, 4.7), (painting and calligraphy, 4.9) ... }.
In the 4th step, the set form of individual interesting data is represented the abstract vector representation (step S240) that is.In specific application, user's interest keyword is specific, and the interest keyword is in case fixing, just further abstract individuality interesting data.Be applied as example with top described museum, if the interest keyword is fixed as (pottery, jadeware, painting and calligraphy, Qin Han period, Song dynasty), so for the individual interesting data { (pottery, 5.1) of set formal description, (painting and calligraphy, 3.2), (jadeware, 2.0), (Qin Han period, 4.5), (Song dynasty, 3.8), just can describe and represent user interest (5.1,2.0 with vector form, 3.2,4.5,3.8).
In the 5th step, all members' individual interesting data forms group member interest knowledge base (step S250) in the comprehensive colony.An example of the interest knowledge base of group member sees Table 1, and wherein P1 refers to interest keyword pottery, jadeware etc. to P7, and P1 is user's concern weights to the value on the P7, and each row is represented a user's individual interesting data in the table.
The 6th step, group member interest knowledge base is handled, obtain group interest data (step S260).With table 1 is example, below describes this step in detail.This step can be realized by following 4 sub-steps again:
Table 1: group member interest knowledge base
1. each in the his-and-hers watches 1 row if contain value in these row less than 3.0 element, are then got rid of these row, remaining like this 3rd row, and the 4th row, the 5th row, the 7th row calculate the value sum of each row element in these 4 row, are respectively: 13.6,13.7,13.1,11.6.The highest two classify the 4th row and the 3rd row, extraction subscript 4 and subscript 3 as.
Result: subscript 4, subscript 3
2. add up each column mean greater than 5.0 element number, get the maximum row of number.Wherein containing 2 such elements (User1 is 5.2 to the concern weights of P6, and User2 is 5.3 to the concern weights of P6) in the 6th row, is the maximum row of number, and individual numerical value is greater than half of line number value, so take off mark 6.
Result: subscript 6
Contain value in the pairing row less than 3.0 element if 3. take off mark in the previous step,, get the pairing row of mxm. in this journey,, then get time corresponding subscript of high value in operating result if this row subscript had occurred at row under this element.Be in order to reduce immoderation/painful degree that low weights interest keyword brings for some group member in the previous step with high weight interest keyword, to reach a whole fair effect like this.The weights of User3 are 1.0 in the 6th row, and the maximum attention weights of User3 appear on the 1st row P1, are 5.4, and subscript 1 do not occur in result as yet, therefore take off mark 1.
Result: subscript 1
The pairing interest keyword of row subscript result that 4. will produce, i.e. P4, P3, P6, P1 joins in the group interest data.
The 7th step, storage group interest data (step S270).The data that storage S260 obtains, promptly (P6 P1) stores for P4, P3, to satisfy the data needs of colony's self-adaptation service to the group interest data.
This method has following characteristics in actual applications:
At first, structure and the quantity to group member does not strictly limit.
Secondly, method is simple, can obtain quickly and easily the individual interesting data of group member, and melt Close processing and then obtain group interest, effectively Data support is carried out in colony's self adaptation service.
Claims (2)
1. group interest data acquisition method of supporting self-adaptation service is characterized in that step is as follows:
Step 1 is gathered the data data relevant with project that the individual consumer is correlated with: the user obtains paying close attention to weight w=s+t/t to the evaluation of estimate s and the concern time t of browsing project on the collection individual consumer hand-held electronic devices
MaxThe value of s from 1 to 5, t and t
MaxUnit be second t
MaxIt is individual consumer's the longest current concern time;
Step 2 is mapped to the concern weight w of project on the interest keyword: overlapping if the interest keyword occurs, the mean value of then getting the concern weights obtains gathering the individual interesting data of formal description: { (keyword 1 as new concern weights, w1), (keyword 2, w2) ...; Described interest keyword is a characteristic key words of obtaining project that the user browses from project database;
The individual interesting data of step 3 polymerization forms group member interest knowledge base: with the set form of individual interesting data represent further abstract for vector representation be individual interesting data: (w1, w2, w3 ...); The individual interesting data of all members in the colony is integrated, form the group member interest knowledge base W of two-dimensional array; W can use matrix representation, and the element wij in the matrix represents the concern weights of i group member on j interest keyword;
The step 4 pair group member interest knowledge base that polymerization procedure produced is handled, and obtains the group interest data:
A) to each column element of matrix W,, then do not consider these row if exist the value of certain row element to be lower than 3.0 in these row; Otherwise, calculate all element value sums of going in these row, extract and be worth the subscripts of the highest 2 row;
B) each column element intermediate value of statistical matrix W is got the maximum row of number greater than 5.0 element number, if number surpasses the line number value half, then extracts this row subscript;
C) be lower than 3.0 element if in last step, contained value in the row of the subscript correspondence of extracting, be listed as under then from then on getting the mxm. element in the row at element place, occurred, then get inferior high value institute respective column subscript if this row subscript has gone on foot in the results last two;
D) the pairing interest keyword of row subscript result that 3 steps of front are produced joins in the group interest data.
2. a device of realizing the group interest data acquisition method of the described support self-adaptation service of claim 1 is characterized in that comprising: collector, converter, polymerizer, processor and storer; Collector will be gathered the data data relevant with project that the individual consumer is correlated with and export converter to, converter is handled the data that collector obtains, and export the data of handling to polymerizer, the individual interesting data of polymerizer polymerization forms group member interest knowledge base, provide processor processing to obtain the group interest data this database, and be delivered to storer and store.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810150317A CN101625687A (en) | 2008-07-11 | 2008-07-11 | Group interest data acquisition method and device supporting self-adaptive service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810150317A CN101625687A (en) | 2008-07-11 | 2008-07-11 | Group interest data acquisition method and device supporting self-adaptive service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101625687A true CN101625687A (en) | 2010-01-13 |
Family
ID=41521538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810150317A Pending CN101625687A (en) | 2008-07-11 | 2008-07-11 | Group interest data acquisition method and device supporting self-adaptive service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101625687A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102779154A (en) * | 2012-05-25 | 2012-11-14 | 上海斐讯数据通信技术有限公司 | Database, establishing method of database and data search method |
| CN107203515A (en) * | 2016-03-15 | 2017-09-26 | 北京京东尚科信息技术有限公司 | Topic generation method and device |
| CN113239185A (en) * | 2021-07-13 | 2021-08-10 | 深圳市创能亿科科技开发有限公司 | Method and device for making teaching courseware and computer readable storage medium |
-
2008
- 2008-07-11 CN CN200810150317A patent/CN101625687A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102779154A (en) * | 2012-05-25 | 2012-11-14 | 上海斐讯数据通信技术有限公司 | Database, establishing method of database and data search method |
| CN107203515A (en) * | 2016-03-15 | 2017-09-26 | 北京京东尚科信息技术有限公司 | Topic generation method and device |
| CN113239185A (en) * | 2021-07-13 | 2021-08-10 | 深圳市创能亿科科技开发有限公司 | Method and device for making teaching courseware and computer readable storage medium |
| CN113239185B (en) * | 2021-07-13 | 2021-10-29 | 深圳市创能亿科科技开发有限公司 | Method and device for making teaching courseware and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103886090B (en) | Content recommendation method and device based on user preferences | |
| CN102663626B (en) | Based on the collaborative filtering recommending method of provincial characteristics | |
| CN102426610B (en) | Microblog rank searching method and microblog searching engine | |
| CN108885627A (en) | Inquiry, that is, service system of query result data is provided to Terminal Server Client | |
| CN104281718B (en) | A kind of method that intelligent recommendation is excavated based on user group's behavioral data | |
| CN107193967A (en) | A kind of multi-source heterogeneous industry field big data handles full link solution | |
| CN102999507B (en) | The recommendation process method and apparatus of network microblog famous person's information | |
| CN111708740A (en) | Mass search query log calculation analysis system based on cloud platform | |
| CN107066476A (en) | A kind of real-time recommendation method based on article similarity | |
| CN110489590A (en) | For the viewing time cluster of video search | |
| CN101572629A (en) | Method and device for processing IP data | |
| CN112307329A (en) | Resource recommendation method and device, equipment and storage medium | |
| CN106446189A (en) | Message-recommending method and system | |
| JP2011154467A (en) | Retrieval result ranking method and system | |
| CN102890725A (en) | Result ranking method for search engine | |
| CN111177559A (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
| CN106156230A (en) | A kind of method and device generating interior chain | |
| CN109635192A (en) | Magnanimity information temperature seniority among brothers and sisters update method and platform towards micro services | |
| CN104992352A (en) | Individualized resource retrieval method | |
| CN102930052A (en) | Interest resource recommendation method based on multi-dimensional attribute attention | |
| CN101625687A (en) | Group interest data acquisition method and device supporting self-adaptive service | |
| CN102521413B (en) | Data reading device based on network reports and method | |
| CN102231158B (en) | Data set recommendation method and system | |
| CN109640128A (en) | A kind of TV user watching behavior feature extracting method and system | |
| CN105608158A (en) | Method and apparatus for displaying picture in waterfall flow manner |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20100113 |