CN108647312A - A kind of user preference analysis method and its device - Google Patents
A kind of user preference analysis method and its device Download PDFInfo
- Publication number
- CN108647312A CN108647312A CN201810441397.6A CN201810441397A CN108647312A CN 108647312 A CN108647312 A CN 108647312A CN 201810441397 A CN201810441397 A CN 201810441397A CN 108647312 A CN108647312 A CN 108647312A
- Authority
- CN
- China
- Prior art keywords
- user
- preference
- product
- information
- case
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The problem of disclosure is for the individual demand information push for going out the user according to the preference analysis of user is lacked in the prior art,A kind of user preference analysis method and its device are provided,Extract the Feature Words of product and case information,User's history data are acquired by journal file and database,Non-real user data in filtering user's history data obtains filtered user's history data and calculates the preference of integral product and case,Preference information is obtained according to preference matching product and the Feature Words of case,The preference information excavated in record to user is accessed from user's history,And relevant product information is recommended to user according to preference information,Save the time that user obtains useful products information,Personalized product recommendation service is come into being,Personalized product recommendation service can carry out corresponding user behavior preference analysis according to user behavior data first.
Description
Technical field
This disclosure relates to computer network data technical field, more particularly to a kind of user preference analysis method and its dress
It sets.
Background technology
Recommended products information is provided the user with for efficient high-speed, accesses in record and is excavated to user's from user's history
Preference information, and relevant product information is recommended to user according to preference information, the time that user obtains useful products information is saved,
Personalized product recommendation service is come into being, and personalized product recommendation service can carry out corresponding according to user behavior data first
User behavior preference analysis, common method is to establish a user preferences modeling by user behavior analysis, by the row of user
To be converted to the preference of user.The disclosure is in information search engine, electric business platform etc., needle mostly to the modeling of user behavior preference
To user information search keyword, record, visiting frequency, search information are accessed, access log, evaluation information etc. carry out inclined
Good analysis can not go out the individual demand information push of the user according to the preference analysis of user.
Invention content
The purpose of the disclosure is to be directed to lack the personalized need for going out the user according to the preference analysis of user in the prior art
The problem of asking information to push provides a kind of user preference analysis method and its device, a kind of user preference analysis method tool
Body includes the following steps:
Step 1, the Feature Words of product and case information are extracted;
Step 2, user's history data are acquired by journal file and database;
Step 3, the non-real user data filtered in user's history data obtains filtered user's history data;
Step 4, the preference of integral product and case is calculated using filtered user's history data;
Step 5, preference information is obtained according to preference matching product and the Feature Words of case;
Step 6, the preference information of user is pushed to user;
Wherein, user's history data include at least user to the access times of product and case information, product type, main brick
Colour system, decoration style, shops's reception history, vertical/mobile service platform access history, user service system behavior record, building
Disk, house type preference.
Further, in step 1, the method for the Feature Words of the extraction product and case information includes following sub-step
Suddenly:
Step 1.1, the product and the text of case are segmented, obtains classificating word;
Step 1.2, all classificating words are traversed and count each classificating word number;
Step 1.3, it chooses classificating word number and is greater than or equal to the classificating word of frequency threshold value as Feature Words;
Wherein, frequency threshold value is 5 times.
Further, in step 2, the method for the acquisition user's history data includes following sub-step:
Step 2.1, user's access critical word in journal file is acquired;
Step 2.2, user's access type record in SQL database is read;
Step 2.3, merge user's access critical word and user accesses record and obtains user's history data.
Wherein, user's access type record includes product type, main brick colour system, decoration style, shops's reception history, hangs down
Directly/mobile service platform accesses history, user service system behavior record, building, house type preference.
Further, in step 3, the non-real user data includes that nonregistered user accesses data, casual user
Data and canceled user data.
Further, in step 4, the method for the preference for calculating integral product and case is:
Wherein weight is the shared proportion of journal file and database, daily record text
The user's history data of part acquisition are 5, and the user's history data of database acquisition are 10, and access type is product type, main brick
Colour system, decoration style, shops's reception history, vertical/mobile service platform access history, user service system behavior record, building
Disk, house type preference.
Further, in steps of 5, described that preference information side is obtained according to preference matching product and the Feature Words of case
Method is:
Step 5.1, class threshold is arranged to the access times of product and case information according to Feature Words and user;
Step 5.2, the product corresponding to characteristic value is read when preference is more than or equal to class threshold with case preference to believe
Breath;
Wherein, class threshold is user to access times/weighted value of product and case information, and wherein weight is daily record text
The user's history data of the shared proportion of part and database, journal file acquisition are 5, the user's history data of database acquisition
It is 10.
The present invention also provides a kind of user preference analytical equipment, described device includes:
Feature Words extraction unit, the Feature Words for extracting product and case information;
Historical data collecting unit, for acquiring user's history data by journal file and database;
Historical data filter element, the non-real user data for filtering in user's history data obtain filtered use
Family historical data;
Preference computing unit, the preference for calculating integral product and case using filtered user's history data
Degree;
Preference information acquiring unit, for obtaining preference information according to preference matching product and the Feature Words of case;
Preference information push unit, the preference information for pushing user to user.
The disclosure has the beneficial effect that:The disclosure passes through user's search, browsing, collection product and case for single user
Data and the preference Value Data of integral product and case calculate preference value of each user to product and case, then in conjunction with
Individual subscriber essential information judges push, can accurately push the Related product of user preference to user, being capable of efficient high-speed
Provide the user with recommended products information.
Description of the drawings
By the way that the embodiment in conjunction with shown by attached drawing is described in detail, above-mentioned and other features of the disclosure will
More obvious, identical reference label indicates same or analogous element in disclosure attached drawing, it should be apparent that, in being described below
Attached drawing be only some embodiments of the present disclosure, for those of ordinary skill in the art, do not making the creative labor
Under the premise of, other drawings may also be obtained based on these drawings, in the accompanying drawings:
Fig. 1 show a kind of user preference analysis method work flow diagram of the disclosure;
Fig. 2 show a kind of user preference analytical equipment module rack composition of the disclosure.
Specific implementation mode
The technique effect of the design of the disclosure, concrete structure and generation is carried out below with reference to embodiment and attached drawing clear
Chu, complete description, to be completely understood by the purpose, scheme and effect of the disclosure.It should be noted that the case where not conflicting
Under, the features in the embodiments and the embodiments of the present application can be combined with each other.
As shown in Figure 1 according to a kind of user preference analysis method and its device work flow diagram of the disclosure, to tie below
Fig. 1 is closed to illustrate the user preference analysis method according to the disclosure.
The disclosure proposes a kind of user preference analysis method, specifically includes following steps:
Step 1, the Feature Words of product and case information are extracted;
Step 2, user's history data are acquired by journal file and database;
Step 3, the non-real user data filtered in user's history data obtains filtered user's history data;
Step 4, the preference of integral product and case is calculated using filtered user's history data;
Step 5, preference information is obtained according to preference matching product and the Feature Words of case;
Step 6, the preference information of user is pushed to user;
Wherein, user's history data include at least user to the access times of product and case information, product type, main brick
Colour system, decoration style, shops's reception history, vertical/mobile service platform access history, user service system behavior record, building
Disk, house type preference.
Further, in step 1, the method for the Feature Words of the extraction product and case information includes following sub-step
Suddenly:
Step 1.1, the product and the text of case are segmented, obtains classificating word;
Step 1.2, all classificating words are traversed and count each classificating word number;
Step 1.3, it chooses classificating word number and is greater than or equal to the classificating word of frequency threshold value as Feature Words;
Wherein, frequency threshold value is 5 times.
Wherein, text segmenting method is to assume that the most long word in dictionary for word segmentation has i chinese character, then with by processing document
Current word string in preceding i word as matching field, search dictionary.If being matched there are such a i words in dictionary
Success, matching field are come out as a word segmentation.If can not find such a i words in dictionary, it fails to match,
The last character in matching field is removed, matching treatment is re-started to remaining word string ... and so gone on, directly
To successful match, that is, until the length that is syncopated as a word or remaining word string is zero.This completes a wheel matchings, then take
Next i words word string carries out matching treatment, until document has been scanned.
Text segmentation methods are described as follows:
S1:Take m character of Chinese sentence to be slit as matching field from left to right, m is most long word in big machine dictionary
Number.
S2:It searches big machine dictionary and is matched.If successful match, using this matching field as a word segmentation
Out.If matching is unsuccessful, the last character of this matching field is removed, remaining character string is as new matching word
Section, is matched again, above procedure is repeated, until being syncopated as all words.
Further, in step 2, the method for the acquisition user's history data includes following sub-step:
Step 2.1, user's access critical word in journal file is acquired;
Step 2.2, user's access type record in SQL database is read;
Step 2.3, merge user's access critical word and user accesses record and obtains user's history data;
Wherein, user's access type record includes product type, main brick colour system, decoration style, shops's reception history, hangs down
Directly/move
Dynamic service platform accesses history, user service system behavior record, building, house type preference.
Wherein, user's access critical word of journal file is acquired, can be performed, be executed such as after data harvesting request is requested
Lower step:
(1) information is acquired by javascript objects built in browser, as webpage t itle (passes through
Document.title), referrer (upper hop url, pass through document.referrer), user display resolution ratio are (logical
Cross windows.screen), user's access critical word of cookie information (passing through document.cookie) etc..
(2) parsing _ gaq acquisition configuration information.Here include user-defined event tracking, business datum (such as electricity
The goods number etc. of sub- business web site) etc. users' access critical word.
(3) user data that two steps above acquire is parsed and is spliced by predefined format.
Further, in step 3, non-real user data includes that nonregistered user accesses data, casual user's data
With canceled user data.
Further, in step 4, the method for the preference for calculating integral product and case is:
Wherein weight is the shared proportion of journal file and database, daily record text
The user's history data of part acquisition are 5, and the user's history data of database acquisition are 10, and access type is product type, main brick
Colour system, decoration style, shops's reception history, vertical/mobile service platform access history, user service system behavior record, building
Disk, house type preference.
Further, in steps of 5, described that preference information side is obtained according to preference matching product and the Feature Words of case
Method is:
Step 5.1, class threshold is arranged to the access times of product and case information according to Feature Words and user;
Step 5.2, the product corresponding to characteristic value is read when preference is more than or equal to class threshold with case preference to believe
Breath;
Wherein, class threshold is user to access times/weighted value of product and case information, and wherein weight is daily record text
The user's history data of the shared proportion of part and database, journal file acquisition are 5, the user's history data of database acquisition
It is 10.
The present invention also provides a kind of user preference analytical equipments, as shown in Fig. 2, described device includes:
Feature Words extraction unit, the Feature Words for extracting product and case information;
Historical data collecting unit, for acquiring user's history data by journal file and database;
Historical data filter element, the non-real user data for filtering in user's history data obtain filtered use
Family historical data;
Preference computing unit, the preference for calculating integral product and case using filtered user's history data
Degree;
Preference information acquiring unit, for obtaining preference information according to preference matching product and the Feature Words of case;
Preference information push unit, the preference information for pushing user to user.
A kind of user preference analytical equipment can run on desktop PC, notebook, palm PC and high in the clouds
In the computing devices such as server.The device that a kind of user preference analytical equipment can be run may include, but be not limited only to, processing
Device, memory.It will be understood by those skilled in the art that the example is only a kind of example of user preference analytical equipment, and
It does not constitute to a kind of restriction of user preference analytical equipment, may include component more more or fewer than example, or combine certain
A little components or different components, such as a kind of user preference analytical equipment can also include input-output equipment, network
Access device, bus etc..Alleged processor can be central processing unit (Central Processing Unit, CPU), also
Can be other general processors, digital signal processor (Digital Signal Processor, DSP), special integrated electricity
Road (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng the processor is a kind of control centre of user preference analytical equipment running gear, utilizes various interfaces and circuit
A kind of entire user preference analytical equipment of connection can running gear various pieces.
The memory can be used for storing the computer program and/or module, and the processor is by running or executing
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
A kind of various functions of user preference analytical equipment.The memory can include mainly storing program area and storage data field,
In, storing program area can storage program area, application program (such as sound-playing function, image needed at least one function
Playing function etc.) etc.;Storage data field can be stored uses created data (such as audio data, phone directory according to mobile phone
Deng) etc..In addition, memory may include high-speed random access memory, can also include nonvolatile memory, such as firmly
Disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital,
SD) block, flash card (Flash Card), at least one disk memory, flush memory device or other volatile solid-states
Part.
Although the description of the disclosure is quite detailed and especially several embodiments are described, it is not
Any of these details or embodiment or any specific embodiments are intended to be limited to, but it is by reference to appended that should be considered as
Claim considers that the prior art provides the possibility explanation of broad sense for these claims, to effectively cover the disclosure
Preset range.In addition, the disclosure is described with inventor's foreseeable embodiment above, its purpose is to be provided with
Description, and those equivalent modifications that the disclosure can be still represented to the unsubstantiality change of the disclosure still unforeseen at present.
Claims (7)
1. a kind of user preference analysis method, which is characterized in that the method includes:
Step 1, the Feature Words of product and case information are extracted;
Step 2, user's history data are acquired by journal file and database;
Step 3, the non-real user data filtered in user's history data obtains filtered user's history data;
Step 4, the preference of integral product and case is calculated using filtered user's history data;
Step 5, preference information is obtained according to preference matching product and the Feature Words of case;
Step 6, the preference information of user is pushed to user;
Wherein, user's history data include at least user to the access times of product and case information, product type.
2. a kind of user preference analysis method according to claim 1, which is characterized in that in step 1, the extraction production
The method of the Feature Words of product and case information includes following sub-step:
Step 1.1, the product and the text of case are segmented, obtains classificating word;
Step 1.2, all classificating words are traversed and count each classificating word number;
Step 1.3, it chooses classificating word number and is greater than or equal to the classificating word of frequency threshold value as Feature Words;
Wherein, frequency threshold value is 5 times.
3. a kind of user preference analysis method according to claim 1, which is characterized in that in step 2, the acquisition is used
The method of family historical data includes following sub-step:
Step 2.1, user's access critical word in journal file is acquired;
Step 2.2, user's access type record in SQL database is read;
Step 2.3, merge user's access critical word and user accesses record and obtains user's history data.
4. a kind of user preference analysis method according to claim 1, which is characterized in that in step 3, non-real user
Data include that nonregistered user accesses data, casual user's data and canceled user data.
5. a kind of user preference analysis method according to claim 1, which is characterized in that in step 4, described to calculate
The method of the preference of integral product and case is:Wherein weight is journal file
User's history data with the shared proportion of database, journal file acquisition are 5, and the user's history data of database acquisition are
10。
6. a kind of user preference analysis method according to claim 1, which is characterized in that in steps of 5, the basis is inclined
Degree matching product and the Feature Words of case acquisition preference information method are well:
Step 5.1, class threshold is arranged to the access times of product and case information according to Feature Words and user;
Step 5.2, the product and case preference information corresponding to characteristic value are read when preference is more than or equal to class threshold;
Wherein, class threshold is user to access times/weighted value of product and case information, wherein weight be journal file and
The user's history data of the shared proportion of database, journal file acquisition are 5, and the user's history data of database acquisition are
10。
7. a kind of user preference analytical equipment, which is characterized in that described device includes:
Feature Words extraction unit, the Feature Words for extracting product and case information;
Historical data collecting unit, for acquiring user's history data by journal file and database;
Historical data filter element, the non-real user data for filtering in user's history data obtain filtered user and go through
History data;
Preference computing unit, the preference for calculating integral product and case using filtered user's history data;
Preference information acquiring unit, for obtaining preference information according to preference matching product and the Feature Words of case;
Preference information push unit, the preference information for pushing user to user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810441397.6A CN108647312A (en) | 2018-05-10 | 2018-05-10 | A kind of user preference analysis method and its device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810441397.6A CN108647312A (en) | 2018-05-10 | 2018-05-10 | A kind of user preference analysis method and its device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108647312A true CN108647312A (en) | 2018-10-12 |
Family
ID=63754081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810441397.6A Pending CN108647312A (en) | 2018-05-10 | 2018-05-10 | A kind of user preference analysis method and its device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108647312A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112328644A (en) * | 2020-10-12 | 2021-02-05 | 联通智网科技有限公司 | Application preference degree generation method and device, storage medium and computer equipment |
CN112348594A (en) * | 2020-11-25 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method, device, computing equipment and medium for processing article demands |
CN113378056A (en) * | 2021-06-28 | 2021-09-10 | 特赞(上海)信息科技有限公司 | Data processing method and device for acquiring creative case |
CN113672088A (en) * | 2021-08-11 | 2021-11-19 | 岳阳天赋文化旅游有限公司 | Interaction system and method based on wearable device |
CN114218493A (en) * | 2021-12-23 | 2022-03-22 | 淄博云科互联网信息技术有限公司 | Cloud service big data mining method based on artificial intelligence and cloud computing system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102831199A (en) * | 2012-08-07 | 2012-12-19 | 北京奇虎科技有限公司 | Method and device for establishing interest model |
CN103577478A (en) * | 2012-08-06 | 2014-02-12 | 腾讯科技(深圳)有限公司 | Web page pushing method and system |
CN104217031A (en) * | 2014-09-28 | 2014-12-17 | 北京奇虎科技有限公司 | Method and device for classifying users according to search log data of server |
CN107016026A (en) * | 2016-11-11 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of user tag determination, information-pushing method and equipment |
-
2018
- 2018-05-10 CN CN201810441397.6A patent/CN108647312A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103577478A (en) * | 2012-08-06 | 2014-02-12 | 腾讯科技(深圳)有限公司 | Web page pushing method and system |
CN102831199A (en) * | 2012-08-07 | 2012-12-19 | 北京奇虎科技有限公司 | Method and device for establishing interest model |
CN104217031A (en) * | 2014-09-28 | 2014-12-17 | 北京奇虎科技有限公司 | Method and device for classifying users according to search log data of server |
CN107016026A (en) * | 2016-11-11 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of user tag determination, information-pushing method and equipment |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112328644A (en) * | 2020-10-12 | 2021-02-05 | 联通智网科技有限公司 | Application preference degree generation method and device, storage medium and computer equipment |
CN112348594A (en) * | 2020-11-25 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method, device, computing equipment and medium for processing article demands |
CN113378056A (en) * | 2021-06-28 | 2021-09-10 | 特赞(上海)信息科技有限公司 | Data processing method and device for acquiring creative case |
CN113378056B (en) * | 2021-06-28 | 2023-09-26 | 特赞(上海)信息科技有限公司 | Data processing method and device for acquiring creative cases |
CN113672088A (en) * | 2021-08-11 | 2021-11-19 | 岳阳天赋文化旅游有限公司 | Interaction system and method based on wearable device |
CN114218493A (en) * | 2021-12-23 | 2022-03-22 | 淄博云科互联网信息技术有限公司 | Cloud service big data mining method based on artificial intelligence and cloud computing system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108647312A (en) | A kind of user preference analysis method and its device | |
US9448999B2 (en) | Method and device to detect similar documents | |
US10572565B2 (en) | User behavior models based on source domain | |
Cai et al. | Extracting content structure for web pages based on visual representation | |
WO2019041521A1 (en) | Apparatus and method for extracting user keyword, and computer-readable storage medium | |
CN101950312B (en) | Method for analyzing webpage content of internet | |
CN106383887A (en) | Environment-friendly news data acquisition and recommendation display method and system | |
CN105279277A (en) | Knowledge data processing method and device | |
CN111460153A (en) | Hot topic extraction method and device, terminal device and storage medium | |
CN106980651B (en) | Crawling seed list updating method and device based on knowledge graph | |
CN105095209B (en) | Document clustering method and device, the network equipment | |
CN106294815B (en) | A kind of clustering method and device of URL | |
CN104090904A (en) | Method and equipment for providing target search result | |
CN101188521B (en) | A method for digging user behavior data and website server | |
Alassi et al. | Effectiveness of template detection on noise reduction and websites summarization | |
WO2012006828A1 (en) | Method and device for presenting web pages | |
CN110377796A (en) | Text extracting method, device, equipment and storage medium based on dom tree | |
CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
WO2023040530A1 (en) | Webpage content traceability method, knowledge graph construction method and related device | |
CN104123321B (en) | A kind of determining method and device for recommending picture | |
CN105204806A (en) | Individual display method and device for mobile terminal webpage | |
CN103745383A (en) | Method and system of realizing redirection service based on operator data | |
CN107735785B (en) | Automatic information retrieval | |
CN108875050B (en) | Text-oriented digital evidence-obtaining analysis method and device and computer readable medium | |
CN106202312A (en) | A kind of interest point search method for mobile Internet and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |
|
RJ01 | Rejection of invention patent application after publication |