CN103678652A - Information individualized recommendation method based on Web log data - Google Patents
Information individualized recommendation method based on Web log data Download PDFInfo
- Publication number
- CN103678652A CN103678652A CN201310717507.4A CN201310717507A CN103678652A CN 103678652 A CN103678652 A CN 103678652A CN 201310717507 A CN201310717507 A CN 201310717507A CN 103678652 A CN103678652 A CN 103678652A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- page
- users
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- 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
Abstract
The invention discloses an information individualized recommendation method based on Web log data, and belongs to the technical field of electronic information. The method is used for an information mode of a server plus a broadband network plus a multimedia thin client side. The method includes the steps that users have access to internet sources through the multimedia thin client side, and theserver records the behaviors of the users into server log files; clean, regular and accurate data sources are extracted through analysis and preprocessing of data of the Web log files in the server; a user interest matrix is built through a collaborative filtering technology, similarity between the users is calculated, and the users with large similarity are selected as similar users; a recommendation resource pool is built according to hobbies and interests of the similar users; the server selects and recommends pages of which the recommendation value is larger than the threshold value in the recommendation resource pool to the users. The method has the advantages that the data in the Web log files are preprocessed to acquire the clean and regular data sources, and accurate and individualized information recommendation is provided for the users by the cooperation of the hobbies and the interests of the similar users.
Description
Technical field
The present invention relates to a kind of information personalized recommend method based on Web daily record data, belong to electronic information technical field.
Background technology
Along with the fast development of internet, there is every day the webpage of magnanimity on Internet, upgrade or issue.For users, in a large amount of information, want that it has been more and more difficult finding the information oneself being satisfied with, thereby caused " information is excessive " contradictory phenomena with " information is hungry ".For addressing this problem, individual info service has been proposed, this is a kind of intelligent information service mode.Can initiatively search relevant information according to user's information requirement and personalized pattern, and utilize on-line intelligence recommendation service or push technology, accurately the required information of user is sent to corresponding user.In Personalized Service Technology, application is more successfully collaborative filtering method.The method refers to that user is according to the demand of self, by cooperating with other users, form certain cooperation rule, or the tendentiousness of utilizing a plurality of information users is predicted the interest of unique user, then according to the user with same interest hobby, information is evaluated, thereby obtained recommendation results.Owing to having recorded a large amount of user behavior information in Web daily record, utilize Web daily record to provide important Data support for personalized service.But original log record is mixed and disorderly, imperfect and non-structured, so need to carry out efficient pre-service to it.In addition, aspect user interest tolerance, the method that the access module that extracts user from access log file existing is at present recommended, do not consider the time response of user to access pages, and the interest level of user to certain page, the time length that can stop at this page according to user is weighed.If the patent No. of Tsing-Hua University's application is 103338223A, denomination of invention is that recommend method, client and the server > > that mono-kind of < < moves application belong to these row.On the basis of this problem, a kind of information personalized recommend method based on Web daily record data is proposed.First to the data analysis in journal file and pre-service, assurance extracts totally, rule, data source accurately, secondly, the time response of user to access pages is added to limit of consideration, in conjunction with the hobby of similar users, be reached for the object that user provides more accurate, personalized information recommendation.
Summary of the invention
The defect and the deficiency that for existing background technology, exist, the present invention proposes a kind of information personalized recommend method based on Web daily record data, be intended to solve the data source of extracting in traditional information recommendation method based on Web daily record data clean not, regular, and the problem existing aspect user interest tolerance.By this method, can provide more accurate, personalized information recommendation for user.
Technical scheme of the present invention is as follows:
An information personalized recommend method based on Web daily record data, step is as follows:
A, user be by the resource in multimedia thin-client accesses network, server by this behavior record of user in server log file;
B, data analysis and pre-service to Web journal file in server, exclude that visit capacity is few, under-represented user's Visitor Logs and middle blade-rotating be referred to as some data of junk data, convert the original semi-structured Web daily record data that is not easy to be understood by people to structurized data, for example, only comprise the url of User IP, access time, accession page, the tables of data of access bytes digital section extracts as meeting rule, data source accurately;
According to the content information of Web journal file, in tables of data, build corresponding field, then text data is imported in tables of data;
Data in tables of data are cleared up, by data nonsensical in user access information, these Visitor Logs of bmp, jpg as by name in suffix, jpeg, php, jsp and status code are not 200 to represent that the log recording of unsuccessful access deletes, and only retain the log recording of suffix HTML, HTM by name and XML; Wherein bmp represents bitmap, jpg and jpeg represent the slightly graphics file format of distortion compression, and php is supertext pre-service language, the script of the embedded html document of carrying out at server end, jsp represents embedded web page script, and HTML, HTM and XML are web page files;
The status code of Web journal file acquiescence represents to ask successfully with 2 beginnings, with 3 beginnings, represents that user asks to be redirected to other positions, with 4 beginnings, represents that client exists mistake, with 5 beginnings, represents that server end exists mistake;
According to user's IP, identify different users, the user who selects visit capacity to reach certain value carries out behavioural analysis;
According to user, in the residence time of whole website, carry out session identification, set a time threshold, if surpass this time threshold, think that new session starts;
From user conversation, find out significant accession page and access path, the link page that user is had to access for the page that achieves the goal in access process is that middle blade-rotating is deleted from session;
C, use collaborative filtering are set up user interest matrix, calculate the similarity between each user, select some users with larger similarity as similar users;
Yong Hu ?page matrix representation be R (M * N), matrix value Rm wherein, n represents the time of user M browsing pages N, Jiang Yong Hu ?page matrix R (M * N) be converted into Yong Hu ?resource class Matrix C (M * X), matrix value Cm wherein, x represents that user M browses the time of a certain resource class X, and Matrix C (M * X) is weighted to filtering data pre-service, obtain standardized resource, thereby form user interest matrix;
Adopt K ?means Data Cluster Algorithm user is carried out to cluster, user's similarity is chosen cosine similarity and is evaluated;
D, for the hobby of similar users, set up and recommend resource pool;
The interest-degree U of user i to page j
i,jcan be expressed as the product to the byte number of the ratio of all page browsing temporal summation and page j and all accession page byte number sum ratios in total residence time of page j and user i, that is:
Wherein: timei, j be user i in total residence time of page j, timei, k be user i to all page browsing temporal summation, sizei, j is the byte number of page j, sizei, k is all accession page byte number sums, k is natural number, m is all pages sums;
E, the threshold value at server place by threshold value assigning unit assigns recommendation, the web page recommendation that the recommendation in server selection recommendation resource pool is greater than assign thresholds is to user.
Described URL means URL(uniform resource locator), is the abbreviation of English Uniform Resource Locator, is the position of the resource to obtaining from internet and a kind of succinct expression of access method, is the address of standard resource on internet.Each file on internet has a unique URL, and the information that it comprises points out how the position of file and browser should process it.
Described weighting filtering data pre-service is to be carried out overall treatment and calculated prediction scoring by the average weighted scoring to matrix row and column, so just can make each user have score value to each accession page, thereby alleviate sparse property problem.Avoid the different user evaluation difference to accession page simultaneously, for normalization evaluation result, obtain standardized resource.
Described K ?means Data Cluster Algorithm is: initial random given K Ge Cu center, according to proximity principle, sample point to be sorted is assigned to each bunch.Then by the method for average, recalculate the barycenter of each bunch, thereby determine the new bunch heart.Iteration always, until the displacement of bunch heart is less than certain specified value.
Described cosine similarity uses the cosine value of two vector angles in vector space as the size of weighing two interindividual variations.Measuring similarity (Similarity), calculates the similarity degree between individuality, contrary with distance metric, and the value of measuring similarity is less, illustrates that between individuality, similarity is less, and difference is larger.Compare distance metric, cosine similarity is focused on the difference of two vectors in direction more, but not distance or length on difference.
The invention has the beneficial effects as follows by the data in Web journal file and carry out pre-service, through steps such as data-switching, data scrubbing, user's identification, session identifications, obtained cleaner, accurate, regular data source, and aspect user interest tolerance, the time response of user to access pages is added to limit of consideration, in conjunction with the hobby of similar users, for user provides more accurate, personalized information recommendation.
Embodiment
Below in conjunction with embodiment, the invention will be further described, but be not limited to this.
Embodiment:
An information personalized recommend method based on Web daily record data, step is as follows:
A, user be by the resource in multimedia thin-client accesses network, server by this behavior record of user in server log file;
B, data analysis and pre-service to Web journal file in server, exclude that visit capacity is few, under-represented user's Visitor Logs and middle blade-rotating be referred to as some data of junk data, convert the original semi-structured Web daily record data that is not easy to be understood by people to structurized data, for example, only comprise the url of User IP, access time, accession page, the tables of data of access bytes digital section extracts as meeting rule, data source accurately;
According to the content information of Web journal file, in tables of data, build corresponding field, then text data is imported in tables of data;
Data in tables of data are cleared up, by data nonsensical in user access information, these Visitor Logs of bmp, jpg as by name in suffix, jpeg, php, jsp and status code are not 200 to represent that the log recording of unsuccessful access deletes, and only retain the log recording of suffix HTML, HTM by name and XML; Wherein bmp represents bitmap, jpg and jpeg represent the slightly graphics file format of distortion compression, and php is supertext pre-service language, the script of the embedded html document of carrying out at server end, jsp represents embedded web page script, and HTML, HTM and XML are web page files;
The status code of Web journal file acquiescence represents to ask successfully with 2 beginnings, with 3 beginnings, represents that user asks to be redirected to other positions, with 4 beginnings, represents that client exists mistake, with 5 beginnings, represents that server end exists mistake;
According to user's IP, identify different users, the user who selects visit capacity to reach certain value carries out behavioural analysis;
According to user, in the residence time of whole website, carry out session identification, set a time threshold, if surpass this time threshold, think that new session starts;
From user conversation, find out significant accession page and access path, the link page that user is had to access for the page that achieves the goal in access process is that middle blade-rotating is deleted from session;
C, use collaborative filtering are set up user interest matrix, calculate the similarity between each user, select some users with larger similarity as similar users;
Yong Hu ?page matrix representation be R (M * N), matrix value Rm wherein, n represents the time of user M browsing pages N, Jiang Yong Hu ?page matrix R (M * N) be converted into Yong Hu ?resource class Matrix C (M * X), matrix value Cm wherein, x represents that user M browses the time of a certain resource class X, and Matrix C (M * X) is weighted to filtering data pre-service, obtain standardized resource, thereby form user interest matrix;
Adopt K ?means Data Cluster Algorithm user is carried out to cluster, user's similarity is chosen cosine similarity and is evaluated;
D, for the hobby of similar users, set up and recommend resource pool;
The interest-degree U of user i to page j
i, jcan be expressed as the product to the byte number of the ratio of all page browsing temporal summation and page j and all accession page byte number sum ratios in total residence time of page j and user i, that is:
Wherein: timei, j be user i in total residence time of page j, timei, k be user i to all page browsing temporal summation, sizei, j is the byte number of page j, sizei, k is all accession page byte number sums, k is natural number, m is all pages sums;
E, the threshold value at server place by threshold value assigning unit assigns recommendation, the web page recommendation that the recommendation in server selection recommendation resource pool is greater than assign thresholds is to user.
Claims (1)
1. the information personalized recommend method based on Web daily record data, step is as follows:
A, user be by the resource in multimedia thin-client accesses network, server by this behavior record of user in server log file;
B, data analysis and pre-service to Web journal file in server, exclude that visit capacity is few, under-represented user's Visitor Logs and middle blade-rotating be referred to as some data of junk data, convert the original semi-structured Web daily record data that is not easy to be understood by people to structurized data, for example, only comprise the url of User IP, access time, accession page, the tables of data of access bytes digital section extracts as meeting rule, data source accurately;
According to the content information of Web journal file, in tables of data, build corresponding field, then text data is imported in tables of data;
Data in tables of data are cleared up, by data nonsensical in user access information, these Visitor Logs of bmp, jpg as by name in suffix, jpeg, php, jsp and status code are not 200 to represent that the log recording of unsuccessful access deletes, and only retain the log recording of suffix HTML, HTM by name and XML; Wherein bmp represents bitmap, jpg and jpeg represent the slightly graphics file format of distortion compression, and php is supertext pre-service language, the script of the embedded html document of carrying out at server end, jsp represents embedded web page script, and HTML, HTM and XML are web page files;
The status code of Web journal file acquiescence represents to ask successfully with 2 beginnings, with 3 beginnings, represents that user asks to be redirected to other positions, with 4 beginnings, represents that client exists mistake, with 5 beginnings, represents that server end exists mistake;
According to user's IP, identify different users, the user who selects visit capacity to reach certain value carries out behavioural analysis;
According to user, in the residence time of whole website, carry out session identification, set a time threshold, if surpass this time threshold, think that new session starts;
From user conversation, find out significant accession page and access path, the link page that user is had to access for the page that achieves the goal in access process is that middle blade-rotating is deleted from session;
C, use collaborative filtering are set up user interest matrix, calculate the similarity between each user, select some users with larger similarity as similar users;
Yong Hu ?page matrix representation be R (M * N), matrix value Rm wherein, n represents the time of user M browsing pages N, Jiang Yong Hu ?page matrix R (M * N) be converted into Yong Hu ?resource class Matrix C (M * X), matrix value Cm wherein, x represents that user M browses the time of a certain resource class X, and Matrix C (M * X) is weighted to filtering data pre-service, obtain standardized resource, thereby form user interest matrix;
Adopt K ?means Data Cluster Algorithm user is carried out to cluster, user's similarity is chosen cosine similarity and is evaluated;
D, for the hobby of similar users, set up and recommend resource pool;
The interest-degree U of user i to page j
i,jcan be expressed as the product to the byte number of the ratio of all page browsing temporal summation and page j and all accession page byte number sum ratios in total residence time of page j and user i, that is:
Wherein: timei, j be user i in total residence time of page j, timei, k be user i to all page browsing temporal summation, sizei, j is the byte number of page j, sizei, k is all accession page byte number sums, k is natural number, m is all pages sums;
E, the threshold value at server place by threshold value assigning unit assigns recommendation, the web page recommendation that the recommendation in server selection recommendation resource pool is greater than assign thresholds is to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310717507.4A CN103678652B (en) | 2013-12-23 | 2013-12-23 | Information individualized recommendation method based on Web log data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310717507.4A CN103678652B (en) | 2013-12-23 | 2013-12-23 | Information individualized recommendation method based on Web log data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103678652A true CN103678652A (en) | 2014-03-26 |
| CN103678652B CN103678652B (en) | 2017-02-01 |
Family
ID=50316196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310717507.4A Active CN103678652B (en) | 2013-12-23 | 2013-12-23 | Information individualized recommendation method based on Web log data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103678652B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331433A (en) * | 2014-10-22 | 2015-02-04 | 浙江中烟工业有限责任公司 | Tobacco information recommending method based on mobile terminal user logs |
| CN104506480A (en) * | 2014-06-27 | 2015-04-08 | 深圳市永达电子股份有限公司 | Cross-domain access control method and system based on marking and auditing combination |
| CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
| CN105589917A (en) * | 2015-09-17 | 2016-05-18 | 广州市动景计算机科技有限公司 | Method and device for analyzing log information of browser |
| WO2016101777A1 (en) * | 2014-12-26 | 2016-06-30 | 中国银联股份有限公司 | Analysis and collection system for user interest data and method therefor |
| CN106302851A (en) * | 2016-08-09 | 2017-01-04 | 厦门天锐科技股份有限公司 | A kind of method judging that server by which kind of network type is accessed |
| CN106302849A (en) * | 2016-08-04 | 2017-01-04 | 北京集奥聚合科技有限公司 | A kind of method carrying out moving solid fusion by carrier data |
| CN106528852A (en) * | 2016-11-25 | 2017-03-22 | 盐城工学院 | Method and device for conducting redirecting by accessing data |
| CN107256261A (en) * | 2017-06-13 | 2017-10-17 | 中原工学院 | Electro-nic message transmissions system and method |
| CN107341397A (en) * | 2017-06-30 | 2017-11-10 | 福建师范大学 | Big data platform session recognition methods based on dynamic time threshold value |
| CN108109043A (en) * | 2017-12-22 | 2018-06-01 | 重庆邮电大学 | A kind of commending system reduces the method for repeating to recommend |
| CN108109035A (en) * | 2017-12-08 | 2018-06-01 | 上海电机学院 | Webpage recommending method based on Web personalizations |
| CN109299375A (en) * | 2018-10-24 | 2019-02-01 | 中国平安人寿保险股份有限公司 | Information personalized push method, device, electronic equipment and storage medium |
| CN109388737A (en) * | 2017-08-03 | 2019-02-26 | 腾讯科技（北京）有限公司 | A kind of sending method, device and the storage medium of the exposure data of content item |
| CN110188566A (en) * | 2019-05-19 | 2019-08-30 | 复旦大学 | A method of the test access behavior based on sequence analysis damages data equity |
| CN111400628A (en) * | 2020-03-12 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Information propagation method, device, equipment and medium |
| CN114840486A (en) * | 2022-06-28 | 2022-08-02 | 广州趣米网络科技有限公司 | User behavior data acquisition method and system and cloud platform |
| CN117194804A (en) * | 2023-11-08 | 2023-12-08 | 上海银行股份有限公司 | Guiding recommendation method and system suitable for operation management system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100412870C (en) * | 2006-07-17 | 2008-08-20 | 北京航空航天大学 | Gateway personalized recommendation service method and system introduced yuan recommendation engine |
| CN102141986A (en) * | 2010-01-28 | 2011-08-03 | 北京邮电大学 | Individualized information providing method and system based on user behaviors |
| CN102819575B (en) * | 2012-07-20 | 2015-06-17 | 南京大学 | Personalized search method for Web service recommendation |
-
2013
- 2013-12-23 CN CN201310717507.4A patent/CN103678652B/en active Active
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506480A (en) * | 2014-06-27 | 2015-04-08 | 深圳市永达电子股份有限公司 | Cross-domain access control method and system based on marking and auditing combination |
| CN104506480B (en) * | 2014-06-27 | 2018-11-23 | 深圳市永达电子信息股份有限公司 | The cross-domain access control method and system combined based on label with audit |
| CN104331433B (en) * | 2014-10-22 | 2017-12-29 | 浙江中烟工业有限责任公司 | A kind of Tobacco Reference based on mobile terminal user's daily record recommends method |
| CN104331433A (en) * | 2014-10-22 | 2015-02-04 | 浙江中烟工业有限责任公司 | Tobacco information recommending method based on mobile terminal user logs |
| WO2016101777A1 (en) * | 2014-12-26 | 2016-06-30 | 中国银联股份有限公司 | Analysis and collection system for user interest data and method therefor |
| US10762549B2 (en) | 2014-12-26 | 2020-09-01 | China Unionpay Co., Ltd. | Analysis and collection system for user interest data and method therefor |
| CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
| CN104866540B (en) * | 2015-05-04 | 2018-04-27 | 华中科技大学 | A kind of personalized recommendation method based on group of subscribers behavioural analysis |
| CN105589917A (en) * | 2015-09-17 | 2016-05-18 | 广州市动景计算机科技有限公司 | Method and device for analyzing log information of browser |
| CN106302849A (en) * | 2016-08-04 | 2017-01-04 | 北京集奥聚合科技有限公司 | A kind of method carrying out moving solid fusion by carrier data |
| CN106302851A (en) * | 2016-08-09 | 2017-01-04 | 厦门天锐科技股份有限公司 | A kind of method judging that server by which kind of network type is accessed |
| CN106302851B (en) * | 2016-08-09 | 2019-08-02 | 厦门天锐科技股份有限公司 | A method of judging that server is accessed by which kind of network type |
| CN106528852A (en) * | 2016-11-25 | 2017-03-22 | 盐城工学院 | Method and device for conducting redirecting by accessing data |
| CN107256261A (en) * | 2017-06-13 | 2017-10-17 | 中原工学院 | Electro-nic message transmissions system and method |
| CN107341397A (en) * | 2017-06-30 | 2017-11-10 | 福建师范大学 | Big data platform session recognition methods based on dynamic time threshold value |
| CN109388737B (en) * | 2017-08-03 | 2023-03-31 | 腾讯科技（北京）有限公司 | Method and device for sending exposure data of content item and storage medium |
| CN109388737A (en) * | 2017-08-03 | 2019-02-26 | 腾讯科技（北京）有限公司 | A kind of sending method, device and the storage medium of the exposure data of content item |
| CN108109035A (en) * | 2017-12-08 | 2018-06-01 | 上海电机学院 | Webpage recommending method based on Web personalizations |
| CN108109043A (en) * | 2017-12-22 | 2018-06-01 | 重庆邮电大学 | A kind of commending system reduces the method for repeating to recommend |
| CN109299375A (en) * | 2018-10-24 | 2019-02-01 | 中国平安人寿保险股份有限公司 | Information personalized push method, device, electronic equipment and storage medium |
| CN110188566A (en) * | 2019-05-19 | 2019-08-30 | 复旦大学 | A method of the test access behavior based on sequence analysis damages data equity |
| CN111400628A (en) * | 2020-03-12 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Information propagation method, device, equipment and medium |
| CN114840486A (en) * | 2022-06-28 | 2022-08-02 | 广州趣米网络科技有限公司 | User behavior data acquisition method and system and cloud platform |
| CN114840486B (en) * | 2022-06-28 | 2022-09-16 | 广州趣米网络科技有限公司 | User behavior data acquisition method and system and cloud platform |
| CN117194804A (en) * | 2023-11-08 | 2023-12-08 | 上海银行股份有限公司 | Guiding recommendation method and system suitable for operation management system |
| CN117194804B (en) * | 2023-11-08 | 2024-01-26 | 上海银行股份有限公司 | Guiding recommendation method and system suitable for operation management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103678652B (en) | 2017-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103678652B (en) | Information individualized recommendation method based on Web log data | |
| CN111159564A (en) | Information recommendation method and device, storage medium and computer equipment | |
| US9639622B2 (en) | Image processing system, image processing method, program, and non-transitory information storage medium | |
| US20090319449A1 (en) | Providing context for web articles | |
| US20170235726A1 (en) | Information identification and extraction | |
| US20170316519A1 (en) | Mutually reinforcing ranking of social media accounts and contents | |
| CN107436877B (en) | Hot topic pushing method and device | |
| CN107862058B (en) | Method and apparatus for generating information | |
| CN102207967B (en) | Method and system for automatically providing new browser plugin | |
| CN104866557A (en) | Customized just-in-time learning support system and method based on constructivist learning theory | |
| Leiva et al. | Building a better mousetrap: Compressing mouse cursor activity for web analytics | |
| US11665121B2 (en) | Determining topic cohesion between posted and linked content | |
| CN113592522A (en) | Method and apparatus for processing traffic data, and computer-readable storage medium | |
| CN104778164A (en) | Method and device for detecting repeated URL (Uniform Resource Locator) | |
| CN112287272B (en) | Method, system and storage medium for classifying website list pages | |
| CN105160016A (en) | Method and device for acquiring user attributes | |
| CN113032525A (en) | False news detection method and device, electronic equipment and storage medium | |
| CN115659008A (en) | Information pushing system and method for big data information feedback, electronic device and medium | |
| CN104537080B (en) | Information recommends method and system | |
| US20220318653A1 (en) | Social media content recommendation | |
| CN114138968A (en) | Network hotspot mining method, device, equipment and storage medium | |
| CN111966946A (en) | Method, device, equipment and storage medium for identifying authority value of page | |
| CN112685618A (en) | User feature identification method and device, computing equipment and computer storage medium | |
| CN108595453B (en) | URL (Uniform resource locator) identifier mapping obtaining method and device | |
| CN112464087B (en) | Recommendation probability output method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |