CN112085099A - Distributed student clustering integration method and system - Google Patents
Distributed student clustering integration method and system Download PDFInfo
- Publication number
- CN112085099A CN112085099A CN202010943424.7A CN202010943424A CN112085099A CN 112085099 A CN112085099 A CN 112085099A CN 202010943424 A CN202010943424 A CN 202010943424A CN 112085099 A CN112085099 A CN 112085099A
- Authority
- CN
- China
- Prior art keywords
- cluster
- user
- same specific
- clustering
- specific characteristics
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention discloses a distributed student clustering integration method and a distributed student clustering integration system, relates to the technical field of network education, and solves the problems that an existing online education platform cannot accurately recommend learning resources to users, and the system is easy to crash due to large data calculation amount, and the technical scheme is as follows: acquiring original behavior data of a user, analyzing the original behavior data through a naive Bayes model, and extracting behavior characteristics; the user behaviors are accurately clustered, the similarity between cluster objects is small, and the similarity in the clusters is large, so that technical support can be provided for an online education platform to accurately recommend learning resources to the user, recommendation errors are reduced, and the user experience is improved; distributed calculation is performed on all user behaviors, so that the operation load of the online platform is reduced, and the normal operation of the online platform is ensured; through multiple times of fusion and identification of the user behavior classified and aggregated data, the calculation amount of the user behavior data classified and aggregated is reduced, and the reaction speed of the online education system is improved.
Description
Technical Field
The invention relates to the technical field of network education, in particular to a distributed student clustering integration method and system.
Background
With the rapid development of internet technology, the large-scale popularization of intelligent terminal devices such as smart phones and tablet computers and the like, mobile network resources such as 4G and the like are not scarce any more, and digitization and mobile online learning become new ways for people to accept education. Online education, also known as distance education and online learning, refers to a method for content dissemination and fast learning through application information technology and internet technology. Compared with the traditional education mode, the network education has the advantages of dispersed learning time, unlimited learning places, strong content targeting, high online interaction efficiency, repeated learning and the like.
In recent years, online education is more and more favored by users, wherein most online education platforms recommend related learning resources directly according to user behaviors, analysis on the user behaviors is not needed, investment cost is low, however, the recommended learning resources change along with the change of the user behaviors, accurate recommendation cannot be performed on the users, and meanwhile, the emotional feeling of the users is easily felt; a small number of online education platforms classify user behaviors after analyzing the user behaviors, and accurately recommend the user behaviors according to classification results, so that the user requirements are met to a certain extent, however, the similarity between clusters is large, the similarity in the clusters is small in the conventional clustering integration method, and a large error still exists in accurate recommendation; meanwhile, as the number of the intelligent terminals is increased, the data calculation amount is large, system breakdown is easily caused, and the reaction speed is low.
Therefore, how to research and design a distributed student clustering integration method and system is a problem which is urgently needed to be solved at present, and technical support is provided for online education to realize accurate learning resource recommendation.
Disclosure of Invention
In order to solve the problems that the existing online education platform cannot accurately recommend learning resources to users, and the system is easy to crash due to large data calculation amount, the invention aims to provide a distributed student clustering integration method and system.
The technical purpose of the invention is realized by the following technical scheme:
in a first aspect, a distributed student clustering integration method is provided, which includes the following steps:
s1: acquiring original behavior data of a user, analyzing the original behavior data through a naive Bayes model, and extracting behavior characteristics;
s2: performing first classification and aggregation on the behavior characteristics of all users in the service area by using the same specific characteristics as standards through a lower server to form a plurality of cluster objects, wherein the same specific characteristics are selected by using a Pearson correlation coefficient as a standard; using the same specific characteristic as the cluster identification of the corresponding cluster object; simultaneously removing the same specific characteristics of each user in the cluster object to form a first cluster object;
s3: fusing all first cluster objects with the same cluster identifier in the subordinate server through the superior server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; removing the same specific characteristics of each user in the new cluster object to form a second cluster object;
s4: repeating the step S3 by using the upper server in the step S3 as a lower server until the cluster object forms a cluster identifier;
s5: and carrying out statistical storage on the user information and the corresponding cluster identifications after the clustering is finished.
Preferably, in step S1, the original behavior data is subjected to non-associative data elimination and dimensionality reduction by a PCA principal component analysis method to obtain associated original behavior data.
Preferably, in step S3, the upper level server performs a second fusion on all second cluster objects with the same second cluster identifier to form a new second cluster object.
Preferably, when the behavior characteristics of the user simultaneously include the same specific characteristics of two or more cluster objects, the same specific characteristics of the cluster objects are weighted, and the same specific characteristics with larger weights are taken as priorities to be classified and aggregated.
Preferably, after the cluster object completes forming the cluster identifier, the cluster classification of the corresponding user is stopped.
In a second aspect, a distributed student clustering integration system is provided, which comprises user terminals, a database and at least two levels of servers, wherein a plurality of user terminals are arranged in a service area to which lower level servers belong, and a plurality of lower level servers are arranged in a service area to which upper level servers belong;
the user terminal is used for acquiring original behavior data of a user, analyzing the original behavior data through a naive Bayes model, and extracting behavior characteristics;
the lower server is used for carrying out first classification and aggregation on the behavior characteristics of all users in the service area to which the users belong by taking the same specific characteristics as standards to form a plurality of cluster objects, and the same specific characteristics are selected by taking a Pearson correlation coefficient as a standard; using the same specific characteristic as the cluster identification of the corresponding cluster object; simultaneously removing the same specific characteristics of each user in the cluster object to form a first cluster object;
the upper-level server is used for fusing all the first cluster objects with the same cluster identifier in the lower-level server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; removing the same specific characteristics of each user in the new cluster object to form a second cluster object; repeatedly performing classification and aggregation by taking the superior server as the inferior server until the cluster object forms a cluster identifier;
and the database is used for counting and storing the user information completing the clustering and the corresponding clustering identification.
Preferably, the user terminal further includes a principal component analysis module, and the principal component analysis module obtains associated original behavior data after removing dimensionality reduction of non-associated data of the original behavior data.
Preferably, the upper level server is further configured to perform secondary fusion on all second cluster objects with the same second cluster identifier to form a new second cluster object.
Preferably, the server further comprises a weight calculation module; when the behavior characteristics of the user simultaneously contain the same specific characteristics of more than two cluster objects, the weight calculation module carries out weight value calculation on the same specific characteristics of the cluster objects, and the same specific characteristics with large weight values are taken as priorities to carry out classification and aggregation.
Preferably, the servers are all in communication connection with the database; and when the cluster object completes the formation of the cluster identifier, stopping the aggregation classification of the corresponding user.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the method, the user behaviors are accurately clustered, the similarity between cluster objects is small, the similarity in the clusters is large, technical support can be provided for an online education platform to accurately recommend learning resources to the user, recommendation errors are reduced, and the user experience is improved;
(2) according to the invention, distributed calculation is carried out on all user behaviors, so that the operation load of the online platform is reduced, and the normal operation of the online platform is ensured;
(3) according to the invention, the user behavior classified and aggregated data is subjected to multiple times of fusion and identification, so that the calculation amount of the user behavior classified and aggregated data is reduced, and the reaction speed of the online education system is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flowchart in example 1 of the present invention;
fig. 2 is an architecture diagram in embodiment 2 of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to fig. 1-2 and embodiments 1-2.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Example 1: a distributed student clustering integration method, as shown in fig. 1, includes the following steps:
the method comprises the steps of firstly, obtaining original behavior data of a user, carrying out non-associated data elimination and dimensionality reduction on the original behavior data through a Principal Component Analysis (PCA) method to obtain associated original behavior data, analyzing the original behavior data through a naive Bayes model, and then extracting behavior characteristics. The original behavior data can be operation footprints, operation sequences, residence time, first attention points, click rates, login time, login places, user information and the like after the user logs in the online education platform. The original behavior data can also be online test results, past examination results and the like.
And step two, performing first classification and aggregation on the behavior characteristics of all users in the service area by using the same specific characteristics as standards through a lower-level server to form a plurality of cluster objects, wherein the same specific characteristics are selected by using a Pearson correlation coefficient as a standard. Using the same specific characteristic as the cluster identification of the corresponding cluster object; and simultaneously removing the same specific characteristics of all users in the cluster object to form a first cluster object. When the behavior characteristics of the user simultaneously contain the same specific characteristics of more than two cluster objects, the weight value calculation is carried out on the same specific characteristics of the cluster objects, and the same specific characteristics with large weight values are taken as priorities to carry out classification and aggregation.
For example, the behavior signature of USER-1 is A, B, C, D, E, F, the behavior signature of USER-2 is A, C, D, Q, H, the behavior signature of USER-3 is A, B, E, Q, H, and the same particular signature may be one or more particular signatures. If user 1, user 2, have A, C as a particular feature, a first cluster object identified as an AC may be formed, with the remaining behavior features for user 1 in the first cluster object comprising B, D, E, F and the remaining behavior features for user 2 comprising D, Q, H.
If user 2, user 3, with Q, H as a particular feature, a first cluster object identified as QH may be formed, with the remaining behavior features for user 2 in the first cluster object comprising A, C, D and the remaining behavior features for user 3 comprising A, B, E.
If two cluster objects are classified and aggregated by taking the AC and the QH as the same specific features, the behavior feature of the user 2 includes both the AC and the QH, at this time, it is necessary to calculate the weighted value of A, C and calculate the average value, and calculate the weighted value of Q, H and calculate the average value, if the average value of the AC is large, the user 2 is integrated into the first cluster object identified by the AC, and otherwise, the user 2 is integrated into the first cluster object identified by the QH.
Step three, fusing all first cluster objects with the same cluster identifier in the subordinate server through the superior server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; and removing the same specific characteristics of all users in the new cluster object to form a second cluster object.
And the superior server performs secondary fusion on all the second cluster objects with the same second cluster identifier to form a new second cluster object.
Assume that one subordinate server forms the AC as the identified first cluster object (AC, User1-B, D, E, F, User2-D, Q, H) and the QH as the identified first cluster object (QH, User3-B, D, E, F, User4-B, D). Another subordinate server forms the AC as an identified first cluster object (AC, Users 5-B, D, E, F, Users 6-B, D, Q, H) and the BD as an identified first cluster object (BD, Users 7-A, C, E, F, Q, H, Users 8-A, C, Q, H).
The four first cluster objects are fused for the first time to form a new first cluster object identified by the AC (AC, users 1-B, D, E, F, users 2-D, Q, H, users 5-B, D, E, F and users 6-B, D, Q, H), the QH is the first identified cluster object (QH, users 3-B, D, E, F and users 4-B, D), and the BD is the first identified cluster object (BD, users 7-A, C, E, F, Q, H and users 8-A, C, Q, H).
And classifying and aggregating the first clustering object with the QH as the identifier by taking the BD as the same specific feature to obtain a second clustering object with the QHBD as the identifier (QHBD, users 3-E, F and user 4-none), and classifying and aggregating the first clustering object with the BD as the identifier by taking the QH as the same specific feature to obtain a second clustering object with the BDQH as the identifier (BDQH, users 7-A, C, E, F and users 8-A, C). At this point, the two second cluster objects have the same aggregation identification, so performing a second fusion results in a new second cluster object identified as BDQH (QHBD, user 3-E, F, user 4-none, user 7-A, C, E, F, user 8-A, C).
And step four, the upper server in the step three is used as a lower server to repeatedly carry out the operation in the step three until the cluster object forms the cluster identifier. And when the cluster object completes the formation of the cluster identifier, stopping the aggregation classification of the corresponding user. For example, the new second cluster object identified as BDQH in step three (QHBD, Users 3-E, F, Users 4-none, Users 7-A, C, E, F, Users 8-A, C), where Users 4 have no behavioral characteristics, is marked as QHBD cluster object, and user 4 is removed to get the updated second cluster object (QHBD, Users 3-E, F, Users 7-A, C, E, F, Users 8-A, C).
And step five, counting and storing the user information and the corresponding cluster identifications after the clustering is finished. Such as user 4 labeled QHBD cluster object in step four, at which time the online platform may make an accurate recommendation of learning resources to user 4.
Example 2: a distributed student clustering integration system, as shown in fig. 2, for implementing the distributed student clustering integration method in embodiment 1, includes a user terminal, a database, and at least two levels of servers, where a plurality of user terminals are provided in a service area to which lower levels of servers belong, and a plurality of lower levels of servers are provided in a service area to which upper levels of servers belong.
And the user terminal is used for acquiring the original behavior data of the user, analyzing the original behavior data through a naive Bayes model, and extracting the behavior characteristics.
The lower-level server is used for carrying out first classification and aggregation on the behavior characteristics of all users in the service area to which the users belong by taking the same specific characteristics as standards to form a plurality of cluster objects, and the same specific characteristics are selected by taking a Pearson correlation coefficient as a standard; using the same specific characteristic as the cluster identification of the corresponding cluster object; and simultaneously removing the same specific characteristics of all users in the cluster object to form a first cluster object.
The upper server is used for fusing all the first cluster objects with the same cluster identifier in the lower server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; removing the same specific characteristics of each user in the new cluster object to form a second cluster object; repeatedly performing classification and aggregation by taking the superior server as the inferior server until the cluster object forms a cluster identifier;
and the database is used for counting and storing the user information completing the clustering set and the corresponding clustering identification.
The user terminal also comprises a principal component analysis module, and the principal component analysis module eliminates dimensionality reduction on the non-associated data of the original behavior data to obtain associated original behavior data.
The superior server is also used for performing secondary fusion on all the second cluster objects with the same second cluster identifier to form a new second cluster object.
The server also comprises a weight calculation module; when the behavior characteristics of the user simultaneously contain the same specific characteristics of more than two cluster objects, the weight calculation module carries out weight value calculation on the same specific characteristics of the cluster objects, and the same specific characteristics with large weight values are taken as priorities to carry out classification and aggregation.
The servers are all in communication connection with the database. And when the cluster object completes the formation of the cluster identifier, stopping the aggregation classification of the corresponding user.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
Claims (10)
1. A distributed student clustering integration method is characterized by comprising the following steps:
s1: acquiring original behavior data of a user, analyzing the original behavior data through a naive Bayes model, and extracting behavior characteristics;
s2: performing first classification and aggregation on the behavior characteristics of all users in the service area by using the same specific characteristics as standards through a lower server to form a plurality of cluster objects, wherein the same specific characteristics are selected by using a Pearson correlation coefficient as a standard; using the same specific characteristic as the cluster identification of the corresponding cluster object; simultaneously removing the same specific characteristics of each user in the cluster object to form a first cluster object;
s3: fusing all first cluster objects with the same cluster identifier in the subordinate server through the superior server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; removing the same specific characteristics of each user in the new cluster object to form a second cluster object;
s4: repeating the step S3 by using the upper server in the step S3 as a lower server until the cluster object forms a cluster identifier;
s5: and carrying out statistical storage on the user information and the corresponding cluster identifications after the clustering is finished.
2. The distributed student clustering integration method of claim 1, wherein in step S1, the original behavior data is subjected to non-associative data elimination and dimensionality reduction by a PCA principal component analysis method to obtain associated original behavior data.
3. The distributed student clustering method according to claim 1, wherein in step S3, the upper level server performs a second fusion on all second cluster objects with the same second cluster identifier to form a new second cluster object.
4. The distributed student clustering method according to claim 1, wherein when the behavior features of the user include the same specific features of more than two cluster objects at the same time, the same specific features of the cluster objects are weighted, and the same specific features with higher weights are classified and aggregated as priorities.
5. The distributed student clustering method of claim 1 wherein clustering classification of corresponding users is stopped after clustering identification formation of the cluster objects is completed.
6. A distributed student clustering integrated system is characterized by comprising user terminals, a database and at least two levels of servers, wherein a plurality of user terminals are arranged in a service area to which a lower level server belongs, and a plurality of lower level servers are arranged in a service area to which a higher level server belongs;
the user terminal is used for acquiring original behavior data of a user, analyzing the original behavior data through a naive Bayes model, and extracting behavior characteristics;
the lower server is used for carrying out first classification and aggregation on the behavior characteristics of all users in the service area to which the users belong by taking the same specific characteristics as standards to form a plurality of cluster objects, and the same specific characteristics are selected by taking a Pearson correlation coefficient as a standard; using the same specific characteristic as the cluster identification of the corresponding cluster object; simultaneously removing the same specific characteristics of each user in the cluster object to form a first cluster object;
the upper-level server is used for fusing all the first cluster objects with the same cluster identifier in the lower-level server to form a new first cluster object; performing secondary classification and aggregation by taking the same specific characteristics as standards to form a plurality of new cluster objects; adding the same specific characteristics into the first cluster identifier of the corresponding new cluster object to form a second cluster identifier; removing the same specific characteristics of each user in the new cluster object to form a second cluster object; repeatedly performing classification and aggregation by taking the superior server as the inferior server until the cluster object forms a cluster identifier;
and the database is used for counting and storing the user information completing the clustering and the corresponding clustering identification.
7. The distributed student clustering integration system of claim 6, wherein the user terminal further comprises a principal component analysis module, and the principal component analysis module eliminates dimensionality reduction on non-associated data of the original behavior data to obtain associated original behavior data.
8. The distributed student clustering integration system of claim 6, wherein the upper level server is further configured to perform secondary fusion on all second cluster objects with the same second cluster identifier to form a new second cluster object.
9. The distributed student clustering integration system of claim 6 wherein the server further comprises a weight calculation module; when the behavior characteristics of the user simultaneously contain the same specific characteristics of more than two cluster objects, the weight calculation module carries out weight value calculation on the same specific characteristics of the cluster objects, and the same specific characteristics with large weight values are taken as priorities to carry out classification and aggregation.
10. The distributed student clustering integration system of claim 6 wherein the servers are each communicatively coupled to a database; and when the cluster object completes the formation of the cluster identifier, stopping the aggregation classification of the corresponding user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010943424.7A CN112085099B (en) | 2020-09-09 | 2020-09-09 | Distributed student clustering integration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010943424.7A CN112085099B (en) | 2020-09-09 | 2020-09-09 | Distributed student clustering integration method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112085099A true CN112085099A (en) | 2020-12-15 |
| CN112085099B CN112085099B (en) | 2022-05-17 |
Family
ID=73731682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010943424.7A Active CN112085099B (en) | 2020-09-09 | 2020-09-09 | Distributed student clustering integration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085099B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057519A (en) * | 2023-10-13 | 2023-11-14 | 北京布局未来教育科技有限公司 | Teaching information demonstration method based on convolutional neural network and computer equipment |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101174265A (en) * | 2006-11-04 | 2008-05-07 | 吴风勇 | Method for recording and estimating search action of users |
| CN101894327A (en) * | 2010-07-07 | 2010-11-24 | 清华大学 | Digital resource long-term storage format outdating risk quantitative evaluation method |
| CN101989289A (en) * | 2009-08-06 | 2011-03-23 | 富士通株式会社 | Data clustering method and device |
| CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| CN102143389A (en) * | 2011-04-22 | 2011-08-03 | 赛特斯网络科技(南京)有限责任公司 | Quality assurance (QA) system and method of internet protocol television (IPTV) services |
| CN103377242A (en) * | 2012-04-25 | 2013-10-30 | Tcl集团股份有限公司 | User behavior analysis method, user behavior analytical prediction method and television program push system |
| US20140012785A1 (en) * | 2012-07-06 | 2014-01-09 | Samsung Electronics Co., Ltd. | Apparatus and method for recognizing representative user behavior based on recognition of unit behaviors |
| JP2014038606A (en) * | 2012-07-20 | 2014-02-27 | Jfe Steel Corp | Feature point extraction method for photographed image, and feature point extraction device |
| CN103869367A (en) * | 2014-03-25 | 2014-06-18 | 中南大学 | Seismic event time and space gathering mode extraction method based on shared density |
| CN104253879A (en) * | 2014-09-15 | 2014-12-31 | 北京锐安科技有限公司 | IP (Internet protocol) address-based position calibration method and IP address-based position calibration device |
| CN104951499A (en) * | 2015-04-23 | 2015-09-30 | 中国科学院信息工程研究所 | Method for associating users with one another across domains and method for pushing information |
| CN105404697A (en) * | 2015-12-29 | 2016-03-16 | 成都陌云科技有限公司 | Social interaction behavior collection and detection method |
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN107798557A (en) * | 2017-09-30 | 2018-03-13 | 平安科技（深圳）有限公司 | Electronic installation, the service location based on LBS data recommend method and storage medium |
| CN110110225A (en) * | 2019-04-17 | 2019-08-09 | 重庆第二师范学院 | Online education recommended models and construction method based on user behavior data analysis |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
-
2020
- 2020-09-09 CN CN202010943424.7A patent/CN112085099B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101174265A (en) * | 2006-11-04 | 2008-05-07 | 吴风勇 | Method for recording and estimating search action of users |
| CN101989289A (en) * | 2009-08-06 | 2011-03-23 | 富士通株式会社 | Data clustering method and device |
| CN101894327A (en) * | 2010-07-07 | 2010-11-24 | 清华大学 | Digital resource long-term storage format outdating risk quantitative evaluation method |
| CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| CN102143389A (en) * | 2011-04-22 | 2011-08-03 | 赛特斯网络科技(南京)有限责任公司 | Quality assurance (QA) system and method of internet protocol television (IPTV) services |
| CN103377242A (en) * | 2012-04-25 | 2013-10-30 | Tcl集团股份有限公司 | User behavior analysis method, user behavior analytical prediction method and television program push system |
| US20140012785A1 (en) * | 2012-07-06 | 2014-01-09 | Samsung Electronics Co., Ltd. | Apparatus and method for recognizing representative user behavior based on recognition of unit behaviors |
| JP2014038606A (en) * | 2012-07-20 | 2014-02-27 | Jfe Steel Corp | Feature point extraction method for photographed image, and feature point extraction device |
| CN103869367A (en) * | 2014-03-25 | 2014-06-18 | 中南大学 | Seismic event time and space gathering mode extraction method based on shared density |
| CN104253879A (en) * | 2014-09-15 | 2014-12-31 | 北京锐安科技有限公司 | IP (Internet protocol) address-based position calibration method and IP address-based position calibration device |
| CN104951499A (en) * | 2015-04-23 | 2015-09-30 | 中国科学院信息工程研究所 | Method for associating users with one another across domains and method for pushing information |
| CN105404697A (en) * | 2015-12-29 | 2016-03-16 | 成都陌云科技有限公司 | Social interaction behavior collection and detection method |
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN107798557A (en) * | 2017-09-30 | 2018-03-13 | 平安科技（深圳）有限公司 | Electronic installation, the service location based on LBS data recommend method and storage medium |
| CN110110225A (en) * | 2019-04-17 | 2019-08-09 | 重庆第二师范学院 | Online education recommended models and construction method based on user behavior data analysis |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
Non-Patent Citations (3)
| Title |
|---|
| PERDISCI R: "Scalable fine-grained behavioral clustering of http-based malware", 《COMPUTER NETWORKS》 * |
| 吴介等: "底层内容特征的融合在图像检索中的研究进展", 《中国图象图形学报》 * |
| 马辉民等: "文本聚类在Web挖掘系统中的应用", 《统计与决策》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057519A (en) * | 2023-10-13 | 2023-11-14 | 北京布局未来教育科技有限公司 | Teaching information demonstration method based on convolutional neural network and computer equipment |
| CN117057519B (en) * | 2023-10-13 | 2024-01-23 | 北京布局未来科技发展有限公司 | Teaching information demonstration method based on convolutional neural network and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112085099B (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108021929B (en) | Big data-based mobile terminal e-commerce user portrait establishing and analyzing method and system | |
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| CN108804567A (en) | Improve method, equipment, storage medium and the device of intelligent customer service response rate | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| CN104040963A (en) | System and methods for spam detection using frequency spectra of character strings | |
| CN111797320B (en) | Data processing method, device, equipment and storage medium | |
| CN108345908A (en) | Sorting technique, sorting device and the storage medium of electric network data | |
| CN114168761B (en) | Multimedia data pushing method and device, electronic equipment and storage medium | |
| CN103577876A (en) | Credible and incredible user recognizing method based on feedforward neural network | |
| EP4131031A1 (en) | Recommendation method and device based on automatic feature grouping | |
| CN106951471A (en) | A kind of construction method of the label prediction of the development trend model based on SVM | |
| CN112085099B (en) | Distributed student clustering integration method and system | |
| CN112579822A (en) | Video data pushing method and device, computer equipment and storage medium | |
| CN112308345A (en) | Communication network load prediction method, device and server | |
| US20130108180A1 (en) | Information processing device, information processing method, and program | |
| CN114169439A (en) | Abnormal communication number identification method and device, electronic equipment and readable medium | |
| CN114138968A (en) | Network hotspot mining method, device, equipment and storage medium | |
| CN111177564B (en) | Product recommendation method and device | |
| CN111444933A (en) | Object classification method and device | |
| KR101935330B1 (en) | Conflict factor evaluation system of construction project and method thereof | |
| CN112764923B (en) | Computing resource allocation method, computing resource allocation device, computer equipment and storage medium | |
| CN110070297A (en) | Tourist classification marketing management method, Scenery Management System, server | |
| CN112214675B (en) | Method, device, equipment and computer storage medium for determining user purchasing machine | |
| CN112463964B (en) | Text classification and model training method, device, equipment and storage medium | |
| CN113886547A (en) | Client real-time conversation switching method and device based on artificial intelligence and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |