CN109446394A - For network public-opinion event based on modular public sentiment monitoring method and system - Google Patents
For network public-opinion event based on modular public sentiment monitoring method and system Download PDFInfo
- Publication number
- CN109446394A CN109446394A CN201811132909.7A CN201811132909A CN109446394A CN 109446394 A CN109446394 A CN 109446394A CN 201811132909 A CN201811132909 A CN 201811132909A CN 109446394 A CN109446394 A CN 109446394A
- Authority
- CN
- China
- Prior art keywords
- public
- public sentiment
- module
- topic
- sentiment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 abstract 1
- 238000007418 data mining Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000097202 Rathbunia alamosensis Species 0.000 description 1
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of for network public-opinion event based on modular public sentiment monitoring method and system, and network social intercourse platform is divided into several modules first and is monitored；Then the public sentiment in timing acquisition each period in modules platform actively counts, and predicts the public sentiment staple of conversation and computing module topic liveness of public sentiment；The topic Global Information of topic liveness value beyond the mark is obtained, and is included in emphasis public sentiment list；All modules are integrated, the topic numbers of each public sentiment module are obtained, for redistributing the weight of each module；Then all public feelings informations under the topic are obtained, Cluster Classification operation is carried out to each public feelings information, obtain basic the analysis of public opinion report；The last public sentiment sample of extraction in proportion, which is put into integrated model, to be trained, and predicts the trend of the following public sentiment topic.The present invention can obtain real-time public sentiment report in the outburst for detecting great public sentiment event at the first time, predict next public sentiment trend.
Description
Technical field
This research belongs to field of computer technology, particularly belong to machine learning in Computer Subject, data mining and
The technical field of modularization weight；It is related to a kind of public opinion prediction method and system based on integrated approach, and in particular to Yi Zhongzhen
The big network public-opinion event of counterweight based on modular public sentiment monitoring method and system.
Background technique
Machine learning (Machine Learning) is one and specializes in the mankind were simulated or realized to computer how
Habit behavior reorganizes the existing structure of knowledge and is allowed to constantly improve the performance of itself to obtain new knowledge or skills
Section.
Data mining (English: Data mining), and it is translated into Date Mining, data mining.It is knowledge discovery in database
A step in (English: Knowledge-Discovery in Databases, abbreviation: KDD).Data mining generally refers to
The process of wherein information is hidden in by algorithm search from a large amount of data.Data mining is usually related with computer science,
And pass through statistics, online analysis and processing, information retrieval, machine learning, expert system (relying on the past rule of thumb) and mode
All multi-methods such as identification realize above-mentioned target.
The main thought of model integrated is to first pass through certain rule to generate multiple learners, then use certain Integrated Strategy
It is combined, last comprehensive descision exports final result.In general, multiple learners in usually said integrated study are all
It is homogeneity " weak learner ".Based on the weak learner, disturbance is indicated by sample set disturbance, input feature vector disturbance, output, is calculated
The modes such as method parameter perturbation generate multiple learners, carry out obtaining a precision preferably " strong learner " after integrating.With collection
At going deep into for Learning Studies, the definition of broad sense is gradually received by scholars, it refers to multiple learner set using
The mode of habit, without being distinguish to learner property.According to this definition, more learner system (multi-classifier
System), multi-expert mixing (mixture of experts) and the study (committee-based based on the committee
) etc. learning multiple fields can be brought into integrated study.But it is currently still ground with the integrated study of homogeneous classification device
Study carefully in the majority.
Summary of the invention
The present invention is difficult to collect and public feelings information caused by analysis to solve social networks particular network public feelings information
Be difficult to the problem of monitoring, propose pioneeringly it is a kind of for great network public-opinion event based on modular public sentiment monitoring side
Method and system.
Technical solution used by method of the invention is: it is a kind of for network public-opinion event based on modular public sentiment
Monitoring method, which comprises the following steps:
Step 1: network social intercourse platform being divided into several modules and is monitored；
Step 2: the public sentiment in timing acquisition each period in modules platform actively counts, and predicts the public sentiment of public sentiment
The staple of conversation and computing module topic liveness；
Step 3: obtaining the topic Global Information of topic liveness value beyond the mark, and be included in emphasis public sentiment list；
Step 4: all modules are integrated, the topic numbers of each public sentiment module are obtained, it is each for redistributing
The weight of module；
Step 5: obtaining all public feelings informations under the topic, Cluster Classification operation is carried out to each public feelings information, obtains base
This analysis of public opinion report；
Step 6: according to the weight of each module obtained in step 4, extracting public sentiment sample in proportion and be put into integrated model
It is trained, predicts the trend of the following public sentiment topic.
Technical solution used by system of the invention is: it is a kind of for network public-opinion event based on modular public sentiment
Monitoring system, it is characterised in that: including monitoring module, public opinion information acquisition module, emphasis public sentiment list builder module, integrate mould
Block, public opinion information analysis module, the following public sentiment topic trend estimate module；
The monitoring module is monitored for network social intercourse platform to be divided into several modules；
The public opinion information acquisition module, it is active for the public sentiment in modules platform in timing acquisition each period
Number, and predict the public sentiment staple of conversation and computing module topic liveness of public sentiment；
The emphasis public sentiment list builder module, for obtaining the topic Global Information of topic liveness value beyond the mark,
And it is included in emphasis public sentiment list；
It is described to integrate module, for being integrated to all modules, the topic numbers of each public sentiment module are obtained, weight is used to
Newly distribute the weight of each module；
The public opinion information analysis module carries out each public feelings information for obtaining all public feelings informations under the topic
Cluster Classification operation obtains basic the analysis of public opinion report；
Described future public sentiment topic trend estimate module is taken out in proportion for the weight according to each module of acquisition
It takes public sentiment sample to be put into integrated model to be trained, predicts the trend of the following public sentiment topic.
The present invention proposes modular concept for major social portal website, and combines integrated learning approach.The party
Method realizes the Quick Acquisition to network public-opinion, efficient analysis, in conjunction with multiple social platform modules, so that finally obtained prediction
It is more accurate reliable.
Detailed description of the invention
Fig. 1 is the method flow diagram of the embodiment of the present invention；
Fig. 2 is social platform monitoring module schematic diagram in system of the embodiment of the present invention；
Fig. 3 is integrated model block schematic illustration in system of the embodiment of the present invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and embodiments to this hair
It is bright to be described in further detail, it should be understood that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
Referring to Fig.1, it is provided by the invention it is a kind of for network public-opinion event based on modular public sentiment monitoring method, packet
Include following steps:
Step 1: network social intercourse platform being divided into several modules and is monitored；
See Fig. 2, network social intercourse platform is divided into Sina weibo acquisition module, knows acquisition module, takes journey by the present embodiment
Acquisition module, room world acquisition module, Baidu's discussion bar acquisition module, bean cotyledon acquisition module etc.；
Step 2: the public sentiment in timing acquisition each period in modules platform actively counts, and utilizes classification ensemble side
Method predicts the public sentiment staple of conversation and computing module topic liveness of public sentiment；
Wherein i-th of module topic liveness aiCalculation formula are as follows:
Step 3: obtaining the topic Global Information of topic liveness value beyond the mark (the present embodiment takes 30%), and be included in weight
Point public sentiment list；
Step 4: all modules are integrated, the topic numbers of each public sentiment module are obtained, it is each for redistributing
The weight of module；
Step 5: obtaining all public feelings informations under the topic, Cluster Classification operation is carried out to each public feelings information, obtains base
This analysis of public opinion report；
In the present embodiment, using the methods of Cluster Classification to the time of each public feelings information delivered, geographical location, user
Age, gender, occupation carry out Cluster Classification operation, obtain basic the analysis of public opinion report.
Step 6: according to the weight of each module obtained in step 4, extracting public sentiment sample in proportion and be put into integrated model
It is trained, predicts the trend of the following public sentiment topic；
The integrated model of the present embodiment, construction method are as follows: be utilized respectively a variety of Weak Classifiers and emotion is carried out to micro-blog information
Analysis integrates the classification results of all Weak Classifiers then by way of integrated, finally utilizes " simple vote method "
Integrated Strategy multiple disaggregated models are integrated, obtain final classification result；
It designs cluster device and after category set grows up to be a useful person, this two parts is connected into the complete public feelings information of composition and is analyzed
Submodel；When training, the public feelings information data of training sample are first clustered into device by K-Means, to form multiple clusters, then
It is grown up to be a useful person and is trained using the category set being made of three kinds of neural network, logistic regression, decision tree Weak Classifiers on each cluster,
Finally obtain trained integrated model.
It is that the integrated model frame diagram of the present embodiment divides all independent models by way of integrated see Fig. 3
Class result is integrated, and finally the Integrated Strategy of " simple vote method " is utilized to integrate multiple disaggregated models, obtained most
Whole classification results.It designs cluster device and after category set grows up to be a useful person, this two parts is connected into the complete public feelings information of composition
Analyze submodel.When training, the public feelings information data of training sample are first clustered into device by K-Means, so that multiple clusters are formed,
Then on each cluster using by neural network, logistic regression, the category set of three kinds of Weak Classifiers of decision tree composition is grown up to be a useful person progress
Training, finally obtains trained model.
The present embodiment, which additionally provides, a kind of monitors system, including prison based on modular public sentiment for network public-opinion event
Control module, public opinion information acquisition module, emphasis public sentiment list builder module, integrate module, public opinion information analysis module, it is following should
Public sentiment topic trend estimate module；
Monitoring module is monitored for network social intercourse platform to be divided into several modules；
Public opinion information acquisition module is actively counted for the public sentiment in modules platform in timing acquisition each period,
And predict the public sentiment staple of conversation and computing module topic liveness of public sentiment；
Emphasis public sentiment list builder module, for obtaining the topic Global Information of topic liveness value beyond the mark, side by side
Enter emphasis public sentiment list；
Module is integrated, for integrating to all modules, the topic numbers of each public sentiment module are obtained, for dividing again
Weight with each module；
Public opinion information analysis module clusters each public feelings information for obtaining all public feelings informations under the topic
Sort operation obtains basic the analysis of public opinion report；
The following public sentiment topic trend estimate module extracts carriage for the weight according to each module of acquisition in proportion
Feelings sample is put into integrated model and is trained, and predicts the trend of the following public sentiment topic.
Real-time public sentiment report can be obtained in the outburst for detecting great public sentiment event at the first time through the invention, predicted
Next public sentiment trend.In order to guarantee the accuracy of prediction result, disparate modules are provided with to each social platform, and use
The mode of weight carries out extracting public sentiment sample, to predict that public sentiment is moved towards, keeps the result of prediction more accurate.
It should be understood that the part that this specification does not elaborate belongs to the prior art.
It should be understood that the above-mentioned description for preferred embodiment is more detailed, can not therefore be considered to this
The limitation of invention patent protection range, those skilled in the art under the inspiration of the present invention, are not departing from power of the present invention
Benefit requires to make replacement or deformation under protected ambit, fall within the scope of protection of the present invention, this hair
It is bright range is claimed to be determined by the appended claims.
Claims (6)
1. it is a kind of for network public-opinion event based on modular public sentiment monitoring method, which comprises the following steps:
Step 1: network social intercourse platform being divided into several modules and is monitored；
Step 2: the public sentiment in timing acquisition each period in modules platform actively counts, and predicts that the public sentiment of public sentiment is main
Topic and computing module topic liveness；
Step 3: obtaining the topic Global Information of topic liveness value beyond the mark, and be included in emphasis public sentiment list；
Step 4: all modules being integrated, the topic numbers of each public sentiment module are obtained, for redistributing each module
Weight；
Step 5: obtaining all public feelings informations under the topic, Cluster Classification operation is carried out to each public feelings information, is obtained basic
The analysis of public opinion report；
Step 6: according to the weight of each module obtained in step 4, extracting public sentiment sample in proportion and be put into integrated model progress
The trend of the following public sentiment topic is predicted in training.
2. it is according to claim 1 for network public-opinion event based on modular public sentiment monitoring method, feature exists
In: in step 2, utilize the public sentiment staple of conversation and computing module topic liveness of classification ensemble method prediction public sentiment；
Wherein i-th of module topic liveness aiCalculation formula are as follows:
3. it is according to claim 1 for network public-opinion event based on modular public sentiment monitoring method, feature exists
In: in step 4, weight calculation formula is
4. it is according to claim 1 for network public-opinion event based on modular public sentiment monitoring method, feature exists
In: in step 5, using the methods of Cluster Classification to the time of each public feelings information delivered, geographical location, age of user, property
Not, occupation carries out Cluster Classification operation, obtains basic the analysis of public opinion report.
5. it is according to any one of claims 1-4 for network public-opinion event based on modular public sentiment monitoring side
Method, it is characterised in that: integrated model described in step 6, construction method are as follows: be utilized respectively a variety of Weak Classifiers to micro-blog information
Sentiment analysis is carried out, then by way of integrated, the classification results of all Weak Classifiers are integrated, finally utilizes " letter
The Integrated Strategy of single-throw ticket method " integrates multiple disaggregated models, obtains final classification result；
It designs cluster device and after category set grows up to be a useful person, this two parts is connected into the complete public feelings information of composition and analyzes submodule
Type；When training, the public feelings information data of training sample are first clustered into device by K-Means, so that multiple clusters are formed, then every
It is grown up to be a useful person and is trained using the category set being made of three kinds of neural network, logistic regression, decision tree Weak Classifiers on a cluster, finally
Obtain trained integrated model.
6. a kind of monitor system based on modular public sentiment for network public-opinion event, it is characterised in that: including monitoring module,
Public opinion information acquisition module, emphasis public sentiment list builder module integrate module, public opinion information analysis module, the following public sentiment words
Inscribe trend estimate module；
The monitoring module is monitored for network social intercourse platform to be divided into several modules；
The public opinion information acquisition module is actively counted for the public sentiment in modules platform in timing acquisition each period,
And predict the public sentiment staple of conversation and computing module topic liveness of public sentiment；
The emphasis public sentiment list builder module, for obtaining the topic Global Information of topic liveness value beyond the mark, side by side
Enter emphasis public sentiment list；
It is described to integrate module, for integrating to all modules, the topic numbers of each public sentiment module are obtained, for dividing again
Weight with each module；
The public opinion information analysis module clusters each public feelings information for obtaining all public feelings informations under the topic
Sort operation obtains basic the analysis of public opinion report；
Described future public sentiment topic trend estimate module extracts carriage for the weight according to each module of acquisition in proportion
Feelings sample is put into integrated model and is trained, and predicts the trend of the following public sentiment topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811132909.7A CN109446394A (en) | 2018-09-27 | 2018-09-27 | For network public-opinion event based on modular public sentiment monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811132909.7A CN109446394A (en) | 2018-09-27 | 2018-09-27 | For network public-opinion event based on modular public sentiment monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446394A true CN109446394A (en) | 2019-03-08 |
Family
ID=65546045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811132909.7A Pending CN109446394A (en) | 2018-09-27 | 2018-09-27 | For network public-opinion event based on modular public sentiment monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446394A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144575A (en) * | 2019-12-05 | 2020-05-12 | 支付宝(杭州)信息技术有限公司 | Public opinion early warning model training method, early warning method, device, equipment and medium |
| CN112632218A (en) * | 2020-12-15 | 2021-04-09 | 西安电子科技大学 | Network public opinion monitoring method for enterprise crisis public customs |
| CN114610980A (en) * | 2022-03-21 | 2022-06-10 | 平安普惠企业管理有限公司 | Network public opinion based black product identification method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150335A (en) * | 2013-01-25 | 2013-06-12 | 河南理工大学 | Co-clustering-based coal mine public sentiment monitoring system |
| US20140052753A1 (en) * | 2010-12-21 | 2014-02-20 | Peking University Founder Group Co., Ltd. | Method, device and system for processing public opinion topics |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN106096056A (en) * | 2016-06-30 | 2016-11-09 | 西南石油大学 | A kind of based on distributed public sentiment data real-time collecting method and system |
| CN108052586A (en) * | 2017-12-11 | 2018-05-18 | 上海壹账通金融科技有限公司 | The analysis of public opinion method, system, computer equipment and storage medium |
-
2018
- 2018-09-27 CN CN201811132909.7A patent/CN109446394A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140052753A1 (en) * | 2010-12-21 | 2014-02-20 | Peking University Founder Group Co., Ltd. | Method, device and system for processing public opinion topics |
| CN103150335A (en) * | 2013-01-25 | 2013-06-12 | 河南理工大学 | Co-clustering-based coal mine public sentiment monitoring system |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN106096056A (en) * | 2016-06-30 | 2016-11-09 | 西南石油大学 | A kind of based on distributed public sentiment data real-time collecting method and system |
| CN108052586A (en) * | 2017-12-11 | 2018-05-18 | 上海壹账通金融科技有限公司 | The analysis of public opinion method, system, computer equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 唐涛: "《网络舆情治理研究》", 31 December 2014 * |
| 李彤,宋之杰: "基于模型集成的突发事件舆情分析与趋势预测研究", 《系统工程理论与实践》 * |
| 汤景泰: "《危机传播管理》", 31 December 2015 * |
| 范春晓: "《Web数据分析关键技术及解决方案》", 31 December 2017 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144575A (en) * | 2019-12-05 | 2020-05-12 | 支付宝(杭州)信息技术有限公司 | Public opinion early warning model training method, early warning method, device, equipment and medium |
| CN112632218A (en) * | 2020-12-15 | 2021-04-09 | 西安电子科技大学 | Network public opinion monitoring method for enterprise crisis public customs |
| CN114610980A (en) * | 2022-03-21 | 2022-06-10 | 平安普惠企业管理有限公司 | Network public opinion based black product identification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105677873B (en) | Text Intelligence association cluster based on model of the domain knowledge collects processing method | |
| CN103530540B (en) | User identity attribute detection method based on man-machine interaction behavior characteristics | |
| CN106095928B (en) | A kind of event type recognition methods and device | |
| CN104182805B (en) | Dangerous tendency Forecasting Methodology based on inmate's behavioural characteristic integrated study model | |
| CN109241255A (en) | A kind of intension recognizing method based on deep learning | |
| CN106709754A (en) | Power user grouping method based on text mining | |
| CN106528528A (en) | A text emotion analysis method and device | |
| CN109446394A (en) | For network public-opinion event based on modular public sentiment monitoring method and system | |
| CN110555568A (en) | Road traffic running state real-time perception method based on social network information | |
| CN101645083A (en) | Acquisition system and method of text field based on concept symbols | |
| CN112051986B (en) | Code search recommendation device and method based on open source knowledge | |
| CN115526590B (en) | Efficient person post matching and re-pushing method combining expert knowledge and algorithm | |
| CN115544348A (en) | Intelligent mass information searching system based on Internet big data | |
| CN111353085A (en) | Cloud mining network public opinion analysis method based on feature model | |
| CN111767404A (en) | Event mining method and device | |
| CN116756373A (en) | Project review expert screening method, system and medium based on knowledge graph update | |
| CN110619422A (en) | Intelligent station passenger flow condition prediction method and system | |
| CN116186422A (en) | Disease-related public opinion analysis system based on social media and artificial intelligence | |
| CN115050484A (en) | Analysis and prejudgment method and system based on modeling of epidemic prevention control scene | |
| CN112069390B (en) | User book borrowing behavior analysis and interest prediction method based on space-time dimension | |
| Wang | [Retracted] Construction and Effect Analysis of College Students’ Physical Education Teaching Mode Based on Data Mining Algorithm | |
| Yifan et al. | Design and implementation of tourism activity recognition and discovery system | |
| CN113792794A (en) | Feature selection method based on membrane algorithm | |
| Hartanto et al. | Classifying User Personality Based on Media Social Posts Using Support Vector Machine Algorithm Based on DISC Approach | |
| Zhang et al. | Robust social event detection via deep clustering |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |