CN109636495A - A kind of online recommended method of scientific and technological information based on big data - Google Patents
A kind of online recommended method of scientific and technological information based on big data Download PDFInfo
- Publication number
- CN109636495A CN109636495A CN201811107445.4A CN201811107445A CN109636495A CN 109636495 A CN109636495 A CN 109636495A CN 201811107445 A CN201811107445 A CN 201811107445A CN 109636495 A CN109636495 A CN 109636495A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- scientific
- online
- algorithm
- 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
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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of online recommended methods of the scientific and technological information based on big data, comprising the following steps: acquisition history science and technology information data；User's history behavioral data is collected using the embedding code of JS；It based on user's history behavioral data, labels to user, obtains subscriber data center；Depth analysis is carried out to subscriber data center using deep learning algorithm, machine learning algorithm and semantic analysis algorithm, and formulates proposed algorithm model；The online behavioral data of user is acquired in real time using the embedding code of JS, and the trigger event during browsing web sites according to user is that user recommends corresponding scientific and technological information using proposed algorithm model；Log collection is carried out to the access behavior of user in the way of SDK, and analysis optimization is carried out to proposed algorithm model based on log collection result.The present invention obtains concern information portrait result relevant to user Focus Area and concern action trail relational network using portrait analysis and atlas analysis, the business scenario precisely recommended for scientific and technological information provides strong data basis, it is ensured that the convenience and accuracy recommended on line.
Description
Technical field
The present invention relates to big data processing technology field, in particular to a kind of scientific and technological information based on big data is recommended online
Method.
Background technique
Scientific and technological information is to record the information carrier of science and technology activity, Sci-tech Knowledge；It is record and propagation scientific and technological information
Main means are also to aid in the important tool that people recognize objective things, inspire thinking, seek technical support.
Now with the progress of social scientific and technological level, scientific and technological information data volume is in explosive increase.Scientific and technological information data without
By being exploitation or use, it all be unable to do without the support of network technology.But the scientific and technological information on current network is many and diverse, comprehensive and quasi-
True property is not high, and scientific and technical personnel is caused to be not easy to directly obtain true valuable information.If can filtering useless information, realize
The accurate information of scientific and technical personnel is recommended, it is of increasing concern.
Currently, the recommendation of scientific and technological information is still simply to be recommended based on text approximation, and scientific and technical personnel wish to obtain
What is obtained is that more fully, accurately information, the effect that this also results in current scientific and technological information recommendation are undesirable.
Summary of the invention
To solve the above problems, the present invention provides a kind of online recommended methods of the scientific and technological information based on big data.
The invention adopts the following technical scheme:
A kind of online recommended method of scientific and technological information based on big data, comprising the following steps:
S1, acquisition history science and technology information data, HDFS file system is arrived in storage after being sorted out；
S2, user's history behavioral data is collected using the embedding code of JS, and stores and arrives HDFS file system, the historical behavior number
According to browsing area content, residence time and the Ajax when browsing web sites including user；
S3, it is based on user's history behavioral data, labelled to user, obtain subscriber data center；
S4, depth is carried out to subscriber data center using deep learning algorithm, machine learning algorithm and semantic analysis algorithm
Analysis, and formulate proposed algorithm model；
S5, the online behavioral data of user is acquired in real time using the embedding code of JS, the triggering thing during browsing web sites according to user
Part is that user recommends corresponding scientific and technological information using proposed algorithm model, and the online behavioral data includes that user browses web sites
When clicking operation, browsing area and Ajax；
S6, log collection is carried out to the access behavior of user in the way of SDK, and recommendation is calculated based on log collection result
Method model carries out analysis optimization.
Preferably, the step S1 include it is following step by step:
S11, cluster feature collection is pre-established, the cluster feature collection is real including one group of name entity and with each name
The corresponding characteristic information knowledge base of body；
S12, acquisition history science and technology information data, carry out Chinese word segmentation to history science and technology information data and extract keyword,
Obtain keyword data collection；
S13, using keyword as basic feature, clustered using k-means algorithm, obtain cluster set；
S14, according to the topic relativity of cluster set and cluster feature collection, data source is carried out to history science and technology information data and is returned
Class；
S15, according to the correlation of cluster feature collection and keyword data collection, extract corresponding structured data sets, obtain
Index file corresponding to history science and technology information data；
S16, history science and technology information data and its corresponding index file are stored to HDFS file system.
Preferably, the step S2 include it is following step by step:
When S21, user browse web sites, the JS code being nested in Website page is executed；
S22, JS code will need the user behavior data obtained to send in a manner of avro by event or time trigger
To Flume listening port；
When S23, Flume listening port listen to port and has data input, stored as user's history behavioral data
To HDFS file system.
Preferably, the step S3 include it is following step by step:
S31, user's history behavioral data is cleaned, converted and is loaded, obtain goal behavior data；
S32, it is labelled based on goal behavior data to user, obtains subscriber data center.
Preferably, the step S4 include it is following step by step:
S41, portrait analysis is carried out to the user for having accomplished fluently label, obtain concern information portrait result；
S42, the visualization technique that figure is led using chart database and power restore the concern action trail network of personal connections of user
Network；
S43, it is combined on the basis of paying close attention to information portrait result, concern action trail relational network and scene formulation is recommended to push away
Recommend algorithm model.
Preferably, the step S5 include it is following step by step:
S51, it acquires the online behavioral data of user in real time using the embedding code of JS, and stores and arrive HDFS file system；
S52, clustering is carried out for the online behavioral data of user, obtains trigger event；
S53, trigger event is sent to STORM engine, STORM engine executes proposed algorithm model, realizes online recommend.
Preferably, the step S6 include it is following step by step:
S61, log collection is carried out to the access behavior of user in the way of SDK；
S62, clustering is carried out for the online behavioral data of user, obtains trigger event；
S63, log collection is carried out to the access behavior of user in the way of SDK, and based on log collection result to recommendation
Algorithm model carries out analysis optimization.
Preferably, HBASE database and Solrcloud index are stored in the HDFS file system.
Preferably, described in step S3 labels using in machine learning, deep learning, clustering, statistical analysis
One or more modes.
Preferably, the proposed algorithm model includes collaborative filtering, association analysis algorithm, deep learning algorithm, divides
One of class algorithm, rule-based algorithm, clustering algorithm are a variety of.
After adopting the above technical scheme, compared with the background technology, the present invention, having the advantages that
The present invention obtains concern information portrait result relevant to user Focus Area using portrait analysis and atlas analysis
With concern action trail relational network, the business scenario precisely recommended for scientific and technological information provides strong data basis；This hair
Bright combination concern information portrait result, recommends scene to make corresponding recommended models at concern action trail relational network, it is ensured that
The convenience and accuracy recommended on line.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Embodiment
Refering to what is shown in Fig. 1, a kind of online recommended method of scientific and technological information based on big data, comprising the following steps:
A kind of online recommended method of scientific and technological information based on big data, comprising the following steps:
S1, acquisition history science and technology information data, HDFS file system is arrived in storage after being sorted out.Step S1 includes following point
Step:
S11, cluster feature collection is pre-established, the cluster feature collection is real including one group of name entity and with each name
The corresponding characteristic information knowledge base of body.Naming entity includes industry field relevant to scientific and technological information, product, technique, equipment, material
Material, expert's name, scientific research institution etc..By taking one of name entity " product " as an example, characteristic information knowledge base has included " lamp
Tool, chip, mobile phone, battery ... " etc. information；By taking another names entity " material " as an example, characteristic information knowledge base is received
Information such as " polyethylene, GaAs, monocrystalline silicon, glass, copper ... " are recorded.
S12, acquisition history science and technology information data, carry out Chinese word segmentation to history science and technology information data and extract keyword,
Obtain keyword data collection.
S13, using keyword as basic feature, clustered using k-means algorithm, obtain cluster set.
S14, according to the topic relativity of cluster set and cluster feature collection, data source is carried out to history science and technology information data and is returned
Class.
S15, according to the correlation of cluster feature collection and keyword data collection, extract corresponding structured data sets, obtain
Index file corresponding to history science and technology information data.
S16, history science and technology information data and its corresponding index file are stored to HDFS file system.HDFS file system
HBASE database and Solrcloud index are stored on system.
S2, user's history behavioral data is collected using the embedding code of JS, and stores and arrives HDFS file system, the historical behavior number
According to browsing area content, residence time and the Ajax when browsing web sites including user.Step S2 include it is following step by step:
When S21, user browse web sites, the JS code being nested in Website page is executed.
S22, JS code will need the user behavior data obtained to send in a manner of avro by event or time trigger
To Flume listening port.
When S23, Flume listening port listen to port and has data input, stored as user's history behavioral data
To HDFS file system.
S3, it is based on user's history behavioral data, labelled to user, obtain subscriber data center.Step S3 includes
Below step by step:
S31, user's history behavioral data is cleaned, converted and is loaded, obtain goal behavior data.
S32, it is labelled based on goal behavior data to user, obtains subscriber data center.It labels using machine
One of study, deep learning, clustering, statistical analysis or various ways.
S4, depth is carried out to subscriber data center using deep learning algorithm, machine learning algorithm and semantic analysis algorithm
Analysis, and formulate proposed algorithm model.Step S4 include it is following step by step:
S41, portrait analysis is carried out to the user for having accomplished fluently label, obtain concern information portrait result.
S42, the visualization technique that figure is led using chart database and power restore the concern action trail network of personal connections of user
Network.
S43, it is combined on the basis of paying close attention to information portrait result, concern action trail relational network and scene formulation is recommended to push away
Recommend algorithm model.Proposed algorithm model includes collaborative filtering, association analysis algorithm, deep learning algorithm, sorting algorithm, rule
Then one of algorithm, clustering algorithm or a variety of.
S5, the online behavioral data of user is acquired in real time using the embedding code of JS, the triggering thing during browsing web sites according to user
Part is that user recommends corresponding scientific and technological information using proposed algorithm model, and the online behavioral data includes that user browses web sites
When clicking operation, browsing area and Ajax.Step S5 include it is following step by step:
S51, it acquires the online behavioral data of user in real time using the embedding code of JS, and stores and arrive HDFS file system.
S52, clustering is carried out for the online behavioral data of user, obtains trigger event.The online behavioral data master of user
It to include the content-data of browsing area and the FORM list submit the total amount evidence of Ajax.To the use of user's online behavioral data and step
1 similar fashion carries out Chinese word segmentation to the online behavioral data of user and extracts keyword, carries out clustering, and then cluster is special
Collection obtains the corresponding name entity of each keyword, finally obtains trigger event.
S53, trigger event is sent to STORM engine, STORM engine executes proposed algorithm model, realizes online recommend.
Online recommendation results include the scientific and technological information of identical name entities one or more to trigger event matching, also include and triggering thing
The information of the high different name entities of the part degree of association.For example, the corresponding keyword of trigger event is LED chip, corresponding name
Entity is product, but recommendation results are likely to be expert info or R&D institution's information including LED chip field.
S6, log collection is carried out to the access behavior of user in the way of SDK, and recommendation is calculated based on log collection result
Method model carries out analysis optimization.Step S6 include it is following step by step:
S61, log collection is carried out to the access behavior of user in the way of SDK；
S62, clustering is carried out for the online behavioral data of user, obtains trigger event；
S63, log collection is carried out to the access behavior of user in the way of SDK, and based on log collection result to recommendation
Algorithm model carries out analysis optimization.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (10)
1. a kind of online recommended method of scientific and technological information based on big data, which comprises the following steps:
S1, acquisition history science and technology information data, HDFS file system is arrived in storage after being sorted out；
S2, user's history behavioral data is collected using the embedding code of JS, and stores and arrives HDFS file system, the historical behavior data packet
Include browsing area content, residence time and the Ajax when user browses web sites；
S3, it is based on user's history behavioral data, labelled to user, obtain subscriber data center；
S4, depth analysis is carried out to subscriber data center using deep learning algorithm, machine learning algorithm and semantic analysis algorithm,
And formulate proposed algorithm model；
S5, the online behavioral data of user is acquired in real time using the embedding code of JS, the trigger event during being browsed web sites according to user, benefit
It is that user recommends corresponding scientific and technological information with proposed algorithm model, the online behavioral data includes point when user browses web sites
Hit operation, browsing area and Ajax；
S6, log collection is carried out to the access behavior of user in the way of SDK, and based on log collection result to proposed algorithm mould
Type carries out analysis optimization.
2. a kind of online recommended method of scientific and technological information based on big data as described in claim 1, which is characterized in that the step
Rapid S1 include it is following step by step:
S11, pre-establish cluster feature collection, the cluster feature collection include one group of name entity and with each name entity pair
The characteristic information knowledge base answered；
S12, acquisition history science and technology information data, carry out Chinese word segmentation to history science and technology information data and extract keyword, obtain
Keyword data collection；
S13, using keyword as basic feature, clustered using k-means algorithm, obtain cluster set；
S14, according to the topic relativity of cluster set and cluster feature collection, data source classification is carried out to history science and technology information data；
S15, according to the correlation of cluster feature collection and keyword data collection, extract corresponding structured data sets, obtain to going through
The corresponding index file of history scientific and technological information data；
S16, history science and technology information data and its corresponding index file are stored to HDFS file system.
3. a kind of online recommended method of scientific and technological information based on big data as claimed in claim 2, which is characterized in that the step
Rapid S2 include it is following step by step:
When S21, user browse web sites, the JS code being nested in Website page is executed；
S22, JS code will need the user behavior data obtained to be sent in a manner of avro by event or time trigger
Flume listening port；
When S23, Flume listening port listen to port and has data input, arrived as user's history behavioral data storage
HDFS file system.
4. a kind of online recommended method of scientific and technological information based on big data as claimed in claim 3, which is characterized in that the step
Rapid S3 include it is following step by step:
S31, user's history behavioral data is cleaned, converted and is loaded, obtain goal behavior data；
S32, it is labelled based on goal behavior data to user, obtains subscriber data center.
5. a kind of online recommended method of scientific and technological information based on big data as claimed in claim 4, which is characterized in that the step
Rapid S4 include it is following step by step:
S41, portrait analysis is carried out to the user for having accomplished fluently label, obtain concern information portrait result；
S42, the visualization technique that figure is led using chart database and power restore the concern action trail relational network of user；
S43, it is formulated on the basis of paying close attention to information portrait result, concern action trail relational network in conjunction with recommendation scene and recommends to calculate
Method model.
6. a kind of online recommended method of scientific and technological information based on big data as claimed in claim 5, which is characterized in that the step
Rapid S5 include it is following step by step:
S51, it acquires the online behavioral data of user in real time using the embedding code of JS, and stores and arrive HDFS file system；
S52, clustering is carried out for the online behavioral data of user, obtains trigger event；
S53, trigger event is sent to STORM engine, STORM engine executes proposed algorithm model, realizes online recommend.
7. a kind of online recommended method of scientific and technological information based on big data as claimed in claim 6, which is characterized in that the step
Rapid S6 include it is following step by step:
S61, log collection is carried out to the access behavior of user in the way of SDK；
S62, clustering is carried out for the online behavioral data of user, obtains trigger event；
S63, log collection is carried out to the access behavior of user in the way of SDK, and based on log collection result to proposed algorithm
Model carries out analysis optimization.
8. a kind of online recommended method of scientific and technological information based on big data as described in claim 1, it is characterised in that: described
HBASE database and Solrcloud index are stored in HDFS file system.
9. a kind of online recommended method of scientific and technological information based on big data as described in claim 1, it is characterised in that: step S3
In described label using one of machine learning, deep learning, clustering, statistical analysis or various ways.
10. a kind of online recommended method of scientific and technological information based on big data as described in claim 1, it is characterised in that: described
Proposed algorithm model includes collaborative filtering, association analysis algorithm, deep learning algorithm, sorting algorithm, rule-based algorithm, cluster
One of algorithm is a variety of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811107445.4A CN109636495A (en) | 2018-09-21 | 2018-09-21 | A kind of online recommended method of scientific and technological information based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811107445.4A CN109636495A (en) | 2018-09-21 | 2018-09-21 | A kind of online recommended method of scientific and technological information based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636495A true CN109636495A (en) | 2019-04-16 |
Family
ID=66066282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811107445.4A Pending CN109636495A (en) | 2018-09-21 | 2018-09-21 | A kind of online recommended method of scientific and technological information based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636495A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
| CN111177552A (en) * | 2019-12-27 | 2020-05-19 | 绍兴市上虞区理工高等研究院 | Scientific and technological achievement pushing method and device based on user requirements |
| CN111429293A (en) * | 2020-04-21 | 2020-07-17 | 重庆新致金服信息技术有限公司 | Recommendation system and recommendation method for insurance products |
| CN111460046A (en) * | 2020-03-06 | 2020-07-28 | 合肥海策科技信息服务有限公司 | Scientific and technological information clustering method based on big data |
| CN112365230A (en) * | 2020-11-04 | 2021-02-12 | 上海翕证科技发展有限公司 | Data self-adaptive analysis system |
| CN113378076A (en) * | 2021-06-29 | 2021-09-10 | 哈尔滨工业大学 | Online education-oriented learner collaborative learning social relationship construction method |
| CN113807926A (en) * | 2021-09-26 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Recommendation information generation method and device, electronic equipment and computer readable medium |
| CN113901325A (en) * | 2021-10-27 | 2022-01-07 | 首都信息发展股份有限公司 | User behavior analysis device and method |
| CN115203578A (en) * | 2022-09-16 | 2022-10-18 | 深圳云威网络科技有限公司 | User behavior analysis system based on big data platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016194A1 (en) * | 2010-07-30 | 2012-02-02 | Mohammad Al Hasan | Query suggestion for e-commerce sites |
| CN104021483A (en) * | 2014-06-26 | 2014-09-03 | 陈思恩 | Recommendation method for passenger demands |
| CN107229708A (en) * | 2017-05-27 | 2017-10-03 | 科技谷（厦门）信息技术有限公司 | A kind of personalized trip service big data application system and method |
| CN107341199A (en) * | 2017-06-21 | 2017-11-10 | 北京林业大学 | A kind of recommendation method based on documentation ＆ info general model |
-
2018
- 2018-09-21 CN CN201811107445.4A patent/CN109636495A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016194A1 (en) * | 2010-07-30 | 2012-02-02 | Mohammad Al Hasan | Query suggestion for e-commerce sites |
| CN104021483A (en) * | 2014-06-26 | 2014-09-03 | 陈思恩 | Recommendation method for passenger demands |
| CN107229708A (en) * | 2017-05-27 | 2017-10-03 | 科技谷（厦门）信息技术有限公司 | A kind of personalized trip service big data application system and method |
| CN107341199A (en) * | 2017-06-21 | 2017-11-10 | 北京林业大学 | A kind of recommendation method based on documentation ＆ info general model |
Non-Patent Citations (1)
| Title |
|---|
| 骆焦煌: "数据挖掘技术在入侵检测系统中的应用研究", 《吉林师范大学学报( 自然科学版)》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
| CN111177552A (en) * | 2019-12-27 | 2020-05-19 | 绍兴市上虞区理工高等研究院 | Scientific and technological achievement pushing method and device based on user requirements |
| CN111460046A (en) * | 2020-03-06 | 2020-07-28 | 合肥海策科技信息服务有限公司 | Scientific and technological information clustering method based on big data |
| CN111429293A (en) * | 2020-04-21 | 2020-07-17 | 重庆新致金服信息技术有限公司 | Recommendation system and recommendation method for insurance products |
| CN112365230A (en) * | 2020-11-04 | 2021-02-12 | 上海翕证科技发展有限公司 | Data self-adaptive analysis system |
| CN113378076A (en) * | 2021-06-29 | 2021-09-10 | 哈尔滨工业大学 | Online education-oriented learner collaborative learning social relationship construction method |
| CN113807926A (en) * | 2021-09-26 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Recommendation information generation method and device, electronic equipment and computer readable medium |
| CN113901325A (en) * | 2021-10-27 | 2022-01-07 | 首都信息发展股份有限公司 | User behavior analysis device and method |
| CN115203578A (en) * | 2022-09-16 | 2022-10-18 | 深圳云威网络科技有限公司 | User behavior analysis system based on big data platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636495A (en) | A kind of online recommended method of scientific and technological information based on big data | |
| US9449271B2 (en) | Classifying resources using a deep network | |
| CN101119326B (en) | Method and device for managing instant communication conversation record | |
| CN103455545B (en) | The method and system of the location estimation of social network user | |
| Ye et al. | Sentiment classification for movie reviews in Chinese by improved semantic oriented approach | |
| US8380697B2 (en) | Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency | |
| CN103593425B (en) | Preference-based intelligent retrieval method and system | |
| CN107862022B (en) | Culture resource recommendation system | |
| Stowe et al. | Improving classification of twitter behavior during hurricane events | |
| CN104239373B (en) | Add tagged method and device for document | |
| Foley et al. | Learning to extract local events from the web | |
| Wakade et al. | Text mining for sentiment analysis of Twitter data | |
| CN111461553A (en) | System and method for monitoring and analyzing public sentiment in scenic spot | |
| CN103324666A (en) | Topic tracing method and device based on micro-blog data | |
| Ye et al. | Sentiment classification for Chinese reviews: A comparison between SVM and semantic approaches | |
| CN104143005A (en) | Related searching system and method | |
| US20120030211A1 (en) | Message processing method and system | |
| CN105512333A (en) | Product comment theme searching method based on emotional tendency | |
| CN111723256A (en) | Government affair user portrait construction method and system based on information resource library | |
| Koswatte et al. | VGI and crowdsourced data credibility analysis using spam email detection techniques | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| Ahmed et al. | Real-time traffic congestion information from tweets using supervised and unsupervised machine learning techniques | |
| CN106874509B (en) | Resource recommendation method and device based on medium-granularity user grouping | |
| Cacheda et al. | Click through rate prediction for local search results | |
| Li et al. | Netnews bursty hot topic detection based on bursty features |
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 |