CN110427549A - A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium - Google Patents
A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium Download PDFInfo
- Publication number
- CN110427549A CN110427549A CN201910538471.0A CN201910538471A CN110427549A CN 110427549 A CN110427549 A CN 110427549A CN 201910538471 A CN201910538471 A CN 201910538471A CN 110427549 A CN110427549 A CN 110427549A
- Authority
- CN
- China
- Prior art keywords
- account
- article
- hostility
- group
- source tracing
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a kind of network public opinion Source Tracing method, apparatus, terminal and storage mediums, this method comprises: carrying out emotion attribute identification to acquisition public feelings information, extract negative emotions article；The negative emotions article is clustered, similar article group is generated, determines starting information source of the similar article group；The account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；Mining multi-dimensional data is carried out to the account in the hostility account group, generates Source Tracing result.Network public opinion Source Tracing method, apparatus, terminal and storage medium provided by the invention can carry out various dimensions Source Tracing for " black public relations " phenomenon.
Description
Technical field
The present invention relates to network public opinion Source Tracing technical field, in particular to a kind of network public opinion Source Tracing method,
Device, terminal and storage medium.
Background technique
As long as there is market competition, there are the needs of public relations activity.Under social media environment, broken out between rival
Query to other side is placed on daylight by some " wars of words ", this is also more normal thing.But there is also some black public relations,
And black public relations then refers to for the purpose of maliciously hitting opponent, with report that is organized, thering is step, paid manufacture and propagation to blacken the name of opponent
Road is means, and it is unilateral it is not firm, content is not professional, a kind of unbalanced behind-the-scene activities of position.It can many times be related to offending
Legal deadline, lowest permissible level of virtue, newspapering profession baseline.If black public relations is allowed to be full of, not only when thing enterprise can meet with injustice,
Whole market environment will have a greatly reduced quality in poor quality, the overall image and value of Chinese Enterprise.
Summary of the invention
The present invention provides a kind of network public opinion Source Tracing method, apparatus, terminal and storage medium, existing for " black public relations "
As various dimensions Source Tracing can be carried out.
In a first aspect, the embodiment of the invention provides a kind of network public opinion Source Tracing methods, comprising:
Emotion attribute identification is carried out to acquisition public feelings information, extracts negative emotions article；
The negative emotions article is clustered, similar article group is generated, determines starting letter of the similar article group
Source；
The account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；
Mining multi-dimensional data is carried out to the account in the hostility account group, generates Source Tracing result.
Preferably, emotion attribute identification is carried out to acquisition public feelings information, before extracting negative emotions article, further comprised the steps of:
Acquire the relevant the whole network public feelings information of target keyword by reptile instrument, the target keyword include brand names, senior executive,
At least one of product and project.
Preferably, described pair of acquisition public feelings information carries out emotion attribute identification, extracts negative emotions article, specifically: it is logical
It crosses natural language processing and emotion attribute identification is carried out to acquisition public feelings information, extract negative emotions article.
Preferably, described that the negative emotions article is clustered, similar article group is generated, determines the similar article
Starting information source of group, specifically: the negative emotions article is clustered, similar article group is generated, according to the similar text
The article issuing time of Zhang Qunzhong determines starting information source.
Preferably, the account in the hostility account group carries out mining multi-dimensional data, generates Source Tracing knot
Fruit, specifically: by excavating the running individual of the account and article, integrate owned enterprise/tissue, association main body and correspondent party
Formula；By excavating certification main body, registered enterprise and the affiliated enterprise of the account, hostility Enterprise Lists are integrated；Pass through the enemy
The financing and investment behavior, the superior and the subordinate's business connection of meaning enterprise, trace capital system belonging to the hostility enterprise, are closed by capital
System excavates the internal relation between the hostility enterprise；By connecting each other between the account and business organization, enterprise is constructed
Hostility network map；By recalling to the account and the dispatch of enterprise subordinate account history, the history dispatch is extracted
In hostility information and direction, the whole hostility degree of each capital system, organizations and account is compared and analyzed.
Second aspect, the embodiment of the invention provides a kind of network public opinion Source Tracing devices, comprising:
Extraction module extracts negative emotions article for carrying out emotion attribute identification to acquisition public feelings information；
Starting information source determining module generates similar article group, determines institute for clustering to the negative emotions article
State starting information source of similar article group；
Hostility account group's generation module, for extracting the account that publication amount is more than preset threshold from starting information source,
Generate hostility account group；
Result-generation module, for carrying out mining multi-dimensional data to the account in the hostility account group, generation is traced to the source
Analyze result.
Preferably, further include acquisition module, believe for acquiring the relevant the whole network public sentiment of target keyword by reptile instrument
Breath, the target keyword includes at least one of brand names, senior executive, product and project.
Preferably, in the extraction module: carrying out emotion attribute identification to acquisition public feelings information, extract negative emotions text
Chapter, specifically: emotion attribute identification is carried out to acquisition public feelings information by natural language processing, extracts negative emotions article.
The third aspect, the embodiment of the present application provide a kind of terminal, comprising: one or more processors, one or more
Memory；One or more of memories are coupled with one or more of processors, and one or more of memories are used
In storage computer program code, the computer program code includes computer instruction, when one or more of processors
When executing the computer instruction, the terminal executes above-mentioned network public opinion Source Tracing method.
Fourth aspect, the embodiment of the present application provide computer storage medium, store computer instruction thereon, when the meter
When the instruction of calculation machine is run at the terminal, so that the terminal executes above-mentioned network public opinion Source Tracing method.
By adopting the above technical scheme, emotion attribute identification first is carried out to acquisition public feelings information, extracts negative emotions article
As hostility information；Then hostility information is clustered, generates similar article group, determine starting information source of similar article group；
The account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；To the account in hostility account group
Number mining multi-dimensional data is carried out, generates Source Tracing as a result, tracing to the source point to realize various dimensions for " black public relations " phenomenon
Analysis.
Detailed description of the invention
Fig. 1 is the flow chart of network public opinion Source Tracing method provided in an embodiment of the present invention；
Fig. 2 is the structural block diagram of network public opinion Source Tracing device provided in an embodiment of the present invention；
Fig. 3 is another structural block diagram of network public opinion Source Tracing device provided in an embodiment of the present invention.
Specific embodiment
Specific embodiments of the present invention will be further explained with reference to the accompanying drawing.It should be noted that for
The explanation of these embodiments is used to help understand the present invention, but and does not constitute a limitation of the invention.In addition, disclosed below
The each embodiment of the present invention involved in technical characteristic can be combined with each other as long as they do not conflict with each other.
Wherein, in the description of the embodiment of the present application, unless otherwise indicated, "/" indicate or the meaning, for example, A/B can be with
Indicate A or B；"and/or" herein is only a kind of incidence relation for describing affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, at this
In the description for applying for embodiment, " multiple " refer to two or more.
Hereinafter, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.In the description of the embodiment of the present application, unless otherwise indicated, " multiples' " contains
Justice is two or more.
In a first aspect, as shown in Figure 1, the embodiment of the present application provides a kind of network public opinion Source Tracing method, comprising:
Step S101, emotion attribute identification is carried out to acquisition public feelings information, extracts negative emotions article；
The emotion attribute of center cathode in the public feelings information of acquisition is identified, using negative emotions article as hostility
Information extracts.
Step S102, negative emotions article is clustered, generates similar article group, determine starting letter of similar article group
Source；
Negative emotions article is clustered using the method for cluster, the article that similarity two-by-two is reached preset ratio is true
It is set to similar article, these similar polymerizable clcs is generated into similar article group together.
Earliest information source of starting information source, that is, time of origin, i.e. account.
Wherein, similar article group is usually multiple.
Step S103, the account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；
" hostility article " quantity of each account history publication is counted, the account that publication amount is more than preset threshold is extracted
Number be used as hostility account, these hostility accounts are configured to hostility account group.
Step S104, mining multi-dimensional data is carried out to the account in hostility account group, generates Source Tracing result.
By adopting the above technical scheme, emotion attribute identification first is carried out to acquisition public feelings information, extracts negative emotions article
As hostility information；Then hostility information is clustered, generates similar article group, determine starting information source of similar article group；
The account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；To the account in hostility account group
Number mining multi-dimensional data is carried out, generates Source Tracing as a result, tracing to the source point to realize various dimensions for " black public relations " phenomenon
Analysis.
Preferably, emotion attribute identification is carried out to acquisition public feelings information, before extracting negative emotions article, further comprised the steps of:
The relevant the whole network public feelings information of target keyword is acquired by reptile instrument, target keyword includes brand names, senior executive, product
At least one of with project.
Specifically, the whole network phase can be acquired based on crawler technology with brand names, senior executive, product, project etc. for keyword
Close public feelings information.Big data resource layer is built for each different data source, disposes corresponding crawler, the collection rule of crawler
It can flexibly define.Crawler supports intelligent recognition identifying code, and is based on dynamic proxy server (IP address pond) mechanism, automatically
Assignment agent server resumes resource automatically and closes the information for causing crawl to fail during crawl.Data acquisition and preliminary solution
After analysis, Data distributing Kafka cluster is submitted to.The information of acquisition back is subjected to subsequent clustering.
By being passed through with crawler technology acquisition data and other data sources, the text data of each platform of overlay network
Computer technology carries out automatic collection, intelligently parsing, all-round structuring and mass memory to data, solves the magnanimity of information source
Covering and the abundant accumulation of analysis case are that the continuous improvement reservoir data of judging result and algorithm learn iteration basis.
Preferably, emotion attribute identification is carried out to acquisition public feelings information, extracts negative emotions article, specifically: by certainly
Right Language Processing carries out emotion attribute identification to acquisition public feelings information, extracts negative emotions article.
The emotion attribute of the center cathode of content based on natural language processing technique (NLP) to acquisition back is known
Not, it is extracted negative emotions content as hostility information.Realize that algorithm includes fasttext, f-r-cnn, rnn, cnn etc.；
The open source component or frame of use include keras, tf, pytorch etc..
By natural language processing technique, fine-grained cutting and subject extraction are carried out to enterprise's public sentiment data, for carriage
It is covered by the more details of hot spot, the content tendency of user in hot spot of public opinions is more comprehensively analyzed, for negative information
The fineness of judgement has better grasp.
The application, based on the data collection of the whole network to the relevant public opinion information of enterprise, overcomes under the completely new public opinion environment
The drawbacks of enterprise is by manually collecting the method inefficiency of information in the past, accuracy heavy dependence knowledge experience, by big
Data and semantic analysis technology, are realized using computerized algorithm, greatly promote speed, efficiency and its scene on probation.
Preferably, negative emotions article is clustered, generates similar article group, determine starting letter of similar article group
Source, specifically: negative emotions article is clustered, similar article group is generated, when being issued according to the article in similar article group
Between determine starting information source.
Preferably, mining multi-dimensional data is carried out to the account in hostility account group, generates Source Tracing as a result, specific
Are as follows: by excavating the running individual of account and article, integrate owned enterprise/tissue, association main body and contact method；Pass through excavation
Certification main body, registered enterprise and the affiliated enterprise of account, integrate hostility Enterprise Lists；Pass through the financing and investment row of hostility enterprise
For, the superior and the subordinate's business connection, capital system belonging to hostility enterprise is traced, pass through that capital ties excavate between hostility enterprise inherent closes
System；By connecting each other between account and business organization, the hostility network map of enterprise is constructed；By under account and enterprise
Belong to the dispatch of account history to be recalled, the hostility information and direction in history dispatch is extracted, to each capital system, organizations and account
Number whole hostility degree compare and analyze.
By organization's relationship of excavation hostility account behind, capital ties and it is associated with main body, from surface layer data mining
To analysis of overall importance, various dimensions Source Tracing is carried out to " black public relations " phenomenon, judgment basis has enough ranges and certain journey
The depth of degree substantially increases the science and reasonability of result.
In addition, the application greatly expands the sample data of analysis by big data technology, acquisition and analysis mass data
And case, a large amount of cases of historical accumulation are made full use of, for each side's region feature of user content tendency and enterprise's Public Opinion Transmission
It is excavated, model is more scientific rationally, and analysis result is continuously available improvement, and reaches certain accuracy.
Second aspect, as shown in Fig. 2, the embodiment of the present application provides a kind of network public opinion Source Tracing device, comprising:
Extraction module 21 extracts negative emotions article for carrying out emotion attribute identification to acquisition public feelings information；
Starting information source determining module 22 generates similar article group, determines similar for clustering to negative emotions article
Starting information source of article group；
Hostility account group generation module 23, it is raw for extracting the account that publication amount is more than preset threshold from starting information source
At hostility account group；
Result-generation module 24, for carrying out mining multi-dimensional data to the account in hostility account group, generation is traced to the source point
Analyse result.
It preferably, further include acquisition module 25, for acquiring the relevant the whole network public sentiment of target keyword by reptile instrument
Information, target keyword include at least one of brand names, senior executive, product and project.
Preferably, in extraction module 21: emotion attribute identification is carried out to acquisition public feelings information, extracts negative emotions article,
Specifically: emotion attribute identification is carried out to acquisition public feelings information by natural language processing, extracts negative emotions article.
The third aspect, the embodiment of the present application provide a kind of terminal, comprising: one or more processors, one or more
Memory；One or more of memories are coupled with one or more of processors, and one or more of memories are used
In storage computer program code, the computer program code includes computer instruction, when one or more of processors
When executing the computer instruction, the terminal executes such as above-mentioned network public opinion Source Tracing method.
Above-mentioned memory can be read-only memory (read-only memory, ROM) or can store static information and refer to
The other kinds of static storage device enabled, random access memory (random access memory, RAM) or can store
The other kinds of dynamic memory of information and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory
(electrically erasable programmable read-only memory, EEPROM), CD-ROM (compact
Disc read-only memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, light
Dish, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or
Store have instruction or data structure form desired program code and can by any other medium of computer access, but
It is without being limited thereto.Memory, which can be, to be individually present, and is connected by bus with processor.Memory can also be integrated with processor
Together.
Wherein, memory is used to store the application code for executing application scheme, and execution is controlled by processor.
Processor is for executing the application code stored in memory, to realize the function in this patent method.
In the concrete realization, as one embodiment, processor may include one or more CPU.
In the concrete realization, as one embodiment, which may include multiple processors.It is every in these processors
One can be monokaryon (single-CPU) processor, be also possible to multicore (multi-CPU) processor.Here
Processor can refer to one or more equipment, circuit, and/or the processing for handling data (such as computer program instructions)
Core.
Fourth aspect, the embodiment of the present application provide computer storage medium, store computer instruction thereon, when the meter
When the instruction of calculation machine is run at the terminal, so that the terminal executes such as above-mentioned network public opinion Source Tracing method.
In conjunction with attached drawing, the embodiments of the present invention are described in detail above, but the present invention is not limited to described implementations
Mode.For a person skilled in the art, in the case where not departing from the principle of the invention and spirit, to these embodiments
A variety of change, modification, replacement and modification are carried out, are still fallen in protection scope of the present invention.
Claims (10)
1. a kind of network public opinion Source Tracing method characterized by comprising
Emotion attribute identification is carried out to acquisition public feelings information, extracts negative emotions article；
The negative emotions article is clustered, similar article group is generated, determines starting information source of the similar article group；
The account that publication amount is more than preset threshold is extracted from starting information source, generates hostility account group；
Mining multi-dimensional data is carried out to the account in the hostility account group, generates Source Tracing result.
2. network public opinion Source Tracing method according to claim 1, which is characterized in that carry out feelings to acquisition public feelings information
Feel Attribute Recognition, before extracting negative emotions article, further comprises the steps of: and the relevant the whole network of target keyword is acquired by reptile instrument
Public feelings information, the target keyword include at least one of brand names, senior executive, product and project.
3. network public opinion Source Tracing method according to claim 1, which is characterized in that described pair of acquisition public feelings information into
Market sense Attribute Recognition extracts negative emotions article, specifically: emotion is carried out to acquisition public feelings information by natural language processing
Attribute Recognition extracts negative emotions article.
4. network public opinion Source Tracing method according to claim 1, which is characterized in that described to the negative emotions text
Zhang Jinhang cluster, generates similar article group, determines starting information source of the similar article group, specifically: to the negative emotions
Article is clustered, and similar article group is generated, and determines starting information source according to the article issuing time in the similar article group.
5. network public opinion Source Tracing method according to claim 1, which is characterized in that described to the hostility account group
In account carry out mining multi-dimensional data, generate Source Tracing as a result, specifically: pass through the fortune for excavating the account and article
Make individual, integrates owned enterprise/tissue, association main body and contact method；By the certification main body, the registration enterprise that excavate the account
Industry and affiliated enterprise integrate hostility Enterprise Lists；It is closed by the financing of the hostility enterprise and investment behavior, enterprise, the superior and the subordinate
System, traces capital system belonging to the hostility enterprise, excavates the internal relation between the hostility enterprise by capital ties；Pass through
Connecting each other between the account and business organization constructs the hostility network map of enterprise；By to the account and enterprise
The dispatch of subordinate's account history is recalled, and hostility information and direction in the history dispatch is extracted, to each capital system, tissue group
Body and the whole hostility degree of account compare and analyze.
6. a kind of network public opinion Source Tracing device characterized by comprising
Extraction module extracts negative emotions article for carrying out emotion attribute identification to acquisition public feelings information；
Starting information source determining module generates similar article group, determines the phase for clustering to the negative emotions article
Like starting information source of article group；
Hostility account group's generation module is generated for extracting the account that publication amount is more than preset threshold from starting information source
Hostility account group；
Result-generation module generates Source Tracing for carrying out mining multi-dimensional data to the account in the hostility account group
As a result.
7. network public opinion Source Tracing device according to claim 6, which is characterized in that further include acquisition module, be used for
Acquire the relevant the whole network public feelings information of target keyword by reptile instrument, the target keyword include brand names, senior executive,
At least one of product and project.
8. network public opinion Source Tracing device according to claim 6, which is characterized in that in the extraction module: to adopting
Collect public feelings information and carry out emotion attribute identification, extracts negative emotions article, specifically: by natural language processing to acquisition public sentiment
Information carries out emotion attribute identification, extracts negative emotions article.
9. a kind of terminal characterized by comprising one or more processors, one or more memories；It is one or more
A memory is coupled with one or more of processors, and one or more of memories are for storing computer program generation
Code, the computer program code includes computer instruction, when one or more of processors execute the computer instruction
When, the terminal executes network public opinion Source Tracing method as described in any one in claim 1-5.
10. a kind of computer storage medium, which is characterized in that including computer instruction, when the computer instruction at the terminal
When operation, so that the terminal executes network public opinion Source Tracing method as described in any one in claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538471.0A CN110427549A (en) | 2019-06-20 | 2019-06-20 | A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538471.0A CN110427549A (en) | 2019-06-20 | 2019-06-20 | A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110427549A true CN110427549A (en) | 2019-11-08 |
Family
ID=68408792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538471.0A Withdrawn CN110427549A (en) | 2019-06-20 | 2019-06-20 | A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110427549A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046085A (en) * | 2019-12-19 | 2020-04-21 | 南京医睿科技有限公司 | Data source tracing processing method and device, medium and equipment |
| CN111784492A (en) * | 2020-07-10 | 2020-10-16 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method, device, electronic equipment and storage medium |
| CN112000866A (en) * | 2020-08-05 | 2020-11-27 | 杭州安恒信息技术股份有限公司 | Internet data analysis method, device, electronic device and medium |
| CN112395539A (en) * | 2020-11-26 | 2021-02-23 | 格美安(北京)信息技术有限公司 | Public opinion risk monitoring method and system based on natural language processing |
| CN112559845A (en) * | 2020-12-23 | 2021-03-26 | 北京清博大数据科技有限公司 | Method and system for identifying identity and motivation of atypical media account |
| CN113535813A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN113918794A (en) * | 2021-12-13 | 2022-01-11 | 宝略科技(浙江)有限公司 | Enterprise network public opinion benefit analysis method, system, electronic equipment and storage medium |
-
2019
- 2019-06-20 CN CN201910538471.0A patent/CN110427549A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046085A (en) * | 2019-12-19 | 2020-04-21 | 南京医睿科技有限公司 | Data source tracing processing method and device, medium and equipment |
| CN111046085B (en) * | 2019-12-19 | 2023-04-28 | 医渡云（北京）技术有限公司 | Data tracing processing method and device, medium and equipment |
| CN111784492A (en) * | 2020-07-10 | 2020-10-16 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method, device, electronic equipment and storage medium |
| CN112000866A (en) * | 2020-08-05 | 2020-11-27 | 杭州安恒信息技术股份有限公司 | Internet data analysis method, device, electronic device and medium |
| CN112000866B (en) * | 2020-08-05 | 2024-03-26 | 杭州安恒信息技术股份有限公司 | Internet data analysis method, device, electronic device and medium |
| CN112395539A (en) * | 2020-11-26 | 2021-02-23 | 格美安(北京)信息技术有限公司 | Public opinion risk monitoring method and system based on natural language processing |
| CN112395539B (en) * | 2020-11-26 | 2021-12-17 | 格美安(北京)信息技术有限公司 | Public opinion risk monitoring method and system based on natural language processing |
| CN112559845A (en) * | 2020-12-23 | 2021-03-26 | 北京清博大数据科技有限公司 | Method and system for identifying identity and motivation of atypical media account |
| CN113535813A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN113535813B (en) * | 2021-06-30 | 2023-07-28 | 北京百度网讯科技有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN113918794A (en) * | 2021-12-13 | 2022-01-11 | 宝略科技(浙江)有限公司 | Enterprise network public opinion benefit analysis method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427549A (en) | A kind of network public opinion Source Tracing method, apparatus, terminal and storage medium | |
| CN108121795B (en) | User behavior prediction method and device | |
| CN108595583A (en) | Dynamic chart class page data crawling method, device, terminal and storage medium | |
| CN103823844B (en) | Question forwarding system and question forwarding method on the basis of subjective and objective context and in community question-and-answer service | |
| CN106408249A (en) | Resume and position matching method and device | |
| CN109684481A (en) | The analysis of public opinion method, apparatus, computer equipment and storage medium | |
| CN106936781A (en) | A kind of decision method and device of user's operation behavior | |
| CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
| CN108108821A (en) | Model training method and device | |
| CN109189991A (en) | Repeat video frequency identifying method, device, terminal and computer readable storage medium | |
| CN109583738A (en) | A kind of device and method for bond risk control | |
| CN106919661A (en) | A kind of affective style recognition methods and relevant apparatus | |
| CN110309114B (en) | Method and device for processing media information, storage medium and electronic device | |
| CN106779278A (en) | The evaluation system of assets information and its treating method and apparatus of information | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN110321466A (en) | A kind of security information duplicate checking method and system based on semantic analysis | |
| Chhabra et al. | Dynamics of edit war sequences in Wikipedia | |
| CN103593355A (en) | User original content recommending method and device | |
| CN109711849B (en) | Ether house address portrait generation method and device, electronic equipment and storage medium | |
| Pajo et al. | Fast lead user identification framework | |
| CN110069686A (en) | User behavior analysis method, apparatus, computer installation and storage medium | |
| CN109508557A (en) | A kind of file path keyword recognition method of association user privacy | |
| CN107527289A (en) | A kind of investment combination industry distribution method, apparatus, server and storage medium | |
| CN111046281A (en) | Hot topic construction method and device | |
| CN111325422A (en) | Work order distribution method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191108 |