CN109635283B - Public safety event pre-warning method based on mining citizen complaint text - Google Patents
Public safety event pre-warning method based on mining citizen complaint text Download PDFInfo
- Publication number
- CN109635283B CN109635283B CN201811414512.7A CN201811414512A CN109635283B CN 109635283 B CN109635283 B CN 109635283B CN 201811414512 A CN201811414512 A CN 201811414512A CN 109635283 B CN109635283 B CN 109635283B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- word
- information
- operation range
- industry
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005065 mining Methods 0.000 title claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims description 49
- 230000008569 process Effects 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 abstract description 16
- 238000004458 analytical method Methods 0.000 abstract description 9
- 230000009849 deactivation Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a public safety event pre-warning method based on mining citizen complaint texts, which mainly comprises the steps of constructing an enterprise name word bank and an industry operation range word bank through text analysis to form a custom dictionary; segmenting the content of the citizen complaint text by using a custom dictionary, then carrying out fuzzy matching on enterprise names and secondary association of an industry operating range, finally matching the public safety events with the enterprises, carrying out enterprise ranking according to the number of the citizen complaint records matched by the enterprises to form a high-risk enterprise list, and taking corresponding early warning measures. The data of the invention specifically utilizes citizen complaint text information, does not need to specially arrange corresponding monitoring equipment, has wide information source channels, and can carry out effective incident early warning of public safety incidents.
Description
Technical Field
The patent relates to the technical field of public safety, in particular to a public safety event advance early warning method based on mining of citizen complaint texts.
Background
Public safety refers to a state in which the safety of people's lives and properties is not threatened, and the order, benefits and values related to the public field can normally operate according to the inherent logic of public life. Public safety events easily cause great negative effects on social order and social stability, so public safety emergencies are effectively predicted and early warned in time, and great practical significance is achieved for ensuring stable social operation.
The traditional public safety event early warning mechanism is established through a monitoring system, but the public safety monitoring system cannot automatically judge dangerous information, and an on-duty person needs to check the monitoring system in real time to find the dangerous information, so that great labor cost is needed, and real-time early warning cannot be really realized.
In view of the above pain points, chinese patent application CN106780235A discloses a social security incident monitoring and tracing method, which comprises: establishing a prediction early warning database, a case library, a pre-case library and an expert evaluation library; setting index data of an emergent safety event; carrying out model calculation on the data newly introduced into the prediction and early warning database, analyzing and predicting the trend of the social security events, and displaying the prediction result by adopting a graph; and generating an early warning grade according to the trend of the predicted social security event, and providing an auxiliary decision for a decision maker. However, the public safety monitoring system related to the technical scheme is only a video monitoring system, and most public safety events can make unexpected sounds, such as explosion, help calling of crime victims and the like.
Further, for example, chinese patent application CN102938187A discloses a public security incident detection system, which relates to the technical field of public security incident information monitoring. The system comprises sensor and control center platform two parts, and wherein the sensor includes: physical sensing devices such as a fire detector, a sound (explosion) sensor, a video sensor and the like are used for acquiring road and peripheral information thereof; the control center platform comprises a node controller which is connected with the sensor and the processing circuit thereof, completes signal acquisition and discrimination and sends out early warning signals and other control instructions. However, the technical scheme needs to specially arrange corresponding monitoring equipment, and the channel is limited.
At present, the public safety monitoring systems all need to be independently wired, so that the public safety monitoring systems are only wired in key zones of densely populated cities, and the public safety monitoring systems are difficult to be wired in suburban areas and remote road sections with high crimes and accidents. Meanwhile, the awareness of rights maintenance of citizens is increased, the complaint amount is basically kept rising in recent years, and the complaint content of citizens relates to various aspects such as personal consumption, food safety and environmental protection. The current analysis and research on the complaint content of the user is widely applied to the service industry, the financial industry and other industries to improve the satisfaction degree and the viscosity of the user. For the public safety field, by means of analysis and mining of complaint contents of users, the method omits to arrange corresponding sensors in advance and is convenient for pertinently establishing a prior early warning mechanism.
For example, chinese patent application CN106529804A discloses a complaint early warning monitoring analysis method based on text mining technology, which includes: a text data normalization step, namely converting the input text data into a normalized data mode of a uniform rule; and a step of normalized data analysis and early warning, which is to analyze a normalized data mode by establishing a complaint analysis grade clustering model, divide complaint risk grades according to clustering results and send out early warning according to the grade of the risk. But the technical scheme focuses on emotion analysis of feedback texts of clients.
Existing complaint handling implementations are passive, inefficient, and delayed. The processing content of the complaint handling personnel at the upper level has little help to the complaint handling personnel at the lower level, each layer of complaint handling personnel needs to carefully read the complaint text content and carry out corresponding processing, so that the problems of repeated labor and low efficiency are caused, and the complaint reply quality of users is also uneven according to different service mastering degrees of the complaint handling personnel, so that the satisfaction degree of the users is reduced. The manual analysis has a large number of subjective factors and cannot be used as the basis for establishing an authoritative public safety early warning mechanism.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a public safety event advance early warning method based on mining of citizen complaint texts, which utilizes the information of the citizen complaint texts to carry out early warning, does not need to specially arrange corresponding monitoring equipment, has wide source channels and can carry out effective event early warning of the public safety events.
In order to achieve the purpose, the invention adopts the following technical scheme:
a public safety event advance early warning method based on mining of citizen complaint texts comprises the following steps:
s1, obtaining original citizen complaint text content and basic information of an enterprise, wherein the basic information comprises enterprise full-name information, attribution industry information and management range information;
s2, performing word segmentation on all the acquired enterprise full-name information;
s3, aiming at the word segmentation result obtained in the step S2, extracting high-frequency words in the word segmentation result, and establishing an enterprise full-scale information stop word bank and an enterprise full-scale information self-defined dictionary according to the high-frequency words;
s4, segmenting all enterprise full-name information acquired in the step S1, and utilizing the enterprise full-name information disabling word library and the enterprise full-name information self-defined dictionary established in the step S3 to reduce noise to construct an enterprise name word library;
s5, according to the attribution industry information of the enterprises, the operation range information of each industry is summarized and is arranged into a document;
s6, segmenting the enterprise operation range information in the document obtained in the step S5 by using a segmentation packet, and establishing an enterprise operation range stop word bank and an enterprise operation range custom dictionary;
s7, performing word segmentation again on the operation range information of the enterprises in the document obtained in the step S5, and denoising the result of the word segmentation again by using the enterprise operation range stop word bank and the enterprise operation range self-determined dictionary obtained in the step S6 to obtain a word segmentation result of the operation range information of each industry;
s8, extracting keywords from the word segmentation result of the operation range information of each industry, and constructing an industry operation range word bank by using the extracted keywords;
s9, segmenting the original citizen complaint text content obtained in the step S1 by using the enterprise name word bank obtained in the step S4 and the industry management range word bank obtained in the step S8 as a segmentation custom dictionary to obtain a segmentation text;
s10, carrying out fuzzy name matching on the word segmentation text obtained in the step S9 and the enterprise name word bank constructed in the step S4;
s11, performing secondary association of the industry operation range based on the fuzzy name matching result obtained in the step S10, and determining associated enterprises;
and S12, ranking the enterprises according to the number of the citizen complaint text contents corresponding to the associated enterprises to form a high-risk enterprise list, and taking related high-level early warning measures for the high-risk enterprises.
Further, in step S2, the Chinese ending segmentation packet is used in an accurate mode for segmentation.
Further, in step S8, the TF-IDF is used to calculate the weight of each word in the word segmentation result of the business scope information of each industry, and extract keywords.
Further, in step S10, the process of fuzzy name matching is:
firstly, performing low-frequency word judgment on each word in the word segmentation text, if the number of enterprises corresponding to the word in an enterprise name word bank is less than a set value k, recording the word as a low-frequency word, and directly using the enterprise corresponding to the low-frequency word as a fuzzy name matching result; meanwhile, if an intersection exists between the enterprise sets corresponding to the non-low-frequency words, the enterprises in the intersection are also used as fuzzy name matching results.
Further, the specific process of step S11 is:
for each enterprise in the fuzzy name matching result, tracing the attributive industry information of the enterprise, acquiring the key words of the corresponding operation range through an industry operation range word bank, judging the number of the acquired key words of the operation range appearing in the content of the citizen complaint text, and recording the number as a co-occurrence number; and finally, selecting the enterprise corresponding to the maximum number of the co-occurrences as the final associated enterprise of the complaint text.
The invention has the beneficial effects that:
1. in the invention, for the acquisition of public safety event sources, the text information of the citizen complaints is adopted, the corresponding monitoring equipment is not required to be specially arranged, and the citizen complaints come from various channels such as labor supervision departments, traffic bureaus, market supervision departments and the like, and the source channels are wide.
2. In the method, the analysis of the complaint text focuses on the identification of complaint subjects in the complaint text, the matching model is based on the Boolean expression, the correlation of the text is based on whether the Boolean expression is satisfied, if the keywords appear in the text, the expression is 1, otherwise, the expression is 0. On the basis of the model, methods such as word segmentation, re-matching and the like are introduced to the text, so that the matching efficiency and precision are improved.
Drawings
FIG. 1 is a general flow diagram of a method in an embodiment of the invention;
FIG. 2 is a diagram illustrating an example of a public safety event correlation process according to an embodiment of the present invention;
Detailed Description
The present invention will be further described with reference to the accompanying drawings, and it should be noted that the present embodiment is based on the technical solution, and the detailed implementation and the specific operation process are provided, but the protection scope of the present invention is not limited to the present embodiment.
As shown in fig. 1-2, a public safety event pre-warning method based on mining of a citizen complaint text comprises the following steps:
s1, obtaining original citizen complaint text content and basic information of an enterprise, wherein the basic information comprises enterprise full-name information, attribution industry information and management range information;
s2, segmenting all the acquired enterprise full-name information by using a segmentation packet; in this embodiment, in this step, the precise mode of the chinese ending participle packet is used for participling.
S3, aiming at the word segmentation result obtained in the step S2, extracting high-frequency words in the word segmentation result, and establishing an enterprise full-scale information stop word bank and an enterprise full-scale information self-defined dictionary according to the high-frequency words;
specifically, high-frequency words 20 before the ranking can be extracted, words with high occurrence frequency but without great meaning, such as "shares, limited words, companies" and the like, are added into an enterprise full-name information stop word library, after stop words are filtered out, high-frequency words 40 before the ranking, such as "information, science and technology, software" and the like, representing industry attributes are screened out again and extracted, and the words are added into an enterprise full-name information self-defined dictionary;
s4, segmenting all enterprise full-name information obtained in the step S1, and utilizing the enterprise full-name information disabling word library and the enterprise full-name information self-defining dictionary established in the step S3 to reduce noise to establish an enterprise name word library;
s5, according to the attribution industry information of the enterprises, the operation range information of each industry is summarized and is arranged into a document;
s6, segmenting the business range information of the enterprise in the document obtained in the step S5 by using a segmentation packet, and establishing an enterprise business range stop word bank and an enterprise business range custom dictionary;
similarly, words with high occurrence frequency but little meaning in the word segmentation result can be added into the enterprise operation range deactivation word bank, and after the deactivation words are filtered out, the high-frequency words are screened out again and added into the enterprise operation range deactivation word bank.
S7, performing word segmentation on the business range information of the enterprises in the document obtained in the step S5 again, and denoising the result of the word segmentation again by using the enterprise business range stop word bank and the enterprise business range self-determined dictionary obtained in the step S6 to obtain a word segmentation result of the business range information of each industry, so that the word segmentation effect is improved;
specifically, chinese word segmentation is carried out on the operation range information documents of each industry by using the crust word segmentation bag, and noise reduction is carried out by utilizing an enterprise operation range stop word bank and an enterprise operation range self-defined dictionary;
and S8, extracting keywords from the word segmentation result of the operation range information of each industry, and constructing an industry operation range word bank by using the extracted keywords. In the embodiment, TF-IDF is adopted to calculate the weight of each participle in the participle result of the business range information of each industry, and keywords are extracted;
for example, for each industry, the top 20 words with the weight can be selected as the keywords of the business scope information of the industry, and the construction of the industry business scope word bank can be completed.
S9, segmenting the original citizen complaint text content acquired in the step S1 by using the enterprise name word bank acquired in the step S4 and the industry management range word bank acquired in the step S8 as a segmentation custom dictionary to acquire a segmentation text;
specifically, the segmentation can be selected as a full mode of the ending segmentation, and all words appearing in the segmentation user-defined dictionary are scanned out. For example, if both the words "hip-hop game" and "hakuai" exist in the customized dictionary, the word "hip-hop game" can be split into two words "hip-hop game" and "hakuai".
And S10, carrying out fuzzy name matching on the word segmentation text obtained in the step S9 and the enterprise name word bank constructed in the step S4.
Specifically, the fuzzy name matching process includes: firstly, low-frequency word judgment is carried out on each word in the word segmentation text, if the number of enterprises corresponding to the word in the enterprise name word bank is smaller than a set value k, the words are recorded as low-frequency words, the enterprises corresponding to the low-frequency words are directly used as fuzzy name matching results, and k =10 in practical operation. Meanwhile, if an intersection exists between the enterprise sets corresponding to the non-low-frequency words, the enterprises in the intersection are also used as fuzzy name matching results.
And S11, performing secondary association of the industry operation range based on the fuzzy name matching result obtained in the step S10, and determining the associated enterprises.
Specifically, for each enterprise in the fuzzy name matching result, the affiliated industry information of the enterprise is traced, the keywords of the corresponding operation range are obtained through an industry operation range word bank, the number of the obtained keywords of the operation range appearing in the content of the citizen complaint text is judged, and the number is recorded as the co-occurrence number; and finally, selecting the enterprise corresponding to the maximum number of the co-occurrences as the final associated enterprise of the complaint text.
And S12, carrying out enterprise ranking (descending order) according to the number of the citizen complaint text contents corresponding to the associated enterprises to form a high-risk enterprise list, and taking relevant high-level early warning measures. For example, the top 100 enterprises in descending order are taken out to form a high-risk enterprise list, and corresponding early warning measures are taken for the related high-risk enterprises.
In the method, for the acquisition of the public safety event source, the text information of the citizen complaints is adopted, the corresponding monitoring equipment is not required to be specially arranged, and the information of the citizen complaints comes from various channels such as labor supervision departments, traffic bureaus, market supervision departments and the like. In the method, the analysis of the complaint texts focuses on the identification of complaint subjects in the complaint texts.
Various corresponding changes and modifications can be made by those skilled in the art based on the above technical solutions and concepts, and all such changes and modifications should be included in the protection scope of the present invention.
Claims (5)
1. A public safety event advance early warning method based on mining of citizen complaint texts is characterized by comprising the following steps:
s1, obtaining original citizen complaint text content and basic information of an enterprise, wherein the basic information comprises enterprise full-name information, attribution industry information and management range information;
s2, performing word segmentation on all the acquired enterprise full-name information;
s3, aiming at the word segmentation result obtained in the step S2, extracting high-frequency words in the word segmentation result, and establishing an enterprise full-name information stop word bank and an enterprise full-name information custom dictionary according to the high-frequency words;
s4, segmenting all enterprise full-name information obtained in the step S1, and utilizing the enterprise full-name information disabling word library and the enterprise full-name information self-defining dictionary established in the step S3 to reduce noise to establish an enterprise name word library;
s5, according to the attribution industry information of the enterprises, the operation range information of each industry is summarized and is arranged into a document;
s6, segmenting the enterprise operation range information in the document obtained in the step S5 by using a segmentation packet, and establishing an enterprise operation range stop word bank and an enterprise operation range custom dictionary;
s7, performing word segmentation again on the operation range information of the enterprises in the document obtained in the step S5, and denoising the result of the word segmentation again by using the enterprise operation range stop word bank and the enterprise operation range self-determined dictionary obtained in the step S6 to obtain a word segmentation result of the operation range information of each industry;
s8, extracting keywords from the word segmentation result of the operation range information of each industry, and constructing an industry operation range word bank by using the extracted keywords;
s9, segmenting the original citizen complaint text content acquired in the step S1 by using the enterprise name word bank acquired in the step S4 and the industry management range word bank acquired in the step S8 as a segmentation custom dictionary to acquire a segmentation text;
s10, carrying out fuzzy name matching on the word segmentation text obtained in the step S9 and the enterprise name word bank constructed in the step S4;
s11, performing secondary association of the industry operation range based on the fuzzy name matching result obtained in the step S10, and determining associated enterprises;
and S12, ranking the enterprises according to the number of the citizen complaint text contents corresponding to the associated enterprises to form a high-risk enterprise list, and taking high-level early warning measures for the high-risk enterprises.
2. The method according to claim 1, wherein in step S2, the segmentation is performed using an exact model of chinese ending segmentation.
3. The method according to claim 1, wherein in step S8, TF-IDF is used to calculate the weight of each participle in the participle result of the business segment information of each industry, and keywords are extracted.
4. The method according to claim 1, wherein in step S10, the fuzzy name matching process is:
firstly, performing low-frequency word judgment on each word in a word segmentation text, if the number of enterprises corresponding to the word in an enterprise name word bank is less than a set value k, recording the word as a low-frequency word, and directly using the enterprise corresponding to the low-frequency word as a fuzzy name matching result; meanwhile, if an intersection exists between the enterprise sets corresponding to the non-low-frequency words, the enterprises in the intersection are also used as fuzzy name matching results.
5. The method according to claim 1, wherein the specific process of step S11 is:
for each enterprise in the fuzzy name matching result, tracing the attributive industry information of the enterprise, acquiring the key words of the corresponding operation range through an industry operation range word bank, judging the number of the acquired key words of the operation range appearing in the content of the citizen complaint text, and recording the number as a co-occurrence number;
and finally, selecting the enterprise corresponding to the maximum number of the co-occurrences as the final associated enterprise of the content of the citizen complaint text.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811414512.7A CN109635283B (en) | 2018-11-26 | 2018-11-26 | Public safety event pre-warning method based on mining citizen complaint text |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811414512.7A CN109635283B (en) | 2018-11-26 | 2018-11-26 | Public safety event pre-warning method based on mining citizen complaint text |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109635283A CN109635283A (en) | 2019-04-16 |
CN109635283B true CN109635283B (en) | 2022-10-14 |
Family
ID=66069122
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811414512.7A Active CN109635283B (en) | 2018-11-26 | 2018-11-26 | Public safety event pre-warning method based on mining citizen complaint text |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635283B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134779A (en) * | 2019-05-13 | 2019-08-16 | 极智(上海)企业管理咨询有限公司 | A kind of method of enterprise name processing |
CN110134759A (en) * | 2019-05-13 | 2019-08-16 | 极智(上海)企业管理咨询有限公司 | A method of obtaining the trade information of enterprise |
CN110308244B (en) * | 2019-06-26 | 2022-03-04 | 深圳市宇驰检测技术股份有限公司 | Air monitoring and early warning method and system of unmanned aerial vehicle and storage medium |
CN111046144A (en) * | 2019-12-17 | 2020-04-21 | 深圳前海环融联易信息科技服务有限公司 | Intelligent matching method and device, computer equipment and storage medium |
CN111241240B (en) * | 2020-01-08 | 2023-08-15 | 中国联合网络通信集团有限公司 | Industry keyword extraction method and device |
CN111967249A (en) * | 2020-07-24 | 2020-11-20 | 南京网感至察信息科技有限公司 | Method for predicting potential risk of specific target entity from public information |
CN112101002B (en) * | 2020-09-15 | 2021-04-02 | 南京行者易智能交通科技有限公司 | Big data based case situation perception early warning method, measure recommendation method and device and terminal equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
CN104573016A (en) * | 2015-01-12 | 2015-04-29 | 武汉泰迪智慧科技有限公司 | System and method for analyzing vertical public opinions based on industry |
CN108108352A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of enterprise's complaint risk method for early warning based on machine learning Text Mining Technology |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8682032B2 (en) * | 2011-08-19 | 2014-03-25 | International Business Machines Corporation | Event detection through pattern discovery |
-
2018
- 2018-11-26 CN CN201811414512.7A patent/CN109635283B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
CN104573016A (en) * | 2015-01-12 | 2015-04-29 | 武汉泰迪智慧科技有限公司 | System and method for analyzing vertical public opinions based on industry |
CN108108352A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of enterprise's complaint risk method for early warning based on machine learning Text Mining Technology |
Also Published As
Publication number | Publication date |
---|---|
CN109635283A (en) | 2019-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109635283B (en) | Public safety event pre-warning method based on mining citizen complaint text | |
CN109615116A (en) | A kind of telecommunication fraud event detecting method and detection system | |
US20140172497A1 (en) | Apparatus and method for managing risk based on prediction on social web media | |
CN110417721A (en) | Safety risk estimating method, device, equipment and computer readable storage medium | |
CN109086808B (en) | Traffic high-risk personnel identification method based on random forest algorithm | |
CN113887219B (en) | Hot line public opinion identification and early warning method and system for competent department | |
CN110826852B (en) | Risk assessment method and system for forced isolation drug-relief personnel | |
CN112765485A (en) | Network social event prediction method, system, terminal, computer device and medium | |
CN111159272A (en) | Data quality monitoring and early warning method and system based on data warehouse and ETL | |
CN111898385A (en) | Earthquake disaster assessment method and system | |
CN110727805A (en) | Community knowledge graph construction method and system | |
CN117057611A (en) | Self-building house security risk identification method and system | |
Kabir et al. | IoT, Big Data and AI Applications in the Law Enforcement and Legal System: A Review | |
Baqir et al. | Evaluating the performance of hierarchical clustering algorithms to detect spatio-temporal crime hot-spots | |
CN107391712A (en) | A kind of network public opinion trend prediction analysis method | |
Kabbani et al. | What do riders say and where? The detection and analysis of eyewitness transit tweets | |
CN113642926A (en) | Method and device for risk early warning, electronic equipment and storage medium | |
CN111080005B (en) | Support vector machine-based public security risk early warning method and system | |
KR102242317B1 (en) | Qualitative system for determining fake news, qualitative method for determining fake news, and computer-readable medium having a program recorded therein for executing the same | |
CN111813922B (en) | High-temperature event detection method and system based on microblog text data | |
CN113723811B (en) | Equipment maintenance unit assessment method and device based on machine learning and electronic equipment | |
Dong et al. | [Retracted] Railway Traffic Emergency Management Relying on Image Recognition Technology in the Context of Big Data | |
Girard et al. | Identifying Locations of Drug Overdose in Las Vegas to Implement the Cardiff Violence Prevention Model | |
CN111324656B (en) | Personnel management method and related equipment | |
Shetty et al. | SafeRoute: Analysing Online Websites To Indicate Crime Zones Using Machine Learning And Suggest Safe Route |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |