CN112131392A - Public health epidemic situation early warning method and system based on knowledge graph - Google Patents
Public health epidemic situation early warning method and system based on knowledge graph Download PDFInfo
- Publication number
- CN112131392A CN112131392A CN202010763919.1A CN202010763919A CN112131392A CN 112131392 A CN112131392 A CN 112131392A CN 202010763919 A CN202010763919 A CN 202010763919A CN 112131392 A CN112131392 A CN 112131392A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- information
- public health
- early warning
- health epidemic
- 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
Images
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a public health epidemic situation early warning system and method based on knowledge map, belonging to the technical field of computer network, the key point of the technical scheme is that the method comprises the following steps: step S1, constructing an early warning model based on the public health epidemic situation knowledge graph; step S2, acquiring entities and relations needed by the public health epidemic situation knowledge graph; step S3, extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technology, and accessing the extracted knowledge into a public health epidemic situation knowledge map for use; step S4, knowledge reasoning, through the existing knowledge organization, the relationship between the entities obtained is excavated and reasoned, and the information authenticity is obtained through a weight algorithm; public health epidemic early warning system based on knowledge map includes: the system comprises a knowledge map and early warning model module, a knowledge acquisition module, a knowledge extraction module and a knowledge reasoning and analyzing module. The invention can conveniently and efficiently judge the authenticity of the public health epidemic situation.
Description
Technical Field
The invention relates to the technical field of computer networks, in particular to a public health epidemic situation early warning method and system based on a knowledge graph.
Background
In recent years, increasingly abusive prevalence of unknown diseases and important infectious diseases has made a serious threat to human life safety, and especially in recent years, outbreaks of influenza A (H1N 1) and avian influenza infection (H7N 9) of people have made alarms. Since 2006, emergency mechanisms, disease prevention and control systems, medical treatment and cure systems and health supervision and law enforcement systems for emergent public health incidents are gradually built in China, and many defects of public health information systems in China are made up. The public health epidemic situation monitoring system can timely and effectively monitor the sudden public health epidemic situation in time, and has important significance for guaranteeing the life health of people.
In recent years, along with popularization and application of the internet and big data, public health epidemic situation early warning systems based on computers and network information technologies are gradually used for medical purposes. The current public health epidemic situation early warning system can refer to a Chinese utility model patent document with the publication number of CN206332770U, and discloses an epidemic situation monitoring early warning platform, which comprises an epidemic situation data acquisition terminal, a switch, a server terminal and a monitoring terminal; epidemic situation data acquisition terminal the server end with monitor terminal respectively with the switch communication is connected, monitor terminal's quantity is 1 or a plurality ofly, epidemic situation data acquisition terminal's quantity is a plurality of.
The invention discloses a method and a system for monitoring and analyzing flu epidemic situation facing microblog data, which are disclosed by Chinese patent invention with an authorized public number of CN103593462B, and the method for monitoring and analyzing the flu epidemic situation facing microblog data comprises the following steps: acquiring a part of microblogs as a training microblog set; marking each microblog in the training microblog set; obtaining a microblog text lexical item set of a training microblog set; obtaining a microblog text original feature lexical item set of a training microblog set; obtaining a feature lexical dictionary; vectorizing the characteristics; training the feature vector to obtain an SVM classifier; acquiring the rest microblogs as a test microblog set; obtaining a microblog text lexical item set of a test microblog set; obtaining a microblog text original characteristic lexical item set of a test microblog set; vectorizing the characteristics; automatically classifying each microblog in the test microblog set by the SVM classifier; visualizing the classification result to monitor and analyze the influenza epidemic; the system comprises an acquisition module, a marking module, an initialization module, a feature extraction module, a feature selection module, a feature vectorization module, a training module, a classification module and a visualization module which are electrically connected with one another.
The existing public health epidemic situation early warning system carries out information retrieval through the internet, but the information quantity of collecting is many and complicated, needs the staff later stage to carry out statistical analysis, and then just can judge the authenticity of public health epidemic situation, consumes the manpower, and work efficiency is low.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the public health epidemic situation early warning system based on the knowledge graph, which adopts the knowledge graph technology and can conveniently and efficiently judge the authenticity of the public health epidemic situation.
The above object is achieved by the following technical scheme: a public health epidemic situation early warning method based on a knowledge graph comprises the following steps:
step S1, constructing an early warning model based on the public health epidemic situation knowledge graph;
step S2, acquiring entities and relations needed by the public health epidemic situation knowledge graph;
step S3, extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technology, and accessing the extracted knowledge into a public health epidemic situation knowledge map for use;
and step S4, knowledge reasoning, wherein the relationship between the obtained entities is explored and reasoned through the existing knowledge mechanism, and the authenticity of the information is obtained through a weight algorithm.
By adopting the technical scheme, the public health epidemic situation knowledge graph is established, and then the relation between the obtained entities is excavated and reasoned by acquiring the entities and the relation required by the public health epidemic situation knowledge graph, and the authenticity of the public health epidemic situation is judged conveniently and efficiently by obtaining the authenticity of the information through a weight algorithm.
The invention is further configured to: step S1 includes:
step S11, constructing public health epidemic situation knowledge map triplets, namely entities and relations;
step S12, establishing an early warning model based on knowledge graph entities and relations;
and step S13, collecting input and feedback data, and correcting the early warning model.
By adopting the technical scheme, the early warning model is established based on the knowledge map entity and relation through the set public health epidemic situation knowledge map triple, and the early warning model is corrected by collecting input and feedback data, so that the early warning model is more accurate, and information can be screened in a wide and efficient manner through the early warning model.
The invention is further configured to: the entity information of the public health epidemic situation knowledge map triple comprises address information, unit information, occupation information and job title information of an information publisher.
By adopting the technical scheme, the information such as the address information, the unit information, the occupation information, the job title information and the like of the information publisher is collected, and the authenticity of the published information is judged through the information, so that the method is more accurate when the truth of the event is integrated.
The invention is further configured to: in step S4, the information distributor' S information distributor is examined by address information, unit information, career information, and title information of the distributor, and when the weight of the information distributor is lower than a set value, the current information is excluded.
By adopting the technical scheme, the issued information motivation of the information issuer is researched and judged through the address information, the unit information and the professional information of the issuer, and when the weight of the issued information motivation is lower than a set value, the current information is eliminated, so that the deviation sample can be timely and efficiently discharged, and the judgment on public health epidemic situations is more accurate.
The invention is further configured to: in step S4, f (x) = ∑ f (x)/N, and when f (x) > f (a), the current event information is determined to be a true event; wherein F (X) is event truth count; f (a) setting values for the degree of realism; (x) a weight value of the truth of a single piece of published information; n is a calculation proportionality coefficient, and is positively correlated with the number of times of information issuing.
By adopting the technical scheme, the truth of the event is judged by accumulating the truth weighted values of the single pieces of issued information and the magnitude of the accumulated values, and the calculation proportionality coefficient N is introduced when the event truth count F (X) is calculated, so that the influence of diffusion effect in the propaganda science on the event truth is reduced.
The invention also aims to provide a public health epidemic situation early warning system based on the knowledge graph, which adopts the knowledge graph technology and can conveniently and efficiently judge the authenticity of the public health epidemic situation.
The above object is achieved by the following technical scheme: a public health epidemic early warning system based on knowledge graph includes: the knowledge graph modeling module is used for inputting the information, knowledge and relationship of the public health epidemic situation knowledge graph triples;
the input module is used for inputting information in the public health epidemic situation knowledge map triplets and basic words of the relationship;
the retrieval module is used for matching the information in the public health epidemic situation knowledge map triplets and the basic words of the relationship with the knowledge map triplets;
and the analysis module is used for carrying out weight calculation according to the matching result of the retrieval module to obtain a retrieval result.
By adopting the technical scheme, the public health epidemic situation knowledge map triple is established through the knowledge map modeling module, information in the public health epidemic situation knowledge map triple and basic words of the relation are input through the input module, therefore, the intelligent statistical association is carried out on related release information through the knowledge map technology, then the matching result of the retrieval module is subjected to weight calculation through the analysis module, the retrieval result is obtained, and the authenticity of public health epidemic situation events can be conveniently and efficiently judged.
The invention is further configured to: the public health epidemic situation knowledge graph publishing system further comprises a map display module (5) which is used for displaying and outputting the quantity and the geographical distribution of the published information according to the entities and the relations which are needed for obtaining the public health epidemic situation knowledge graph.
By adopting the technical scheme, the map display module is arranged, so that the quantity and the geographical distribution of the published information are displayed and output, and the statistical state of the published information can be visually checked.
In conclusion, the beneficial technical effects of the invention are as follows:
1. by establishing the public health epidemic situation knowledge graph and acquiring the entities and the relations required by the public health epidemic situation knowledge graph, the relation between the acquired entities is explored and inferred, and the authenticity of the information is obtained through a weight algorithm, so that the authenticity of the public health epidemic situation can be conveniently and efficiently judged.
2. The truth of the event is judged by accumulating the truth weighted values of the single pieces of issued information and the magnitude of the accumulated values, and a calculation proportion coefficient N is introduced when the truth count F (X) of the event is calculated, so that the influence of diffusion effect in the propaganda science on the truth of the event is reduced.
Drawings
FIG. 1 is a block diagram of steps of a public health epidemic early warning method based on a knowledge-graph;
FIG. 2 is a functional block diagram of a public health epidemic early warning system based on a knowledge-graph.
In the figure, 1, a knowledge graph and early warning model module; 2. a knowledge acquisition module; 3. a knowledge extraction module; 4. a knowledge reasoning and analysis module; 5. and a map display module.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1: a public health epidemic situation early warning method based on knowledge graph is disclosed, referring to FIG. 1, comprising the following steps: step S1, constructing an early warning model based on the public health epidemic situation knowledge graph; step S2, acquiring entities and relations needed by the public health epidemic situation knowledge graph; step S3, extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technology, and accessing the extracted knowledge into a public health epidemic situation knowledge map for use; and step S4, knowledge reasoning, wherein the relationship between the obtained entities is explored and reasoned through the existing knowledge mechanism, and the authenticity of the information is obtained through a weight algorithm.
Step S1 includes: step S11, constructing public health epidemic situation knowledge map triplets, namely entities and relations, wherein the entity information of the public health epidemic situation knowledge map triplets comprises address information, unit information, occupation information and job title information of an information publisher; step S12, establishing an early warning model based on knowledge graph entities and relations; and step S13, collecting input and feedback data, and correcting the early warning model. After the early warning model is preliminarily established, test data is input into the early warning model, the feedback of the test data is collected, and then the early warning model is corrected through input and feedback, so that the early warning model is more real and reliable.
And step S2, acquiring the entities and relations needed by the public health epidemic situation knowledge graph. The entities and the relations required by the public health epidemic situation knowledge graph are mainly obtained through two modes of active input and network retrieval. Report data mainly from each layer of health and epidemic prevention organizations, community transaction data and other publicly acquired data are actively input. And the network retrieval utilizes a crawler technology to capture and retrieve corresponding keywords.
And step S3, extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technologies, and accessing the extracted knowledge into the public health epidemic situation knowledge map for use. Knowledge elements such as entities, relationships, attributes and the like can be extracted from some published semi-structured and unstructured data through knowledge extraction technology. Through knowledge fusion, ambiguity between the referent items such as entities, relations and attributes and the fact objects can be eliminated, and a high-quality knowledge base is formed. The semantic analysis technology carries out matching connection on the associated words, so that the data retrieval can be more comprehensive and intelligent.
And step S4, knowledge reasoning, wherein the relationship between the obtained entities is explored and reasoned through the existing knowledge mechanism, the authenticity of the information is obtained through a weight algorithm, the information issuing motivation of the information issuer is researched and judged through the address information, the unit information, the occupation information and the job title information of the issuer, and the current information is excluded when the weight of the information issuing motivation is lower than a set value. In step S4, f (x) = ∑ f (x)/N, and when f (x) > f (a), the current event information is determined to be a true event; wherein F (X) is event truth count; f (a) setting values for the degree of realism; (x) a weight value of the truth of a single piece of published information; n is a calculation proportionality coefficient, and is positively correlated with the number of times of information issuing. The information issuing motivation of the information issuer is researched and judged through the address information, the unit information and the professional information of the issuer, when the weight of the information issuing motivation is lower than a set value, the current information is eliminated, and then a deviation sample can be timely and efficiently discharged, so that the judgment on public health epidemic situation events is more accurate. The truth of the event is judged by accumulating the truth weighted values of the single pieces of issued information and the magnitude of the accumulated values, and a calculation proportion coefficient N is introduced when the truth count F (X) of the event is calculated, so that the influence of diffusion effect in the propaganda science on the truth of the event is reduced.
Example 2: a public health epidemic early warning system based on knowledge graph, refer to FIG. 2, includes: the system comprises a knowledge map and early warning model module 1, a knowledge acquisition module 2, a knowledge extraction module 3, a knowledge reasoning and analysis module 4 and a map display module 5. The system comprises a knowledge graph and early warning model module 1, a public health epidemic situation knowledge graph triple relation module and a public health epidemic situation early warning model generation module, wherein the knowledge graph and early warning model module is used for inputting entities and relations of public health epidemic situation knowledge graph triples and generating an early warning model; the knowledge acquisition module 2 is used for acquiring entities and relations required by the public health epidemic situation knowledge map; the knowledge extraction module 3 is used for extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technologies, acquiring information and sending the information to the knowledge map and early warning model module 1; the knowledge reasoning and analyzing module 4 is used for carrying out mining and reasoning on the acquired relationship between the entities and obtaining the authenticity of the information through a weight algorithm; and the map display module 5 is used for displaying and outputting the quantity and the geographical distribution of the issued information according to the entities and the relations required for acquiring the public health epidemic situation knowledge map.
The knowledge graph can be divided into a mode layer and a data layer in a logic structure, wherein the data layer mainly comprises a series of facts, and the knowledge is stored by taking the facts as units. If facts are expressed in triplets of (entity 1, relationship, entity 2), (entity, attribute value), graph databases may be selected as storage media, such as open source Neo4j, Twitter's FlockDB, JanusGraph, etc. The mode layer is built on the data layer, and a series of fact expressions of the data layer are specified mainly through an ontology library. The ontology is a concept template of the structured knowledge base, and the knowledge base formed by the ontology base has a strong hierarchical structure and a small redundancy degree. Knowledge elements such as entities, relationships, attributes and the like can be extracted from some published semi-structured and unstructured data through knowledge extraction technology. Through knowledge fusion, ambiguity between the referent items such as entities, relations and attributes and the fact objects can be eliminated, and a high-quality knowledge base is formed. The early warning model is built through the knowledge map and early warning model module 1, and the knowledge acquisition module 2 comprises two information acquisition modes of active input and network retrieval. The network retrieval utilizes keywords and adopts a crawler technology to retrieve network databases, such as retrieval words of continuous high-grade fever, H1N1 and the like. The knowledge extraction module 3 acquires the address information, the unit information, the occupation information and the title information of the information publisher through information extraction and semantic analysis technologies, so as to analyze, construct and display knowledge and mutual relations among the knowledge and the title information.
The knowledge reasoning and analyzing module 4 studies and judges the truth weight value f (x) of the single piece of information according to the address information, the unit information, the occupation information and the job title information of the information publisher of each piece of information, and studies and judges the information-publishing motive, and when the weight of the information-publishing motive is lower than a set value, the current information is excluded, so that the deviation sample can be timely and efficiently discharged. F (x) = ∑ f (x)/N, and when f (x) > f (a), the current event information is determined to be a real event; wherein F (X) is event truth count; f (a) setting values for the degree of realism; (x) a weight value of the truth of a single piece of published information; n is a calculation proportionality coefficient, and is positively correlated with the number of times of information issuing. And introducing a calculation proportionality coefficient N, and further reducing the influence of diffusion effect in the propaganda on the event truth. And the map display module 5 is used for displaying and outputting the quantity and the geographic distribution of the issued information according to the retrieval information of the retrieval module. Through the arrangement of the map display module 5, the number and the geographic distribution of the issued information are displayed and output, so that the statistical state of the issued information can be visually checked.
The embodiments of the present invention are preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (7)
1. A public health epidemic situation early warning method based on a knowledge graph is characterized by comprising the following steps:
step S1, constructing an early warning model based on the public health epidemic situation knowledge graph;
step S2, acquiring entities and relations needed by the public health epidemic situation knowledge graph;
step S3, extracting knowledge on the basis of information acquisition through information extraction and semantic analysis technology, and accessing the extracted knowledge into a public health epidemic situation knowledge map for use;
and step S4, knowledge reasoning, wherein the relationship between the obtained entities is explored and reasoned through the existing knowledge mechanism, and the authenticity of the information is obtained through a weight algorithm.
2. The public health epidemic early warning method based on knowledge-graph of claim 1, wherein step S1 comprises:
step S11, constructing public health epidemic situation knowledge map triplets, namely entities and relations;
step S12, establishing an early warning model based on knowledge graph entities and relations;
and step S13, collecting input and feedback data, and correcting the early warning model.
3. The public health epidemic early warning method based on knowledge-graph as claimed in claim 2, characterized in that: the entity information of the public health epidemic situation knowledge map triple comprises address information, unit information, occupation information and job title information of an information publisher.
4. The public health epidemic early warning method based on knowledge-graph as claimed in claim 3, wherein: in step S4, the information distributor' S information distributor is examined by address information, unit information, career information, and title information of the distributor, and when the weight of the information distributor is lower than a set value, the current information is excluded.
5. The public health epidemic early warning method based on knowledge-graph according to claim 4, characterized in that: in step S4, f (x) = ∑ f (x)/N, and when f (x) > f (a), the current event information is determined to be a true event; wherein F (X) is event truth count; f (a) setting values for the degree of realism; (x) a weight value of the truth of a single piece of published information; n is a calculation proportionality coefficient, and is positively correlated with the number of times of information issuing.
6. The utility model provides a public health epidemic early warning system based on knowledge-graph which characterized in that includes:
the knowledge map and early warning model module (1) is used for inputting entities and relations of the public health epidemic situation knowledge map triples to generate an early warning model;
the knowledge acquisition module (2) is used for acquiring entities and relations required by the public health epidemic situation knowledge map;
the knowledge extraction module (3) extracts knowledge on the basis of information acquisition through information extraction and semantic analysis technologies, acquires the information and sends the information to the knowledge map and early warning model module (1);
and the knowledge reasoning and analyzing module (4) is used for carrying out mining and reasoning on the obtained relationship between the entities and obtaining the authenticity of the information through a weight algorithm.
7. The public health epidemic early warning system based on knowledge-graph of claim 6, wherein: the public health epidemic situation knowledge graph publishing system further comprises a map display module (5) which is used for displaying and outputting the quantity and the geographical distribution of the published information according to the entities and the relations which are needed for obtaining the public health epidemic situation knowledge graph.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010763919.1A CN112131392A (en) | 2020-08-01 | 2020-08-01 | Public health epidemic situation early warning method and system based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010763919.1A CN112131392A (en) | 2020-08-01 | 2020-08-01 | Public health epidemic situation early warning method and system based on knowledge graph |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112131392A true CN112131392A (en) | 2020-12-25 |
Family
ID=73851444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010763919.1A Pending CN112131392A (en) | 2020-08-01 | 2020-08-01 | Public health epidemic situation early warning method and system based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112131392A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113342913A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Community information model-based epidemic prevention control method, system and storage medium |
CN116167616A (en) * | 2022-12-29 | 2023-05-26 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751304A (en) * | 2015-04-28 | 2015-07-01 | 河南理工大学 | Specialty structural adjustment early warning system and early warning method for higher education |
CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
WO2018072563A1 (en) * | 2016-10-18 | 2018-04-26 | 中兴通讯股份有限公司 | Knowledge graph creation method, device, and system |
CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
CN110866126A (en) * | 2019-11-22 | 2020-03-06 | 福建工程学院 | College online public opinion risk assessment method |
CN111383102A (en) * | 2020-03-27 | 2020-07-07 | 北京明略软件系统有限公司 | Financial credit risk identification method, model construction method and device |
-
2020
- 2020-08-01 CN CN202010763919.1A patent/CN112131392A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751304A (en) * | 2015-04-28 | 2015-07-01 | 河南理工大学 | Specialty structural adjustment early warning system and early warning method for higher education |
CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
WO2018072563A1 (en) * | 2016-10-18 | 2018-04-26 | 中兴通讯股份有限公司 | Knowledge graph creation method, device, and system |
CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
CN110866126A (en) * | 2019-11-22 | 2020-03-06 | 福建工程学院 | College online public opinion risk assessment method |
CN111383102A (en) * | 2020-03-27 | 2020-07-07 | 北京明略软件系统有限公司 | Financial credit risk identification method, model construction method and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113342913A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Community information model-based epidemic prevention control method, system and storage medium |
CN116167616A (en) * | 2022-12-29 | 2023-05-26 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
CN116167616B (en) * | 2022-12-29 | 2023-07-28 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Leung et al. | Machine learning and OLAP on big COVID-19 data | |
CN111916215B (en) | Cluster/chronic disease early automatic alarm, preliminary feature analysis and risk assessment system | |
CN107833595A (en) | Medical big data multicenter integration platform and method | |
Zhou et al. | Real-time news cer tification system on sina weibo | |
Rosa et al. | Event detection system based on user behavior changes in online social networks: Case of the covid-19 pandemic | |
Leung et al. | Big data science on COVID-19 data | |
Shen et al. | Discovering the potential opportunities of scientific advancement and technological innovation: A case study of smart health monitoring technology | |
CN110910991B (en) | Medical automatic image processing system | |
CN112131392A (en) | Public health epidemic situation early warning method and system based on knowledge graph | |
CN116186594B (en) | Method for realizing intelligent detection of environment change trend based on decision network combined with big data | |
CN113918725A (en) | Construction method of knowledge graph in water affairs field | |
CN116684200A (en) | Knowledge completion method and system for attack mode of network security vulnerability | |
CN103440308B (en) | A kind of digital thesis search method based on form concept analysis | |
CN108846043A (en) | Network trace mining analysis method and system based on internet big data | |
Aliyu et al. | Analysis of cyber bullying on Facebook using text mining | |
Spurlock et al. | Predicting COVID-19 infection groups using social networks and machine learning algorithms | |
Hui | Construction of information security risk assessment model in smart city | |
CN102521378A (en) | Real-time intrusion detection method based on data mining | |
Xie et al. | Efficient storage management for social network events based on clustering and hot/cold data classification | |
Hu et al. | Evaluation of Big Data Analytics and cognitive computing in smart health systems | |
Wu et al. | A nonparametric approach to uncovering connected anomalies by tree shaped priors | |
Tamir et al. | Soft computing based epidemical crisis prediction | |
CN113343306B (en) | Differential privacy-based data query method, device, equipment and storage medium | |
Tian et al. | [Retracted] Intrusion Detection Method Based on Deep Learning | |
Diday | Symbolic Data Analysis and the SODAS project: purpose, history, perspective |
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 |