CN112101022B - Entity linking method for seismic event - Google Patents
Entity linking method for seismic event Download PDFInfo
- Publication number
- CN112101022B CN112101022B CN202010923698.XA CN202010923698A CN112101022B CN 112101022 B CN112101022 B CN 112101022B CN 202010923698 A CN202010923698 A CN 202010923698A CN 112101022 B CN112101022 B CN 112101022B
- Authority
- CN
- China
- Prior art keywords
- earthquake
- seismic
- information
- entity
- news
- 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
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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
A method of seismic event entity linking, comprising: the seismic catalog data of the seismic bureau are crawled in real time, and the obtained seismic data are stored into an entity library in the form of event entities; extracting the seismic news, extracting the basic information of the earthquake in the seismic news, and arranging the basic information into an earthquake information array according to the sequence of the basic information in the seismic news; firstly, carrying out information grouping on the seismic information arrays based on the depth information of a seismic source, and dividing the seismic basic information arrays into a plurality of seismic information arrays on the basis of a preset sequential structure of the seismic news report and a seismic information logic discrimination method for each grouping information; and carrying out earthquake identification on the earthquake information array based on the earthquake information registered in the entity library and an earthquake identification method, and linking the identified earthquake with the earthquake news. The invention discloses a method for extracting basic information of an earthquake in the earthquake news, carrying out earthquake identification according to the extracted basic information of the earthquake and completing the link with a corresponding earthquake event entity in an entity library.
Description
Technical Field
The invention relates to the field of entity links, in particular to a method for carrying out seismic event entity link on news based on a seismic catalog of a seismic bureau.
Background
Entity links, also known in the art of natural language processing as named entity links, are the identification of certain strings from text and mapping into a knowledge base. The general steps are divided into two steps: the first step is to identify the entity in the text, i.e. entity identification. The second step is to judge which entity belongs to the knowledge base and link the entity, namely, disambiguate the entity.
The existing earthquake identification technology is mainly applied to the fields of earthquake prediction, geology, energy, petroleum exploration and the like, and the earthquake appearing in real life is identified by inputting corresponding earthquake parameters and geophysical prospecting parameters. In the event information extraction field, the granularity of extraction is mainly reflected in the level of earthquake occurrence, namely, only the news is identified as an earthquake news, and the concrete earthquake reported by the news is not identified. In the field of entity linking, the main linked objects are common types of characters, institutions, places and the like, and no entity linking method is disclosed in the field of seismic news at present.
Disclosure of Invention
The invention aims to solve the problem of storing the seismic data of the seismic bureau into the entity library in the form of the entity type of the seismic event, accurately completing the entity link of the seismic news and laying a foundation for realizing the seismic knowledge graph later.
The invention discloses a new entity type-seismic event entity type, and a method for storing seismic data of a seismic bureau into an entity library according to the seismic event entity type.
The invention discloses a method for extracting basic information of earthquake in earthquake news, carrying out earthquake identification according to the extracted basic information of the earthquake, and completing the link with a corresponding earthquake event entity in an entity library.
In order to solve the technical problems, the invention is solved by the following technical scheme:
a method of seismic event entity linking, comprising:
the seismic catalog data of the seismic bureau are crawled in real time, and the obtained seismic data are stored into an entity library in the form of event entities;
extracting the seismic news, extracting the basic information of the earthquake in the seismic news, and arranging the basic information into an earthquake information array according to the sequence of the basic information in the seismic news;
firstly, carrying out information grouping on the seismic information arrays based on the depth information of a seismic source, and dividing the seismic basic information arrays into a plurality of seismic information arrays on the basis of a preset sequential structure of the seismic news report and a seismic information logic discrimination method for each grouping information;
and carrying out earthquake identification on the earthquake information array based on the earthquake information registered in the entity library and an earthquake identification method, and linking the identified earthquake with the earthquake news.
Optionally, normalizing the earthquake starting places in the earthquake catalogue through a place entity library entity identification function, and normalizing the earthquake starting places on the earthquake catalogue into a city and county three-level format according to a place entity library entity identification module;
the method for storing the middle earthquake bureau seismic data subjected to the earthquake starting place normalization processing into the entity library comprises the following steps: each piece of seismic information of the seismic bureau is used as an entity record, which comprises five entity attributes of earthquake starting time, earthquake starting place, earthquake magnitude, earthquake source depth and longitude and latitude, the entity type is a seismic event, and an entity id is allocated to the entity record as a unique identifier.
Optionally, extracting the basic information of the earthquake from the earthquake news, wherein the basic information of the earthquake comprises five types of basic information of the earthquake: time of earthquake, place of earthquake, magnitude of earthquake, depth of earthquake focus, longitude and latitude; the five types of seismic basic information are put into an array according to the appearance sequence
Optionally, the seismic basic information extracted by using the regular expression is put into a word segmentation dictionary, then the word segmentation dictionary is loaded by using a jieba module, then the news is segmented by using the jieba module, and finally the seismic basic information is put into an array according to the appearance sequence of the extracted seismic basic information in the text.
Optionally, after the extraction of the seismic information arrays is completed, judging whether each array in the seismic information arrays contains the depth information of the seismic source, if so, grouping the seismic information arrays by taking the depth information of the seismic source as a grouping node; if not, the whole seismic information array is divided into one group.
Optionally, the method for outputting the seismic information includes: if the depth information of the seismic source is extracted from the seismic news, the preset report sequence is as follows: at the moment of earthquake onset, the earthquake onset place, the earthquake magnitude and the earthquake focus depth; if the depth information of the seismic source is not extracted from the news, the preset report sequence is as follows: at the moment of earthquake starting, the earthquake starting place, the earthquake magnitude and the air space;
and comparing the structures of each seismic information group according to two preset reporting sequences, outputting a seismic information array according to the preset structures if one of the preset reporting sequences is met, and continuing to judge by a seismic logic judging method if the two preset reporting sequence structures are not met.
Optionally, the seismic logic discriminating method includes:
the information in the earthquake information array is reversed in order, three pieces of information, namely the earthquake starting moment, the earthquake starting place and the earthquake magnitude, which appear first in the group are respectively taken according to the adjusted order, and if no relevant information exists, the corresponding field output is null. And finally integrating the information, wherein the output structure is as follows: at the moment of earthquake onset, the earthquake onset place, the earthquake magnitude and the earthquake focus depth, if the relevant information is not contained, the output is null.
Optionally, the format of the grouped seismic information array is converted into a data format consistent with the seismic event entity in the entity library through normalization processing, then the seismic office seismic data stored in the entity library are compared according to the priority of the time of earthquake onset, the place of earthquake onset, the magnitude and the depth of the earthquake focus through a seismic identification method, the earthquake described by the news corresponding to the seismic information array is identified, and the news and the entity library earthquake are subjected to entity link.
Optionally, the entity name is named in "< time of earthquake month, day > + < place of earthquake > + earthquake".
The invention has the beneficial effects that:
1. the entity linking technology is applied to the earthquake news text. And comparing the seismic event entity information stored in the entity library by extracting the seismic basic information in the news, and carrying out seismic identification. The method is different from the traditional earthquake identification method in that the earthquake identification method is carried out through a corresponding geological model according to the input geological parameters and geophysical prospecting parameters.
2. The invention creates a seismic event entity based on a seismic catalog of a seismic bureau, and carries out entity link on the seismic news based on the seismic event entity, thereby establishing a foundation for constructing the news venation carding, intelligent question answering, information extraction and knowledge graph construction under the scene of the seismic news.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a block diagram of an overall flow of seismic news identification and linking;
FIG. 2 is a schematic diagram of a warehouse entry format of a seismic entity;
FIG. 3 is a schematic diagram of a method for extracting an array of seismic basis information;
FIG. 4 is a schematic diagram of a method of grouping arrays of seismic basis information;
FIG. 5 is a block diagram of a seismic identification method.
Detailed Description
The present invention will be described in further detail with reference to the following examples, which are illustrative of the present invention and are not intended to limit the present invention thereto.
A method of seismic event entity linking, as in fig. 1, comprising:
s01: the method comprises the steps of crawling seismic catalogue data of a seismic bureau in real time, carrying out normalization processing on a seismic place in the seismic catalogue through a place entity library entity identification function, and storing the obtained seismic data into an entity library in the form of event entities;
the method specifically comprises the following steps:
the method for normalizing the earthquake starting places comprises the steps of normalizing the earthquake starting places on an earthquake bureau earthquake catalogue into a province county three-level format according to a place entity library entity identification module;
the method for storing the middle earthquake bureau seismic data subjected to the earthquake starting place normalization processing into the entity library comprises the following steps: each piece of earthquake information of a certain earthquake bureau is used as an entity record, the name format of the entity is "< time, month and day of earthquake > + < place of earthquake > + earthquake", the entity record comprises five entity attributes of time of earthquake, place of earthquake, magnitude, depth of earthquake source and longitude and latitude, the entity type is an earthquake event, and an entity id is allocated to the entity attribute as a unique identifier. The entity warehouse entry format is as shown in figure 2.
S02: and extracting the seismic news, extracting the seismic basic information in the news, and arranging the seismic basic information into a seismic information array according to the appearance sequence of the seismic basic information in the news.
The method specifically comprises the following steps: acquiring whole network news data, judging whether the news is earthquake news, and extracting earthquake basic information in the news, wherein the earthquake basic information comprises the following steps: time of earthquake, place of earthquake, magnitude of earthquake, depth of earthquake focus, longitude and latitude;
the method for extracting the basic information of the earthquake comprises the steps of extracting the earthquake basic information of five types mentioned in the earthquake news, namely earthquake starting time, earthquake starting place, earthquake magnitude, earthquake source depth and longitude and latitude by using a regular expression.
The method specifically comprises the following steps: 1. the seismic basic information extracted by using the regular expression is put into a word segmentation dictionary, then the word segmentation dictionary is loaded by using a jieba module, and then the news is segmented by using the jieba module; 2. the five types of seismic basic information are put into an array according to the appearance sequence in the text, as shown in fig. 3.
S03: and (2) firstly grouping the information based on the depth information of the seismic source, and then dividing the seismic basic information array into a plurality of seismic information arrays based on a preset sequence structure of the seismic news report and a seismic information logic discrimination method for each group of information.
If the depth information of the seismic source is extracted from the seismic news, the preset report sequence is as follows: at the moment of earthquake onset, the earthquake onset place, the earthquake magnitude and the earthquake focus depth; if the depth information of the seismic source is not extracted from the news, the preset report sequence is as follows: at the moment of earthquake starting, the earthquake starting place, the earthquake magnitude and the air space;
and comparing the structures of each seismic information group according to two preset reporting sequences, outputting a seismic information array according to the preset structures if one of the preset reporting sequences is met, and continuing to judge by a seismic logic judging method if the two preset reporting sequence structures are not met.
The specific method comprises the following steps:
after the extraction of the seismic information arrays is completed, judging whether each array in the seismic information arrays contains the depth information of the seismic source, if so, grouping the seismic information arrays by taking the depth information of the seismic source as a grouping node; as shown in fig. 4, when the depth information of the seismic source is scanned in a group of arrays, the seismic information of the group is grouped into a group 1 and a group 2 by using the depth information of the seismic source as a grouping node.
If not, the whole seismic information array is divided into one group.
And (3) outputting seismic information:
if the depth information of the seismic source is extracted from the news, the preset report sequence is as follows: [ time of earthquake, place of earthquake, magnitude, depth of earthquake focus ]; if the depth information of the seismic source is not extracted from the news, a second preset report sequence is adopted: the vibration moment, vibration place, vibration level and air. And comparing each seismic information group according to the two reporting sequence structures, if the two types of structures are met, directly outputting a seismic information array according to a preset structure, and if the two types of structures are not met, continuing to judge by a seismic logic judging method.
If group 1 satisfies the report preset order: and outputting according to the preset earthquake information output structure, wherein the output of the group 1 is shown in the figure.
If the group 2 does not contain the depth information of the seismic source and does not meet the second preset report sequence, further judging by a logic judging method.
The earthquake logic discrimination method specifically comprises the following steps:
the information in the earthquake information array is reversed in order, three pieces of information, namely the earthquake starting moment, the earthquake starting place and the earthquake magnitude, which appear first in the group are respectively taken according to the adjusted order, and if no relevant information exists, the corresponding field output is null. And finally integrating the information, wherein the output structure is as follows: [ time of earthquake, place of earthquake, magnitude of earthquake, depth of earthquake source ], if not containing the relevant information, the output is null.
S04: and carrying out earthquake identification on the earthquake information array based on the earthquake information registered in the entity library and an earthquake identification method, and linking the identified earthquake with the earthquake news.
Converting the format of the seismic information array combined by the seismic information in the step 3 into a data format consistent with the seismic event entity in the entity library through normalization processing, and comparing the seismic data stored in the entity library according to the priority of the time, the place, the magnitude and the depth of the seismic source by a seismic identification method to identify the earthquake described by the earthquake news.
As shown in fig. 5, the linking of the seismic information array and the entity library specifically includes:
judging whether a vibration moment field in the earthquake information array contains complete year-month-day-time-minute information or not;
if yes, entering S100; if not, go to step S200.
S100, judging whether the entity library has only one earthquake and the same earthquake starting time of news extraction;
if yes, the calcium news is physically linked with the entity library earthquake;
if not, judging that the entity library has a plurality of earthquakes and the earthquake starting time of news extraction is the same, and if not, outputting is not finished.
If a plurality of earthquakes exist in the entity library and the earthquake starting time of news extraction is the same, comparing all earthquakes meeting the time condition according to the priorities of the earthquake starting place, the earthquake magnitude and the earthquake source depth, and carrying out entity link on the earthquakes with the highest priorities.
S200, judging whether the earthquake information array contains earthquake place information, if not, outputting is not finished;
if yes, screening all the earthquakes occurring at the place in the entity library according to the earthquake-generating place, and continuously judging whether only one earthquake occurs at the place in the entity library;
if yes, carrying out entity link on the news and the entity library earthquake;
if not, entering S210;
s210, judging whether a plurality of earthquakes occur at the place in the entity library or not, if not, outputting is not finished;
if yes, go to S220;
s220, judging whether the seismic information array contains the magnitude information or not, if not, outputting is not finished;
if yes, go to S220;
s220, judging whether an earthquake with the same magnitude as that of the earthquake information array exists in the entity library or not;
if yes, carrying out entity link on the news and the entity library earthquake; if not, the news is physically linked with the latest earthquake which occurs in the same area with the earthquake level in the entity library.
After the calculation processing, the entity link is carried out on all the seismic information output and the earthquakes in the entity library.
In addition, the specific embodiments described in the present specification may differ in terms of parts, shapes of components, names, and the like. All equivalent or simple changes of the structure, characteristics and principle according to the inventive concept are included in the protection scope of the present invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions in a similar manner without departing from the scope of the invention as defined in the accompanying claims.
Claims (6)
1. A method of physical linking of seismic events, comprising:
the seismic catalog data of the seismic bureau are crawled in real time, and the obtained seismic data are stored into an entity library in the form of event entities;
extracting the seismic news, extracting the basic information of the earthquake in the seismic news, and arranging the basic information into an earthquake information array according to the sequence of the basic information in the seismic news; the basic information of the earthquake comprises earthquake starting time, earthquake starting place, earthquake magnitude, earthquake source depth and longitude and latitude;
firstly, carrying out information grouping on the seismic information arrays based on the depth information of a seismic source, and dividing the seismic basic information arrays into a plurality of seismic information arrays on the basis of a preset sequential structure of the seismic news report and a seismic information logic discrimination method for each grouping information;
carrying out earthquake identification on the earthquake information array based on the earthquake information registered in the entity library and an earthquake identification method, and linking the identified earthquake with the earthquake news;
the seismic information output method comprises the following steps: if the depth information of the seismic source is extracted from the seismic news, the preset report sequence is as follows: at the moment of earthquake onset, the earthquake onset place, the earthquake magnitude and the earthquake focus depth; if the depth information of the seismic source is not extracted from the news, the preset report sequence is as follows: at the moment of earthquake starting, the earthquake starting place, the earthquake magnitude and the air space;
comparing the structures of each seismic information group according to two preset report sequences, outputting a seismic information array according to the preset structures if one of the preset report sequences is met, and continuing to judge by a seismic logic judging method if the two preset report sequence structures are not met; the earthquake logic discrimination method comprises the following steps:
the information in the earthquake information array is reversed in order, three pieces of information, namely the earthquake starting moment, the earthquake starting place and the earthquake magnitude, which appear first in the group are respectively taken according to the adjusted order, and if no related information exists, the corresponding field output is null; and finally integrating the information, wherein the output structure is as follows: at the moment of earthquake onset, the earthquake onset place, the earthquake magnitude and the earthquake focus depth, if the relevant information is not contained, the output is null.
2. The method for linking seismic event entities according to claim 1, wherein the seismic locations in the seismic catalogue are normalized by a location entity library entity identification function, and the seismic locations in the seismic catalogue are normalized into a province county three-level format according to a location entity library entity identification module;
the method for storing the middle earthquake bureau seismic data subjected to the earthquake starting place normalization processing into the entity library comprises the following steps: each piece of seismic information of the seismic bureau is used as an entity record, which comprises five entity attributes of earthquake starting time, earthquake starting place, earthquake magnitude, earthquake source depth and longitude and latitude, the entity type is a seismic event, and an entity id is allocated to the entity record as a unique identifier.
3. The method for physical linking of seismic events according to claim 1, wherein the seismic basic information extracted by using regular expressions is put into a word segmentation dictionary, then the word segmentation dictionary is loaded by using a jieba module, then news is segmented by using the jieba module, and finally the extracted seismic basic information is put into an array according to the appearance sequence of the extracted seismic basic information.
4. The method for physically linking seismic event according to claim 1, wherein after the extraction of the seismic information arrays is completed, determining whether each of the seismic information arrays contains source depth information, and if so, grouping the seismic information arrays by using the source depth information as a grouping node; if not, the whole seismic information array is divided into one group.
5. The method for linking seismic event entities according to claim 1, wherein the grouped seismic information arrays are converted into data format consistent with the seismic event entities in the entity library through normalization processing, then the seismic data stored in the entity library are compared according to the priority of the time, place, magnitude and depth of the earthquake by means of earthquake identification, the earthquake described by the news corresponding to the seismic information arrays is identified, and the news is physically linked with the earthquake of the entity library.
6. The method of claim 1, wherein the entity name is in the format "< time of origin, month, day > + < place of origin > + earthquake".
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020108082594 | 2020-08-12 | ||
| CN202010808259 | 2020-08-12 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101022A CN112101022A (en) | 2020-12-18 |
| CN112101022B true CN112101022B (en) | 2024-02-20 |
Family
ID=73757359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010923698.XA Active CN112101022B (en) | 2020-08-12 | 2020-09-04 | Entity linking method for seismic event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101022B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052968B (en) * | 2021-04-30 | 2022-08-05 | 电子科技大学 | A Knowledge Graph Construction Method for 3D Structural Geological Models |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1363046A (en) * | 2000-02-14 | 2002-08-07 | 法兰西气体公司 | Method for seismic monitoring of underground zone by simutaneous use of several vibroseismic sources |
| CN102066978A (en) * | 2008-03-24 | 2011-05-18 | 雪佛龙美国公司 | System and method for migrating seismic data |
| CN102622696A (en) * | 2011-01-27 | 2012-08-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for customer service return visit |
| CN103364830A (en) * | 2013-07-24 | 2013-10-23 | 北京师范大学 | Predication method of happening position of slump disaster after earthquake based on multiple factors |
| CN103853822A (en) * | 2014-02-24 | 2014-06-11 | 北京奇虎科技有限公司 | Method and device for pushing news information in browser |
| CN104679825A (en) * | 2015-01-06 | 2015-06-03 | 中国农业大学 | Web text-based acquiring and screening method of seismic macroscopic anomaly information |
| KR20150123550A (en) * | 2014-04-25 | 2015-11-04 | 주식회사 코어밸런스 | System and Method for Measuring and Monitoring Seismic data Applied to the City Building |
| CN105183942A (en) * | 2015-07-28 | 2015-12-23 | 中国地震局地球物理研究所 | Novel earthquake catalogue persistence and visualization method |
| CN106874345A (en) * | 2016-12-23 | 2017-06-20 | 中国科学院自动化研究所 | Media event information extraction method based on object of planning figure |
| WO2018056299A1 (en) * | 2016-09-26 | 2018-03-29 | 日本電気株式会社 | Information collection system, information collection method, and recording medium |
| AU2018100678A4 (en) * | 2015-11-05 | 2018-06-14 | Tongji University | News events extracting method and system |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN110045413A (en) * | 2019-04-22 | 2019-07-23 | 中国地质大学（北京） | A kind of Earthquake Short-term method and apparatus |
| CN110968700A (en) * | 2019-11-01 | 2020-04-07 | 数地科技(北京)有限公司 | Domain event map construction method and device fusing multi-class affairs and entity knowledge |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9021364B2 (en) * | 2011-05-31 | 2015-04-28 | Microsoft Technology Licensing, Llc | Accessing web content based on mobile contextual data |
| WO2015084726A1 (en) * | 2013-12-02 | 2015-06-11 | Qbase, LLC | Event detection through text analysis template models |
-
2020
- 2020-09-04 CN CN202010923698.XA patent/CN112101022B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1363046A (en) * | 2000-02-14 | 2002-08-07 | 法兰西气体公司 | Method for seismic monitoring of underground zone by simutaneous use of several vibroseismic sources |
| CN102066978A (en) * | 2008-03-24 | 2011-05-18 | 雪佛龙美国公司 | System and method for migrating seismic data |
| CN102622696A (en) * | 2011-01-27 | 2012-08-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for customer service return visit |
| CN103364830A (en) * | 2013-07-24 | 2013-10-23 | 北京师范大学 | Predication method of happening position of slump disaster after earthquake based on multiple factors |
| CN103853822A (en) * | 2014-02-24 | 2014-06-11 | 北京奇虎科技有限公司 | Method and device for pushing news information in browser |
| KR20150123550A (en) * | 2014-04-25 | 2015-11-04 | 주식회사 코어밸런스 | System and Method for Measuring and Monitoring Seismic data Applied to the City Building |
| CN104679825A (en) * | 2015-01-06 | 2015-06-03 | 中国农业大学 | Web text-based acquiring and screening method of seismic macroscopic anomaly information |
| CN105183942A (en) * | 2015-07-28 | 2015-12-23 | 中国地震局地球物理研究所 | Novel earthquake catalogue persistence and visualization method |
| AU2018100678A4 (en) * | 2015-11-05 | 2018-06-14 | Tongji University | News events extracting method and system |
| WO2018056299A1 (en) * | 2016-09-26 | 2018-03-29 | 日本電気株式会社 | Information collection system, information collection method, and recording medium |
| CN106874345A (en) * | 2016-12-23 | 2017-06-20 | 中国科学院自动化研究所 | Media event information extraction method based on object of planning figure |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN110045413A (en) * | 2019-04-22 | 2019-07-23 | 中国地质大学（北京） | A kind of Earthquake Short-term method and apparatus |
| CN110968700A (en) * | 2019-11-01 | 2020-04-07 | 数地科技(北京)有限公司 | Domain event map construction method and device fusing multi-class affairs and entity knowledge |
Non-Patent Citations (1)
| Title |
|---|
| 多策略中文微博实体词消歧及实体链接;向宇;郭云龙;徐潇;曾维刚;李莉;;计算机应用与软件(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101022A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zelenin et al. | The database of the active faults of Eurasia (AFEAD): Ontology and design behind the continental-scale dataset | |
| CN110222373B (en) | Geotechnical engineering full life cycle oriented engineering investigation data processing method | |
| CN114896472B (en) | Knowledge graph machine reasoning system and method based on multi-source space-time data | |
| CN112612908A (en) | Natural resource knowledge graph construction method and device, server and readable memory | |
| CN108038222A (en) | System for Information System Modeling and entity-property frame of data access | |
| CN111813956A (en) | Knowledge graph construction method and device, and information penetration method and system | |
| CN111159428A (en) | Method and device for automatically extracting event relation of knowledge graph in economic field | |
| CN108595664A (en) | A kind of agricultural data monitoring method under hadoop environment | |
| CN107679221A (en) | Towards the time-space data acquisition and Services Composition scheme generation method of mitigation task | |
| CN117076463B (en) | Multi-source data aggregation storage system for smart city | |
| CN114817557B (en) | Enterprise risk detection method and device based on enterprise credit big data knowledge graph | |
| CN112101022B (en) | Entity linking method for seismic event | |
| CN117312578B (en) | Construction method and system of non-genetic carrier spectrum | |
| CN114238488A (en) | Multi-professional digital fruit integration and data interaction method and system | |
| CN110515994A (en) | A kind of geologic prospect analysis and management system based on big data | |
| CN117151659A (en) | Ecological restoration engineering full life cycle tracing method based on large language model | |
| CN116775661A (en) | Big space data storage and management method based on Beidou grid technology | |
| Caprari et al. | Upgrade of the CEDIT database of earthquake-induced ground effects in Italy | |
| CN113407726A (en) | Emergency disposal plan method and system | |
| CN118246539B (en) | Space-time feature-based composite disaster knowledge platform construction method and system | |
| Basnet et al. | Analysis of multifactorial social unrest events with spatio-temporal k-dimensional tree-based dbscan | |
| Tuluka et al. | Seismic hazard assessment of the Democratic Republic of Congo and Environs based on the GEM–SSA Catalogue and a new seismic source model | |
| CN109213909A (en) | A kind of big data analysis system and its analysis method fusion search and calculated | |
| Stéphan et al. | Generation of symbolic objects from relational databases | |
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |