CN110110969A - A kind of space environment forecast product gross examines appraisal procedure and system automatically - Google Patents
A kind of space environment forecast product gross examines appraisal procedure and system automatically Download PDFInfo
- Publication number
- CN110110969A CN110110969A CN201910284784.8A CN201910284784A CN110110969A CN 110110969 A CN110110969 A CN 110110969A CN 201910284784 A CN201910284784 A CN 201910284784A CN 110110969 A CN110110969 A CN 110110969A
- Authority
- CN
- China
- Prior art keywords
- space environment
- forecast
- content
- product
- environment forecast
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000007613 environmental effect Effects 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims description 35
- 230000000694 effects Effects 0.000 claims description 32
- 238000000605 extraction Methods 0.000 claims description 23
- 238000012800 visualization Methods 0.000 claims description 23
- 238000007689 inspection Methods 0.000 claims description 22
- 230000002452 interceptive effect Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000009472 formulation Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 206010028916 Neologism Diseases 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 241000502522 Luscinia megarhynchos Species 0.000 claims 2
- 239000004744 fabric Substances 0.000 claims 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 6
- 230000005389 magnetism Effects 0.000 description 6
- 241000220317 Rosa Species 0.000 description 4
- 230000004907 flux Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 206010054949 Metaplasia Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 230000005923 long-lasting effect Effects 0.000 description 1
- 230000015689 metaplastic ossification Effects 0.000 description 1
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/06395—Quality analysis or management
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of space environment forecast product grosses to examine appraisal procedure and system automatically, the described method includes: obtaining space environment forecast product to be detected, the space environment forecast product includes space environment forecast content of text, space environment forecast numeric type content and space environment event prediction content;Using the automatic abstracting method of forecast content information of rule-based neighborhood search, corresponding space environment forecast main element information is extracted from space environment forecast content of text;It examines evaluation index to carry out gross to space environment forecast main element information, space environment forecast numeric type content and space environment event prediction content according to space environment gross and examines assessment, and assessment result storage will be examined into database.Method of the invention can be realized an environmental forecasting product gross and examine assessment automatically, provide technical support for the control of space environment operational forecast quality.
Description
Technical field
The present invention relates to space environment operational forecast control of product quality fields, and in particular to a kind of space environment forecast production
Product gross examines appraisal procedure and system automatically.
Background technique
Space environment forecast product is the important component of space environment support, and forecast model products include day towards the public
Report, weekly, monthly magazine and notification, the forecast model products towards professional user's customization.Generally included from content space environment summary and
The space environment forecast of following a period of time.Currently, space environment forecast product is semi-automatic according to experience by forecaster
Metaplasia at.In the manufacturing process of space environment forecast product, caused in text due to forecaster's knowledge background difference etc.
There is deviation and mistake in appearance, and the main punctuality including forecast model products publication, text spelling accuracy, physical quantity unit are accurate
Property, value data accuracy, the forecast grosses problem such as the self-consistent property of content, it is necessary to examine and comment by gross
Estimate, could find quality problems present in forecast model products in time.
Forecast verification evaluation studies start from weather forecast field, are also mainly developed in the field.Space environment is pre-
The research that assessment system is tested in inspection declaration is in just getting started.USA space environmental forecasting center (SWPC) is pre- to space environment
Tentative evaluation work has been carried out in report business, and SWPC is pre- for geomagnetic activity indexes, solar active index such as Ap, Kp
The forecast model products such as the probability forecast of space environments event such as report and geomagnetic storm, solar flare, proton event are periodically assessed
(annual assessment is primary), and issue in its official website.But the data found at present shows that a set of reality has not yet been formed in SWPC
When automation inspection assessment system, the artificial forecast model products also do not issued to it carry out the inspection of gross.
The more than two decades time has been carried out in the space environment operational forecast service in China, with to the more of space environment forecast
Concern also starts to be paid attention to evaluation of prediction effect work, however systematic evaluation of prediction effect method is established perfect not yet, faces
Problems need to solve.A kind of Chinese patent: the patent No.: the automation space environment model of ZL 2,013 1 0303921.0
Assessment system and method the characteristics of for different forecast model products, devise successive value appraisal procedure and the classification assessment of event two
Method.
At present both at home and abroad to the assessment of Space Forecast product just for the assessment of numeric type forecast result, do not relate to
Inspection and assessment to space environment forecast product gross.
Summary of the invention
It is empty by analysis it is an object of the invention to fill up the blank of current spatial environmental forecasting product quality inspection tool
Between in environmental forecasting product punctuality, the text of potential forecast model products publication spell accuracy, physical quantity unit accuracy, number
According to grosses problems such as Numerical accuracy, the forecast self-consistent property of content, it is basic to propose a kind of space environment forecast product
The appraisal procedure of quality inspection;And interactive visualization system is designed, the problem of space environment forecast product, is carried out
Visual analyzing.
To achieve the goals above, the present invention provides a kind of space environment forecast product gross and examines assessment side automatically
Method, which comprises
Space environment forecast product to be detected is obtained, the space environment forecast product includes space environment forecast text
Content, space environment forecast numeric type content and space environment event prediction content;
Using the automatic abstracting method of forecast content information of rule-based neighborhood search, from space environment forecast content of text
It is middle to extract corresponding space environment forecast main element information;
Examine evaluation index pre- to space environment forecast main element information, space environment according to space environment gross
It reports numeric type content and space environment event prediction content to carry out gross and examines assessment, and assessment result storage will be examined to arrive
In database.
As a kind of improvement of the above method, is extracted from database and examine assessment result, utilize Interactive Visualization circle
It realizes the visual quality analysis of space environment forecast product and examines the visualization of assessment result in face;The Interactive Visualization
Interface includes that Nightingale, Florence rose figure shows that various problem accountings present in whole forecast, parallel coordinates show each forecaster
The various problems present in forecast.
It is described to be extracted automatically using the forecast content information of rule-based neighborhood search as a kind of improvement of the above method
Method extracts corresponding space environment forecast main element information from space environment forecast content of text;It specifically includes:
Sentence segmentation is carried out to space environment forecast content of text according to text punctuate, each sentence includes independent spatial loop
Forecast main element in border;The space environment forecast main element includes: solar activity level, geomagnetic activity level, sun matter
Subevent and the sudden and violent event of high energy electron;
Using open source Chinese word segmentation kit IKAnalyzer2012, it is based on space environment forecast domain lexicon, to sentence
Content is segmented, and<the form of glossarial index, word>key-value pair is converted into after participle;
Based on<glossarial index, word>key-value pair are formulated corresponding information and taken out for different space environment forecast main elements
Rule is taken, corresponding space environment forecast main element information is extracted from space environment forecast content of text.
As a kind of improvement of the above method, the construction step of the space environment forecast domain lexicon includes:
Step S1) according to space environment Disciplinary Characteristics and forecast experience, formulate space environment forecast domain lexicon;
Step S2) using open source Chinese word segmentation kit IKAnalyzer2012, it is based on space environment forecast domain lexicon,
Text segmentation is carried out to space environment forecast historical product, obtains space environment forecast word sequence;
Step S3) analysis space environmental forecasting word sequence, it is wrong to judge whether there is the segmentation of space environment forecast field term
Accidentally, the term of segmentation errors is added in space environment forecast domain lexicon;
Step S4) repeat step S2)-step S3), until all space environment field terms are correctly split, then it is empty
Between environmental forecasting domain lexicon building complete.
As a kind of improvement of the above method, it includes: forecast model products that the space environment gross, which examines evaluation index,
It is self-consistent that punctuality, the text of publication spell accuracy, physical quantity unit accuracy, value data accuracy and forecast content
Property;
The punctuality of the forecast model products publication, refers to whether defined timing node completes space environment forecast product
Publication;
The text spells accuracy, refers to whether the text spelling in the space environment forecast product of generation is correct;
The physical quantity unit accuracy refers to the space environment forecast physical quantity unit dictionary according to formulation, judges sky
Between in environmental forecasting product physical quantity unit it is whether correct;
The value data accuracy refers to the space environment forecast numeric type physical quantity numberical range word according to formulation
Allusion quotation judges whether the numerical value of physical quantity data in space environment forecast product is more than its zone of reasonableness;
The self-consistent property of forecast content, refers to space environment forecast content of text and space environment event prediction content
Between it is whether consistent.
It is described to examine evaluation index to space environment according to space environment gross as a kind of improvement of the above method
Forecast that main element information, space environment forecast numeric type content and space environment event prediction content carry out gross inspection
Assessment, specifically includes:
The issuing time of space environment forecast product to be detected is obtained, and is compared with defined issuing time the latest, if
Issuing time is upchecked earlier than the stipulated time, is otherwise examined and is not passed through;And the publication to space environment forecast product to be detected
Punctuality marking;
Space environment forecast product content of text to be detected is segmented, then checks whether the word separated appears in spatial loop
In the domain lexicon of border, if do not occurred, then it is assumed that there may be problems for the spelling of forecast model products text;Record spatial loop to be detected
There may be the neologisms of problem in the forecast model products of border, the text spelling accuracy marking to space environment forecast product to be detected;
It determines the physical quantity for needing to examine, physical quantity unit is determined from space environment physical quantity unit dictionary;Then exist
Physical quantity to be detected and extracts physical amount unit, corresponding standard in last and dictionary are identified in space environment forecast product to be detected
True physical quantity unit compares, if physical quantity unit compares successfully, upchecks, otherwise examines and do not pass through;In records tests
There is the physical quantity and errors number of mistake, is given a mark according to errors number to physical quantity unit accuracy;
It determines the index class product for needing to examine, is determined from space environment forecast numeric type physical quantity numberical range dictionary
The zone of reasonableness of the product;Then corresponding index class forecast model products are extracted, check whether to have exceeded reasonable value data model
It encloses;If numerical value in the reasonable scope, is upchecked, otherwise, inspection does not pass through;Exceed the physics of zone of reasonableness in records tests
Amount and Problem-Error give a mark to data Numerical accuracy according to problem number;
Judge the consistency of space environment forecast main element information Yu space environment event prediction content, comprising: space
Environmental forecasting probability of happening consistency and space environment forecast main element ranking consistence;The space environment forecast probability of happening one
Cause sex expression when space environment forecast main element grade reaches certain rank, event occurrence rate should be higher than that certain threshold
Value;Space environment forecast main element ranking consistence show space environment environmental forecasting main element grade should and spatial loop
Space environment forecast main element grade in the event prediction content of border is corresponding;The space environment of inconsequent in records tests
It forecasts main element, is given a mark according to problem number to the self-consistent property of forecast content.
The present invention also provides a kind of space environment forecast product grosses to examine assessment system, the system packet automatically
Contain:
Space environment forecast product database is used for memory space environmental forecasting product;The space environment forecast product
Including space environment forecast content of text, space environment forecast numeric type content and space environment event prediction content;
Space environment forecast domain lexicon, for recording proper noun and term in space environment forecast text;
Subordinate sentence/word segmentation module, it is each for carrying out sentence segmentation to space environment forecast content of text according to text punctuate
Sentence includes independent space environment forecast main element;Using open source Chinese word segmentation kit IKAnalyzer2012, based on sky
Between environmental forecasting domain lexicon, sentence content is segmented,<the form of glossarial index, word>key-value pair is converted into after participle;
Space environment forecast element information abstraction module, for realizing name Entity recognition, be also used to be based on < glossarial index,
Word > key-value pair formulates corresponding information extraction rules for different space environment forecast main elements, realizes space environment
Forecast main element information extraction;
Gross examines evaluation module, for examining evaluation index pre- to space environment according to space environment gross
Report main element information, space environment forecast numeric type content and space environment event prediction content carry out gross inspection and comment
Estimate, and assessment result storage will be examined into database.
As a kind of improvement of above system, the system also includes: visualization model, for extracting inspection from database
Assessment result is tested, the visual analyzing of space environment forecast quality is realized by Interactive Visualization interface and examines assessment result
Visualization;The Interactive Visualization interface shows that various problems present in whole forecast account for by Nightingale, Florence rose figure
Than showing each forecaster various problems present in forecast by parallel coordinates.
The present invention also provides a kind of computer equipment, including memory, processor and it is stored on the memory simultaneously
The computer program that can be run on the processor, the processor realize above-mentioned side when executing the computer program
Method.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has calculating
Machine program, the computer program make the processor execute above-mentioned method when being executed by a processor.
Compared with the prior art, the advantages of the present invention are as follows:
1, the present invention, which takes the lead in designing, realizes space environment forecast product gross inspection appraisal procedure and system, fills up
The blank of the existing space environmental forecasting product gross instruments of inspection realizes that real-time quality examines assessment, is space environment
Operational forecast quality controls offer system and supports;
2, method of the invention is using Historic Environment forecast model products as sample, in conjunction with space environment scientific domain feature,
Design realizes space environment domain lexicon, space environment forecast physical quantity standard unit dictionary, space environment numeric type physics
Numerical quantity range dictionary;The space environment gross method of inspection based on dictionary is devised, program scalability is improved;In sky
Between in the case where environmental forecasting corpus negligible amounts, propose the forecast content information of the rule-based neighborhood search side of extraction automatically
Method reduces the constraint of rule compared to the rule-based information extraction method of tradition, improves information extraction accuracy rate;
3, the present invention is based on the space environment domain lexicons independently refined, space environment forecast physical quantity standard unit word
Allusion quotation, space environment numeric type physical quantity numberical range dictionary, the forecast content information for proposing rule-based neighborhood search are automatic
Abstracting method, design realize space environment forecast product gross and examine appraisal procedure and system, realize that space environment is pre-
Report product gross is assessed automatically in real time.
Detailed description of the invention
Fig. 1 is space environment forecast domain lexicon of the invention;
Fig. 2 is space environment forecast physical quantity unit dictionary of the present invention;
Fig. 3 is space environment forecast numeric type physical quantity numberical range dictionary of the present invention;
Fig. 4 is space environment forecast product quality inspection assessment system block diagram of the invention.
Specific embodiment
Present invention is further described in detail with reference to the accompanying drawings and detailed description.
Embodiment 1:
The embodiment of the present invention 1 proposes a kind of space environment forecast product gross and examines appraisal procedure automatically, institute
The method of stating comprises the following steps:
Step 1) obtains space environment forecast product to be detected, which includes space environment forecast content of text, sky
Between environmental forecasting numeric type content and space environment event prediction content;
Step 2) is literary from space environment forecast using the automatic abstracting method of forecast content information of rule-based neighborhood search
This content extraction space environment forecast main element information;
It specifically includes:
Step 2-1) according to text punctuate, sentence segmentation is carried out to space environment forecast content of text, each sentence includes only
Vertical space environment event;
Wherein space environment forecast main element include: solar activity level, geomagnetic activity horizontal, solar proton event and
The sudden and violent event of high energy electron;
It is needed in space environment forecast to solar activity level, geomagnetic activity level, solar proton event and high energy electron
Sudden and violent four space-like environmental forecasting main element of event carries out descriptive grade, in order to correctly identify and assess space environment forecast
Four space-like environmental forecasting main element grades are mapped as numeric type descriptive grade by the gross of product, and space environment is pre-
Report main element grade and mapping relations particular content as follows.
1 space environment forecast main element grade of table and mapping relations
Step 2-2) using open source Chinese word segmentation kit IKAnalyzer2012, it is based on space environment forecast domain term
Allusion quotation segments sentence content, and<the form of glossarial index, word>key-value pair is converted into after participle;
It will use specific proper noun and term in space environment subject in space environment forecast, in order to correctly know
Not and the proper noun and term in space environment forecast text are split, in conjunction with space environment forecast historical product, induction and conclusion
It is used in the space environment domain lexicon of space environment forecast gross inspection, as shown in Figure 1.Space environment forecast field art
Language particular content is as follows:
2 space environment field term library of table
Space environment forecast field term and space environment domain lexicon include but is not limited to table 2 and Fig. 1.
The construction method of the space environment forecast domain lexicon includes:
Step S1) according to space environment Disciplinary Characteristics and forecast experience, formulate initial space environmental forecasting domain lexicon;
Step S2) using open source Chinese word segmentation kit IKAnalyzer2012, the space environment forecast neck based on formulation
Domain dictionary carries out text segmentation to space environment forecast historical product;
Step S3) space environment forecast word sequence after segmentation is analyzed, judge whether there is space environment forecast field term
The term of segmentation errors is added in space environment forecast domain lexicon by segmentation errors;
Step S4) repeat step S2)-step S3), until all space environment field terms are correctly split, until
This complete space environment forecast domain lexicon, which is established, to be completed.
Step 2-3) based on<form of glossarial index, word>key-value pair, for different space environment forecast main elements, system
Fixed corresponding information extraction rules, realize the information extraction of space environment forecast main element.
Wherein, the description of solar activity situation is fairly simple, using solar activity as event extraction root node, in root node week
The sequence from the near to the remote according to distance between word is enclosed, solar activity level Terminology is searched for.Solar activity event information extraction rule
Then is defined as: (<Level>)?<solar activity><Level>;
Geomagnetic activity situation describes more complicated, needs correctly to match following three days daily geomagnetic activity situations.With ground
Magnetic acitvity rank is event extraction root node, according to the search rule of time name entity before root node, and with word spacing
From sequence from the near to the remote, searched events forecast date of occurrence;After root node and before name of next time entity, look into
Look for the detailed description term of geomagnetic activity situation.Geomagnetic activity situation information extraction rules is defined as:<Date><earth magnetism><
Level>{ [<Date><earth magnetism><Level>] [<Date><earth magnetism><Level>] }.Wherein, the lookup rule of time name entity
Then include: (( d+) moon)? (( d+) (day)? ([- |~| and | extremely | arrive |, | ,]))? (( d+) moon)? (( d+) day), its
The remaining time;
Solar proton event forecast is divided into three types: event, which starts type, event duration type, event, terminates type.Root first
One of three types are divided into according to event description keyword, event starts type keyword and includes: generation, generates, reaches, thing
Part sustained keyword includes: to continue, maintain, and it includes: to terminate that event, which terminates type keyword,.Type information extraction is started for event
Rule is defined as:<Date><Level><proton event>, wherein time name entity lookup rule is defined as: (( d+) moon)?
(( d+) -)? (( d+) moon)? (( d+) day);For event duration type information extraction rules is defined as: < Date
Duration><Level><proton event>, wherein time name entity lookup rule is defined as: (( d+) -)? the day (d+),
Then according to current date, following three days corresponding proton event situations are inferred;Type information extraction rules are terminated for event
Is defined as:<Level><proton event><Date><terminates>, wherein time name entity lookup rule is defined as: (( d+)
Month)? (( d+) day) it is similar with event duration type, according to current date, infer following three days corresponding proton event feelings
Condition;
The extraction of the sudden and violent event information of high energy electron is similar with the decimation rule of geomagnetic activity information.It is primarily based on space environment
Domain lexicon, the sudden and violent event of identification high energy electron name entity, then according to the search rule of time name entity, and with word spacing
From sequence from the near to the remote, searched events forecast date of occurrence.The decimation rule of the sudden and violent event information of high energy electron is defined as: <
Date><Level><high energy electron is sudden and violent>, wherein time name entity lookup rule is defined as: (( d+) moon)? (( d+)
(day)? ([- | and | extremely |, | ,]))? (( d+) moon)? (( d+) day);
The automatic abstracting method of forecast content information of the rule-based neighborhood search proposed according to the present invention, to four space-likes
Environmental forecasting main element details are extracted.Below with country, the Chinese Academy of Sciences space science center publication on the 9th of September in 2017
Space environment forecast for be illustrated, forecast original text are as follows: " it is expected that following three days, until height, outburst in solar activity level
M grades and a possibility that above rank solar flare it is larger.By the long lasting effect of CME, earth magnetism on the 9th is still likely to be breached small magnetic storm level, 10-
Ground magnetically quiet was to perturbation on 11st.High energy proton flux of the geostationary orbit greater than 10MeV is still slowly declining, it is contemplated that proton thing
9 end of day of part.Geostationary orbit is greater than 2MeV high energy electrical flux, and on 9-11 to be likely to be breached high energy electron cruelly horizontal."
1, solar activity event information extraction
Solar activity descriptive statement is identified first, and word participle is carried out by subordinate sentence/word segmentation module.Word segmentation result are as follows:
" { 0=is estimated, 2=future, and 4=tri- days, 7=solar activity, 11=was horizontal, and 13=is medium, and 15=is arrived, 16=high, and 18=is quick-fried
Hair, 20=m grades, 23=or more, 25=rank, 27=solar flare, 30=possibility, 33=is larger } ", < word rope is converted into after participle
Draw, word > key-value pair form storage word segmentation result.Then solar activity event description keyword " solar activity " is positioned, finally
Following three days solar activity situation highest levels can be gone out with rapidly extracting according to neighborhood search strategy for " 3 ".
2, geomagnetic activity information extraction
The descriptive statement of geomagnetic activity is identified first, and word participle is carried out by subordinate sentence/word segmentation module.Word segmentation result
Are as follows: " { 0=is by 1=cme, 5=is lasting, and 7=influences, and 10=9 days, 12=earth magnetism, 15=was possible, and 17=reaches, the small magnetic of 19=
Cruelly, 22=is horizontal, 25=10-11,30=day, 31=earth magnetism, and 33=is tranquil, and 35=is arrived, 36=perturbation } ", geomagnetic activity cause
Description it is simpler, and forecast result, following three world are all clearly given to following three days daily geomagnetic activity situations
It is " [4,1,1] " that magnetic acitvity situation, which extracts result,.
3, solar proton event information extraction
The descriptive statement of solar proton event is identified first, and word participle is carried out by subordinate sentence/word segmentation module.Participle knot
Fruit are as follows: " 0=geostationary orbit, 6=are greater than, 8=10mev, 14=high energy, 16=proton, 18=flux, and 20=still exists,
22=is slow, and 24=decline, 27=is, it is expected that 29=proton event, and 33=9 days, 35=terminated } ", analysis present case belongs to event
Terminate forecast, then extract the Close Date of event prediction, is finally extrapolated according to current date and Close Date three days following
Proton event information.It is " [1,0,0] " that present case, which extracts result,
4, the sudden and violent event information extraction of high energy electron
The descriptive statement of the sudden and violent event of identification high energy electron first, and word participle is carried out by subordinate sentence/word segmentation module.Participle
As a result are as follows: " 0=geostationary orbit, 6=are greater than, 8=2mev, 12=high energy electrical flux, and 19=9-11,23=days, 24
=may, 26=reaches, and 28=high energy electron is sudden and violent, and 33=is horizontal } ", the sudden and violent event of identification high energy electron names entity, then according to
Time names the search rule of entity, and the sequence with distance between word from the near to the remote, and searched events forecast date of occurrence, high energy electricity
It is " [1,1,1] " that sub sudden and violent event information, which extracts result,.
Step 3) examines evaluation index to carry out gross to space environment forecast product according to space environment gross
Assessment is examined, and assessment result storage will be examined into database;
Space environment gross examine evaluation index include: forecast model products publication punctuality, text spelling accuracy,
Physical quantity unit accuracy, value data accuracy and the forecast self-consistent property of content.
The punctuality of the forecast model products publication, refers to whether defined timing node completes the publication of forecast model products.
By comparing the issuing time of defined timing node and forecast model products, determine that forecast model products publication is asked with the presence or absence of punctuality
Topic.
The text spells accuracy, refers to whether the text spelling in the space environment forecast product of generation is correct.This
The word that forecast model products text segmentation goes out is searched in invention in space environment domain lexicon, if searched in dictionary less than correspondence
Word, then illustrating that the word may misspelling.
Whether just the physical quantity unit accuracy refers to the unit of physical quantity in the space environment forecast product of generation
Really.The present invention formulates space environment forecast physical quantity unit dictionary first, then identifies dictionary in space environment forecast text
Defined in physical quantity if identified successfully physical quantity is extracted using physical quantity information decimation rule defined in dictionary
Unit information determines whether physical quantity unit is accurate in forecast model products.
It needs to describe specific physical quantity in space environment forecast, but due to a variety of causes such as clerical mistakes, will cause description object
The single bit error of reason amount goes out physical quantity unit mistake present in forecast model products in order to real-time detection, has formulated spatial loop
Border forecast physical quantity unit dictionary makes in shelf space environmental forecasting as shown in Fig. 2, dictionary is stored by way of key-value pair
Physical quantity and corresponding physical quantity unit.Space environment forecast physical quantity unit dictionary includes but is not limited to Fig. 2.
The value data accuracy, refers to whether the numerical value of physical quantity data in the space environment forecast product of generation surpasses
Cross its zone of reasonableness.The present invention formulates space environment forecast numeric type physical quantity numberical range dictionary first, is forecast by judgement
Whether the numerical value of physical quantity in the reasonable scope, determines forecast model products with the presence or absence of value data accuracy problem in product.
The inspection of space environment forecast numeric type content gross is that the reasonability of exponent value range is checked, in order to
Enough real-time detections go out obvious numberical range mistake present in forecast model products, have formulated space environment forecast numeric type physical quantity number
It is worth range dictionary, as shown in figure 3, dictionary is stored by way of key-value pair, numeric type used in shelf space environmental forecasting
Physical quantity and corresponding numerical value zone of reasonableness.Space environment forecast numeric type physical quantity numberical range dictionary includes but is not limited to scheme
3。
The self-consistent property of forecast content, refers to space environment forecast content of text and space environment event prediction content
Between consistency problem.The invention firstly uses the automatic abstracting methods of the forecast content information of rule-based neighborhood search to extract
Space environment forecast main element information described in space environment forecast content of text, then and in space environment event prediction
Space environment main element class information, space environment main element probabilistic information in appearance compare, and determine space environment
Forecast model products whether there is consistency problem.
1, the punctuality of forecast model products publication
From space environment forecast product library obtain forecast model products issuing time, and with defined issuing time pair the latest
Than otherwise examining and not passing through if issuing time is upchecked earlier than the stipulated time.And forecast model products publication punctuality is beaten
Point.It upchecks and gets a mark of 100, examine not by obtaining 0 point.
2, text spells accuracy
Text spells Test of accuracy and first segments space environment forecast text to be detected, then checks the word separated
Whether appear in space environment domain lexicon, if the word separated does not appear in domain lexicon, it is considered that forecast produces
There may be problems for the spelling of product text.The neologisms in product to be detected there may be problem are recorded, text spelling accuracy is beaten
Point.There is problem at 1, obtains 50 points;Problem at more than or equal to 2 obtains 0 point;There is no problem, wins the full 100 marks.
3, physical quantity unit accuracy
Physical quantity unit Test of accuracy is to carry out Test of accuracy to the physical quantity unit occurred in forecast model products.First
It determines the physical quantity for needing to examine, physical quantity unit is determined from space environment physical quantity unit dictionary.Then to be detected pre-
Identify physical quantity to be detected and extracts physical amount unit in report product, corresponding accurate physical quantity unit ratio after group and in dictionary
It is right, if physical quantity unit compares successfully, upcheck, otherwise examines and do not pass through.Occur the physical quantity of mistake in records tests,
And errors number, it is given a mark according to errors number to physical quantity unit accuracy.There is mistake at 1, obtains 50 points;At 2
Mistake obtains 0 point;There is no mistake, wins the full 100 marks.
4, value data accuracy
The inspection of value data is the inspection to space environment index class forecast model products.The index for needing to examine is determined first
Class product determines the zone of reasonableness of the product from space environment forecast numeric type physical quantity numberical range dictionary.Then it extracts
Corresponding index class forecast model products check whether to have exceeded reasonable value data range.Numerical value in the reasonable scope, is examined logical
It crosses, otherwise, inspection does not pass through.The physical quantity and Problem-Error for exceeding zone of reasonableness in records tests, according to problem number logarithm
It gives a mark according to Numerical accuracy.There is problem at 1, obtains 50 points;Problem at more than or equal to 2 obtains 0 point;There is no problem, gets full marks 100
Point.
5, the self-consistent property of content is forecast
After extracting space environment forecast main element information, consistency check is done to space environment forecast product, it is main
It to include space environment forecast probability of happening consistency and space environment forecast main element ranking consistence.Space environment forecast
Probability of happening consistency shows that event occurrence rate answers height when space environment forecast main element grade reaches certain rank
In certain threshold value.If the sudden and violent event class of high energy electron is orange, then the sudden and violent event occurrence rate forecast of high energy electron should be higher than that
50%.Space environment forecast main element ranking consistence shows space environment described in space environment forecast content of text
Environmental forecasting main element grade should be corresponding with the space environment forecast main element grade in space environment event prediction content.
The event description of inconsequent in records tests gives a mark to the self-consistent property of forecast content according to problem number.Occur asking at 1
Topic, obtains 50 points;Problem at more than or equal to 2 obtains 0 point;There is no problem, wins the full 100 marks.
Step 4) realizes visual analyzing and the inspection of space environment forecast gross using Interactive Visualization interface
The visualization of assessment result;
Interactive Visualization interface includes that Nightingale, Florence rose figure shows various problem accountings present in whole forecast, puts down
Row coordinate shows the statistical graphs such as each forecaster various problems present in forecast.
Embodiment 2
The assessment is examined to be automatically as shown in Fig. 2, the embodiment of the present invention 2 proposes a kind of space environment forecast product quality
System, the system includes:
Space environment forecast product database, for obtaining space environment forecast product;
Space environment forecast domain lexicon, in view of assessment object space environmental forecasting corpus negligible amounts, and corpus format
It is more unified, used in vocabulary of terms it is relatively fixed, the invention proposes based on Historic Environment forecast corpus
Space environment forecast domain lexicon construction method;
Subordinate sentence/word segmentation module, the module are based on space environment using open source Chinese word segmentation kit IKAnalyzer2012
It forecasts that domain lexicon realizes the participle of space environment forecast product, is converted into that<form of glossarial index, word>key-value pair is deposited after participle
Storage;
Space environment forecast main element information extraction module, the module realize that name is real on the basis of subordinate sentence/participle
Body identification, extracts space environment forecast main element details described in space environment forecast content of text, needle of the present invention
Feature is described to different space environment forecast main elements, the forecast content information for proposing rule-based neighborhood search is automatic
Abstracting method;Identification is main including space environment forecast field term, date, number of days, space environment forecast in real time for the name
The identification of element rank etc..
Quality inspection evaluation module, the module spell accuracy, physics by punctuality, the text issued to forecast model products
Unit accuracy, value data accuracy, the comprehensive analysis for forecasting the self-consistent property of content are measured, to space environment forecast product base
This quality is tested and is assessed;
Visualization model, the module realize space environment forecast gross by design Interactive Visualization interface
Visual analyzing and the visualization for examining assessment result.The Interactive Visualization interface is shown whole by Nightingale, Florence rose figure
Various problem accountings present in body forecast, show each forecaster various problems present in forecast by parallel coordinates.
And be equipped with details list and interactive measured data chart, realize space environment forecast gross visual analyzing and
Examine the visualization of assessment result.
Embodiment 3
The embodiment of the present invention 3 provides a kind of computer equipment, including memory, processor and is stored in the storage
On device and the computer program that can run on the processor, the processor are realized above-mentioned when executing the computer program
Space environment forecast product quality examine appraisal procedure automatically.
Embodiment 4
The embodiment of the present invention 4 provides a kind of computer readable storage medium, and the computer readable storage medium is deposited
Computer program is contained, when the computer program makes the processor execute the computer program when being executed by a processor
Realize that above-mentioned space environment forecast product quality examines appraisal procedure automatically.
It should be noted last that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting.Although ginseng
It is described the invention in detail according to embodiment, those skilled in the art should understand that, to technical side of the invention
Case is modified or replaced equivalently, and without departure from the spirit and scope of technical solution of the present invention, should all be covered in the present invention
Scope of the claims in.
Claims (10)
1. a kind of space environment forecast product gross examines appraisal procedure automatically, which comprises
Space environment forecast product to be detected is obtained, the space environment forecast product includes in space environment forecast text
Appearance, space environment forecast numeric type content and space environment event prediction content;
Using the automatic abstracting method of forecast content information of rule-based neighborhood search, taken out from space environment forecast content of text
Take corresponding space environment forecast main element information;
Examine evaluation index to space environment forecast main element information, space environment forecast number according to space environment gross
Value type content and space environment event prediction content carry out gross and examine assessment, and assessment result storage will be examined to data
In library.
2. space environment forecast product gross according to claim 1 examines appraisal procedure automatically, which is characterized in that
The method also includes: it is extracted from database and examines assessment result, realize that space environment is pre- using Interactive Visualization interface
The visual quality analysis for reporting product and the visualization for examining assessment result;The Interactive Visualization interface includes Nightingale, Florence
Rose figure shows that various problem accountings present in whole forecast, parallel coordinates show that each forecaster is each present in forecast
Kind problem.
3. space environment forecast product gross according to claim 1 or 2 examines appraisal procedure automatically, feature exists
In the automatic abstracting method of forecast content information using rule-based neighborhood search, from space environment forecast content of text
It is middle to extract corresponding space environment forecast main element information;It specifically includes:
Sentence segmentation is carried out to space environment forecast content of text according to text punctuate, each sentence includes that independent space environment is pre-
Report main element;The space environment forecast main element includes: solar activity level, geomagnetic activity level, solar proton thing
Part and the sudden and violent event of high energy electron;
Using open source Chinese word segmentation kit IKAnalyzer2012, it is based on space environment forecast domain lexicon, to sentence content
It is segmented,<the form of glossarial index, word>key-value pair is converted into after participle;
Based on<glossarial index, word>key-value pair formulate corresponding information extraction rule for different space environment forecast main elements
Then, corresponding space environment forecast main element information is extracted from space environment forecast content of text.
4. space environment forecast product gross according to claim 3 examines appraisal procedure automatically, which is characterized in that
The construction step of the space environment forecast domain lexicon includes:
Step S1) according to space environment Disciplinary Characteristics and forecast experience, formulate space environment forecast domain lexicon;
Step S2) using open source Chinese word segmentation kit IKAnalyzer2012, it is based on space environment forecast domain lexicon, to sky
Between environmental forecasting historical product carry out text segmentation, obtain space environment forecast word sequence;
Step S3) analysis space environmental forecasting word sequence, space environment forecast field term segmentation errors are judged whether there is, it will
The term of segmentation errors is added in space environment forecast domain lexicon;
Step S4) repeat step S2)-step S3), until all space environment field terms are correctly split, then spatial loop
Forecast that domain lexicon building is completed in border.
5. space environment forecast product gross according to claim 4 examines appraisal procedure automatically, which is characterized in that
It includes: the punctuality of forecast model products publication, text spelling accuracy, physics that the space environment gross, which examines evaluation index,
Measure unit accuracy, value data accuracy and the forecast self-consistent property of content;
The punctuality of the forecast model products publication, refers to whether defined timing node completes the hair of space environment forecast product
Cloth;
The text spells accuracy, refers to whether the text spelling in the space environment forecast product of generation is correct;
The physical quantity unit accuracy refers to the space environment forecast physical quantity unit dictionary according to formulation, judges spatial loop
Whether the unit of physical quantity is correct in the forecast model products of border;
The value data accuracy refers to the space environment forecast numeric type physical quantity numberical range dictionary according to formulation, sentences
Whether the numerical value of physical quantity data is more than its zone of reasonableness in disconnected space environment forecast product;
The self-consistent property of forecast content, refers between space environment forecast content of text and space environment event prediction content
It is whether consistent.
6. space environment forecast product gross according to claim 5 examines appraisal procedure automatically, which is characterized in that
It is described to examine evaluation index to space environment forecast main element information, space environment forecast number according to space environment gross
Value type content and space environment event prediction content carry out gross and examine assessment, specifically include:
The issuing time of space environment forecast product to be detected is obtained, and is compared with defined issuing time the latest, if publication
Time earlier than the stipulated time, upchecks, and otherwise examines and does not pass through;And it is punctual to the publication of space environment forecast product to be detected
Property marking;
Space environment forecast product content of text to be detected is segmented, then checks whether the word separated appears in space environment neck
In the dictionary of domain, if do not occurred, then it is assumed that there may be problems for the spelling of forecast model products text;It is pre- to record space environment to be detected
There may be the neologisms of problem in report product, the text spelling accuracy marking to space environment forecast product to be detected;
It determines the physical quantity for needing to examine, physical quantity unit is determined from space environment physical quantity unit dictionary;Then to be checked
It surveys in space environment forecast product and identifies physical quantity to be detected and extracts physical amount unit, it is corresponding accurate in last and dictionary
Physical quantity unit compares, if physical quantity unit compares successfully, upchecks, otherwise examines and do not pass through;Occur in records tests
The physical quantity and errors number of mistake give a mark to physical quantity unit accuracy according to errors number;
It determines the index class product for needing to examine, the production is determined from space environment forecast numeric type physical quantity numberical range dictionary
The zone of reasonableness of product;Then corresponding index class forecast model products are extracted, check whether to have exceeded reasonable value data range;Such as
Fruit numerical value in the reasonable scope, is upchecked, and otherwise, inspection does not pass through;In records tests beyond zone of reasonableness physical quantity and
Problem-Error gives a mark to data Numerical accuracy according to problem number;
Judge the consistency of space environment forecast main element information Yu space environment event prediction content, comprising: space environment
Forecast events probabilistic consistency and space environment forecast main element ranking consistence;Space environment forecast probability of happening consistency
Show that event occurrence rate should be higher than that certain threshold value when space environment forecast main element grade reaches certain rank;It is empty
Between environmental forecasting main element ranking consistence show that space environment environmental forecasting main element grade should be with space environment thing
Part forecasts that the space environment forecast main element grade in content is corresponding;The space environment forecast of inconsequent in records tests
Main element gives a mark to the self-consistent property of forecast content according to problem number.
7. a kind of space environment forecast product gross examines assessment system automatically, the system includes:
Space environment forecast product database is used for memory space environmental forecasting product;The space environment forecast product includes
Space environment forecast content of text, space environment forecast numeric type content and space environment event prediction content;
Space environment forecast domain lexicon, for recording proper noun and term in space environment forecast text;
Subordinate sentence/word segmentation module, for carrying out sentence segmentation, each packet to space environment forecast content of text according to text punctuate
Containing independent space environment forecast main element;Using open source Chinese word segmentation kit IKAnalyzer2012, it is based on spatial loop
Domain lexicon is forecast in border, segments to sentence content,<the form of glossarial index, word>key-value pair is converted into after participle;
Space environment forecast element information abstraction module is also used to for realizing name Entity recognition based on<glossarial index, word>key
Value pair formulates corresponding information extraction rules for different space environment forecast main elements, realizes space environment forecast master
Element information is wanted to extract;
Gross examines evaluation module, for examining evaluation index to space environment forecast master according to space environment gross
It wants element information, space environment forecast numeric type content and space environment event prediction content to carry out gross and examines assessment,
And assessment result storage will be examined into database.
8. space environment forecast product gross according to claim 7 examines assessment system automatically, the system is also
Include: visualization model examines assessment result for extracting from database, realizes spatial loop by Interactive Visualization interface
The visual analyzing of border quality of forecast and the visualization for examining assessment result;The Interactive Visualization interface passes through Nightingale, Florence
Rose figure shows various problem accountings present in whole forecast, shows that each forecaster exists in forecast by parallel coordinates
Various problems.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor is realized in claim 1 to 6 when executing the computer program
Described in any item methods.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make the processor perform claim require 1 to 6 described in any item sides when being executed by a processor
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284784.8A CN110110969A (en) | 2019-04-10 | 2019-04-10 | A kind of space environment forecast product gross examines appraisal procedure and system automatically |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284784.8A CN110110969A (en) | 2019-04-10 | 2019-04-10 | A kind of space environment forecast product gross examines appraisal procedure and system automatically |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110969A true CN110110969A (en) | 2019-08-09 |
Family
ID=67484068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910284784.8A Pending CN110110969A (en) | 2019-04-10 | 2019-04-10 | A kind of space environment forecast product gross examines appraisal procedure and system automatically |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110969A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639301A (en) * | 2020-05-26 | 2020-09-08 | 国家卫星气象中心(国家空间天气监测预警中心) | Geomagnetic Ap index medium-term forecasting method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104166682A (en) * | 2014-07-21 | 2014-11-26 | 安徽华贞信息科技有限公司 | Method and system for extracting natural-language-like semantic information on the basis combinatorial theory |
CN105279149A (en) * | 2015-10-21 | 2016-01-27 | 上海应用技术学院 | Chinese text automatic correction method |
CN108073571A (en) * | 2018-01-12 | 2018-05-25 | 中译语通科技股份有限公司 | A kind of multi-language text method for evaluating quality and system, intelligent text processing system |
WO2018220688A1 (en) * | 2017-05-29 | 2018-12-06 | 株式会社Pfu | Dictionary generator, dictionary generation method, and program |
CN109101483A (en) * | 2018-07-04 | 2018-12-28 | 浙江大学 | A kind of wrong identification method for electric inspection process text |
-
2019
- 2019-04-10 CN CN201910284784.8A patent/CN110110969A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104166682A (en) * | 2014-07-21 | 2014-11-26 | 安徽华贞信息科技有限公司 | Method and system for extracting natural-language-like semantic information on the basis combinatorial theory |
CN105279149A (en) * | 2015-10-21 | 2016-01-27 | 上海应用技术学院 | Chinese text automatic correction method |
WO2018220688A1 (en) * | 2017-05-29 | 2018-12-06 | 株式会社Pfu | Dictionary generator, dictionary generation method, and program |
CN108073571A (en) * | 2018-01-12 | 2018-05-25 | 中译语通科技股份有限公司 | A kind of multi-language text method for evaluating quality and system, intelligent text processing system |
CN109101483A (en) * | 2018-07-04 | 2018-12-28 | 浙江大学 | A kind of wrong identification method for electric inspection process text |
Non-Patent Citations (1)
Title |
---|
周学广: "《信息内容安全》", 30 November 2012, 武汉:武汉大学出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639301A (en) * | 2020-05-26 | 2020-09-08 | 国家卫星气象中心(国家空间天气监测预警中心) | Geomagnetic Ap index medium-term forecasting method |
CN111639301B (en) * | 2020-05-26 | 2023-05-23 | 国家卫星气象中心(国家空间天气监测预警中心) | Geomagnetic Ap index medium-term forecasting method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Caro et al. | intsvy: An R package for analyzing international large-scale assessment data | |
Hershberger et al. | Modeling intraindividual variability with repeated measures data: Methods and applications | |
Vassend et al. | The NEO personality inventory revised (NEO-PI-R): Exploring the measurement structure and variants of the five-factor model | |
CN108733793B (en) | Ontology model construction method and system for relational database | |
Byrne et al. | Factorial structure of the family values scale from a multilevel-multicultural perspective | |
CN102662930A (en) | Corpus tagging method and corpus tagging device | |
CN102119385A (en) | Method and subsystem for searching media content within a content-search-service system | |
CN102930048B (en) | Use the data rich found automatically with reference to the semanteme with vision data | |
CN109739997A (en) | Address control methods, apparatus and system | |
CN112925901B (en) | Evaluation resource recommendation method for assisting online questionnaire evaluation and application thereof | |
Smith et al. | The impact of using incorrect weights with the multiple membership random effects model | |
CN110298597A (en) | A kind of assessment method, device and storage medium | |
Ureña-Cámara et al. | A method for checking the quality of geographic metadata based on ISO 19157 | |
CN110888989A (en) | Intelligent learning platform and construction method thereof | |
CN110110969A (en) | A kind of space environment forecast product gross examines appraisal procedure and system automatically | |
Malik et al. | Student query trend assessment with semantical annotation and artificial intelligent multi-agents | |
Yeung et al. | Computational narrative mapping for the acquisition and representation of lessons learned knowledge | |
US11500885B2 (en) | Generation of insights based on automated document analysis | |
Handayani et al. | Designing Popular Classes on Viewboard Public Assessment of Lectures Based on YII Framework | |
Liu et al. | Construction of intelligent query system for metro electromechanical equipment faults based on the knowledge graph | |
Hara et al. | Development of methods to extract place names and estimate their places from Web newspaper articles | |
AbuJarour et al. | Automatic sampling of web services | |
KR100700376B1 (en) | Real-time quality measurement method of bibliographic database | |
CN117236648B (en) | Intelligent system for talent recruitment and matching | |
CN112015780B (en) | Intelligent proposition analysis processing method and system based on deep learning |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |