CN107562814A - A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system - Google Patents
A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system Download PDFInfo
- Publication number
- CN107562814A CN107562814A CN201710692655.3A CN201710692655A CN107562814A CN 107562814 A CN107562814 A CN 107562814A CN 201710692655 A CN201710692655 A CN 201710692655A CN 107562814 A CN107562814 A CN 107562814A
- Authority
- CN
- China
- Prior art keywords
- information
- network information
- segmented
- text
- speech
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system.Methods described includes：By data reptile instrument, objective network information is captured；The objective network information grabbed is segmented, and marks part of speech, obtains text participle information；Information is segmented according to the initial weight of preset keyword and the text, calculates the scale value that refers generally to of the objective network information, and to information type corresponding to objective network information matching.Method provided by the invention, according to the characteristics of Earthquake emergency information different type, by being segmented to the network information, the accuracy of grouped data is ensure that according to Keyword Weight progress text classification.The present invention on the whole, constructs the emergency information index system of public participation, realizes emergency information Quick Acquisition and extracting tool, and extends the information source of earthquake emergency, improves the ageing and accuracy of earthquake disaster emergency service.
Description
Technical field
The present invention relates to Computer Science and Technology field, is obtained more particularly, to a kind of earthquake emergency and the condition of a disaster information
Take sorting technique and system.
Background technology
China is the more country of the accident such as natural calamity, an accident, and disaster species is more, disaster occurs
Frequency is high, casualty loss is serious.At the same time, and in the world most strong and earthquake disaster most serious the country of seismic activity
One of.Wenchuan earthquake in 2008, Lushan earthquake in 2013 all bring huge economic loss.And earthquake emergency commanding arrives
Position and the achievement for being related to the disaster relief in time.
7.2 grades of earthquakes of nineteen ninety-five Japan's slope god, the 7.8 grades of earthquakes of Turkey's Izmit in 1999 and India's Gu in 2001
Why the post-earthquake emergency response of 7.9 grades of earthquakes of Ji Latebang is slow in action, commanding and decision-making is not in place, even be delayed the disaster relief when
Machine etc., it is particularly since and lacks timely and accurate, comprehensive Informational support.On the contrary, Los Angeles,U.S in 1994-
During the northern 7.1 grades of earthquakes in ridge, the earthquake emergency commanding technological system under being supported due to Earthquake emergency information has played important function,
Information and the technical support of key are provided for Emergency decision, effectively alleviates earthquake disaster damage.Can be with by above-mentioned example
Find out, Earthquake emergency information occupies core status in earthquake emergency mechanism.In recent years, China pays much attention to earthquake emergency work
Make, set up within 2000 State Council's earthquake relief headquarter, set up within 2001 national antidetonation rescue group and embodied country
Attention for earthquake emergency Mechanism establishing.Earthquake emergency refers to the various Emergency Preparedness that ruinous earthquake is done before and after occurring
And the urgent rescue and relief work action taken after the earthquake.
After the earthquake, both implied in substantial amounts of micro-blog information studied and judged available for the condition of a disaster, rescue guarantee etc. it is valuable
Emergency information, while there is also the redundancy of many, deceptive information, this category information to shake rescue and play interference effect over the ground,
On the other hand there is also the problems such as data volume is huge, true and information category is various so that target information is extracted and produces obstruction.
The content of the invention
For the present invention to overcome in the prior art, can not be directed to earthquake information data huge in network after earthquake can not
The problem of effectively being classified, propose a kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system.
According to the first aspect of the invention, there is provided a kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique, including：
S1, by data reptile instrument, capture objective network information；；
S2, the objective network information grabbed is segmented, and mark part of speech, obtain text participle information；
S3, information is segmented according to the initial weight of preset keyword and the text, calculates the objective network information
Scale value is referred generally to, and to information type corresponding to objective network information matching.
Wherein, the network information is included at least one in the mhkc network information, news network information and micro blog network information
The kind network information.
Wherein, also include after the S1：Based on the training text for completion of classifying under manual intervention, keyword is calculated
Weight.
Wherein, the data based on completion of classifying under manual intervention, the step of calculating the weight of preset keyword, are specific
Including：
According to the training text, descriptor is extracted；
The word frequency and inverse document frequency of preset keyword in the training text are calculated using TF-IDF algorithms, is led
The classified weight table of epigraph.
Wherein, participle is carried out to the network information of the crawl in the S2 to specifically include：
S21, segmented using the network information captured described in NLPIR Words partition systems；
S22, part-of-speech information is marked, extract location information and temporal information, and the part-of-speech information is saved into data
Storehouse.
Wherein, it is described to be segmented specially using the network information captured described in NLPIR Words partition systems：Pass through N member texts
Method model algorithm, the network information is segmented.
Wherein, the mark part-of-speech information is specially：By HMM part-of-speech tagging algorithm, described in mark
Part of speech of the network information after participle.
According to the second aspect of the invention, there is provided a kind of earthquake emergency and the condition of a disaster acquisition of information categorizing system, including：
Data acquisition module, for by data reptile instrument, capturing objective network information；
Word-dividing mode, the objective network information grabbed is segmented, and mark part of speech, obtain text participle
Information
Sort module is calculated, for the initial weight according to preset keyword and text participle information, described in calculating
Objective network information refers generally to scale value, and to information type corresponding to objective network information matching.
According to the third aspect of the invention we, there is provided a kind of computer-readable recording medium, be stored thereon with computer journey
Sequence, a kind of earthquake emergency that the various possible implementations that the program is executed by processor above-mentioned first aspect are provided and
The condition of a disaster acquisition of information sorting technique.
According to the fourth aspect of the invention, there is provided a kind of earthquake emergency and the condition of a disaster acquisition of information sorting device, including：
At least one processor；And
At least one memory being connected with the processor, wherein：
The memory storage has and can call described program by the programmed instruction of the computing device, the processor
Instruction is able to carry out operating as follows：
By data reptile instrument, objective network information is captured；
The objective network information grabbed is segmented, and marks part of speech, obtains text participle information；
According to the initial weight of preset keyword and text participle information, the total of the objective network information is calculated
Body desired value, and to information type corresponding to objective network information matching.
Method provided by the invention, according to the characteristics of Earthquake emergency information different type, by dividing the network information
Word, the accuracy of grouped data is ensure that according to Keyword Weight progress text classification.On the whole, public participation is constructed
Emergency information index system, realize emergency information Quick Acquisition and extracting tool, and extend the information of earthquake emergency
Source, improve the ageing and accuracy of earthquake disaster emergency service.
Brief description of the drawings
Fig. 1 is the bulk flow of a kind of earthquake emergency that one embodiment of the invention provides and the condition of a disaster acquisition of information sorting technique
Journey schematic diagram；
Fig. 2 is that descriptor is weighed in a kind of earthquake emergency provided in an embodiment of the present invention and the condition of a disaster acquisition of information sorting technique
Re-computation schematic flow sheet；
Fig. 3 is participle and word in a kind of earthquake emergency provided in an embodiment of the present invention and the condition of a disaster acquisition of information sorting technique
Property annotation step schematic flow sheet；
Fig. 4 is a kind of earthquake emergency provided in an embodiment of the present invention and the structural representation of the condition of a disaster acquisition of information categorizing system
Figure；
A kind of Fig. 5 earthquake emergencies provided in an embodiment of the present invention and the structure chart of the condition of a disaster acquisition of information sorting device.
Embodiment
With reference to the accompanying drawings and examples, the embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
With reference to figure 1, Fig. 1 is a kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique that one embodiment of the invention provides
Flow chart, methods described includes：
S1, by data reptile instrument, capture objective network information.
Specifically, turn-on data reptile instrument, and descriptor is set and preserves database information；By monitoring descriptor,
The Webpage for possessing related subject word is captured, obtains the network information related to earthquake, and periodic refreshing interface,
If fresh information is then grabbed into database.
Web crawlers is a kind of program for capturing info web automatically according to established rule, and it is from an initial link
Start to access, the link included in the webpage having access to or network documentation is put into queue to be visited, afterwards from team
New connection is taken out in row to continue to access, and activity above is then repeated, untill termination condition is met.
By the method, by web crawlers instrument, quickly the information in network can be captured, and passes through
Descriptor is set, so as to more accurately capture news and various information about earthquake in network.
S2, the objective network information grabbed is segmented, and mark part of speech, obtain text participle information.
Specifically, being segmented to the information crawled, and mark part of speech.Wherein part of speech mark table is as shown in table 1.
Table 1：Part of speech marks table
The text data of crawl is segmented using NLPIR participle instruments, so as to which the network information is split as into multiple words
The text participle information of composition, while each word to splitting out carries out the mark of part of speech, and the network information will be carried out
Text message after word segmentation processing is stored in database.
By the method, the word composition in the earthquake information obtained from network can be quickly distinguished, so as to fast
Speed, targetedly extraction includes the information for specifying part of speech.
S3, information is segmented according to the initial weight of preset keyword and the text, calculates the objective network information
Scale value is referred generally to, and to information type corresponding to objective network information matching.
Specifically, using descriptor classified weight table, term weighing matching is carried out to the word of upper step participle, it is accumulative to ask
With obtain total weight of text, the principle based on statistics, a word or phrase are characterized for a text with TF-IDF values
Important degree size.Some word is for the significance level of a text and its frequency occurred in this text into just
Than, but be inversely proportional with its frequency in whole corpus.
By selecting the theme of weight limit to be used as the affiliated classification of Seismic net information, by Seismic net information and its
Affiliated classification matched.
By the method, attempt to believe earthquake emergency using the reverse text matches algorithm based on descriptor weight
Breath and the condition of a disaster information carry out text classification, and combine practical application with web crawlers, ensure that the accurate of grouped data
Property.Emergency information Quick Acquisition and extracting tool are realized, improves the ageing and accuracy of earthquake disaster emergency service.
On the basis of above-described embodiment, the network information includes the mhkc network information, news network information and microblogging
At least one of network information network information.
Specifically, pass through microblog data reptile module, mhkc data reptile module and news website data reptile module point
The other information in microblogging, the information in information and news website in mhkc are extracted, wherein, microblog data reptile mould
Block captures the page info, and periodic refreshing interface, if fresh information is then grabbed by monitoring s.weibo.com/ descriptor
Enter database；Mhkc data reptile module is scanned to all models of mhkc, content of pages is captured, by model theme, note
Son is replied, and information-reply deposit database；News website data reptile module is scanned to news information in website, is grabbed
Content of pages is taken, headline, is given a news briefing the time at news spokesman, and news content deposit database.
By the method, three kinds of Network Information Sources have chosen according to network information feature, ensure that the various of information source
Property.
Also include the training text based on completion of classifying under manual intervention on the basis of above-described embodiment, after the S1
This, calculates the weight of keyword.
Wherein, the data based on completion of classifying under manual intervention, the step of calculating the weight of preset keyword, are specific
Including：
According to the training text, descriptor is extracted；
The word frequency and inverse document frequency of keyword in the training text are calculated using TF-IDF algorithms, obtains descriptor
Classified weight table.
Specifically, algorithm flow to part earthquake emergency and the condition of a disaster information as shown in Fig. 2 first carry out manual sort, preservation
For training text, the descriptor in training text is extracted, descriptor classification chart is as shown in table 2.
Table 2：Descriptor classification chart
Using TF-IDF algorithms, the word frequency and inverse document frequency of descriptor in training text are calculated, it is each so as to calculate
The weight of descriptor, obtain the classified weight table of descriptor.
Wherein TF-IDF calculation formula is：
TF-IDF=TF × IDF
Wherein TF represents the frequency that entry occurs in classification based training text, i.e. word frequency, and IDF represents inverse document frequency, i.e.,
Number of files comprising entry is fewer, and the entry is stronger to the separating capacity of document.Using TF-IDF algorithms, training text is calculated
The word frequency and inverse document frequency of middle keyword, so as to which the classified weight of descriptor be calculated, descriptor weight table is formed, is protected
Save as text.
On the basis of the various embodiments described above, with reference to figure 3, the network information of the crawl is segmented in the S2
Specifically include：
S21, segmented using the network information captured described in NLPIR Words partition systems；
S22, part-of-speech information is marked, extract location information and temporal information, and the part-of-speech information is saved into data
Storehouse.
Wherein, it is described to be segmented specially using the network information captured described in NLPIR Words partition systems：Pass through N member texts
Method model algorithm, the network information is segmented.
Wherein, the mark part-of-speech information is specially：By HMM part-of-speech tagging algorithm, described in mark
Part of speech of the network information after participle.
Specifically, language material object is pre-processed：Just it is cut into according to the progress such as punctuation mark, space, carriage return character short
Sentence；Short sentence is carried out to carry out atom cutting by rule：Numeral, hyphen and Chinese character are all the rules of atom cutting；With
N- shortest paths carry out thick cutting：Part-of-speech tagging (POS...) is carried out for each atom, after having marked, to each atom
Matched backward according to dictionary maximum possible into word, initial position of these words in sentence and end position are entered
Row record, initial participle is completed, and the result of record is formed into 2 fork tabular forms；From y-bend list in word segmentation result, meter
Calculate be likely to become front and rear word two-by-two between smoothness (i.e. twice may be independently into the possibility of word)；Utilize N- shortest paths
Segmentation methods (are similar to Dijkstra shortest path first thoughts, simply need the beeline calculated to top n node)
N number of possible 2 fork participle path is calculated；To this word segmentation result, according to unknown word identification regular (name, place name, machine
Structure name recognition rule) identification of unregistered word is carried out, and carry out part-of-speech tagging using HMM；To whole point
Word result carries out part-of-speech tagging using HMM；The carry out repeated to other such as folded words, part of speech is further
Merging treatment；Obtain final word segmentation result.
Specifically, the N-gram model algorithm formula being related to during described text participle is
P(W)≈P(W1)P(W2/W1)ПI=3 ... n P(Wi/IWi-2Wi-1)
Here by taking N=3 as an example, wherein P represents the probability that W occurs, w1,w2,w3,...,wnIt is the character string that length is n,
P (A/B) represents the probability that A occurs under B, it is specified that any word wiIt is only related to its first two.
After being segmented again to information and marking part of speech, place and temporal information can further be extracted, on ground
Point information extraction in HMM part-of-speech tagging algorithm be：
First, W=w is made1w2…wnThe word string being made up of n word, T=t1t2…tnIt is mark string corresponding to word string W,
Wherein tkIt is wkPart-of-speech tagging；Further according to HMM, calculate and cause conditional probability P (T | W) maximum situation of value
T '=argmaxP (T | W).
Then according to Bayesian formula：P (T | W)=P (T) * P (W | T)/P (W).Because word string is constant, p (W) does not influence
Total probable value, therefore continue to be reduced to：P (T | W)=P (T) * P (W | T).Wherein p (T)=p (t1|t0)*p(t2|t1)…p
(ti|ti-1).According to single order HMM independence assumption, can obtain：P (T)=p (t1|t0)*p(t2|t1)…p(ti|
ti-1), i.e. P (ti|ti-1T in)=training corpusiAppear in ti-1T in number/training corpus afterwardsi-1The total degree of appearance.
According to Bayesian formula：P (W | T)=p (w1|t1)*p(w2|t2, t1)…p(wi|ti,ti-1,…,t1) and according to one
Rank HMM independence assumption：P (W | T)=p (w1|t1)*p(w2|t2)…p(wi|ti).It can obtain：P(wi|ti)=
W in training corpusiPart of speech be marked as tiNumber/training corpus in ti occur total degree.
Then, part-of-speech information is marked, extraction belongs to the information of place (ns) and time (t), is saved into database.
By the method, analyzed by Text Feature Extraction, obtain the contents such as scene, the time of origin of earthquake, by information
It is divided into multiple classifications and is stored in database；By exporting Excel file, derived information content, affiliated classification, scene etc.
Function, emergency information Quick Acquisition and extracting tool are realized, improve the ageing and accuracy of earthquake disaster emergency service.
With reference to figure 4, Fig. 4 is a kind of earthquake emergency provided in an embodiment of the present invention and the condition of a disaster acquisition of information categorizing system
Mechanism map, the system include：Data acquisition module 41, word-dividing mode 42 and calculating sort module 43.
Wherein data acquisition module 41 is used to pass through data reptile instrument, captures objective network information.
Specifically, turn-on data reptile instrument, and descriptor is set and preserves database information；By monitoring descriptor,
The Webpage for possessing related subject word is captured, obtains the network information related to earthquake, and periodic refreshing interface,
If fresh information is then grabbed into database.
Web crawlers is a kind of program for capturing info web automatically according to established rule, and it is from an initial link
Start to access, the link included in the webpage having access to or network documentation is put into queue to be visited, afterwards from team
New connection is taken out in row to continue to access, and activity above is then repeated, untill termination condition is met.
By this system, by web crawlers instrument, quickly the information in network can be captured, and passes through
Descriptor is set, so as to more accurately capture news and various information about earthquake in network.
Wherein, word-dividing mode 42 is used to segment the objective network information grabbed, and marks part of speech, obtains
Text is taken to segment information.
Specifically, specifically, segmented to the information crawled, and part of speech is marked, utilize NLPIR participle instruments will
The text data participle of crawl, information is segmented so as to which the network information to be split as to the text of multiple word compositions, while to tearing open
Each word for branching away carries out the mark of part of speech, and is stored in the text message after word segmentation processing is carried out to the network information
In database.
By this system, the word composition in the earthquake information obtained from network can be quickly distinguished, so as to fast
Speed, targetedly extraction includes the information for specifying part of speech.
Wherein, sort module 43 is calculated to be used to segment information, meter according to the initial weight of preset keyword and the text
The scale value that refers generally to of the objective network information is calculated, and to information type corresponding to objective network information matching.
Specifically, using descriptor classified weight table, term weighing matching is carried out to the word of upper step participle, it is accumulative to ask
With obtain total weight of text, the principle based on statistics, a word or phrase are characterized for a text with TF-IDF values
Important degree size.Some word is for the significance level of a text and its frequency occurred in this text into just
Than, but be inversely proportional with its frequency in whole corpus.
By selecting the theme of weight limit to be used as the affiliated classification of Seismic net information, by Seismic net information and its
Affiliated classification matched.
By this system, attempt to believe earthquake emergency using the reverse text matches algorithm based on descriptor weight
Breath and the condition of a disaster information carry out text classification, and combine practical application with web crawlers, ensure that the accurate of grouped data
Property.Emergency information Quick Acquisition and extracting tool are realized, improves the ageing and accuracy of earthquake disaster emergency service.
On the basis of above-described embodiment, the system also includes：Keyword Weight computing module, for based on artificial
Intervene the training text that lower classification is completed, calculate the weight of preset keyword.
Specifically, according to the training text, descriptor is extracted；
The word frequency and inverse document frequency of keyword in the training text are calculated using TF-IDF algorithms, obtains descriptor
Classified weight table.
Using TF-IDF algorithms, the word frequency and inverse document frequency of descriptor in training text are calculated, it is each so as to calculate
The weight of descriptor, obtain the classified weight table of descriptor.
Wherein TF-IDF calculation formula is：
TF-IDF=TF × IDF
Wherein TF represents the frequency that entry occurs in classification based training text, i.e. word frequency, and IDF represents inverse document frequency, i.e.,
Number of files comprising entry is fewer, and the entry is stronger to the separating capacity of document.Using TF-IDF algorithms, training text is calculated
The word frequency and inverse document frequency of middle keyword, so as to which the classified weight of descriptor be calculated, form descriptor weight table and protect
Save as text.
By this system, using the reverse text matches algorithm based on descriptor weight come to Earthquake emergency information and calamity
Feelings information carries out text classification, and combines practical application with data obtaining module, ensure that the accuracy of grouped data,
Improve the ageing and accuracy of earthquake disaster emergency service.
With reference to figure 5, Fig. 5 is a kind of earthquake emergency provided in an embodiment of the present invention and the condition of a disaster acquisition of information sorting device knot
Composition, as shown in figure 5, the equipment includes：Processor 501, memory 502 and bus 503.
The processor 501 is used to call the programmed instruction in the memory 502, is implemented with performing above-mentioned each method
The method that example is provided, such as including by data reptile instrument, capturing objective network information；To the target grabbed
The network information is segmented, and marks part of speech, obtains text participle information；According to the initial weight of preset keyword and described
Text segments information, calculates the scale value that refers generally to of the objective network information, and to letter corresponding to the network information matching
Cease type.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment
The mode of required general hardware platform can be added by software to realize, naturally it is also possible to pass through hardware.Based on such reason
Solution, the part that above-mentioned technical proposal substantially contributes to prior art in other words can be embodied in the form of software product
Out, the computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD,
Including some instructions causing a computer equipment (can be personal computer, server, or network equipment etc.) to hold
Method described in some parts of each embodiment of row or embodiment.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；To the greatest extent
The present invention is described in detail with reference to the foregoing embodiments for pipe, it will be understood by those within the art that：It is still
Technical scheme described in foregoing embodiments can be modified, or which part technical characteristic is equally replaced
Change；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technical scheme
Spirit and scope.
Claims (10)
1. a kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique, it is characterised in that including：
S1, by data reptile instrument, capture objective network information；
S2, the objective network information grabbed is segmented, and mark part of speech, obtain text participle information；
S3, information is segmented according to the initial weight of preset keyword and the text, calculates the totality of the objective network information
Desired value, and to information type corresponding to objective network information matching.
2. according to the method for claim 1, it is characterised in that the network information includes the mhkc network information, News Network
At least one of network information and micro blog network the information network information.
3. according to the method for claim 1, it is characterised in that also include after the S1：Based on classifying under manual intervention
The training text of completion, calculate the weight of preset keyword.
4. according to the method for claim 3, it is characterised in that the data based on completion of classifying under manual intervention, meter
The step of weight for calculating keyword, specifically includes：
According to the training text, descriptor is extracted；
The word frequency and inverse document frequency of preset keyword in the training text are calculated using TF-IDF algorithms, obtains descriptor point
Class weight table.
5. according to the method for claim 1, it is characterised in that the network information of the crawl is segmented in the S2
Specifically include：
S21, segmented using the network information captured described in NLPIR Words partition systems；
S22, part-of-speech information is marked, extract location information and temporal information, and the part-of-speech information is saved into database.
6. according to the method for claim 5, it is characterised in that described to utilize the network captured described in NLPIR Words partition systems
Information is segmented specially：By N-gram model algorithm, the network information is segmented.
7. according to the method for claim 5, it is characterised in that it is described mark part-of-speech information be specially：Pass through hidden Ma Erke
Husband's model part-of-speech tagging algorithm, marks part of speech of the network information after participle.
8. a kind of earthquake emergency and the condition of a disaster acquisition of information categorizing system, it is characterised in that including：
Data acquisition module, for by data reptile instrument, capturing objective network information；
Word-dividing mode, for being segmented to the objective network information grabbed, and part of speech is marked, obtain text participle letter
Breath
Sort module is calculated, for the initial weight according to preset keyword and text participle information, calculates the target
The network information refers generally to scale value, and to information type corresponding to objective network information matching.
9. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is held by processor
The step of any methods described in such as claim 1-7 is realized during row.
10. a kind of earthquake emergency and the condition of a disaster acquisition of information sorting device, it is characterised in that including：
At least one processor；And
At least one memory being connected with the processor, wherein：
The memory storage has can be by the programmed instruction of the computing device, and the processor calls described program instruction energy
Enough perform the method as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710692655.3A CN107562814A (en) | 2017-08-14 | 2017-08-14 | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710692655.3A CN107562814A (en) | 2017-08-14 | 2017-08-14 | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107562814A true CN107562814A (en) | 2018-01-09 |
Family
ID=60975487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710692655.3A Pending CN107562814A (en) | 2017-08-14 | 2017-08-14 | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107562814A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108391177A (en) * | 2018-02-07 | 2018-08-10 | 广州视源电子科技股份有限公司 | Television early warning method and system |
| CN108694247A (en) * | 2018-05-08 | 2018-10-23 | 北京师范大学 | A kind of typhoon disaster the condition of a disaster analysis method based on microblog topic temperature |
| CN108897792A (en) * | 2018-06-11 | 2018-11-27 | 中国科学院遥感与数字地球研究所 | Extract the disaster surveillance analysis method that internet multidimensional relates to calamity information |
| CN109145117A (en) * | 2018-09-05 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Bonus system recognition methods, device and the electronic equipment of multiple level marketing project |
| CN110377680A (en) * | 2019-07-11 | 2019-10-25 | 中国水利水电科学研究院 | The method of mountain flood database sharing and update based on web crawlers and semantics recognition |
| CN111382332A (en) * | 2019-04-02 | 2020-07-07 | 江苏省地震局 | Earthquake disaster information processing method and system |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN112069814A (en) * | 2020-09-01 | 2020-12-11 | 应急管理部沈阳消防研究所 | Fire-fighting plan classification method based on deep learning |
| CN112966169A (en) * | 2021-04-13 | 2021-06-15 | 四川省广播电视科学技术研究所 | Internet emergency information capturing method |
| CN113468320A (en) * | 2021-07-22 | 2021-10-01 | 中国地震台网中心 | Method and system for quickly visualizing earthquake emergency information |
| CN114201579A (en) * | 2021-11-17 | 2022-03-18 | 佛山市宏图数据有限公司 | Alarm positioning method based on artificial intelligence |
| CN114201959A (en) * | 2021-11-16 | 2022-03-18 | 湖南长泰工业科技有限公司 | Mobile emergency command method |
| CN116361463A (en) * | 2023-03-27 | 2023-06-30 | 应急管理部国家减灾中心(应急管理部卫星减灾应用中心) | Earthquake disaster information extraction method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289522A (en) * | 2011-09-19 | 2011-12-21 | 北京金和软件股份有限公司 | Method of intelligently classifying texts |
| CN102622373A (en) * | 2011-01-31 | 2012-08-01 | 中国科学院声学研究所 | Statistic text classification system and statistic text classification method based on term frequency-inverse document frequency (TF*IDF) algorithm |
| CN103744981A (en) * | 2014-01-14 | 2014-04-23 | 南京汇吉递特网络科技有限公司 | System for automatic classification analysis for website based on website content |
| CN105045857A (en) * | 2015-07-09 | 2015-11-11 | 中国科学院计算技术研究所 | Social network rumor recognition method and system |
| CN105468713A (en) * | 2015-11-19 | 2016-04-06 | 西安交通大学 | Multi-model fused short text classification method |
| CN105701084A (en) * | 2015-12-28 | 2016-06-22 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Characteristic extraction method of text classification on the basis of mutual information |
| CN106202372A (en) * | 2016-07-08 | 2016-12-07 | 中国电子科技网络信息安全有限公司 | A kind of method of network text information emotional semantic classification |
-
2017
- 2017-08-14 CN CN201710692655.3A patent/CN107562814A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622373A (en) * | 2011-01-31 | 2012-08-01 | 中国科学院声学研究所 | Statistic text classification system and statistic text classification method based on term frequency-inverse document frequency (TF*IDF) algorithm |
| CN102289522A (en) * | 2011-09-19 | 2011-12-21 | 北京金和软件股份有限公司 | Method of intelligently classifying texts |
| CN103744981A (en) * | 2014-01-14 | 2014-04-23 | 南京汇吉递特网络科技有限公司 | System for automatic classification analysis for website based on website content |
| CN105045857A (en) * | 2015-07-09 | 2015-11-11 | 中国科学院计算技术研究所 | Social network rumor recognition method and system |
| CN105468713A (en) * | 2015-11-19 | 2016-04-06 | 西安交通大学 | Multi-model fused short text classification method |
| CN105701084A (en) * | 2015-12-28 | 2016-06-22 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Characteristic extraction method of text classification on the basis of mutual information |
| CN106202372A (en) * | 2016-07-08 | 2016-12-07 | 中国电子科技网络信息安全有限公司 | A kind of method of network text information emotional semantic classification |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108391177A (en) * | 2018-02-07 | 2018-08-10 | 广州视源电子科技股份有限公司 | Television early warning method and system |
| CN108694247B (en) * | 2018-05-08 | 2020-11-20 | 北京师范大学 | Typhoon disaster analysis method based on microblog topic popularity |
| CN108694247A (en) * | 2018-05-08 | 2018-10-23 | 北京师范大学 | A kind of typhoon disaster the condition of a disaster analysis method based on microblog topic temperature |
| CN108897792A (en) * | 2018-06-11 | 2018-11-27 | 中国科学院遥感与数字地球研究所 | Extract the disaster surveillance analysis method that internet multidimensional relates to calamity information |
| CN108897792B (en) * | 2018-06-11 | 2022-05-03 | 中国科学院遥感与数字地球研究所 | Disaster monitoring and analyzing method for extracting multi-dimensional disaster-related information of Internet |
| CN109145117A (en) * | 2018-09-05 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Bonus system recognition methods, device and the electronic equipment of multiple level marketing project |
| CN111382332B (en) * | 2019-04-02 | 2021-12-17 | 江苏省地震局 | Earthquake disaster information processing method and system |
| CN111382332A (en) * | 2019-04-02 | 2020-07-07 | 江苏省地震局 | Earthquake disaster information processing method and system |
| CN110377680B (en) * | 2019-07-11 | 2020-04-28 | 中国水利水电科学研究院 | Method for constructing and updating mountain torrent disaster database based on web crawler and semantic recognition |
| CN110377680A (en) * | 2019-07-11 | 2019-10-25 | 中国水利水电科学研究院 | The method of mountain flood database sharing and update based on web crawlers and semantics recognition |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN111626568B (en) * | 2020-05-06 | 2024-02-20 | 厦门理工学院 | Knowledge base construction method and knowledge search method and system in natural disaster field |
| CN112069814A (en) * | 2020-09-01 | 2020-12-11 | 应急管理部沈阳消防研究所 | Fire-fighting plan classification method based on deep learning |
| CN112966169A (en) * | 2021-04-13 | 2021-06-15 | 四川省广播电视科学技术研究所 | Internet emergency information capturing method |
| CN113468320A (en) * | 2021-07-22 | 2021-10-01 | 中国地震台网中心 | Method and system for quickly visualizing earthquake emergency information |
| CN114201959A (en) * | 2021-11-16 | 2022-03-18 | 湖南长泰工业科技有限公司 | Mobile emergency command method |
| CN114201579A (en) * | 2021-11-17 | 2022-03-18 | 佛山市宏图数据有限公司 | Alarm positioning method based on artificial intelligence |
| CN116361463A (en) * | 2023-03-27 | 2023-06-30 | 应急管理部国家减灾中心(应急管理部卫星减灾应用中心) | Earthquake disaster information extraction method, device, equipment and medium |
| CN116361463B (en) * | 2023-03-27 | 2023-12-08 | 应急管理部国家减灾中心(应急管理部卫星减灾应用中心) | Earthquake disaster information extraction method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107562814A (en) | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system | |
| CN107204184B (en) | Audio recognition method and system | |
| CN107808011B (en) | Information classification extraction method and device, computer equipment and storage medium | |
| CN103744905B (en) | Method for judging rubbish mail and device | |
| CN109582704B (en) | Recruitment information and the matched method of job seeker resume | |
| CN102799647B (en) | Method and device for webpage reduplication deletion | |
| US10169331B2 (en) | Text mining for automatically determining semantic relatedness | |
| CN111767725B (en) | Data processing method and device based on emotion polarity analysis model | |
| CN108268668B (en) | Topic diversity-based text data viewpoint abstract mining method | |
| CN108763510A (en) | Intension recognizing method, device, equipment and storage medium | |
| CN103425777B (en) | A kind of based on the short message intelligent classification and the searching method that improve Bayes's classification | |
| CN110083832B (en) | Article reprint relation identification method, device, equipment and readable storage medium | |
| CN109325124B (en) | Emotion classification method, device, server and storage medium | |
| JP2006293767A (en) | Sentence categorizing device, sentence categorizing method, and categorization dictionary creating device | |
| CN106484797A (en) | Accident summary abstracting method based on sparse study | |
| CN111753082A (en) | Text classification method and device based on comment data, equipment and medium | |
| US11048934B2 (en) | Identifying augmented features based on a bayesian analysis of a text document | |
| CN105550359B (en) | Webpage sorting method and device based on vertical search and server | |
| CN106557777A (en) | It is a kind of to be based on the improved Kmeans clustering methods of SimHash | |
| CN107797994A (en) | Vietnamese noun phrase block identifying method based on constraints random field | |
| CN111489030B (en) | Text word segmentation based job leaving prediction method and system | |
| CN114357164B (en) | Emotion-reason pair extraction method, device, equipment and readable storage medium | |
| CN114141235A (en) | Voice corpus generation method and device, computer equipment and storage medium | |
| CN103984731B (en) | Self adaptation topic tracking method and apparatus under microblogging environment | |
| CN116502637A (en) | Text keyword extraction method combining context semantics |
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 |
Application publication date: 20180109 |
|
| RJ01 | Rejection of invention patent application after publication |