CN107168948A - A kind of sentence recognition methods and system - Google Patents
A kind of sentence recognition methods and system Download PDFInfo
- Publication number
- CN107168948A CN107168948A CN201710258868.5A CN201710258868A CN107168948A CN 107168948 A CN107168948 A CN 107168948A CN 201710258868 A CN201710258868 A CN 201710258868A CN 107168948 A CN107168948 A CN 107168948A
- Authority
- CN
- China
- Prior art keywords
- phrase
- sentence
- interdependent
- grade
- subtree
- 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
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
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Abstract
The present invention relates to a kind of sentence recognition methods and system, methods described includes:One sentence to be identified is carried out dependency analysis to obtain the interdependent syntax tree corresponding with the sentence to be identified;The more specific location information of predetermined word is searched in the interdependent syntax tree, the interdependent subtree for determining to include the predetermined word according to the more specific location information;All non-temporal phrases are obtained in the interdependent subtree to obtain tournament names.Sentence recognition methods proposed by the present invention and system, can be accurately identified and be extracted to the competition title in a large amount of resumes simultaneously, largely improved data-handling efficiency, meet practical application request.
Description
Technical field
The present invention relates to sentence identification technology field, more particularly to a kind of sentence recognition methods and system.
Background technology
It is well known that during being hunted for a job in workplace, resume is acknowledged as job hunting successfully " stepping-stone to success ".Specifically,
Resume is exactly the introducing in written text concisely made to personal educational background, experience, speciality, hobby and prize-winning situation etc., is one kind
The standardization targetedly introduced myself, wirtiting logically.
General, in the screening process of resume, it is often necessary to overall scoring is carried out to resume, and is hunted for a job when being scored
The prize-winning situation of person is a highly important Score index.When the prize-winning situation to job hunter is estimated, it is necessary first to
Corresponding competition title is extracted from resume sentence (for example, " participating within 2014 national energy-saving and emission-reduction contest and winning school level three
Deng prize " in " national energy-saving and emission-reduction contest " be competition title), be extracted it is corresponding competition title after again to competition title
Specific assessment is carried out finally to be scored.Therefore, how effectively competition title is extracted into order to which one is relatively attached most importance to
The precondition wanted.
General, existing competition title of being extracted from resume is mainly carried out by way of manually extracting, but this side
Method is only applicable to the less situation of workload data, when required resume amount to be processed is very big, by manually extracting competition
The method of title undoubtedly wastes time and energy, especially in the environment of current big data, it is impossible to meet practical application request.
The content of the invention
, can be simultaneously to a large amount of it is an object of the invention to propose a kind of new sentence recognition methods and system based on this
Competition title in resume is accurately identified and extracted, and is largely improved data-handling efficiency, is met reality
Application demand.
The present invention proposes a kind of sentence recognition methods, wherein, methods described comprises the following steps:
One sentence to be identified is carried out dependency analysis to obtain the interdependent syntax tree corresponding with the sentence to be identified;
The more specific location information of predetermined word is searched in the interdependent syntax tree, is determined according to the more specific location information
Include the interdependent subtree of the predetermined word;
All non-temporal phrases are obtained in the interdependent subtree to obtain tournament names.
The sentence recognition methods, wherein, it is described to obtain all non-temporal phrases in the interdependent subtree to obtain
The step of to tournament names, includes:
Examined by regular expression and whether there is timeliness phrase in the interdependent subtree;
If in the presence of the timeliness phrase in the interdependent subtree is deleted by the regular expression;
All non-temporal phrases are obtained in the interdependent subtree after deleting the timeliness phrase
To obtain the tournament names.
The sentence recognition methods, wherein, all non-temporal phrases are obtained in the interdependent subtree to be compared
After the step of matching title, methods described also includes:
Regional phrase is obtained in the tournament names, area grade is determined according to the regional phrase;
The grade scoring corresponding with the area grade is confirmed in default score data storehouse according to the area grade.
The sentence recognition methods, wherein, confirmed according to the area grade in default score data storehouse with it is described
After the corresponding grade scoring of area grade, methods described also includes:
Multiple resumes are arranged according to its corresponding described grade scoring in the way of descending.
The sentence recognition methods, wherein, all non-temporal phrases are obtained in the interdependent subtree to be compared
After the step of matching title, methods described also includes:
Match theme phrase is obtained in the tournament names, corresponding match class is determined according to the match theme phrase
Type;
It will be divided into the one-to-one resume of the racing tip in corresponding resume subregion.
The present invention also proposes a kind of sentence identifying system, wherein, the system includes:
Dependency analysis module, it is relative with the sentence to be identified to obtain for carrying out dependency analysis to a sentence to be identified
The interdependent syntax tree answered;
Search determining module, the more specific location information for searching predetermined word in the interdependent syntax tree, according to institute
State the interdependent subtree that more specific location information determines to include the predetermined word;
Name acquiring module, for obtaining all non-temporal phrases in the interdependent subtree with obtain compete name
Claim.
The sentence identifying system, wherein, the name acquiring module includes:
Phrase verification unit, timeliness phrase is whether there is for being examined by regular expression in the interdependent subtree;
Phrase deletes unit, if for there is the timeliness phrase, will be described interdependent by the regular expression
The timeliness phrase in subtree is deleted;
Name acquiring unit, for obtaining all in the interdependent subtree after deleting the timeliness phrase
The non-temporal phrase is to obtain the tournament names.
The sentence identifying system, wherein, the system also includes grade scoring module, the grade scoring module bag
Include:
Area division unit, it is true according to the regional phrase for obtaining regional phrase in the tournament names
Determine area grade;
Grade scoring unit, for being confirmed according to the area grade in default score data storehouse and the area grade
Corresponding grade scoring.
The sentence identifying system, wherein, the system also includes a grade order module, and the grade sequence module is used
Arranged in by multiple resumes according to its corresponding described grade scoring in the way of descending.
The sentence identifying system, wherein, the system also includes a resume division module, the resume division module bag
Include:
Type determining units, it is short according to the match theme for obtaining match theme phrase in the tournament names
Language determines corresponding racing tip;
Resume zoning unit, for corresponding resume subregion will to be divided into the one-to-one resume of the racing tip
In.
Sentence recognition methods proposed by the present invention and system, first carry out interdependent point to a sentence to be identified in actual applications
After analysis obtains interdependent syntax tree, then determine in the interdependent syntax tree the interdependent subtree where predetermined word, finally from this according to
Deposit and corresponding tournament names are extracted in subtree.Sentence recognition methods proposed by the present invention and system, can be simultaneously in a large amount of resumes
Competition title accurately identified and extracted, largely improve data-handling efficiency, meet practical application need
Ask.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Fig. 1 is the theory diagram for the sentence recognition methods that first embodiment of the invention is proposed;
Fig. 2 is the schematic flow sheet for the sentence recognition methods that second embodiment of the invention is proposed;
Fig. 3 is the structural representation of interdependent syntax tree in the sentence recognition methods that second embodiment of the invention is proposed;
Fig. 4 be Fig. 3 shown in interdependent syntax tree in interdependent subtree structural representation;
Fig. 5 is the structural representation for the sentence identifying system that third embodiment of the invention is proposed.
Embodiment
For the ease of understanding the present invention, the present invention is described more fully below with reference to relevant drawings.In accompanying drawing
Give the preferred embodiment of the present invention.But, the present invention can be realized in many different forms, however it is not limited to this paper institutes
The embodiment of description.On the contrary, the purpose that these embodiments are provided be make to the disclosure more it is thorough comprehensively.
Unless otherwise defined, all of technologies and scientific terms used here by the article is with belonging to technical field of the invention
The implication that technical staff is generally understood that is identical.Term used in the description of the invention herein is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term as used herein " and/or " include one or more phases
The arbitrary and all combination of the Listed Items of pass.
Referring to Fig. 1, for the sentence recognition methods in first embodiment of the invention, for identifying ratio from a sentence
Title is matched, methods described comprises the following steps:
S101, carries out dependency analysis to obtain the interdependent syntax corresponding with the sentence to be identified to a sentence to be identified
Tree.
Specifically, in the screening of resume, thering are many sentences to be identified to need to carry out judging examination so as to therefrom
Extract tournament names.In the present embodiment, from LTP clouds, (wherein the LTP clouds are Harbin Institute of Technology's social computing and Research into information retrieval
The language technology platform of center research and development) dependency analysis is carried out to obtain an interdependent syntax tree to a sentence to be identified, then with cloud
API mode obtains request results.
When carrying out dependency analysis, the mainly relation of interdependence in anolytic sentence between single vocabulary and to disclose its right
The syntactic structure answered.General, dependence includes polytype, for example:" red " and " apple " is fixed middle pass in " red apple "
It is (ATT);" mountain " and " sea " is coordination (COO) in " mountain and sea ";In " I gives her a bunch of flowers " " I " and
" sending " be subject-predicate relation (SBV), " sending " and " flower " be guest's relation (VOB), " sending " and " she " be between guest's relation (IOB);" he is assorted
Book is all read " in " book " and " reading " be preposition object relation (FOB);In " very beautiful " " very " and " beauty " be shape in relation
(ADV);" done " in " doing the operation that is over " and " End " is dynamic benefit relation (CMP);It is " " and " interior " for guest Jie in " in trade area "
The Key Relationships (HED) of relation (POB) and the core of the whole sentence of reference.For example, what is inputted in above-mentioned LTP clouds is to be identified
Sentence is " the 6th national college students' mechanical creative design match first prizes of 2014.7.30 ", is then carried out by LTP clouds interdependent
Corresponding interdependent syntax tree is obtained after analysis.
S102, searches the more specific location information of predetermined word in the interdependent syntax tree, is believed according to the particular location
Breath determines the interdependent subtree for including the predetermined word.
For the predetermined word, the predetermined word can be " match ", " match " or " contest ", in the present embodiment
In, the predetermined word is " match ".As described above, by LTP clouds to above-mentioned sentence " 2014.7.30 the 6th to be identified
National college students' mechanical creative design is competed the first prize " carry out after dependency analysis obtains corresponding interdependent syntax tree, this according to
The particular location where lookup " match " two word in syntax tree is deposited, after the particular location of " match " two word is determined, according to
The particular location determines the interdependent subtree corresponding to it.In the present embodiment, the corresponding interdependent son for including " match " two word
Set as " the 6th national college students' mechanical creative design match ".
S103, obtains all non-temporal phrases to obtain tournament names in the interdependent subtree.
Herein it should be noted that due to during the extraction of above-mentioned interdependent subtree confirmation, it is possible to there is extraction not
Correct and intersexuality phrase, such as " 2014/2/4 ", " 2015.6.7 " in the presence of causing in the interdependent subtree that finally obtains.And it is above-mentioned
Timeliness phrase should not be included in tournament names, it is therefore desirable to make delete processing to the timeliness phrase in interdependent subtree.
Specifically, when deleting above-mentioned timeliness phrase, being deleted using regular expression to timeliness phrase
Remove.In the present embodiment, regular expression can be expressed as following form:
D { 1,4 } [- |/| year | ] d { 1,2 } [- |/| the moon | ] d { 1,2 } ([day | number]) |
Then (it is, for example, " 2014/2/ by the timeliness phrase being mingled with above-mentioned interdependent subtree by the regular expression
4 ") filter out, resulting interdependent subtree is all non-temporal phrases, when then obtaining all non-in the interdependent subtree
Intersexuality phrase is to obtain correct tournament names for " the 6th national college students' mechanical creative design match ".
Fig. 2 to Fig. 4 is referred to, for the sentence recognition methods in second embodiment, first, (work is breathed out still through LTP clouds
Big language technology platform) sentence to be identified is carried out dependency analysis to obtain corresponding interdependent syntax tree.To interdependent syntax tree
For, there is more dependence in interdependent syntax tree, such as " red " and " apple " is fixed middle relation in " red apple "
(ATT);" mountain " and " sea " is coordination (COO) in " mountain and sea ";In " I gives her a bunch of flowers " " I " and " sending "
For subject-predicate relation (SBV), " sending " and " flower " be guest's relation (VOB), " sending " and " she " be between guest's relation (IOB);" his what book
" book " and " reading " is preposition object relation (FOB) in all readings ";In " very beautiful " " very " and " beauty " be shape in relation
(ADV);" done " in " doing the operation that is over " and " End " is dynamic benefit relation (CMP);It is " " and " interior " for guest Jie in " in trade area "
The Key Relationships (HED) of relation (POB) and the core of the whole sentence of reference.
For example, when sentence to be identified " to participate within 2 months 2014 Asia university student's supercomputer contest and to obtain team excellent
During show prize ", interdependent syntax tree as shown in Figure 3 is obtained after dependency analysis according to above-mentioned LTP clouds.As can be seen from Figure 3:
" 2014 " and " 2 months ", " Asia " and " university student ", " super " and " computer ", " computer " and " contest ", " team " with
It is surely middle relation (ATT) between " excellent prize ";It is relation in shape between " 2 months " and " participation ", " simultaneously " and " acquisition "
(ADV), between " participation " and " contest ", " acquisition " and " excellent prize " it is dynamic guest's relation (VOB);Between " participation " and " acquisition "
For coordination (COO), in addition, for the sentence, " participation " for the core, also as whole sentence of whole sentence core
Heart relation (HED).
After above-mentioned interdependent syntax tree has been obtained, the particular location for including " match " word is searched in the interdependent syntax tree,
In the present embodiment, the particular location for " contest " two word of lookup.When lookup obtain " contest " two word particular location it
Afterwards, the interdependent subtree of " contest " two word is then included according to particular location determination.
Herein it should be noted that due to during the extraction of above-mentioned interdependent subtree confirmation, it is possible to there is extraction not
Correct and intersexuality phrase, such as " 2014/2/4 ", " 2015.6.7 " in the presence of causing in the interdependent subtree that finally obtains.And it is above-mentioned
Timeliness phrase should not be included in tournament names, it is therefore desirable to which first being examined by regular expression in the interdependent subtree is
Intersexuality phrase in the presence of no.If there is the timeliness phrase, by the regular expression by the interdependent subtree
The timeliness phrase is deleted, and obtains all in the interdependent subtree after deleting the timeliness phrase
The non-temporal phrase is to obtain the tournament names;If being not present, correct ratio is directly obtained from the interdependent subtree
Match title.
Specifically, when deleting above-mentioned timeliness phrase, being deleted using regular expression to timeliness phrase
Remove.In the present embodiment, regular expression can be expressed as following form:
D { 1,4 } [- |/| year | ] d { 1,2 } [- |/| the moon | ] d { 1,2 } ([day | number]) |
Then (it is, for example, by the timeliness phrase being mingled with above-mentioned interdependent subtree by the regular expression
" 2015.6.7 ") filter out, resulting interdependent subtree is all non-temporal phrases, then obtains institute in the interdependent subtree
Some non-temporal phrases are to obtain correct tournament names for " Asia university student's supercomputer contest " (as shown in Figure 4).
Herein it should also be noted that, after correct tournament names are obtained, in order to more accurately according to match
The rank of title and then resume is scored, in addition it is also necessary to regional phrase is obtained in the tournament names (for example, common
Regional phrase is " whole nation ", " Asia ", " Guangzhou province " and " Chongqing " etc.), because different region ranks is directly determined
The corresponding rank of the match, therefore corresponding regional phrase is obtained in the tournament names, it is then short according to the regionality
Language determines corresponding area grade.For example, when the regional phrase got is " whole nation ", now corresponding area grade
For one-level, grade corresponding with its area grade is then searched in default score data storehouse according to the area grade of the determination
Scoring, the grade scoring will directly affect the scoring of resume.Further, since the grade of the match included in different resumes
It is different, the scoring finally given is also different.It is higher in order to quickly and conveniently screen scoring in practical operation
Resume, to select the more outstanding talent.In the present embodiment, mainly by by the resume according to its corresponding institute
Grade scoring is stated to be arranged to realize in the way of descending.In this way, operating personnel can sieve from top to bottom at a glance
Select the satisfactory application talent.
Finally it may also be noted that by job hunter learns specialty and the difference of hobby, the ratio participated in
The type of match and the awards obtained is naturally also different, for example, the specialty that a part of applicant is learned is special for science and engineering
Industry, the awards of the awards that correspondence is obtained also for machinery or computer etc, and the specialty that a part of applicant is learned is literature and history class
Specialty, the awards that correspondence is obtained also are awards of composition or calligraphy etc etc..Therefore when being arranged to resume, it is desirable to
It is enough that different types of resume is correctly classified.Be directed to this, in the present embodiment, obtain the tournament names it
Afterwards, it (is, for example, " computer application ", " Machine Design ", " recitation of poems " that match theme phrase is obtained in the tournament names
Or " calligraphy " etc.), corresponding racing tip is then determined according to the match theme phrase.For example, when the ratio got
When matching theme phrase for " Machine Design ", it is determined that the racing tip is science and engineering class contest;When the match theme phrase got
During for " recitation of poems ", it is determined that the racing tip is literature and history class contest., will be with institute after corresponding racing tip is determined
The one-to-one resume of racing tip is stated to be divided into corresponding resume subregion.It can deduce, for above-mentioned science and engineering class
For contest or above-mentioned literature and history class contest, in actual applications, can also further it be divided inside it, so as to the later stage
Resume is realized and more accurately managed.
Referring to Fig. 5, for the sentence identifying system in third embodiment of the invention, for identifying ratio from a sentence
Title is matched, wherein, the system includes dependency analysis module, lookup determining module, name acquiring module, the grade being sequentially connected
Grading module and grade descending module, wherein the dependency analysis module be used to carrying out a sentence to be identified dependency analysis with
Obtain the interdependent syntax tree corresponding with the sentence to be identified;The lookup determining module is used in the interdependent syntax tree
The more specific location information of predetermined word is searched, the interdependent son for determining to include the predetermined word according to the more specific location information
Tree;The name acquiring module is used to obtain all non-temporal phrases in the interdependent subtree to obtain tournament names.
For the name acquiring module, the name acquiring module includes the phrase verification unit, short being sequentially connected
Language deletes unit and name acquiring unit, wherein, the phrase verification unit be used for by regular expression examine described according to
Deposit and whether there is timeliness phrase in subtree;If the phrase, which deletes unit, is used for the presence of the timeliness phrase, pass through institute
Regular expression is stated to be deleted the timeliness phrase in the interdependent subtree;The name acquiring unit is used to delete
Except obtaining all non-temporal phrases in the interdependent subtree after the timeliness phrase to obtain the ratio
Match title.
For the grade scoring module, the grade scoring module include be connected with each other area division unit and
Grade scoring unit, wherein the area division unit is used to obtain regional phrase in the tournament names, according to described
Regional phrase determines area grade;The grade scoring unit is used for according to the area grade in default score data storehouse
Confirm the grade scoring corresponding with the area grade.
In addition, the grade sequence module be used for by resume according to its corresponding described grade scoring in the way of descending
Arranged.
At the same time, what is be connected with the name acquiring module also has a resume division module, the resume division module
Type determining units and resume zoning unit including interconnection, wherein the type determining units are used in the match
Match theme phrase is obtained in title, corresponding racing tip is determined according to the match theme phrase;The resume subregion list
Member is used to be divided into the one-to-one resume of the racing tip in corresponding resume subregion.
Sentence recognition methods proposed by the present invention and system, first carry out interdependent point to a sentence to be identified in actual applications
After analysis obtains interdependent syntax tree, then determine in the interdependent syntax tree the interdependent subtree where predetermined word, finally from this according to
Deposit and corresponding tournament names are extracted in subtree.Sentence recognition methods proposed by the present invention and system, can be simultaneously in a large amount of resumes
Competition title accurately identified and extracted, largely improve data-handling efficiency, meet practical application need
Ask.
Can be with one of ordinary skill in the art will appreciate that realizing that all or part of step in above-described embodiment method is
The hardware of correlation is instructed to complete by program.Described program can be stored in a computer read/write memory medium.
The program upon execution, including the step described in the above method.Described storage medium, including:ROM/RAM, magnetic disc, CD
Deng.
Embodiment described above only expresses the several embodiments of the present invention, and it describes more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of sentence recognition methods, it is characterised in that comprise the following steps:
One sentence to be identified is carried out dependency analysis to obtain the interdependent syntax tree corresponding with the sentence to be identified;
The more specific location information of predetermined word is searched in the interdependent syntax tree, is determined to include according to the more specific location information
The interdependent subtree of the predetermined word;
All non-temporal phrases are obtained in the interdependent subtree to obtain tournament names.
2. sentence recognition methods according to claim 1, it is characterised in that described to obtain all in the interdependent subtree
Non-temporal phrase to obtain tournament names the step of include:
Examined by regular expression and whether there is timeliness phrase in the interdependent subtree;
If in the presence of the timeliness phrase in the interdependent subtree is deleted by the regular expression;
All non-temporal phrases are obtained in the interdependent subtree after deleting the timeliness phrase to obtain
To the tournament names.
3. sentence recognition methods according to claim 1, it is characterised in that obtain all non-in the interdependent subtree
After the step of timeliness phrase is to obtain tournament names, methods described also includes:
Regional phrase is obtained in the tournament names, area grade is determined according to the regional phrase;
The grade scoring corresponding with the area grade is confirmed in default score data storehouse according to the area grade.
4. sentence recognition methods according to claim 3, it is characterised in that scored according to the area grade default
Confirm in database after the grade scoring corresponding with the area grade, methods described also includes:
Multiple resumes are arranged according to its corresponding described grade scoring in the way of descending.
5. sentence recognition methods according to claim 1, it is characterised in that obtain all non-in the interdependent subtree
After the step of timeliness phrase is to obtain tournament names, methods described also includes:
Match theme phrase is obtained in the tournament names, corresponding racing tip is determined according to the match theme phrase;
It will be divided into the one-to-one resume of the racing tip in corresponding resume subregion.
6. a kind of sentence identifying system, it is characterised in that the system includes:
Dependency analysis module, it is corresponding with the sentence to be identified to obtain for carrying out dependency analysis to a sentence to be identified
Interdependent syntax tree;
Search determining module, the more specific location information for searching predetermined word in the interdependent syntax tree, according to the tool
Body position information determines the interdependent subtree for including the predetermined word;
Name acquiring module, for obtaining all non-temporal phrases in the interdependent subtree to obtain tournament names.
7. sentence identifying system according to claim 6, it is characterised in that the name acquiring module includes:
Phrase verification unit, timeliness phrase is whether there is for being examined by regular expression in the interdependent subtree;
Phrase deletes unit, if for there is the timeliness phrase, by the regular expression by the interdependent subtree
In the timeliness phrase deleted;
Name acquiring unit, for obtained in the interdependent subtree after deleting the timeliness phrase it is all described in
Non-temporal phrase is to obtain the tournament names.
8. sentence identifying system according to claim 6, it is characterised in that the system also includes grade scoring module,
The grade scoring module includes:
Area division unit, for obtaining regional phrase in the tournament names, area is determined according to the regional phrase
Domain grade;
Grade scoring unit is relative with the area grade for being confirmed according to the area grade in default score data storehouse
The grade scoring answered.
9. sentence identifying system according to claim 8, it is characterised in that the system also includes a grade sequence mould
Block, the grade sequence module is used to according to its corresponding described grade scoring be arranged multiple resumes in the way of descending
Row.
10. sentence identifying system according to claim 6, it is characterised in that the system also includes a resume subregion mould
Block, the resume division module includes:
Type determining units, it is true according to the match theme phrase for obtaining match theme phrase in the tournament names
Fixed corresponding racing tip;
Resume zoning unit, for that will be divided into the one-to-one resume of the racing tip in corresponding resume subregion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710258868.5A CN107168948A (en) | 2017-04-19 | 2017-04-19 | A kind of sentence recognition methods and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710258868.5A CN107168948A (en) | 2017-04-19 | 2017-04-19 | A kind of sentence recognition methods and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107168948A true CN107168948A (en) | 2017-09-15 |
Family
ID=59813438
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710258868.5A Pending CN107168948A (en) | 2017-04-19 | 2017-04-19 | A kind of sentence recognition methods and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107168948A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107656921A (en) * | 2017-10-10 | 2018-02-02 | 上海数眼科技发展有限公司 | A kind of short text dependency analysis method based on deep learning |
CN109582968A (en) * | 2018-12-04 | 2019-04-05 | 北京容联易通信息技术有限公司 | The extracting method and device of a kind of key message in corpus |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101094135A (en) * | 2006-06-23 | 2007-12-26 | 腾讯科技(深圳)有限公司 | Method and system for extracting information of content in Internet |
CN102142127A (en) * | 2010-07-30 | 2011-08-03 | 华为技术有限公司 | Method and device for managing consumption details of user |
CN102968431A (en) * | 2012-09-18 | 2013-03-13 | 华东师范大学 | Control device for mining relation between Chinese entities on basis of dependency tree |
CN104881402A (en) * | 2015-06-02 | 2015-09-02 | 北京京东尚科信息技术有限公司 | Method and device for analyzing semantic orientation of Chinese network topic comment text |
CN105472580A (en) * | 2015-11-17 | 2016-04-06 | 小米科技有限责任公司 | Information processing method, information processing device, terminal and server |
CN106339366A (en) * | 2016-08-08 | 2017-01-18 | 北京百度网讯科技有限公司 | Method and device for requirement identification based on artificial intelligence (AI) |
-
2017
- 2017-04-19 CN CN201710258868.5A patent/CN107168948A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101094135A (en) * | 2006-06-23 | 2007-12-26 | 腾讯科技(深圳)有限公司 | Method and system for extracting information of content in Internet |
CN102142127A (en) * | 2010-07-30 | 2011-08-03 | 华为技术有限公司 | Method and device for managing consumption details of user |
CN102968431A (en) * | 2012-09-18 | 2013-03-13 | 华东师范大学 | Control device for mining relation between Chinese entities on basis of dependency tree |
CN104881402A (en) * | 2015-06-02 | 2015-09-02 | 北京京东尚科信息技术有限公司 | Method and device for analyzing semantic orientation of Chinese network topic comment text |
CN105472580A (en) * | 2015-11-17 | 2016-04-06 | 小米科技有限责任公司 | Information processing method, information processing device, terminal and server |
CN106339366A (en) * | 2016-08-08 | 2017-01-18 | 北京百度网讯科技有限公司 | Method and device for requirement identification based on artificial intelligence (AI) |
Non-Patent Citations (2)
Title |
---|
赵明等: "植物领域知识图谱构建中本体非分类关系提取方法", 《农业机械学报》 * |
邱炳城: "《网页设计与制作》", 31 August 2011, 广东高等教育出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107656921A (en) * | 2017-10-10 | 2018-02-02 | 上海数眼科技发展有限公司 | A kind of short text dependency analysis method based on deep learning |
CN109582968A (en) * | 2018-12-04 | 2019-04-05 | 北京容联易通信息技术有限公司 | The extracting method and device of a kind of key message in corpus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104573028B (en) | Realize the method and system of intelligent answer | |
KR100816934B1 (en) | Clustering system and method using search result document | |
CN103268339B (en) | Named entity recognition method and system in Twitter message | |
CN102693219B (en) | Method and system for extracting Chinese event | |
CN106663125A (en) | Question sentence generation device and computer program | |
Kuzey et al. | Extraction of temporal facts and events from Wikipedia | |
CN106021410A (en) | Source code annotation quality evaluation method based on machine learning | |
CN109635083A (en) | It is a kind of for search for TED speech in topic formula inquiry document retrieval method | |
CN107491447A (en) | Establish inquiry rewriting discrimination model, method for distinguishing and corresponding intrument are sentenced in inquiry rewriting | |
CN108520038B (en) | Biomedical literature retrieval method based on sequencing learning algorithm | |
CN107168948A (en) | A kind of sentence recognition methods and system | |
CN106951414A (en) | A kind of academic text vocabulary identification of function method sorted based on machine learning | |
CN110276079A (en) | A kind of dictionary method for building up, information retrieval method and corresponding system | |
KR20140026796A (en) | System and method for providing customized patent analysis service | |
CN109446399A (en) | A kind of video display entity search method | |
Dorn et al. | Unlocking cultural conceptualisation in indigenous language resources: Collaborative computing methodologies | |
CN106557577A (en) | The quick check method of marine organisms survey data and device | |
CN110297886A (en) | OJ topic classifier construction method and topic analogy method based on short text | |
CN104376041B (en) | A kind of information extraction method based on microblogging classification | |
CN111061853B (en) | Method for rapidly acquiring FAQ model training corpus | |
Nowak | Theorising the natural archive | |
Panizza | Gasparino Barzizza's Commentaries on Seneca's letters | |
KR102497151B1 (en) | Applicant information filling system and method | |
Lawton | The Kiriwinan Classifiers | |
Artese et al. | A multimedia system for the management of intangible cultural heritage |
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: 20170915 |