CN106611058A - Test question searching method and device - Google Patents
Test question searching method and device Download PDFInfo
- Publication number
- CN106611058A CN106611058A CN201611229381.6A CN201611229381A CN106611058A CN 106611058 A CN106611058 A CN 106611058A CN 201611229381 A CN201611229381 A CN 201611229381A CN 106611058 A CN106611058 A CN 106611058A
- Authority
- CN
- China
- Prior art keywords
- examination question
- search results
- scoring
- search
- examination
- 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 27
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 235000013399 edible fruits Nutrition 0.000 claims description 5
- 238000013499 data model Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 241000283070 Equus zebra Species 0.000 description 1
- 241000288988 Galago Species 0.000 description 1
- 241000008357 Okapia johnstoni Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for searching test questions, comprising the following steps: acquiring an original image of a target test question, and carrying out image recognition on the original image of the target test question; carrying out full text retrieval in a question bank based on the result of image identification to obtain a test question searching result; when the number of the obtained test question search results is more than two, calculating first scores corresponding to the obtained test question search results according to a scoring mechanism of full-text retrieval; calculating second scores corresponding to the obtained test question search results respectively according to a similarity calculation method; and according to a preset weighted linear scheme, carrying out weighted calculation on the first score and the second score, determining a final score, and sequencing and outputting the test question search results from high to low according to the final score. By the scheme of the invention, the accuracy of the test question search is improved.
Description
Technical field
The present invention relates to communication technical field, and in particular to a kind of examination question searching method and device.
Background technology
At present, education sector is also integrating with the Internet, occurs in that many online education products, takes pictures including possessing
The function such as answer questions searches topic class product.When searching topic class product and being intended to User and encounter a difficulty in operation, can obtain and include
The image of exercise question simultaneously carries out image recognition to the image, and the result based on image recognition searches for the topic that user needs in backstage exam pool
Mesh and answer are parsed.
However, the ambient light that can be taken due to existing image recognition technology and light are affected, use is frequently resulted in
When family is using topic class product is searched, it is impossible to correctly search for out the examination question required for user and answer parsing, can not meet user's
Topic demand is searched, the Consumer's Experience of such product is affected.
The content of the invention
The present invention provides a kind of examination question searching method and device, it is intended to improve the accuracy rate of examination question search.
The first aspect of the embodiment of the present invention, there is provided a kind of examination question searching method, the examination question searching method includes:
The original image of target examination question is obtained, and the original image to the target examination question carries out image recognition;
Result based on image recognition carries out full-text search in exam pool, obtains examination question Search Results;
When the quantity of the examination question Search Results for obtaining is two or more, according to the scoring of full-text search, calculating is obtained
Corresponding first scoring of each examination question Search Results difference for taking;
According to similarity algorithm, corresponding second scoring of each examination question Search Results difference for obtaining is calculated;
According to default weighted linear scheme, the described first scoring and the second scoring are weighted, it is determined that most final review
Point, and according to the final scoring, from high to low the examination question Search Results are ranked up and are exported.
The second aspect of the embodiment of the present invention, there is provided a kind of examination question searcher, the examination question searcher includes:
Target examination question acquiring unit, for obtaining the original image of target examination question, and to the original graph of the target examination question
As carrying out image recognition;
Preliminary search unit, the result for obtaining image recognition based on the target examination question acquiring unit is entered in exam pool
Row full-text search, obtains examination question Search Results;
First score calculation unit, the quantity of the examination question Search Results for getting when the preliminary search unit is two
When more than individual, according to the scoring of full-text search, corresponding first scoring of each examination question Search Results difference for obtaining is calculated;
Second score calculation unit, for according to similarity algorithm, calculate that the preliminary search unit gets each
Corresponding second scoring of examination question Search Results difference;
Search result determination unit, for according to default weighted linear scheme, obtaining to the first score calculation unit
The first scoring and the second scoring for obtaining of the second score calculation unit be weighted, it is determined that final scoring, and root
According to the final scoring, from high to low the examination question Search Results are ranked up and are exported.
Therefore, in the present invention program, the original image of target examination question is obtained first, and to the target examination question
Original image carries out image recognition, and be then based on the result of image recognition carries out full-text search in exam pool, obtains examination question search
As a result, when examination question Search Results include two or more result, according to the scoring of full-text search, each examination question search is calculated
As a result distinguish corresponding first scoring, and according to similarity algorithm, calculate each examination question Search Results and corresponding second comment respectively
Point, finally according to default weighted linear scheme, the described first scoring and the second scoring are weighted, it is determined that most final review
Point, and according to the final scoring, from high to low the examination question Search Results are ranked up and are exported.So that examination question search
As a result can further be screened, and finally filtered out more accurately, the higher examination question of matching degree and accordingly parsing.Relative to
In prior art, the examination question result for finally searching is had influence on due to the inaccuracy of image recognition, lead to not search out
The examination question of matching, the present invention program improves accuracy rate when examination question is searched for, and better met user searches topic demand, is lifted
Consumer's Experience.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is the flowchart of the examination question searching method that the embodiment of the present invention one is provided;
Fig. 2 implements flow chart for examination question searching method step S102 of the offer of the embodiment of the present invention one;
Fig. 3 is the structured flowchart of the examination question searcher that the embodiment of the present invention two is provided.
Specific embodiment
To enable goal of the invention, feature, the advantage of the present invention more obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described reality
It is only a part of embodiment of the invention to apply example, and not all embodiments.Based on the embodiment in the present invention, the common skill in this area
The every other embodiment that art personnel are obtained under the premise of creative work is not made, belongs to the model of present invention protection
Enclose.
In embodiments of the present invention, the original image of target examination question is obtained first, and to the original graph of the target examination question
As carrying out image recognition, be then based on the result of image recognition carries out full-text search in exam pool, obtains examination question Search Results, when
When examination question Search Results include two or more result, according to the scoring of full-text search, each examination question Search Results point are calculated
Not corresponding first scoring, and according to similarity algorithm, corresponding second scoring of each examination question Search Results difference is calculated, finally
According to default weighted linear scheme, the described first scoring and the second scoring are weighted, it is determined that final scoring, and according to
The examination question Search Results are ranked up and are exported by the final scoring from high to low.The result that examination question is searched for
Further screened, and finally filtered out more accurately, the higher examination question of matching degree and accordingly parsing.
It is described in detail below in conjunction with realization of the specific embodiment to the present invention:
Embodiment one
Fig. 1 shows that the examination question searching method that the embodiment of the present invention one is provided realizes flow process, and details are as follows:
In step S101, the original image of target examination question is obtained, and the original image to above-mentioned target examination question carries out figure
As identification.
In embodiments of the present invention, the original image comprising target examination question can be obtained by way of photographic head shoots,
For example can be to start after camera function, target examination question is taken pictures by photographic head.Or, in step S101, also may be used
Actively or passively to obtain the original image comprising target examination question from miscellaneous equipment;Or, in step S101, it is also possible to from
The original image comprising target examination question is obtained in image library, is not construed as limiting herein.After the original image for getting target examination question,
Text identification is carried out to the original image of above-mentioned target examination question, is realized in several ways with this, it is convenient rapidly to get bag
Original image containing target examination question.Specifically, in step S101, optical character recognition (OCR, Optical can be adopted
Character Recognition) technology carries out text identification to the original image comprising target examination question for getting.Certainly,
Step S104 can also carry out text knowledge using other text recognition techniques to the original image comprising target examination question for getting
Not, it is not construed as limiting herein.
In step s 102, the result based on image recognition carries out full-text search in exam pool, obtains examination question Search Results.
In embodiments of the present invention, examination question searcher will receive the original image that includes target examination question and right
Above-mentioned original image is carried out after image recognition, based on the result of image recognition, full-text search is carried out in exam pool, is got and mesh
The related Search Results of mark examination question.Wherein, exam pool includes local exam pool, also including the exam pool on the Internet.Local exam pool can
Think exam pool built-in in examination question searcher, or user via the topic in the Internet download to examination question searcher
Storehouse, facilitates user that required exam pool can be downloaded under networked environment with this, and the topic downloaded can be accessed under offline environment
Storehouse, does not limit herein.Full-text search all enters line retrieval due to the result that can be obtained image recognition in step S101, thus
The degree of association and matching degree of the Search Results for being obtained all can be higher.
Specifically, when full-text search is carried out in exam pool based on the result of image recognition, it is possible to use Lucene frameworks
Full-text search is carried out to the result of image recognition.The development language that Lucene is used is Java, is a full-text search increased income
Engine tool bag.It is not a complete full-text search engine, but the framework of a full-text search engine, there is provided it is complete
Query engine and index engine and part text analyzing engine.Lucene provides instrument easy to use for developer
Bag, realizes easily complete full-text search engine being set up in examination question searcher with this, thus user can be based on this
Realize the function of full-text search.Certainly, in step S102, can also be using other retrieval frameworks or search program to image recognition
Result carry out full-text search, such as Galago, Xapian or Zebra etc., here is not limited.
In step s 103, when the quantity of the examination question Search Results for obtaining is two or more, commenting according to full-text search
Extension set system, calculates corresponding first scoring of each entity search result difference for obtaining.
In embodiments of the present invention, the quantity of the examination question Search Results that step S102 is finally obtained cannot determine.When
When the target examination question of user's search is more novel, step S102 it is possible that the examination question Search Results for retrieving seldom, or even
Without situation.Examination question Search Results quantity for obtaining is different, there are following several application scenarios:
In a kind of application scenarios, step S102 does not get any examination question search knot matched with target examination question
Really.Now, step S103 can directly return the information without Search Results, and with this user is informed, it is impossible to search in existing exam pool
Rope is to the exercise question matched with target examination question.
In another kind of application scenarios, step S102 only gets an examination question Search Results.Now, step S103 is direct
The said one examination question Search Results for getting are returned to into user, is consulted for user.
Alternatively, in above two application scenarios, can be with step display S102 on screen, examination question searcher
Specifically searched in which exam pool, and other exam pools for recommending to attempt scanning for for user, user can be voluntarily
Select download exam pool to be searched again for or to be networked search again for online, more examination question Search Results are obtained with this.
In the third application scenarios, step S102 has got two or more examination question Search Results.Now, due to examination question
Search Results exist multiple, thus step S103 first can carry out for the first time scoring screening to it.Global search technology is provided
A kind of scoring, can score the result that search is obtained, and the scoring of Search Results is higher, represents it with target examination question
Degree of association it is higher.In step s 103, each Search Results for obtaining for step S102, all can once be scored,
Gained score is corresponding first scoring of each Search Results difference, and is designated as S1.Above-mentioned first scoring S1 will be by
Temporary transient stores, to treat that the above-mentioned first scoring S1 of later use is further calculated.
Specifically, when being in step s 102 to carry out full-text search to the result of image recognition using Lucene frameworks,
For above-mentioned the third application scenarios, step S103 can be that each examination question Search Results to obtaining carry out respectively Lucene
Scoring, obtains corresponding first scoring of above-mentioned each examination question Search Results difference.When carrying out full-text search based on Lucene frameworks,
Each examination question Search Results can be scored.Wherein, the Lucene corresponding to arbitrary examination question Search Results scores most
Big score value is 1.0.
In step S104, according to similarity algorithm, each examination question Search Results difference corresponding second for obtaining is calculated
Scoring.
In embodiments of the present invention, in step S103 it is possible that three kinds of application scenarios, and step S104 is then directed to
The third application scenarios, i.e. when the examination question number of searches that step S102 is obtained is two or more, the step of just performing.In step
In rapid S104, it will according to similarity algorithm, for each Search Results that step S102 is obtained, make similar to target examination question
Degree contrast, is once scored again, and gained score is corresponding second scoring of each Search Results difference, is designated as
S2.Above-mentioned second scoring S2 will be stored by temporary transient, to treat that the above-mentioned second scoring S2 of later use is carried out further
Meter.
Specifically, above-mentioned similarity algorithm can be longest common subsequence algorithm.Then now, step S104 concrete manifestation
For according to longest common subsequence algorithm, each examination question Search Results to obtaining score respectively, obtain above-mentioned each examination
Corresponding second scoring of topic Search Results difference.Longest common subsequence, english abbreviation is LCS (longest Common
Subsequence), it can describe the similarity between two sections of texts, thus in step S104, use most long public sub- sequence
Row algorithm, effectively can calculate the similarity between each examination question Search Results and target examination question, with this to examination question
Search Results are further analyzed.Alternatively, examination question searcher can according to second scoring S2 score value, from high to low
Two minor sorts are carried out to examination question Search Results.
In step S105, according to default weighted linear scheme, meter is weighted to the above-mentioned first scoring and the second scoring
Calculate, it is determined that final scoring, and according to above-mentioned final scoring, examination question Search Results more than above-mentioned two are arranged from high to low
Sequence is simultaneously exported.
In embodiments of the present invention, when above-mentioned the third application scenarios being in, i.e., the examination question that step S102 is obtained
When Search Results quantity is two or more, the examination question searcher in step S105 will be respectively directed to each examination question search knot
Really, corresponding first scoring S1 and the second scoring S2 is obtained, and according to default weighted linear scheme, to each examination question search knot
The first scoring S1 and the second scoring S2 corresponding to fruit is weighted, and obtains the corresponding final scoring of examination question Search Results,
S3 is designated as, and according to the score value of final scoring S3, from high to low, corresponding examination question Search Results is ranked up, and will
Result output after sequence, for user's access.
Further, above-mentioned default weighted linear scheme can be:S3=n1*S1+n2*S2.Wherein, n1>0, n2>0, n1
+ n2=1.Specifically, n1=0.3 can be taken, takes n2=0.7, the final scoring S3 for obtaining in this case and corresponding examination question
What the sequence of Search Results more met most of user searches topic demand.
Therefore, in embodiments of the present invention, examination question Search Results can twice be scored, and this is commented twice
Weighted calculation is allocated as, is finally scored, it is final because obtained from because final scoring is that the front weighting scored twice is processed
Examination question Search Results accuracy will be enhanced, and can be very good to solve user in light by force or by other extraneous bad borders
In the case of interference, target examination question is carried out taking pictures when searching topic, examination question Search Results can be affected, cause result it is inaccurate this
One problem.Accuracy rate when user searches topic is improve, the operating experience of user is improved, having better met the topic of searching of user needs
Ask.
Fig. 2 shows the flow chart that implements of examination question searching method step S102 provided in an embodiment of the present invention, describes in detail
It is as follows:
In step s 201, full-text search is carried out in exam pool according to the result of image recognition, obtains all related examinations
Topic Search Results.
In step S202, when the quantity of above-mentioned all related examination question Search Results is two or more, according to default
Data model various dimensions statistics is carried out to above-mentioned all related examination question Search Results, it is determined that including examination question Search Results quantity
Most examination question classifications.
In embodiments of the present invention, the quantity of all related examination question Search Results for obtaining in step S201 is uncertain
's.Only when the quantity of all related examination question Search Results obtained in step S201 is two or more, the just meeting of step S202
Various dimensions statistics is carried out to above-mentioned all related examination question Search Results according to default data filtering model, can be screened with this
The examination question Search Results gone out under optimal classification.Specifically, above-mentioned dimension including but not limited to it is following more than one:Time, region,
Subject, grade.
Wherein, the time is the proposition time corresponding to examination question.For User, especially in junior-senior high school
Raw user group, the exercise question that they are faced is often the middle college entrance examination very topic or middle college entrance examination simulation topic in former years, and these exercise questions exist
Year information can be usually remained with exam pool.Now in step S202, examination question searcher can be counted and target examination question
In related examination question Search Results, the situation of each examination question result Annual distribution, and filter out most comprising examination question Search Results
The affiliated time, obtain all examination question Search Results under the affiliated time.
Corresponding, region is the proposition region corresponding to examination question.For junior-high school student user group, region
A key factor for being them when examination question is searched for, because junior-senior high school examination question usually has very strong region.Now in step
In S202, when examination question is searched for, examination question searcher can count each examination question to user using region as a dimension of statistics
As a result the situation of Regional Distribution, and filter out comprising the most affiliated region of examination question Search Results, and obtain under the affiliated region
All examination question Search Results.
Meanwhile, subject is also an important dimension.Each examination question has the subject subject belonging to it, but due to actual life
In work, knowledge is to intersect, therefore some knowledge points may all occur in multiple subjects.By taking natural sciences as an example, physics, change
The subject such as, biology, mathematics, all can intersect each other, particularly mathematics as natural sciences class basic subject, in thing
In reason, chemistry, biology, can all there is involved.For example, when user is searched using the application topic in one mathematics as target examination question
Suo Shi, if this includes physical background, the displacement of entitled certain object of calculating, speed, distance or other things using topic
During reason amount, if making full-text search in exam pool to above-mentioned target examination question, having greatly can not only may retrieve under mathematic subject
Examination question, and can retrieve and include physics or other section's purpose exercise questions.Now in step S202, it is it to arrange subject
In a statistical dimension, subject statistics has been carried out in all examination question results to searching, it is determined that the examination affiliated now of different section
After the quantity of topic Search Results, can effectively filter out and the affiliated subject identical examination question Search Results of target examination question.
And grade is directed to, and in actual life, to some knowledge point, often having learnt the grade of this knowledge point,
Number of setting a question is concentrated the most, and other grades will not be investigated emphatically to the knowledge point.Thus examination question searcher is also provided with
For the statistics of grade of setting a question, the examination question search knot in same grade with target examination question can be accurately filtered out
Really, it is to avoid examination question Search Results super guiding principles or other do not meet the desired situation of user and occur.
Alternatively, user can voluntarily select to be counted using which kind of or which kind dimension.
Alternatively, after user can count various dimensions have been carried out, in the different examination question classifications included under different dimensions,
The examination question classification that user is interested or needs voluntarily is selected, and is selected automatically without examination question searcher and is tied comprising examination question search
The most examination question classification of fruit quantity.
In step S203, under the above-mentioned examination question classification most comprising examination question Search Results quantity, retain degree of association high
Examination question Search Results.
In embodiments of the present invention, because step S202 can be got under certain dimension, examination question Search Results quantity is most
Examination question Search Results number under many a certain examination question classifications, wherein the examination question classification is uncertain, and wherein we only need to protect
The examination question Search Results high with target examination question degree of association are stayed, for related to target examination question, but the not high examination question of degree of association
For Search Results, the examination question Search Results can be what is filtered.
Specifically, when the examination question Search Results quantity under above-mentioned examination question classification more than it is N number of when, then under above-mentioned examination question classification
Examination question Search Results carry out relevancy ranking, retain the high top n examination question Search Results of degree of association.Wherein above-mentioned examination question classification
For the examination question classification most comprising examination question Search Results quantity that step S202 determines.Degree of association is being carried out to above-mentioned examination question classification
During sequence, relatedness computation can be carried out with including but not limited to following any one algorithm:TF-IDF(Term Frequency-
Inverse Document Frequency) or Okapi BM25 (Best Match 25).According to above-mentioned relatedness computation
Examination question Search Results are ranked up from high to low by score, and are screened based on above-mentioned relevance score, only retain sequence heel row
The higher N number of examination question Search Results of the forward relevance score of name, it is not intended that examination question classification, rejects step S201 and obtain other
All examination question Search Results.
If the examination question Search Results quantity under above-mentioned examination question classification is not more than N number of, retain the institute under above-mentioned examination question classification
There are examination question Search Results.Now because the examination question Search Results quantity under above-mentioned examination question classification is not unnecessary N number of, then no matter examination question
Search Results and the degree of association height of target examination question, all make reservation process, without the need for making to be based on degree of association under above-mentioned examination question classification
Further screening.But, the examination question Search Results under other examination question classifications will be all disallowable.
Wherein, N mentioned above be it is default be more than or equal to 2 natural number.In step S203, N can be by trying
It is that topic searcher initially sets, or user's sets itself.Alternatively, examination question searcher will initially set N
For 100.
Therefore, in the present embodiment, it is possible to before scoring examination question result, carry out to examination question result first
Once rough preliminary screening, being avoided with this all carries out the first follow-up scoring to all of examination question Search Results, and second comments
Divide and final scoring.Greatly save occupancy of the examination question searching method to system resource.
It should be noted that the examination question searcher referred in the embodiment of the present invention specifically can in the way of software (example
The such as form of App) and/or the mode of hardware be integrated in mobile terminal (such as smart mobile phone, panel computer, learning machine terminal)
In.
One of ordinary skill in the art will appreciate that realizing that all or part of step in above-described embodiment method can be
Related hardware is instructed to complete by program, corresponding program can be stored in a computer read/write memory medium,
Above-mentioned storage medium, such as ROM/RAM, disk or CD.
Embodiment two
Fig. 3 shows the concrete structure block diagram of the examination question searcher that the embodiment of the present invention two is provided, for convenience of description,
Illustrate only the part related to the embodiment of the present invention.The examination question searcher 3 includes:
Target examination question acquiring unit 31, for obtaining the original image of target examination question, and to the original of above-mentioned target examination question
Image carries out image recognition;
Preliminary search unit 32, for obtaining the result of image recognition in exam pool based on above-mentioned target examination question acquiring unit 31
In carry out full-text search, obtain examination question Search Results;
First score calculation unit 33, the quantity of the examination question Search Results for getting when above-mentioned preliminary search unit 32
For two or more when, according to the scoring of full-text search, calculate each examination question Search Results difference corresponding first for obtaining
Scoring;
Second score calculation unit 34, for according to similarity algorithm, calculating what above-mentioned preliminary search unit 32 got
Corresponding second scoring of each examination question Search Results difference;
Search result determination unit 35, for according to default weighted linear scheme, to above-mentioned first score calculation unit 33
The second scoring that the first scoring for obtaining and above-mentioned second score calculation unit 34 are obtained is weighted, it is determined that most final review
Point, and according to above-mentioned final scoring, from high to low above-mentioned examination question Search Results are ranked up and are exported.
Specifically, above-mentioned preliminary search unit 32, for being carried out to the result of image recognition in full using Lucene frameworks
Retrieval;
Specifically, above-mentioned first scoring determining unit 33 is used for, each examination got to above-mentioned preliminary search unit 32
Topic Search Results carry out respectively Lucene scorings, obtain corresponding first scoring of above-mentioned each examination question Search Results difference.
Specifically, above-mentioned second scoring determining unit 34 is used for, when the similarity algorithm for using is longest common subsequence
During algorithm, according to longest common subsequence algorithm, each examination question Search Results got to above-mentioned preliminary search unit 32 point
Do not scored, obtained corresponding second scoring of above-mentioned each examination question Search Results difference.
Alternatively, above-mentioned preliminary search unit 32 also includes:
Search Results obtain subelement, and the image recognition result for being obtained according to above-mentioned target examination question acquiring unit 31 exists
Full-text search is carried out in exam pool, all related examination question Search Results are obtained;
Various dimensions count subelement, and the examination questions for obtaining all correlations that subelement gets when mentioned above searching results are searched
When the quantity of hitch fruit is two or more, the institute that subelement gets is obtained to mentioned above searching results according to default data model
The examination question Search Results for having correlation carry out various dimensions statistics, it is determined that comprising the most examination question classification of examination question Search Results quantity;
As a result subelement is screened, for determining in above-mentioned various dimensions statistics subelement comprising examination question Search Results quantity most
Under many examination question classifications, retain the high examination question Search Results of degree of association.
Specifically, the above results screening subelement is used for, if under the examination question classification of above-mentioned various dimensions statistics subelement determination
Examination question Search Results quantity more than N number of, then relevancy ranking is carried out to the examination question Search Results under above-mentioned examination question classification, retain
The high top n examination question Search Results of degree of association;If the examination question search under the examination question classification that above-mentioned various dimensions statistics subelement determines
Fruiting quantities are not more than N number of, then retain all examination question Search Results under above-mentioned examination question classification;Wherein, N for it is default more than or
Natural number equal to 2.
It should be noted that the examination question searcher in the embodiment of the present invention specifically can (such as App in the way of software
Form) and/or the mode of hardware be integrated in mobile terminal (such as the terminal such as smart mobile phone, panel computer, learning machine).
It should be understood that the examination question searcher in the embodiment of the present invention can be used for realizing the whole in said method embodiment
Technical scheme, the function of its each functional module can be implemented according to the method in said method embodiment, its concrete reality
Existing process can refer to the associated description in above-described embodiment, and here is omitted.
Therefore, in embodiments of the present invention, examination question searcher can be first before scoring examination question result
First rough preliminary screening is carried out once to examination question result, avoided with this all of examination question Search Results are all carried out it is follow-up
First scoring, the second scoring and final scoring.Greatly save occupancy of the examination question searcher to system resource.
It should be noted that in several embodiments provided herein, it should be understood that disclosed device and side
Method, can realize by another way.For example, device embodiment described above is only schematic, for example, above-mentioned
The division of unit, only a kind of division of logic function can have other dividing mode, such as multiple units when actually realizing
Or component can with reference to or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, institute
The coupling each other for showing or discussing or direct-coupling or communication connection can be by some interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, mechanical or other forms.
For aforesaid each method embodiment, for easy description, therefore it is all expressed as a series of combination of actions, but
It is that those skilled in the art should know, the present invention is not limited by described sequence of movement, because according to the present invention, certain
A little steps can adopt other orders or while carry out.Secondly, those skilled in the art also should know, be retouched in description
The embodiment stated belongs to preferred embodiment, and involved action and module might not all be necessary to the present invention.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, without the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiments.
Be more than to a kind of preferred embodiment provided by the present invention, for one of ordinary skill in the art, according to
According to the thought of the embodiment of the present invention, will change in specific embodiments and applications, to sum up, in this specification
Appearance should not be construed as limiting the invention.
Claims (10)
1. a kind of examination question searching method, it is characterised in that include:
The original image of target examination question is obtained, and the original image to the target examination question carries out image recognition;
Result based on image recognition carries out full-text search in exam pool, obtains examination question Search Results;
When the quantity of the examination question Search Results for obtaining is two or more, according to the scoring of full-text search, calculate what is obtained
Corresponding first scoring of each examination question Search Results difference;
According to similarity algorithm, corresponding second scoring of each examination question Search Results difference for obtaining is calculated;
According to default weighted linear scheme, the described first scoring and the second scoring are weighted, it is determined that final scoring, and
According to the final scoring, from high to low examination question Search Results are ranked up and are exported.
2. examination question searching method as claimed in claim 1, it is characterised in that the result based on image recognition is in exam pool
Full-text search is carried out, examination question Search Results are obtained, including:
Full-text search is carried out in exam pool according to the result of image recognition, all related examination question Search Results are obtained;
When the quantity of all related examination question Search Results is two or more, according to default data model to the institute
The examination question Search Results for having correlation carry out various dimensions statistics, it is determined that comprising the most examination question classification of examination question Search Results quantity;
Under the examination question classification most comprising examination question Search Results quantity, retain the high examination question Search Results of degree of association.
3. examination question searching method as claimed in claim 2, it is characterised in that it is described described comprising examination question Search Results quantity
Under most examination question classifications, retain the high examination question Search Results of degree of association, including:
If the examination question Search Results quantity under the examination question classification is more than N number of, to the examination question search knot under the examination question classification
Fruit carries out relevancy ranking, retains the high top n examination question Search Results of degree of association;
If the examination question Search Results quantity under the examination question classification is not more than N number of, retain all examinations under the examination question classification
Topic Search Results;
N be it is default be more than or equal to 2 natural number.
4. the examination question searching method as described in any one of claim 1-3, it is characterised in that the result based on image recognition
Full-text search is carried out in exam pool, including:
Full-text search is carried out to the result of image recognition using Lucene frameworks;
It is described when obtain examination question Search Results quantity be two or more when, according to the scoring of full-text search, calculating is obtained
Corresponding first scoring of each examination question Search Results difference for taking, including:
Each examination question Search Results to obtaining carry out respectively Lucene scorings, obtain described each examination question Search Results right respectively
The first scoring answered.
5. the examination question searching method as described in any one of claim 1-3, it is characterised in that the similarity algorithm is most long public affairs
Common subsequence algorithm;It is described that corresponding second scoring of each examination question Search Results difference for obtaining is calculated based on similarity algorithm,
Including:
According to longest common subsequence algorithm, each examination question Search Results to obtaining score respectively, obtain it is described each
Corresponding second scoring of examination question Search Results difference.
6. a kind of examination question searcher, it is characterised in that the examination question searcher includes:
Target examination question acquiring unit, for obtaining the original image of target examination question, and the original image to the target examination question enters
Row image recognition;
Preliminary search unit, the result for being obtained image recognition based on the target examination question acquiring unit is carried out entirely in exam pool
Text retrieval, obtains examination question Search Results;
First score calculation unit, the quantity of the examination question Search Results for getting when the preliminary search unit be two with
When upper, according to the scoring of full-text search, corresponding first scoring of each examination question Search Results difference for obtaining was calculated;
Second score calculation unit, for according to similarity algorithm, calculating each examination question that the preliminary search unit gets
Corresponding second scoring of Search Results difference;
Search result determination unit, for according to default weighted linear scheme, the first score calculation unit is obtained the
The second scoring that one scoring and the second score calculation unit are obtained is weighted, it is determined that final scoring, and according to institute
Final scoring is stated, from high to low the examination question Search Results is ranked up and is exported.
7. a kind of examination question searcher as claimed in claim 6, it is characterised in that the preliminary search unit, including:
Search Results obtain subelement, for the image recognition result that obtained according to the target examination question acquiring unit in exam pool
Full-text search is carried out, all related examination question Search Results are obtained;
Various dimensions count subelement, for obtaining all related examination question search knot that subelement gets when the Search Results
When the quantity of fruit is two or more, all phases that subelement gets are obtained to the Search Results according to default data model
The examination question Search Results of pass carry out various dimensions statistics, it is determined that comprising the most examination question classification of examination question Search Results quantity;
As a result subelement is screened, for counting the most comprising examination question Search Results quantity of subelement determination in the various dimensions
Under examination question classification, retain the high examination question Search Results of degree of association.
8. a kind of examination question searcher as claimed in claim 7, it is characterised in that the result screens subelement, concrete to use
In when the examination question Search Results quantity under the various dimensions count the examination question classification that subelement determines is more than N number of, to the examination
Examination question Search Results under topic classification carry out relevancy ranking, retain the high top n examination question Search Results of degree of association;
When the examination question Search Results quantity under the various dimensions count the examination question classification that subelement determines is not more than N number of, retain
All examination question Search Results under the examination question classification;
N be it is default be more than or equal to 2 natural number.
9. the examination question searcher as described in any one of claim 6-8, it is characterised in that the preliminary search unit is specifically used
In carrying out full-text search to the result of image recognition using Lucene frameworks;
The first score calculation unit is specifically for each examination question Search Results got to the preliminary search unit point
Lucene scorings are not carried out, corresponding first scoring of described each examination question Search Results difference is obtained.
10. the examination question searcher as described in any one of claim 6-8, it is characterised in that the second score calculation unit
Specifically for when the similarity algorithm for using is longest common subsequence algorithm, according to longest common subsequence algorithm, to institute
State each examination question Search Results that preliminary search unit gets to be scored respectively, obtain described each examination question Search Results point
Not corresponding second scoring.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611229381.6A CN106611058A (en) | 2016-12-27 | 2016-12-27 | Test question searching method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611229381.6A CN106611058A (en) | 2016-12-27 | 2016-12-27 | Test question searching method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106611058A true CN106611058A (en) | 2017-05-03 |
Family
ID=58636226
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611229381.6A Pending CN106611058A (en) | 2016-12-27 | 2016-12-27 | Test question searching method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106611058A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909520A (en) * | 2017-11-02 | 2018-04-13 | 浙江工商大学 | The method and apparatus that make the test based on examination question correlation |
CN108416264A (en) * | 2018-01-29 | 2018-08-17 | 山东汇贸电子口岸有限公司 | A kind of searching method and search module of supporting OCR to input |
CN109325051A (en) * | 2018-08-14 | 2019-02-12 | 广东小天才科技有限公司 | Problem search result output method based on solution model and learning equipment |
CN111241276A (en) * | 2020-01-06 | 2020-06-05 | 广东小天才科技有限公司 | Topic searching method, device, equipment and storage medium |
CN111563498A (en) * | 2020-04-30 | 2020-08-21 | 广东小天才科技有限公司 | Method and device for collecting questions, electronic equipment and storage medium |
CN111652203A (en) * | 2020-06-01 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Resource pushing method and device |
CN118132733A (en) * | 2024-05-07 | 2024-06-04 | 江西风向标智能科技有限公司 | Test question retrieval method, system, storage medium and electronic equipment |
CN118132733B (en) * | 2024-05-07 | 2024-07-26 | 江西风向标智能科技有限公司 | Test question retrieval method, system, storage medium and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140052716A1 (en) * | 2012-08-14 | 2014-02-20 | International Business Machines Corporation | Automatic Determination of Question in Text and Determination of Candidate Responses Using Data Mining |
CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
CN105373594A (en) * | 2015-10-23 | 2016-03-02 | 广东小天才科技有限公司 | Method and device for screening repeated test questions in question bank |
CN105426390A (en) * | 2015-10-23 | 2016-03-23 | 广东小天才科技有限公司 | Test question searching method and system based on image recognition |
-
2016
- 2016-12-27 CN CN201611229381.6A patent/CN106611058A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140052716A1 (en) * | 2012-08-14 | 2014-02-20 | International Business Machines Corporation | Automatic Determination of Question in Text and Determination of Candidate Responses Using Data Mining |
CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
CN105373594A (en) * | 2015-10-23 | 2016-03-02 | 广东小天才科技有限公司 | Method and device for screening repeated test questions in question bank |
CN105426390A (en) * | 2015-10-23 | 2016-03-23 | 广东小天才科技有限公司 | Test question searching method and system based on image recognition |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909520A (en) * | 2017-11-02 | 2018-04-13 | 浙江工商大学 | The method and apparatus that make the test based on examination question correlation |
CN108416264A (en) * | 2018-01-29 | 2018-08-17 | 山东汇贸电子口岸有限公司 | A kind of searching method and search module of supporting OCR to input |
CN109325051A (en) * | 2018-08-14 | 2019-02-12 | 广东小天才科技有限公司 | Problem search result output method based on solution model and learning equipment |
CN111241276A (en) * | 2020-01-06 | 2020-06-05 | 广东小天才科技有限公司 | Topic searching method, device, equipment and storage medium |
CN111563498A (en) * | 2020-04-30 | 2020-08-21 | 广东小天才科技有限公司 | Method and device for collecting questions, electronic equipment and storage medium |
CN111563498B (en) * | 2020-04-30 | 2024-01-19 | 广东小天才科技有限公司 | Method and device for collecting questions, electronic equipment and storage medium |
CN111652203A (en) * | 2020-06-01 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Resource pushing method and device |
CN118132733A (en) * | 2024-05-07 | 2024-06-04 | 江西风向标智能科技有限公司 | Test question retrieval method, system, storage medium and electronic equipment |
CN118132733B (en) * | 2024-05-07 | 2024-07-26 | 江西风向标智能科技有限公司 | Test question retrieval method, system, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
CN106611058A (en) | Test question searching method and device | |
CN112527999B (en) | Extraction type intelligent question-answering method and system for introducing knowledge in agricultural field | |
EP2192500B1 (en) | System and method for providing robust topic identification in social indexes | |
Wolf et al. | Clarifying vulnerability definitions and assessments using formalisation | |
CN106570109B (en) | Method for automatically generating question bank knowledge points through text analysis | |
CN107526846B (en) | Method, device, server and medium for generating and sorting channel sorting model | |
DE102016013372A1 (en) | Image labeling with weak monitoring | |
CN110390052B (en) | Search recommendation method, training method, device and equipment of CTR (China train redundancy report) estimation model | |
US11774264B2 (en) | Method and system for providing information to a user relating to a point-of-interest | |
CN112214670A (en) | Online course recommendation method and device, electronic equipment and storage medium | |
CN111324771B (en) | Video tag determination method and device, electronic equipment and storage medium | |
US20150113388A1 (en) | Method and apparatus for performing topic-relevance highlighting of electronic text | |
CN113312480B (en) | Scientific and technological thesis level multi-label classification method and device based on graph volume network | |
CN113722478B (en) | Multi-dimensional feature fusion similar event calculation method and system and electronic equipment | |
CN104794207A (en) | Recommendation system based on cooperation and working method of recommendation system | |
WO2016114790A1 (en) | Reading difficulty level based resource recommendation | |
CN103744889A (en) | Method and device for clustering problems | |
CN107679121B (en) | Mapping method and device of classification system, storage medium and computing equipment | |
CN113641794A (en) | Resume text evaluation method and device and server | |
Hu et al. | Examining the contextual factors of science effectiveness: a machine learning-based approach | |
CN106971004A (en) | Search result provides method and device | |
CN114067343A (en) | Data set construction method, model training method and corresponding device | |
CN112069423A (en) | Information recommendation method and device, storage medium and computer equipment | |
CN113435213A (en) | Method and device for returning answers aiming at user questions and knowledge base |
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: 20170503 |