CN103914567A - Objective test question answer matching method and objective test question answer matching device - Google Patents
Objective test question answer matching method and objective test question answer matching device Download PDFInfo
- Publication number
- CN103914567A CN103914567A CN201410165812.1A CN201410165812A CN103914567A CN 103914567 A CN103914567 A CN 103914567A CN 201410165812 A CN201410165812 A CN 201410165812A CN 103914567 A CN103914567 A CN 103914567A
- Authority
- CN
- China
- Prior art keywords
- examination question
- word
- target examination
- image
- characteristic information
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/142—Image acquisition using hand-held instruments; Constructional details of the instruments
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an objective test question answer matching method and an objective test question answer matching device. The method includes the following steps of acquiring an image comprising objective test questions; recognizing the image comprising the objective test questions; extracting text contents of the objective test questions; processing the acquired text contents according to a preset strategy to obtain feature information of the objective test questions; matching the objective test questions and test questions in a test question library by using the feature information of the objective test questions; using at least one test question as candidate test questions if the test questions in the test question library contain information matching with the feature information of the objective test questions; acquiring test question answers corresponding to the candidate test questions; and displaying the test question answers. According to the scheme, the test questions are inputted and matched automatically, the answers are acquired automatically, answering time and user operation are greatly reduced, answers can be provided for a user timely, and accuracy of the answers is guaranteed.
Description
Technical field
The present invention relates to terminal applies field, be specifically related to a kind of method and apparatus that mates target script.
Background technology
Students in middle and primary schools do the homework or parental counseling student in, often run into examination question or the exercise question that can not do.At this moment user usually seeks the answer of examination question by internet.
The websites such as current, existing many services is resolved website or network application in students in middle and primary schools' examination question of student or the head of a family, helps user to obtain answer, fulfils assignment smoothly, and for example, operation is helped, and asks him, and operation is precious.User retrieves by manual input contents of test question, obtains script.
But website is resolved in existing operation, and app etc. are by manual answering, other users of website, or provide answer after teacher checks examination question online.Put question to and get answer from user, the problem of life period cost, can not meet user's instant demand fast.Put question to peak period user, or for the larger problem of difficulty, occur sometimes the long period, as the situation that nobody answers in several hours or a day, efficiency is very low.Wait also affects user's experience for a long time.And the different multiple different answers of possibility of answering, makes user's indistinguishable.
Summary of the invention
In view of the above problems, the present invention has been proposed to a kind of method and apparatus of the coupling target script that overcomes the problems referred to above or address the above problem is at least in part provided.
According to an aspect of the present invention, provide a kind of method of mating target script, having comprised: obtain the image that comprises target examination question; The image that comprises target examination question is identified, extracted the word content of target examination question; According to preset strategy, obtained word content is processed, obtained the characteristic information of target examination question; Utilize the characteristic information of target examination question to mate with the examination question in test item bank; If at least one examination question in test item bank comprises the information matching with the characteristic information of described target examination question, using this at least one examination question as candidate's examination question, obtain the script that candidate's examination question is corresponding and show.
Alternatively, describedly according to preset strategy, the word content extracting is processed, the characteristic information that obtains described target examination question is specially: from the word content of described target examination question, intercept and one or morely have the word fragment of preset length as the characteristic information of described target examination question;
The described characteristic information that utilizes described target examination question mates and is specially with the examination question in test item bank: one or more word fragments with preset length that coupling intercepts in described test item bank.
Alternatively, describedly according to preset strategy, obtained word content is processed, the characteristic information that obtains described target examination question is specially: according to default throwing word method, the word content of described target examination question is thrown to word processing, retain the characteristic information of residue word content as described target examination question;
The described characteristic information that utilizes described target examination question mates and is specially with the examination question in test item bank: in described test item bank, mate the residue word content retaining after described throwing word is processed.
Alternatively, the default throwing word method of described basis is thrown word processing to the word content of described target examination question and is specially: from the head or afterbody of the word content of described target examination question, every default word number, the word of skimming, retains residue word content.
Alternatively, the default throwing word method of described basis also comprised before the word content of described target examination question is thrown word processing:
According to the fixed Combination between word and word, retain the word that has fixed Combination in the word content of described target examination question;
The default throwing word method of described basis is thrown word processing to the word content of described target examination question and is specially: the word content to the target examination question outside described fixed Combination is thrown word processing;
Described fixed Combination obtains by the item content of analyzing examination question in described test item bank.
Alternatively, described in, obtaining the image that comprises target examination question comprises: provide shooting guidance information to user, obtain the image that comprises target examination question that user takes;
Described the image that comprises target examination question is identified and is specially: the image that comprises target examination question that described user is taken carries out OCR identification.
Alternatively, described in, obtaining the image that comprises target examination question comprises:
Provide shooting guidance information to user, obtain the initial pictures that comprises target examination question that user takes;
The focal zone of selecting according to user, carries out rim detection to described initial pictures, obtains the border of described target examination question in described initial pictures;
Border according to described target examination question in described initial pictures, the image that comprises target examination question described in intercepting;
Described the image that comprises target examination question is identified and is specially: the image that comprises target examination question described in being truncated to is carried out to OCR identification.
Alternatively, described shooting guidance information comprises the one or more combination of following information: take direction, and shooting angle, light, reminding user focuses on target examination question region.
According to a further aspect in the invention, provide a kind of device that mates target script, having comprised: image collection module, for obtaining the image that comprises target examination question; Identification module, for the image that comprises target examination question is identified, extracts the word content of target examination question; Processing module, for obtained word content being processed according to preset strategy, obtains the characteristic information of target examination question; Matching module, for utilizing the characteristic information of target examination question and the examination question of test item bank to mate; Answer acquisition module, in the time that at least one examination question of test item bank comprises the information matching with the characteristic information of described target examination question, using this at least one examination question as candidate's examination question, obtains the script that candidate's examination question is corresponding and shows.
Alternatively, described processing module comprises: word interception unit, one or morely has the word fragment of preset length as the characteristic information of described target examination question for intercepting from the word content of described target examination question;
Described matching module specifically for: in described test item bank coupling intercept one or more word fragments with preset length.
Alternatively, described processing module further comprises: throw word unit, for according to default throwing word method, the word content of described target examination question being thrown to word processing, retain the characteristic information of residue word content as described target examination question;
Described matching module specifically for: in described test item bank, mate the residue word content retaining after described throwing word is processed.
Alternatively, described throwing word unit specifically for: from the head or afterbody of the word content of described target examination question, every default word number, the word of skimming, retains residue word content.
Alternatively, described processing module also comprises: analytic unit, obtains the fixed Combination between word and word for the item content of analyzing described test item bank examination question;
Described throwing word unit specifically for: according to the fixed Combination between word and word, retain the word that has fixed Combination in the word content of described target examination question, the word content of the target examination question outside described fixed Combination thrown to word processing.
Alternatively, described image collection module comprises: the unit of taking pictures, for shooting guidance information is provided to user, obtains the image that comprises target examination question that user takes;
Described identification module specifically for: the image that comprises target examination question that described user is taken carries out OCR identification.
Alternatively, described image collection module further comprises:
The unit of taking pictures, for shooting guidance information is provided to user, obtains the initial pictures that comprises target examination question that user takes;
Edge detection unit, for the focal zone of selecting according to user, carries out rim detection to described initial pictures, obtains the border of described target examination question in described initial pictures;
Image interception unit, for according to described target examination question on the border of described initial pictures, the image that comprises target examination question described in intercepting;
Described identification module specifically for: the image that comprises target examination question described in being truncated to is carried out to OCR identification.
Alternatively, described shooting guidance information comprises the one or more combination of following information: take direction, and shooting angle, light, reminding user focuses on target examination question region.
According to the method and apparatus of coupling target of the present invention script, carry out word identification image is converted into examination question word content obtaining the image that comprises target examination question, afterwards, word content is processed and obtained characteristic information, utilize this characteristic information to mate in test item bank, obtain candidate's examination question and answer that coupling is passed through.According to this scheme, the input of examination question, coupling, and the obtaining to be automatically and complete of answer, reduced the time of answering and user's operation in a large number, can be in time for user furnishes an answer, and guarantee the accuracy of answer.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to better understand technological means of the present invention, and can be implemented according to the content of instructions, and for above and other objects of the present invention, feature and advantage can be become apparent, below especially exemplified by the specific embodiment of the present invention.
Accompanying drawing explanation
By reading below detailed description of the preferred embodiment, various other advantage and benefits will become cheer and bright for those of ordinary skills.Accompanying drawing is only for the object of preferred implementation is shown, and do not think limitation of the present invention.And in whole accompanying drawing, represent identical parts by identical reference symbol.In the accompanying drawings:
Fig. 1 shows the process flow diagram of the method for mating according to an embodiment of the invention target script;
Fig. 2 shows the process flow diagram of the method for mating in accordance with another embodiment of the present invention target script;
Fig. 3 shows the process flow diagram of the method for mating in accordance with another embodiment of the present invention target script;
Fig. 4 shows the structured flowchart of the device that mates according to an embodiment of the invention target script.
Embodiment
Exemplary embodiment of the present disclosure is described below with reference to accompanying drawings in more detail.Although shown exemplary embodiment of the present disclosure in accompanying drawing, but should be appreciated that and can realize the disclosure and the embodiment that should do not set forth limits here with various forms.On the contrary, it is in order more thoroughly to understand the disclosure that these embodiment are provided, and can be by the those skilled in the art that conveys to complete the scope of the present disclosure.
Fig. 1 shows the process flow diagram of the method for mating according to an embodiment of the invention target script, and as shown in Figure 1, the method comprises the steps:
Step S110, obtains the image that comprises target examination question.
The image that comprises target examination question can be from user's shooting, or is selected from local file, for example, and mobile phone photo album, the sectional drawing to electronic document etc.Image can be bmp, jpg, and the common form such as jpeg, also can comprise that other is suitable for carrying out the electronic document format of image recognition, for example pdf file.
Step S120, identifies the image that comprises target examination question, extracts the word content of target examination question.
This step converts the image that comprises target examination question to computword.
Step S130, processes obtained word content according to preset strategy, obtains the characteristic information of target examination question.
This step can comprise and from the word content of initial identification, intercepts one or more word fragments, as characteristic information, or throw word processing, and from initial word content, remove segment word content with certain strategy, will remain word content as characteristic information.Can avoid the long and degradation problem under the matching efficiency that causes of examination question to the processing of word content.This step can also comprise the detection to word content, and concrete disposal route is determined according to testing result.For example, in the time detecting that word length is greater than matching threshold, remove with segment word; In the time that word comprises mess code, process removal mess code by throwing word.
Step S140, utilizes the characteristic information of target examination question to mate with the examination question in test item bank.
In test item bank, there are a large amount of examination question and corresponding answers with collecting in advance.Test item bank can be one or more, and for example, according to subject, grade classifies to test item bank.When coupling, reminding user is searched in corresponding classification, or according to keyword target exercise question is carried out to automatic classification, to improve search efficiency.
Step S150, if at least one examination question in test item bank comprises the information matching with the characteristic information of target examination question, using this at least one examination question as candidate's examination question, obtains the answer that candidate's examination question is corresponding and shows.
Candidate's examination question is the examination question that coupling is passed through.Because characteristic information may only reflect the partial content of examination question, therefore, what coupling was passed through may be multiple similar examination questions.Obtain whole candidate's examination question exercise questions and answer and show, checking for user.Further, because the form of presentation of examination question is versatile and flexible, for improving recall rate, this coupling can refer to the only coupling of Partial Feature information, for example, calculates by similarity, examination question using similarity more than a certain threshold value is as candidate's examination question and return to exercise question and answer, provides similarity data.
The method providing according to the above embodiment of the present invention, carry out word identification image is converted into examination question word content obtaining the image that comprises target examination question, manually input without user, afterwards, word content is processed and obtained characteristic information, utilize this characteristic information to mate in test item bank, obtain candidate's examination question and answer thereof that coupling is passed through.According to this scheme, the input of examination question, coupling, and obtaining of answer be all automatically to complete, and reduced in a large number the time of answering and user's operation, can be in time for user furnishes an answer, and guarantee the accuracy of answer.
Fig. 2 shows the process flow diagram of the method for mating in accordance with another embodiment of the present invention target script, and as shown in Figure 2, the method comprises the steps:
Step S210, provides shooting guidance information to user, obtains the image that comprises target examination question that user takes.
Take guidance information and comprise shooting direction, shooting angle, light, distance, and reminding user focuses on etc. target examination question region, by guidance information, user done to suitable indication, makes image that user shoots meet the quality requirements of identification.
Method in the present invention can be embodied as the app on intelligent mobile phone platform, and particularly, this step can realize by calling the camera of smart mobile phone or imaging program that system provides.
Particularly, before taking pictures, user provides explanatory note and sample picture etc. as guidance information, for example, prompting user adopts vertical angle to take, and selects good light, laterally takes, show focus frame that user is adjustable etc., in the time that exercise question is long, only take effectively content etc. of a part.
Step S220, the focal zone of selecting according to user, carries out rim detection to initial pictures.
The image of taking using user in step S210, as initial pictures, obtains the border of target examination question in initial pictures by rim detection.For example; the program of taking pictures of smart mobile phone can provide a focus frame that is positioned at mobile phone screen centre position conventionally; adjust its size, position by user by the mode such as manually pulling; ideal situation is; after user adjusts by the guidance information of taking pictures; in focus frame, comprise the effective content of a part of target examination question; take the effective content of this part as basis; on whole initial pictures, carry out rim detection; determine the border of target examination question, in border, comprised and only comprised all or part of content of target examination question.
Step S230, the border according to target examination question in initial pictures, intercepts the image that comprises target examination question.
Image in intercepting border is as image to be identified.As mentioned above, if user has carried out proper operation according to guidance information, in truncated picture, only comprise the word content of target examination question, this has effectively been avoided the interference that may cause in follow-up matching process due to the segment word of adjacent examination question, and causes can not find the situation of candidate's examination question.
The optional step that above-mentioned steps S220 and step S230 are the present embodiment.
Step S240, carries out OCR identification to the image that comprises target examination question intercepting.
In this embodiment, adopt OCR (optical character identification) technology to look like to identify to cut-away view.OCR has higher recognition speed and accuracy rate.OCR comprises binaryzation, noise remove, and slant correction, the processes such as Character segmentation, certainly, binaryzation and noise remove also can complete at pretreatment stage.Then, obtain the word content of target examination question by specific OCR algorithm, have multiple OCR algorithm in prior art, for example, based on template matches, the methods such as feature extraction or neural metwork training, can select as required.In addition, OCR technology also comprises printed page analysis and rejuvenation, in the time not carrying out rim detection and picture intercepting, can only extract by printed page analysis the word content of target examination question.
Step S250 intercepts and one or morely has the word fragment of preset length as the characteristic information of target examination question from the word content of target examination question.
If the word content after OCR identification is long, possibly cannot carry out efficient coupling.At this moment, can intercept from the front portion, middle part, rear portion of the word content of the target examination question of identification the content of suitable length respectively, the length of intercepting can require determine according to examination question length and coupling.
Step S260, one or more word fragments with preset length that coupling intercepts in test item bank.
Characteristic information using the one or more word fragments that intercept as target examination question mates respectively, or will after fragment combination, mate in test item bank.
Whether step S270, judge in test item bank and have at least one examination question to comprise the information matching with the word fragment intercepting, if so, and execution step S280.
In exam pool, may have the examination question that a large amount of similarities are higher, in the higher examination question of these similarities, comprise same word fragment, the quantity of the examination question matching with the word fragment intercepting may be for multiple.
If it fails to match, can also further inquire about in test item bank whether have some examination questions, wherein comprise the content higher with the combination similarity of the word fragment intercepting or word fragment.For example, can intercept further the multiple fragments that intercept, obtain multiple sub-fragments, utilize the combination of this little fragment or sub-fragment to mate, if there is higher similarity between the exercise question matching and target examination question, can be used as relevant examination question record.Because the expression-form of examination question is changeable, the relevant examination question that these similarities are higher may have suggesting effect to user.
Step S280, the examination question that coupling is passed through, as candidate's examination question, obtains answer and shows.
Obtain answer and the exercise question of whole candidate's examination questions and show, further, can provide relevant examination question and the answer higher to target examination question similarity, calculating the similarity between target examination question, by showing after sequencing of similarity, checking for user.
The method providing according to the above embodiment of the present invention, provides to user the guidance information of taking pictures, and makes user be easy to take the image that meets OCR identification requirement; By the rim detection to initial pictures, be truncated to the image that only comprises target examination question word content, this has eliminated uncorrelated content may and mate the impact causing to identification; For the long word content identifying, mate by the word fragment intercepting, improve the efficiency of coupling.
Fig. 3 shows the method for mating in accordance with another embodiment of the present invention target script, and as shown in Figure 3, the method comprises the steps:
Step S310, provides shooting guidance information to user, obtains the image that comprises target examination question that user takes.
Step S320, the image that comprises target examination question that user is taken carries out OCR identification.
The embodiment of step S310 and S320 can be with reference to a upper embodiment, certainly, also can comprise that image to taking carries out the step that rim detection and picture intercept in this embodiment, herein repeated description no longer.
Step S330, throws word processing according to default throwing word method to the word content of described target examination question.
Throwing word refers to removes segment word content from initial word content with certain strategy, will remain word content as characteristic information.
Particularly, throw word method and can be: the head or afterbody of the word content of the target examination question identifying from OCR, every default word number, the word of skimming, or the word of fixed qty, the word at institute interval is several to be required and determines according to examination question length and coupling.With a upper embodiment similarly, the residue word content part effective information that comprises examination question, can be used as the characteristic information for mating, and also may return to multiple candidate's examination questions by the coupling that remains content.
Can also before throwing word, carry out pre-service to word content, for example, due to picture quality and recognition capability, OCR identifies in the word content obtaining may comprise some mess codes, and, in exercise question, often comprise some and provide the words of effective information, for example " ", " institute " etc., can first skim these mess codes and insignificant word, if residue word content still can not meet coupling requirement, then carries out above-mentioned throwing word process.
As example, throw word pre-service before and can carry out as follows:
According to the fixed Combination between word and word, in the word content of reservation target examination question, there is the word of fixed Combination.Wherein, fixed Combination obtains by the item content of analyzing a large amount of examination questions in test item bank, comprises subject term, or the usual combination of the multiple words in a certain subject category etc., for example " friction force ... big or small .. direction " etc.
According to default throwing word method, the word content of target examination question being thrown to word processing is specially: throwing in word process, retain these fixed Combination, the word content of the target examination question outside fixed Combination is thrown to word processing.Like this, throw word processing and have more specific aim, in characteristic information, retained more effective information.
Step S340, in test item bank, coupling is thrown the residue word content retaining after word is processed.
Step S350, obtains and mates the answer of the candidate's examination question passing through and show.
With a upper embodiment similarly, candidate's examination question may have multiple, can also further provide the examination question and the answer that there are higher similarity with target examination question, repeats no more herein.
The method providing according to the above embodiment of the present invention, adopts the method word content that identification obtains to OCR of throwing word to process, and obtains characteristic information, in the characteristic information obtaining, has retained more effective information by throwing word, is conducive to improve matching efficiency.
Fig. 4 shows the structured flowchart of the device that mates according to an embodiment of the invention target script, and as shown in Figure 4, this device comprises:
Image collection module 410, for obtaining the image that comprises target examination question.
The image that comprises target examination question can be from user's shooting, or is selected from local file, for example, and mobile phone photo album, the sectional drawing to electronic document etc.Image can be bmp, jpg, and the common form such as jpeg, also can comprise that other is suitable for carrying out the electronic document format of image recognition, for example pdf file.
Alternatively, image is taken from user, and image collection module 410 further comprises: the unit 4101 of taking pictures, for shooting guidance information is provided to user, obtains the image that comprises target examination question that user takes.
Take guidance information and comprise shooting direction, shooting angle, light, distance, and reminding user focuses on target examination question region etc.By guidance information, user is done to suitable indication, make the quality requirements of the image recognition that user shoots.
The device of the coupling script in the present invention can be embodied as the app on intelligent mobile phone platform, and particularly, the unit 4101 of taking pictures can obtain image by calling the camera of smart mobile phone or imaging program that system provides.
Alternatively, image collection module 410 further comprises: edge detection unit 4102, and for the focal zone of selecting according to user, the initial pictures that user is taken carries out rim detection, obtains the border of target examination question in initial pictures; And
Image interception unit 4103, for the border at initial pictures according to target examination question, intercepts the image that comprises target examination question.
Image interception unit 4103 intercepts image in border as image to be identified.If user operates correctly, in truncated picture, only comprise the word content of target examination question, this has effectively been avoided the interference that may cause in follow-up matching process due to the segment word of adjacent examination question, and causes can not find the situation of candidate's examination question.
The image that comprises target examination question that edge detection unit 4102 and image interception unit 4103 also otherwise obtain applicable to image collection module 410.
Identification module 420, for the image that comprises target examination question is identified, extracts the word content of target examination question.
Identification module 420 converts the image that comprises target examination question to computword.
Alternatively, identification module 420 for: the image that comprises target examination question getting is carried out to OCR identification.OCR identification has higher speed and accuracy rate.Particularly, identification module 420 can be carried out the processing such as binaryzation, noise remove, slant correction, Character segmentation to image, then, obtains the word content of target examination question by specific OCR algorithm, has multiple OCR algorithm in prior art, can select as required.
Alternatively, the image that comprises target examination question is taken from user, identification module 420 specifically for: to user take the image that comprises target examination question carry out OCR identification;
If image has passed through the processing of edge detection unit 4102 and image interception unit 4103, identification module 420 specifically for: the image that comprises target examination question being truncated to is carried out to OCR identification.
Processing module 430, for obtained word content being processed according to preset strategy, obtains the characteristic information of target examination question.
Particularly, processing module 430 can be used for from the word content of initial identification, intercepting multiple word fragments, as characteristic information, or throws word processing for word content is done, from initial word content, remove segment word content with certain strategy, will remain word content as characteristic information.Can avoid the long and degradation problem under the matching efficiency that causes of examination question to the processing of word content.
Alternatively, processing module 430 further comprises: word interception unit 4303, one or morely has the word fragment of preset length as the characteristic information of target examination question for intercepting from the word content of target examination question.Particularly, word interception unit 4303 can intercept from the front portion, middle part, rear portion of the word content of the target examination question of identification the content of suitable length respectively, and the length of intercepting can require determine according to examination question length and coupling; Or
Processing module 430 is done and is thrown word processing word content, processing module 430 further comprises: throw word unit 4302, for according to default throwing word method, the word content of described target examination question being thrown to word processing, retain the characteristic information of residue word content as target examination question.
Throw word unit 4302 specifically for: from the head or afterbody of the word content of target examination question, every default word number, the word of skimming, retains residue word content.
Alternatively, processing module further comprises: analytic unit 4301, obtains the fixed Combination between word and word for the item content of analyzing test item bank examination question; Fixed Combination comprises subject term, or the usual combination of the multiple words in a certain subject category etc., for example " friction force ... big or small .. direction "; Throw word unit 4302 specifically for: according to the fixed Combination between word and word, retain the word that has fixed Combination in the word content of target examination question, the word content of the target examination question outside fixed Combination thrown to word processing.Like this, throw word processing and have more specific aim, in characteristic information, retained more effective information.
Matching module 440, for utilizing the characteristic information of target examination question and the examination question of test item bank to mate;
Alternatively, if multiple word fragments that characteristic information is word interception unit 4303 to be intercepted, matching module 440 specifically for: the one or more word fragments that intercept are mated respectively in test item bank, or mate after multiple fragments are combined;
If characteristic information is to throw the residue word content that obtains of word unit 4302, matching module 440 is specifically in test item bank coupling residue word content.
Answer acquisition module 450, in the time that at least one examination question of test item bank comprises the information matching with the characteristic information of target examination question, using this at least one examination question as candidate's examination question, obtains the script that candidate's examination question is corresponding and shows.
In exam pool, may there is the examination question that a large amount of similarities are higher, in the higher examination question of these similarities, comprise same word fragment, the quantity of candidate's examination question that answer acquisition module 450 obtains may be more than one, at this moment, and alternatively, answer acquisition module 450 obtains answer and the exercise question of whole candidate's examination questions and shows, further, can provide relevant examination question and the answer higher to target similarity, calculate the similarity between target examination question, by showing after sequencing of similarity, check for user.
The device providing according to the above embodiment of the present invention, image collection module is obtained the image that comprises target examination question, identification module carries out word identification to image, image is converted into the word content of examination question, afterwards, processing module is processed and is obtained characteristic information word content, and matching module utilizes this characteristic information to mate in test item bank, and answer acquisition module obtains candidate's examination question and the answer that coupling is passed through.According to this scheme, the input of examination question, coupling, and the obtaining to be automatically and complete of answer, reduced the time of answering and user's operation in a large number, can be in time for user furnishes an answer, and guarantee the accuracy of answer.
The algorithm providing at this is intrinsic not relevant to any certain computer, virtual system or miscellaneous equipment with demonstration.Various general-purpose systems also can with based on using together with this teaching.According to description above, it is apparent constructing the desired structure of this type systematic.In addition, the present invention is not also for any certain programmed language.It should be understood that and can utilize various programming languages to realize content of the present invention described here, and the description of above language-specific being done is in order to disclose preferred forms of the present invention.
In the instructions that provided herein, a large amount of details are described.But, can understand, embodiments of the invention can be put into practice in the situation that there is no these details.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Similarly, be to be understood that, in order to simplify the disclosure and to help to understand one or more in each inventive aspect, in the above in the description of exemplary embodiment of the present invention, each feature of the present invention is grouped together into single embodiment, figure or sometimes in its description.But, the method for the disclosure should be construed to the following intention of reflection: the present invention for required protection requires than the more feature of feature of clearly recording in each claim.Or rather, as reflected in claims below, inventive aspect is to be less than all features of disclosed single embodiment above.Therefore, claims of following embodiment are incorporated to this embodiment thus clearly, and wherein each claim itself is as independent embodiment of the present invention.
Those skilled in the art are appreciated that and can the module in the equipment in embodiment are adaptively changed and they are arranged in one or more equipment different from this embodiment.Module in embodiment or unit or assembly can be combined into a module or unit or assembly, and can put them in addition multiple submodules or subelement or sub-component.At least some in such feature and/or process or unit are mutually repelling, and can adopt any combination to combine all processes or the unit of disclosed all features in this instructions (comprising claim, summary and the accompanying drawing followed) and disclosed any method like this or equipment.Unless clearly statement in addition, in this instructions (comprising claim, summary and the accompanying drawing followed) disclosed each feature can be by providing identical, be equal to or the alternative features of similar object replaces.
In addition, those skilled in the art can understand, although embodiment more described herein comprise some feature rather than further feature included in other embodiment, the combination of the feature of different embodiment means within scope of the present invention and forms different embodiment.For example, in the following claims, the one of any of embodiment required for protection can be used with array mode arbitrarily.
All parts embodiment of the present invention can realize with hardware, or realizes with the software module of moving on one or more processor, or realizes with their combination.It will be understood by those of skill in the art that and can use in practice microprocessor or digital signal processor (DSP) to realize according to the some or all functions of the some or all parts in the device of the coupling target script of the embodiment of the present invention.The present invention can also be embodied as part or all equipment or the device program (for example, computer program and computer program) for carrying out method as described herein.Realizing program of the present invention and can be stored on computer-readable medium like this, or can there is the form of one or more signal.Such signal can be downloaded and obtain from internet website, or provides on carrier signal, or provides with any other form.
It should be noted above-described embodiment the present invention will be described rather than limit the invention, and those skilled in the art can design alternative embodiment in the case of not departing from the scope of claims.In the claims, any reference symbol between bracket should be configured to limitations on claims.Word " comprises " not to be got rid of existence and is not listed as element or step in the claims.Being positioned at word " " before element or " one " does not get rid of and has multiple such elements.The present invention can be by means of including the hardware of some different elements and realizing by means of the computing machine of suitably programming.In the unit claim of having enumerated some devices, several in these devices can be to carry out imbody by same hardware branch.The use of word first, second and C grade does not represent any order.Can be title by these word explanations.
Claims (10)
1. a method of mating target script, comprising:
Obtain the image that comprises target examination question;
The described image that comprises target examination question is identified, extracted the word content of described target examination question;
According to preset strategy, obtained word content is processed, obtained the characteristic information of described target examination question;
Utilize the characteristic information of described target examination question to mate with the examination question in test item bank;
If at least one examination question in test item bank comprises the information matching with the characteristic information of described target examination question, using this at least one examination question as candidate's examination question, obtain the script that candidate's examination question is corresponding and show.
2. method according to claim 1, describedly according to preset strategy, the word content extracting is processed, the characteristic information that obtains described target examination question is specially: from the word content of described target examination question, intercept and one or morely have the word fragment of preset length as the characteristic information of described target examination question;
The described characteristic information that utilizes described target examination question mates and is specially with the examination question in test item bank: one or more word fragments with preset length that coupling intercepts in described test item bank.
3. according to the method described in claim 1-2 any one, describedly according to preset strategy, obtained word content is processed, the characteristic information that obtains described target examination question is specially: according to default throwing word method, the word content of described target examination question is thrown to word processing, retain the characteristic information of residue word content as described target examination question;
The described characteristic information that utilizes described target examination question mates and is specially with the examination question in test item bank: in described test item bank, mate the residue word content retaining after described throwing word is processed.
4. according to the method described in claim 1-3 any one, the default throwing word method of described basis is thrown word processing to the word content of described target examination question and is specially: from the head or afterbody of the word content of described target examination question, every default word number, the word of skimming, retains residue word content.
5. according to the method described in claim 1-4 any one, the default throwing word method of described basis also comprised before the word content of described target examination question is thrown word processing:
According to the fixed Combination between word and word, retain the word that has fixed Combination in the word content of described target examination question;
The default throwing word method of described basis is thrown word processing to the word content of described target examination question and is specially: the word content to the target examination question outside described fixed Combination is thrown word processing;
Described fixed Combination obtains by the item content of analyzing examination question in described test item bank.
6. according to the method described in claim 1-5 any one, described in obtain the image that comprises target examination question and comprise: provide shooting guidance information to user, obtain the image that comprises target examination question that user takes;
Described the image that comprises target examination question is identified and is specially: the image that comprises target examination question that described user is taken carries out OCR identification.
7. according to the method described in claim 1-6 any one, described in obtain the image that comprises target examination question and comprise:
Provide shooting guidance information to user, obtain the initial pictures that comprises target examination question that user takes;
The focal zone of selecting according to user, carries out rim detection to described initial pictures, obtains the border of described target examination question in described initial pictures;
Border according to described target examination question in described initial pictures, the image that comprises target examination question described in intercepting;
Described the image that comprises target examination question is identified and is specially: the image that comprises target examination question described in being truncated to is carried out to OCR identification.
8. according to the method described in claim 1-7 any one, described shooting guidance information comprises the one or more combination of following information: take direction, and shooting angle, light, reminding user focuses on target examination question region.
9. a device that mates target script, comprising:
Image collection module, for obtaining the image that comprises target examination question;
Identification module, for the described image that comprises target examination question is identified, extracts the word content of described target examination question;
Processing module, for obtained word content being processed according to preset strategy, obtains the characteristic information of described target examination question;
Matching module, for utilizing the characteristic information of described target examination question and the examination question of test item bank to mate;
Answer acquisition module, in the time that at least one examination question of test item bank comprises the information matching with the characteristic information of described target examination question, using this at least one examination question as candidate's examination question, obtains the script that candidate's examination question is corresponding and shows.
10. device according to claim 9, described processing module comprises: word interception unit, one or morely has the word fragment of preset length as the characteristic information of described target examination question for intercepting from the word content of described target examination question;
Described matching module is further used for: one or more word fragments with preset length that coupling intercepts in described test item bank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410165812.1A CN103914567A (en) | 2014-04-23 | 2014-04-23 | Objective test question answer matching method and objective test question answer matching device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410165812.1A CN103914567A (en) | 2014-04-23 | 2014-04-23 | Objective test question answer matching method and objective test question answer matching device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103914567A true CN103914567A (en) | 2014-07-09 |
Family
ID=51040247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410165812.1A Pending CN103914567A (en) | 2014-04-23 | 2014-04-23 | Objective test question answer matching method and objective test question answer matching device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103914567A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| CN104376042A (en) * | 2014-10-11 | 2015-02-25 | 武汉天量数据技术有限公司 | Method and system for acquiring test questions from test question database |
| CN104506898A (en) * | 2015-01-12 | 2015-04-08 | 北京东方皆冠科技有限公司 | Image information processing method and system |
| CN104657923A (en) * | 2015-01-15 | 2015-05-27 | 广东小天才科技有限公司 | Method and device for double checking and judging of test questions |
| CN104715253A (en) * | 2015-04-02 | 2015-06-17 | 北京贞观雨科技有限公司 | Method and server for obtaining test question analysis information |
| CN104750791A (en) * | 2015-03-12 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Image retrieval method and device |
| CN104835365A (en) * | 2015-05-05 | 2015-08-12 | 广东小天才科技有限公司 | Method, intelligent device and device suitable for writing operation inspection |
| CN105427696A (en) * | 2015-11-20 | 2016-03-23 | 江苏沁恒股份有限公司 | Method for distinguishing answer to target question |
| CN105426518A (en) * | 2015-12-03 | 2016-03-23 | 广东小天才科技有限公司 | Method and system for searching questions by photographing |
| 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 |
| CN105843855A (en) * | 2016-03-16 | 2016-08-10 | 广东小天才科技有限公司 | Question searching method and device and intelligent equipment |
| CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and device of intelligent equipment |
| CN106023009A (en) * | 2016-05-05 | 2016-10-12 | 广东小天才科技有限公司 | Method and system for establishing test paper question bank |
| CN106095998A (en) * | 2016-06-21 | 2016-11-09 | 广东小天才科技有限公司 | Precise question searching method and device applied to intelligent terminal |
| CN106131422A (en) * | 2016-07-26 | 2016-11-16 | 广东小天才科技有限公司 | Method and device for determining photographing content |
| CN106250518A (en) * | 2016-08-03 | 2016-12-21 | 广东小天才科技有限公司 | Intelligent question searching method and device |
| CN106294659A (en) * | 2016-08-03 | 2017-01-04 | 广东小天才科技有限公司 | Question searching method and device based on intelligent terminal |
| CN106294871A (en) * | 2016-08-24 | 2017-01-04 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN106294717A (en) * | 2016-08-08 | 2017-01-04 | 广东小天才科技有限公司 | Question searching method and device based on intelligent terminal |
| CN106295514A (en) * | 2016-07-27 | 2017-01-04 | 中山市读书郎电子有限公司 | A kind of method and device of image recognition exercise question display answer |
| CN106372216A (en) * | 2016-09-05 | 2017-02-01 | 广东小天才科技有限公司 | Method and device for improving question searching accuracy |
| CN106503634A (en) * | 2016-10-11 | 2017-03-15 | 讯飞智元信息科技有限公司 | A kind of image alignment method and device |
| CN106709055A (en) * | 2017-01-09 | 2017-05-24 | 广东小天才科技有限公司 | Method and device for processing picture test questions |
| CN107330040A (en) * | 2017-06-27 | 2017-11-07 | 李博 | One kind study topic searching method and its system |
| CN107463681A (en) * | 2017-08-08 | 2017-12-12 | 广东小天才科技有限公司 | Method and device for identifying questions to be searched |
| CN108122269A (en) * | 2016-11-28 | 2018-06-05 | 英业达科技有限公司 | Test question generation system and its method based on paper image |
| CN108133209A (en) * | 2016-12-01 | 2018-06-08 | 北京新唐思创教育科技有限公司 | Target area searching method and device in text recognition |
| CN108133039A (en) * | 2018-01-10 | 2018-06-08 | 广州视源电子科技股份有限公司 | Image data processing method and device, electronic equipment and storage medium |
| CN109063182A (en) * | 2018-08-23 | 2018-12-21 | 广东小天才科技有限公司 | Content recommendation method based on voice search questions and electronic equipment |
| CN109242103A (en) * | 2018-07-20 | 2019-01-18 | 张有明 | Difficulty of knowledge points assignment processing method and processing device suitable for learning management system |
| CN109670042A (en) * | 2018-12-04 | 2019-04-23 | 广东宜教通教育有限公司 | A kind of examination question classification and grade of difficulty method based on recurrent neural network |
| CN110033662A (en) * | 2019-03-29 | 2019-07-19 | 金华市花儿教育咨询有限公司 | A kind of method and system of topic information acquisition |
| CN110084099A (en) * | 2019-03-14 | 2019-08-02 | 北京暄暄科技有限公司 | Information feedback method and system based on image recognition technology |
| CN110096589A (en) * | 2019-03-14 | 2019-08-06 | 杭州笔声智能科技有限公司 | A kind of examination question feedback and recommendation explanation method and system based on image recognition technology |
| CN111860526A (en) * | 2020-09-22 | 2020-10-30 | 北京易真学思教育科技有限公司 | Image-based question judging method and device, electronic equipment and computer storage medium |
| CN111915635A (en) * | 2020-08-21 | 2020-11-10 | 广州云蝶科技有限公司 | Test question analysis information generation method and system supporting self-examination paper marking |
| CN113723539A (en) * | 2021-09-02 | 2021-11-30 | 北京云蝶智学科技有限公司 | Test question information acquisition method and device |
-
2014
- 2014-04-23 CN CN201410165812.1A patent/CN103914567A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 贺胜: "面向现代汉语文本处理的全文检索、自动分词通用系统", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| CN104376042A (en) * | 2014-10-11 | 2015-02-25 | 武汉天量数据技术有限公司 | Method and system for acquiring test questions from test question database |
| CN104376042B (en) * | 2014-10-11 | 2017-07-25 | 武汉天量数据技术有限公司 | A kind of item database examination question acquisition methods and system |
| CN104506898A (en) * | 2015-01-12 | 2015-04-08 | 北京东方皆冠科技有限公司 | Image information processing method and system |
| CN104657923A (en) * | 2015-01-15 | 2015-05-27 | 广东小天才科技有限公司 | Method and device for double checking and judging of test questions |
| CN104657923B (en) * | 2015-01-15 | 2018-02-13 | 广东小天才科技有限公司 | Method and device for double checking and judging of test questions |
| CN104750791A (en) * | 2015-03-12 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Image retrieval method and device |
| CN104715253A (en) * | 2015-04-02 | 2015-06-17 | 北京贞观雨科技有限公司 | Method and server for obtaining test question analysis information |
| CN104835365A (en) * | 2015-05-05 | 2015-08-12 | 广东小天才科技有限公司 | Method, intelligent device and device suitable for writing operation inspection |
| 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 |
| CN105427696A (en) * | 2015-11-20 | 2016-03-23 | 江苏沁恒股份有限公司 | Method for distinguishing answer to target question |
| CN105426518A (en) * | 2015-12-03 | 2016-03-23 | 广东小天才科技有限公司 | Method and system for searching questions by photographing |
| CN105843855A (en) * | 2016-03-16 | 2016-08-10 | 广东小天才科技有限公司 | Question searching method and device and intelligent equipment |
| CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and device of intelligent equipment |
| CN106023009A (en) * | 2016-05-05 | 2016-10-12 | 广东小天才科技有限公司 | Method and system for establishing test paper question bank |
| CN106095998B (en) * | 2016-06-21 | 2019-07-05 | 广东小天才科技有限公司 | Precise question searching method and device applied to intelligent terminal |
| CN106095998A (en) * | 2016-06-21 | 2016-11-09 | 广东小天才科技有限公司 | Precise question searching method and device applied to intelligent terminal |
| CN106131422A (en) * | 2016-07-26 | 2016-11-16 | 广东小天才科技有限公司 | Method and device for determining photographing content |
| CN106131422B (en) * | 2016-07-26 | 2019-08-06 | 广东小天才科技有限公司 | Method and device for determining photographing content |
| CN106295514A (en) * | 2016-07-27 | 2017-01-04 | 中山市读书郎电子有限公司 | A kind of method and device of image recognition exercise question display answer |
| CN106250518A (en) * | 2016-08-03 | 2016-12-21 | 广东小天才科技有限公司 | Intelligent question searching method and device |
| CN106294659A (en) * | 2016-08-03 | 2017-01-04 | 广东小天才科技有限公司 | Question searching method and device based on intelligent terminal |
| CN106294659B (en) * | 2016-08-03 | 2019-07-19 | 广东小天才科技有限公司 | Question searching method and device based on intelligent terminal |
| CN106294717A (en) * | 2016-08-08 | 2017-01-04 | 广东小天才科技有限公司 | Question searching method and device based on intelligent terminal |
| CN106294871A (en) * | 2016-08-24 | 2017-01-04 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN106372216A (en) * | 2016-09-05 | 2017-02-01 | 广东小天才科技有限公司 | Method and device for improving question searching accuracy |
| CN106503634A (en) * | 2016-10-11 | 2017-03-15 | 讯飞智元信息科技有限公司 | A kind of image alignment method and device |
| CN108122269A (en) * | 2016-11-28 | 2018-06-05 | 英业达科技有限公司 | Test question generation system and its method based on paper image |
| CN108133209A (en) * | 2016-12-01 | 2018-06-08 | 北京新唐思创教育科技有限公司 | Target area searching method and device in text recognition |
| CN108133209B (en) * | 2016-12-01 | 2021-05-07 | 北京新唐思创教育科技有限公司 | Target area searching method and device in text recognition |
| CN106709055A (en) * | 2017-01-09 | 2017-05-24 | 广东小天才科技有限公司 | Method and device for processing picture test questions |
| CN107330040A (en) * | 2017-06-27 | 2017-11-07 | 李博 | One kind study topic searching method and its system |
| CN107330040B (en) * | 2017-06-27 | 2021-01-26 | 李博 | Learning question searching method and system |
| CN107463681A (en) * | 2017-08-08 | 2017-12-12 | 广东小天才科技有限公司 | Method and device for identifying questions to be searched |
| CN108133039A (en) * | 2018-01-10 | 2018-06-08 | 广州视源电子科技股份有限公司 | Image data processing method and device, electronic equipment and storage medium |
| CN109242103A (en) * | 2018-07-20 | 2019-01-18 | 张有明 | Difficulty of knowledge points assignment processing method and processing device suitable for learning management system |
| CN109063182B (en) * | 2018-08-23 | 2020-11-06 | 广东小天才科技有限公司 | Content recommendation method based on voice search questions and electronic equipment |
| CN109063182A (en) * | 2018-08-23 | 2018-12-21 | 广东小天才科技有限公司 | Content recommendation method based on voice search questions and electronic equipment |
| CN109670042A (en) * | 2018-12-04 | 2019-04-23 | 广东宜教通教育有限公司 | A kind of examination question classification and grade of difficulty method based on recurrent neural network |
| CN110096589A (en) * | 2019-03-14 | 2019-08-06 | 杭州笔声智能科技有限公司 | A kind of examination question feedback and recommendation explanation method and system based on image recognition technology |
| CN110084099A (en) * | 2019-03-14 | 2019-08-02 | 北京暄暄科技有限公司 | Information feedback method and system based on image recognition technology |
| CN110033662A (en) * | 2019-03-29 | 2019-07-19 | 金华市花儿教育咨询有限公司 | A kind of method and system of topic information acquisition |
| CN111915635A (en) * | 2020-08-21 | 2020-11-10 | 广州云蝶科技有限公司 | Test question analysis information generation method and system supporting self-examination paper marking |
| CN111860526A (en) * | 2020-09-22 | 2020-10-30 | 北京易真学思教育科技有限公司 | Image-based question judging method and device, electronic equipment and computer storage medium |
| CN111860526B (en) * | 2020-09-22 | 2020-12-22 | 北京易真学思教育科技有限公司 | Image-based question judging method and device, electronic equipment and computer storage medium |
| CN113723539A (en) * | 2021-09-02 | 2021-11-30 | 北京云蝶智学科技有限公司 | Test question information acquisition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103914567A (en) | Objective test question answer matching method and objective test question answer matching device | |
| CN103927552A (en) | Method and device for matching answers of target test questions | |
| CN110135411B (en) | Business card recognition method and device | |
| Burie et al. | ICDAR2015 competition on smartphone document capture and OCR (SmartDoc) | |
| Ezaki et al. | Text detection from natural scene images: towards a system for visually impaired persons | |
| JP6138305B2 (en) | Camera OCR using context information | |
| US20210020059A1 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN103955525A (en) | Method and client for searching answer to test question | |
| US8953228B1 (en) | Automatic assignment of note attributes using partial image recognition results | |
| CN110175609B (en) | Interface element detection method, device and equipment | |
| KR102569517B1 (en) | Translation method, apparatus and electronic equipment | |
| Sidhwa et al. | Text extraction from bills and invoices | |
| CN112000834B (en) | Document processing method, device, system, electronic equipment and storage medium | |
| CN104750791A (en) | Image retrieval method and device | |
| CN113205046A (en) | Method, system, device and medium for identifying question book | |
| CN113221718B (en) | Formula identification method, device, storage medium and electronic equipment | |
| Tuna et al. | Indexing and keyword search to ease navigation in lecture videos | |
| CN111753715B (en) | Method and device for shooting test questions in click-to-read scene, electronic equipment and storage medium | |
| CN101562694B (en) | Method for realizing functions of character extraction and automatic translation of digital camera | |
| RU2703270C1 (en) | Optical character recognition using specialized confidence functions, implemented on the basis of neural networks | |
| EP4273737A1 (en) | Language labeling method and apparatus, and computer device and storage medium | |
| CN111079777B (en) | Page positioning-based click-to-read method and electronic equipment | |
| Jiju et al. | OCR text extraction | |
| US20230229292A1 (en) | Restoring full online documents from scanned paper fragments | |
| CN112818984B (en) | Title generation method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20140709 |