CN105975552A - Topic search method and apparatus for intelligent device - Google Patents
Topic search method and apparatus for intelligent device Download PDFInfo
- Publication number
- CN105975552A CN105975552A CN201610284975.0A CN201610284975A CN105975552A CN 105975552 A CN105975552 A CN 105975552A CN 201610284975 A CN201610284975 A CN 201610284975A CN 105975552 A CN105975552 A CN 105975552A
- Authority
- CN
- China
- Prior art keywords
- picture
- cursor
- pattern
- content
- exercise question
- 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.)
- Granted
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
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/042—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by opto-electronic means
- G06F3/0425—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by opto-electronic means using a single imaging device like a video camera for tracking the absolute position of a single or a plurality of objects with respect to an imaged reference surface, e.g. video camera imaging a display or a projection screen, a table or a wall surface, on which a computer generated image is displayed or projected
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a topic search method for an intelligent device. The method comprises the steps of enabling cursor display and displaying a cursor in an image obtained by a camera; detecting whether the cursor in the image is in a static state or not; if the cursor in the image is in the static state, searching for topic content in the image according to the position of the cursor; and identifying the searched topic content in the image and performing search according to the identified topic content. According to the method, the search can be automatically performed after the cursor display is enabled and a topic is aligned, so that the convenience of user operation is greatly simplified and the topic search efficiency can be improved.
Description
Technical field
The invention belongs to learning machine field, particularly relate to exercise question searching method and the device of a kind of smart machine.
Background technology
Learning machine is the electronic product that a kind of user of auxiliary carries out learning.Learning machine is typically stored with substantial amounts of
Education resource.Learning machine by by education resource according to certain interactive mode, by display screen or raise one's voice
Device exports such that it is able to preferably help user to understand or mastery learning content.
Do topic efficiency to help user to improve, current learning machine generally has function of search.By study
After the photographic head shooting of machine includes the picture of the item content, the item content in picture are identified, according to
The content identified, searches for identical with the described item content or similar exercise question in resources bank, and shows
The answer scheme of exercise question and answer.
But, current learning machine is when carrying out exercise question search, it usually needs first open the APP application searching topic
Program, then opens photographing unit, after manually taking pictures after focusing exercise question, to the item content in photo
Being identified, the operation of this way of search more bothers, and search efficiency is relatively low.
Summary of the invention
It is an object of the invention to provide the exercise question searching method of a kind of smart machine, enter solving prior art
During the search of row exercise question, operation more bothers, the problem that search efficiency is relatively low.
First aspect, embodiments provides the exercise question searching method of a kind of smart machine, described method
Including:
Unlatching cursor shows, display highlighting in the picture that photographic head obtains;
Detect whether described cursor remains static in described picture;
If described light is marked in described picture and remains static, then according to described smooth target location lookup institute
State the item content in picture;
Identify the item content in the described picture searched, according to the item content search identified.
In conjunction with first aspect, in the first possible implementation of first aspect, described in photographic head acquisition
Picture in display highlighting step particularly as follows:
In the picture that photographic head obtains, show that the first cursor pattern, described first cursor pattern include in cursor
Heart pattern and the light target frame pattern adjacent with described center pattern;
If described light is marked in described picture remain static, then look into according to described smooth target position
The item content step in described picture is looked for include:
If described light is marked in described picture and remains static, then true according to described smooth target Centered Graphs case
Determine the position of the item content;
The border of the described item content, and the position display on the border at the described item content is searched according to picture
Described smooth target frame pattern.
In conjunction with the first possible implementation of first aspect, the second in first aspect may implementation
In, described cursor center pattern is tracking cross pattern, and described smooth target frame pattern is corner frame pattern.
In conjunction with the first possible implementation of first aspect, in the third possible implementation of first aspect
In, the described boundaries step according to the picture described item content of lookup includes:
The line feed identifier included according to described image content searches the border of the described item content;
Or, obtain the line-spacing of the word that described image content includes, presetting in line-spacing is more than picture
Leading value time, it is judged that current location is the border of exercise question.
In conjunction with first aspect, in the 4th kind of possible implementation of first aspect, the described cursor of described detection
The step that whether remains static in described picture includes:
Whether the picture detecting the acquisition of described photographic head changes, and detects whether described cursor receives
Move.
Second aspect, embodiments provides the exercise question searcher of a kind of smart machine, described device
Including:
Cursor opens display unit, is used for opening cursor and shows, display highlighting in the picture that photographic head obtains;
State detection unit, is used for detecting whether described cursor remains static in described picture;
Content search unit, remains static, then according to institute if be marked in described picture for described light
State the item content in picture described in light target location lookup;
Content recognition unit, for identifying the item content in the described picture searched, according to the topic identified
Mesh content search.
In conjunction with second aspect, in the first possible implementation of second aspect, described cursor opens display
Unit specifically for:
In the picture that photographic head obtains, show that the first cursor pattern, described first cursor pattern include in cursor
Heart pattern and the light target frame pattern adjacent with described center pattern;
Described content search unit includes:
Position determines subelement, remains static if be marked in described picture for described light, then basis
Described smooth target Centered Graphs case determines the position of the item content;
Border display subelement, for searching the border of the described item content, and at described exercise question according to picture
Light target frame pattern described in the position display on the border of content.
In conjunction with the first possible implementation of second aspect, the second in second aspect may implementation
In, described cursor center pattern is tracking cross pattern, and described smooth target frame pattern is corner frame pattern.
In conjunction with the first possible implementation of second aspect, in the third possible implementation of second aspect
In, described content search unit includes:
First searches subelement, searches described topic for the line feed identifier included according to described image content
The border of mesh content;
Or, second searches subelement, for obtaining the line-spacing of the word that described image content includes, when
When line-spacing is more than the leading value preset in picture, it is judged that current location is the border of exercise question.
In conjunction with second aspect, in the 4th kind of possible implementation of second aspect, described state detection unit
Specifically for:
Whether the picture detecting the acquisition of described photographic head changes, and detects whether described cursor receives
Move.
In the present invention, when user opens cursor display, display highlighting in the picture that photographic head obtains,
Whether the cursor that system detects in described picture is resting state, when cursor remains static, then and basis
The light target location lookup item content, and scan for according to the item content identified, so that the present invention
After opening cursor display alignment exercise question, can automatically scan for, greatly simplified user operation just
Profit, is conducive to improving the efficiency of exercise question search.
Accompanying drawing explanation
Fig. 1 is the flowchart of the exercise question searching method of the smart machine that first embodiment of the invention provides;
Fig. 2 is the flowchart of the exercise question searching method of the smart machine that second embodiment of the invention provides;
Fig. 3 is the cursor display view that second embodiment of the invention provides;
The structural representation of the exercise question searcher of the smart machine that Fig. 4 provides for third embodiment of the invention.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and reality
Execute example, the present invention is further elaborated.Only should be appreciated that specific embodiment described herein
Only in order to explain the present invention, it is not intended to limit the present invention.
The purpose of the embodiment of the present invention is to provide the exercise question searching method of smart machine, to solve prior art
In time exercise question is scanned for, operation more bothers, the problem that search efficiency is low.In the prior art,
When using learning machine or other study kind equipment to scan for, need first to open the application program of search exercise question,
When application program is opened, open photographic head, photographic head shooting include the picture of the item content,
Then by Text region program, the item content in picture are carried out Text region, user select the topic needed
Mesh content, or directly recognition result is sent to server or local title data base, and in a device
Show corresponding exercise question result.For specifically describing how to solve the problems referred to above, below in conjunction with the accompanying drawings, to this
Bright it is specifically described.
Embodiment one:
Fig. 1 shows the realization stream of the exercise question searching method of the smart machine that first embodiment of the invention provides
Journey, details are as follows:
In step S101, open cursor and show, display highlighting in the picture that photographic head obtains.
Concrete, open cursor described in the embodiment of the present invention and show, can arrange in the equipment such as learning machine
Hardware switch, by hardware switch is switched to opening, such that it is able to during the use of learning machine
Quickly switch to the state of exercise question search.
It is of course also possible to arrange cursor in the equipment such as learning machine to open button, after user clicks on this button,
The equipment such as learning machine can quickly open photographic head, shows the picture obtained by photographic head, and at described picture
Display highlighting in face.
In a kind of embodiment, during the display of described unlatching cursor, can be that equipment is in holding state.
As such, it is possible to the most quickly use equipment to carry out exercise question search, it is possible to be further user-friendly to.
The picture that described photographic head obtains, can show, it is also possible in the appointment of screen by the way of full frame
Region is shown by the form of window.Described cursor can be by the display mode of acquiescence, and display is at described picture
The medium position in face, it is also possible to be redefined for cursor and show other position at described picture.
User by the way of touch, or by the way of mobile mouse, can change described smooth target position
Put, such as by the way of touch, cursor is moved the exercise question position etc. to picture.
In step s 102, detect whether described cursor remains static in described picture.
Concrete, after unlatching cursor shows, the picture of photographic head alignment is not likely to be the picture at exercise question place,
Need user adjust photographic head to picture, or adjust the required exercise question institute identified by adjusting cursor
Position.When, after the picture at the exercise question place that user adjusts required search, in picture, light is marked on picture
Position in face then remains static, then it represents that user has been directed at needs the exercise question of search, if light is marked on
Picture is in relative motion state, then it represents that user is currently at dollying head, or is moving cursor,
The position at exercise question place can't be determined.
Therefore, when in the embodiment of the present invention, whether detection cursor remains static in described picture, permissible
Whether change including the picture detecting the acquisition of described photographic head, and detect whether described cursor receives
Move.
When user determines the item content that the current picture of photographic head includes required search, then need to adjust
Finishing equipment is resting state, and the picture keeping photographic head to obtain does not changes, and is further entered by cursor
The adjustment of row item content position.
If the user while guarantee picture still, and cursor static time reaches certain time length, is such as in
When the time of resting state is more than 500-800 millisecond, then it is believed that current cursor position correspondence exercise question
The position at content place.
In step s 103, remain static if described light is marked in described picture, then according to described light
The item content in picture described in target location lookup.
Concrete, remain static if light is marked in described picture, then the position that explanation cursor currently indicates
It is set to the position at exercise question place.Therefore, the present invention position by cursor place, automatically search in picture and inscribe
The position at mesh content place such that it is able to find the exercise question in picture efficiently, it is to avoid the behaviour that user is loaded down with trivial details
Make.
Wherein, according to the item content in picture described in described smooth target location lookup, can be according to described light
Centered by target position, carry out according to predetermined exercise question scope identifier the lookup of the item content, such as exercise question with
The spacing generally having between newline, or exercise question and exercise question between exercise question is typically larger than normal spacing etc.,
Determine the size of the content of described exercise question.
After finding the described item content, can point out in the way of sending auditory tone cues or display reminding
Currently having found the item content in picture, prompting user is confirmed whether correctly, if the user thinks that correctly
If, can continue to keep such state, and etc. Search Results to be returned, if the content searched is the most just
Really, then can change light target position, or change the picture that photographic head obtains, re-start the item content
Acquisition.
In step S104, identify the item content in the described picture searched, according in the exercise question identified
Hold search.
Behind the position of the item content in determining described picture and size, Text region program can be passed through
The item content in this region are identified, from recognition efficiency for, the present invention has only to exercise question place
The part picture of position is identified, the efficiency that the exercise question in picture is identified by the raising that can show.
In the embodiment of the present invention, when user opens cursor display, in the picture that photographic head obtains, show light
Mark, whether the cursor that system detects in described picture is resting state, when cursor remains static, then
According to the light target location lookup item content, and scan for according to the item content identified, so that this
Invent after opening cursor display alignment exercise question, can automatically scan for, greatly simplified user operation
Convenience, be conducive to improve exercise question search efficiency.
Embodiment two:
Fig. 2 shows the realization stream of the exercise question searching method of the smart machine that second embodiment of the invention provides
Journey, details are as follows:
In step s 201, open cursor and show, in the picture that photographic head obtains, show the first cursor pattern,
Described first cursor pattern includes cursor center pattern and the light target frame figure adjacent with described center pattern
Case.
Concrete, as light target one embodiment described in the embodiment of the present invention, as it is shown on figure 3, described
Cursor includes center pattern and light target frame pattern, and described center pattern is tracking cross pattern, described light
Target frame pattern is corner frame pattern.Certainly, this is one of which embodiment, makes according to user
With needs, center pattern and light target frame pattern can be changed flexibly.
In embodiments of the present invention, described cursor includes two kinds of display states, and the first is that cursor completely shows
State, described smooth target Centered Graphs case is adjacent with light target frame pattern, and in this state, user is permissible
Mobile cursor, or the image content that photographic head obtains can be changed, make the light being under complete display state
Content in the picture that mark and photographic head obtain keeps geo-stationary.So that it is determined that the item content in picture.
The second state is after the first state, after detecting that light is marked on and remains static in picture, and light
Target frame pattern carries out automatic exercise question border searching, and by described smooth target frame pattern on the limit of exercise question
Boundary's position display, described center pattern can adjust described center pattern exist according to the position on the border searched
The center of described smooth target frame pattern shows.
In step S202, detect whether described cursor remains static in described picture.
In step S203, remain static if described light is marked in described picture, then according to described light
Target center pattern determines the position of the item content.
Concrete, light described in the embodiment of the present invention is marked in described picture and remains static, including two
Essential condition:
1) content in picture remains static, say, that the image content acquired in photographic head is not sent out
Changing, user has confirmed that current picture includes the exercise question of required search;
2) cursor on the display screen of the equipment such as learning machine remains static, and during this time, user does not has
Cursor is moved, say, that user has confirmed that the position that cursor is current by modes of operation such as touch or mouses
It is in the position at exercise question place.
In step S204, search the border of the described item content according to picture, and at the described item content
Light target frame pattern described in the position display on border.
In embodiments of the present invention, still further comprise the border to the item content and make a look up, wherein, root
The boundaries step searching the described item content according to picture includes:
The line feed identifier included according to described image content searches the border of the described item content;
Or, obtain the line-spacing of the word that described image content includes, presetting in line-spacing is more than picture
Leading value time, it is judged that current location is the border of exercise question.
Wherein, described default line-spacing, can be the line-spacing of normal words setting.Due to spacing can picture with
The distance of picture and change, in order to improve the accuracy rate of judgement, it is also possible to by word and spacing
Ratio judges, when the ratio of such as word size and line-spacing is less than predetermined value, then judges current behavior exercise question
Boundary position.And show described smooth target frame pattern at described boundary position.For the ease of confirming frame
Position, can show described smooth target frame pattern by the way of flicker.
In step S205, identify the item content in the described picture searched, according in the exercise question identified
Hold search.
After the embodiment of the present invention determines the region at item content place by light target frame pattern, can more enter
One step improves the efficiency that the item content are identified, and is carried out the item content by light target frame pattern
Selected, the accuracy rate of exercise question search can be improved.
Embodiment three:
Fig. 4 shows the structural representation of the exercise question searcher of the smart machine that third embodiment of the invention provides
Figure, details are as follows:
The exercise question searcher of smart machine described in the embodiment of the present invention, including:
Cursor opens display unit 401, is used for opening cursor and shows, shows in the picture that photographic head obtains
Cursor;
State detection unit 402, is used for detecting whether described cursor remains static in described picture;
Content search unit 403, remains static if be marked in described picture for described light, then root
According to the item content in picture described in described smooth target location lookup;
Content recognition unit 404, for identifying the item content in the described picture searched, according to identification
The item content search.
Preferably, described cursor open display unit specifically for:
In the picture that photographic head obtains, show that the first cursor pattern, described first cursor pattern include in cursor
Heart pattern and the light target frame pattern adjacent with described center pattern;
Described content search unit includes:
Position determines subelement, remains static if be marked in described picture for described light, then basis
Described smooth target Centered Graphs case determines the position of the item content;
Border display subelement, for searching the border of the described item content, and at described exercise question according to picture
Light target frame pattern described in the position display on the border of content.
Preferably, described cursor center pattern is tracking cross pattern, and described smooth target frame pattern is corner
Frame pattern.
Preferably, described content search unit includes:
First searches subelement, searches described topic for the line feed identifier included according to described image content
The border of mesh content;
Or, second searches subelement, for obtaining the line-spacing of the word that described image content includes, when
When line-spacing is more than the leading value preset in picture, it is judged that current location is the border of exercise question.
Preferably, described state detection unit specifically for:
Whether the picture detecting the acquisition of described photographic head changes, and detects whether described cursor receives
Move.
The exercise question searcher of smart machine described in the embodiment of the present invention, sets with intelligence described in embodiment one and two
Standby exercise question searching method is corresponding, is not repeated description at this.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, can
To realize by another way.Such as, device embodiment described above is only schematically, example
Such as, the division of described unit, being only a kind of logic function and divide, actual can have other drawing when realizing
Point mode, the most multiple unit or assembly can in conjunction with or be desirably integrated into another system, or some are special
Levy and can ignore, or do not perform.Another point, shown or discussed coupling each other or direct-coupling
Or communication connection can be the INDIRECT COUPLING by some interfaces, device or unit or communication connection, Ke Yishi
Electrically, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, as
The parts that unit shows can be or may not be physical location, i.e. may be located at a place, or
Can also be distributed on multiple NE.Can select therein some or all of according to the actual needs
Unit realizes the purpose of the present embodiment scheme.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit,
Can also be that unit is individually physically present, it is also possible to two or more unit are integrated in a unit
In.Above-mentioned integrated unit both can realize to use the form of hardware, it would however also be possible to employ SFU software functional unit
Form realizes.
If described integrated unit realizes using the form of SFU software functional unit and as independent production marketing or
During use, can be stored in a computer read/write memory medium.Based on such understanding, the present invention
The part that the most in other words prior art contributed of technical scheme or this technical scheme whole or
Part can embody with the form of software product, and this computer software product is stored in a storage medium
In, including some instructions with so that computer equipment (can be personal computer, server, or
Person's network equipment etc.) perform all or part of of method described in each embodiment of the present invention.And aforesaid storage
Medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), deposit at random
Access to memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store program
The medium of code.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all at this
Any amendment, equivalent and the improvement etc. made within bright spirit and principle, should be included in the present invention
Protection domain within.
Claims (10)
1. the exercise question searching method of a smart machine, it is characterised in that described method includes:
Unlatching cursor shows, display highlighting in the picture that photographic head obtains;
Detect whether described cursor remains static in described picture;
If described light is marked in described picture and remains static, then according to described smooth target location lookup institute
State the item content in picture;
Identify the item content in the described picture searched, according to the item content search identified.
Method the most according to claim 1, it is characterised in that described aobvious in the picture that photographic head obtains
Show cursor step particularly as follows:
In the picture that photographic head obtains, show that the first cursor pattern, described first cursor pattern include in cursor
Heart pattern and the light target frame pattern adjacent with described center pattern;
If described light is marked in described picture remain static, then look into according to described smooth target position
The item content step in described picture is looked for include:
If described light is marked in described picture and remains static, then true according to described smooth target Centered Graphs case
Determine the position of the item content;
The border of the described item content, and the position display on the border at the described item content is searched according to picture
Described smooth target frame pattern.
Method the most according to claim 2, it is characterised in that described cursor center pattern is tracking cross
Pattern, described smooth target frame pattern is corner frame pattern.
Method the most according to claim 2, it is characterised in that described according in the picture described exercise question of lookup
The boundaries step held includes:
The line feed identifier included according to described image content searches the border of the described item content;
Or, obtain the line-spacing of the word that described image content includes, presetting in line-spacing is more than picture
Leading value time, it is judged that current location is the border of exercise question.
Method the most according to claim 1, it is characterised in that whether the described cursor of described detection is described
The step that remains static in picture includes:
Whether the picture detecting the acquisition of described photographic head changes, and detects whether described cursor receives
Move.
6. the exercise question searcher of a smart machine, it is characterised in that described device includes:
Cursor opens display unit, is used for opening cursor and shows, display highlighting in the picture that photographic head obtains;
State detection unit, is used for detecting whether described cursor remains static in described picture;
Content search unit, remains static, then according to institute if be marked in described picture for described light
State the item content in picture described in light target location lookup;
Content recognition unit, for identifying the item content in the described picture searched, according to the topic identified
Mesh content search.
Device the most according to claim 6, it is characterised in that described cursor is opened display unit and specifically used
In:
In the picture that photographic head obtains, show that the first cursor pattern, described first cursor pattern include in cursor
Heart pattern and the light target frame pattern adjacent with described center pattern;
Described content search unit includes:
Position determines subelement, remains static if be marked in described picture for described light, then basis
Described smooth target Centered Graphs case determines the position of the item content;
Border display subelement, for searching the border of the described item content, and at described exercise question according to picture
Light target frame pattern described in the position display on the border of content.
Device the most according to claim 7, it is characterised in that described cursor center pattern is tracking cross
Pattern, described smooth target frame pattern is corner frame pattern.
Device the most according to claim 7, it is characterised in that described content search unit includes:
First searches subelement, searches described topic for the line feed identifier included according to described image content
The border of mesh content;
Or, second searches subelement, for obtaining the line-spacing of the word that described image content includes, when
When line-spacing is more than the leading value preset in picture, it is judged that current location is the border of exercise question.
Device the most according to claim 6, it is characterised in that described state detection unit specifically for:
Whether the picture detecting the acquisition of described photographic head changes, and detects whether described cursor receives
Move.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610284975.0A CN105975552B (en) | 2016-04-29 | 2016-04-29 | Question searching method and device of intelligent equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610284975.0A CN105975552B (en) | 2016-04-29 | 2016-04-29 | Question searching method and device of intelligent equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105975552A true CN105975552A (en) | 2016-09-28 |
CN105975552B CN105975552B (en) | 2020-01-03 |
Family
ID=56994594
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610284975.0A Active CN105975552B (en) | 2016-04-29 | 2016-04-29 | Question searching method and device of intelligent equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105975552B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106681538A (en) * | 2016-12-07 | 2017-05-17 | 广东小天才科技有限公司 | Method, equipment and system for locating content |
CN107463681A (en) * | 2017-08-08 | 2017-12-12 | 广东小天才科技有限公司 | A kind of recognition methods of topic to be searched and device |
CN110069206A (en) * | 2019-04-23 | 2019-07-30 | 广东小天才科技有限公司 | A kind of method and device obtaining topic picture |
CN111711757A (en) * | 2020-06-29 | 2020-09-25 | 广东小天才科技有限公司 | Test question shooting method and device capable of preventing finger from being blocked, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1208199A (en) * | 1997-08-12 | 1999-02-17 | 英业达股份有限公司 | Fast word translating method and device for computer windows |
JP2004318365A (en) * | 2003-04-15 | 2004-11-11 | Hokkaido Univ | Image search system, image search method, and its program |
CN103237109A (en) * | 2013-04-10 | 2013-08-07 | 广东欧珀移动通信有限公司 | Method and device for turning on flash lamp in standby state based on mobile phone |
CN103927552A (en) * | 2014-04-23 | 2014-07-16 | 北京奇虎科技有限公司 | Method and device for matching answers of target test questions |
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 |
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 |
CN105426390A (en) * | 2015-10-23 | 2016-03-23 | 广东小天才科技有限公司 | Image recognition-based question search method and system |
-
2016
- 2016-04-29 CN CN201610284975.0A patent/CN105975552B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1208199A (en) * | 1997-08-12 | 1999-02-17 | 英业达股份有限公司 | Fast word translating method and device for computer windows |
JP2004318365A (en) * | 2003-04-15 | 2004-11-11 | Hokkaido Univ | Image search system, image search method, and its program |
CN103237109A (en) * | 2013-04-10 | 2013-08-07 | 广东欧珀移动通信有限公司 | Method and device for turning on flash lamp in standby state based on mobile phone |
CN103927552A (en) * | 2014-04-23 | 2014-07-16 | 北京奇虎科技有限公司 | Method and device for matching answers of target test questions |
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 |
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 |
CN105426390A (en) * | 2015-10-23 | 2016-03-23 | 广东小天才科技有限公司 | Image recognition-based question search method and system |
Non-Patent Citations (1)
Title |
---|
手机百度: "手机百度APP版本7.2", 《安智市场》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106681538A (en) * | 2016-12-07 | 2017-05-17 | 广东小天才科技有限公司 | Method, equipment and system for locating content |
CN106681538B (en) * | 2016-12-07 | 2019-08-09 | 广东小天才科技有限公司 | A kind of content positioning method and equipment, system |
CN107463681A (en) * | 2017-08-08 | 2017-12-12 | 广东小天才科技有限公司 | A kind of recognition methods of topic to be searched and device |
CN110069206A (en) * | 2019-04-23 | 2019-07-30 | 广东小天才科技有限公司 | A kind of method and device obtaining topic picture |
CN111711757A (en) * | 2020-06-29 | 2020-09-25 | 广东小天才科技有限公司 | Test question shooting method and device capable of preventing finger from being blocked, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105975552B (en) | 2020-01-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105975550A (en) | Examination question search method and device of intelligent device | |
CN105892685B (en) | A kind of the topic searching method and device of smart machine | |
US11238628B2 (en) | Intelligent context-based image recommendations | |
CN105933607B (en) | A kind of take pictures effect method of adjustment and the mobile terminal of mobile terminal | |
CN105975560B (en) | Question searching method and device of intelligent equipment | |
KR102173123B1 (en) | Method and apparatus for recognizing object of image in electronic device | |
CN101295352B (en) | Human face recognition and user interface system for digital camera and video camera | |
US8873845B2 (en) | Contextual dominant color name extraction | |
US20150277686A1 (en) | Systems and Methods for the Real-Time Modification of Videos and Images Within a Social Network Format | |
CN105975552A (en) | Topic search method and apparatus for intelligent device | |
CN103838566A (en) | Information processing device, and information processing method | |
US9449216B1 (en) | Detection of cast members in video content | |
CN101867755A (en) | Information processing apparatus, information processing method, and program | |
CN104166694A (en) | Image classifying and storing method and electronic device | |
CN106101771A (en) | Method for processing video frequency, device and terminal | |
CN112487242A (en) | Method and device for identifying video, electronic equipment and readable storage medium | |
US20220254143A1 (en) | Method and apparatus for determining item name, computer device, and storage medium | |
CN105956078A (en) | Question searching method and device for intelligent device | |
CN106407977A (en) | Target content positioning and search method and device | |
CN113873166A (en) | Video shooting method and device, electronic equipment and readable storage medium | |
CN103543916A (en) | Information processing method and electronic equipment | |
CN108664339A (en) | A kind of information displaying method and device, terminal, readable storage medium storing program for executing | |
CN109697242B (en) | Photographing question searching method and device, storage medium and computing equipment | |
CN106446884A (en) | Method and device for rapidly capturing images | |
US11763564B1 (en) | Techniques for generating optimized video segments utilizing a visual search |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |