CN111563511A

CN111563511A - Method and device for intelligently framing questions, electronic equipment and storage medium

Info

Publication number: CN111563511A
Application number: CN202010366614.7A
Authority: CN
Inventors: 曾菲
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2020-04-30
Filing date: 2020-04-30
Publication date: 2020-08-21
Anticipated expiration: 2040-04-30
Also published as: CN111563511B

Abstract

The embodiment of the invention relates to the technical field of intelligent equipment, and discloses a method and a device for intelligently framing a topic, electronic equipment and a storage medium. The method comprises the following steps: when receiving a frame question instruction, acquiring an image containing a target question; identifying the position coordinates of each character in the target title in the image; sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line, and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line; acquiring a picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line. By implementing the embodiment of the invention, the intelligent box can be automatically adjusted according to the character direction of the target topic, the incomplete target topic or invalid information obtained by the target topic is avoided, the efficiency of the target topic is improved, and the user experience is improved.

Description

Method and device for intelligently framing questions, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of intelligent equipment, in particular to a method and a device for intelligently framing questions, electronic equipment and a storage medium.

Background

At present, intelligent devices such as learning machines and home education machines have a question-framing function. The existing manual or automatic frame question is to select the framed selection content by setting a rectangular frame, and then obtain the question in the rectangular frame through an intercepting function. The adjustment of the rectangular frame is generally limited to the adjustment of the length or the width, but the angle of the question is set in an inclined manner, for example, as shown in fig. 1, when the rectangular frame is too small, all the contents of the question cannot be completely framed, and if the rectangular frame is too large, the frame is taken into invalid information, that is, the contents of other questions are framed, so that the user may need to adjust the size of the rectangular frame many times to complete one-time question framing operation by adopting the rectangular frame mode, the use efficiency is reduced, and bad experience is brought to the user.

Disclosure of Invention

Aiming at the defects, the embodiment of the invention discloses a method and a device for intelligently framing a question, electronic equipment and a storage medium, wherein a framing area can be intelligently set according to the character direction of the question.

The first aspect of the embodiment of the invention discloses a method for intelligently framing a topic, which comprises the following steps:

when receiving a frame question instruction, acquiring an image containing a target question;

identifying the position coordinates of each character in the target title in the image;

sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line, and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line;

acquiring a picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, sequentially connecting vertex position coordinates of a first row in the target topic to form a first connection line, and sequentially connecting bottom position coordinates of a last row in the target topic to form a second connection line includes:

each character is given a rectangular frame, and the rectangular frames satisfy the following conditions: no overlapping area exists between the rectangular frames, each character is positioned in the corresponding rectangular frame, and the length or/and the width of any two rectangular frames are equal;

acquiring the position coordinates of the middle points of four sides of each rectangular frame;

determining a target point; the distance between the target point and any other midpoint position coordinate is larger than a preset threshold value;

determining vertex coordinates and bottom coordinates in the target point; the vertex coordinates are the coordinates of the middle point position of the upper frame of the rectangular frame, and the bottom coordinates are the coordinates of the middle point position of the lower frame of the rectangular frame;

and sequentially connecting the vertex coordinates to form the first connecting line, and sequentially connecting the bottom coordinates to form the second connecting line.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the intelligent box includes:

determining a left point coordinate and a right point coordinate in a target point; the left point coordinate is a middle point position coordinate of a left frame of the rectangular frame, and the right point coordinate is a middle point position coordinate of a right frame of the rectangular frame;

the intelligent frame is a closed line segment set formed by sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate and the right point coordinate.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate, and the right point coordinate includes:

any target point is connected to two other target points which are closest to it.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, connecting an arbitrary target point with two other target points closest to the arbitrary target point further includes:

determining a multipoint rectangular frame and a plurality of related target points on the multipoint rectangular frame, wherein the related target points are two or more than two target points on the multipoint rectangular frame;

the connecting line between two adjacent related target points comprises a first line segment and a second line segment, wherein the first line segment and the second line segment are distributed on the frame of the multipoint rectangular frame where the two adjacent related target points are located, and the first line segment and the second line segment exist and only have one intersection point.

determining a target left point coordinate and a target right point coordinate; the target left point coordinate is the left point coordinate with the minimum abscissa, and the target right point coordinate is the right point coordinate with the maximum abscissa;

determining a first target vertex coordinate, a first target bottom coordinate, a second target vertex coordinate and a second target bottom coordinate; the first target vertex coordinate is a vertex coordinate closest to a target left point coordinate in a first row of a target title, the first target bottom coordinate is a bottom coordinate closest to the target left point coordinate in a last row of the target title, the second target vertex coordinate is a vertex coordinate closest to a target right point coordinate in the first row of the target title, and the second target bottom coordinate is a bottom coordinate closest to the target right point coordinate in the last row of the target title;

obtaining a left boundary according to the target left point coordinate, the first target vertex coordinate and the first target bottom coordinate; obtaining a right boundary according to the target right point coordinate, the second target vertex coordinate and the second target bottom coordinate;

sequentially connecting the first target vertex coordinate, the hit vertex coordinate and the second target vertex coordinate to form an upper edge line; sequentially connecting the first target bottom coordinate, the hit bottom coordinate and the second target bottom coordinate to form a lower edge line;

the intelligent frame is an area defined by a left boundary, an upper sideline, a right boundary and a lower sideline;

a first intersection point and a second intersection point are formed between the extension line of the left frame where the target left point coordinate is located and the extension line of the upper frame where the first target vertex coordinate is located and the extension line of the lower frame where the first target bottom coordinate is located respectively; the left boundary comprises a connecting line between the first target vertex coordinate and the first intersection point, a connecting line between the first intersection point and the second intersection point and a connecting line between the second intersection point and the first target bottom coordinate;

a third intersection point and a fourth intersection point are formed between the extension line of the right frame where the target right point coordinate is located and the extension line of the upper frame where the second target vertex coordinate is located and the extension line of the lower frame where the second target bottom coordinate is located respectively; the right boundary comprises a connecting line between the second target vertex coordinate and a third intersection point, a connecting line between the third intersection point and a fourth intersection point and a connecting line between the fourth intersection point and the second target bottom coordinate;

the first intersection point, the second intersection point, the first target vertex coordinate and the first target bottom coordinate form a first quadrangle; the third intersection point, the fourth intersection point, the second target vertex coordinate and the second target bottom coordinate form a second quadrangle; the hit vertex coordinates and the hit bottom coordinates are not located in the first quadrangle or the second quadrangle, and a rectangular frame where the hit vertex coordinates and the hit bottom coordinates are located is not intersected with a connecting line between the first target vertex coordinates and the first target bottom coordinates or a connecting line between the second target vertex coordinates and the second target bottom coordinates.

As an optional implementation manner, in the first aspect of this embodiment of the present invention, the method further includes:

judging whether the line segments in the intelligent frame are intersected with the position coordinates of the image where the characters are located;

if the intersection exists, determining a target line segment which is intersected with the position coordinate of the image where the character is located in the intelligent frame;

determining a rectangular frame in which two end points of the target line segment are located,

and adjusting the size of the rectangular frame where the two end points are located.

The second aspect of the embodiments of the present invention discloses an intelligent question framing device, which includes:

the acquisition unit is used for acquiring an image containing a target question when receiving a frame question instruction;

the identification unit is used for identifying the position coordinates of each character in the target title in the image;

the marking unit is used for sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line;

the frame selection unit is used for acquiring the picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line.

A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory to execute the method for intelligent framing disclosed by the first aspect of the embodiment of the invention.

A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, where the computer program enables a computer to execute the method for intelligently framing a topic disclosed in the first aspect of the embodiments of the present invention.

A fifth aspect of the embodiments of the present invention discloses a computer program product, which, when running on a computer, causes the computer to execute the method for intelligently framing topics disclosed in the first aspect of the embodiments of the present invention.

A sixth aspect of the present invention discloses an application publishing platform, where the application publishing platform is configured to publish a computer program product, and when the computer program product runs on a computer, the computer is enabled to execute the method for intelligently framing a topic disclosed in the first aspect of the present invention.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, when a frame question instruction is received, an image containing a target question is collected; identifying the position coordinates of each character in the target title in the image; sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line, and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line; acquiring a picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line. Therefore, by implementing the embodiment of the invention, the intelligent frame can be determined by adopting the vertex position coordinates of the first line and the bottom position coordinates of the last line, the intelligent frame is automatically adjusted according to the target character direction of the target title, the incomplete target title or invalid information obtained by the frame is avoided, the frame title efficiency is improved, and the user experience is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a schematic diagram of a conventional block-topic method;

FIG. 2 is a flow chart of a method for intelligently framing questions according to an embodiment of the present invention;

FIG. 3 is a diagram of an intelligent box according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of an embodiment of the invention for adjusting the smart box;

FIG. 5 is a schematic diagram of an intelligent frame edge optimization disclosed in an embodiment of the present invention;

FIG. 6 is a schematic diagram of another smart box disclosed in embodiments of the present invention;

FIG. 7 is a schematic diagram of another smart box disclosed in embodiments of the present invention;

FIG. 8 is a flow chart illustrating another method for intelligently framing questions in accordance with an embodiment of the present invention;

FIG. 9 is a diagram illustrating an acquire smart box according to an embodiment of the present disclosure;

FIG. 10 is a schematic diagram of another smart box disclosed in embodiments of the present invention;

FIG. 11 is a schematic diagram of another smart box disclosed in embodiments of the present invention;

FIG. 12 is a schematic diagram of another smart box disclosed in embodiments of the present invention;

FIG. 13 is a schematic structural diagram of an intelligent question framing apparatus according to an embodiment of the present invention;

fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second", "third", "fourth", and the like in the description and the claims of the present invention are used for distinguishing different objects, and are not used for describing a specific order. The terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a method, a device, electronic equipment and a storage medium for intelligent framing, which can determine a framing area through a vertex coordinate connecting line and a bottom coordinate connecting line by acquiring position coordinates of each character, can intelligently frame contents according to the actual situation of a target topic, ensure the accuracy of the framing topic and improve the efficiency of the framing topic, and are described in detail in combination with the attached drawings.

Example one

Referring to fig. 2, fig. 2 is a schematic flow chart of an intelligent question framing method according to an embodiment of the present invention. The method is suitable for intelligent equipment such as learning machines, family education machines, point reading machines, tablet computers or mobile phones. The frame title is to select and extract the contents with the target title and the target destination in the image. As shown in fig. 2, the intelligent question framing method includes the following steps:

110. when a framing question instruction is received, an image containing a target question is collected.

The frame questions are used in learning, and the purpose of the frame questions can be to search for questions, store wrong questions, knowledge points and the like. The framing instruction is initiated by a user, i.e., an operator, and may be a voice instruction, or a pulse instruction formed by triggering by the user through a touch screen or a mechanical button, or formed by a specific gesture, which is not limited herein. Before the frame question instruction is received, most devices of the camera and the intelligent device are in a sleep state, so that the electric quantity can be saved, and the camera and the intelligent device are awakened through the frame question instruction.

After receiving the instruction of the frame topic, the intelligent device starts a camera, and takes an image with the target topic according to the intention of the operator (for example, by means of finger positioning), wherein the image generally comprises all contents of the target topic and some invalid information irrelevant to the target topic, and the embodiment of the invention aims to accurately select the target content of the target topic.

120. And identifying the position coordinates of each character in the target title in the image.

The method mainly comprises two steps of firstly identifying each character in a target title and then determining the position coordinate of each character. Before step 120 is performed, the image may be pre-processed by the smart device, the pre-processing including but not limited to: denoising, contrast enhancement, shape correction and the like.

Illustratively, recognizing each character of the target title can be realized by a mature OCR (Optical character recognition) technology, where the OCR is to detect a character in an image by an electronic device, determine a shape of the character by detecting a dark and light pattern, optically convert characters in the image into an image file of a black-and-white dot matrix, and then convert the image characters into a text format by an identification software from the image file of the black-and-white dot matrix.

The position coordinates of each identified character are determined only by positioning the black and white dot matrix in the image file, so that the position coordinates of each character in the image are determined.

The determination of the coordinates of each character of the target title is realized based on the user intention and a preset rule, for example, a user selects a point on a book through a finger, the preset rule is a title on the upper side of the point, the coordinates of the point in the image can be obtained through affine transformation, and each character of the target title and the position coordinates of each character in the image can be obtained through the image coordinates according to the preset rule.

130. And sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line, and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line.

The black dot matrix or the white dot matrix among the black-and-white dot matrix is an image of each character. Taking a character image as an example of a black dot matrix, after the position coordinates of each black dot matrix are determined, the vertex position coordinates of the black dot matrix in the first row and the bottom position coordinates of the black dot matrix in the last row are screened out, and the judgment of the first row and the last row can be based on the positions of the black dot matrixes in the image coordinates. The vertex position coordinate may be the maximum ordinate of each black dot matrix of the first row, and the bottom position coordinate may be the minimum ordinate of each black dot matrix of the last row.

In order to prevent intersection with corresponding characters during connection, the final vertex position coordinates and bottom position coordinates can be obtained by adding a preset value on the basis of the maximum ordinate and subtracting the preset value on the basis of the minimum coordinate. The preset value is selected to ensure that the vertex position coordinates and the bottom position coordinates do not fall on characters outside the target subject, and meanwhile, the first connecting line and the second connecting line do not intersect with the characters outside the target subject.

And sequentially connecting the vertex position coordinates to obtain a first connecting line, and sequentially connecting the bottom position coordinates to obtain a second connecting line.

140. Acquiring a picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line.

The area between the first connecting line and the second connecting line forms the intelligent frame, and as for the left edge and the right edge of the intelligent frame, the left edge and the right edge can be formed by extending towards the edge of the image according to the end points of the first connecting line and the second connecting line, namely the left edge and the right edge are not arranged.

After the intelligent frame is obtained, the corresponding image in the intelligent frame can be obtained, and the image can be stored or searched.

By implementing the embodiment of the invention, the first connecting line and the second connecting line can be obtained based on the position coordinates of each character, and the intelligent frame is formed by the area enclosed between the first connecting line and the second connecting line. Except the situation that the target topic is completely horizontal, the intelligent frame is a rectangular frame, and as long as the target topic is slightly inclined, the intelligent frame is a closed line segment set formed by a plurality of line segments, but not a rectangular structure, the intelligent frame is automatically adjusted according to the character direction of the target topic, and various operations such as rotation of a shot image are not needed, so that the target topic is prevented from being incomplete or invalid information is obtained by the frame, the efficiency of the frame topic is improved, and the user experience is improved.

Example two

On the basis of the first embodiment, each character is selected through the rectangular frame, and the vertex position coordinates of the first row and the bottom position coordinates of the last row of the target title are determined according to the vertex coordinates and the bottom coordinates of the rectangular frame, so that the method is more intelligent.

In the second embodiment, each character is given a rectangular box, and the rectangular box satisfies: no overlapping area exists between the rectangular frames, and each character is positioned inside the corresponding rectangular frame;

The characters comprise Chinese characters, letters, punctuation marks, formulas and the like, a preset threshold value is conveniently and uniformly set, the rectangular frame is mainly set according to the Chinese characters, if a single letter or punctuation mark appears, the rectangular frame identical to the Chinese character is adopted, if a combination of a plurality of letters appears, such as English words or Pinyin or formula appears, the size of the rectangular frame is adaptively set according to the situation, and the rectangular frame becomes a special rectangular frame.

The distance between the target point and any other midpoint position coordinate is larger than a preset threshold value. If the value is less than the preset threshold, it may be the bottom coordinate of the middle line or the first line or the vertex coordinate of the last line, and these midpoint position coordinates need to be excluded, and generally, the preset threshold may be set slightly less than the preset threshold

a and b are the length and width of the rectangular frame, respectively.

Based on the preset threshold, if the target title has multiple lines and the interval between the lines of content is large, the height of the rectangular frame can be increased appropriately to prevent the midpoint position coordinate between two lines from being identified as the target point.

Four types exist in the target point, namely a vertex coordinate formed by the middle point position coordinates of the upper frame of the rectangular frame and a bottom coordinate formed by the middle point position coordinates of the lower frame of the rectangular frame; and the left point coordinate is formed by the middle point position coordinate of the left frame of the rectangular frame, and the right point coordinate is formed by the middle point position coordinate of the right frame of the rectangular frame. And obtaining the type of the target point according to the position relation between the rectangular frame and the midpoint coordinate.

In the second embodiment of the present invention, only the vertex coordinate connection line is used to construct the first connection line, the bottom coordinate is used to construct the second connection line, and the rest is similar to the step 140 of the first embodiment to obtain the smart box.

By implementing the embodiment of the invention, the first connecting line and the second connecting line can be obtained based on the connecting line of the target point, and the intelligent frame is formed by the area enclosed between the first connecting line and the second connecting line. Except for the situation that the target subject is completely horizontal, the intelligent frame is a rectangular frame, and as long as the target subject is slightly inclined, the intelligent frame is a closed line segment set formed by a plurality of line segments, and is not in a rectangular structure. The intelligent frame is automatically adjusted according to the character direction of the target title and the target character direction, various operations such as rotation of a shot image are not needed, incomplete target titles or invalid information obtained by the frame can be avoided, the efficiency of the frame titles is improved, and user experience is improved.

EXAMPLE III

The third embodiment improves the second embodiment, reduces the size of the intelligent frame, and ensures the accuracy of the frame question.

Determining a left point coordinate and a right point coordinate in the target point on the basis of determining a vertex coordinate and a bottom coordinate in the target point; the intelligent frame is a closed line segment set formed by sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate and the right point coordinate.

The vertex coordinate, the bottom coordinate, the left point coordinate and the right point coordinate are connected in sequence by connecting any target point with two other target points which are closest to the target point.

Referring to fig. 3, each character 210 is framed by a rectangular frame 220, so that no overlapping area exists between any rectangular frames, and the character is also located inside the corresponding rectangular frame, i.e., the black dot matrix corresponding to the character does not intersect with the rectangular frame in which the character is located. All the target points 230 are obtained through the above method, and then are connected in sequence to obtain the intelligent box 240, where the intelligent box 240 is a closed line segment set (bold part).

The intelligent frame obtained by the method can firstly reduce the range of the intelligent frame, so that the framed subject occupies a smaller storage space when being stored, secondly, the integrity of the target subject can be ensured, and the method is also suitable for the situation that the first line of the target subject is indented and the last line of the target subject is not full, and can be widely applied to the requirements of various content framing.

In the smart box 240, there may also be a line segment meeting the character, for example, the "black" character in fig. 3 meets one of the line segments, in this case, two end points of the line segment may be found, then two corresponding rectangular boxes are determined based on the two end points, the size of any one or two rectangular boxes is adjusted (generally, the size of the rectangular box is increased), that is, the line segment can be prevented from meeting the character, as shown in fig. 4, and the size of the rectangular box where the "black" character is located is adjusted.

Moreover, two or more target points may exist on a partial rectangular frame (generally located at four corners of the target title), and if the target points are connected, the connected line segments may intersect with the characters, so that the information is incomplete during the capturing process.

In this case, such target points may be specially treated.

As shown in fig. 5, a multi-point rectangular frame and a plurality of relevant targets on the multi-point rectangular frame are determined, where the relevant targets are two or more targets existing on the multi-point rectangular frame, and taking the multi-point rectangular frame 310 in fig. 5 as an example, it has a relevant target a and a relevant target B, then a connecting line between the relevant target a and the relevant target B is not directly connected to each other, but a first line segment 311 and a second line segment 312 are set, the first line segment and the second line segment are both distributed on the borders of the multi-point rectangular frame where the two adjacent relevant targets are located, and the first line segment and the second line segment exist and only have one intersection.

The first line segment and the second line segment exist and only one intersection point exists, namely the first line segment and the second line segment are sent out from the related target point A and travel along the side line of the multipoint rectangular frame 310, and the route which reaches the related target point B most recently is the connecting line between the related target point A and the related target point B.

Fig. 3 and 4 are schematic diagrams of the connection of the relevant target points of the multipoint rectangular frame by the above method. Fig. 3 and 4 show the situation that the target topic is inclined downwards, and likewise, the embodiment of the present invention is also applicable to the situation that the target topic is horizontally arranged as shown in fig. 6 and the situation that the target topic is inclined upwards as shown in fig. 7.

By implementing the embodiment of the invention, the intelligent frame can be formed by sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate and the right point coordinate, the size of the intelligent frame is reduced, the integrity of the target title can be ensured while the framed title occupies a smaller storage space when being stored, and the method is also suitable for the situation that the first line of the target title is retracted and the last line of the target title is not full, and can be widely applied to the requirements of various content framing. The intelligent frame is automatically adjusted according to the character direction of the target title and the target character direction, various operations such as rotation of a shot image are not needed, incomplete target titles or invalid information obtained by the frame can be avoided, the efficiency of the frame titles is improved, and user experience is improved.

Example four

The fourth embodiment is similar to the third embodiment, and the accuracy of the frame question is ensured while the size of the intelligent frame is reduced on the basis of the second embodiment.

Referring to fig. 8, fig. 8 is a schematic flow chart of another intelligent question framing method according to an embodiment of the present invention. The method is suitable for intelligent equipment such as learning machines, family education machines, point reading machines, tablet computers or mobile phones. The frame title is to select and extract the contents with the target title and the target destination in the image. As shown in fig. 8, the intelligent question framing method includes the following steps:

410. when a framing question instruction is received, an image containing a target question is collected.

420. And identifying the position coordinates of each character in the target title in the image.

430. Each character is given a rectangular frame, and the rectangular frames satisfy the following conditions: no overlapping area exists between the rectangular frames, each character is positioned in the corresponding rectangular frame, and the length or/and the width of any two rectangular frames are equal; acquiring the position coordinates of the middle points of four sides of each rectangular frame; determining a target point; and the distance between the target point and any other midpoint position coordinate is larger than a preset threshold value.

440. Determining vertex coordinates and bottom coordinates in the target point; the vertex coordinates are the coordinates of the middle point position of the upper frame of the rectangular frame, and the bottom coordinates are the coordinates of the middle point position of the lower frame of the rectangular frame.

450. Determining a left point coordinate and a right point coordinate in a target point; the left point coordinate is the middle point position coordinate of the left frame of the rectangular frame, and the right point coordinate is the middle point position coordinate of the right frame of the rectangular frame.

Step 410 and step 420 are similar to step 110 and step 120 in the first embodiment, step 430 and step 440 are similar to the second embodiment, and step 450 is similar to the third embodiment, which are not repeated herein.

460. Determining a target left point coordinate and a target right point coordinate; the target left point coordinate is the left point coordinate with the minimum abscissa, and the target right point coordinate is the right point coordinate with the maximum abscissa.

As shown in fig. 9, the coordinates D of the target left point existing on the rectangular frame 520 and the coordinates I of the target right point existing on the rectangular frame 530 are obtained by the coordinate system of the image in accordance with the size of the abscissa.

470. Determining a first target vertex coordinate, a first target bottom coordinate, a second target vertex coordinate and a second target bottom coordinate; the first target vertex coordinate is a vertex coordinate closest to a target left point coordinate in a target subject head line, the first target bottom coordinate is a bottom coordinate closest to the target left point coordinate in a target subject tail line, the second target vertex coordinate is a vertex coordinate closest to a target right point coordinate in the target subject head line, and the second target bottom coordinate is a bottom coordinate closest to the target right point coordinate in the target subject tail line.

As shown in fig. 9, the first target vertex coordinate C existing on the rectangular frame 510, the first target bottom coordinate E existing on the rectangular frame 520, the second target vertex coordinate H existing on the rectangular frame 530, and the second target bottom coordinate J existing on the rectangular frame 540 are obtained from the target left point coordinate D and the target right point coordinate I.

480. Obtaining a left boundary according to the target left point coordinate, the first target vertex coordinate and the first target bottom coordinate; and obtaining a right boundary according to the target right point coordinate, the second target vertex coordinate and the second target bottom coordinate.

A first intersection point and a second intersection point are formed between the extension line of the left frame where the target left point coordinate is located and the extension line of the upper frame where the first target vertex coordinate is located and the extension line of the lower frame where the first target bottom coordinate is located respectively; the left boundary comprises a connecting line between the first target vertex coordinate and the first intersection point, a connecting line between the first intersection point and the second intersection point, and a connecting line between the second intersection point and the first target bottom coordinate.

As shown in fig. 9, the first intersection point F and the second intersection point G, and the third intersection point K and the fourth intersection point L are determined. Meanwhile, the left boundary is obtained to include the line segment 511, the line segment 512, and the line segment 513, and the right boundary is obtained to include the line segment 531, the line segment 532, and the line segment 533.

490. Sequentially connecting the first target vertex coordinate, the hit vertex coordinate and the second target vertex coordinate to form an upper edge line; and sequentially connecting the first target bottom coordinate, the hit bottom coordinate and the second target bottom coordinate to form a lower sideline, wherein a closed line segment set formed by enclosing the left boundary, the upper sideline, the right boundary and the lower sideline is the intelligent frame.

As shown in fig. 9, an upper edge line 570 and a lower edge line 580 are obtained, where two ends of the upper edge line 570 are a first target vertex coordinate C and a second target vertex coordinate H, respectively; the two ends of the lower edge line 580 are the first target bottom coordinate E and the second target bottom coordinate J, respectively. Thereby, a set of closed line segments is formed.

The first intersection point, the second intersection point, the first target vertex coordinate and the first target bottom coordinate form a first quadrangle; and the third intersection point, the fourth intersection point, the second target vertex coordinate and the second target bottom coordinate form a second quadrangle. It should be noted that some interfering target points need to be excluded to obtain the hit vertex coordinates and bottom coordinates; the hit vertex coordinate and the hit bottom coordinate are not located in the first quadrangle or the second quadrangle, and the rectangle frame where the hit vertex coordinate and the hit bottom coordinate are located is not intersected with the connecting line 514 between the first target vertex coordinate and the first target bottom coordinate or the connecting line 534 between the second target vertex coordinate and the second target bottom coordinate.

For example, in FIG. 9, rectangular box 550 is located in the second quadrilateral, and

rectangular boxes

540, 560, and 530 meet with continuum 534, then the target points above them are all interference target points, not calculated within the top coordinates of the hit and the bottom coordinates of the hit. Because the bottom coordinates J of the excluded rectangular box 540 and the vertex coordinates H of the rectangular box 530 are used as the starting or ending points in making the determination of the lower or upper edge lines, excluding them as the hit vertex coordinates and hit bottom coordinates does not affect the closing of the smart box.

FIG. 10 shows the smart box selection process for the case that the target topic is tilted downward, and the embodiment of the present invention is also applicable to the case that the target topic is horizontally arranged as shown in FIG. 11 and the case that the target topic is tilted upward as shown in FIG. 12.

By implementing the embodiment of the invention, the closed line set enclosed by the left boundary, the upper boundary, the right boundary and the lower boundary is the intelligent frame, the size of the intelligent frame is reduced, the integrity of the target title can be ensured while the title taken by the frame occupies a smaller storage space when being stored, and the method is also suitable for the situation that the first line of the target title is indented and the last line of the target title is not full, and can be widely applied to the requirements of various content framing. The intelligent frame is automatically adjusted according to the character direction of the target title and the target character direction, various operations such as rotation of a shot image are not needed, incomplete target titles or invalid information obtained by the frame can be avoided, the efficiency of the frame titles is improved, and user experience is improved.

EXAMPLE five

Referring to fig. 13, fig. 13 is a schematic structural diagram of an intelligent framing device according to an embodiment of the present invention. As shown in fig. 13, the intelligent question device may include:

the acquisition unit 610 is used for acquiring an image containing a target topic when receiving a framing topic instruction;

the identifying unit 620 is used for identifying the position coordinates of each character in the target title in the image;

the scribing unit 630 is used for sequentially connecting vertex position coordinates of a first row in the target title to form a first connecting line, and sequentially connecting bottom position coordinates of a last row in the target title to form a second connecting line;

the frame selection unit 640 is configured to obtain a picture of the target content of the target title in the intelligent frame; the intelligent frame is an area enclosed by the first connecting line and the second connecting line.

As an alternative embodiment, the scribing unit 630 may include:

a first subunit 631, configured to assign each character a rectangular frame, where the rectangular frame satisfies: no overlapping area exists between the rectangular frames, and each character is positioned inside the corresponding rectangular frame;

a second subunit 632, configured to obtain coordinates of midpoint positions of four sides of each rectangular frame;

a third subunit 633 for determining a target point; the distance between the target point and any other midpoint position coordinate is larger than a preset threshold value;

a fourth subunit 634 for determining the vertex coordinates and the bottom coordinates in the target point; the vertex coordinates are the coordinates of the middle point position of the upper frame of the rectangular frame, and the bottom coordinates are the coordinates of the middle point position of the lower frame of the rectangular frame;

the fifth subunit 635 is configured to sequentially connect the vertex coordinates to form the first connection line, and sequentially connect the bottom coordinates to form the second connection line.

As an alternative embodiment, the coordinates of the left point and the coordinates of the right point in the target point are determined; the left point coordinate is a middle point position coordinate of a left frame of the rectangular frame, and the right point coordinate is a middle point position coordinate of a right frame of the rectangular frame; the intelligent frame is a closed line segment set formed by sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate and the right point coordinate.

As an optional implementation, sequentially connecting the vertex coordinate, the bottom coordinate, the left point coordinate, and the right point coordinate includes: any target point is connected to two other target points which are closest to it.

As an optional implementation manner, connecting any target point with two other target points closest to the target point further includes:

As an optional implementation, the smart box includes:

As an optional implementation manner, judging whether a line segment in the intelligent frame intersects with the position coordinate of the image where the character is located;

The intelligent frame topic device shown in fig. 13 automatically constructs an intelligent frame according to the character direction of the target topic, so that the target topic is prevented from being incomplete or invalid information is prevented from being obtained by the frame topic device, the frame topic efficiency is improved, and the user experience is improved.

EXAMPLE six

Referring to fig. 14, fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. The electronic device can be a learning machine, a family education machine, a point reading machine, a tablet computer, a mobile phone or other intelligent devices, and can also be a desktop computer, a notebook computer and the like. As shown in fig. 14, the electronic device may include:

a memory 710 storing executable program code;

a processor 720 coupled to the memory 710;

the processor 720 calls the executable program code stored in the memory 710 to execute some or all of the steps of the method of any one of the first to fourth embodiments.

The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute part or all of the steps in the method of any one of the first to fourth embodiments of the intelligent theme.

The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the method for intelligent framing questions in any one of the first embodiment to the fourth embodiment.

The embodiment of the invention also discloses an application publishing platform, wherein the application publishing platform is used for publishing the computer program product, and when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the method for intelligent framing in any one of the first embodiment to the fourth embodiment.

In various embodiments of the present invention, it should be understood that the sequence numbers of the processes do not mean the execution sequence necessarily in order, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the method according to the embodiments of the present invention.

In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.

Those skilled in the art will appreciate that some or all of the steps of the methods of the embodiments may be implemented by hardware instructions of a program, which may be stored in a computer-readable storage medium, such as Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (CD-ROM), or other disk Memory, or other Memory, or may be stored in a computer-readable storage medium, A tape memory, or any other medium readable by a computer that can be used to carry or store data.

The method, the device, the electronic device and the storage medium for the intelligent framework disclosed by the embodiment of the invention are introduced in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A method for intelligently framing questions, comprising:

2. The method of claim 1, wherein sequentially connecting the vertex position coordinates of the first row in the target topic to form a first connection line and sequentially connecting the bottom position coordinates of the last row in the target topic to form a second connection line comprises:

3. The method of claim 2, wherein the smart box comprises:

4. The method of claim 3, wherein connecting the vertex, bottom, left, and right coordinates in sequence comprises:

5. The method of claim 4, wherein connecting any target point to two other target points that are closest in distance further comprises:

6. The method of claim 2, wherein the smart box comprises:

7. The method according to any one of claims 3-6, further comprising:

8. An intelligence frame topic device, its characterized in that, it includes:

9. An electronic device, comprising: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory for executing a method of intelligent framing of any of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to perform the method of an intelligent framework of any of claims 1 to 7.