CN111159433B

CN111159433B - Content positioning method and electronic equipment

Info

Publication number: CN111159433B
Application number: CN201910749297.4A
Authority: CN
Inventors: 周林
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2019-08-14
Filing date: 2019-08-14
Publication date: 2023-07-25
Anticipated expiration: 2039-08-14
Also published as: CN111159433A

Abstract

The embodiment of the invention relates to the technical field of education, and discloses a content positioning method and electronic equipment, wherein the method comprises the following steps: identifying text content from the book image, and carrying out semantic analysis processing on the text content to obtain text meaning and semantic logic relation of the text content; then, based on text meaning and semantic logic relation, dividing the text content into a plurality of text groups meeting complete semantics, and associating the corresponding position information of each text group in the book image with the text groups; outputting a target consist associated with the target location when the target location is invoked; the target position is position information corresponding to any text group. By implementing the embodiment of the invention, the accuracy of content positioning can be improved.

Description

Content positioning method and electronic equipment

Technical Field

The invention relates to the technical field of education, in particular to a content positioning method and electronic equipment.

Background

Currently, electronic devices equipped with a click-to-read function are not uncommon in the market. In the click-to-read scene, when the electronic equipment shoots a book page touched (e.g. clicked) by a user finger, the content corresponding to the touch position can be broadcasted as the click-to-read content by determining the touch position of the user finger on the book page. However, in practice, it is found that the existing electronic device generally directly calls the text paragraph where the touch position is located to be used as the click-to-read content, so the accuracy of content positioning is not high.

Disclosure of Invention

The embodiment of the invention discloses a content positioning method and electronic equipment, which can improve the accuracy of content positioning.

The first aspect of the embodiment of the invention discloses a content positioning method, which comprises the following steps:

identifying text content from the book image;

carrying out semantic analysis processing on the text content to obtain text meanings and semantic logic relations of the text content;

dividing the text content into a plurality of text groups meeting complete semantics based on the text meanings and the semantic logic relations;

associating corresponding location information for each of the groupings of text in the book image with the grouping of text;

outputting a target consist associated with a target location when the target location is invoked; the target position is position information corresponding to any text grouping.

In a first aspect of the embodiment of the present invention, the performing semantic analysis processing on the text content to obtain text meaning and semantic logic relationship of the text content includes:

word segmentation processing is carried out on the text content so as to obtain a plurality of target words which are arranged in sequence from the text content;

Carrying out semantic analysis processing on the target words to obtain word senses of each target word and semantic logic relations among the target words;

the classifying the text content into a plurality of text groups meeting complete semantics based on the text meaning and the semantic logic relationship comprises:

dividing the target words into a plurality of text groups which meet complete semantics and are arranged in sequence based on word senses of the target words and semantic logic relations of the target words; any of the text groupings is a sentence or word.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the identifying text content from the book image, the method further includes:

determining a location range of the text content from the book image;

the associating the corresponding location information of each text grouping in the book image with the text grouping includes:

for each text grouping, determining position coordinates corresponding to each word included in the text grouping in the position range according to the arrangement sequence corresponding to each word included in the text grouping;

Combining the position coordinates corresponding to all words included in the text group to obtain the position information corresponding to the text group in the book image;

the location information is associated with the text groupings.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, when the target location is invoked, outputting the target group associated with the target location includes:

when the pointing direction of the indicator to the target position is detected in the shooting image matched with the book image, judging that the target position is called, and marking a target group associated with the target position on the shooting image;

judging whether the sliding operation of the indicator is detected or not;

if the sliding operation is detected, acquiring a sliding direction and a sliding distance indicated by the sliding operation;

determining a grouping merge number N based on the sliding distance; wherein the grouping combination quantity N is in direct proportion to the sliding distance, and N is a positive integer;

if the sliding direction is a preset sequence direction, outputting the target group and N text groups which are continuously arranged after the target group;

And if the sliding direction is a preset reverse order direction, outputting the target group and N text groups which are continuously arranged before the target group.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the outputting the target grouping associated with the target position, the method further includes:

when entering a review mode, outputting a practice page corresponding to the book image; the exercise page comprises an original text page and a plurality of option puzzle blocks which can be dragged, the original text page is obtained after the blank processing is carried out on an area to be filled in the book image, and the area to be filled in at least comprises a text area determined based on the target position;

detecting a sliding track input when a user drags a target puzzle piece; the target puzzle piece is any one of the plurality of option puzzle pieces;

and if the target puzzle block is matched with the target group and the end point of the sliding track is any position coordinate included in the target position, outputting the target group and learning content related to the target group.

A second aspect of an embodiment of the present invention discloses an electronic device, including:

A first recognition unit for recognizing text content from the book image;

the semantic analysis unit is used for carrying out semantic analysis processing on the text content so as to obtain text meanings and semantic logic relations of the text content;

the grouping unit is used for dividing the text content into a plurality of text groups meeting complete semantics based on the text meanings and the semantic logic relations;

an association unit, configured to associate, with each text group, corresponding position information of the text group in the book image;

a first output unit for outputting a target group associated with a target location when the target location is invoked; the target position is position information corresponding to any text grouping.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the semantic analysis unit includes:

the word segmentation subunit is used for carrying out word segmentation processing on the text content so as to obtain a plurality of target words which are arranged in sequence from the text content;

the analysis subunit is used for carrying out semantic analysis processing on the target words so as to obtain word senses of each target word and semantic logic relations among the target words;

The grouping unit is specifically configured to divide the plurality of target words into a plurality of text groups that satisfy complete semantics and are arranged in sequence based on word senses of each of the target words and semantic logic relationships of the plurality of target words; any of the text groupings is a sentence or word.

As an optional implementation manner, in the second aspect of the embodiment of the present invention, the electronic device further includes:

a position determining unit configured to determine a position range of text content from a book image after the first identifying unit identifies the text content from the book image;

the association unit includes:

the coordinate determination subunit is used for determining the position coordinate corresponding to each word included in the text grouping in the position range according to the arrangement sequence corresponding to each word included in the text grouping;

a merging subunit, configured to merge position coordinates corresponding to all words included in the text group, so as to obtain position information corresponding to the text group in the book image;

and an association subunit for associating the location information with the text groupings.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the first output unit includes:

the marking subunit is used for judging that the target position is called when the target position pointed by the indicator is detected in the shooting image matched with the book image, and marking the target group associated with the target position on the shooting image;

a judging subunit configured to judge whether or not to detect a sliding operation of the indicator;

an acquisition subunit, configured to acquire a sliding direction and a sliding distance indicated by the sliding operation when the determination subunit determines that the sliding operation is detected;

a grouping determination subunit configured to determine a grouping merge number N based on the sliding distance; wherein the grouping combination quantity N is in direct proportion to the sliding distance, and N is a positive integer;

the first output subunit is used for outputting the target group and N text groups which are continuously arranged after the target group when the sliding direction is a preset sequence direction;

and the second output subunit is used for outputting the target grouping and N text groupings which are continuously arranged before the target grouping when the sliding direction is a preset reverse order direction.

the second output unit is used for outputting exercise pages corresponding to the book images after the first output unit outputs the target group associated with the target position and when the first output unit enters a review mode; the exercise page comprises an original text page and a plurality of option puzzle blocks which can be dragged, the original text page is obtained after the blank processing is carried out on an area to be filled in the book image, and the area to be filled in at least comprises a text area determined based on the target position;

the detection unit is used for detecting a sliding track input when a user drags the target puzzle piece; the target puzzle piece is any one of the plurality of option puzzle pieces;

and the third output unit is used for outputting the target group and learning content related to the target group when the target puzzle block is matched with the target group and the end point of the sliding track is any position coordinate included in the target position.

A third aspect of an embodiment of the present invention discloses an electronic device, including:

A memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program code stored in the memory to perform a content locating method disclosed in the first aspect of the embodiment of the present invention.

A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a content locating method 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 run on a computer, causes the computer to perform part or all of the steps of any one of the methods of the first aspect.

A sixth aspect of the embodiments of the present invention discloses an application publishing platform for publishing a computer program product, wherein the computer program product, when run on a computer, causes the computer to perform part or all of the steps of any one of the methods of the first aspect.

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

in the embodiment of the invention, the text meaning and the semantic logic relation of the text content are obtained by carrying out semantic analysis processing on the text content identified from the book image, so that the text content is divided into a plurality of text groups meeting the complete semantics, the corresponding position information of the text groups in the book image is associated with the text groups, and the corresponding text groups are output when the position information is called, so that the accuracy of content positioning can be reduced to sentences or words, the accuracy of content positioning is improved, and the learning experience of a user is further improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed 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 other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a content locating method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a scenario for detecting a page of a paper book according to an embodiment of the present invention;

FIG. 3 is a flow chart of another method for content localization disclosed in an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of another electronic device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations 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 or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a content positioning method and electronic equipment, which can improve the accuracy of content positioning. The content positioning method disclosed by the embodiment of the invention is suitable for electronic equipment such as learning flat plates, learning mobile phones, learning machines, home education machines, click-to-read machines and the like used by users, and is particularly suitable for Web application, APP or special software in the electronic equipment. The following detailed description refers to the accompanying drawings.

Example 1

Referring to fig. 1, fig. 1 is a flow chart of a content positioning method according to an embodiment of the invention. As shown in fig. 1, the content locating method may include the following steps.

101. The electronic device identifies text content from the book image.

In an embodiment of the invention, the electronic device may recognize text content from the book image through OCR (Optical Character Recognition ) technology. In addition, before step 101, the electronic device may acquire a book image from a book database storing a plurality of learning resources, where the learning resources may include a plurality of publications obtained by digitizing information content such as text and pictures included in paper books such as textbooks and exercise books of each subject, and the book image is an electronic image corresponding to a certain book page in any of the publications; or, the electronic device may further perform shooting on the paper book page in the shooting range in response to a shooting instruction to obtain a book image, where the shooting instruction may be an action instruction generated when the user presses a virtual shooting key on a display interface of the electronic device, or a control instruction generated after the user has a shooting intention (such as "shooting" when the user inputs voice) through voice recognition, and is not limited in particular.

Specifically, the electronic device utilizes the photographing device to photograph the page of the paper book, and the photographing device can comprise a front camera arranged on one surface of the display screen and a rear camera arranged on one surface of the non-display screen. The electronic device may use the front camera to photograph the page of the paper book, or may use the rear camera to photograph the page of the paper book, which is not limited in detail.

Referring to fig. 2, fig. 2 is a schematic diagram of a scenario for detecting a page of a paper book according to an embodiment of the invention. In fig. 2, an electronic device is placed at a certain angle with a horizontal plane (such as a desktop), and the electronic device is provided with a photographing device and a light reflecting device, wherein the light reflecting device is used for changing a light path of the photographing device, so that the photographing device photographs a paper book page (such as a exercise book, a textbook, etc.) placed on the horizontal plane.

102. The electronic equipment performs semantic analysis processing on the text content to obtain text meanings and semantic logic relations of the text content.

In the embodiment of the invention, the electronic equipment obtains a plurality of words by word segmentation of text content; and then, analyzing the text meaning of the text content based on the word meaning and the part of speech of the word, and combining the connecting words included in the word to obtain the semantic logic relation of the text content, wherein the connecting words comprise but are not limited to parallel connecting words (such as sum, heel and equal), adapting connecting words (such as then, like, namely, etc.), turning connecting words (such as but, however, not to wait), causal connecting words (such as due to, so, etc.), and hypothesizing connecting words (such as if, provided).

103. The electronic device divides the text content into a plurality of text groupings meeting the complete semantics based on text meanings and semantic logic relationships.

In the embodiment of the present invention, the text grouping may be sentences or words, which is not limited in particular. For example, a text content is "they mean going back into the hole for a long period of time and then going back into the hole at a glance" from which the conjunctions "then" are obtained, so that there is a conjunctive relationship between the upper and lower sentences of the text content, which can be divided into two text groups "they mean going back into the hole for a long period of time" and "going back into the hole at a glance".

104. The electronic device associates with each grouping of text corresponding location information in the book image.

It can be understood that the electronic device recognizes the text content from the book image according to the designated recognition sequence, so that the position range of the text content corresponding to the book image is known, and then the position information corresponding to each text grouping in the book image can be obtained by combining the arrangement sequence and the text ratio corresponding to each text grouping in the text content. For example, a coordinate system is established in the book image, the electronic device determines that the text content corresponds to a range of positions (10, 20) to (20, 20) in the book image, and the horizontal and vertical axes of each text occupy 1. Assuming that the text content can be divided into a text group 1 containing 4 characters and a text group 2 containing 7 characters in the recognition order, the position information corresponding to the text group 1 is (10, 20) to (13, 20), and the position information corresponding to the text group 2 is (14, 20) to (20, 20).

105. When the target location is invoked, the electronic device outputs a target consist associated with the target location; the target position is position information corresponding to any text group.

Specifically, in step 105, each time the electronic device invokes the location information corresponding to any text group in the book image in response to the user click operation, the electronic device may quickly output the text group associated with the location information (i.e., the target group), and optionally may also output learning content (such as noun interpretation, teaching audio and video, etc.) related to the target group. The user click operation can be a click operation performed on a target position in the book image by directly calling the book image from the book database through a corresponding learning application on the electronic equipment by the user; alternatively, the user may perform the pointing operation by using an indicator (such as a finger or a stylus) at a target position on the paper page when the user places the paper page matching the book image in the shooting range of the electronic device, which is not limited specifically.

In addition, the manner of outputting the target group and the related learning content by the electronic device includes, but is not limited to, voice, text or a combination of voice and text.

As an alternative implementation, before the electronic device outputs the target group, it is determined whether the electronic device is connected to the headset; the electronic equipment is provided with a physical interface for accessing the wired earphone or/and a WiFi module or a Bluetooth module for accessing the wireless earphone;

if the target group is connected to the earphone, playing the target group through the accessed earphone voice;

if the earphone is not connected, acquiring the current scene (such as a study room, a classroom, a library or a user bedroom and the like) of the user according to the current positioning information and the scene image shot by the shooting device;

judging whether the current scene belongs to a specified voice playing scene (for example, the library does not belong to the specified voice playing scene, and a bedroom of a user can be the specified voice playing scene);

if the target group belongs to the voice playing scene, directly playing the target group through a loudspeaker voice; if the target group does not belong to the voice playing scene, outputting prompt information for indicating the user to replace the learning environment or wear the earphone, or outputting the target group in a text form.

Therefore, the voice playing strategy can be adaptively adjusted according to the change of the learning environment, and the good learning environment is maintained.

Therefore, by implementing the method described in fig. 1, the text meaning and the semantic logic relationship of the text content are obtained by performing semantic analysis processing on the text content identified from the book image, so that the text content is divided into a plurality of text groups meeting the complete semantics, so that the position information corresponding to the text groups in the book image is associated with the text groups, and the corresponding text groups are output when the position information is called, so that the accuracy of content positioning can be reduced to sentences or words, the accuracy of content positioning is improved, and the learning experience of a user is improved.

Example two

Referring to fig. 3, fig. 3 is a flow chart of another content locating method according to an embodiment of the invention. As shown in fig. 3, the content locating method may include the following steps.

301. The electronic device identifies text content from the book image.

302. The electronic device performs word segmentation processing on the text content to obtain a plurality of target words which are arranged in sequence from the text content.

303. The electronic equipment performs semantic analysis processing on the target words so as to obtain word senses of each target word and semantic logic relations among the target words.

304. The electronic device divides the plurality of target words into a plurality of text groups which satisfy complete semantics and are arranged in sequence based on word senses of each target word and semantic logic relations of the plurality of target words.

In the embodiment of the invention, any text is grouped into sentences or words. For example, a text content is "a small forest likes not only volleyball but also basketball", a target word obtained by word segmentation is "a small forest", "not only", "like", "volleyball", "also", "like", "basketball", "a word part of speech corresponding to" a small forest "," volleyball "and" basketball "is a noun, a word part of speech corresponding to" not only "and" also "is a pronoun, and a word part of speech corresponding to" like "is a verb. As the ' not only ' and the ' but also the ' are progressive connecting words, corpus before and after the connecting words are divided by taking the connecting words as boundaries, and two text groups of ' small forests like volleyball ' and ' basketball ' are obtained, wherein ' basketball ' is liked and ' main word ' small forests ' are omitted, and a moving guest structure is met.

It can be seen that, by implementing the steps 301 to 304, the text content is segmented, and the connective words and sentence pattern structure included in the text content are analyzed based on the segmentation result, so that the association relationship between the words in the text content can be obtained, and the text content can be further rapidly and accurately divided into a plurality of text groups.

305. The electronic device associates with each grouping of text corresponding location information in the book image.

As an alternative embodiment, after step 301, it may further include:

the electronic equipment determines the position range of the text content from the book image;

accordingly, step 305 may specifically be:

the electronic equipment determines position coordinates corresponding to each word included in the text grouping in a position range according to the arrangement sequence corresponding to each word included in the text grouping aiming at each text grouping; the electronic equipment combines the position coordinates corresponding to all words included in the text group to obtain the position information corresponding to the text group in the book image; the electronic device associates the location information with a grouping of text.

For example, in the text group "the small forest likes not only the volleyball", the position information associated with the text group is (5, 10) to (12, 10) assuming that the horizontal axis and the vertical axis of each text are 1, the position coordinates corresponding to the word "the small forest" are (5, 10) to (6, 10), the position coordinates corresponding to "not only" are (7, 10) to (8, 10), the position coordinates corresponding to "the like" are (9, 10) to (10, 10), and the position coordinates corresponding to "the volleyball" are (11, 10) to (12, 10).

306. When the electronic equipment detects that the indicator points to the target position in the shooting image matched with the book image, the electronic equipment judges that the target position is called, and marks a target group associated with the target position on the shooting image.

In the embodiment of the invention, the indicator is a finger, a writing pen, a touch pen or the like, and is not particularly limited; the target position is the position information corresponding to any text group. Before step 306, the electronic device may acquire a captured image through the capturing device, and determine whether there is a book image matching the captured image based on image information (such as a page number, a title, a book cover, page content, etc.) included in the captured image, and if so, step 306 is performed. The specific implementation of the electronic device obtaining the captured image through the capturing device may refer to the description of fig. 2 in the first embodiment, which is not described herein again.

Further, the captured image should include a book page boundary that matches the book page boundary in the book image. Therefore, when the electronic device acquires the original image shot by the shooting device, the electronic device performs image correction (such as inclination correction, equal-proportion amplification, etc.) on the original image, so that the corrected original image is used as the shot image, and the shot image and the book image have an accurate coordinate corresponding relation.

307. The electronic device determines whether to detect the sliding operation of the indicator, and if not, executes step 308; if yes, go to step 309-step 310; if not, outputting the target group.

308. The electronic device outputs the target consist.

309. The electronic device acquires a sliding direction and a sliding distance indicated by the sliding operation.

310. The electronic device determines the grouping merge number N based on the sliding distance and performs step 311 or step 312.

In the embodiment of the invention, the grouping combination quantity N (N is a positive integer) is in a direct proportion relation with the sliding distance, namely, the larger the sliding distance is, the larger the value of N is; the smaller the sliding distance, the smaller the value of N. For example, if the electronic device detects that the finger of the user slides by 1cm, the grouping combination number N is 1; if the electronic device detects that the finger of the user slides by 2cm, the grouping combination number N is 2.

311. If the sliding direction is a preset sequential direction, the electronic device outputs a target group and N text groups which are arranged after the target group in succession.

312. If the sliding direction is a preset reverse order direction, the electronic device outputs a target group and N text groups which are arranged in succession before the target group.

In the embodiment of the present invention, the preset sequence direction may be upward or rightward, and the preset reverse sequence direction may be downward or leftward, which is not particularly limited. For example, assuming a right order direction, a left reverse order direction, the currently selected text groupings are "and night fog", and the former text grouping is "aromatic and rich", and the latter text grouping is "diffuse entire village". If the electronic equipment detects that the user fingers slide rightwards to form groups and the corresponding distance is 1, outputting 'and night fog to spread the whole village'; if the electronic equipment detects that the user fingers slide leftwards to form the corresponding distance when the combined number N is 1, the electronic equipment outputs aromatic and strong and night fog. As can be seen, by implementing the steps 306 to 312, the click-to-read range can be adjusted based on the click-to-read requirement of the user, so that the interactivity of the user during the click-to-read learning is increased, and the learning experience of the user is further improved.

Optionally, if the preset sequence direction is up or right, and the preset reverse sequence direction is down or left, when the sliding direction is right/left, the electronic device outputs the target group and N text groups continuously arranged after and/or before the target group; when the sliding direction is downward and/or upward, the electronic device outputs the target grouping and the text groupings included in M text lines sequentially arranged after and/or before the target text line (i.e., the text line where the target grouping is located), where M is a positive integer, and M is in a proportional relationship with the sliding distance. Therefore, different sliding directions can also correspond to different merging modes, and the operability of the click-to-read range adjusted by a user can be improved.

Further, as an alternative embodiment, after the electronic device outputs the target group associated with the target position, the method may further include the steps of:

when the electronic equipment enters a review mode, outputting a practice page corresponding to the book image; the training page comprises an original text page and a plurality of option puzzle blocks which can be dragged, wherein the original text page is a page obtained after the blank treatment is carried out on an area to be filled in a book image, and the area to be filled in at least comprises a text area determined based on a target position; the electronic equipment detects a sliding track input when a user drags a target puzzle piece; the target puzzle piece is any one of a plurality of option puzzle pieces; if the target puzzle piece is matched with the target group and the end point of the sliding track is any position coordinate included in the target position, the electronic equipment outputs the target group and learning content related to the target group.

The plurality of option puzzle pieces may include, in addition to puzzle pieces matching with corresponding contents of the region to be filled, puzzle pieces randomly generated based on a user's history wrong records, which are not particularly limited. Therefore, the optional implementation mode can generate the blank filling test questions for the user to review according to the content read by the history points, and can increase the interest of the test question exercise in the form of the puzzle blocks, thereby being beneficial to improving the learning interest of the user.

As another alternative embodiment, the present solution may further include:

when the electronic equipment enters a recitation mode, if the current contents to be recited are text contents included in the book image, the recitation voice information of the user is received in real time;

the electronic equipment compares the recitation voice information with text contents included in the book image, and judges whether target contents with recitation errors exist or not;

if the target content exists, the electronic equipment acquires a text grouping corresponding to the target content as an error grouping, and simultaneously records user voice information acquired for the target content;

when the electronic equipment finishes recitation, the error grouping and corresponding user voice information are output for the user to perform recitation error correction. Therefore, the optional implementation mode can also locate the recitation error content of the user according to the more accurate text grouping under the recitation practice scene, so as to assist the user in dictation error correction, and improve the learning efficiency of the user.

In addition, it will be appreciated that the electronic device may also establish a connection with a user's wearable device (e.g., smart watch, smart bracelet), optionally, when entering a recitation mode, the electronic device receives recitation voice information collected by the wearable device and remotely transmitted to the electronic device, and performs the step of comparing the recitation voice information with text content included in the book image. Therefore, the user can conveniently use the wearable device to perform recitation exercises anytime and anywhere, and can obtain corresponding error correction feedback on the electronic device, so that the learning mode is more flexible.

Further, as an optional implementation manner, the scheme further includes:

if the target content with the recitation error exists, the electronic equipment also records the last text group or/and the next text group corresponding to the error group; the last text grouping corresponding to the error grouping is a text grouping arranged before the error grouping in the text content, and the next text grouping corresponding to the error grouping is a text grouping arranged after the error grouping in the text content;

the electronic device outputs the error grouping and the corresponding user voice information for the user to recite and correct, and the method specifically can include:

The electronic equipment outputs a recitation prompt message and a last text group or/and a next text group corresponding to the error group; the recitation prompt information is used for indicating a user to recite again according to the last text group or/and the next text group corresponding to the error group;

the electronic equipment detects the rereaded voice information of the user and judges whether the rereaded voice information is matched with the error grouping, if not, the electronic equipment outputs the error grouping and the corresponding user voice information for the user to recite and correct. Therefore, the method can assist the user to independently think and self-correct before directly acquiring the recitation standard answers, and is more beneficial to improving the recitation effect.

Therefore, by implementing the method described in fig. 3, through word segmentation of the text content and analyzing the connective words and sentence pattern structures contained in the text content based on the word segmentation result, the text content can be rapidly and accurately divided into a plurality of text groups based on the association relation between each word in the text content, so that the accuracy of content positioning is reduced to sentences or words, the accuracy of content positioning is improved, and the learning experience of users is improved; in addition, the click-to-read range can be adjusted based on the click-to-read requirement of the user, so that the interactivity of the user in the click-to-read learning process is improved; furthermore, the method can also generate the blank filling test questions for the user to review according to the contents read by the history points, and increase the interest of the test question exercise in the form of the puzzle blocks, thereby being beneficial to improving the learning interest of the user.

Example III

Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the invention. As shown in fig. 4, the electronic device may include a first recognition unit 401, a semantic analysis unit 402, a grouping unit 403, an association unit 404, and a first output unit 405, wherein:

the first recognition unit 401 is configured to recognize text content from a book image.

The semantic analysis unit 402 is configured to perform semantic analysis processing on the text content to obtain text meaning and semantic logic relationship of the text content.

Grouping unit 403, configured to divide the text content into a plurality of text groupings satisfying the complete semantics based on the text meaning and the semantic logic relationship.

An association unit 404 is configured to associate, with each text grouping, corresponding position information of each text grouping in the book image.

A first output unit 405 for outputting a target group associated with a target position when the target position is called; the target position is position information corresponding to any text group.

As an alternative embodiment, the electronic device further comprises:

a first judging unit for judging whether the electronic device is connected to the earphone before the first outputting unit 405 outputs the target group associated with the target position; the electronic equipment is provided with a physical interface for accessing the wired earphone or/and a WiFi module or a Bluetooth module for accessing the wireless earphone;

The playing unit is used for playing the target grouping through the accessed earphone voice when the first judging unit judges that the electronic equipment is connected to the earphone;

the first judging unit is used for judging whether the electronic equipment is connected to the earphone or not according to the current positioning information and the scene image shot by the shooting device, and acquiring a current scene (such as a study room, a classroom, a library or a user bedroom and the like) where the user is located;

a second judging unit, configured to judge whether the current scene belongs to a specified voice playing scene (for example, the library does not belong to the specified voice playing scene, and the user bedroom may be the specified voice playing scene);

the playing unit is further used for directly playing the target grouping through the loudspeaker voice when the second judging unit judges that the current scene belongs to the voice playing scene;

the first output unit is further configured to output prompt information for instructing a user to replace a learning environment or wear headphones, or output a target group in a text form when the second determination unit determines that the current scene does not belong to the voice playing scene.

Therefore, the electronic device described in fig. 4 is implemented, by performing semantic analysis processing on text content identified from a book image, text meaning and semantic logic relation of the text content are obtained, so that the text content is divided into a plurality of text groups meeting complete semantics, corresponding position information of the text groups in the book image is associated with the text groups, and corresponding text groups are output when the position information is called, so that accuracy of content positioning can be reduced to sentences or words, accuracy of content positioning is improved, and learning experience of a user is improved.

Example IV

Referring to fig. 5, fig. 5 is a schematic structural diagram of another electronic device according to an embodiment of the invention. The electronic device shown in fig. 5 is obtained by optimizing the electronic device shown in fig. 4. In the electronic device shown in fig. 5, compared with the electronic device shown in fig. 4:

semantic analysis unit 402 includes:

the word segmentation subunit 4021 is configured to perform word segmentation processing on the text content, so as to obtain a plurality of target words arranged in sequence from the text content;

the analysis subunit 4022 is configured to perform semantic analysis processing on the plurality of target terms to obtain a word meaning of each target term and a semantic logic relationship between the plurality of target terms.

A grouping unit 403, specifically configured to divide the plurality of target words into a plurality of text groups that satisfy complete semantics and are arranged in sequence based on word senses of each target word and semantic logic relationships of the plurality of target words; any text is grouped into sentences or words.

The first output unit 405 includes:

the labeling subunit 4051 is configured to determine that the target position is called when the pointing object is detected to be directed to the target position in the captured image matched with the book image, and label the target group associated with the target position on the captured image;

a judging subunit 4052 for judging whether or not to detect a sliding operation of the pointer;

an acquisition subunit 4053 configured to acquire a sliding direction and a sliding distance indicated by the sliding operation when the determination subunit 4052 determines that the sliding operation is detected;

a group determination subunit 4054 for determining a group merging number N based on the sliding distance; wherein the grouping combination quantity N is in a direct proportion relation with the sliding distance, and N is a positive integer;

a first output subunit 4055 configured to output a target group and N text groups sequentially arranged after the target group when the sliding direction is a preset sequential direction;

The second output subunit 4056 is configured to output the target group and N text groups sequentially arranged before the target group when the sliding direction is a preset reverse direction.

Further, the captured image should include a book page boundary that matches the book page boundary in the book image. Therefore, the electronic device further comprises a correction unit, and the correction unit is used for carrying out image correction (such as inclination correction, equal-proportion amplification and the like) on the original image when the original image shot by the shooting device is acquired, so that the corrected original image is taken as the shooting image, and the shooting image and the book image have accurate coordinate corresponding relation.

Alternatively, if the preset sequential direction is up or right, and the preset reverse direction is down or left, the first output subunit 4055 is specifically configured to output the target group and N text groups sequentially arranged after the target group when the sliding direction is right; and outputting the target group and the text groups included in the M text lines arranged consecutively after the target text line (i.e., the text line in which the target group is located) when the sliding direction is downward;

A second output subunit 4056, specifically configured to output the target group and N text groups sequentially arranged before the target group when the sliding direction is leftward; and outputting the target group and the text groups included in the M text lines arranged in succession before the target text line (i.e., the text line in which the target group is located) when the sliding direction is upward; wherein M is a positive integer, and M is in direct proportion to the sliding distance. Therefore, different sliding directions can also correspond to different merging modes, and the operability of the click-to-read range adjusted by a user can be improved.

As an alternative embodiment, the electronic device may further include:

a position determining unit 406 for determining a position range of the text content from the book image after the first identifying unit 401 identifies the text content from the book image;

accordingly, the association unit 404 includes:

a coordinate determining subunit 4041, configured to determine, for each text group, a position coordinate corresponding to each word included in the text group in a position range according to an arrangement order corresponding to each word included in the text group;

a merging subunit 4042, configured to merge the position coordinates corresponding to all the words included in the text group, so as to obtain position information corresponding to the text group in the book image;

An association subunit 4043 for associating the location information with the text groupings.

Further, as an optional embodiment, the electronic device further includes:

a second output unit 407 for outputting a practice page corresponding to the book image after the first output unit 405 outputs the target group associated with the target position and when entering the review mode; the training page comprises an original text page and a plurality of option puzzle blocks which can be dragged, wherein the original text page is a page obtained after the blank treatment is carried out on an area to be filled in a book image, and the area to be filled in at least comprises a text area determined based on a target position;

a detection unit 408 for detecting a sliding track input when a user drags a target piece; the target puzzle piece is any one of a plurality of option puzzle pieces;

and a third output unit 409, configured to output the target group and learning content related to the target group when the target puzzle piece matches the target group and the end point of the sliding track is any position coordinate included in the target position.

As another alternative embodiment, the electronic device may further include:

the receiving unit is used for receiving the recitation voice information of the user in real time if the current contents to be recited are text contents included in the book image when entering the recitation mode;

The comparison unit is used for comparing the recitation voice information with text content included in the book image and judging whether target content with recitation errors exists or not;

the recording unit is used for acquiring a text grouping corresponding to the target content by the electronic equipment when the target content exists, taking the text grouping as an error grouping, and simultaneously recording user voice information acquired for the target content;

and the fourth output unit is used for outputting the error grouping and corresponding user voice information for the user to recite and correct when reciting is finished.

Therefore, the optional implementation mode can also locate the recitation error content of the user according to the more accurate text grouping under the recitation practice scene, so as to assist the user in dictation error correction, and improve the learning efficiency of the user.

In addition, it can be understood that the electronic device can also be connected with a wearable device (such as a smart watch and a smart bracelet) of a user, and optionally, the receiving unit is specifically configured to receive recitation voice information collected by the wearable device and remotely transmitted to the electronic device when entering the recitation mode, and trigger the comparing unit to perform comparison between the recitation voice information and text content included in the book image. Therefore, the user can conveniently use the wearable device to perform recitation exercises anytime and anywhere, and can obtain corresponding error correction feedback on the electronic device, so that the learning mode is more flexible.

Further, as an optional embodiment, the electronic device further includes: the recording unit is also used for recording the last text grouping or/and the next text grouping corresponding to the error grouping; the last text grouping corresponding to the error grouping is a text grouping arranged before the error grouping in the text content, and the next text grouping corresponding to the error grouping is a text grouping arranged after the error grouping in the text content;

a fourth output unit including:

the third output subunit is used for outputting the recitation prompt information and the last text grouping or/and the next text grouping corresponding to the error grouping; the recitation prompt information is used for indicating a user to recite again according to the last text group or/and the next text group corresponding to the error group;

the detection subunit is used for detecting the rereaded voice information of the user and judging whether the rereaded voice information is matched with the error grouping or not;

and the fourth output subunit is used for outputting the error grouping and the corresponding user voice information for recitation correction of the user when the reread voice information is not matched with the error grouping.

Therefore, the method can assist the user to independently think and self-correct before directly acquiring the recitation standard answers, and is more beneficial to improving the recitation effect.

Therefore, by implementing the electronic device described in fig. 5, through word segmentation of the text content and analyzing the connective words and sentence pattern structures contained in the text content based on the word segmentation result, the text content can be rapidly and accurately divided into a plurality of text groups based on the association relation between each word in the text content, so that the accuracy of content positioning is reduced to sentences or words, the accuracy of content positioning is improved, and the learning experience of users is improved; in addition, the click-to-read range can be adjusted based on the click-to-read requirement of the user, so that the interactivity of the user in the click-to-read learning process is improved; furthermore, the method can also generate the blank filling test questions for the user to review according to the contents read by the history points, and increase the interest of the test question exercise in the form of the puzzle blocks, thereby being beneficial to improving the learning interest of the user.

Example five

Referring to fig. 6, fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the invention. As shown in fig. 6, the electronic device may include:

a memory 601 in which executable program codes are stored;

a processor 602 coupled to the memory 601;

wherein the processor 602 invokes executable program code stored in the memory 601 to perform a content locating method as shown in fig. 1 or 3.

The embodiment of the invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a content positioning method shown in fig. 1 or 3.

The embodiments of the present invention also disclose a computer program product, wherein the computer program product, when run on a computer, causes the computer to perform some or all of the steps of the method as in the method embodiments above.

The embodiment of the invention also discloses an application release platform which is used for releasing 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 of the method in the method embodiments.

Those of ordinary skill in the art will appreciate that all or part of the steps of the various methods of the above embodiments may be implemented by a program that instructs associated hardware, the program may be stored in a computer readable storage medium including Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (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 (Compact Disc Read-Only Memory, CD-ROM) or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium that can be used for carrying or storing data that is readable by a computer.

The foregoing describes in detail a content locating method and an electronic device disclosed in the embodiments of the present invention, and specific examples are applied to illustrate the principles and embodiments of the present invention, where the foregoing examples are only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method of content localization, the method comprising:

identifying text content from the book image;

2. The method according to claim 1, wherein said performing semantic analysis processing on said text content to obtain text meaning and semantic logic relationship of said text content comprises:

3. The method of claim 2, wherein after identifying text content from the book image, the method further comprises:

determining a location range of the text content from the book image;

the location information is associated with the text groupings.

4. A method according to claim 2 or 3, wherein outputting the target consist associated with the target location when the target location is invoked comprises:

judging whether the sliding operation of the indicator is detected or not;

5. A method according to any one of claims 1 to 3, wherein after outputting a target consist associated with the target location, the method further comprises:

6. An electronic device for content location, the electronic device comprising:

a first recognition unit for recognizing text content from the book image;

7. The electronic device of claim 6, wherein the semantic analysis unit comprises:

8. The electronic device of claim 7, wherein the electronic device further comprises:

the association unit includes:

9. The electronic device of claim 7 or 8, wherein the first output unit comprises:

10. The electronic device according to any one of claims 6 to 8, characterized in that the electronic device further comprises: