CN108133214B

CN108133214B - Information search method based on picture correction and mobile terminal

Info

Publication number: CN108133214B
Application number: CN201711422309.XA
Authority: CN
Inventors: 龙安忠
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2017-12-25
Filing date: 2017-12-25
Publication date: 2021-01-26
Anticipated expiration: 2037-12-25
Also published as: CN108133214A

Abstract

An information search method based on picture correction and a mobile terminal are provided, the method comprises the following steps: recognizing word space of adjacent characters in each line of characters in a target picture; judging whether at least one character space smaller than a first threshold exists, if so, adjusting the character spaces of all adjacent characters smaller than the first threshold to be larger than or equal to the first threshold so as to obtain a first character display layer; the first character display layer is used for displaying the characters in each row, and the word spacing between adjacent characters in the characters in each row is larger than or equal to the first threshold; acquiring a target character corresponding to any click event of a user on the first character display layer; and acquiring a target search result corresponding to the target character. By implementing the embodiment of the invention, the probability of mistaken touch caused by too tight arrangement of characters of a user can be reduced, the user can conveniently click the word to be searched, and the probability of clicking other words by misoperation is reduced.

Description

Information search method based on picture correction and mobile terminal

Technical Field

The invention relates to the technical field of internet, in particular to an information search method based on picture correction and a mobile terminal.

Background

Currently, more and more students use photo-taking problem-searching software to assist learning. For example, when a student reads a title in english, if a plurality of words with unknown paraphrases in chinese appear in a session, the student can take a picture of the session, click a word on the picture, and the question searching software can search for a translation result of the word and display the translation result. However, in practice, when words on the picture are too dense and gaps between the words are small, it is difficult for students to click on the word to be searched, and the students are liable to click on other words by misoperation.

Disclosure of Invention

The embodiment of the invention discloses an information searching method based on picture correction and a mobile terminal, which can enable a user to conveniently click a word to be searched and reduce the probability of clicking other words by misoperation.

The first aspect of the embodiments of the present invention discloses an information search method based on picture correction, where the method includes:

recognizing word space of adjacent characters in each line of characters in a target picture;

judging whether at least one character space smaller than a first threshold exists, if so, adjusting the character spaces of all adjacent characters smaller than the first threshold to be larger than or equal to the first threshold so as to obtain a first character display layer; the first character display layer is used for displaying the characters in each row, and the word spacing between adjacent characters in the characters in each row is larger than or equal to the first threshold;

acquiring a target character corresponding to any click event of a user on the first character display layer;

and acquiring a target search result corresponding to the target character.

As an optional implementation manner, in the first aspect of this embodiment of the present invention, if there is no at least one word spacing smaller than the first threshold, the method further includes:

identifying the line spacing of any two adjacent lines of characters in the lines of characters;

judging whether at least one line spacing smaller than a second threshold exists, if so, adjusting the line spacing of all adjacent two lines of characters smaller than the second threshold to be larger than or equal to the second threshold so as to obtain a second character display layer; the second character display layer is used for displaying the characters in each row, and the row spacing between any two adjacent rows of characters in the characters in each row is larger than or equal to the second threshold;

and acquiring a target character corresponding to any click event of the user on the second character display layer, and executing a target search result corresponding to the acquired target character.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, before the word pitch of adjacent characters in each line of characters in the recognition target picture, the method further includes:

performing character recognition on the target picture to obtain recognition results of all characters in the target picture;

sending the identification result to a server;

receiving a first search result fed back by the server aiming at the identification result;

and the obtaining of the target search result corresponding to the target character comprises:

and searching a target search result corresponding to the target character from the first search result.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, before performing character recognition on the target picture to obtain recognition results of all characters in the target picture, the method further includes:

detecting a photographing instruction triggered by a user, and starting a gravity sensor of the mobile terminal according to the photographing instruction;

detecting a horizontal angle of the mobile terminal relative to a horizontal position according to data acquired by the gravity sensor;

and judging whether the horizontal angle is within a preset threshold range, and if so, triggering a camera of the mobile terminal to shoot the target picture.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the searching for the target search result corresponding to the target character from the first search result, the method further includes:

acquiring the searching times of the user aiming at the target character, and judging whether the searching times is greater than a third threshold value;

if the search times are larger than the third threshold value, displaying prompt information associated with the target character, and recording the display duration of the prompt information;

and judging whether the display duration is greater than or equal to a preset fourth threshold, and if so, displaying the target search result.

A second aspect of an embodiment of the present invention discloses a mobile terminal, including:

the first identification unit is used for identifying the word spacing of adjacent characters in each line of characters in the target picture;

the first judging unit is used for judging whether at least one word space is smaller than a first threshold value;

the adjusting unit is used for adjusting the word spacing of all adjacent characters smaller than the first threshold value to be larger than or equal to the first threshold value when the first judging unit judges that at least one word spacing is smaller than the first threshold value, so as to obtain a first character display layer; the first character display layer is used for displaying the characters in each row, and the word spacing between adjacent characters in the characters in each row is larger than or equal to the first threshold;

the acquisition unit is used for acquiring a target character corresponding to any click event of a user on the first character display layer; and acquiring a target search result corresponding to the target character.

As an alternative implementation, in the second aspect of the embodiment of the present invention:

the first identifying unit is further configured to identify a line spacing between any two adjacent lines of characters in the lines of characters when the first judging unit judges that at least one word spacing is smaller than the first threshold value;

and, the mobile terminal further comprises:

a second judging unit, configured to judge whether at least one of the line spacings is smaller than a second threshold;

the adjusting unit is further configured to adjust, when the second determining unit determines that at least one line spacing is smaller than the second threshold, the line spacing between two adjacent lines of characters smaller than the second threshold to be greater than or equal to the second threshold, so as to obtain a second character display layer; the second character display layer is used for displaying the characters in each row, and the row spacing between any two adjacent rows of characters in the characters in each row is larger than or equal to the second threshold;

the obtaining unit is further configured to obtain a target character corresponding to any click event of the user on the second character display layer.

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

the second identification unit is used for carrying out character identification on the target picture to obtain identification results of all characters in the target picture;

the communication unit is used for sending the identification result to a server; receiving a first search result fed back by the server aiming at the identification result;

and the mode of acquiring the target search result corresponding to the target character by the acquisition unit is specifically as follows:

the obtaining unit searches a target search result corresponding to the target character from the first search result.

the first detection unit is used for detecting a photographing instruction triggered by a user;

the starting unit is used for starting a gravity sensor of the mobile terminal according to the photographing instruction;

the second detection unit is used for detecting the horizontal angle of the mobile terminal relative to the horizontal position according to the data collected by the gravity sensor;

the third judging unit is used for judging whether the horizontal angle is in a preset threshold range or not;

and the shooting unit is used for triggering the camera of the mobile terminal to shoot the target picture when the third judging unit judges that the horizontal angle is within the preset threshold range.

the acquisition unit is further used for acquiring the search times of the user for the target character;

a fourth judging unit configured to judge whether the number of searches is greater than a third threshold;

the display unit is used for displaying prompt information associated with the target character and recording the display duration of the prompt information when the fourth judging unit judges that the search frequency is greater than the third threshold;

the fourth judging unit is further configured to judge whether the display duration is greater than or equal to the fourth threshold;

the display unit is further configured to display the target search result when the fourth determination unit determines that the display duration is greater than or equal to the fourth threshold.

A third aspect of the embodiments of the present invention discloses a mobile terminal, 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 of any one of the claims disclosed in the first aspect of the embodiments of the invention.

A fourth aspect of the present embodiments is a computer-readable storage medium storing a computer program, where the computer program causes a computer to execute any one of the methods disclosed in the first aspect of the present embodiments.

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 any one of the methods disclosed in the first aspect of the embodiments of the present invention.

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

the mobile terminal judges whether the characters in the target picture are too dense or not by identifying the character spacing in the target picture, if the character spacing is smaller than a first threshold value, the characters are considered to be too dense, and therefore the character spacing smaller than the first threshold value in the target picture is adjusted to be larger than or equal to the first threshold value, so that a first character display layer is obtained.

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 flowchart of an information search method based on picture correction according to an embodiment of the present invention;

FIG. 2 is a schematic flowchart of another information search method based on picture correction according to an embodiment of the present disclosure;

FIG. 3 is a schematic flowchart of another information search method based on picture correction according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a mobile terminal disclosed in the embodiment of the present invention;

fig. 5 is a schematic structural diagram of another mobile terminal disclosed in the embodiment of the present invention;

fig. 6 is a schematic structural diagram of another mobile terminal disclosed in the embodiment of the present invention;

fig. 7 is a schematic structural diagram of another mobile terminal disclosed in the embodiment of the present invention.

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 is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses an information searching method based on picture correction and a mobile terminal, which can enable a user to conveniently click a word to be searched and reduce the probability of clicking other words by misoperation. The following are detailed below.

Example one

Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an information search method based on picture correction according to an embodiment of the present invention. The information search method based on picture correction described in fig. 1 is applicable to mobile devices such as mobile phones and tablet computers, and the embodiment of the present invention is not limited thereto. The operating system of the mobile device may include, but is not limited to, an Android operating system, an IOS operating system, a Symbian operating system, a blackberry operating system, a Windows Phone8 operating system, and the like. As shown in fig. 1, the information search method based on picture correction may include the steps of:

101. and the mobile terminal identifies the word space of adjacent characters in each line of characters in the target picture.

In the embodiment of the present invention, the mobile device may recognize the characters in the target picture as computer-readable characters through an Optical Character recognition technology (OCR). Before character recognition is carried out by using an OCR technology, a target picture needs to be preprocessed, and the target picture is divided into a plurality of individual characters. The pre-processing process may include: gray processing, binarization, denoising, rotation, horizontal cutting and vertical cutting. One way to implement vertical cutting is to project any line of characters obtained after horizontal cutting of a target picture onto an x-axis to obtain a histogram of the line of characters on the x-axis, and in the histogram, each valley part can be regarded as a gap between adjacent characters, so that the line of characters is segmented from each valley part, the line of characters can be cut into single independent characters, and meanwhile, the word space between adjacent characters in the line of characters can be identified by analyzing the valley parts. The mobile terminal can identify the word space of all adjacent characters in the target picture by analyzing a histogram obtained by projecting each line of characters obtained after horizontal cutting on an x axis.

In the process of analyzing the trough part of the histogram, the mobile terminal may filter the trough data according to the language type of the character. For example, for a square font with a fixed size of a single character, such as chinese, japanese, korean, etc., any valley in the histogram can be regarded as a word space between adjacent characters; for a font in which a single word is composed of letters, such as english, any valley in the histogram may be a gap between two adjacent letters, or a gap between two adjacent words, and in general, the gap between two adjacent letters is much smaller than the gap between two adjacent words. Therefore, in the embodiment of the present invention, the mobile terminal determines, for any valley in the histogram projected on the x-axis, whether the number of coordinate units occupied by the valley is greater than a preset threshold, and if so, the gap represented by the valley is considered to be a gap between two adjacent words, and the number of coordinate units occupied by the valley is taken as the word space of the adjacent character.

102. The mobile terminal judges whether at least one word space is smaller than a first threshold value, if so, step 103 is executed, and if not, the process is ended.

103. The mobile terminal adjusts the word spacing of all adjacent characters smaller than the first threshold value to be larger than or equal to the first threshold value so as to obtain a first character display layer.

In the embodiment of the present invention, the first character display layer is used for displaying each line of characters, and a word pitch between adjacent characters in each line of characters displayed on the first character display layer is greater than or equal to a first threshold. The first character display layer may be a layer regenerated by the mobile terminal, and the layer may be superimposed on the target picture and output to the display screen, or may be output to the display screen separately. After the mobile terminal recognizes the characters in the target picture through the OCR technology, the arrangement order of the characters can be obtained, and therefore, the mobile terminal can generate the first character display layer according to the arrangement order of the characters and the preset character interval (the preset character interval is greater than or equal to the first threshold).

104. The mobile terminal obtains a target character corresponding to any click event of a user on the first character display layer, and obtains a target search result corresponding to the target character.

As an optional implementation manner, in the embodiment of the present invention, a manner of acquiring, by the mobile terminal, the target character corresponding to any click event of the user on the first character display layer may be:

when the mobile terminal generates the first character display layer, recording the position of each character in the first character display layer, dividing the first character display layer into a plurality of character areas according to the position of each character, wherein each character area corresponds to one character;

the method comprises the steps that after a mobile terminal detects any click event of a user on a first character display layer, the click position of the click event is obtained;

and the mobile terminal searches a character area where the click position is located, and determines the character corresponding to the character area as a target character corresponding to the click event.

As another optional implementation manner, the manner in which the mobile terminal acquires the target character corresponding to any click event of the user on the first character display layer may further be:

the mobile terminal acquires a click position corresponding to any click event of a user on a first character display layer;

the mobile terminal takes the click position as a center, and sub-images with the length as a preset length and the width as a preset width are intercepted from the first character display layer;

and the mobile terminal performs character recognition on the sub-image and determines a recognition result as a target character corresponding to the click event.

In the above embodiment, the number of characters in the target character corresponding to any click event may be multiple. As can be seen, by implementing the above embodiment, for a character string or a phrase (such as a commodity name with a uniform naming format) that includes a plurality of characters and has a certain length, all the characters in the character string or the phrase can be obtained by one click, thereby reducing the number of operation steps.

In addition, in the embodiment of the present invention, the target search result may be a translation result corresponding to the target character, including but not limited to information such as a part of speech, a paraphrase, and an example sentence application of the target character. It should be noted that the target search result may not be limited to the translation result corresponding to the target character, and depends on the current application mode of the mobile terminal. For example, if the current mobile terminal is in a web page search mode, the target search result may be web page information captured on the internet by the mobile terminal using a target character as a keyword; if the current mobile terminal is in the warehouse management mode, the target search result may be commodity information such as a rack number, a production date, and the like of a commodity with a target character as a commodity name in a warehouse.

It can be seen that, in the method described in fig. 1, when recognizing that the word pitch is smaller than the first threshold, the mobile terminal may automatically generate the first character display layer whose word pitch is greater than or equal to the first threshold, so that when a user performs a click operation on the first character display layer, the probability of a false operation due to too dense characters is reduced, the user may click a target character that needs to be searched conveniently, and the probability of another character being clicked by the false operation is reduced.

Example two

Referring to fig. 2, fig. 2 is a schematic flowchart illustrating another information search method based on picture correction according to an embodiment of the present invention. As shown in fig. 2, the information search method based on picture correction may include the steps of:

201. and the mobile terminal performs character recognition on the target picture to obtain recognition results of all characters in the target picture.

In the embodiment of the present invention, the mobile terminal may perform character recognition on the target picture by using an OCR technology, may also perform character recognition on the target picture by using a deep learning technology, or perform character recognition on the target picture by using a mode of integrating OCR and deep learning, which is not limited in the embodiment of the present invention.

202. The mobile terminal sends the identification result to the server and receives a first search result fed back by the server aiming at the identification result.

In the embodiment of the invention, after the mobile terminal sends the identification result to the server, the server judges whether the character exists in the database or not aiming at each character in the identification result, if so, the information corresponding to the character is searched and added into the first search result. And the first search result is a set formed by information corresponding to each character in the identification result. If the server determines that the character cannot exist in the database, the character can be corrected by the server using the language model, for example, the "good" in the "good graph" can be corrected to "like" by the language model. And after the error correction is finished, the server searches the information corresponding to the character again.

203. And the mobile terminal identifies the word space of adjacent characters in each line of characters in the target picture.

204. The mobile terminal judges whether at least one word space smaller than a first threshold exists, if so, the steps 205 to 206 are executed, and if not, the steps 207 to 208 are executed.

205. The mobile terminal adjusts the word spacing of all adjacent characters smaller than the first threshold value to be larger than or equal to the first threshold value so as to obtain a first character display layer.

206. The mobile terminal obtains a target character corresponding to any click event of the user on the first character display layer, and directly executes step 211.

207. And the mobile terminal identifies the line spacing of any two adjacent lines of characters in each line of characters of the target picture.

In the embodiment of the present invention, if the word pitch of adjacent characters already meets the requirement that is greater than or equal to the first threshold, it may be further determined whether the line pitch of two adjacent lines of characters meets the requirement that is greater than or equal to the second threshold. Due to the shooting distance, the character font, the paragraph format and other reasons, the gaps between the character lines in the target picture may also be too small, so that the arrangement of the character lines is too dense, and the user may also click other characters by mistake.

The mobile terminal can horizontally cut the target picture before performing character recognition on the target picture. One implementation of horizontal segmentation is to project the target picture on the y-axis, so as to obtain a histogram of the target picture on the y-axis. The histogram may contain a plurality of valleys, each valley representing a gap between two adjacent lines of characters, so that by analyzing the valley portions of the histogram, the line spacing of any two adjacent lines of characters can be identified.

208. The mobile terminal judges whether at least one line spacing is smaller than a second threshold value, if so, the step 209 to the step 211 are executed, and if not, the flow is ended.

209. And the mobile terminal adjusts the line spacing of all adjacent two lines of characters smaller than the second threshold value to be larger than or equal to the second threshold value so as to obtain a second character display layer.

In the embodiment of the present invention, the second character display layer is configured to display characters in rows, and a row spacing between any two adjacent rows of characters in the characters in rows displayed on the second character layer is greater than or equal to a second threshold.

210. And the mobile terminal acquires a target character corresponding to any click event of the user on the second character display layer.

211. And the mobile terminal acquires a target search result corresponding to the target character from the first search result.

In the embodiment of the invention, aiming at the target character corresponding to each click event on the first or second character display layer, the mobile terminal obtains the target search result corresponding to the target character from the first search result. After receiving the first search result sent by the server, the mobile terminal may temporarily store the first search result in a storage device of the mobile terminal, so that, if there are multiple click events on the first or second character display layer, for a target character corresponding to each click event in the multiple click events, the mobile terminal may find the target search result of the target character from the first search result stored in the storage device of the mobile terminal without requesting the target search result of the target character from the server every time, thereby reducing the number of times of interaction between the mobile terminal and the server, improving the efficiency of obtaining the target search result by the mobile terminal, reducing the probability of slow search speed caused by network congestion and the like, and providing a good use experience for a user.

It can be seen that, in the method described in fig. 2, the mobile terminal may further identify the line spacing of the target picture when the word spacing of the target picture meets the preset condition, and adjust the line spacing of the target picture so that the line spacing of any two adjacent lines of characters in each line of characters displayed on the second character display layer is greater than or equal to the second threshold, so that the user may click a character to be searched more conveniently, and further reduce the probability that the user clicks other characters by mistake. In addition, in the method described in fig. 2, the mobile terminal searches for the target search result corresponding to the target character from the first search result, so that the number of times of interaction between the mobile terminal and the server can be reduced, the efficiency of obtaining the target search result by the mobile terminal is improved, the probability of slow search speed caused by network congestion and other reasons is reduced, and good use experience is provided for the user.

EXAMPLE III

Referring to fig. 3, fig. 3 is a schematic flowchart illustrating another information search method based on picture correction according to an embodiment of the present invention. As shown in fig. 3, the information search method based on picture correction may include the steps of:

301. the mobile terminal detects a photographing instruction triggered by a user and starts a gravity sensor of the mobile terminal according to the photographing instruction.

302. And the mobile terminal detects the horizontal angle of the mobile terminal relative to the horizontal position according to the data acquired by the gravity sensor.

303. The mobile terminal judges whether the horizontal angle is within a preset threshold range, if so, step 304 is executed, and if not, the mobile terminal outputs prompt information for prompting a user to adjust the mobile terminal to a horizontal state.

304. The mobile terminal triggers the camera to shoot a target picture.

In the embodiment of the invention, after the mobile terminal receives the photographing instruction, whether the mobile terminal is in a horizontal state is judged by analyzing the data acquired by the gravity sensor, and the camera is triggered to photograph the target picture when the mobile terminal is relatively horizontal, so that the horizontal degree of each character arrangement in the photographed target picture is higher. When character recognition is carried out on a target picture through an OCR technology, the higher the horizontal degree of character arrangement in the target picture is, the better the effect of horizontal cutting and vertical cutting on the target picture is, and the higher the character recognition effect is, the higher the accuracy rate is. Therefore, by implementing steps 301 to 304, the accuracy of character recognition on the target picture can be improved.

Optionally, in the embodiment of the present invention, a manner in which the mobile terminal triggers the camera to shoot the target picture may specifically be:

the method comprises the steps that the mobile terminal respectively obtains a plurality of pressure signals collected by pressure sensors arranged on frames at two sides of the mobile terminal;

the mobile terminal judges whether the number of the pressure signals of which the pressure values are greater than the pressure threshold value in the plurality of pressure signals exceeds a preset threshold value or not;

and if the number of the target pictures exceeds the preset value, the mobile terminal controls the camera to shoot the target picture.

In the embodiment, the mobile terminal controls the camera to shoot the target picture by judging the pressure applied to the two side frames, so that a user does not need to change hand motions to click a shooting key after adjusting the mobile terminal to be in a horizontal state, and the mobile terminal can be kept in a relatively stable state when the user holds the mobile terminal to shoot the picture. Meanwhile, when a user triggers the camera to shoot a target picture, certain pressure needs to be applied to the frames on the two sides of the mobile terminal, so that the stability of the mobile terminal is further improved, and the horizontal degree of character arrangement in the shot target picture can be further improved.

305. And the mobile terminal performs character recognition on the target picture to obtain recognition results of all characters in the target picture.

306. The mobile terminal sends the identification result to the server and receives a first search result fed back by the server aiming at the identification result.

307. And the mobile terminal identifies the word space of adjacent characters in each line of characters in the target picture.

In the embodiment of the present invention, the target picture may be a picture obtained by shooting by the mobile terminal, may also be a picture stored in a storage device of the mobile terminal, and may also be a screen capture picture of the mobile terminal.

In the embodiment of the present invention, steps 308 to 315 are the same as steps 204 to 211 in the second embodiment, and are not described again in the embodiment of the present invention.

Optionally, in the embodiment of the present invention, after the mobile terminal performs step 315, the following steps may also be performed.

The mobile terminal obtains the search times of the user aiming at the target character, judges whether the search times is larger than a third threshold value or not, and if so, executes the following steps:

the mobile terminal displays prompt information associated with the target character and records the display duration of the prompt information;

and the mobile terminal judges whether the display duration is greater than or equal to a preset fourth threshold, and if so, the target search result is displayed.

And if the searching times is less than or equal to the third threshold value, directly displaying the target searching result.

In one possible implementation, the user uses the mobile terminal to assist in learning english, and the target character clicked by the user may be a word that the user does not understand. The mobile terminal judges the number of searches of the user for the word, and if the number of searches of the user for the word is greater than a preset third threshold, the user can be considered to have contacted the word for multiple times, but still does not know the interpretation of the word. Therefore, the mobile terminal outputs the prompt information associated with the word to assist the user in recalling the definition of the word. And meanwhile, the mobile terminal records the display duration of the prompt message, and when the display duration of the prompt message is greater than or equal to a preset fourth threshold, the target search result is displayed so that the user can confirm whether the explanation thought during recall is correct. Therefore, by implementing the steps, the mobile terminal can reduce the dependence on reference materials when the user uses the mobile terminal for auxiliary learning, and the enthusiasm of the user for autonomous learning is improved.

Therefore, in the method described in fig. 3, the mobile terminal can enable the user to click the character to be searched more conveniently and more conveniently by adjusting the word space and the line space in the target picture, and reduce the probability of clicking other characters by misoperation. Further, in the method described in fig. 3, the camera is triggered to shoot the target picture only when the current placement state is relatively horizontal, so that the horizontal degree of character arrangement in the shot target picture can be improved, and the accuracy of character recognition on the target picture can be improved. Furthermore, in the method described in fig. 3, when the mobile terminal determines that the number of searches for the target character is greater than the third threshold, the prompt information associated with the target character is displayed first, and when the display duration of the prompt information is greater than or equal to the fourth threshold, the target search result is displayed, so that the dependency of the user on the reference material during the auxiliary learning using the mobile terminal can be reduced, and the enthusiasm of the user for autonomous learning is improved.

Example four

Referring to fig. 4, fig. 4 is a mobile terminal according to an embodiment of the present invention. As shown in fig. 4, the mobile terminal may include:

a first identifying unit 401 configured to identify a word pitch of adjacent characters in each line of characters in the target picture;

a first judging unit 402, configured to judge whether at least one word pitch among all the word pitches recognized by the first recognizing unit 401 is smaller than a first threshold;

an adjusting unit 403, configured to, when the first determining unit 402 determines that at least one inter-word distance is smaller than the first threshold, adjust the inter-word distances of all adjacent characters smaller than the first threshold to be greater than or equal to the first threshold, so as to obtain a first character display layer;

in the embodiment of the invention, the first character display layer is used for displaying characters in each row, and the word spacing between adjacent characters in the characters in each row displayed on the first character display layer is greater than or equal to a first threshold value;

in addition, when the adjusting unit 403 generates the first character display layer, it may record the position of each character in the first character display layer, and divide the first character display layer into a plurality of character areas according to the position of each character, where each character area corresponds to one character;

an obtaining unit 404, configured to obtain a target character corresponding to any click event on the first character display layer obtained by the user in the adjusting unit 403; and acquiring a target search result corresponding to the target character.

In this embodiment of the present invention, the manner for acquiring, by the acquiring unit 404, the target character corresponding to any click event on the first character display layer acquired by the user in the adjusting unit 403 may be:

the obtaining unit 404 obtains a click position of a click event after detecting any click event of the user on the first character display layer obtained by the adjusting unit 403;

the obtaining unit 404 searches for a character area where the click position is located, and determines a character corresponding to the character area as a target character corresponding to the click event; wherein, the character area is any one of a plurality of character areas divided by the adjusting unit 403 on the first character display layer;

optionally, the manner of acquiring, by the acquiring unit 404, the target character corresponding to any click event on the first character display layer acquired by the user in the adjusting unit 403 may also be:

the obtaining unit 404 obtains a click position corresponding to any click event of the user on the first character display layer obtained by the adjusting unit 403;

the obtaining unit 404 captures a sub-image with a preset length and a preset width from the first character display layer by taking the click position as a center;

the obtaining unit 404 performs character recognition on the sub-image, and determines a recognition result as a target character corresponding to the click event;

It can be seen that, with the mobile terminal shown in fig. 4, when it is recognized that the word space is smaller than the first threshold, the first character display layer with the word space larger than or equal to the first threshold may be automatically generated, so that when a user performs a click operation on the first character display layer, the probability of a misoperation caused by excessively dense characters is reduced, the user may conveniently click a target character to be searched, and the probability of clicking other characters by the misoperation is reduced.

EXAMPLE five

Referring to fig. 5, fig. 5 is a diagram of another mobile terminal according to the disclosure of the embodiment of the present invention. The mobile terminal shown in fig. 5 is optimized by the mobile terminal shown in fig. 4. Compared with the mobile terminal shown in fig. 4, in the mobile terminal shown in fig. 5:

the first identifying unit 401 is further configured to identify a line spacing between any two adjacent lines of characters in each line of characters when the first judging unit 402 judges that at least one word spacing is smaller than the first threshold;

and, the mobile terminal shown in fig. 5 may further include:

a second determining unit 405, configured to determine whether at least one line spacing in all the line spacings identified by the first identifying unit 401 is smaller than a second threshold;

an adjusting unit 403, configured to, when the second determining unit 402 determines that at least one line spacing is smaller than the second threshold, adjust the line spacing of all adjacent two lines of characters smaller than the second threshold to be greater than or equal to the second threshold, so as to obtain a second character display layer;

in the embodiment of the invention, the second character display layer is used for displaying characters in each row, and the row spacing between any two adjacent rows of characters in the characters in each row is larger than or equal to a second threshold value;

the obtaining unit 404 is further configured to obtain a target character corresponding to any click event on the second character display layer obtained by the user in the adjusting unit 403;

optionally, the mobile terminal shown in fig. 5 may further include:

the second identification unit 406 is configured to perform character identification on the target picture to obtain identification results of all characters in the target picture;

a communication unit 407, configured to send the identification result obtained by the second identification unit 406 to the server; receiving a first search result fed back by the server aiming at the identification result;

in this embodiment of the present invention, after receiving the first search result fed back by the server, the communication unit 407 may further trigger to start the first identification unit 401.

In addition, after the communication unit 407 receives the first search result fed back by the server, the manner of acquiring, by the acquiring unit 404, the target search result corresponding to the target character may specifically be:

the obtaining unit 404 finds a target search result corresponding to the target character from the first search result.

The mobile terminal shown in fig. 5 is implemented to further identify the line space of the target picture when the word space of the target picture meets the preset condition, and adjust the line space of the target picture to enable the line space of any two adjacent lines of characters in each line of characters displayed on the second character display layer to be larger than or equal to the second threshold, so that the user can click the character to be searched more conveniently, and the probability that the user clicks other characters by mistake is further reduced. In addition, the mobile terminal shown in fig. 5 searches for the target search result corresponding to the target character from the first search result, so that the number of times of interaction between the mobile terminal and the server can be reduced, the efficiency of obtaining the target search result by the mobile terminal is improved, the probability of slow search speed caused by network congestion and other reasons is reduced, and good use experience is provided for the user.

EXAMPLE six

Referring to fig. 6, fig. 6 is a diagram of another mobile terminal according to the disclosure of the embodiment of the present invention. The mobile terminal shown in fig. 6 is optimized by the mobile terminal shown in fig. 5. Compared to the mobile terminal shown in fig. 5, the mobile terminal shown in fig. 6 may further include:

a first detection unit 408, configured to detect whether a photographing instruction triggered by a user is received;

the starting unit 409 is used for starting the gravity sensor of the mobile terminal when the first detection unit 408 detects the photographing instruction;

in this embodiment of the present invention, after the starting unit 409 starts the gravity sensor of the mobile terminal, the second detecting unit 410 may also be triggered and started.

The second detecting unit 410 is configured to detect a horizontal angle of the mobile terminal relative to a horizontal position according to data collected by the gravity sensor after the starting unit 409 starts the gravity sensor of the mobile terminal;

a third judging unit 411, configured to judge whether the horizontal angle detected by the second detecting unit 410 is within a preset threshold range;

a shooting unit 412, configured to trigger a camera of the mobile terminal to shoot a target picture when the third determining unit 411 determines that the horizontal angle is within the preset threshold range;

in the embodiment of the present invention, after the shooting unit 412 triggers the camera of the mobile terminal to shoot the target picture, the second identification unit 406 may also be triggered and started.

Optionally, in the embodiment of the present invention, a manner of triggering the camera of the mobile terminal to shoot the target picture by the shooting unit 412 may specifically be:

the shooting unit 412 respectively obtains a plurality of pressure signals collected by pressure sensors arranged on the frames at the two sides of the mobile terminal;

the shooting unit 412 determines whether the number of pressure signals with pressure values larger than the pressure threshold value in the plurality of pressure signals exceeds a preset threshold value;

In the above embodiment, the shooting unit 412 controls the camera to shoot the target picture by determining the pressure applied to the two side frames of the mobile terminal, so that the user does not need to change the hand motion to click the shooting button after adjusting the mobile terminal to the horizontal state, and the mobile terminal can be kept in a relatively stable state when the user holds the mobile terminal to shoot the picture. Meanwhile, when a user triggers the camera to shoot a target picture, certain pressure needs to be applied to the frames on the two sides of the mobile terminal, so that the stability of the mobile terminal is further improved, and the horizontal degree of character arrangement in the shot target picture can be further improved.

Further optionally, in the mobile terminal shown in fig. 6:

the obtaining unit 404 is further configured to obtain the number of times of searching for the target character by the user;

the mobile terminal shown in fig. 6 may further include:

a fourth determination unit 413 configured to determine whether the number of searches acquired by the acquisition unit 404 is greater than the third threshold;

a display unit 414, configured to display prompt information associated with the target character and record a display duration of the prompt information when the fourth determining unit 405 determines that the search frequency is greater than the third threshold;

a fourth judging unit 413, further configured to judge whether a display duration of the prompting information recorded by the display unit 414 is greater than or equal to a fourth threshold;

the display unit 414 is further configured to display the target search result when the fourth determination unit 413 determines that the display duration is greater than or equal to the fourth threshold.

By implementing the mobile terminal shown in fig. 6, the user can click the character to be searched more conveniently and more conveniently by adjusting the word space and the line space in the target picture, and the probability of clicking other characters by misoperation is reduced. Further, the mobile terminal shown in fig. 6 triggers the camera to shoot the target picture only when the current placement state is relatively horizontal, so that the horizontal degree of character arrangement in the shot target picture can be improved, and the accuracy of character recognition on the target picture can be improved. Furthermore, when the mobile terminal shown in fig. 6 determines that the number of searches for the target character is greater than the third threshold, the prompt information associated with the target character is displayed first, and when the display duration of the prompt information is greater than or equal to the fourth threshold, the target search result is displayed, so that the dependency of the user on the reference material during the auxiliary learning using the mobile terminal can be reduced, and the enthusiasm of the user for autonomous learning is improved.

EXAMPLE seven

Referring to fig. 7, fig. 7 is a schematic structural diagram of another mobile terminal according to an embodiment of the disclosure. As shown in fig. 7, the mobile terminal may further include:

a memory 701 in which executable program code is stored;

a processor 702 coupled to the memory 701;

the processor 702 calls the executable program code stored in the memory 701 to execute any one of the information search methods based on picture correction in fig. 1 to 3.

It should be noted that the mobile terminal shown in fig. 7 may further include components, which are not shown, such as a power supply, an input key, a camera, a speaker, a screen, an RF circuit, a Wi-Fi module, a bluetooth module, and a sensor, which are not described in detail in this embodiment.

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 any one of the information search methods based on picture correction in figures 1-3.

An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute any one of the information search methods based on picture correction of fig. 1 to 3.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Those skilled in the art should also appreciate that the embodiments described in this specification are exemplary and alternative embodiments, and that the acts and modules illustrated are not required in order to practice the invention.

In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the execution order of the processes should be determined by their functions 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 above-described method of each embodiment of the present invention.

It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by hardware instructions of a program, and the program may be stored in a computer-readable storage medium, where the storage medium includes 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 Memory, such as a magnetic disk, or a combination thereof, A tape memory, or any other medium readable by a computer that can be used to carry or store data.

The above detailed description is provided for the information search method based on image correction and the mobile terminal, and the specific examples are applied in this document to explain the principle and implementation of the present invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the present 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. An information search method based on picture correction is characterized by comprising the following steps:

carrying out character recognition on the target picture to obtain recognition results of all characters in the target picture;

sending the identification result to a server;

receiving a first search result fed back by the server aiming at the identification result; wherein the first search result includes information corresponding to the error-corrected character when the recognition result includes a character that does not exist in the database; the character after error correction is obtained by the server after error correction is carried out on the character which does not exist in the database by utilizing a language model, and the information corresponding to the character after error correction is searched from the database;

recognizing word space of adjacent characters in each line of characters in the target picture;

2. The picture correction-based information search method according to claim 1, wherein if there is no at least one of the word intervals smaller than the first threshold, the method further comprises:

3. The information search method based on picture correction according to claim 1, wherein before the character recognition is performed on the target picture to obtain recognition results of all characters in the target picture, the method further comprises:

4. The information search method based on picture correction according to claim 1 or 3, wherein after the target search result corresponding to the target character is found from the first search result, the method further comprises:

5. A mobile terminal, comprising:

the communication unit is used for sending the identification result to a server; receiving a first search result fed back by the server aiming at the identification result; wherein the first search result includes information corresponding to the error-corrected character when the recognition result includes a character that does not exist in the database; the character after error correction is obtained by the server after error correction is carried out on the character which does not exist in the database by utilizing a language model, and the information corresponding to the character after error correction is searched from the database;

the acquisition unit is used for acquiring a target character corresponding to any click event of a user on the first character display layer; and searching a target search result corresponding to the target character from the first search result.

6. The mobile terminal of claim 5, wherein:

and, the mobile terminal further comprises:

7. The mobile terminal of claim 5, further comprising:

when the first detection unit detects the photographing instruction, starting a gravity sensor of the mobile terminal;

8. The mobile terminal according to claim 5 or 7, further comprising:

the fourth judging unit is further configured to judge whether the display duration is greater than or equal to a fourth threshold;