CN111026837B - Learning content searching method and family education equipment - Google Patents

Abstract

The embodiment of the present invention relates to the technical field of tutoring equipment, and discloses a learning content search method and tutoring equipment. The method includes: identifying a user's intention according to a voice input by a user; if the user's intention is literacy, determining from a target image obtained by shooting Identify the designated position in the image; identify several candidate characters near the designated position from the target image; display a list of candidate characters containing the several candidate characters on the display screen; adjust the candidate characters according to the input selection information The cursor position in the list; when the input confirmation information is detected, the candidate word currently selected by the cursor position is used as the target candidate word; the learning content related to the target candidate word is searched; the learning content is output. In the embodiment of the present invention, a certain word indicated by the user can be accurately identified, and the accuracy of searching for the learning content related to the word can be improved.

Description

A kind of learning content search method and home teaching equipment

technical field

The invention relates to the technical field of education, and in particular, to a learning content search method and a family teaching device.

Background technique

With the continuous popularization of tutoring machines, more and more users (such as students) use tutoring machines for learning. At present, the way that users use the tutoring machine to read words is generally: The tutoring machine on the market generally uses the following method: the tutoring machine recognizes the scanning area obtained by the user on the textbook through the scanning pen, and extracts from the scanning area to be searched. word, search for the learning content (such as word meaning) related to the word to be searched.

However, it is found in practice that when the font or kerning in the scanning area is small, it is difficult to accurately identify a word indicated by the user in the above manner, thereby reducing the accuracy of searching for learning content related to the word.

SUMMARY OF THE INVENTION

Embodiments of the present invention disclose a learning content search method and a family education device, which can accurately identify a word indicated by a user and improve the accuracy of learning content search related to the word.

A first aspect of the embodiments of the present invention discloses a method for searching content, the method comprising:

Identify the user intent according to the voice input by the user;

If the user intends to be literate, determining the designated position in the image from the captured target image;

Identify several candidate words near the designated position from the target image;

Displaying a candidate word list containing the several candidate words on the display screen;

Adjust the cursor position in the candidate word list according to the input selection information;

When the input confirmation information is detected, the candidate word currently selected by the cursor position is used as the target candidate word;

Search for learning content related to the target candidate word;

The learning content is output.

A second aspect of the embodiments of the present invention discloses a family education device, and the family education device includes:

a memory in which executable program code is stored;

a processor coupled to the memory;

The processor invokes the executable program code stored in the memory to execute the learning content search method disclosed in the first aspect of the embodiment of the present invention.

A third 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 the learning content search method disclosed in the first aspect of the embodiments of the present invention.

A fourth aspect of the embodiments of the present invention discloses a computer program product, which, when the computer program product runs on a computer, causes the computer to execute part or all of the steps of any one of the learning content search methods of the first aspect.

A fifth aspect of the embodiments of the present invention discloses an application publishing platform, where the application publishing platform is used for publishing a computer program product, wherein when the computer program product runs on a computer, the computer is made to execute any one of the first aspect. Some or all of the steps of a learning content search method.

Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

In the embodiment of the present invention, when the tutoring device recognizes that the user's intention is literacy according to the voice input by the user, the designated position is obtained from the captured image, and several candidate words near the designated position are searched, and the display contains the above-mentioned The candidate word list of several candidate words is displayed on the display screen, and then the cursor position in the candidate word list is adjusted according to the voice selection information input by the user. When the tutoring device detects the voice confirmation information input by the user, the current cursor position is selected. The candidate word is used as the target candidate word, and the searched learning content related to the target candidate word is pushed to the user. It can be seen that, in the embodiment of the present invention, a certain word indicated by the user can be accurately identified, and the accuracy of searching for the learning content related to the word can be improved.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

1 is a schematic flowchart of a learning content search method disclosed in an embodiment of the present invention;

2 is a schematic flowchart of another learning content search method disclosed in an embodiment of the present invention;

3 is a schematic flowchart of another learning content search method disclosed in an embodiment of the present invention;

4 is a schematic structural diagram of a family education device disclosed in an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another kind of tutoring device disclosed in an embodiment of the present invention;

6 is a schematic structural diagram of another kind of tutoring device disclosed in an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of another tutoring device disclosed in an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second", "third" and "fourth" in the description and claims of the present invention are used to distinguish different objects, rather than to describe a specific order. . The terms "comprising" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to the explicit Instead, those steps or elements listed may include other steps or elements not expressly listed or inherent to the process, method, product or apparatus.

Embodiments of the present invention disclose a learning content search method and a family education device, which can accurately identify a word indicated by a user and improve the accuracy of learning content search related to the word. A detailed description is given below in conjunction with the accompanying drawings.

Example 1

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a learning content search method disclosed in an embodiment of the present invention. As shown in FIG. 1 , the learning content search method may include the following steps.

101. The tutoring device recognizes the user's intention according to the voice input by the user.

In the embodiment of the present invention, the home teaching device may be an electronic device such as a learning tablet, a learning machine, a home teaching machine, and a point-reading machine for students to use, which is not limited in the embodiment of the present invention.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device can identify whether there are preset keywords related to the literacy intention in the speech input by the user, such as "what word", "how to write", "how to read" , "how to read" or "what does it mean", etc., if it exists, it is determined that the user's intention is literacy.

For example, after the tutoring device has entered the learning mode, the user can wake up the user intent recognition function of the tutoring device by voice. Step 101 is executed.

For another example, after the tutoring device has entered the learning mode, the user can manually wake up the user intent recognition function of the tutoring device by touching the screen. After the user intent recognition function of the tutoring device is awakened, the tutoring device can receive user input. voice, go to step 101.

For another example, after the tutoring device has entered the learning mode, the user can manually turn on the physical key switch set on the tutoring device to wake up the user intent recognition function of the tutoring device. After the user intent recognition function of the tutoring device is awakened, The tutoring device can receive the voice input by the user, and step 101 is executed.

102. When the user's intention is to read words, the tutoring device determines the designated position in the image from the captured target image.

As an optional implementation manner, in this embodiment of the present invention, the designated position may be designated in the target image by a stick-shaped object (eg, a finger, a pen). The tutoring device can first identify the contour of the stick-shaped object from the captured target image, and use the contour of the stick-shaped object as the basis for identifying the designated position. When the tutoring device determines the designated position in the image from the captured target image, the tutoring device can determine the directivity of the contour of the stick-shaped object in the target image according to the contour of the stick-shaped object in the target image, and according to the contour of the stick-shaped object in the target image The directivity of the contour determines the position pointed by the contour, and uses the position pointed by the contour as the designated position in the image in the target image.

103. The tutoring device identifies several candidate words near the designated position from the target image.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device recognizes several candidate words near the designated position from the target image, including:

The tutoring device determines from the target image a circular area with the above-mentioned designated position as the center of the circle and the length of the area occupied by the preset number of words as the radius, and recognizes several words located in the circular area as Several candidate words near the designated position above.

Or, the tutoring device recognizes several candidate words near the designated position from the target image, including:

The tutoring device determines from the target image a rectangular area with the above-mentioned designated position as the diagonal intersection and the area occupied by the preset number of words arranged as the diagonal length, and identifies the rectangular area located in the rectangular area. Several words are used as several candidate words near the designated position.

Or, the tutoring device recognizes several candidate words near the designated position from the target image, including:

The tutoring device determines from the target image that the length of the area occupied by the above specified position as the midpoint and the arrangement of the preset number of words is the length of the side of the rectangle, and the width of the area occupied by a single word is the length of the side of the rectangle. A rectangular area is identified, and several characters located in the rectangular area are identified as several candidate characters near the designated position.

104. The tutoring device displays a candidate character list including the above-mentioned several candidate characters on the display screen.

For example, the tutoring device can display the above-mentioned designated position as the center of the circle and a circular area with the length of the area occupied by the preset number of characters arranged as the radius as the candidate character list displayed on the display screen of the tutoring device.

For another example, the tutoring device can set the above-mentioned specified position as the intersection of the diagonal lines and a rectangular area whose length is the diagonal length of the area occupied by the preset number of characters when arranged as a list of candidate characters displayed on the tutoring device. on the display.

For another example, the tutoring device may place the specified position and several candidate characters near the designated position in sequence in a rectangular area as a list of candidate characters to display on the display screen of the tutoring device.

For another example, the tutoring device can sort the above-mentioned several candidate characters according to the order of the number of strokes of the candidate characters from high to bottom, and display the above-mentioned several candidate characters on the display screen of the tutoring device.

For another example, the tutoring device can sort the above-mentioned several candidate words according to the search times of the relevant learning content of the candidate words in descending order, and display the above-mentioned several candidate words after sorting on the display screen of the tutoring device. superior.

105. The tutoring device adjusts the cursor position in the candidate word list according to the input selection information.

In this embodiment of the present invention, the cursor position in the candidate word list may be statically displayed on the display screen of the home teaching device; or the cursor position in the candidate word list may be dynamically displayed on the display screen of the home teaching device.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device may select information, such as "leftward", "rightward", "upward" or "downward", through the voice input by the user, and select the information for the candidate word. The cursor position in the list moves until the user selects the target candidate word.

106. When detecting the input confirmation information, the tutoring device takes the candidate word currently selected by the cursor position as the target candidate word.

In the embodiment of the present invention, the tutoring device can detect whether there is a preset keyword related to the voice confirmation information in the voice input by the user, such as "Yes", if there is a preset keyword related to the voice confirmation information in the voice input by the user , the candidate word currently selected by the cursor is used as the target candidate word.

As an optional implementation manner, in this embodiment of the present invention, before the voice confirmation information input by the user, the tutoring device can send out selection confirmation prompt information, such as "is this word", "do you want to learn this word?" Or "Do you want to understand this word?" etc.

As an optional implementation manner, in this embodiment of the present invention, the selection confirmation prompt information sent by the tutoring device includes:

Display information prompts on the display screen of the tutoring equipment;

And/or, voice message prompts sent by tutoring equipment.

107. The tutoring device searches for learning content related to the target candidate word.

As an optional implementation manner, in this embodiment of the present invention, after the home teaching device searches for learning content related to the target candidate word, options for different learning content related to the target candidate word will appear on the display screen of the home teaching device, Users can choose the learning content according to their own needs.

108. The tutoring device outputs the above learning content.

In this embodiment of the present invention, the user can log in to the tutoring device using an account (such as a social account), and after the tutoring device outputs the above learning content, the user can use the account to communicate with others in learning, thereby improving the user's enthusiasm for learning and learning efficiency .

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also report the target candidate word and the user's identity information to the teacher's terminal corresponding to the user, so that the teacher's terminal The affiliated teacher learns which words of the user are unfamiliar or unfamiliar to the user, so that the teacher can provide targeted guidance to the user.

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also pass the target candidate word and the learning content related to the target candidate word through an intermediate server (such as a social server) It is sent to the friend account selected by the user to increase the communication between the user and his friend in learning, so as to improve the user's enthusiasm for learning. The tutoring device may provide the user with a relational user chain of the account that the user uses to log in to the tutoring appliance, so that the user can select a friend account from the relational user chain.

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also report the target candidate word to an intermediate server (such as a social server), and the intermediate server (such as a social server) ) can query the accounts of other users who have reported the target candidate word according to the target candidate word, and recommend the accounts of other users to the tutoring device, so that the user can not only make more friends, but also learn with other users The exchange of method experience, which helps to improve the enthusiasm of users to learn.

As an optional implementation manner, in this embodiment of the present invention, after the tutoring device outputs the above learning content to the user, the user can deepen the mastery of the learning content corresponding to the unknown words through games, so as to improve the user's learning positivity.

In the learning content search method shown in FIG. 1 , the description is given by taking a tutoring device as an execution subject as an example. It should be noted that, the execution subject of the learning content search method shown in FIG. 1 may also be an independent device associated with the tutoring device, which is not limited in the embodiment of the present invention.

It can be seen that, by implementing the learning content search method described in FIG. 1 , the method can accurately identify a certain word indicated by the user, and improve the accuracy of the learning content search related to the word.

Embodiment 2

Please refer to FIG. 2 , which is a schematic flowchart of another learning content search method disclosed in an embodiment of the present invention. As shown in Figure 2, the learning content search method may include the following steps:

201. The tutoring device detects whether the tutoring device currently enters the learning mode, and if so, executes step 202, and if not, ends this process.

In the embodiment of the present invention, the tutoring device may detect whether the application program of the tutoring device currently enters the learning mode, and if so, execute step 202, and if not, end the current process.

Among them, the applications of the tutoring device may include learning applications and entertainment applications. Among them, learning applications may include language applications, mathematics applications, and English applications; and entertainment applications may include music applications, video applications, game applications, and social applications. Wait.

As an optional implementation manner, the tutoring device determines whether the user intent recognition function of the tutoring device is awakened only when it detects that the application of the tutoring device currently enters the learning mode by detecting the application of the tutoring device.

202. The tutoring device determines whether the user's intent recognition function is awakened, and if so, executes steps 203 to 205, and if not, ends the current process.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device is provided with an intelligent tutoring device voice assistant, and the intelligent tutoring device voice assistant will have a corresponding name, and the name may be preset by the tutoring device The title may also be a name set by the user, which is not limited in this embodiment of the present invention.

For example, after performing step 201, the user can call the name of the voice assistant of the smart tutoring device to wake up the user intent recognition function of the tutoring device. After the user intent recognition function of the tutoring device is awakened, the steps can be executed. 203.

For another example, after step 201 is performed, the user can manually wake up the user intent recognition function of the tutoring device by touching the screen, and after the user intent recognition function of the tutoring device is woken up, step 203 can be performed.

For another example, after performing step 201, the user can manually turn on the physical key switch set on the tutoring device to wake up the user intent recognition function of the tutoring device, and after the user intent identifying function of the tutoring device is awakened, the steps can be executed. 203.

203. The tutoring device acquires the voice input by the user.

204. The tutoring device recognizes the user's intention according to the voice input by the user.

205. The tutoring device determines whether the identified user's intention is literacy, and if so, executes steps 206 to 207, and if not, ends this process.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device can identify whether there are preset keywords related to the literacy intention in the speech input by the user, such as "what word", "how to write", "how to read" , "how to read" or "what does it mean", etc., if it exists, it is determined that the user's intention is literacy, and steps 206 to 207 are executed.

206. The tutoring device recognizes the voice feature corresponding to the voice according to the voice.

207. The tutoring device determines whether a designated cartoon character image associated with the above-mentioned voice feature is pre-stored, and if so, executes steps 208 to 220, and if not, ends this process.

As an optional implementation manner, in this embodiment of the present invention, after the tutoring device detects that the user's intention is literacy, the recognized voice feature may be matched with the voice feature that is pre-stored in the tutoring device and is associated with the specified cartoon character. Matching is performed, and if the matching is successful, it is determined that the designated cartoon character image associated with the above-mentioned voice feature is pre-stored, and steps 208 to 220 are executed, and if not, the process ends.

208. The tutoring device outputs a designated cartoon character image associated with the above-mentioned voice feature.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device may output a designated cartoon character associated with the above-mentioned voice feature, and the designated cartoon character may be displayed on the tutoring device along with its classic appearance. on the screen.

And/or, the tutoring device may output the classic lines of the designated cartoon character associated with the above-mentioned voice feature, so that the designated cartoon character appears on the display screen of the tutoring device along with the classic lines.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device outputs a designated cartoon character image associated with the above-mentioned voice feature, so that the literacy learning of the entire tutoring device becomes more vivid, interesting and exciting, thereby improving the It improves the enthusiasm and learning efficiency of users.

209. The tutoring device loads the first virtual object into one palm of the output designated cartoon character image.

As an optional implementation manner, in this embodiment of the present invention, the first virtual object loaded by the tutoring device may be a classic necessary item for a designated cartoon character. For example, if the designated cartoon character is "Pleasant Goat and Big Big Wolf" The Red Wolf", the first virtual object can be displayed as "Red Wolf's Pan".

210. The tutoring device loads the second virtual object into the other palm of the outputted designated cartoon character image.

As an optional implementation manner, in this embodiment of the present invention, the second virtual object loaded by the tutoring device may be a designated cartoon character image in addition to other classic necessary items as the first virtual object. For example, if the designated cartoon character image is "The Red Wolf in "Pleasant Goat and Big Big Wolf", and "Red Wolf's Pan" has been used as the first virtual object, the second virtual object can be displayed as "the crown worn by the Red Wolf".

211. The tutoring device loads first prompt information to the first virtual object, where the first prompt information is used to prompt to select a target image from an album.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device may directly display the first prompt information on the first virtual object in text, so that the user can directly use the prompt information content on the first virtual object to choose.

Alternatively, the tutoring device may hide the first prompt information on the first virtual object in a hidden manner, and only when the user touches the first virtual object, the first prompt information will appear on the first virtual object.

Alternatively, when the user touches the first virtual object, the tutoring device may play the content of the first prompt information in a classic tone of a designated cartoon character.

212. The tutoring device loads the second prompt information to the second virtual object, where the second prompt information is used to prompt invoking the camera to capture the target image.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device may directly display the second prompt information on the second virtual object in text form, so that the user can directly use the prompt information content on the second virtual object to choose.

Alternatively, the tutoring device may hide the second prompt information on the second virtual object in a hidden manner, and only when the user touches the second virtual object, the second prompt information will appear on the second virtual object.

Alternatively, when the user touches the second virtual object, the tutoring device may play the content of the second prompt information in a classic tone of a designated cartoon character.

213. When detecting that the first virtual object is touched by the user, the tutoring device opens the album; detects at least one image selected from the opened album as the target image; or, when detecting that the second virtual object is touched by the user , the tutoring device calls the camera to perform shooting, and uses the image obtained by the camera to perform shooting as the target image.

214. The tutoring device determines the designated position in the target image from the target image.

In this embodiment of the present invention, by implementing the above steps 206 to 214, the tutoring device can determine the designated position in the target image from the captured target image when the user intends to read.

215. The tutoring device identifies several candidate words near the designated position from the target image.

216. The tutoring device displays a candidate character list including the above-mentioned several candidate characters on the display screen.

217. The tutoring device adjusts the cursor position in the candidate word list according to the input selection information.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device may select information, such as "leftward", "rightward", "upward" or "downward", through the voice input by the user, and select the information for the candidate word. The cursor position in the list moves until the user selects the target candidate word.

218. When the input confirmation information is detected, the tutoring device takes the candidate character currently selected by the cursor position as the target candidate character.

In the embodiment of the present invention, the tutoring device can detect whether there is a preset keyword related to the voice confirmation information in the voice input by the user, such as "Yes", if there is a preset keyword related to the voice confirmation information in the voice input by the user , the candidate word currently selected by the cursor is used as the target candidate word.

As an optional implementation manner, in this embodiment of the present invention, before the voice confirmation information input by the user, the tutoring device can send out selection confirmation prompt information, such as "is this word", "do you want to learn this word?" Or "Do you want to understand this word?" etc.

As an optional implementation manner, in this embodiment of the present invention, the selection confirmation prompt information sent by the tutoring device includes:

Display information prompts on the display screen of the tutoring equipment;

And/or, voice message prompts sent by tutoring equipment.

219. The tutoring device searches for learning content related to the target candidate word.

As an optional implementation manner, in this embodiment of the present invention, after the home teaching device searches for learning content related to the target candidate word, options for different learning content related to the target candidate word will appear on the display screen of the home teaching device, Users can choose the learning content according to their own needs.

220. The tutoring device outputs the above learning content.

In this embodiment of the present invention, the user can log in to the tutoring device using an account (such as a social account), and after the tutoring device outputs the above learning content, the user can use the account to communicate with others in learning, thereby improving the user's enthusiasm for learning and learning efficiency .

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also report the target candidate word and the user's identity information to the teacher's terminal corresponding to the user, so that the teacher's terminal The affiliated teacher learns which words of the user are unfamiliar or unfamiliar to the user, so that the teacher can provide targeted guidance to the user.

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also pass the target candidate word and the learning content related to the target candidate word through an intermediate server (such as a social server) It is sent to the friend account selected by the user to increase the communication between the user and his friend in learning, so as to improve the user's enthusiasm for learning. The tutoring device may provide the user with a relational user chain of the account that the user uses to log in to the tutoring appliance, so that the user can select a friend account from the relational user chain.

As an optional implementation manner, in this embodiment of the present invention, after outputting the above learning content to the user, the tutoring device may also report the target candidate word to an intermediate server (such as a social server), and the intermediate server (such as a social server) ) can query the accounts of other users who have reported the target candidate word according to the target candidate word, and recommend the accounts of other users to the tutoring device, so that the user can not only make more friends, but also learn with other users The exchange of method experience, which helps to improve the enthusiasm of users to learn.

As an optional implementation manner, in this embodiment of the present invention, after the tutoring device outputs the above learning content to the user, the user can deepen the mastery of the learning content corresponding to the unknown words through games, so as to improve the user's learning positivity.

It can be seen that, implementing another learning content search method described in FIG. 2, when the tutoring device judges that the user's intention is literacy, the tutoring device obtains the corresponding voice feature of the voice by recognizing the voice input by the user, and there is the above-mentioned voice in the tutoring device. When there is a designated cartoon character associated with the voice feature, the tutoring device will output the designated cartoon character associated with the above voice feature, and load the first virtual object and the first prompt information, as well as the second virtual object and the second prompt information. into the palm of the user, wherein the first prompt information is used to prompt the selection of the target image from the album, and the second prompt information is used to prompt to call the camera to shoot the target image. When detecting that the first virtual object is touched by the user, the tutoring device opens the album; detects at least one image selected from the opened album as the target image; or, when detecting that the second virtual object is touched by the user, The tutoring device calls the camera to perform shooting, and uses the image obtained by the camera to perform the shooting as the target image. This process can not only output the specified cartoon character image on the home teaching device, make the literacy learning process of the home teaching device more vivid, interesting and exciting, thereby improving the user's enthusiasm for learning and learning efficiency, but also can accurately identify the user's instruction. to improve the search accuracy of learning content related to the word.

Embodiment 3

Please refer to FIG. 3 , which is a schematic flowchart of another learning content search method disclosed in an embodiment of the present invention. As shown in Figure 3, the learning content search method may include the following steps:

301. The tutoring device acquires the voice input by the user.

Correspondingly, the tutoring device may perform step 301 only after the tutoring device has entered the learning mode and the user intention recognition function of the tutoring device is awakened.

302. The tutoring device recognizes the user's intention according to the voice input by the user.

303. The tutoring device determines whether the identified user intention is literacy, and if so, executes steps 304 to 305, and if not, ends the current process.

As an optional implementation manner, in this embodiment of the present invention, the tutoring device can identify whether there are preset keywords related to the literacy intention in the speech input by the user, such as "what word", "how to write", "how to read" , "how to pronounce" or "what does it mean", etc., if it exists, it is determined that the user's intention is literacy, and steps 304 to 305 are executed.

304. The tutoring device recognizes the voice feature corresponding to the voice according to the voice.

305. The tutoring device determines whether a designated cartoon character image associated with the above-mentioned voice feature is pre-stored, and if so, executes steps 306 to 321, and if not, ends this process.

306. The tutoring device acquires the voice feature of the specified cartoon character whose image matches the specified cartoon character.

As an optional implementation manner, in this embodiment of the present invention, the voice features of the designated cartoon characters that are acquired by the tutoring device and match the above-mentioned designated cartoon characters include:

As an optional implementation manner, the tutoring device may acquire the voice features of the designated cartoon characters that match the designated cartoon characters through the cartoon classic lines uttered by the designated cartoon characters.

As another optional implementation manner, the tutoring device may acquire the voice features of the designated cartoon characters that match the designated cartoon characters through the cartoon classic lines uttered by the designated cartoon characters.

307. The tutoring device outputs a designated cartoon character image associated with the above-mentioned voice feature.

308. The tutoring device loads the first virtual object into one palm of the outputted designated cartoon character image.

309. The tutoring device loads the second virtual object into the other palm of the outputted designated cartoon character image.

310. The tutoring device loads the first prompt information to the first virtual object, where the first prompt information is used to prompt the selection of the target image from the album.

311. The tutoring device uses the cartoon tone corresponding to the voice feature of the specified cartoon character to play the first prompt message.

As an optional implementation manner, in this embodiment of the present invention, when the user touches the first virtual object, the tutoring device may play the first prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character.

Alternatively, the tutoring device may play the first prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character when the first prompt information is loaded into the first virtual object.

Among them, by using the cartoon tone corresponding to the voice characteristics of the designated cartoon characters to play the first prompt information, the tutoring device can make the literacy learning process of the tutoring device more vivid, interesting and exciting, thereby improving the user's enthusiasm for learning and learning efficiency.

312. The tutoring device loads the second prompt information to the second virtual object, where the second prompt information is used to prompt invoking the camera to capture the target image.

313. The tutoring device uses the cartoon intonation corresponding to the voice feature of the specified cartoon character to play the second prompt information.

As an optional implementation manner, in the embodiment of the present invention, when the user touches the second virtual object, the tutoring device may play the second prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character.

Alternatively, the tutoring device may play the second prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character when the second prompt information is loaded into the second virtual object.

Among them, by using the cartoon tone corresponding to the voice feature of the designated cartoon character to play the second prompt information, the tutoring device can make the literacy learning process of the tutoring device more vivid, interesting and exciting, thereby improving the user's learning enthusiasm and learning efficiency.

314. When detecting that the first virtual object is touched by the user, the tutoring device opens the album; detects at least one image selected from the opened album as the target image; or, when detecting that the second virtual object is touched by the user , the tutoring device calls the camera to perform shooting, and uses the image obtained by the camera to perform shooting as the target image.

315. The tutoring device determines the designated position in the target image from the target image.

316. The tutoring device identifies several candidate characters near the designated position from the target image.

317. The tutoring device displays a candidate character list including the above-mentioned several candidate characters on the display screen.

318. The tutoring device adjusts the cursor position in the candidate word list according to the input selection information.

319. When the input confirmation information is detected, the tutoring device takes the candidate character currently selected by the cursor position as the target candidate character.

320. The tutoring device searches for learning content related to the target candidate word.

As an optional implementation manner, the learning content related to the target candidate word may include:

Pinyin, radicals, strokes and meaning explanation of the target candidate word;

and/or, synonyms, antonyms, synonyms, example sentences and usages of the target candidate word;

And/or, the English translation, example sentences and usage corresponding to the target candidate word;

and/or, exercises corresponding to the target candidate words.

321. The tutoring device outputs the above learning content.

As an optional implementation manner, in the above step 301, the tutoring device can obtain the voice input by the user through the wired headset, that is, the user can input voice to the tutoring device through the microphone configured with the wired headset when wearing the wired headset.

Correspondingly, in the above step 321, the tutoring device may output the audio signal corresponding to the above learning content through the wired earphone.

Furthermore, in the process of outputting the audio signal corresponding to the above-mentioned learning content through the wired earphone, the tutoring device can monitor whether the earphone line of the wired earphone generates a vibration signal through the vibration sensor set on the earphone line of the wired earphone. Whether the intensity of the ear vibration signal is greater than the preset value, if it is greater than the preset value, the audio signal played by the wired earphone is processed.

For example, the processing of the audio signal played by the wired earphone by the tutoring device may include:

Calculate the ratio of the intensity of the vibration signal to the intensity of the audio signal played by the wired earphone, and amplify the audio signal according to the ratio.

For another example, the processing of the audio signal played by the wired headset by the tutoring device may include:

Collect audio signals played by wired headphones and echo signals generated by vibration signals in the user's ear canal;

Calculate impulse response from audio signal, vibration signal and echo signal;

Determine whether the number of impulse responses in a preset time period (for example, within 10 seconds) is greater than the preset value (for example, the preset value is 3), if it is greater, then calculate the time difference between every two adjacent impulse responses ; judge whether the time difference between two adjacent impulse responses is the same, for example, whether they are both 1 second), if so, it means that the vibration signal and the audio signal are matched in phase, and the user may be hitting the beat or following the If the audio signal moves together, there is no need to amplify the audio signal at this time, just continue to play the audio signal; If there is noise in the signal, a reverse noise signal with the opposite phase and the same intensity as the vibration signal is added to the audio signal to eliminate noise.

As an optional implementation manner, the impulse response is calculated according to the audio signal, the vibration signal and the echo signal, including:

Calculate the impulse response from the audio signal, vibration signal, echo signal, and the following formula:

w(t)=(r(t)-e(t))/(s(t)+z(t));

Among them, w(t) is the impulse response, r(t) is the echo signal, s(t) is the audio signal, z(t) is the vibration signal; e(t) is the noise parameter, including environmental noise and circuit noise. Noise is the noise generated during the recording process when no audio signal is played; circuit noise is related to the inherent properties of headphones.

In this embodiment of the present invention, when a user wears a wired earphone to listen to the audio signal played by the tutoring device, there is usually a "stethoscope effect", that is, the vibration generated when the earphone cable of the wired earphone shakes and/or rubs will directly pass through the earphone cable. It is transmitted into the user's ear canal, resulting in a very unpleasant sound for the user. Therefore, implementing the above manner can reduce the influence of the "stethoscope effect" on the audio signal when the user wears wired earphones to listen to the audio signal played by the tutoring device, and improves the user's experience when wearing the wired earphone to listen to the audio signal played by the tutoring device.

Visible, implement another kind of learning content search method described in Figure 3, when there is a pre-stored designated cartoon character image associated with the above-mentioned voice feature in the tutoring equipment, the tutoring equipment will obtain the matching of the designated cartoon character image. Specify the voice characteristics of cartoon characters, and after the home teaching device loads the prompt information into the virtual object, the home teaching device will play the prompt information in the cartoon tone corresponding to the voice characteristics of the specified cartoon characters, and this process can not only effectively prevent the home teaching device from obtaining errors It makes the literacy learning process of the tutoring equipment more vivid, interesting and exciting, so as to improve the user's enthusiasm and learning efficiency, and can accurately identify a word indicated by the user. , to improve the accuracy of learning content searches related to the word.

Embodiment 4

Please refer to FIG. 4 , which is a schematic structural diagram of a family education device disclosed in an embodiment of the present invention. As shown in FIG. 1 , the tutoring device 400 may include a first identification unit 401 , a first determination unit 402 , a second identification unit 403 , a display unit 404 , an adjustment unit 405 , a second determination unit 406 , a search unit 407 , and an output unit 408, where:

The first recognition unit 401 is configured to recognize the user's intention according to the voice input by the user.

The first determining unit 402 is configured to determine the designated position in the image from the captured target image when the user intends to read.

The second identifying unit 403 is configured to identify several candidate words near the designated position from the target image.

The display unit 404 is configured to display a candidate word list including several candidate words on the display screen.

The adjustment unit 405 is configured to adjust the cursor position in the candidate word list according to the input selection information.

The second determining unit 406 is configured to use the candidate word currently selected by the cursor position as the target candidate word when the input confirmation information is detected.

The search unit 407 is configured to search for learning content related to the target candidate word.

The output unit 408 is configured to output the above learning content.

It can be seen that, by implementing the tutoring device described in FIG. 4 , the device can accurately identify a certain word indicated by the user, and improve the accuracy of searching for the learning content related to the word.

Embodiment 5

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of another tutoring device disclosed in an embodiment of the present invention. The home teaching device shown in FIG. 5 is obtained by optimizing the home teaching device shown in FIG. 4 . Compared with the tutoring device shown in FIG. 4 , the tutoring device illustrated in FIG. 5 may further include:

The detection unit 409 is configured to detect whether the tutoring device currently enters the learning mode.

The first judging unit 410 is configured to judge whether the user intention recognition function is awakened.

The first obtaining unit 411 is configured to obtain the voice input by the user.

Correspondingly, the tutoring device can recognize the voice acquired by the first acquiring unit 411 through the first recognition unit 401 after the tutoring device has entered the learning mode and the user intention recognition function of the tutoring device is awakened, thereby recognizing the user's intent.

The second judging unit 412 is configured to judge whether the identified user intent is literacy.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the tutoring device can use the second judging unit 412 to identify whether there is a preset keyword related to the literacy intention in the voice input by the user, such as “what word ", "how to write", "how to read", "how to read" or "what does it mean", etc., if it exists, it is determined that the user intends to be literate.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the first determining unit 402 includes:

The first recognition subunit 4021 is used for recognizing the speech feature corresponding to the speech according to the speech.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the tutoring device recognizes the voice feature corresponding to the above-mentioned voice according to the above-mentioned voice through the first recognition subunit 4021, including:

The way the user calls the cartoon character's name;

and/or, classic lines related to cartoon characters uttered by users;

and/or, mood words related to cartoon characters uttered by users;

And/or, the tone of voice spoken by the user in relation to the cartoon character.

The judgment subunit 4022 is used for judging whether a designated cartoon character image associated with the voice feature is pre-stored.

The output subunit 4023 is configured to output the specified cartoon character when the judgment subunit judges that the specified cartoon character associated with the voice feature is pre-stored.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the tutoring device can output a designated cartoon character image associated with the above-mentioned voice feature through the output subunit 4023, and the designated cartoon character image is accompanied by its classic The appearance method of the home teaching device is displayed on the display screen of the tutoring device, so that the above-mentioned designated cartoon character image appears on the display screen of the tutoring device along with its classic appearance mode.

And/or, the tutoring device can output the classic lines of the designated cartoon character associated with the above-mentioned voice feature through the output subunit 4023, so that the designated cartoon character appears on the display screen of the tutoring device along with its classic lines.

And/or, the tutoring device can output the classic intonation of the designated cartoon character associated with the above-mentioned voice feature through the output subunit 4023, so that the designated cartoon character appears on the display screen of the tutoring device along with its classic lines.

And/or, the tutoring device can output the classical modal particles of the designated cartoon character associated with the above-mentioned voice feature through the output subunit 4023, so that the above-mentioned designated cartoon character appears on the display screen of the tutoring device along with its classic lines.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the tutoring device outputs the specified cartoon characters associated with the above-mentioned voice features through the output subunit 4023, so that the literacy learning of the entire tutoring device becomes more efficient. Vivid, interesting and exciting, thus improving the enthusiasm and efficiency of user learning.

The first loading subunit 4024 is configured to load the first virtual object into one palm of the output designated cartoon character, and load the second virtual object into the other palm of the output designated cartoon character.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the first virtual object and the second virtual object loaded by the tutoring device may be classic necessary items for specifying cartoon characters, for example, specifying cartoon characters If it is "Red Wolf in "Pleasant Goat and Big Big Wolf", the first virtual object can be displayed as "Red Wolf's pan", and the second virtual object can be displayed as "Red Wolf's crown".

Alternatively, the first virtual object loaded by the tutoring device may be an album pattern mark, and the second virtual object may be a camera pattern mark. The album and camera pattern mark may be directly used as prompt information, and the prompt information is the virtual object information that the user chooses to touch. , so that the user can make a choice.

The second loading subunit 4025 is used to load the first prompt information to the first virtual object, the first prompt information is used to prompt the selection of the target image from the album; the second prompt information is loaded to the second virtual object, and the second prompt information The information is used to prompt the camera to be called to capture the target image.

As an optional implementation, in the tutoring device shown in FIG. 5 , the tutoring device can directly display the prompt information on the virtual object in the form of text, so that the user can directly pass the prompt information on the virtual object. content to select.

And/or, the tutoring device can hide the prompt information on the virtual object in a hidden manner, and the prompt information will appear on the virtual object only when the user touches the virtual object.

And/or, when the user touches the virtual object, the tutoring device can play the content of the prompt information in a classic tone of a designated cartoon character.

The first determination subunit 4026 is used to open the album when it is detected that the first virtual object is touched by the user, and to detect at least one image selected from the opened album as the target image; When the second virtual object is touched by the user, the camera is called to perform shooting, and the image obtained by the camera performing shooting is used as the target image.

The second determination subunit 4027 is configured to determine the designated position in the target image from the target image.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , the second identification unit 403 includes:

The third determination subunit 4031 is used to determine, from the target image, a circular area with the specified position as the center of the circle and the length of the area occupied by the preset number of words arranged as the radius; Determine a rectangular area with the diagonal cross point at the specified position and the area occupied by the predetermined number of words arranged as the diagonal length.

The second identification subunit 4032 is used to identify several words located in the circular area as several candidate words near the designated position; or, used to identify several words located in the rectangular area as designated Several candidate words near the location.

As an optional embodiment, in the tutoring device shown in FIG. 5 , the user can log in to the tutoring device with an account (such as a social account), and after the tutoring device outputs the above learning content, the user can communicate with others through the account. Carry out learning exchanges, thereby improving users' enthusiasm for learning and learning efficiency.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , after outputting the above learning content to the user, the tutoring device can also report the target candidate word and the user's identity information to the teacher terminal corresponding to the user , so that the teacher to which the teacher terminal belongs can learn which words of the user are unfamiliar or unfamiliar to the user, so that the teacher can provide targeted guidance to the user.

As an optional implementation manner, in the tutoring device shown in FIG. 5 , after outputting the above learning content to the user, the tutoring device can also pass the target candidate word and the learning content related to the target candidate word through an intermediate server ( Such as a social server) sent to the user's selected friend account, in order to increase the communication between the user and the friend in learning, so as to improve the user's enthusiasm for learning. The tutoring device may provide the user with a relational user chain of the account that the user uses to log in to the tutoring appliance, so that the user can select a friend account from the relational user chain.

As an optional implementation, in the tutoring device shown in FIG. 5 , after outputting the above learning content to the user, the tutoring device can also report the target candidate word to an intermediate server (such as a social server), and the intermediate server can (such as a social server) can query the accounts of other users who have reported the target candidate word according to the target candidate word, and recommend the accounts of other users to the tutoring device, so that the user can not only meet more friends, but also communicate with Other users exchange learning methods and experiences, which helps to improve users' enthusiasm for learning.

As an optional embodiment, in the tutoring device shown in FIG. 5 , after the tutoring device outputs the above-mentioned learning content to the user, the user can deepen the degree of mastery of the learning content corresponding to the unknown word through games, In order to improve the enthusiasm of users to learn.

It can be seen that, implementing the tutoring device described in Fig. 5, when the tutoring device judges that the user's intention is literacy, the tutoring device obtains the corresponding voice feature of the voice by recognizing the voice input by the user, and the tutoring device has the associated voice feature in the tutoring device. When specifying a cartoon character, the tutoring device will output the specified cartoon character associated with the above-mentioned voice feature, and load the first virtual object and the first prompt information and the second virtual object and the second prompt information into the palm of the user, Wherein, the first prompt information is used for prompting to select the target image from the album, and the second prompt information is used for prompting calling the camera to shoot the target image. When detecting that the first virtual object is touched by the user, the tutoring device opens the album; detects at least one image selected from the opened album as the target image; or, when detecting that the second virtual object is touched by the user, The tutoring device calls the camera to perform shooting, and uses the image obtained by the camera to perform the shooting as the target image. This process can not only output the specified cartoon character image on the home teaching device, make the literacy learning process of the home teaching device more vivid, interesting and exciting, thereby improving the user's enthusiasm for learning and learning efficiency, but also can accurately identify the user's instruction. to improve the search accuracy of learning content related to the word.

Embodiment 6

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of another tutoring device disclosed in an embodiment of the present invention. The home teaching device shown in FIG. 6 is obtained by optimizing the home teaching device shown in FIG. 5 . Compared with the tutoring device shown in FIG. 5 , the tutoring device illustrated in FIG. 6 may further include:

The second obtaining unit 413 is configured to obtain the voice feature of the specified cartoon character matched with the specified cartoon character after the judgment subunit 4022 judges that the specified cartoon character associated with the voice feature is pre-stored.

As an optional implementation manner, in the tutoring device shown in FIG. 6 , the voice features of the designated cartoon characters that are acquired by the tutoring device through the second obtaining unit 413 and match the above-mentioned designated cartoon characters include:

The cartoon intonation corresponding to the designated cartoon character;

And/or, the cartoon modal particle corresponding to the designated cartoon character;

And/or, the cartoon classic lines corresponding to the designated cartoon character.

As an optional implementation manner, the voice feature acquired by the tutoring device is the voice feature of a pre-stored designated cartoon character matching the voice feature of the user in the tutoring device. This process can effectively prevent the tutoring device from acquiring wrong cartoon characters. This happens in the case of the character's voice characteristics.

The playing unit 414 is configured to play the first prompt information using the cartoon tone corresponding to the voice feature of the specified cartoon character after the second loading subunit 4025 loads the first prompt information to the first virtual object.

As an optional implementation manner, in the tutoring device shown in FIG. 6 , the playing unit 414 is further configured to use the voice feature of the specified cartoon character after the second loading subunit 4025 loads the second prompt information into the second virtual object. The corresponding cartoon tone plays the second prompt information.

As an optional embodiment, in the tutoring device shown in FIG. 6 , the tutoring device can play the content of the prompt information in a cartoon tone corresponding to the voice characteristics of the designated cartoon characters when the user touches the virtual object.

And/or, when the prompt information is loaded into the virtual object, the tutoring device may play the content of the prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character.

As an optional implementation, the tutoring device plays the prompt information by using the cartoon tone corresponding to the voice characteristics of the designated cartoon characters. This process can make the literacy learning process of the tutoring device more vivid, interesting and exciting, thereby improving user learning. motivation and learning efficiency.

As can be seen, implement the tutoring equipment described in Figure 6, when there is a pre-stored designated cartoon character image associated with the above-mentioned voice feature in the tutoring equipment, the tutoring equipment will obtain the designated cartoon character voice feature that the designated cartoon character image matches. , and after the home teaching device loads the prompt information into the virtual object, the home teaching device will use the cartoon tone corresponding to the voice characteristics of the specified cartoon characters to play the prompt information, and this process can not only effectively prevent the home teaching device from obtaining the wrong cartoon characters' voices It makes the literacy learning process of the tutoring equipment more vivid, interesting and exciting, thereby improving the user's enthusiasm for learning and learning efficiency, and can also accurately identify a word indicated by the user, improve the relationship with the word. The accuracy of relevant learning content searches.

Embodiment 7

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of another tutoring device disclosed in an embodiment of the present invention. As shown in Figure 7, the tutoring equipment may include:

a memory 701 storing executable program code;

a processor 702 coupled to the memory 701;

The processor 702 invokes the executable program code stored in the memory 701 to execute any one of the learning content search methods in FIGS. 1 to 3 .

An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program causes a computer to execute any one of the learning content search methods shown in FIGS. 1 to 3 .

The embodiment of the present invention also discloses a computer program product, wherein when the computer program product runs on the computer, the computer is made to execute some or all of the steps of the learning content search method in the above method embodiments.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only storage medium. Memory (Read-Only Memory, ROM), Random Access Memory (Random Access Memory, RAM), Programmable Read-only Memory (PROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically-Erasable Programmable Read-Only Memory (EEPROM), CompactDisc Read -Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

A learning content search method and a tutoring device disclosed in the embodiments of the present invention are described above in detail. The principles and implementations of the present invention are described with specific examples in this paper. The method of the invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and application scope. To sum up, the content of this description should not be understood to limit the present invention.

Claims (10)

1. a learning content search method, is characterized in that, described method comprises: Identify the user intent according to the voice input by the user; If the user intends to be literate, identify the voice feature corresponding to the voice according to the voice; Judging whether the designated cartoon character image associated with the voice feature is pre-stored; If the designated cartoon character image associated with the voice feature is pre-stored, output the designated cartoon character image; Loading a first virtual object into one palm of the outputted designated cartoon character, and loading a second virtual object into the other palm of the outputted designated cartoon character; Loading first prompt information to the first virtual object, the first prompt information is used to prompt selection of a target image from an album; loading second prompt information to the second virtual object, the second prompt information Used to prompt calling the camera to shoot the target image; When it is detected that the first virtual object is touched by the user, an album is opened; at least one image selected from the opened album is detected as a target image; or, when it is detected that the second virtual object is touched When the user touches, call the camera to perform shooting, and use the image obtained by the camera to perform shooting as the target image; determining the designated position in the target image from the target image; Identify several candidate words near the designated position from the target image; Displaying a candidate word list containing the several candidate words on the display screen; Adjust the cursor position in the candidate word list according to the input selection information; When the input confirmation information is detected, the candidate word currently selected by the cursor position is used as the target candidate word; Search for learning content related to the target candidate word; The learning content is output. 2. The method according to claim 1, wherein after judging that a designated cartoon character image associated with the voice feature is pre-stored, the method further comprises: Acquiring the voice features of the specified cartoon characters matched by the specified cartoon characters; After the loading of the first prompt information to the first virtual object, the method further includes: Play the first prompt information using the cartoon intonation corresponding to the voice feature of the specified cartoon character; After loading the second prompt information to the second virtual object, the method further includes: The second prompt information is played by using the cartoon intonation corresponding to the voice feature of the specified cartoon character. 3. The method according to claim 1 or 2, wherein the identifying several candidate words near the designated position from the target image comprises: Determine from the target image a circular area with the specified position as the center of the circle and the length of the area occupied by the predetermined number of words arranged as the radius; Identifying several characters located in the circular area as several candidate characters near the designated position; Or, identifying several candidate words near the designated position from the target image, including: Determine from the target image that the specified position is set as the diagonal intersection point and the area length occupied when the predetermined number of words are arranged is the rectangular area of the diagonal length; Several characters located in the rectangular area are identified as several candidate characters near the designated position. 4. The method according to claim 3, wherein the learning content related to the target candidate word comprises: Pinyin, radicals, strokes and meaning explanation of the target candidate word; And/or, the synonyms, antonyms, synonyms, example sentences and usages of the target candidate word; And/or, the corresponding English translation, example sentences and usage of the target candidate word; and/or, exercises corresponding to the target candidate words. 5. A tutoring device, characterized in that the tutoring device comprises: a first recognition unit, configured to recognize the user's intention according to the voice input by the user; a first determining unit, configured to determine a designated position in the image from the captured target image when the user intends to read; a second identification unit, configured to identify several candidate words near the designated position from the target image; a display unit for displaying a list of candidate words containing the several candidate words on the display screen; an adjustment unit for adjusting the cursor position in the candidate word list according to the input selection information; a second determining unit, configured to use the currently selected candidate word at the cursor position as the target candidate word when the input confirmation information is detected; A search unit, used to search for learning content related to the target candidate word; an output unit for outputting the learning content; The first determining unit includes: a first recognition subunit, configured to recognize the voice feature corresponding to the voice according to the voice when the user's intention is literacy; A judging subunit for judging whether a designated cartoon character associated with the voice feature is pre-stored; An output subunit for outputting the specified cartoon character when the judgment subunit judges that the specified cartoon character associated with the voice feature is pre-stored; a first loading subunit, configured to load a first virtual object into one palm of the outputted designated cartoon character, and load a second virtual object into the other palm of the outputted designated cartoon character; a second loading subunit, configured to load first prompt information to the first virtual object, where the first prompt information is used to prompt to select a target image from an album; load second prompt information to the second virtual object object, the second prompt information is used to prompt calling the camera to shoot the target image; a first determination subunit, configured to open an album when it is detected that the first virtual object is touched by the user, and detect at least one image selected from the opened album as a target image; or, use When it is detected that the second virtual object is touched by the user, the camera is called to perform shooting, and the image obtained by the camera performing the shooting is used as the target image; The second determination subunit is configured to determine the designated position in the target image from the target image. 6. The tutoring device according to claim 5, wherein the tutoring device further comprises: an acquisition unit, configured to acquire the voice features of the specified cartoon characters matched by the specified cartoon characters after the judgment subunit determines that the specified cartoon characters associated with the voice features are pre-stored; a playing unit, configured to play the first prompt information in a cartoon tone corresponding to the voice feature of the specified cartoon character after the second loading subunit loads the first prompt information into the first virtual object; The playing unit is further configured to, after the second loading subunit loads the second prompt information to the second virtual object, play the second virtual object by using the cartoon intonation corresponding to the voice feature of the specified cartoon character. prompt information. 7. The tutoring device according to claim 5 or 6, wherein the second identification unit comprises a third determination subunit and a second identification subunit: The third determination subunit is used to determine, from the target image, a circular area with the specified position as the center of the circle and the length of the area occupied by the preset number of words as the radius; the first Two identification subunits, used to identify several characters located in the circular area as several candidate characters near the designated position; Or, the third determination subunit is used to determine from the target image that the specified position is set as the diagonal intersection and the length of the area occupied when the predetermined number of words are arranged is the diagonal line A rectangular area with a length; the second identification subunit is used to identify several characters located in the rectangular area as several candidate characters near the designated position. 8. The tutoring device according to claim 7, wherein the learning content related to the target candidate word comprises: Pinyin, radicals, strokes and meaning explanation of the target candidate word; And/or, the synonyms, antonyms, synonyms, example sentences and usages of the target candidate word; And/or, the corresponding English translation, example sentences and usage of the target candidate word; and/or, exercises corresponding to the target candidate words. 9. A tutoring device, characterized in that the tutoring device comprises: a memory in which executable program code is stored; a processor coupled to the memory; The processor invokes the executable program code stored in the memory to execute the learning content search method according to any one of claims 1-4. 10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program causes a computer to execute the learning content search method according to any one of claims 1-4 .

Images