CN105975552B - Question searching method and device of intelligent equipment - Google Patents

Abstract

The present invention provides a method for searching questions on a smart device, the method comprising: turning on cursor display, displaying a cursor in a picture captured by a camera; detecting whether the cursor is in a stationary state in the picture; if the cursor is in a stationary state in the picture, searching for question content in the picture according to the position of the cursor; identifying the question content in the picture to be searched, and searching according to the identified question content. After turning on the cursor display and aligning the question, the present invention can automatically search, which greatly simplifies the convenience of user operation and is conducive to improving the efficiency of question search.

Description

Method and device for topic search for intelligent equipment

technical field

The invention belongs to the field of learning machines, and in particular relates to a topic search method and device for intelligent equipment.

Background technique

A learning machine is an electronic product that assists users in learning. A large number of learning resources are usually stored in the learning machine. The learning machine can better help users understand or master the learning content by outputting learning resources through a display screen or a speaker according to a certain interactive mode.

In order to help users improve the efficiency of answering questions, current learning machines usually have a search function. After shooting the picture including the question content through the camera of the learning machine, identify the question content in the picture, according to the identified content, search the resource library for questions that are the same or similar to the question content, and display the solution to the question and answers.

However, when the current learning machine searches for a question, it usually needs to open the APP for searching questions first, then open the camera, focus on the question and take a photo manually, and then identify the content of the question in the photo. This search method operates It is more troublesome and the search efficiency is low.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a topic search method for an intelligent device, so as to solve the problems of troublesome operation and low search efficiency when performing topic search in the prior art.

In a first aspect, an embodiment of the present invention provides a method for searching a topic of a smart device, the method comprising:

Turn on the cursor display, and display the cursor in the screen captured by the camera;

detecting whether the cursor is in a static state in the picture;

If the cursor is in a static state in the picture, searching for the title content in the picture according to the position of the cursor;

Identify the subject content in the screen that is found, and search according to the identified subject content.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the step of displaying the cursor in the picture acquired by the camera is specifically:

Displaying a first cursor pattern in the picture acquired by the camera, where the first cursor pattern includes a cursor center pattern and a border pattern of a cursor adjacent to the center pattern;

If the cursor is in a static state in the picture, the step of searching for the topic content in the picture according to the position of the cursor includes:

If the cursor is in a static state in the picture, then determine the position of the topic content according to the center pattern of the cursor;

The boundary of the title content is searched according to the screen, and the border pattern of the cursor is displayed at the position of the boundary of the title content.

With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the cursor center pattern is a cross cursor pattern, and the cursor border pattern is a four-corner border pattern.

With reference to the first possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the step of searching for the boundary of the topic content according to the screen includes:

Find the boundary of the title content according to the line feed identifier included in the screen content;

Or, the line spacing of the text included in the screen content is acquired, and when the line spacing is greater than a preset line spacing value in the screen, it is determined that the current position is the boundary of the topic.

With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the step of detecting whether the cursor is in a static state in the screen includes:

It is detected whether the picture acquired by the camera has changed, and whether the cursor has received a movement instruction.

In a second aspect, an embodiment of the present invention provides a topic search apparatus for a smart device, the apparatus comprising:

The cursor opens the display unit, which is used to open the cursor display and display the cursor in the picture obtained by the camera;

a state detection unit, configured to detect whether the cursor is in a static state in the picture;

a content search unit, configured to search for topic content in the screen according to the position of the cursor if the cursor is in a static state in the screen;

The content identification unit is configured to identify the searched topic content in the screen, and search according to the identified topic content.

With reference to the second aspect, in a first possible implementation manner of the second aspect, the cursor-on display unit is specifically used for:

Displaying a first cursor pattern in the picture acquired by the camera, where the first cursor pattern includes a cursor center pattern and a border pattern of a cursor adjacent to the center pattern;

The content search unit includes:

a position determination subunit, used for determining the position of the topic content according to the center pattern of the cursor if the cursor is in a static state in the picture;

The boundary display subunit is used for searching the boundary of the title content according to the screen, and displaying the border pattern of the cursor at the position of the boundary of the title content.

With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the cursor center pattern is a cross cursor pattern, and the cursor border pattern is a four-corner border pattern.

With reference to the first possible implementation manner of the second aspect, in a third possible implementation manner of the second aspect, the content search unit includes:

a first search subunit, configured to search for the boundary of the title content according to the line feed identifier included in the screen content;

Alternatively, the second search subunit is configured to obtain the line spacing of the text included in the screen content, and when the line spacing is greater than a preset line spacing value in the screen, determine that the current position is the boundary of the topic.

With reference to the second aspect, in a fourth possible implementation manner of the second aspect, the state detection unit is specifically configured to:

It is detected whether the picture acquired by the camera has changed, and whether the cursor has received a movement instruction.

In the present invention, when the user turns on the cursor display, the cursor is displayed in the picture obtained by the camera, and the system detects whether the cursor in the picture is in a static state. And search is performed according to the identified topic content, so that the present invention can automatically search after the cursor is turned on to display and align the topic, which greatly simplifies the convenience of user operation and helps to improve the efficiency of topic search.

Description of drawings

Fig. 1 is the realization flow chart of the topic search method of the smart device provided by the first embodiment of the present invention;

Fig. 2 is the realization flow chart of the topic search method of the smart device provided by the second embodiment of the present invention;

3 is a schematic diagram of a cursor display state provided by a second embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a topic search apparatus for a smart device according to a third embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

The purpose of the embodiments of the present invention is to provide a topic search method for a smart device, so as to solve the problems of complicated operation and low search efficiency when searching for topics in the prior art. In the prior art, when using a learning machine or other learning equipment to search, it is necessary to open an application program to search for a topic first, and when the application program is open, turn on the camera, and the camera shoots a picture including the topic content, and then uses the text The recognition program performs text recognition on the topic content in the screen, and the user selects the required topic content, or directly sends the recognition result to the server or local topic database, and displays the corresponding topic result in the device. In order to specifically describe how to solve the above problems, the present invention will be specifically described below with reference to the accompanying drawings.

Example 1:

Fig. 1 shows the realization flow of the topic search method of the smart device provided by the first embodiment of the present invention, which is described in detail as follows:

In step S101 , the cursor display is turned on, and the cursor is displayed on the screen captured by the camera.

Specifically, to enable the cursor display in the embodiment of the present invention, a hardware switch can be set in the learning machine and other equipment, and by switching the hardware switch to the on state, it is possible to quickly switch to the topic search mode during the use of the learning machine. state.

Of course, a cursor start button can also be set in the learning machine and other devices. After the user clicks the button, the learning machine and other devices can quickly turn on the camera, display the picture obtained by the camera, and display the cursor in the picture.

In a preferred implementation manner, when the cursor display is turned on, the device may be in a standby state. In this way, the device can be used to quickly search for topics at any time, which can further facilitate the use of the user.

The picture acquired by the camera may be displayed in a full-screen manner, or may be displayed in a window manner in a designated area of the screen. The cursor may be displayed in the middle of the screen by a default display mode, or it may be preset to display the cursor at other positions of the screen.

The user can change the position of the cursor by touching or moving the mouse, for example, by touching, moving the cursor to the position of the title in the screen.

In step S102, it is detected whether the cursor is in a static state in the screen.

Specifically, after the cursor display is turned on, the picture on which the camera is aimed may not be the picture where the question is, and the user needs to adjust the picture on which the camera is directed, or adjust the position of the question to be identified by adjusting the cursor. After the user adjusts the screen where the title to be searched is located, the position of the cursor in the screen is in a static state, which means that the user has aimed at the subject to be searched. If the cursor is in a relative motion state in the screen, then Indicates that the user is currently moving the camera or moving the cursor, and the location of the question cannot be determined yet.

Therefore, in the embodiment of the present invention, when detecting whether the cursor is in a static state in the picture, it may include detecting whether the picture acquired by the camera changes, and detecting whether the cursor receives a movement instruction.

When the user determines that the current image of the camera includes the subject content to be searched, the user needs to adjust the device to a static state, keep the image captured by the camera unchanged, and further adjust the position of the subject content through the cursor.

If the user is ensuring that the screen is still and the cursor is still for a certain period of time, for example, when the time in the still state exceeds 500-800 milliseconds, it can be considered that the current cursor position corresponds to the position of the topic content.

In step S103, if the cursor is in a static state in the picture, search for the topic content in the picture according to the position of the cursor.

Specifically, if the cursor is in a static state in the picture, it means that the position currently indicated by the cursor is the position where the title is located. Therefore, the present invention automatically finds the position of the subject content in the screen through the position of the cursor, so that the subject in the screen can be found efficiently and the cumbersome operation of the user is avoided.

Wherein, according to the position of the cursor to search for the title content in the screen, the title content can be searched according to the position of the cursor as the center and according to the predetermined title range identifier, for example, there is usually a line break between the title and the title. , or the distance between topics is usually larger than the normal distance, etc., to determine the size of the content of the topic.

After finding the content of the subject, a voice prompt or a prompt can be issued to prompt the content of the subject in the screen that has been found, and prompt the user to confirm whether it is correct. Wait for the search result to be returned. If the searched content is incorrect, you can change the position of the cursor, or change the screen obtained by the camera, and obtain the title content again.

In step S104, the title content in the searched screen is identified, and the search is performed according to the identified title content.

After determining the position and size of the topic content in the screen, the topic content in the area can be identified through a character recognition program. In terms of recognition efficiency, the present invention only needs to identify part of the screen where the topic is located. It can be displayed to improve the efficiency of recognizing the subject in the screen.

In the embodiment of the present invention, when the user turns on the cursor display, the cursor is displayed in the picture obtained by the camera, and the system detects whether the cursor in the picture is in a static state. , and search according to the identified topic content, so that the present invention can automatically search after turning on the cursor display and aiming at the topic, which greatly simplifies the convenience of user operation and helps to improve the efficiency of topic search.

Embodiment 2:

Fig. 2 shows the realization flow of the topic search method of the smart device provided by the second embodiment of the present invention, which is described in detail as follows:

In step S201 , the cursor display is turned on, and a first cursor pattern is displayed on the screen captured by the camera, where the first cursor pattern includes a cursor center pattern and a border pattern of a cursor adjacent to the center pattern.

Specifically, as an implementation of the cursor according to the embodiment of the present invention, as shown in FIG. 3 , the cursor includes a center pattern and a border pattern of the cursor, the center pattern is a cross cursor pattern, and the border pattern of the cursor For the four-corner border pattern. Of course, this is just one of the implementations, and the center pattern and the border pattern of the cursor can be flexibly replaced according to the needs of the user.

In this embodiment of the present invention, the cursor includes two display states. The first is a complete cursor display state. The center pattern of the cursor is adjacent to the border pattern of the cursor. In this state, the user can move the cursor. Alternatively, the content of the picture acquired by the camera can be changed, so that the cursor in the complete display state and the content in the picture acquired by the camera remain relatively still. Thereby, the content of the title in the screen is determined.

The second state is after the first state, after detecting that the cursor is in a static state in the screen, the border pattern of the cursor performs automatic topic boundary search, and the border pattern of the cursor is displayed at the border position of the topic, so The center pattern can be adjusted to be displayed at the center of the border pattern of the cursor according to the position of the searched boundary.

In step S202, it is detected whether the cursor is in a static state in the picture.

In step S203, if the cursor is in a static state in the screen, the position of the topic content is determined according to the center pattern of the cursor.

Specifically, in this embodiment of the present invention, the cursor is in a static state on the screen, including two necessary conditions:

1) The content in the screen is in a static state, that is to say, the content of the screen obtained by the camera has not changed, and the user has confirmed that the current screen includes the subject to be searched;

2) The cursor on the display screen of the learning machine and other equipment is in a static state. At this time, the user does not move the cursor through touch or mouse operation, that is to say, the user has confirmed that the current position of the cursor is at the position of the question.

In step S204, the boundary of the title content is searched according to the screen, and the border pattern of the cursor is displayed at the position of the boundary of the title content.

In the embodiment of the present invention, it further includes searching for the boundary of the topic content, wherein the step of searching for the boundary of the topic content according to the screen includes:

Find the boundary of the title content according to the line feed identifier included in the screen content;

Or, the line spacing of the text included in the screen content is acquired, and when the line spacing is greater than a preset line spacing value in the screen, it is determined that the current position is the boundary of the topic.

The preset line spacing may be the line spacing set for general characters. Since the spacing will change with the distance of the screen, in order to improve the accuracy of the judgment, it can also be judged by the ratio of the text to the spacing. For example, when the ratio of the text size to the line spacing is smaller than the predetermined value, the boundary of the current behavior topic is judged Location. and displaying the border pattern of the cursor at the border position. In order to facilitate the confirmation of the position of the frame, the frame pattern of the cursor may be displayed in a blinking manner.

In step S205, the title content in the searched screen is identified, and the search is performed according to the identified title content.

In the embodiment of the present invention, after determining the area where the topic content is located by the border pattern of the cursor, the efficiency of identifying the topic content can be further improved, and selecting the topic content by the border pattern of the cursor can improve the accuracy of topic search.

Embodiment three:

FIG. 4 shows a schematic structural diagram of a topic search apparatus for a smart device provided by a third embodiment of the present invention, which is described in detail as follows:

The topic search device of the smart device according to the embodiment of the present invention includes:

The cursor open display unit 401 is used to open the cursor display, and display the cursor in the picture obtained by the camera;

a state detection unit 402, configured to detect whether the cursor is in a static state in the picture;

A content search unit 403, configured to search the title content in the screen according to the position of the cursor if the cursor is in a static state in the screen;

The content identification unit 404 is configured to identify the title content in the screen that is found, and search according to the identified title content.

Preferably, the cursor opening display unit is specifically used for:

Displaying a first cursor pattern in the picture acquired by the camera, where the first cursor pattern includes a cursor center pattern and a border pattern of a cursor adjacent to the center pattern;

The content search unit includes:

a position determination subunit, used for determining the position of the topic content according to the center pattern of the cursor if the cursor is in a static state in the picture;

The boundary display subunit is used for searching the boundary of the title content according to the screen, and displaying the border pattern of the cursor at the position of the boundary of the title content.

Preferably, the center pattern of the cursor is a cross cursor pattern, and the border pattern of the cursor is a four-corner border pattern.

Preferably, the content search unit includes:

a first search subunit, configured to search for the boundary of the title content according to the line feed identifier included in the screen content;

Alternatively, the second search subunit is configured to obtain the line spacing of the text included in the screen content, and when the line spacing is greater than a preset line spacing value in the screen, determine that the current position is the boundary of the topic.

Preferably, the state detection unit is specifically used for:

It is detected whether the picture acquired by the camera has changed, and whether the cursor has received a movement instruction.

The topic searching apparatus of the smart device according to the embodiment of the present invention corresponds to the topic searching method of the smart device according to the first and second embodiments, and will not be described repeatedly here.

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.

Claims (8)

1. A title searching method of intelligent equipment is characterized by comprising the following steps:

when the equipment is in a standby state, starting cursor display through a hardware switch, and displaying a cursor in a picture acquired by a camera;

detecting whether the cursor is in a static state in the picture or not, wherein the static time reaches a certain duration;

if the cursor is in a static state in the picture and the static time reaches a certain duration, searching the title content in the picture according to the position of the cursor;

identifying the searched topic content in the picture, and searching according to the identified topic content;

the step of displaying the cursor in the picture acquired by the camera specifically comprises the following steps: displaying a first cursor pattern in a picture acquired by a camera, wherein the first cursor pattern comprises a cursor center pattern and a frame pattern of a cursor adjacent to the center pattern;

if the cursor is in a static state in the picture and the static time reaches a certain duration, the step of searching the title content in the picture according to the position of the cursor comprises the following steps:

if the cursor is in a static state in the picture, determining the position of the title content according to the central pattern of the cursor;

searching the boundary of the theme content according to the picture, and displaying the border pattern of the cursor at the position of the boundary of the theme content, wherein the step of searching the boundary of the theme content according to the picture comprises the following steps:

and acquiring the line spacing of characters included in the picture content, and judging that the current position is the boundary of the topic when the line spacing is larger than a preset line spacing value in the picture.

2. The method of claim 1, wherein the cursor center pattern is a cross cursor pattern and the border pattern of the cursor is a four-corner border pattern.

3. The method according to claim 1, wherein the step of finding the boundary of the title content according to the frame comprises:

and searching the boundary of the title content according to the line feed identifier included in the picture content.

4. The method according to claim 1, wherein the step of detecting whether the cursor is in a still state in the screen comprises:

and detecting whether the picture acquired by the camera changes or not and detecting whether the cursor receives a moving instruction or not.

5. A title search device of intelligent equipment, characterized in that, the device includes:

the cursor opening display unit is used for opening cursor display through a hardware switch when the equipment is in a standby state and displaying a cursor in a picture acquired by the camera;

the state detection unit is used for detecting whether the cursor is in a static state in the picture or not, and the static time reaches a certain duration;

the content searching unit is used for searching the title content in the picture according to the position of the cursor if the cursor is in a static state in the picture and the static time reaches a certain duration;

the content identification unit is used for identifying the searched topic content in the picture and searching according to the identified topic content;

the cursor opening display unit is specifically configured to:

displaying a first cursor pattern in a picture acquired by a camera, wherein the first cursor pattern comprises a cursor center pattern and a frame pattern of a cursor adjacent to the center pattern;

the content search unit includes:

the position determining subunit is used for determining the position of the title content according to the central pattern of the cursor if the cursor is in a static state in the picture;

the boundary display subunit is used for searching the boundary of the theme content according to the picture and displaying the frame pattern of the cursor at the position of the boundary of the theme content;

the content search unit includes:

and the second searching subunit is used for acquiring the line spacing of the characters included in the picture content, and judging that the current position is the boundary of the topic when the line spacing is larger than a preset line spacing value in the picture.

6. The apparatus of claim 5, wherein the cursor center pattern is a cross cursor pattern, and the border pattern of the cursor is a four-corner border pattern.

7. The apparatus of claim 5, wherein the content search unit comprises:

and the first searching subunit is used for searching the boundary of the title content according to the line feed identifier included in the picture content.

8. The apparatus according to claim 5, wherein the state detection unit is specifically configured to:

and detecting whether the picture acquired by the camera changes or not and detecting whether the cursor receives a moving instruction or not.

Images