CN106202360A - Test question searching method and device - Google Patents

Abstract

The invention is suitable for the technical field of test question searching and provides a test question searching method and device. The method comprises the following steps: after receiving a starting instruction of a search question application, starting the search question application and a camera; acquiring a picture of a question including a test question, and identifying text information corresponding to the picture; searching the question according to the identification result of the text information; and when the number of searched topics is 1, acquiring and displaying information corresponding to the topics. By the method, the problem searching efficiency can be improved.

Description

Test question search method and device

technical field

The embodiments of the present invention belong to the technical field of question search, and in particular relate to a method and device for searching test questions.

Background technique

At present, there are many search apps for smart device products that solve students' homework problems, such as Xiaoyuan Soti, Xuebajun, Homework Help, etc. They all take pictures of the problems, and then input the content of the photos into the search app to facilitate the search. The question APP searches for the corresponding answer to the question according to the content of the photo. However, when using the search question APP, the following steps are often required: the user opens the APP, the user turns on the camera, the user takes a picture of the test question, and the user uploads the picture including the taken test question so that the search question APP can search for the test question, etc. Therefore, using the search question The operation steps of the question APP are too cumbersome, which reduces the speed of searching questions.

Contents of the invention

Embodiments of the present invention provide a method and device for searching test questions, aiming at solving the problem of low efficiency of searching questions in existing methods.

The embodiment of the present invention is achieved in this way, a method for searching for test questions, said method comprising:

After receiving the search question application starting instruction, start the search question application and the camera;

Obtaining pictures of topics including test questions, and identifying text information corresponding to the pictures;

Search for topics based on the recognition results of text information;

When the number of topics searched is 1, information corresponding to the topic is acquired and displayed.

Another object of the embodiments of the present invention is to provide a test question search device, which includes:

A camera starting unit, configured to start the topic-searching application and the camera after receiving the topic-searching application startup instruction;

A text information recognition unit, configured to acquire pictures of topics including test questions, and identify text information corresponding to the pictures;

a topic search unit, configured to search for a topic according to the recognition result of the text information;

The information display unit is configured to acquire and display information corresponding to the topic when the number of topics searched is 1.

In the embodiment of the present invention, since the camera is also started when the application for searching questions is started, and after obtaining the pictures including the questions of the test questions, the text information corresponding to the pictures is directly recognized without the user uploading, thereby reducing user operations and improving Search efficiency and improve user experience.

Description of drawings

Fig. 1 is the flow chart of a kind of test question search method that the first embodiment of the present invention provides;

Fig. 2 is a structural diagram of a test question search device provided by the second embodiment of the present invention.

detailed description

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

In the embodiment of the present invention, after receiving the start command of the search question application, start the search question application and the camera, obtain pictures including the questions of the test questions, and identify the text information corresponding to the pictures, and perform the test according to the recognition result of the text information. Topic search: when the number of topics searched is 1, information corresponding to the topic is obtained and displayed.

In order to illustrate the technical solutions of the present invention, specific examples are used below to illustrate.

Embodiment one:

Fig. 1 shows the flow chart of a kind of test question search method that the first embodiment of the present invention provides, and details are as follows:

Step S11, start the topic searching application and the camera after receiving the topic searching application starting instruction.

In this step, after the user starts the topic-searching application, the smart terminal automatically starts its own camera to take pictures. Since the user does not need to perform the operation of turning on the camera, the operation complexity is simplified.

Step S12, acquiring pictures including the titles of the test questions, and identifying text information corresponding to the pictures.

Wherein, the picture including the title of the test question can be: a picture including the text information of the first line of the title; a picture including the text information of the second line of the title; a picture including the text information of the first line and the second line of the title ,etc.

In this step, the text information in the picture may be recognized by an optical character recognition (Optical Character Recognition, OCR) recognition technology.

Optionally, in order to reduce search content and improve search efficiency, the step S12 specifically includes:

A picture including the title of the test question is obtained, and text information in the picture corresponding to the line where the cursor of the screen is projected on the title of the test question is identified. Since only the text information in the picture corresponding to the line where the cursor of the screen is projected on the title of the test question is recognized, and a line of text information contains less information, therefore, when subsequent searches are performed based on text information, search results can be obtained quickly .

Optionally, after acquiring the picture including the title of the test question and identifying the text information in the picture corresponding to the line where the cursor of the screen is projected on the title of the test question, include:

A1. Determine whether the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title.

A2. When the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title, search for the title according to the recognition result of the text information.

A3. When the text information corresponding to the line where the cursor of the screen is projected on the subject of the test question is not the text information of the first line of the question, adjust the cursor on the screen to the projection range of the test question so that the obtained picture is consistent with The text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title.

In the above A1-A3, it is first judged whether the text information corresponding to the line where the cursor is projected is the text information of the first line of the title, and if so, execute step S13 and subsequent step S14. Otherwise, the camera can actively adjust the viewing range to adjust the projection range of the screen cursor on the test question; or, send a reminder (such as language reminder or vibration reminder, etc.), so that the user can adjust the screen cursor to the test question according to the reminder sent by the smart terminal. projection range.

Optionally, judge whether the text information is the text information of the first line of the title by judging whether the beginning or end of the text information is a number. At this time, the A1 specifically includes:

A11. Determine whether the beginning or end of the text information corresponding to the line where the projection of the cursor on the screen is located on the title of the test question is a number.

A12. When the beginning or end of the text information corresponding to the line where the cursor of the screen is projected on the subject of the test question is a number, determine the text information corresponding to the line where the cursor of the screen is projected on the subject of the test question is the text information of the first line of the title; otherwise, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not the text information of the first line of the title.

In the above A11 and A12, since each test question usually has a corresponding serial number, and the serial number only appears at the beginning or end of the test question, when it is judged that the beginning or end of the text information corresponding to the picture is a number , it can quickly and accurately determine that the text information corresponding to the picture is the text information of the first line of the title.

Or, by comparing the interval between two adjacent lines of text information to determine whether the text information is the text information of the first line of the title, at this time, the A1 specifically includes:

A11', judging whether the distance between the text information corresponding to the line where the cursor of the screen is projected on the title of the test question and the text information of the previous line is greater than the preset inter-line threshold.

A12', when the distance between the text information corresponding to the line where the cursor of the screen is projected on the title of the test question and the text information of the previous line is greater than the preset inter-line threshold, it is determined that the cursor on the screen is on the title of the test question The text information corresponding to the line where the projection of is located is the text information of the first line of the title, otherwise, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not the text information of the first line of the title.

Wherein, the preset inter-line threshold is equal to or slightly greater than the interval between each line of text content in the same test question.

Since the interval between the text information of each test question is greater than the interval of each line of text information in the same test question, when the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is separated from the text information of the previous line When the interval is greater than the preset inter-line threshold, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not the text information of the first line of the title.

It should be pointed out that when there is no text information on the previous line of the text information corresponding to the line where the cursor of the screen is projected on the title of the test question, then it is determined that the line corresponding to the line where the cursor of the screen is projected on the title of the test question The text information is the text information of the first line of the title.

Step S13, perform topic search according to the recognition result of the text information.

Specifically, compare the recognition results of the text information with the information in the cloud question bank (such as word-by-word or line-by-line comparison), so that when the two match (for example, the number of the same characters is greater than the specified character number threshold), the corresponding information is output, such as the question purpose answer.

Step S14, when the number of topics searched is 1, acquire and display information corresponding to the topic.

In this step, when a unique search result matching the recognition result of the text information is found, the information corresponding to the topic is obtained and displayed, such as the answer and/or analysis and/or topic corresponding to the topic are displayed.

Optionally, when the number of topics being searched is not 1, the text information of the Nth row of the topic is obtained, and the topic search is performed according to the recognition results of the text information from the first row to the Nth row of the topic, where N is Integer, N greater than or equal to 2.

When the number of topics searched is 1, obtain and display the information corresponding to the topic; when the number of topics searched is not 1, obtain the text information of the (N+1)th row of the topic, according to the topic The recognition results of the text information from one row to the (N+1)th row are used for topic search, and this step is repeated until the topic search is performed according to the recognition results of the text information of all rows of the topic.

In the above steps, when no unique matching title is found according to the text information of the first line of the title, the text information of the second line is obtained, and then the search is continued in the cloud according to the text information of the first line and the second line, If there is still no unique matching title, continue to obtain the text information of the third line until the text information of all lines of the title is obtained, if no matching unique title is found according to the text information of all lines of the title, Then output the information corresponding to all the topics found in the search, so that the user can choose.

In the first embodiment of the present invention, after receiving the start command of the search question application, start the search question application and the camera, obtain pictures including the questions of the test questions, and identify the text information corresponding to the pictures, according to the identification of the text information As a result, topic search is performed, and when the number of topics searched is 1, information corresponding to the topic is acquired and displayed. Since the camera is also activated when the question search application is started, and after obtaining the pictures including the questions of the test questions, the text information corresponding to the pictures is directly recognized without the user uploading, thereby reducing user operations and improving user experience.

It should be understood that in the embodiment of the present invention, the sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, rather than the implementation process of the embodiment of the present invention. constitute any limitation.

Embodiment two:

Fig. 2 shows a structure diagram of a test question search device provided by the second embodiment of the present invention. The test question search device can be applied to an intelligent terminal, and the intelligent terminal can include a wireless access network RAN and one or more core The user equipment that communicates with the network can be a learning machine, a mobile phone (or called a "cellular" phone), a computer with a mobile device, etc. For example, the user equipment can also be a portable, pocket, hand-held, computer Built-in or vehicle-mounted mobile devices that exchange voice and/or data with the radio access network. For another example, the mobile device may include a smart phone, a tablet computer, a personal digital assistant PDA, a sales terminal POS, or a vehicle-mounted computer. For ease of description, only parts related to the embodiments of the present invention are shown.

The test question search device includes: a camera starting unit 21 , a text information recognition unit 22 , a question search unit 23 , and an information display unit 24 . in:

The camera starting unit 21 is configured to start the topic searching application and the camera after receiving the topic searching application starting instruction.

Specifically, after the user starts the topic-searching application, the smart terminal automatically starts its own camera to take pictures. Since the user does not need to perform the operation of turning on the camera, the operation complexity is simplified.

The text information identification unit 22 is configured to obtain pictures including the titles of the test questions, and identify text information corresponding to the pictures.

Wherein, the picture including the title of the test question can be: a picture including the text information of the first line of the title; a picture including the text information of the second line of the title; a picture including the text information of the first line and the second line of the title ,etc.

Optionally, in order to reduce search content and improve search efficiency, the text information identification unit 22 includes:

A picture including the title of the test question is obtained, and text information in the picture corresponding to the line where the cursor of the screen is projected on the title of the test question is identified.

Since only the text information in the picture corresponding to the line where the cursor of the screen is projected on the title of the test question is recognized, and a line of text information contains less information, therefore, when subsequent searches are performed based on text information, search results can be obtained quickly .

Optionally, the test question search device includes:

The first row judging module is used to judge whether the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title, so that the cursor on the screen is in the title of the test question. When the text information corresponding to the line where the projection is located is the text information of the first line of the title, the title search is performed according to the recognition result of the text information.

The viewfinder range adjustment module is used to adjust the projection range of the screen cursor on the test question when the text information corresponding to the line where the cursor of the screen is projected on the test question is not the text information of the first line of the test question, so that In the obtained picture, the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title.

In the above-mentioned first line judging module and viewfinder range adjusting module, it is first judged whether the text information corresponding to the line where the cursor is projected is the text information of the first line of the title, and if so, the title search unit 23 and the information display unit 24 are executed. Otherwise, the camera can actively adjust the viewing range to adjust the projection range of the screen cursor on the test question; or, send a reminder (such as language reminder or vibration reminder, etc.), so that the user can adjust the screen cursor to the test question according to the reminder sent by the smart terminal. projection range.

Optionally, judge whether the text information is the text information of the first line of the title by judging whether the head end or tail end of the text information is a number. At this time, the first line judging module includes:

Whether it includes a number judging module, which is used to judge whether the head end or tail end of the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is a number.

The first line of text information judging module is used to determine that the cursor on the screen is in the test question when the head or tail of the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is a number. The text information corresponding to the line where the projection of the title is located is the text information of the first line of the title, otherwise, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not the text information of the first line of the title .

In the module for judging whether the number is included above and the module for judging the first line of text information, since each test question usually has a corresponding serial number, and the serial number only appears at the beginning or end of the test question, when it is judged that the picture corresponds to When the beginning or end of the text information is a number, it can be quickly and accurately determined that the text information corresponding to the picture is the text information of the first line of the title.

Or, judge whether the text information is the text information of the first line of the title by comparing the interval between two adjacent lines of text information. At this time, the first line judging module includes:

The inter-line interval comparison module is used to determine whether the interval between the text information corresponding to the line where the cursor of the screen is projected on the title of the test question and the text information of the previous line is greater than the preset inter-line threshold.

The second first line of text information judging module is used to judge that when the distance between the text information corresponding to the line where the cursor of the screen is projected on the title of the test question and the text information of the previous line is greater than a preset inter-line threshold The text information corresponding to the line where the cursor of the screen is projected on the title of the test question is the text information of the first line of the title; otherwise, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not a title The text information of the first line of .

Wherein, the preset inter-line threshold is equal to or slightly greater than the interval between each line of text content in the same test question.

Since the interval between the text information of each test question is greater than the interval of each line of text information in the same test question, when the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is separated from the text information of the previous line When the interval is greater than the preset inter-line threshold, it is determined that the text information corresponding to the line where the cursor of the screen is projected on the title of the test question is not the text information of the first line of the title.

It should be pointed out that when there is no text information on the previous line of the text information corresponding to the line where the cursor of the screen is projected on the title of the test question, then it is determined that the line corresponding to the line where the cursor of the screen is projected on the title of the test question The text information is the text information of the first line of the title.

A topic search unit 23, configured to search for a topic according to the recognition result of the text information.

Specifically, compare the recognition results of the text information with the information in the cloud question bank (such as word-by-word or line-by-line comparison), so that when the two match (for example, the number of the same characters is greater than the specified character number threshold), the corresponding information is output, such as the question purpose answer.

The information display unit 24 is configured to acquire and display information corresponding to the topic when the number of topics searched is one.

When a unique search result matching the recognition result of the text information is found, information corresponding to the topic is acquired and displayed, such as an answer and/or analysis and/or topic corresponding to the topic are displayed.

Optionally, the test question search device includes:

A supplementary information acquiring unit, configured to acquire the text information of the Nth row of the topic when the number of the topics being searched is not 1, and perform topic search according to the identification results of the text information of the first row to the Nth row of the topic , N is an integer, and N is greater than or equal to 2.

The supplementary information search unit is used to obtain and display information corresponding to the topic when the number of topics searched is 1; when the number of topics searched is not 1, obtain the information of the (N+1)th line of the topic For the text information, the topic search is performed according to the recognition results of the text information of the first row to the (N+1)th row of the topic, and this step is repeated until the topic search is performed according to the recognition results of the text information of all rows of the topic.

In the second embodiment of the present invention, since the camera is also started when the application for searching questions is started, and after obtaining the picture of the title including the test question, the text information corresponding to the picture is directly recognized without the user uploading, thereby reducing user operations and improving good user experience.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device 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 can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

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

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the 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 are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile 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 is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. A method for searching for test questions, the method comprising:

after receiving a starting instruction of a search question application, starting the search question application and a camera;

acquiring a picture of a question including a test question, and identifying text information corresponding to the picture;

searching the question according to the identification result of the text information;

and when the number of searched topics is 1, acquiring and displaying information corresponding to the topics.

2. The method according to claim 1, wherein the obtaining of the picture corresponding to the projection range of the cursor of the screen on the test question and the identifying of the text information corresponding to the picture specifically include:

the method comprises the steps of obtaining a picture including the subject of the test question, and identifying text information corresponding to a line where a screen cursor projects on the subject of the test question in the picture.

3. The method according to claim 2, wherein after the obtaining of the picture including the subject of the test question and the identification of the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question, the method comprises:

judging whether the text information corresponding to the line of the projection of the cursor of the screen on the question is the text information of the first line of the question or not so as to search the question according to the identification result of the text information when the text information corresponding to the line of the projection of the cursor of the screen on the question is the text information of the first line of the question;

and when the text information corresponding to the line of the projection of the cursor of the screen on the question of the question is not the text information of the first line of the question, adjusting the projection range of the cursor of the screen on the question so as to enable the text information corresponding to the line of the projection of the cursor of the screen on the question in the acquired picture to be the text information of the first line of the question.

4. The method according to claim 3, wherein the determining whether the text information corresponding to the line on which the screen cursor is projected on the question of the question is the text information of the first line of the question specifically includes:

judging whether the head end or the tail end of the text information corresponding to the line where the cursor of the screen is projected on the question of the test question is a number or not;

when the head end or the tail end of the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is a number, judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is the text information of the first line of the subject, otherwise, judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is not the text information of the first line of the subject;

or,

judging whether the interval between the text information corresponding to the line where the screen cursor projects on the question of the test question and the text information of the previous line is larger than a preset threshold value between the lines;

and when the interval between the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question and the text information in the previous line is larger than a preset threshold value between the lines, judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is the text information in the first line of the subject, otherwise, judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is not the text information in the first line of the subject.

5. The method of claim 3,

when the number of the searched topics is not 1, acquiring the text information of the Nth line of the topics, and searching the topics according to the recognition results of the text information of the first to Nth lines of the topics, wherein N is an integer and is greater than or equal to 2;

when the number of searched topics is 1, acquiring and displaying information corresponding to the topics; and when the number of searched topics is not 1, acquiring text information of the (N +1) th line of the topics, searching the topics according to the recognition results of the text information of the first to (N +1) th lines of the topics, and repeating the steps until searching the topics according to the recognition results of the text information of all the lines of the topics.

6. An apparatus for searching for test questions, the apparatus comprising:

the camera starting unit is used for starting the search question application and the camera after receiving a search question application starting instruction;

the text information identification unit is used for acquiring a picture of a question including a test question and identifying text information corresponding to the picture;

the title searching unit is used for searching titles according to the identification result of the text information;

and the information display unit is used for acquiring and displaying the information corresponding to the titles when the number of searched titles is 1.

7. The apparatus according to claim 6, wherein the text information identifying unit includes:

the method comprises the steps of obtaining a picture including the subject of the test question, and identifying text information corresponding to a line where a screen cursor projects on the subject of the test question in the picture.

8. The apparatus of claim 7, wherein the apparatus comprises:

the first line judgment module is used for judging whether the text information corresponding to the line of the projection of the cursor of the screen on the question is the text information of the first line of the question or not so as to search the question according to the identification result of the text information when the text information corresponding to the line of the projection of the cursor of the screen on the question is the text information of the first line of the question;

and the view range adjusting module is used for adjusting the projection range of the cursor of the screen in the test question when the text information corresponding to the line of the projection of the cursor of the screen in the question is not the text information of the first line of the question, so that the text information corresponding to the line of the projection of the cursor of the screen in the question in the acquired picture is the text information of the first line of the question.

9. The apparatus of claim 8, wherein the top line determining module comprises:

the digital judgment module is used for judging whether the head end or the tail end of the text information corresponding to the line where the cursor of the screen is projected on the question of the test question is a number;

the first head line text information judging module is used for judging that the text information corresponding to the line of the projection of the cursor of the screen on the question is the text information of the first line of the question when the head end or the tail end of the text information corresponding to the line of the projection of the cursor of the screen on the question is a number, or else, judging that the text information corresponding to the line of the projection of the cursor of the screen on the question is not the text information of the first line of the question;

or,

the inter-line interval comparison module is used for judging whether the interval between the text information corresponding to the line where the cursor of the screen is projected on the question of the test question and the text information of the previous line is larger than a preset inter-line threshold value or not;

and the second first line text information judging module is used for judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is the text information of the first line of the subject when the interval between the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question and the text information of the previous line is greater than a preset threshold value between the lines, and otherwise, judging that the text information corresponding to the line of the projection of the cursor of the screen on the subject of the test question is not the text information of the first line of the subject.

10. The apparatus of claim 8, wherein the apparatus comprises:

a supplementary information obtaining unit, configured to obtain text information of an nth line of titles when the number of searched titles is not 1, and perform title search according to recognition results of the text information of the first to nth lines of titles, where N is an integer and is greater than or equal to 2;

the supplementary information searching unit is used for acquiring and displaying information corresponding to the titles when the number of searched titles is 1; and when the number of searched topics is not 1, acquiring text information of the (N +1) th line of the topics, searching the topics according to the recognition results of the text information of the first to (N +1) th lines of the topics, and repeating the steps until searching the topics according to the recognition results of the text information of all the lines of the topics.