CN111553366B

CN111553366B - Question matching method and system

Info

Publication number: CN111553366B
Application number: CN202010368340.5A
Authority: CN
Inventors: 曾菲
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2020-04-30
Filing date: 2020-04-30
Publication date: 2023-05-16
Anticipated expiration: 2040-04-30
Also published as: CN111553366A

Abstract

The embodiment of the invention relates to the technical field of topic collection, and discloses a topic matching method and system. The method comprises the following steps: the intelligent terminal acquires a target page image and sends the target page image to the server; the server identifies a header part and a footer part in the target page image, and determines search keywords according to the header part and the footer part; the server traverses the index set by utilizing the search keywords, determines a target index, and acquires target topic resources according to the target index; the server identifies the page number and acquires the relation page according to the page number; the intelligent terminal receives the operation track and sends the operation track to the server; and the server determines a frame question area according to the operation track and a preset rule, and obtains frame question contents from the relation page. By implementing the embodiment of the invention, clearer frame question content pictures or character texts can be obtained, and the definition of subsequent wrong question collection or the accuracy of searching answers can be ensured.

Description

Question matching method and system

Technical Field

The invention relates to the technical field of topic collection, in particular to a topic matching method and system.

Background

In order to solve the homework problems of middle and primary schools, at present, a plurality of application programs for searching questions or summarizing wrong questions for solving the homework problems of students appear on the market, and the application programs all shoot the questions through a camera, then obtain frame questions through modes of cutting, frame selection and the like, and further are used for storing wrong questions or searching corresponding answers.

Because the frame content is a picture for error preservation, printing may be unclear when printing and redoing because of camera pixels and other reasons. When the method is used for searching answers, character recognition is needed to find the answers corresponding to the questions, and meanwhile, if the content of the frame questions is unclear, the search is likely to fail or the answers of other questions are likely to be searched.

Disclosure of Invention

Aiming at the defects, the embodiment of the invention discloses a method and a system for matching questions, which are simple to operate and high in efficiency, and pictures of the questions to be collected are obtained through voice.

The first aspect of the embodiment of the invention discloses a method for matching topics, which is applied to an intelligent terminal and comprises the following steps:

the intelligent terminal acquires a target page image and sends the target page image to a server;

the server identifies a header part and a footer part in the target page image, and determines search keywords according to the header part and the footer part, wherein the search keywords are first conditions or first conditions and second conditions; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

The server traverses an index set of the topic resource library by using the search keyword, determines a target index identical to the search keyword, and acquires a corresponding target topic resource in the topic resource library according to the target index;

the server identifies a page number from the header part or the footer part, and acquires a relation page of the target subject resource according to the page number;

the intelligent terminal receives an operation track of a user on a carrier and sends the operation track to a server;

and the server determines a frame question area according to the operation track and a preset rule, and acquires the content with the same position as the frame question area from the relation page as the frame question content.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the determining the search keyword according to the header portion and the footer portion includes:

identifying characters in the header part or/and the footer part, and screening grades and subjects from the characters as a first condition;

detecting whether characters in the header portion or/and footer portion include one or more of a version number, a book name, and a brand name, and if so, taking the one or more of the version number, the book name, and the brand name as a second condition;

Detecting whether one or more of a press and a brand name are included in a non-character part in the header part or/and the footer part, and if so, taking the one or more of the press and the brand name as a second condition;

when the second condition exists, the first condition and the second condition are used as search keywords.

In a first aspect of the present invention, a server traverses an index set of a topic resource library by using the search keyword, determines a target index identical to the search keyword, and obtains a corresponding target topic resource in the topic resource library according to the target index, including:

traversing an index set of the topic resource library by utilizing the search keywords;

taking an index containing all information of the search keywords in an index set of the topic resource library as a target index;

and acquiring the target topic resources in the topic resource library according to the target index and the mapping relation.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, before the receiving, by the intelligent terminal, an operation track of a user on the carrier, the method further includes:

the server identifies characters at any one or more positions of the text of the target page image, and performs similarity comparison with the characters at the same positions in the relation page; when the similarity comparison is greater than or equal to a first threshold, the target question resource corresponding to the relation page is a matching resource corresponding to the target page image;

The step of obtaining the content with the same position as the frame question area in the relation page as the frame question content comprises the following steps:

and acquiring the content with the same position as the frame question area from the relation page of the matching resource as the frame question content.

In an optional implementation manner, in a first aspect of the embodiment of the present invention, the acquiring, by the intelligent terminal, a target page image includes:

and receiving a trigger instruction sent by a user, and starting a camera to photograph the carrier by the intelligent terminal according to the trigger instruction to acquire a target page image.

In an optional implementation manner, in the first aspect of the embodiment of the present invention, the determining, by the server, a frame question area according to the operation track and a preset rule includes:

the server converts the operation track on the carrier into the target page image through coordinates to obtain the operation track on the target page image;

and the server determines a frame question area of the target page image according to the running track and a preset rule.

In a first aspect of the embodiment of the present invention, the obtaining, in the relationship page, the content with the same position as the frame question area as the frame question content includes:

Acquiring all identifications corresponding to a relation page, and selecting a target identification of a position corresponding to the frame question area from all identifications;

acquiring the content corresponding to the target identifier in the relation page according to the target identifier and the mapping relation;

and taking the content corresponding to the target identifier as the frame question content.

The second aspect of the embodiment of the invention discloses a system for matching topics, which comprises an intelligent terminal and a server;

the intelligent terminal comprises:

the first acquisition unit is used for acquiring a target page image and sending the target page image to the server;

the receiving unit is used for receiving the operation track of the user on the carrier and sending the operation track to the server;

the server comprises:

a first identifying unit, configured to identify a header portion and a footer portion in the target page image, and determine a search keyword according to the header portion and the footer portion, where the search keyword is a first condition, or the first condition and a second condition; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

the search unit is used for traversing the index set of the topic resource library by utilizing the search keywords, determining target indexes which are the same as the search keywords, and acquiring corresponding target topic resources in the topic resource library according to the target indexes;

A second identifying unit, configured to identify a page number from the header portion or the footer portion, and obtain a relationship page of the target topic resource according to the page number;

and the second acquisition unit is used for determining a frame question area according to the operation track and a preset rule, and acquiring the content with the same position as the frame question area in the relation page as the frame question content.

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

a first screening subunit, configured to identify characters in the header portion and/or footer portion, and screen grades and subjects from the characters as a first condition;

a second screening subunit detecting whether characters in the header portion or/and footer portion include one or more of a version number, a book name, and a brand name, and if so, taking the one or more of the version number, the book name, and the brand name as a second condition;

a third screening subunit detecting whether one or more of a press and a brand name are included in the non-character portion in the header portion or/and footer portion, and if so, taking the one or more of the press and the brand name as a second condition;

And the judging subunit is used for taking the first condition and the second condition as search keywords when the second condition exists.

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

a query subunit, configured to traverse an index set of the topic resource library using the search keyword;

a first determining subunit, configured to use, as a target index, an index that includes all information of the search keyword in the index set of the topic resource library;

and the mapping subunit is used for acquiring the target topic resources in the topic resource library according to the target index and the mapping relation.

In a second aspect of the embodiment of the present invention, the server further includes a matching unit, configured to identify characters at any one or more positions of the text of the target page image, and perform similarity comparison with characters at the same position in the relationship page; and when the similarity comparison is greater than or equal to a first threshold, the target subject resource corresponding to the relation page is a matching resource corresponding to the target page image.

As an optional implementation manner, in the second aspect of the embodiment of the present invention, the first obtaining unit includes: and the photographing sub-unit is used for receiving a trigger instruction sent by a user, starting a camera to photograph the carrier according to the trigger instruction and obtaining a target page image.

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

the conversion subunit is used for converting the operation track on the carrier into the target page image through coordinates to obtain the operation track on the target page image;

and the second determination subunit is used for determining the frame question area of the target page image according to the running track and the preset rule.

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

a selecting subunit, configured to obtain all identifiers corresponding to a relationship page, and select a target identifier corresponding to the frame question area from all identifiers;

the second mapping subunit is used for acquiring the content corresponding to the target identifier in the relation page according to the target identifier and the mapping relation;

and the third determination subunit is used for taking the content corresponding to the target identifier as the frame question content.

The third aspect of the embodiment of the invention discloses a method for matching topics, which comprises the following steps:

The server identifies a header part and a footer part in the target page image, and compares the header part and the footer part with header and footer detection images stored in a header resource library, wherein the header and footer detection images correspond to the header resources in the header resource library one by one;

if the similarity comparison of the header part and the footer part with the header footer detection image is larger than or equal to a second threshold value, the server takes the topic resource corresponding to the header footer detection image as a target topic resource;

if the similarity comparison between the header part and the footer part and the header and footer detection image is smaller than a second threshold value, the server determines a search keyword according to the header part and the footer part, wherein the search keyword is a first condition or a first condition and a second condition; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

The fourth aspect of the embodiment of the invention discloses a system for matching topics, which comprises an intelligent terminal and a server;

the intelligent terminal comprises:

the server comprises:

the comparison unit is used for identifying a header part and a footer part in the target page image, comparing the header part and the footer part with header footer detection images stored in a header resource library, wherein the header footer detection images correspond to the header resources in the header resource library one by one;

A first judging unit, configured to, if the similarity comparison between the header portion and the footer portion and the header footer detection image is greater than or equal to a second threshold, take a topic resource corresponding to the header footer detection image as a target topic resource;

a second judging unit, configured to determine a search keyword according to the header portion and the footer portion, where the search keyword is a first condition, or the first condition and a second condition, if the similarity comparison between the header portion and the footer portion and the header footer detection image is less than a second threshold; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

the identifying unit is used for identifying page numbers from the header part or the footer part and acquiring a relation page of the target subject resource according to the page numbers;

A fifth aspect of the embodiment of the present invention discloses an intelligent terminal, including:

a memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program code stored in the memory to execute part or all of the steps executed by the intelligent terminal disclosed in the first aspect or the third aspect of the embodiment of the present invention.

A sixth aspect of an embodiment of the present invention discloses a server, including:

a memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program code stored in the memory to perform some or all of the steps performed by the server disclosed in the first aspect or the third aspect of the embodiments of the present invention.

A seventh aspect of the embodiments of the present invention discloses a computer readable storage medium storing a program code, where the program code includes instructions for executing part or all of the steps of any one of the methods disclosed in the first or third aspects of the embodiments of the present invention.

An eighth aspect of the embodiments of the present invention discloses a computer program product which, when run on a computer, causes the computer to perform part or all of the steps of any one of the methods disclosed in the first or third aspects of the embodiments of the present invention.

A ninth aspect of the embodiment of the present invention discloses an application publishing platform, which is configured to publish the computer program product, where the computer program product when run on a computer causes the computer to execute part or all of the steps of any one of the methods disclosed in the first aspect or the third aspect of the embodiment of the present invention.

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

in the embodiment of the invention, the related target topic resources in the topic resource library are identified through the header and footer information. Therefore, by implementing the embodiment of the invention, a clearer frame question content picture or character text can be obtained, and the definition of subsequent wrong question collection or the accuracy of searching answers can be ensured.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for topic matching according to an embodiment of the present invention;

FIG. 2 is a block diagram of a page of an exercise book according to an embodiment of the present invention;

FIG. 3 is a page structure diagram of another exercise book disclosed in an embodiment of the present invention;

FIG. 4 is a page structure diagram of yet another exercise book disclosed in an embodiment of the present invention;

FIG. 5 is a flow chart of another method of topic matching disclosed in an embodiment of the present invention;

FIG. 6 is a schematic diagram of a system for topic matching in accordance with an embodiment of the present invention;

FIG. 7 is a schematic diagram of another topic matching system disclosed in an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an intelligent terminal according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

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

It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a method and a system for matching topics, which can obtain a selection frame by constructing a first straight line and a second straight line according to the starting point coordinate and the end point coordinate of a moving track, are simple and convenient to operate, can ensure the completeness of the topics and improve the user experience, and are described in detail below with reference to the accompanying drawings.

Example 1

Referring to fig. 1, fig. 1 is a flow chart of a method for matching topics disclosed in an embodiment of the present invention, where the matching of topics is completed in the cooperation of an intelligent terminal and a server. The question matching is used for selecting questions and is applied to wrong question collection or answer searching and the like. As shown in fig. 1, the method for matching the questions comprises the following steps:

110. And the intelligent terminal acquires the target page image and sends the target page image to the server.

The target page image is obtained by shooting a certain page of the carrier by the intelligent terminal according to a trigger instruction which is generated by a user and starting the camera by the intelligent terminal.

The triggering instruction may be generated in various manners, for example, through a voice interaction manner, or through opening a question searching application program or a question collecting application program in the intelligent terminal, or starting a corresponding touch key or a mechanical key of the intelligent terminal, or a combination of the various manners.

The intelligent terminal comprises, but is not limited to, a learning machine, a home teaching machine, a point reading machine, a tablet personal computer, a mobile phone and the like, and the camera can be a front camera or a rear camera of the intelligent device or an external camera which is separated from the intelligent terminal and is in communication connection with the intelligent terminal.

The carrier is the carrier of the subject matter. In the embodiment of the invention, the supporting body is mainly an exercise book. The operation body for carrying out frame questions on the supporting body can be fingers, a touch pen, a pencil, a ruler, a small stick and the like, and the operation body can form an operation track or an operation point on the supporting body.

For example, after receiving the target page image, the server may first pre-process the target page image to ensure accuracy of character recognition. Preprocessing includes, but is not limited to, denoising, contrast enhancement, shape correction and the like, wherein the shape correction mainly aims at the problem of camera view angle to shoot a trapezoid image or a curled carrier, the shape correction can be realized by stretching the edge of a target page image and the like, and the finally obtained target page image is rectangular.

120. The server identifies a header part and a footer part in the target page image, and determines search keywords according to the header part and the footer part, wherein the search keywords are first conditions or first conditions and second conditions; the first condition is a grade and subject, and the second condition is one or more of a title, a publisher, a version number, and a brand name.

In the exercise book page image shown in fig. 2, the rank information 211 (i.e., on seven ranks), subject information 212 (i.e., language), version information 213 (i.e., human teaching version), and brand name information 214 (i.e., teaching material full solution) can be acquired in the header portion. In the exercise book page image shown in fig. 3, the page footer part can acquire the grade information 221 (i.e., six-grade upper book), the subject information 222 (i.e., chinese), the brand name information 223 (i.e., talent course), and the title information 224 (i.e., "happy reading bar" guide and refine). In the exercise book page image shown in fig. 4, the grade information 231 (i.e., in three grades), the subject information 232 (i.e., mathematics), and the version information 233 (i.e., R refers to the human teaching edition) can be obtained in the footer portion, and the brand name information 234 (i.e., the child image with doctor cap, refer to the brand name of yellow-back child) can be obtained in the footer portion.

It is known that the exercise book covers the grade and subject information, so that the part of the information is used as a first condition, one or more of a book name, a publisher, a version number and a brand name also exist in the part of the exercise book, the second condition is used as auxiliary second conditions, the first condition and the second condition are inquired when the second condition exists, and the first condition can be directly used for inquiring when the second condition does not exist.

Specifically, characters in the header portion or/and footer portion are identified, and the rank and subject are screened from the characters as a first condition. Illustratively, the recognition of the header and footer portion characters may be accomplished by mature OCR (Optical Character Recognition ) techniques, where the characters are primarily kanji. Since the grades and subjects can be exhausted, the grades and subjects are screened from the characters by arranging a first search library, exhausting all the grade information and subject information and traversing the characters in the header part or/and the footer part, so that the grade and subject information can be obtained.

Detecting whether characters in the header portion or/and footer portion include one or more of a version number, a book name, and a brand name, and if so, taking the one or more of the version number, the book name, and the brand name as a second condition. And setting a second search library for common version names, book names and brand names in the same method as the first condition, traversing characters in a header part or/and a footer part, and obtaining specific second condition information if the second condition exists. In fact, the version numbers are uniform for different regions, so that when a user uses a search problem application or an error collection application, the version number can be determined according to basic information input by the user, which corresponds to the version number being known.

There are exercise books whose press and brand names are implemented using icons, in which case it may be detected whether one or more of the press and brand names are included in the non-character part of the header part or/and footer part, and if so, the one or more of the press and brand names are taken as the second condition. The implementation mode is that the similarity comparison is carried out between the non-character parts identified in the header part or/and the footer part and the icon search library which can be used for exhaustion, for example, the similarity reaches more than 90 percent, and the corresponding press information or brand name information is identified.

For most users, exercise books which are commonly used in a certain period (for example, a learning period) are fixed, the target question resource library is accurately searched and obtained according to the method in the first recognition, namely, the resource library corresponding to the exercise book used by the user is obtained, and in the other use process, the target question resource library can be quickly obtained by randomly selecting one or two pieces of information.

130. The server traverses the index set of the topic resource library by using the search keyword, determines the target index identical to the search keyword, and acquires the corresponding target topic resource in the topic resource library according to the target index.

The title resource library is formed by constructing a large part of existing exercise books into a resource library, a plurality of small resource libraries are stored in the title resource library, each small resource library corresponds to a different exercise book, and in the small resource library, the titles can be stored into character texts in a concentrated manner or into clear picture formats according to the layout mode of the exercise books used by users. If the text is character text, a mapping relation is needed, and the topic content of the corresponding position of the exercise book of the user can be obtained rapidly through the mapping relation.

The index set refers to the resource guide corresponding to each small resource library, and comprises all information of the first condition and the second condition, namely the resource index is not less than the number of search keywords. The resource index may be obtained from the header and footer of the resource exercise book, or from the cover of the exercise book or other locations such as the top page, etc. The resource index is independently stored in the title resource library, and has a mapping relation with the corresponding small resource library, and the corresponding small resource library can be obtained based on the mapping relation and the resource index.

Specifically, traversing an index set of a topic resource library by utilizing the search keyword; taking a resource index containing all information of the search keywords in an index set of the topic resource library as a target index; and acquiring target topic resources (namely a target small resource library) in the topic resource library according to the target index and the mapping relation.

140. The server identifies the page number from the header part or the footer part, and acquires the relation page of the target topic resource according to the page number.

In the text of the exercise book, the page number of the exercise book is displayed in the header portion or the footer portion.

And obtaining a relation page of the target topic resource according to the page number, and obtaining corresponding relation page content through a page mapping relation for the target topic resource in a character text storage mode, wherein for the target topic resource in a picture format storage mode, only the page corresponding to the target topic resource is needed to be found according to the page number.

When the search keywords of the header and footer are too few, a plurality of different target topic resources may be obtained, so in order to avoid this, in the embodiment of the present invention, the obtained target topic resources are screened and confirmed.

Specifically, the server identifies characters at any one or more positions of the text of the target page image, and performs similarity comparison with characters at the same position in the relation page; and when the similarity comparison is greater than or equal to a first threshold, the target subject resource corresponding to the relation page is a matching resource corresponding to the target page image.

For example, a plurality of characters at the starting position and a plurality of characters at the ending position of the text of the target page image can be selected to perform similarity comparison with characters at the same position in the relationship page. For the target question resource in the character text storage mode, the same number of characters as the target page image can be selected from the initial position and the final position of the relation page obtained through the mapping relation; for the target title resource in the picture format storage mode, the same number of characters as the target page image can be selected from the initial position and the final position of the relation page obtained through the page number.

The similarity comparison can convert characters into vectors, the characters are compared through cosine distance or Euclidean distance, when the comparison between the characters at the starting position and the characters at the ending position is larger than a preset first threshold value, for example, 95%, the relationship page is determined to be a page corresponding to the target page image, and the question resource where the relationship page is located is a matching resource corresponding to the target page image, so that the screening and confirmation process of the target question resource is completed.

150. And the intelligent terminal receives the operation track of the user on the carrier and sends the operation track to the server.

The operation track of the user on the carrier can be a closed curve, can also be a line segment, or can be an operation point, and the implementation form of the specific operation track is related to the corresponding preset rule.

160. And the server determines a frame question area according to the operation track and a preset rule, and acquires the content with the same position as the frame question area from the relation page as the frame question content.

After receiving the operation track, the server converts the operation track on the carrier into a target page image in a coordinate transformation mode such as affine transformation, so as to form a running track of the target page image, and determines a frame question area in the target page image through the running track and a preset rule.

For example, for a closed curve, the preset rule may be that the closed curve itself is a selection box, and the content inside the selection box is a box question area. For a line segment, the preset rule may be that the content covered by the line segment is a frame question area, or that the line segment is a diagonal line, and a formed rectangle is constructed as the frame question area; for an operating point, the predetermined rule may be that a portion within a predetermined range above or below the point is a frame question area.

And acquiring the content with the same position as the frame question area from the relation page as the frame question content.

For the relation page of character text storage, all identifiers in the relation page can be acquired first, each identifier in all identifiers corresponds to an area on an exercise book, and the topic content of each identifier in the relation page can be obtained through the identifiers and the mapping relation.

Selecting the mark of the corresponding position of the frame question area and marking the mark as a target mark, obtaining the question content corresponding to the target mark according to the target mark and the mapping relation, and using the question content as the frame question content to be used for wrong question storage or answer searching.

For the relation page stored in the root mode of the picture, the target page image and the relation page can be converted into the same size or the size proportion of the target page image and the relation page can be obtained, the position of the corresponding relation page is obtained based on the position of the frame question area in the target page image, the question content can be obtained through the corresponding frame question area in the relation page, and the question content can be used as the frame question content for wrong question storage or answer searching.

By implementing the embodiment of the invention, the related target question resources in the question resource library can be identified through the header and footer information, so that a clearer frame question content picture or character text can be obtained, and the definition of subsequent wrong question collection or the accuracy of searching answers can be ensured.

Example two

Referring to fig. 5, fig. 5 is a flow chart of a method for matching questions disclosed in an embodiment of the invention, wherein the matching questions are all completed in an intelligent terminal. As shown in fig. 5, the method for matching the questions includes the following steps:

310. and the intelligent terminal acquires the target page image and sends the target page image to the server.

320. The server identifies header and footer portions in the target page image.

330. And comparing the header portion and the footer portion with header and footer detection images stored in the header resource library, wherein the header and footer detection images are in one-to-one correspondence with the header resources in the header resource library, and if the similarity comparison of the header portion and the footer portion with the header and footer detection images is greater than or equal to a second threshold value, executing step 340, otherwise executing step 350.

Generally, the images of the page and footer portions of the exercise book are substantially unchanged throughout the body portion of the exercise book, except for page changes. Based on this, the target header resource can be quickly determined by comparing both the header portion and the footer portion with the header footer detection image stored in the header resource library. The header and footer detection images are formed by forming header and footer of any number in the text of the corresponding exercise book in the header resource library according to a preset rule, wherein the preset rule adopts the same rule as that of the header part and the footer part identified by the target page image, for example, if the header and the footer are divided into dividing lines, the image is divided by taking the dividing lines as selected boundaries, and if one or two of the header and the footer are not divided into dividing lines, the image is divided by the boundary with the text part.

The image comparison may be implemented by using a mean shift algorithm, when the header portion and the footer portion of the target page image are compared with the header detection image and the footer detection image respectively, when the similarity of the header portion and the footer portion reaches a second threshold, for example 80%, step 340 is executed, otherwise, if more interference information such as famous dialects appears in the exercise book, one or all of the similarity of the header portion and the footer portion may not reach the second threshold, and step 350 is executed.

340. And the server takes the topic resource corresponding to the header footer detection image as a target topic resource.

When the similarity between the header portion and the footer portion of the target page image and the header detection image and the footer detection image respectively reach the second threshold, the topic resource (small resource library) corresponding to the header and the footer detection image is considered to be the target topic resource corresponding to the target page image, and then step 370 is executed.

350. The server determines a search keyword according to the header part and the footer part, wherein the search keyword is a first condition or a first condition and a second condition; the first condition is a grade and subject, and the second condition is one or more of a title, a publisher, a version number, and a brand name.

360. The server traverses the index set of the topic resource library by using the search keyword, determines the target index identical to the search keyword, and acquires the corresponding target topic resource in the topic resource library according to the target index.

370. The server identifies the page number from the header part or the footer part, and acquires the relation page of the target subject resource according to the page number

380. And the intelligent terminal receives the operation track of the user on the carrier and sends the operation track to the server.

390. And the server determines a frame question area according to the operation track and a preset rule, and acquires the content with the same position as the frame question area from the relation page as the frame question content.

Step 310 is similar to step 110 in the first embodiment, step 320 is similar to part of the content of step 120 in the first embodiment, step 350 is similar to part of the content of step 120 in the first embodiment, and steps 360 to 390 are similar to steps 130 to 160 in the first embodiment, and will not be repeated here.

Example III

Referring to fig. 6, fig. 6 is a schematic structural diagram of a system for matching topics disclosed in an embodiment of the present invention, which is applied to an intelligent terminal. As shown in fig. 6, the topic matching system may include an intelligent terminal 400 and a server 500;

the intelligent terminal 400 includes:

a first obtaining unit 410, configured to obtain a target page image, and send the target page image to a server;

a receiving unit 420, configured to receive an operation track of a user on a carrier, and send the operation track to a server;

the server 500 includes:

a first identifying unit 510, configured to identify a header portion and a footer portion in the target page image, and determine a search keyword according to the header portion and the footer portion, where the search keyword is a first condition, or the first condition and a second condition; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

the searching unit 520 is configured to traverse an index set of the topic resource library by using the search keyword, determine a target index identical to the search keyword, and obtain a corresponding target topic resource in the topic resource library according to the target index;

A second identifying unit 530, configured to identify a page number from the header portion or footer portion, and obtain a relationship page of the target topic resource according to the page number;

the second obtaining unit 540 is configured to determine a frame question area according to the operation track and a preset rule, and obtain, in the relationship page, a content with the same position as the frame question area as a frame question content.

As an alternative embodiment, the first identifying unit 510 includes:

a first screening subunit 511 configured to identify characters in the header portion or/and footer portion, screen ranks and subjects from the characters, as a first condition;

a second screening subunit 512, configured to detect whether the characters in the header portion or/and footer portion include one or more of a version number, a title, and a brand name, and if so, take the one or more of the version number, the title, and the brand name as a second condition;

a third screening subunit 513 detecting whether one or more of a press and a brand name are included in the non-character portion in the header portion or/and footer portion, and if so, regarding one or more of the press and the brand name as a second condition;

And the judging subunit 514 is configured to take the first condition and the second condition as the search keywords when the second condition exists.

As an alternative embodiment, the search unit 520 includes:

a query subunit 521, configured to traverse an index set of the topic resource library using the search keyword;

a first determining subunit 522, configured to take, as a target index, an index that includes all information of the search keyword in the index set of the topic resource library;

the first mapping subunit 523 is configured to obtain a target topic resource in the topic resource library according to the target index and the mapping relationship.

As an optional implementation manner, the server further includes a matching unit 550, configured to identify characters at any one or more positions of the text of the target page image, and perform similarity comparison with characters at the same position in the relationship page; and when the similarity comparison is greater than or equal to a first threshold, the target subject resource corresponding to the relation page is a matching resource corresponding to the target page image.

As an alternative embodiment, the first obtaining unit 410 includes: the photographing sub-unit 411 is configured to receive a trigger instruction sent by a user, and start a camera to photograph the carrier according to the trigger instruction, so as to obtain a target page image.

As an alternative embodiment, the second obtaining unit 540 includes:

a conversion subunit 541, configured to convert, by coordinates, an operation track on the carrier to an upper position in the target page image, so as to obtain a running track on the target page image;

and a second determining subunit 542, configured to determine a question area of the target page image according to the running track and a preset rule.

As an optional embodiment, the second obtaining unit 540 further includes:

a selecting subunit 543, configured to obtain all identifiers corresponding to the relationship page, and select a target identifier corresponding to the frame question area from the all identifiers;

a second mapping subunit 544, configured to obtain, according to the target identifier and the mapping relationship, content corresponding to the target identifier in the relationship page;

a third determining subunit 545, configured to take the content corresponding to the target identifier as the frame question content.

The system for matching the questions shown in fig. 6 can identify related target question resources in the question resource library through header and footer information, so as to obtain clearer frame content pictures or character texts, and ensure the definition of subsequent wrong question collection or the accuracy of searching answers.

Example IV

Referring to fig. 7, fig. 7 is a schematic structural diagram of another system for matching topics disclosed in the embodiment of the present invention, which is applied to an intelligent terminal. As shown in fig. 7, the topic matching system may include a smart terminal 600 and a server 700;

the intelligent terminal 600 includes:

a first acquiring unit 610, configured to acquire a target page image, and send the target page image to a server;

a receiving unit 620, configured to receive an operation track of a user on a carrier, and send the operation track to a server;

the server 700 includes:

a comparison unit 710, configured to identify a header portion and a footer portion in the target page image, and compare the header portion and the footer portion with header footer detection images stored in a header resource library, where the header footer detection images correspond to the header resources in the header resource library one by one;

a first judging unit 720, configured to, if the similarity comparison between the header portion and the footer portion and the header footer detected image is greater than or equal to a second threshold, take a topic resource corresponding to the header footer detected image as a target topic resource;

a second judging unit 730, configured to determine a search keyword according to the header portion and the footer portion, where the search keyword is a first condition, or the first condition and a second condition, if the similarity ratio between the header portion and the footer portion and the header footer detected image is less than a second threshold; the first condition is a grade and a subject, and the second condition is one or more of a book name, a press, a version number and a brand name;

The searching unit 740 is configured to traverse an index set of the topic resource library by using the search keyword, determine a target index identical to the search keyword, and obtain a corresponding target topic resource in the topic resource library according to the target index;

an identifying unit 750, configured to identify a page number from the header portion or footer portion, and obtain a relationship page of a target topic resource according to the page number;

and a second obtaining unit 760, configured to determine a frame question area according to the operation track and a preset rule, and obtain, in the relationship page, a content identical to the position of the frame question area as a frame question content.

The system for matching the questions shown in fig. 7 can identify related target question resources in the question resource library through header and footer information, so as to obtain clearer frame content pictures or character texts, and ensure the definition of subsequent wrong question collection or the accuracy of searching answers.

Example five

Referring to fig. 8, fig. 8 is a schematic structural diagram of an intelligent terminal according to an embodiment of the present invention. The intelligent terminal can be a learning machine, a home teaching machine, a point-reading machine, a tablet computer or a mobile phone, etc. As shown in fig. 8, the intelligent terminal 800 may include:

A memory 810 storing executable program code;

a processor 820 coupled to the memory 810;

wherein processor 820 invokes executable program code stored in memory 810 to perform some or all of the steps performed by the intelligent terminal in either embodiment one or embodiment two.

Example six

Referring to fig. 9, fig. 9 is a schematic structural diagram of a server according to an embodiment of the invention. As shown in fig. 9, the server 900 may include:

a memory 910 storing executable program code;

a processor 920 coupled with the memory 910;

wherein the processor 920 invokes executable program code stored in the memory 910 to perform some or all of the steps performed by the server in embodiment one or embodiment two.

The embodiment of the invention discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute part or all of the steps in the method for matching the questions in any one of the first embodiment and the second embodiment.

The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the method for matching the questions in any one of the first embodiment or the second embodiment.

The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing the computer program product, and when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the method for matching the questions in any one of the first embodiment and the second embodiment.

In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

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

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.

In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.

Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data that is readable by a computer.

The foregoing has described in detail a method and system for topic matching disclosed in embodiments of the present invention, and specific examples have been employed herein to illustrate the principles and implementations of the present invention, the above examples being provided only to assist in understanding the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method of topic matching comprising:

the server determines a frame question area according to the operation track and a preset rule, and obtains the content with the same position as the frame question area in the relation page as frame question content;

the intelligent terminal receives an operation track of a user on a carrier, and before the operation track, the intelligent terminal further comprises:

2. The method of claim 1, wherein the determining search keywords from the header portion and footer portion comprises:

3. The method of claim 1, wherein the server traversing the index set of the topic resource library using the search keyword, determining a target index that is the same as the search keyword, and obtaining a corresponding target topic resource in the topic resource library from the target index, comprising:

4. A method according to any one of claims 1-3, wherein the intelligent terminal obtaining a target page image comprises:

5. The method of claim 4, wherein the server determining a box question area according to the operation trajectory and a preset rule, comprising:

6. The method of claim 4, wherein obtaining the same content as the frame question area location in the relationship page as frame question content comprises:

7. The title matching system is characterized by comprising an intelligent terminal and a server;

the intelligent terminal comprises:

the server comprises:

The second acquisition unit is used for determining a frame question area according to the operation track and a preset rule, and acquiring the content with the same position as the frame question area in the relation page as frame question content;

8. The system of claim 7, wherein the first identification unit comprises:

9. The system of claim 7, wherein the search unit comprises:

and the first mapping subunit is used for acquiring the target topic resources in the topic resource library according to the target index and the mapping relation.

10. The system of claim 7, wherein the server further comprises a matching unit for identifying characters at any one or more positions of the target page image text and performing similarity comparison with characters at the same position in the relationship page; and when the similarity comparison is greater than or equal to a first threshold, the target subject resource corresponding to the relation page is a matching resource corresponding to the target page image.

11. The system according to any one of claims 7-10, wherein the first acquisition unit comprises: and the photographing sub-unit is used for receiving a trigger instruction sent by a user, starting a camera to photograph the carrier according to the trigger instruction and obtaining a target page image.

12. The system of claim 11, wherein the second acquisition unit comprises:

13. The system of claim 11, wherein the second acquisition unit further comprises:

14. A method of topic matching comprising:

15. The title matching system is characterized by comprising an intelligent terminal and a server;

the intelligent terminal comprises:

the server comprises: