Question search method, device, terminal device and readable storage medium

Abstract

The present application belongs to the field of question searching, and in particular, relates to a question searching method, apparatus, terminal device, and readable storage medium. The question searching method of the present application includes: obtaining an image of a page title, the page title includes a question to be searched; determining images of multiple questions based on the image of the page title; determining book information corresponding to the question to be searched based on the images of the multiple questions; and determining target question information corresponding to the question to be searched based on the book information. That is, the present application can obtain an image of the page title, and then determine images of multiple questions, determine book information corresponding to the question to be searched based on the images of the multiple questions; and determine target question information corresponding to the question to be searched based on the book information, so as to improve the accuracy of the question searching results.

Description

Technical Field

[0001] The present application relates to the field of question searching, and in particular to a question searching method, apparatus, terminal device and readable storage medium. Background Art

[0002] In the existing photo-taking search technology, a user usually clicks or frames a question to be searched for optical character recognition (OCR) and searches for the question.

[0003] The problem with this method is that when only the OCR text information of one question is used to search in a question bank with a large number of questions and a large number of similar questions, some key information in the question will be recognized incorrectly, resulting in a decrease in the accuracy of the search results and the failure to search out the original question. Summary of the invention

[0004] The embodiments of the present application provide a question search method, apparatus, terminal device and readable storage medium to improve the accuracy of question search results.

[0005] In a first aspect, an embodiment of the present application provides a question search method, comprising:

[0006] Obtaining an image of a page title, wherein the page title includes a title to be searched;

[0007] Determining images of multiple questions based on the image of the page title;

[0008] Determining book information corresponding to the plurality of questions according to the images of the plurality of questions;

[0009] Based on the book information, target topic information corresponding to the topic to be searched is determined.

[0010] In a possible implementation of the first aspect, after acquiring the image of the page title, the method further includes:

[0011] Detecting the image of the page title and obtaining text boxes of the multiple questions;

[0012] According to the multiple text boxes, coordinate information of the multiple text boxes is determined.

[0013] Wherein, determining the images of multiple questions according to the image of the page title includes:

[0014] The image of the page title is segmented according to the coordinate information of the plurality of text boxes to determine the images of the plurality of titles.

[0015] Wherein, determining the book information corresponding to the plurality of questions according to the images of the plurality of questions includes:

[0016] Recognize the images of the plurality of questions and obtain text information of the plurality of questions;

[0017] Searching for document information related to text information of multiple questions in a preset index library, wherein the preset index library contains document information corresponding to each question, and the document information corresponding to each question includes text information of the question, book information corresponding to the text information of the question, and page number information of the text information of the question in the book;

[0018] Based on the document information, book information corresponding to the plurality of questions is determined.

[0019] The searching for document information related to the text information of the multiple questions includes:

[0020] Determining the relevance between the text information of the plurality of questions and the document information in the preset index library according to a preset relevance operator;

[0021] The document information related to the text information of the plurality of questions is determined according to the relevance.

[0022] Wherein, determining the book information corresponding to the plurality of questions based on the document information includes:

[0023] Counting the number of times the book information corresponding to the text information of the plurality of questions appears in the document information related to the text information of the plurality of questions;

[0024] According to the number of times, the book information corresponding to the text information of the multiple questions is sorted to obtain the sequentially sorted book information, and the sequentially sorted book information is determined as the book information corresponding to the multiple questions.

[0025] Wherein, determining the target title information corresponding to the title to be searched based on the book information includes:

[0026] Searching for document information related to the text information of the topic to be searched in the document information corresponding to the book information arranged in sequence;

[0027] When searching, increase the weight of the book information with the maximum number of times;

[0028] According to the weights of the book information arranged in sequence, the target topic information corresponding to the topic to be searched is determined.

[0029] In a second aspect, an embodiment of the present application provides a question searching device, comprising:

[0030] An acquisition module, used to acquire an image of a page title, wherein the page title includes a title to be searched;

[0031] A first determination module, used to determine images of multiple questions according to the image of the page title;

[0032] A second determination module, configured to determine book information corresponding to the plurality of questions based on the images of the plurality of questions;

[0033] The third determination module is used to determine the target title information corresponding to the title to be searched based on the book information.

[0034] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the question searching method as described in any one of the first aspects when executing the computer program.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein the computer program, when executed by a processor, implements the question-searching method as described in any one of the first aspects.

[0036] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the embodiments of the present application obtain an image of a page title, which contains a title to be searched; based on the image of the page title, images of multiple titles are determined; based on the images of the multiple titles, book information corresponding to the multiple titles is determined; based on the book information, target title information corresponding to the title to be searched is determined. That is, the present application obtains an image of a page title, and then can determine images of multiple titles; based on the images of the multiple titles, book information corresponding to the multiple titles is determined; based on the book information, target title information corresponding to the title to be searched is determined, which improves the accuracy of searching for titles compared to searching in a question bank with a large number of titles and a large number of similar titles using only the OCR text information of one title. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is a schematic diagram of an application scenario of the question search method provided in one embodiment of the present application;

[0039] Figure 2 is a schematic flow chart of a method for determining target topic information corresponding to a topic to be searched provided by an embodiment of the present application;

[0040] Figure 3 is a schematic flow chart of a method for detecting an image of a page title provided by an embodiment of the present application;

[0041] Figure 4 is a schematic flow chart of a method for determining book information corresponding to multiple questions provided in an embodiment of the present application;

[0042] Figure 5 is a schematic flow chart of a method for searching document information related to text information of multiple questions provided in an embodiment of the present application;

[0043] Figure 6 is a schematic flow chart of a method for determining book information corresponding to multiple questions provided in an embodiment of the present application;

[0044] Figure 7 It is a structural schematic diagram of a question-searching device provided in an embodiment of the present application;

[0045] Figure 8 It is a structural diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are proposed for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application. In other cases, the specific technical details of each embodiment may be referenced to each other, and a specific system not described in one embodiment may be referenced to other embodiments.

[0047] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0048] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0049] References to "an embodiment of the present application" or "some embodiments" described in the specification of the present application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in other embodiments", "an embodiment of the present application", "other embodiments of the present application", etc. that appear in different places in the specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0050] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0051] In the existing photo-taking search technology, a user usually clicks or frames a question to be searched for optical character recognition (OCR) and searches for the question.

[0052] The problem with this method is that when only the OCR text information of one question is used to search in a question bank with a large number of questions and a large number of similar questions, some key information in the question will be recognized incorrectly, resulting in a decrease in the accuracy of the search results and the failure to search out the original question.

[0053] In order to solve the above-mentioned defects, the inventive concept of the present application is as follows:

[0054] The present application can obtain an image of a page title and then determine images of multiple questions, and determine book information corresponding to the multiple questions based on the images of the multiple questions; based on the book information, determine target question information corresponding to the question to be searched, which improves the accuracy of question search compared to using only the OCR text information of one question to search in a question bank with a massive number of questions and a large number of similar questions.

[0055] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0056] Please refer to Figure 1 , Figure 1 This is a schematic diagram of an application scenario of the topic search method provided in an embodiment of the present application. For the convenience of explanation, only the part related to the present application is shown. The application scenario includes: a terminal device 100 and a page topic 200.

[0057] The terminal device 100 includes a scanning pen, a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The embodiment of the present application does not impose any limitation on the specific type of the terminal device.

[0058] The page title 200 in the embodiment of the present application can be the title of a whole page in a book, or multiple questions in a whole page, or multiple questions in a test paper, or multiple questions written temporarily. Exemplarily, the page title 200 includes three questions A, B and C. Among them, question B is the question to be searched.

[0059] The title in the embodiment of the present application can be a printed font or a handwritten font, and the embodiment of the present application does not limit the font type of the title.

[0060] The terminal device mainly obtains the image of the page title 200, and then can determine the images of multiple questions (A, B and C), and determine the book information corresponding to the multiple questions based on the images of the multiple questions; based on the book information, determine the target title information corresponding to the title to be searched.

[0061] For the method of determining the target topic information corresponding to the topic to be searched in the embodiment of the present application, please refer to Figure 2 , Figure 2 It is a schematic flowchart of a method for determining target topic information corresponding to a topic to be searched provided in an embodiment of the present application. Figure 2 The execution subject of the method in can be Figure 1 The terminal device 100 in FIG. Figure 2 As shown, the method includes: S201 to S204.

[0062] S201, obtaining an image of a page title.

[0063] Specifically, the page title includes the title to be searched.

[0064] A photographic component is usually configured in a terminal device. In the embodiment of the present application, the terminal device can obtain an image of a page title through the photographic component. The embodiment of the present application does not limit the type of the photographic component.

[0065] In the embodiment of the present application, after obtaining the image of the page title, the obtained image needs to be preprocessed, and the preprocessing includes graying, binarization, smoothing and other processing. The purpose of the preprocessing is to correct the obtained image and unify the specifications. The embodiment of the present application does not limit the method of preprocessing.

[0066] In the embodiment of the present application, after the image of the page title is preprocessed, the image of the page title needs to be detected. For a method of detecting the image of the page title, please refer to Figure 3 , please refer to Figure 3 , Figure 3 It is a schematic flow chart of a method for detecting an image of a page title provided in an embodiment of the present application. Figure 3 The execution subject of the method in can be Figure 1 The terminal device 100 in FIG. Figure 3 As shown, the method includes: S301 to S302.

[0067] S301, detecting the image of the page title and obtaining text boxes of multiple questions.

[0068] Specifically, the embodiment of the present application can detect the image of the page title through OCR technology to obtain the text boxes in the multiple images.

[0069] For example: the image of the page title includes three questions A, B, and C, where B is the question to be searched. The image of the page title is detected to obtain text boxes of multiple questions, that is, text boxes of two questions A and B, or two questions A and C, or two questions B and C, or three questions A, B and C.

[0070] It should be noted that: multiple questions may or may not contain questions to be searched.

[0071] In some embodiments, when detecting an image of a page title, the text area of ​​multiple titles in the image is located, and then the text is marked in the form of a text box. In some embodiments, the text box can be a rectangular box. In the embodiment of the present application, a detection model based on deep learning can be used to detect text, such as an efficient and accurate scene text model (Efficient and Accuracy Scene Text, EAST), etc.

[0072] S302: Determine coordinate information of the multiple text boxes according to the multiple text boxes.

[0073] Specifically, when detecting the image of the page title through OCR technology, the image of the page title can be first processed by grayscale, binarization, etc., and then the outline of the area where multiple questions (for example, questions A and C) are located is queried, the area where the multiple questions are located is screened out, and finally the area where the multiple questions are located is marked with text boxes to generate coordinate information of multiple text boxes.

[0074] Exemplarily, when the text box is a rectangular box, the coordinate information is the coordinate information of the four vertices of the rectangular box.

[0075] S202: Determine images of multiple questions based on the image of the page title.

[0076] Specifically, the image of the page title includes the image of the title to be searched.

[0077] In the embodiment of the present application, the method for determining the images of multiple questions according to the image of the page title is:

[0078] According to the coordinate information of the multiple text boxes, the image of the page title is segmented to determine the images of the multiple questions.

[0079] In some embodiments, the terminal device can segment the image of the page title by a threshold-based segmentation method, an edge-based segmentation method, a region-based segmentation method, an image segmentation method based on cluster analysis, a wavelet transform-based segmentation method, a mathematical morphology-based segmentation method, or an artificial neural network-based segmentation method to determine the images of multiple questions. The embodiments of the present application do not limit the image segmentation method.

[0080] S203: Determine book information corresponding to the multiple questions according to the images of the multiple questions.

[0081] Specifically, in some embodiments, when determining the book information corresponding to multiple questions, the images of the multiple questions can be input into a trained neural network model. In the neural network model, the text information in the images of the multiple questions is identified, and based on the text information of the multiple questions, multiple word segments of each question in the multiple questions are obtained. Then, based on the word frequency values ​​of each word segment in multiple different books, book recognition is performed on the text information of the multiple questions to determine the book information corresponding to the multiple questions.

[0082] The training method of the neural network model is:

[0083] The text information of the sample questions is obtained, and the corresponding book information is marked in the text information of the sample questions.

[0084] The text information of the sample questions is input into the neural network model for training.

[0085] In the neural network model, multiple word segments of the sample title and the word frequency values ​​of each word segment in different books are obtained.

[0086] According to the word frequency values ​​of each word segment in different books, book recognition is performed on the text information of the sample title. If the recognition result is inconsistent with the marked book information, the word frequency values ​​of each word segment in different books are adjusted to obtain the adjusted word frequency values.

[0087] After the adjustment, book recognition is performed again according to the adjusted word frequency values ​​corresponding to each word segment in different books. The adjustment and recognition is a cyclic process until the adjusted word frequency values ​​can make the book recognition result consistent with the book mark.

[0088] Through the above process, after training a certain number of sample questions, more accurate word segmentation of the questions and the corresponding word frequency values ​​of different books can be obtained, so that when the question of an unknown book is subsequently recognized, the book to which the question belongs can be accurately identified.

[0089] In other embodiments, determining the book information corresponding to the multiple questions refers to Figure 4 , Figure 4 It is a schematic flow chart of a method for determining book information corresponding to multiple questions provided in an embodiment of the present application. Figure 4 The execution subject of the method in can be Figure 1 The terminal device 100 in FIG. Figure 4 As shown, the method includes: S401 to S403.

[0090] S401, recognizing images of multiple questions and obtaining text information of the multiple questions.

[0091] Specifically, the embodiments of the present application can identify multiple groups of segmented images through OCR technology to obtain text information in the multiple groups of segmented images.

[0092] In some embodiments, recognizing the images of multiple questions is recognizing the text in the text box. In the embodiments of the present application, a recognition model based on deep learning can be used to recognize the text, for example, a residual neural network model ResNet.

[0093] In other embodiments, when recognizing images of multiple questions, text detection and text recognition can also be implemented in a network structure, such as a Fast Oriented Text Spotting with a Unified Network (FOTS) model.

[0094] S402: Searching for document information related to the text information of the multiple questions in a preset index library.

[0095] Specifically, the preset index library contains document information corresponding to each question, and the document information corresponding to each question includes text information of the question, book information corresponding to the text information of the question, and page number information of the text information of the question in the book.

[0096] In the embodiment of the present application, the method for constructing the preset index library is:

[0097] For each question, the subject information corresponding to each question is used to construct an index document. If there are m questions in all books involved in the basic education stage, then m index documents are constructed, and the m index documents constitute the preset index library.

[0098] All books involved in the basic education stage in the embodiment of the present application include textbooks, exercise books, exercise books, test papers, etc.

[0099] The traditional question search method needs to search and identify in the traditional question bank, which includes questions from all books on the market. The number of question banks is very large, resulting in excessive calculation during the search, long search time and low recognition accuracy. The question search method provided in the embodiment of the present application can search and identify in a preset index library, which only includes questions included in all books involved in the basic education stage. Compared with the traditional subject recognition method, it can reduce the amount of calculation, save search time, and improve recognition accuracy.

[0100] For methods to search for document information related to the text information of multiple questions, please refer to Figure 5 , Figure 5 It is a schematic flow chart of a method for searching document information related to text information of multiple questions provided in an embodiment of the present application. Figure 5 The execution subject of the method in can be Figure 1 The terminal device 100 in FIG. Figure 5 As shown, the method includes: S501 to S502.

[0101] S501. Determine the relevance between text information of a plurality of questions and document information in a preset index library according to a preset relevance operator.

[0102] Specifically, the preset relevance operator in the embodiment of the present application may be a weighted algorithm (Term Frequency–Inverse Document Frequency, TF-IDF) for information retrieval and data mining, or may be an algorithm BM25 based on a probability model.

[0103] In an embodiment of the present application, a preset relevance operator is used to score the similarity between the text information of multiple questions and the document information in the preset index library, and the relevance between the text information of multiple questions and the document information in the preset index library can be determined based on the score.

[0104] S502: Determine document information related to the text information of the multiple questions based on the relevance.

[0105] For example, 10 pieces of document information are stored in the preset index library, and according to the preset relevance operator, the scores of the text information of a question and the 10 pieces of document information are calculated to be 0, 0.1, 0.45, 0, 0.6, 0.7, 0.8, 0.6, 0, and 0, respectively. Then, the document information related to the text information of the question is all the document information except the document information with a score of 0.

[0106] By using the above method, document information related to the text information of multiple questions can be determined.

[0107] S403: Determine book information corresponding to the multiple questions based on the document information.

[0108] Specifically, to determine the book information corresponding to multiple questions based on document information, please refer to Figure 6 , Figure 6 It is a schematic flow chart of a method for determining book information corresponding to multiple questions provided in an embodiment of the present application. Figure 6 The execution subject of the method in can be Figure 1 The terminal device 100 in FIG. Figure 6 As shown, the method includes: S601 to S602.

[0109] S601: Count the number of times that book information corresponding to the text information of the multiple questions appears in the document information related to the text information of the multiple questions.

[0110] For example, there are 5 questions A, B, C, D and E in the page title image. According to the method in S502, it is determined that the book information corresponding to the text information of question A is a Chinese textbook, a Chinese workbook and an English workbook, the book information corresponding to question B is a Chinese textbook and a mathematics textbook, the book information corresponding to question C is a Chinese textbook, a Chinese workbook, an English textbook and a mathematics workbook, the book information corresponding to question D is a Chinese textbook and a history textbook, and the book information corresponding to question E is a Chinese textbook and a history workbook. Then, the number of times the book information corresponding to the 5 questions appears is respectively: Chinese textbook 5 times, Chinese workbook 2 times, English workbook 1 time, mathematics textbook 1 time, English textbook 1 time, mathematics workbook 1 time, history textbook 1 time, and history workbook 1 time.

[0111] S602. Sort the book information corresponding to the text information of the multiple questions according to the number of times to obtain the sequentially sorted book information, and determine the sequentially sorted book information as the book information corresponding to the multiple questions.

[0112] Specifically, according to the number of times obtained in S601, the book information corresponding to the text information of the title is sorted to obtain the book information arranged in sequence.

[0113] S204: Determine target title information corresponding to the title to be searched based on the book information.

[0114] In some embodiments, based on the book information, a method for determining the target topic information corresponding to the topic to be searched is:

[0115] In the document information corresponding to the book information arranged in sequence, the document information related to the text information of the subject to be searched is searched.

[0116] Specifically, the search method in the embodiment of the present application is the same as the search method in S402, and will not be repeated here.

[0117] The difference from S402 is: 1. S402 searches in a preset index library, which contains all the questions in all the books involved in the basic education stage, while S204 only contains all the questions in the books arranged in sequence, which reduces the search scope and improves the search accuracy.

[0118] 2. When searching, increase the weight of the book information with the maximum number of times.

[0119] In some embodiments, when searching for document information related to the text information of the topic to be searched, the scores of the document information corresponding to the text information of the topic to be searched and the book information arranged in sequence are calculated based on a preset relevance operator, and when calculating the scores, the weight of the book information with the largest number of times is increased.

[0120] Exemplarily, the book information arranged in sequence is: Chinese textbook 5 times, Chinese exercise book 2 times, English exercise book 1 time, mathematics textbook 1 time, English textbook 1 time, mathematics exercise book 1 time, history textbook 1 time, and history exercise book 1 time.

[0121] Before the weight is increased, when calculating the text information of the question to be searched and the document information corresponding to the Chinese textbook, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the Chinese exercise book, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the English exercise book, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the mathematics exercise book, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the English textbook, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the mathematics exercise book, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the history textbook, the weight is set to 1; when calculating the text information of the question to be searched and the document information corresponding to the history exercise book, the weight is set to 1.

[0122] When the weight is increased, when calculating the text information of the question to be searched and the document information corresponding to the Chinese textbook, the weight is set to 3.5, when calculating the text information of the question to be searched and the document information corresponding to the Chinese exercise book, the weight is set to 1, when calculating the text information of the question to be searched and the document information corresponding to the English exercise book, the weight is set to 1, when calculating the text information of the question to be searched and the document information corresponding to the mathematics exercise book, the weight is set to 1, when calculating the text information of the question to be searched and the document information corresponding to the English textbook, the weight is set to 1, when calculating the text information of the question to be searched and the document information corresponding to the mathematics exercise book, the weight is set to 1, when calculating the text information of the question to be searched and the document information corresponding to the history textbook, the weight is set to 1, and when calculating the text information of the question to be searched and the document information corresponding to the history exercise book, the weight is set to 1.

[0123] In the embodiment of the present application, the preset relevance operator is to adjust the weight by setting the weight parameter boost. The purpose of increasing the weight of the book information with the maximum number of times is to make the score value of the document information corresponding to the text information of the title to be searched and the book information with the maximum number of times greater than the score value of the document information corresponding to the book information with other times.

[0124] According to the weights of the book information arranged in sequence, the target topic information corresponding to the topic to be searched is determined.

[0125] Specifically, after the weights of the sequentially arranged book information are determined, the target title information corresponding to the to-be-searched title can be determined in the document information corresponding to the sequentially arranged book information according to a preset relevance operator.

[0126] In summary, the embodiment of the present application obtains an image of a page title, which includes a title to be searched; determines images of multiple titles based on the image of the page title; determines book information corresponding to the multiple titles based on the images of the multiple titles; and determines target title information corresponding to the title to be searched based on the book information. That is, the present application obtains an image of a page title, and then determines images of multiple titles; determines book information corresponding to the multiple titles based on the images of the multiple titles; and determines target title information corresponding to the title to be searched based on the book information. Compared with searching in a question bank with a large number of titles and a large number of similar titles using only the OCR text information of one title, the accuracy of the search is improved.

[0127] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0128] Please refer to Figure 7 , Figure 7 The invention is a question-searching device, comprising:

[0129] The acquisition module 71 acquires an image of a page title, where the page title includes a title to be searched.

[0130] A first determination module 72 is used to determine images of multiple questions based on the image of the page title;

[0131] A second determination module 73 is used to determine book information corresponding to the multiple questions based on the images of the multiple questions;

[0132] The third determination module 74 is used to determine target topic information corresponding to the topic to be searched based on the book information.

[0133] The device also includes:

[0134] A detection module is used to detect the image of the page title and obtain the text boxes of multiple questions;

[0135] According to the multiple text boxes, coordinate information of the multiple text boxes is determined.

[0136] The first determination module 72 is further used to segment the image of the page title according to the coordinate information of the multiple text boxes, and determine the images of the multiple titles.

[0137] The second determination module 73 is further used to recognize the images of the multiple questions and obtain the text information of the multiple questions;

[0138] Searching for document information related to text information of multiple questions in a preset index library, wherein the preset index library contains document information corresponding to each question, and the document information corresponding to each question includes text information of the question, book information corresponding to the text information of the question, and page number information of the text information of the question in the book;

[0139] Based on the document information, book information corresponding to the multiple questions is determined.

[0140] The second determination module 73 is further used to determine the relevance between the text information of the plurality of questions and the document information in the preset index library according to a preset relevance operator;

[0141] According to the relevance, document information related to the text information of the plurality of questions is determined.

[0142] The second determination module 73 is further used to count the number of times the book information corresponding to the text information of the multiple questions appears in the document information related to the text information of the multiple questions;

[0143] According to the number of times, the book information corresponding to the text information of the multiple questions is sorted to obtain the sequentially sorted book information, and the sequentially sorted book information is determined as the book information corresponding to the multiple questions.

[0144] The third determining module 74 is further used to search for document information related to the text information of the topic to be searched in the document information corresponding to the book information arranged in sequence;

[0145] When searching, increase the weight of the book information with the maximum number of times;

[0146] According to the weights of the book information arranged in sequence, the target topic information corresponding to the topic to be searched is determined.

[0147] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0148] like Figure 8 As shown, an embodiment of the present application also provides a terminal device 100, including a memory 21, a processor 22, and a computer program 23 stored in the memory 21 and executable on the processor 22, and when the processor 22 executes the computer program 23, the question searching methods of the above-mentioned embodiments are implemented.

[0149] The processor 22 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0150] The memory 21 may be an internal storage unit of the terminal device 100. The memory 21 may also be an external storage device of the terminal device 100, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 100. Further, the memory 21 may also include both an internal storage unit of the terminal device 100 and an external storage device. The memory 21 is used to store computer programs and other programs and data required by the terminal device 100. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0151] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the question searching methods of the above embodiments are implemented.

[0152] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal implements the question searching methods of the above-mentioned embodiments when executing the computer program product.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program generation data, which can be in the form of source generation data, object generation data, executable files or some intermediate forms. The computer-readable storage medium may at least include: any entity or device that can carry the computer program generation data to the camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, a computer-readable storage medium cannot be an electric carrier signal and a telecommunication signal.

[0154] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0156] 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 distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0157] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A question searching method, characterized in that: include: Obtaining an image of a page title, wherein the page title includes a title to be searched; Determining images of multiple questions based on the image of the page title; Determining book information corresponding to the plurality of questions according to the images of the plurality of questions; Based on the book information, determining target topic information corresponding to the topic to be searched; The step of determining book information corresponding to the plurality of questions according to the images of the plurality of questions includes: Recognize the images of the plurality of questions and obtain text information of the plurality of questions; Searching for document information related to text information of multiple questions in a preset index library, wherein the preset index library contains document information corresponding to each question, and the document information corresponding to each question includes text information of the question, book information corresponding to the text information of the question, and page number information of the text information of the question in the book; Based on the document information, determining book information corresponding to the plurality of questions; The searching for document information related to the text information of the multiple questions includes: Determining the relevance between the text information of the plurality of questions and the document information in the preset index library according to a preset relevance operator; Determining the document information related to the text information of the plurality of questions according to the relevance; The step of determining book information corresponding to the plurality of questions based on the document information includes: Counting the number of times the book information corresponding to the text information of the plurality of questions appears in the document information related to the text information of the plurality of questions; According to the number of times, the book information corresponding to the text information of the plurality of questions is sorted to obtain sequentially sorted book information, and the sequentially sorted book information is determined as the book information corresponding to the plurality of questions; The step of determining target topic information corresponding to the topic to be searched based on the book information includes: Searching for document information related to the text information of the topic to be searched in the document information corresponding to the book information arranged in sequence; When searching, increase the weight of the book information with the maximum number of times; According to the weights of the book information arranged in sequence, the target topic information corresponding to the topic to be searched is determined.

2. The question searching method according to claim 1, characterized in that: After acquiring the image of the page title, the method further includes: Detecting the image of the page title and obtaining text boxes of the multiple questions; According to the multiple text boxes, coordinate information of the multiple text boxes is determined.

3. The question searching method according to claim 2, characterized in that: The step of determining images of multiple questions according to the image of the page title includes: The image of the page title is segmented according to the coordinate information of the plurality of text boxes to determine the images of the plurality of titles.

4. A question-searching device, characterized in that: include: An acquisition module, used to acquire an image of a page title, wherein the page title includes a title to be searched; A first determination module, used to determine images of multiple questions according to the image of the page title; A second determination module, configured to determine book information corresponding to the plurality of questions based on the images of the plurality of questions; A third determination module, configured to determine target title information corresponding to the title to be searched based on the book information; The second determining module is further used for: Recognize the images of the plurality of questions and obtain text information of the plurality of questions; Searching for document information related to text information of multiple questions in a preset index library, wherein the preset index library contains document information corresponding to each question, and the document information corresponding to each question includes text information of the question, book information corresponding to the text information of the question, and page number information of the text information of the question in the book; Based on the document information, determining book information corresponding to the plurality of questions; The second determining module is further used for: Determining the relevance between the text information of the plurality of questions and the document information in the preset index library according to a preset relevance operator; Determining the document information related to the text information of the plurality of questions according to the relevance; The second determining module is further used for: Counting the number of times the book information corresponding to the text information of the plurality of questions appears in the document information related to the text information of the plurality of questions; According to the number of times, the book information corresponding to the text information of the plurality of questions is sorted to obtain sequentially sorted book information, and the sequentially sorted book information is determined as the book information corresponding to the plurality of questions; The third determining module is further used for: Searching for document information related to the text information of the topic to be searched in the document information corresponding to the book information arranged in sequence; When searching, increase the weight of the book information with the maximum number of times; According to the weights of the book information arranged in sequence, the target topic information corresponding to the topic to be searched is determined.

5. A terminal device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the question searching method as claimed in any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the question searching method according to any one of claims 1 to 3 is implemented.

Images