CN114547467A

CN114547467A - Question searching method and device, terminal equipment and readable storage medium

Info

Publication number: CN114547467A
Application number: CN202210193128.9A
Authority: CN
Inventors: 张维鹏
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-05-27
Anticipated expiration: 2042-02-28

Abstract

The application belongs to the field of topic searching, and particularly relates to a topic searching method, a topic searching device, terminal equipment and a readable storage medium. The title searching method comprises the following steps: acquiring a target title image to be searched and book information corresponding to a searched historical title; determining the searched book information in a preset first time period according to the searched book information corresponding to the historical title; and determining the answer of the target title according to the target title image and the book information searched in the preset first time period. When the method and the device are used for searching the target topic, the searched book information in the preset first time period can be determined through the book information corresponding to the searched historical topic, the answer of the target topic is determined according to the book information, and compared with the method and the device which use the OCR text information of the target topic, the method and the device can directly search in a topic library which has a large number of topics and a large number of similar topics, the method and the device for searching the target topic improve the accuracy rate of searching the topic.

Description

Question searching method and device, terminal equipment and readable storage medium

Technical Field

The present application belongs to the field of topic search, and in particular, to a topic search method, device, terminal device, and readable storage medium.

Background

In the existing photo-topic searching technology, a user is usually used to click or frame a topic to be searched for, and perform Optical Character Recognition (OCR) and search for the topic.

The method has the problems that when one question is searched, the OCR text information of the question is directly searched in a question bank which has a large number of questions and a large number of similar questions, the accuracy rate of the question searching result is not high, and the effect of searching the original question cannot be achieved.

Disclosure of Invention

The embodiment of the application provides a method and a device for searching for a question, a terminal device and a readable storage medium, and the accuracy of the question searching result is improved.

In a first aspect, an embodiment of the present application provides a topic searching method, including:

the acquisition module is used for acquiring a target topic image to be searched and book information corresponding to a searched historical topic;

the first determining module is used for determining the searched book information in a preset first time period according to the searched book information corresponding to the historical title;

and the second determining module is used for determining the answer of the target title according to the target title image and the book information searched in the preset first time period.

In a possible implementation manner of the first aspect, the method for determining the book information corresponding to the searched historical title includes:

searching a plurality of channels of related topic information related to each channel of historical topic information in a preset index library;

determining book information corresponding to each piece of relevant subject information according to the plurality of pieces of relevant subject information;

and determining the book information corresponding to the searched historical title according to the book information corresponding to each related title information.

Wherein, according to the book information corresponding to the searched historical title, determining the book information searched in a preset first time period comprises:

determining book information corresponding to the historical title information within a preset first time period according to the searched book information corresponding to the historical title;

and counting first times of book information corresponding to the historical title information in a preset first time period, and if the first times is not less than a first threshold, determining the book information of which the first times is not less than the first threshold as the book information searched in the preset first time period.

Wherein, the determining the answer of the target title according to the target title image and the book information searched within the preset first time period comprises:

identifying the target topic image to obtain target topic information;

calculating the correlation degree of the target title information and the title information corresponding to the book information searched in the preset first time period;

and determining the answer of the target title according to the correlation degree of the target title information and the title information corresponding to the book information searched in the preset first time period.

Wherein the calculating the correlation between the target title information and the title information corresponding to the book information searched within the preset first time period comprises:

determining the searched book information within a preset second time period according to the searched book information corresponding to the historical title, wherein the second time period is the time period within the first time period;

judging whether the book information searched in the preset first time period exists in the book information searched in the preset second time period;

if the book information exists, the weight of the searched book information in the preset second time period is increased;

and calculating the correlation degree of the target title information and the title information corresponding to the book information searched in the preset first time period according to the weight.

Wherein, the increasing of the weight of the book information searched in the preset second time period includes:

counting a second time of the book information searched in the preset second time period;

and if the second times is not less than a second threshold and not more than a first threshold, increasing the weight of the book information which is searched for the second times within a preset second time period.

Wherein, the determining the answer of the target title according to the relevance between the target title information and the title information corresponding to the book information searched in the preset first time period comprises:

sequencing the relevance of the target title information and the title information corresponding to the book information searched in the preset first time period;

and determining the answer information corresponding to the searched book information within the preset first time period with the maximum correlation degree as the target title answer information.

In a second aspect, an embodiment of the present application provides a topic searching apparatus, including:

In a third aspect, an embodiment of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the topic searching method according to any one of the first aspects.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the topic searching method according to any one of the first aspect.

Compared with the prior art, the embodiment of the application has the advantages that: according to the method and the device, the target topic image to be searched and the book information corresponding to the searched historical topic are obtained; determining the searched book information in a preset first time period according to the searched book information corresponding to the historical title; and determining the answer of the target title according to the target title image and the searched book information in the preset first time period. When the method and the device are used for searching the target topic, the searched book information in the preset first time period can be determined through the book information corresponding to the searched historical topic, the answer of the target topic is determined according to the book information, and compared with the method and the device which use the OCR text information of the target topic, the method and the device can directly search in a topic library which has a large number of topics and a large number of similar topics, the method and the device for searching the target topic improve the accuracy rate of searching the topic.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of a topic searching method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart diagram of a method for determining answers to topic headings provided by embodiments of the present application;

fig. 3 is a schematic flowchart of a method for determining book information corresponding to historical title information according to an embodiment of the present application;

fig. 4 is a schematic flowchart of a specific method of S202 provided by an embodiment of the present application;

fig. 5 is a schematic flowchart of a specific method of S203 provided by an embodiment of the present application;

fig. 6 is a schematic flowchart of a specific method of S502 provided in an embodiment of the present application;

fig. 7 is a schematic flowchart of a specific method of S603 provided in an embodiment of the present application;

fig. 8 is a schematic flowchart of a specific method of S503 provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a title searching apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail, and in other instances, specific technical details may be mutually referenced in various embodiments, and a specific system not described in one embodiment may be referenced in other embodiments.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Reference throughout this specification to "one embodiment of the present application" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in other embodiments," "an embodiment of the present application," "other embodiments of the present application," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather mean "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless otherwise specifically stated.

Furthermore, in the description of the present application and the appended claims, the terms "first," "second," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

In order to solve the above defects, the inventive concept of the present application is:

when the method and the device are used for searching the target topic, the searched book information in the preset first time period can be determined through the searched book information corresponding to the historical topic, the answer of the target topic is determined according to the book information, and compared with the method and the device, the method and the device for searching the target topic directly carry out retrieval in a question bank which has a large number of topics and a large number of similar topics compared with OCR text information using the target topic, and the accuracy rate of searching the topic is improved.

In order to explain the technical means of the present application, the following description will be given by way of specific examples.

Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a topic searching method according to an embodiment of the present application, and only a portion related to the present application is shown for convenience of description. The application scenario includes: a terminal device 100 and a target topic 200.

The terminal device 100 includes a scanning pen, a mobile phone, a tablet computer, a wearable device, an in-vehicle device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), and the like, and the specific type of the terminal device is not limited in the embodiment of the present application.

The target topic 200 in the embodiment of the present application may be a topic in a whole page of a book, a topic in a test paper, or a topic written temporarily.

The target subject in the embodiment of the present application may be a printed font or a handwritten font, and the font type of the subject is not limited in the embodiment of the present application.

The terminal equipment mainly obtains the target title 200 image to be searched and the book information corresponding to the searched historical title; determining the searched book information in a preset first time period according to the searched book information corresponding to the historical title; according to the image of the target topic 200 and the book information searched in the preset first time period, the answer of the target topic is determined.

Referring to fig. 2, fig. 2 is a schematic flowchart of a method for determining an answer to a title target provided in an embodiment of the present application. The main body of execution of the method in fig. 2 may be the terminal device 100 in fig. 1. As shown in fig. 2, the method includes: s201 to S203.

S201, obtaining a target topic image to be searched and book information corresponding to a searched historical topic.

Specifically, a camera module is generally configured in the terminal device, in this application embodiment, the terminal device may obtain an image of a target topic to be searched through the camera module, and the application embodiment does not limit the type of the camera module.

In the embodiment of the application, after the target topic image to be searched is acquired, the acquired image needs to be preprocessed, and the preprocessing includes graying, binarization, smoothing and other processing. The purpose of the pre-processing is to correct the acquired images and to unify the specifications. The embodiment of the present application does not limit the pretreatment method.

In the embodiment of the application, the book information corresponding to the searched historical title refers to the title information which is searched by the searcher before searching the target title by using the terminal equipment, and the book information is determined by the searched title information.

In the embodiment of the application, when a searcher searches historical title information by using terminal equipment each time, the historical title information and book information corresponding to the historical title information are recorded by using a point-embedding technology.

The embedded point is a term in the field of data acquisition, and in the embodiment of the application, historical topic information searched by a topic searcher and book information corresponding to the historical topic information can be captured and stored through the embedded point.

In some embodiments, the method for determining the book information corresponding to the searched historical title information comprises:

inputting each piece of historical topic information into a trained neural network model, obtaining a plurality of participles of each piece of historical topic in the neural network model according to each piece of historical topic information, and then carrying out book identification on each piece of historical topic information according to word frequency values of each obtained participle in a plurality of different books so as to determine book information corresponding to each piece of historical topic.

The training method of the neural network model comprises the following steps:

and acquiring sample historical title information, and marking corresponding book information in the sample historical title information.

Inputting the sample historical topic information into a neural network model for training.

In the neural network model, a plurality of participles of the sample historical topic information and word frequency values of the participles in different books are obtained.

And performing book identification on the sample historical title information according to the word frequency values of the participles in different books, and if the identification result is inconsistent with the labeled book information, adjusting the word frequency values of the participles in the different books to obtain the adjusted word frequency values.

And after adjustment, performing book identification again according to the corresponding adjusted word frequency value of each participle in different books, wherein the adjustment and identification are a cyclic process until the adjusted word frequency value can enable the book identification result to be consistent with the book mark.

Through the process, after a certain number of sample historical titles are trained, more accurate word segmentation of the historical titles and word frequency values of different corresponding books can be obtained, and therefore the books to which the historical titles belong can be accurately identified when the historical titles of unknown books are identified in the follow-up process.

In other embodiments of the present application, reference may be made to fig. 3 for a method for determining book information corresponding to searched historical topic information, where fig. 3 is a schematic flowchart of a method for determining book information corresponding to historical topic information provided in an embodiment of the present application. The execution subject of the method in fig. 3 may be the terminal device 100 in fig. 1. As shown in fig. 3, the method includes: s301 to S303.

S301, searching multiple channels of related topic information related to each channel of historical topic information in a preset index library.

Specifically, the preset index database contains document information corresponding to each topic, and the document information corresponding to each topic includes each topic information, book information corresponding to each topic information, and answer information corresponding to each topic information.

The construction method of the preset index library comprises the following steps:

and constructing an index document by using each topic, book information corresponding to each topic and answer information corresponding to each topic. And (3) constructing m index documents if all the books related to the basic education stage have m questions, wherein the m index documents form a preset index library.

All books involved in the basic education stage in the embodiment of the present application include textbooks, exercise books, problem sets, test papers, and the like.

The traditional question searching method needs to search and identify in a traditional question bank which comprises questions in all books on the market, and the number of the question bank is very large, so that the calculation amount is too large during searching, the searching time is too long, and the identification accuracy is low. The title searching method provided by the embodiment of the application can be used for searching and identifying in the preset index database, the preset index database only comprises titles contained in all books related to the basic education stage, and compared with the traditional title identifying method, the method can reduce the calculated amount, save the searching time and improve the identification accuracy.

The method of searching for multiple channels of related topic information related to each channel of historical topic information may be:

firstly, according to a preset correlation operator, determining the correlation between each history topic information and the document information in a preset index database.

Specifically, the preset relevance operator in the embodiment of the present application may be a terminal Frequency-Inverse Document Frequency (TF-IDF) weighting algorithm for information retrieval and data mining. May be a probabilistic model based algorithm BM 25.

In the embodiment of the application, the preset correlation operator is used for scoring the similarity between each piece of historical topic information and the file information in the preset index database, and the correlation between each piece of historical topic information and the file information in the preset index database can be determined according to the score.

And secondly, determining a plurality of channels of related topic information related to each channel of historical topic information according to the correlation.

Specifically, for example: the preset index library stores 10 pieces of document information, and scores of the historical title information and the 10 pieces of document information are respectively calculated to be 0, 0.1, 0.45, 0, 0.6, 0.7, 0.8, 0.6, 0 and 0 according to a preset correlation operator. The plurality of pieces of associated topic information associated with the piece of historical topic information are topic information in all the document information except for the score of 0. According to this method, a plurality of pieces of associated topic information associated with each piece of historical topic information can be determined.

S302, book information corresponding to each channel of related title information is determined according to the channels of related title information.

When multiple channels of related topic information are determined by using the method in S301, the embodiment of the present application may determine book information corresponding to each channel of related topic information according to a preset index library.

S303, determining book information corresponding to the historical title information according to the book information corresponding to each related title information.

Specifically, in some embodiments, the book information corresponding to each related topic information may be determined as the book information corresponding to the historical topic information. For example, the book information corresponding to the related topic information having a score of 0.1, 0.45, 0.6, 0.7, 0.8, or 0.6 may be determined as the book information corresponding to the history topic information.

In the embodiment of the application, the book information corresponding to each piece of related topic information can be sorted according to the degree of correlation, and the book information corresponding to a plurality of pieces of related topic information with high degree of correlation is determined as the book information corresponding to the historical topic information. Illustratively, the ranking is based on scores, such as: the order of scores from large to small is 0.8, 0.7, 0.6, 0.45 and 0.1, and book information corresponding to the related topic information of the first 3 or 4 tracks can be determined as book information corresponding to the historical topic information.

In the embodiment of the application, the book information corresponding to the multiple related topic information with high correlation is determined as the multiple related topic information in the book information corresponding to the historical topic information, and the multiple related topic information can be specifically selected according to actual conditions.

S202, determining the book information searched in a preset first time period according to the book information corresponding to the searched historical title.

Specifically, in some embodiments, please refer to fig. 4 for a method of determining book information that has been searched within a preset first time period, where fig. 4 is a schematic flowchart of a specific method of S202 provided in the embodiments of the present application. The execution subject of the method in fig. 4 may be the terminal device 100 in fig. 1. As shown in fig. 4, the method includes: s401 to S402.

S401, according to the searched historical title information, book information corresponding to the historical title information in a preset first time period is determined.

Specifically, the preset first time period refers to a time period before the subject searcher searches for the subject by using the terminal device, and exemplarily, the preset first time period is 5 months to 7 months, for example, 6 months.

In the embodiment of the application, when the searched historical title information is recorded through a point burying technology, the searched historical title information can be stored in a preset first database, and the preset first database only comprises book information corresponding to the historical title information in a preset first time period.

For example: the preset first database only contains book information corresponding to the historical title information within 6 months before the search for the title, so that when the searched historical title information is stored in the preset first database, data within 6 months before the search for the title needs to be continuously deleted, and the preset first database only stores the data within 6 months before the search for the title.

S402, counting the first times of book information corresponding to historical title information in a preset first time period, and if the first times is not smaller than a first threshold, determining the book information of which the first times is not smaller than the first threshold as the book information searched in the preset first time period.

Illustratively, book information stored in the first database is preset as a Chinese teaching book, a Chinese exercise book, a math teaching book, an English teaching book, and a history teaching book. The number of times these books are counted, for example: the Chinese teaching book is used for 4 times, the Chinese exercise book is used for 3 times, the Chinese exercise question set is used for 5 times, the math teaching book is used for 2 times, the English teaching book is used for 1 time, and the history teaching book is used for 1 time.

The first threshold in the embodiment of the present application may be specifically set according to the actual application, and exemplarily, the first threshold is 2 to 4 times, for example, 3 times.

And comparing the counted times of the Chinese textbook, the Chinese exercise book, the Chinese exercise question set, the math textbook, the English textbook and the historical textbook with a first threshold value for 3 times, wherein the times of the Chinese textbook, the Chinese exercise book and the Chinese exercise question set are not less than the first threshold value, and then determining the Chinese textbook, the Chinese exercise book and the Chinese exercise question set as the book information searched in a preset first time period.

S203, according to the target topic image and the book information searched in the preset first time period, determining the answer of the target topic.

Specifically, please refer to fig. 5, wherein a method for determining a target topic answer according to a target topic image and book information searched within a preset first time period is shown in fig. 5, and fig. 5 is a schematic flowchart of an embodiment of the present application, which is a specific method of S203. The execution subject of the method in fig. 5 may be the terminal device 100 in fig. 1. As shown in fig. 5, the method includes: s501 to S503.

S501, identifying the target topic image and obtaining target topic information.

Specifically, in the embodiment of the present application, a guest recognizes a target topic image by an Optical Character Recognition (OCR) technology to obtain target topic information.

In some embodiments, identifying the target topic image can be divided into 2 steps, one step is detecting text information in the target topic image, and one step is identifying the text information. When the target topic image is detected, the text area of the topic in the image is positioned, and then the text is marked in the form of a text box. In some embodiments, the text box may be a rectangular box. In the embodiment of the present application, the text may be detected by using a detection model based on deep learning, for example: efficient and accurate Scene Text model (EAST), etc. Identifying the target topic image means identifying the text in the text box. In the embodiment of the present application, the text may be recognized by using a recognition model based on deep learning, for example: residual neural network models ResNet, etc.

In other embodiments, when the target topic image is identified, the text detection and the text identification can be implemented in a network structure. For example: a Fast organized Text Spotting with a Unified Network (FOTS) based on a Unified Network, and the like.

S502, calculating the correlation degree of the target title information and the title information corresponding to the book information searched in the preset first time period.

Please refer to fig. 6, wherein a method for calculating a correlation between target topic information and topic information corresponding to book information searched within a preset first time period is shown in fig. 6, and fig. 6 is a schematic flowchart of a specific method of S502 provided in an embodiment of the present application. The main body of execution of the method in fig. 6 may be the terminal device 100 in fig. 1. As shown in fig. 6, the method includes: s601 to S604.

S601, book information searched in a preset second time period is determined according to the historical title information.

And the second time period is the time period in the first time period. Illustratively, the predetermined first period of time is from 5 months to 7 months, e.g. 6 months, and the second predetermined period of time is from 1 week to 3 weeks, e.g. 2 weeks.

In the embodiment of the application, when the searched historical title information is recorded by using a point-burying technology, the searched historical title information can be stored in the preset second database, and the preset second database only comprises book information corresponding to the historical title information in the preset second time period.

For example: the preset second database only contains book information corresponding to the historical title information within 2 weeks before the search for the title, so that when the searched historical title information is stored in the preset second database, the data within 2 weeks before the search for the title needs to be continuously deleted, and the preset second database only stores the data within 2 weeks before the search for the title.

S602, judging whether the book information searched in the preset first time period exists in the book information searched in the preset second time period.

For example, the book information searched for in the preset second time period determined according to S601 includes a chinese textbook, a chinese exercise set, an english textbook, and a history textbook, and the book information searched for in the preset first time period determined according to S402 includes a chinese textbook, a chinese exercise book, and a chinese exercise set, and then it is determined whether the book information determined according to S601 exists in the book information determined according to S402.

And S603, if the book information exists, increasing the weight of the book information searched in the preset second time period.

For example, the book information (the chinese textbook and the chinese exercise set) searched for the preset first period exists in the book information searched for the preset second period.

According to the embodiment of the application, the preset correlation operator is utilized to calculate the correlation between the target topic information and the topic information corresponding to the book information searched in the preset first time period, and when the preset correlation operator is utilized to calculate, the weight needs to be given to the book information searched in the preset first time period.

In the embodiment of the present application, the preset relevancy operator adjusts the weight by setting the weight parameter boost, and the purpose of increasing the weight of the book information searched in the preset second time period, that is, increasing the weight of the chinese textbook and the chinese exercise collection, is: the scoring values of the target question information, the Chinese teaching book and the Chinese exercise set are larger than the scoring values of the document information corresponding to other book information.

In other embodiments, the method for increasing the weight of the book information searched within the preset second time period includes the method in fig. 7, and fig. 7 is a schematic flowchart of a specific method of S603 provided in this application embodiment. The main body of execution of the method in fig. 7 may be the terminal device 100 in fig. 1. As shown in fig. 7, the method includes: s701 to S702.

And S701, counting a second time of the book information searched in a preset second time period.

Specifically, the second number is smaller than the first number.

Illustratively, the book information determined according to S601 and searched in the preset second time period includes a chinese textbook, a chinese exercise collection, an english textbook, and a history textbook, and the times of counting the book information are respectively: chinese textbook 2 times, Chinese exercise collection 3 times, English textbook 1, history textbook 1.

And S702, if the second frequency is not less than the second threshold and not greater than the first threshold, increasing the weight of the book information searched in a preset second time period, wherein the second frequency is not less than the second threshold and not greater than the first threshold.

Specifically, the second threshold is 1 to 3 times, for example, 2 times.

An exemplary first threshold is 3 times, the second threshold is 2 times, and the number of times of the chinese textbook and the chinese exercise set is not less than 2 times and not more than 3 times, then the weight of the book information corresponding to the chinese textbook and the chinese exercise set is increased.

S604, calculating the correlation degree of the target title information and the title information corresponding to the book information searched in the preset first time period according to the weight.

Illustratively, the book information searched for in the preset first time period determined according to S402 includes a chinese lesson book, a chinese exercise book, and a chinese exercise question set.

Before the weight is not increased, when the score of the target topic information and the document information corresponding to the Chinese textbook is calculated, the weight is set to be 1, when the score of the target topic information and the document information corresponding to the Chinese exercise book is calculated, the weight is set to be 1, and when the score of the target topic information and the document information corresponding to the Chinese exercise book is calculated, the weight is set to be 1.

Because the times of the Chinese teaching book and the Chinese exercise set are not less than the second threshold and not more than the first threshold, when the weight is adjusted high, the weight is set to 3.5 when the scoring of the target question information and the document information corresponding to the Chinese teaching book is calculated, the weight is set to 1 when the scoring of the target question information and the document information corresponding to the Chinese exercise book is calculated, and the weight is set to 3.5 when the scoring of the target question information and the document information corresponding to the Chinese exercise set is calculated.

S503, determining the answer of the target title according to the relevance between the target title information and the title information corresponding to the book information searched in the preset first time period.

Specifically, please refer to fig. 8, where a method for determining a target topic answer according to a correlation between the target topic information and topic information corresponding to book information searched within a preset first time period is provided, and fig. 8 is a schematic flowchart of a specific method of S503 according to an embodiment of the present application. The execution subject of the method in fig. 8 may be the terminal device 100 in fig. 1. As shown in fig. 8, the method includes: s801 to S802.

S801, sorting the relevance of the target title information and the title information corresponding to the book information searched in the preset first time period.

Illustratively, the Chinese textbook corresponds to 3 pieces of document information A1, B1 and C1, the Chinese exercise book corresponds to 4 pieces of document information A2, B2, C2 and D2, the Chinese exercise question set corresponds to 2 pieces of document information A3 and B3, and when the scoring of the target question information and the 3 pieces of document information corresponding to the Chinese textbook is calculated, the weight is set to be 3.5, the A1 scoring is 0.92, the B1 scoring is 0.87, and the C1 scoring is 0.97.

When the scores of the target topic information and the 4 pieces of document information corresponding to the Chinese exercise book are calculated, the weight is set to be 1, the A2 score is 0.32, the B2 score is 0.37, the C2 score is 0.47, and the D2 score is 0.31.

When the scoring of the target topic information and the 2 pieces of document information corresponding to the Chinese exercise set is calculated, the weight is set to be 3.5, the score of A3 is 0.93, and the score of B3 is 0.83.

And sequencing the relevance of the target title information and the title information corresponding to the book information searched in the preset first time period, namely sequencing the scores of the 9 pieces of document information.

S802, determining answer information corresponding to the book information searched within a preset first time period and having the maximum correlation degree as answer information of the target title.

For example, the answer information corresponding to the book information with the largest score among the scores of the 9 pieces of document information is determined as the answer information of the target title.

In summary, the embodiment of the application obtains the target topic image to be searched and the book information corresponding to the searched historical topic; determining the searched book information in a preset first time period according to the searched book information corresponding to the historical title; and determining the answer of the target title according to the target title image and the book information searched in the preset first time period. When the method and the device are used for searching the target topic, the searched book information in the preset first time period can be determined through the book information corresponding to the searched historical topic, the answer of the target topic is determined according to the book information, and compared with the method and the device which use the OCR text information of the target topic, the method and the device can directly search in a topic library which has a large number of topics and a large number of similar topics, the method and the device for searching the target topic improve the accuracy rate of searching the topic.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Referring to fig. 9, fig. 9 is a device for searching for a question, including:

the obtaining module 91 is configured to obtain a target topic image to be searched and book information corresponding to a searched historical topic.

The first determining module 92 is configured to determine, according to the book information corresponding to the searched historical title, the book information that has been searched within a preset first time period.

And a third determining module 93, configured to determine an answer to the target topic according to the target topic image and the book information that has been searched within a preset first time period.

The obtaining module 91 is further configured to search, in a preset index library, multiple channels of related topic information related to each channel of historical topic information;

determining book information corresponding to each channel of related subject information according to the plurality of channels of related subject information;

The first determining module 92 is further configured to determine, according to the book information corresponding to the searched historical title, book information corresponding to the historical title information within a preset first time period;

counting a first time of book information corresponding to historical title information in a preset first time period, and if the first time is not less than a first threshold, determining the book information with the first time not less than the first threshold as the book information searched in the preset first time period.

The second determining module 93 is further configured to identify the target topic image and obtain target topic information;

calculating the correlation degree of the target title information and the title information corresponding to the book information searched in a preset first time period;

and determining the answer of the target title according to the relevance between the target title information and the title information corresponding to the book information searched in the preset first time period.

The second determining module 93 is further configured to determine, according to the book information corresponding to the searched historical title, the book information that has been searched within a preset second time period, where the second time period is a time period within the first time period;

The second determining module 93 is further configured to count a second number of times that the book information has been searched within a preset second time period;

and if the second times is not less than the second threshold and not more than the first threshold, increasing the weight of the book information searched for the second times within the preset second time period.

The second determining module 93 is further configured to rank the relevance between the target topic information and the topic information corresponding to the book information that has been searched within the preset first time period;

and determining answer information corresponding to the book information searched within a preset first time period with the maximum correlation degree as the answer information of the target title.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

As shown in fig. 10, the present embodiment further provides a terminal device 100, which includes a memory 21, a processor 22, and a computer program 23 stored in the memory 21 and executable on the processor 22, where the processor 22 implements the topic searching method of each of the above embodiments when the computer program 23 is executed by the processor 22.

The Processor 22 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

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 memory Card (Flash Card) and the like provided 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.

The embodiment of the application also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the computer program realizes the topic searching method of each embodiment.

The embodiment of the application provides a computer program product, and when the computer program product runs on a mobile terminal, the mobile terminal can implement the title searching method of each embodiment when executed.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be implemented by instructing relevant hardware by a computer program, which can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the embodiments of the methods described above can be implemented. The computer program includes computer program data, which may be in the form of source data, object data, executable file or some intermediate form. The computer-readable storage medium may include at least: any entity or device capable of carrying computer program data instead to a photographing apparatus/terminal device, a recording medium, computer memory, read-only memory (ROM), Random Access Memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. Such as a usb-drive, a removable hard drive, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable storage media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and proprietary practices.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

Units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for searching for a question, comprising:

acquiring a target title image to be searched and book information corresponding to a searched historical title;

determining the searched book information within a preset first time period according to the searched book information corresponding to the historical title;

and determining the answer of the target title according to the target title image and the searched book information in the preset first time period.

2. The method according to claim 1, wherein the method for determining the book information corresponding to the searched historical title comprises:

3. The method according to claim 1, wherein the determining the book information searched within a preset first time period according to the book information corresponding to the searched historical title comprises:

4. The method of claim 1, wherein the determining an answer to the target topic according to the target topic image and the book information searched within the preset first time period comprises:

identifying the target topic image to obtain target topic information;

5. The method according to claim 4, wherein the calculating the degree of correlation between the target title information and the title information corresponding to the book information searched in the preset first time period comprises:

6. The method according to claim 5, wherein the increasing the weight of the book information searched within the preset second time period comprises:

7. The method according to claim 4, wherein the determining the answer to the target topic according to the degree of correlation between the target topic information and the topic information corresponding to the book information searched in the preset first time period comprises:

and determining the answer information corresponding to the searched book information within the preset first time period with the maximum correlation degree as the answer information of the target title.

8. A device for searching for a question, comprising:

9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the title searching method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method of searching for a subject according to any one of claims 1 to 7.