WO2023272660A1

WO2023272660A1 - Test question picture optimization method and apparatus, computer device and storage medium

Info

Publication number: WO2023272660A1
Application number: PCT/CN2021/103866
Authority: WO
Inventors: 何华强
Original assignee: 东莞市小精灵教育软件有限公司
Priority date: 2021-06-30
Filing date: 2021-06-30
Publication date: 2023-01-05

Abstract

Disclosed in embodiments of the present application is a test question picture optimization method, comprising: constructing an initial test question picture library; when a picture storage instruction is received, acquiring test question pictures to be stored contained in the picture storage instruction, and recognizing said test question pictures to obtain second test question information and second picture parameters of said test question pictures; retrieving the initial test question picture library on the basis of the second test question information; if first test question information consistent with the second test question information exists, when the second picture parameters are superior to first picture parameters, storing said test question pictures into the initial test question picture library; and if the first test question information consistent with the second test question information does not exist, constructing a second test question picture library, and storing said test question pictures into the second test question picture library, such that automatic iteration and storage of test question pictures are realized by combining with comparison of the initial test question picture library, the question quality of the pictures is automatically optimized, the question quantity of the test question pictures is expanded, and the user experience in test question answering is improved.

Description

Test question picture optimization method, device, computer equipment and storage medium

technical field

The present application relates to the technical field of image processing, in particular to a test question picture optimization method, device, computer equipment and storage medium.

Background technique

With the development of the Internet and science and technology, people's learning methods are becoming more and more diverse and convenient. For example, using tutoring machines to learn, mock exams will be involved in the learning process, which requires tutoring machines to provide test questions picture.

technical problem

However, the current source of test question pictures is mainly to make test question pictures and store them in the database or users take photos and upload them. There is a certain limitation in the breadth of the input pictures for making test questions, which will reduce the number and richness of the test questions, and the pictures taken by users have problems of randomness and clarity that are difficult to meet the requirements, which cannot well meet the use of picture questions. Scenes.

technical solution

Based on this, it is necessary to address the above problems and propose a test question picture optimization method, device, computer equipment and storage medium that can automatically optimize the test question picture quality and expand the number of questions.

A test question picture optimization method, the method comprising:

Constructing an initial test question picture library, said initial test question picture bank comprising a plurality of initial test question pictures and first test question information and first picture parameters of each said initial test question picture;

When receiving the image storage instruction, obtain the test question picture to be stored in the picture storage instruction, identify the test question picture to be stored, and obtain the second test item information and the test question picture to be stored in the storage. Second picture parameter;

Searching in the initial test question image library based on the second test question information;

If there is first test item information consistent with the second test item information, the initial test item picture corresponding to the first test item information consistent with the second test item information is used as a candidate picture;

comparing the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and deleting the candidate picture when the second picture parameter is better than the first picture parameter , and store the picture of the test question to be stored into the library of the initial test question picture;

If there is no first test item information consistent with the second test item information, a second test item image library is constructed, and the test item images to be stored are stored in the second test item image library.

A test question picture optimization device, said device comprising:

A construction module for constructing an initial test question image library, the initial test question image library including a plurality of initial test question pictures and first test question information and first picture parameters of each of the initial test question pictures;

The receiving module is configured to obtain the picture of the test questions to be stored included in the picture storage instruction when receiving the picture storage instruction, identify the picture of the test questions to be stored, and obtain the picture of the test questions to be stored The second test question information and the second picture parameters;

A retrieval module, configured to search in the initial test question picture library based on the second test question information;

A determining module, configured to use the initial test question picture corresponding to the first test question information consistent with the second test question information as a candidate picture if there is first test question information consistent with the second test question information;

A comparison module, configured to compare the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and when the second picture parameter is better than the first picture parameter , deleting the candidate picture, and storing the test question picture to be stored in the initial test question picture library;

The storage module is configured to construct a second test question picture library if there is no first test question information consistent with the second test question information, and store the test question pictures to be stored into the second test question picture bank.

A computer device, comprising a memory and a processor, the memory stores computer-readable instructions computer-readable instructions, the computer-readable instructions, when executed by the processor, cause the processor to perform the following step:

A computer-readable medium, storing computer-readable instructions computer-readable instructions, when the computer-readable instructions computer-readable instructions are executed by a processor, cause the processor to perform the following steps:

Beneficial effect

The above-mentioned test question picture optimization method, device, computer equipment, and storage medium construct an initial test question picture library, and the initial test question picture storehouse includes a plurality of initial test question pictures and first test question information and first picture parameters of each initial test question picture ; When receiving the picture storage instruction, obtain the test question picture to be stored in the picture storage instruction, identify the test question picture to be stored, and obtain the second test question information of the test question picture to be stored and the second picture parameter; based on the second test question information, search in the initial test question picture library; if there is the first test question information consistent with the second test question information, then the first test question information consistent with the second test question information will be The initial test question picture corresponding to the first test question information is used as a candidate picture; the first picture parameter of the candidate picture is compared with the second picture parameter according to a preset comparison rule, and when the second picture parameter is better than When the first picture parameter is used, delete the candidate picture, and store the test question picture to be stored in the initial test question picture library; if there is no first test question information consistent with the second test question information, construct The second test question picture library, and store the test question pictures to be stored in the second test question picture bank, through the analysis and comparison of the test question pictures, realize the self-iteration and optimization of the test question pictures, and improve the quality of the test question pictures At the same time, it also expands the number of test questions and pictures to improve user experience.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present application. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

in:

Fig. 1 is the flow chart of test question picture optimization method in an embodiment;

Fig. 2 is the flow chart of the method for obtaining pictures of test questions to be put into storage in one embodiment;

Fig. 3 is the flowchart of the method for determining the second test question information and the second picture parameters in one embodiment;

Fig. 4 is a flowchart of a method for determining the completeness of a second picture parameter in an embodiment;

FIG. 5 is a flow chart of a method for comparing first picture parameters and second picture parameters in an embodiment;

Fig. 6 is a structural block diagram of a test question picture optimization device in an embodiment;

Figure 7 is a block diagram of a computer device in one embodiment.

Embodiments of the present invention

The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

As shown in FIG. 1 , in one embodiment, a test question picture optimization method is provided, and the test question picture optimization method can be applied to both a terminal and a server, and this embodiment is illustrated by using a server as an example. The test question image optimization method specifically includes the following steps:

Step 102, building an initial test question picture library, which includes a plurality of initial test question pictures and first test question information and first picture parameters of each initial test question picture.

Among them, the initial test question picture refers to the qualified test question picture that is pre-entered into the server, and the initial test question picture library is composed of a plurality of initial test question pictures, so as to be subsequently used as a standard for measuring whether the test question picture taken or uploaded by the user satisfies optimization. The first test question information refers to the content information of the initial test question picture, such as OCR content information, and the first picture parameter refers to the parameters reflecting the quality of the initial test question picture, for example, the color information, resolution, completeness or angle of the test question picture.

Step 104, when receiving the image storage instruction, obtain the picture of the test question to be stored in the picture storage instruction, identify the picture of the test question to be stored, and obtain the second test item information and the second picture parameters of the test question picture to be stored in the storage .

Wherein, the picture to be stored refers to the test question picture taken or uploaded by the user, the second test question information is the content information of the test question picture to be stored, and the second picture parameter is the quality parameter of the test question picture to be stored. And the determination methods of the first test item information and the second test item information are consistent, for example, using the OCR recognition method for identification and acquisition, and the parameter types of the first picture parameters and the second picture parameters are consistent with the determination methods. It can be understood that in this embodiment, by obtaining the picture of the test question to be stored, based on the comparison between the picture of the test question to be stored and the picture of the initial test question, it is ensured that the picture of the test question with better quality and more abundant questions can be screened out later.

Step 106, based on the second test question information, search in the initial test question picture library.

Specifically, the second test question information is used as the search condition to search in the initial test question picture library, and determine whether the content information of the test question picture to be stored in the library is repeated with the content of an initial test question picture in the initial test question picture storehouse according to the search results, In order to ensure the accuracy of subsequent optimization of the initial test question image library.

Step 108: If there is first test item information consistent with the second test item information, the initial test item picture corresponding to the first test item information consistent with the second test item information is used as a candidate picture.

Wherein, the candidate picture refers to the initial test question picture whose content is repeated with that of the test question picture to be stored in the database. Specifically, when there is the first test item information that is consistent with the second test item information, it indicates that the content of the test item picture to be stored in the library is the same as the content of an initial test question picture in the initial test question image library, so it will be consistent with the second test item information The initial test question picture corresponding to the first test question information is used as a candidate picture, and then the quality comparison is performed based on the candidate picture, so as to realize automatic iteration and optimization of the test question picture.

Step 110, compare the first picture parameter and the second picture parameter of the candidate picture according to the preset comparison rules, and delete the candidate picture when the second picture parameter is better than the first picture parameter, and store the test questions The pictures are stored in the initial test question picture library.

Wherein, the preset comparison rule refers to a comparison rule for comparing the quality of the picture of the test question to be stored in the database with the picture of the initial test question. For example, it may be to directly compare the size of a parameter contained in the first picture parameter and the second picture parameter, or to separately calculate the parameters contained in the first picture parameter and the second picture parameter according to the calculation rule of weighted summation Compare the calculated results. As a preference in this embodiment, the latter comparison rule is selected to ensure the accuracy and comprehensiveness of the comparison.

When the second image parameter is better than the first image parameter, it indicates that the quality of the test question picture to be stored is better, so the candidate picture is deleted, and the test question picture to be stored is stored in the initial test question picture library, and the original test question picture is realized. The automatic iteration and optimization of the library improves the quality of the initial test question image library.

Step 112, if there is no first test item information consistent with the second test item information, construct a second test item image library, and store the test item images to be stored into the second test item image library.

Specifically, when there is no first test question information consistent with the second test question information, it indicates that the test question in the picture of the test question to be stored is a new question. The second test question picture library realizes the expansion of test question pictures and improves the richness of test question picture questions.

The above method for optimizing test question pictures is to construct an initial test question picture library, which contains a plurality of initial test question pictures and the first test question information and first picture parameters of each initial test question picture; when receiving the picture storage instruction, obtain The pictures of the test questions to be stored in the picture storage instruction are identified, and the second test question information and the second picture parameters of the test question pictures to be stored are obtained; based on the second test question information, in the initial test question picture library Retrieve; if there is the first test item information consistent with the second test item information, then the initial test item picture corresponding to the first test item information consistent with the second test item information is used as a candidate picture; the first picture parameter of the candidate picture and the second The picture parameters are compared according to the preset comparison rules. When the second picture parameter is better than the first picture parameter, delete the candidate picture, and store the test question pictures to be stored in the initial test question picture library; If the first test question information is consistent with the two test question information, the second test question picture library will be constructed, and the test question pictures to be stored will be stored in the second test question picture library. Iterates and stores, automatically optimizes the quality of picture questions, expands the number of questions in test picture pictures, and improves users' experience in answering test questions.

It is worth noting that, for the second test question picture library, when the test question picture to be stored is subsequently received, the method such as step 102-step 112 can be used to continue to optimize the second test question picture bank and build the third test question picture bank , so as to further optimize and iterate the pictures of the test questions, and further expand the number of questions for the picture questions.

As shown in Figure 2, in one embodiment, the picture of the test question to be stored is obtained by controlling the shooting device to take pictures of the picture question according to the preset photographing method, and the preset photographing method includes:

Step 104A, setting a shooting frame when starting the camera interface of the shooting device, and adjusting the picture title to be located in the shooting frame;

Step 104B, when the question number information of the picture question is detected, set at least one sub-shooting frame in the shooting frame according to the question number information and the corresponding question number position, and adjust the interval between each sub-shooting frame and the interval between each question number Take consistent photos to get the pictures of the test questions to be stored.

In this embodiment, the shooting frame is set when the camera interface of the shooting device is started, for example, in the interface for the user to take a picture of a picture question, a shooting mine with two horizontal and two vertical guide lines is set to guide the user to adjust the horizontal and vertical of the picture of the test question, thereby obtaining A relatively standard picture of the test questions to be stored. Further, when the question number information of the picture question is detected, the user can automatically pre-frame the test question according to the question number information and the question number position when the user takes a photo of the picture question, that is, set a sub-shooting mine for each question number, and adjust the frame size of each sub-shooting frame. The interval is consistent with the interval between each question number, so as to obtain standardized pictures of the test questions to be stored. Understandably, in this embodiment, by setting the shooting frame, the accuracy of the angles of the pictures of the test questions to be stored is ensured, making the pictures of the test questions to be stored more standardized.

As shown in Figure 3, in one embodiment, the second test question information and/or the first test question information include test question key text information, and the second picture parameters and/or the first picture parameters include picture file memory, resolution, color value and completeness; identify the picture of the test question to be stored, and obtain the second test question information and the parameters of the second picture of the picture of the test question to be stored, including:

Step 104C, using the optical character recognition method to recognize the initial test question picture to obtain the first test question information, and using the optical character recognition method to identify the test question picture to be stored in the storage to obtain the second test question information;

Step 104D, obtain the pixel information of the picture of the test question to be stored, and calculate the resolution and picture file memory based on the pixel information;

Step 104E, obtain the color depth and bit depth of the picture of the test question to be stored, and determine the color value based on the color depth and bit depth;

Step 104F, determine the completeness based on the key word information of the test question in the first test question information and the test question keyword information in the second test question information; or determine the completeness according to the second test question information.

In this embodiment, firstly, an optical character recognition algorithm is used to identify the initial test question pictures and the test question pictures to be stored in the database, so as to obtain the first test question information and the second test question information. Use the pixel acquisition tool in OPENCV to obtain the pixel information of the picture to be stored in the test question; according to the calculation formula of the picture file memory: picture file memory = picture length (pixel) x picture width (pixel) x memory space occupied by one pixel, calculated Image file memory. According to the calculation formula of resolution: resolution = image length (pixel) × image width (pixel), calculate the resolution. Bit depth refers to the number of bits used to store each pixel, and color depth refers to how many bits each pixel uses to store the color. Obtain the color depth and bit depth of the picture of the test question to be stored, and determine the color value according to the color depth and bit depth. For example, the sum or product of the color depth and bit depth can be calculated as the color value. Completeness is a parameter used to reflect the completeness of the picture of the test question to be stored in the database. The completeness can be determined according to the key word information of the test question in the first test question information and the test question keyword information in the second test question information. For example, when the first test question information The key text information of the test questions in the test question information and the test question keyword information in the second test question information are completely consistent, then it is judged that the completeness of the second picture parameter is 100%, the first test question information in the initial test question bank contains the second test question information, and it is judged that The completeness in the second picture parameter is less than 100%, specifically, the completeness can be set to 0. Alternatively, the completeness is determined according to the second test item information, and the completeness in the second picture parameter may be judged according to the semantic information of the second test item information. It can be understood that in this embodiment, by analyzing the pictures of the test questions to be stored, the quantitative calculation of the parameters of the second picture is realized, so that more accurate comparison and optimization can be performed based on the parameters of the second picture. It should be noted that the calculation method of the first picture parameter of the initial test question picture is consistent with the calculation method of the second picture parameter, so as to ensure the accuracy of the subsequent comparison.

As shown in Figure 4, in one embodiment, the completeness is determined according to the second test question information, including:

Step 104F1, respectively analyzing the test question key text information, picture information and table information in the second test question information, detecting whether the numbers corresponding to the question numbers in the test question key text information are continuous, and obtaining the first detection result;

Step 104F2, detecting whether there is picture information or table information consistent with the semantics of the key text information of the test question in the second test question information, and obtaining the second test result;

Step 104F3, determine the completeness according to the first detection result and the second detection result.

In this embodiment, the test question key text information, picture information and table information in the second test question information are respectively analyzed to detect whether the numbers corresponding to the question numbers in the test question key text information are continuous, and the first detection result is obtained. When the number corresponding to the question number is continuous, the first test result is determined to be complete; when the number corresponding to the question number is not continuous, the first test result is determined to be incomplete. For example, the key text information of the test question has subtitle (1) but no subtitle (2) etc. Detect whether there is picture information or table information consistent with the semantics of the key text information of the test question in the second test question information, and when there is picture information or table information consistent with the semantics of the key text information of the test question, it is determined that the second detection result is complete. When there is picture information or table information that is semantically consistent with the key text information of the test question, it is determined that the second test result is incomplete, for example, the key text of the test question contains "picture", "see table", etc. There are picture information and table information, which realizes the efficient detection of the completeness of the second picture parameters.

As shown in FIG. 5, in one embodiment, the first picture parameter and the second picture parameter of the candidate picture are compared according to a preset comparison rule, including:

Step 110A, obtain the preset weights corresponding to the picture file memory, resolution, color value and completeness;

Step 110B, for the first picture parameter, perform weighted calculation based on the picture file memory, resolution, color value and integrity and the corresponding preset weight, to obtain the first target parameter;

Step 110C, for the second picture parameters, perform weighted calculation based on the picture file memory, resolution, color value and integrity and the corresponding preset weights to obtain the second target parameters;

Step 110D, when the second target parameter is greater than the first target parameter, it is determined that the second picture parameter is better than the first picture parameter.

In this embodiment, preset weights corresponding to image file memory, resolution, color value, and completeness are obtained in advance, and then weighted summation calculations are performed based on each parameter value in the first image parameter and the second image parameter, thereby realizing The quantitative calculation of the parameters of the first picture and the parameters of the second picture is carried out to obtain specific values, which ensures the accuracy and comprehensiveness of the comparison.

In one embodiment, based on the second test question information, searching in the initial test question picture library includes: using the first test question information as the first index value of the initial test question picture, and using the second test question information as the test question picture to be stored in the library of the second index value; searching among multiple first index values to find out whether there is a first index value consistent with the second index value.

Specifically, the first test question information is used as the first index value of the initial test question picture, and the second test question information is used as the second index value of the test question picture to be stored in the library, and a plurality of first index values are searched to find out whether there is a The second index value is consistent with the first index value, so it only needs to match the first index value and the second index value, which improves retrieval efficiency.

In one embodiment, after storing the test question pictures to be stored in the second test question picture library, the method further includes: when the user answering instruction is detected, acquiring the target index value contained in the user answering instruction; value, search for the corresponding target test question picture in the initial test question picture library and the second question picture library; send the target test question picture to the user for answering.

Specifically, since the target test question picture is an iteratively optimized test question picture, it is always kept that the user uses the picture question with the best quality so far, which improves the user experience.

As shown in Figure 6, in one embodiment, a device for optimizing test question images is proposed, the device comprising:

A construction module 602, configured to construct an initial test question picture library, the initial test question picture library including a plurality of initial test question pictures and first test question information and first picture parameters of each of the initial test question pictures;

The receiving module 604 is configured to obtain the picture of the test question to be stored included in the picture storage instruction when receiving the picture storage instruction, identify the test question picture to be stored, and obtain the test question picture to be stored The second test question information and the second picture parameters;

A retrieval module 606, configured to search in the initial test question picture library based on the second test question information;

A determining module 608, configured to use the initial test question picture corresponding to the first test question information consistent with the second test question information as a candidate picture if there is first test question information consistent with the second test question information;

A comparison module 610, configured to compare the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and if the second picture parameter is better than the first picture parameter , delete the candidate picture, and store the test question picture to be stored in the initial test question picture library;

The storage module 612 is configured to construct a second test question image library if there is no first test item information consistent with the second test item information, and store the test question pictures to be stored into the second test item image library.

In one embodiment, the receiving module includes:

A first adjustment unit, configured to set a shooting frame when starting the camera interface of the shooting device, and adjust the picture title to be located in the shooting frame;

The second adjustment unit is configured to set at least one sub-frame in the frame according to the frame information and the corresponding position of the frame when detecting the frame number information of the picture frame, and adjust each of the frame frames. The intervals between the shooting frames are consistent with the intervals between the various question numbers to obtain the pictures of the test questions to be stored.

In one embodiment, the receiving module also includes:

The recognition unit is configured to use an optical character recognition method to recognize the picture of the initial test question to obtain the information of the first test question, and use an optical character recognition method to recognize the picture of the test question to be stored in the database to obtain the second test question information;

A calculation unit, configured to obtain pixel information of the picture of the test question to be stored, and calculate the resolution and the memory of the picture file based on the pixel information;

A first determining unit, configured to acquire the color depth and bit depth of the picture of the test question to be stored, and determine the color value based on the color depth and bit depth;

The second determining unit is configured to determine the completeness based on the test question key word information in the first test question information and the test question keyword information in the second test question information; or, determine the completeness according to the second test question information completeness of description.

In one embodiment, the second determination unit includes:

The analysis subunit is used to analyze the test question key text information, picture information and table information in the second test question information, and detect whether the numbers corresponding to the question numbers in the test question key text information are continuous, and obtain the first detection result;

The detection subunit is used to detect whether there is picture information or table information consistent with the semantics of the key text information of the test item in the second test item information, and obtain a second test result;

A determining subunit, configured to determine the completeness according to the first detection result and the second detection result.

In one embodiment, the comparison module includes:

An acquisition unit, configured to acquire preset weights corresponding to memory, resolution, color value and integrity of the image file;

The first calculation unit is configured to perform weighted calculations for the first picture parameters based on the picture file memory, resolution, color value and integrity and corresponding preset weights to obtain the first target parameters;

The first calculation unit is configured to perform weighted calculations for the second picture parameters based on the picture file memory, resolution, color value and completeness and corresponding preset weights to obtain second target parameters;

A third determining unit, configured to determine that the second picture parameter is better than the first picture parameter when the second target parameter is greater than the first target parameter.

In one embodiment, the retrieval module includes:

An identification unit, configured to use the first test question information as the first index value of the initial test question picture, and use the second test question information as the second index value of the test question picture to be stored;

A searching unit, configured to search among a plurality of first index values, and find whether there is the first index value consistent with the second index value.

In one embodiment, the test question picture optimization device also includes:

A detection module, configured to obtain the target index value contained in the user answering instruction when the user answering instruction is detected;

A search module, configured to search for a corresponding target test question picture in the initial test question picture library and the second question picture library according to the target index value;

A sending module, configured to send the target test question picture to the user for answering the question.

Figure 7 shows a diagram of the internal structure of a computer device in one embodiment. Specifically, the computer device may be a server, and the server includes but is not limited to a high-performance computer and a cluster of high-performance computers. As shown in FIG. 7, the computer device includes a processor, a memory, and a network interface connected through a system bus. Wherein, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store computer-readable instructions. When the computer-readable instructions are executed by the processor, the computer-readable instructions can cause the processor to implement Optimization. The internal memory may also store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the test question picture optimization method. Those skilled in the art can understand that the structure shown in Figure 7 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, the test question picture optimization method provided by the present application can be realized in the form of a computer readable instruction computer readable instruction, and the computer readable instruction computer readable instruction can be run on a computer device as shown in FIG. 7 . Various program templates constituting the test question picture optimization device can be stored in the memory of the computer equipment. For example, a construction module 602 , a receiving module 604 , a retrieval module 606 , a determination module 608 , a comparison module 610 , and a storage module 612 .

A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing the computer readable instructions The following steps are implemented during the instruction: constructing an initial test question picture library, said initial test question picture storehouse comprising a plurality of initial test question pictures and the first test question information and first picture parameters of each said initial test question picture; when receiving the picture storage instruction , obtain the picture of the test question to be stored in the instruction for storing the picture, identify the picture of the test question to be stored in the store, and obtain the second test question information and the second picture parameters of the picture of the test question to be stored in the store; based on the The second test question information is searched in the initial test question picture library; if there is the first test question information consistent with the second test question information, the initial test question corresponding to the first test question information consistent with the second test question information A picture is used as a candidate picture; comparing the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and when the second picture parameter is better than the first picture parameter, Deleting the candidate picture, and storing the test question picture to be stored in the initial test question picture storehouse; if there is no first test question information consistent with the second test question information, then constructing the second test question picture storehouse, and The pictures of the test questions to be stored are stored in the second test question picture database.

In one embodiment, the picture of the test questions to be stored is obtained by controlling the shooting device to take pictures of the picture questions according to a preset way of taking pictures, and the preset way of taking pictures includes: Set the shooting frame, adjust the picture title to be located in the shooting frame; when the question number information of the picture question is detected, set at least one in the shooting frame according to the question number information and the corresponding question number position Sub-shooting frames, adjust the intervals of each sub-shooting frame to be consistent with the intervals between each question number, and shoot to obtain the pictures of the test questions to be stored.

In one embodiment, the second test question information and/or the first test question information includes test question key text information, and the second picture parameters and/or first picture parameters include picture file memory, resolution, color value and completeness. degree; the identifying the picture of the test question to be stored in the database, and obtaining the second test question information and the second picture parameters of the picture of the test question to be stored in the database, includes: using an optical character recognition method to identify the initial test question picture, Obtaining the first test item information, and using an optical character recognition method to identify the picture of the test question to be stored, and obtaining the second test item information; acquiring the pixel information of the picture of the test question to be stored, based on the pixel information Calculate the resolution and the image file memory; obtain the color depth and bit depth of the test question picture to be stored, and determine the color value based on the color depth and bit depth; based on the first test question information The completeness is determined according to the key text information of the test question and the key word information of the test question in the second test question information; or, the completeness is determined according to the second test question information.

In one embodiment, the determining the completeness according to the second test item information includes: respectively analyzing the test item key text information, picture information and form information in the second test item information, and detecting the test item Whether the number corresponding to the question number in the key text information is continuous, obtains the first test result; detects whether there is picture information or form information consistent with the semantics of the key text information of the test question in the second test question information, and obtains the second test result Result; determining the completeness according to the first detection result and the second detection result.

In one embodiment, the comparing the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule includes: acquiring the memory, resolution, and color value of the picture file and the preset weight corresponding to the completeness; for the first picture parameter, weighted calculation is performed based on the picture file memory, resolution, color value and completeness and the corresponding preset weight to obtain the first target parameter; for the first picture parameter The second picture parameter is weighted calculation based on the picture file memory, resolution, color value and integrity and the corresponding preset weight to obtain the second target parameter; when the second target parameter is greater than the first target parameters, it is determined that the second picture parameter is better than the first picture parameter.

In one embodiment, the searching in the initial test question picture library based on the second test question information includes: using the first test question information as the first index value of the initial test question picture, and setting The second test question information is used as the second index value of the test question picture to be stored in the library; searching among multiple first index values to find out whether there is the first index value consistent with the second index value.

In one embodiment, after storing the test question pictures to be stored in the second test question picture library, the method further includes: when a user answering instruction is detected, acquiring the user answering instruction The target index value contained in; according to the target index value, search for the corresponding target test picture in the initial test picture library and the second question picture library; send the target test picture to the user for answering .

A computer-readable storage medium, the computer-readable storage medium stores computer-readable instructions computer-readable instructions, characterized in that, when the computer-readable instructions are executed by a processor, the following steps are implemented: constructing An initial test question picture library, the initial test question picture bank includes a plurality of initial test question pictures and the first test question information and first picture parameters of each of the initial test question pictures; The picture of the test question to be stored in the library instruction is identified, and the second test question information and the second picture parameters of the picture of the test question to be stored in the picture are obtained; based on the second test question information, in Retrieve in the initial test question picture library; if there is the first test question information consistent with the second test question information, then use the initial test question picture corresponding to the first test question information consistent with the second test question information as a candidate picture; The first picture parameter of the candidate picture is compared with the second picture parameter according to a preset comparison rule, and when the second picture parameter is better than the first picture parameter, the candidate picture is deleted, and Put the pictures of the test questions to be stored into the initial test question picture library; if there is no first test question information consistent with the second test question information, build a second test question picture library, and store the test question pictures to be stored Stored in the second test question image library.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized by computer-readable instructions and computer-readable instructions to instruct related hardware, and the program can be stored in a non-volatile In the computer-readable storage medium, when the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims

A test question picture optimization method is characterized in that the method comprises:

Constructing an initial test question picture library, said initial test question picture bank comprising a plurality of initial test question pictures and first test question information and first picture parameters of each said initial test question picture;

When receiving the image storage instruction, obtain the test question picture to be stored in the picture storage instruction, identify the test question picture to be stored, and obtain the second test item information and the test question picture to be stored in the storage. Second picture parameter;

Searching in the initial test question image library based on the second test question information;

If there is first test item information consistent with the second test item information, the initial test item picture corresponding to the first test item information consistent with the second test item information is used as a candidate picture;

comparing the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and deleting the candidate picture when the second picture parameter is better than the first picture parameter , and store the picture of the test question to be stored into the library of the initial test question picture;

If there is no first test item information consistent with the second test item information, a second test item image library is constructed, and the test item images to be stored are stored in the second test item image library.
The test question picture optimization method according to claim 1, wherein the test question picture to be stored is obtained by controlling the photographing device to take pictures of the picture questions according to a preset photographing mode, and the preset photographing mode includes:

When starting the photographing interface of the photographing device, a photographing frame is set, and the title of the picture is adjusted to be located in the photographing frame;

When the question number information of the picture question is detected, at least one sub-shooting frame is set in the shooting frame according to the question number information and the corresponding question number position, and the interval between each sub-shooting frame and each question are adjusted. The intervals between the numbers are consistent to shoot, and the pictures of the test questions to be stored are obtained.
The test question picture optimization method according to claim 1, wherein the second test question information and/or the first test question information includes test question key text information, and the second picture parameter and/or the first picture parameter includes a picture File memory, resolution, color value and completeness; said identifying the picture of the test question to be stored in the database, and obtaining the second test question information and the second picture parameters of the picture of the test question to be stored in the database, including:

Using an optical character recognition method to recognize the initial test question picture to obtain the first test question information, and using an optical character recognition method to recognize the test question picture to be stored to obtain the second test question information;

Obtain the pixel information of the picture of the test question to be stored, and calculate the resolution and the memory of the picture file based on the pixel information;

Acquiring the color depth and bit depth of the picture of the test question to be stored, and determining the color value based on the color depth and bit depth;

The completeness is determined based on the key word information of the test question in the first test question information and the test question keyword information in the second test question information; or, the completeness is determined according to the second test question information.
The test question picture optimization method according to claim 1, wherein said determining said completeness according to said second test question information comprises:

Analyzing the test question key text information, picture information and table information in the second test question information respectively, detecting whether the numbers corresponding to the question numbers in the test question key text information are continuous, and obtaining the first detection result;

Detecting whether there is picture information or form information consistent with the semantics of the key text information of the test in the second test item information, and obtaining a second test result;

The completeness is determined based on the first detection result and the second detection result.
The test question picture optimization method according to claim 3, wherein said comparing the first picture parameter of said candidate picture with said second picture parameter according to a preset comparison rule comprises:

Acquiring preset weights corresponding to memory, resolution, color value and completeness of the image file;

For the first picture parameter, perform weighted calculation based on the picture file memory, resolution, color value and integrity and the corresponding preset weight to obtain the first target parameter;

For the second picture parameter, perform weighted calculation based on the picture file memory, resolution, color value and integrity and the corresponding preset weight to obtain the second target parameter;

When the second target parameter is greater than the first target parameter, it is determined that the second picture parameter is better than the first picture parameter.
The test question picture optimization method according to claim 2, wherein said searching in said initial test question picture library based on said second test question information includes:

Using the first test question information as the first index value of the initial test question picture, and using the second test question information as the second index value of the test question picture to be stored;

Searching among multiple first index values to find out whether there is the first index value consistent with the second index value.
The test question picture optimization method according to claim 6, characterized in that, after storing the test question picture to be stored in the second test question picture library, the method further comprises:

When the user answering instruction is detected, the target index value contained in the user answering instruction is obtained;

According to the target index value, search for a corresponding target test question picture in the initial test question picture library and the second question picture library;

Sending the picture of the target test question to the user for answering the question.
A test question picture optimization device, characterized in that the test question picture optimization device comprises:

A construction module for constructing an initial test question image library, the initial test question image library including a plurality of initial test question pictures and first test question information and first picture parameters of each of the initial test question pictures;

The receiving module is configured to obtain the picture of the test questions to be stored included in the picture storage instruction when receiving the picture storage instruction, identify the picture of the test questions to be stored, and obtain the picture of the test questions to be stored The second test question information and the second picture parameters;

A retrieval module, configured to search in the initial test question picture library based on the second test question information;

A determining module, configured to use the initial test question picture corresponding to the first test question information consistent with the second test question information as a candidate picture if there is first test question information consistent with the second test question information;

A comparison module, configured to compare the first picture parameter of the candidate picture with the second picture parameter according to a preset comparison rule, and when the second picture parameter is better than the first picture parameter , deleting the candidate picture, and storing the test question picture to be stored in the initial test question picture library;

The storage module is configured to construct a second test question picture library if there is no first test question information consistent with the second test question information, and store the test question pictures to be stored into the second test question picture bank.
A computer device, characterized in that it comprises a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor executes the When the computer-readable instructions are computer-readable instructions, the steps of the test question picture optimization method according to any one of claims 1 to 7 are realized.
A computer-readable storage medium, the computer-readable storage medium stores computer-readable instructions and computer-readable instructions, characterized in that, when the computer-readable instructions are executed by a processor, the computer-readable instructions of claim 1 are implemented. Steps in the test question image optimization method described in any one of 7 to 7.