A test question generation method, device and equipment

Abstract

The application discloses a test question generation method, device and equipment, the method comprises the following steps: receiving a test question generation request; determining the examination content matched with the test question generation request, wherein the examination content has relevance with the operation difficulty of the operation object to the processing object in the recognition result of the operation video; generating the examination test question according to the examination content. In this way, the operation video is automatically recognized in advance, in the test question generation process, the examination content is determined in combination with the operation difficulty of the operation object to the processing object in the recognition result of the operation video, the test question with controllable difficulty is automatically generated, the process that the test question is artificially generated after the operation video is artificially understood and summarized is effectively avoided, the human cost is significantly saved, and the test question difficulty has strong explainability, and the examination content for the whole operation video is relatively balanced.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a method, apparatus and equipment for generating test questions. Background Technology

[0002] Online education and training have developed rapidly in recent years, making the evaluation of their effectiveness a major undertaking, especially for practical courses. Currently, the main method involves training instructors manually generating multiple test questions based on the training videos, which is highly inefficient, time-consuming, and labor-intensive. Summary of the Invention

[0003] This application provides a method, apparatus, and device for generating test questions.

[0004] According to a first aspect of this application, a test question generation method is provided, the method comprising: receiving a test question generation request; determining examination content matching the test question generation request, wherein the examination content is correlated with the difficulty of operation of the operation object to the processing object in the recognition result of the operation video to be examined; and generating examination questions based on the examination content.

[0005] According to one embodiment of this application, determining the examination content that matches the test question generation request includes: determining the operation steps that match the test question generation request; and determining the examination content based on the determined operation steps.

[0006] According to one embodiment of this application, the step of determining the operation step that matches the test question generation request includes: parsing the test question generation request to obtain the examination difficulty coefficient; and selecting an operation step from the operation steps that match the examination difficulty coefficient.

[0007] According to one embodiment of this application, the test question generation request carries a test question type; correspondingly, generating test questions based on the test content includes: processing the test content in accordance with the test question type.

[0008] According to an embodiment of this application, the recognition result is obtained in advance through the following operations: acquiring multiple frames of video images of the operation video; performing image recognition on the multiple frames of video images to obtain a first state change of the operation object and a second state change of the processing object; determining multiple operation steps of the operation object on the processing object based on the second state change; and determining the operation difficulty of the operation object on the processing object in the operation steps based on the first state change in the operation steps.

[0009] According to an embodiment of this application, the step of performing image recognition on the multi-frame video images includes: performing image recognition on the video images to obtain a first positional relationship between the operation object and the processing object and a second positional relationship between the processing object and the processing tool; and determining the first state change based on the first positional relationship and the second positional relationship in the video images of a first set frame.

[0010] According to one embodiment of this application, the step of determining multiple operation steps of the operation object on the processing object based on the second state change includes: detecting a first image including the processing object in the multi-frame video images; and determining the operation of the operation object on the processing object in the second set frame as an operation step when the second state change of the first image in the second set frame meets a first condition.

[0011] According to an embodiment of this application, determining the operational difficulty of the operation object for the processing object in the operation step based on the first state change in the operation step includes: determining the number of hand shape changes, finger operation precision, and hand coordination state of the operation object in the operation step based on the second state change of the operation object in the operation step; assigning values ​​to the number of hand shape changes, the finger operation precision, and the hand coordination state according to a set assignment rule; and performing a weighted summation of the assigned values ​​of the number of hand shape changes, the finger operation precision, and the hand coordination state to determine the operational difficulty of the operation step.

[0012] According to a second aspect of this application, a test question generation apparatus is also provided, the apparatus comprising: a request receiving module for receiving a test question generation request; a content determining module for determining examination content matching the test question generation request, wherein the examination content is correlated with the difficulty of operation of the operation object to the processing object in the recognition result of the operation video to be examined, the recognition result including the processing difficulty of the operation steps of the operation object to the processing object; and a generation module for generating examination questions based on the examination content.

[0013] According to a third aspect of this application, an apparatus is also provided, the apparatus comprising at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; the processor is used to call program instructions in the memory to execute the above-described test question generation method.

[0014] In the test question generation method, apparatus, and device of this application embodiment, a test question generation request is received; examination content matching the test question generation request is determined, wherein the examination content is correlated with the difficulty of the operation of the object to be processed in the recognition result of the operation video to be examined; and examination questions are generated according to the examination content. Thus, the operation video is automatically recognized in advance, and during the test question generation process, the examination content is determined by combining the difficulty of the operation of the object to be processed in the recognition result of the operation video, automatically generating test questions with controllable difficulty. This effectively avoids the process of manually generating examination questions after understanding and summarizing the operation video, significantly saving labor costs. Furthermore, the difficulty of the test questions is highly interpretable, and the examination content for the entire operation video is relatively balanced.

[0015] It should be understood that the teachings of this application are not required to achieve all the beneficial effects described above, but rather that specific technical solutions can achieve specific technical effects, and other embodiments of this application can also achieve beneficial effects not mentioned above. Attached Figure Description

[0016] The above and other objects, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated in the drawings by way of example and not limitation, wherein:

[0017] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0018] Figure 1 A schematic diagram illustrating the implementation flow of the test question generation method according to an embodiment of this application is shown;

[0019] Figure 2 A schematic diagram of the input interface for a test question generation request according to an embodiment of this application is shown;

[0020] Figure 3 A schematic diagram of the input interface for a test question generation request according to another embodiment of this application is shown;

[0021] Figure 4 This paper illustrates a schematic diagram of the implementation flow of the operational video recognition process in the test question generation method of this application embodiment;

[0022] Figure 5 This application shows a video frame in which the processing object is processed according to an embodiment of the present application;

[0023] Figure 6 Another video frame is shown in an embodiment of this application, showing the operation of processing the object.

[0024] Figure 7This illustrates another frame of video image in an embodiment of this application, showing the operation of processing the object.

[0025] Figure 8 A schematic diagram of the composition structure of the test question generation device according to an embodiment of this application is shown;

[0026] Figure 9 A schematic diagram of the composition structure of the device according to an embodiment of this application is shown. Detailed Implementation

[0027] The principles and spirit of this application will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement this application, and are not intended to limit the scope of this application in any way. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0028] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] Figure 1 The diagram illustrates the implementation flow of the test question generation method according to an embodiment of this application.

[0030] refer to Figure 1 The test question generation method of this application embodiment includes at least the following operation process: operation 101, receiving a test question generation request; operation 102, determining the examination content that matches the test question generation request, wherein the examination content is related to the difficulty of the operation of the operation object to the processing object in the recognition result of the operation video to be examined; operation 103, generating examination questions according to the examination content.

[0031] In operation 101, a question generation request is received.

[0032] In this embodiment of the application, the test question generation request can carry the difficulty level of the operation on the processing object. Specifically, this can be achieved by configuring a button on the device display interface for sending the test question generation request. The display interface can also include an input box for entering the operation difficulty or a selection bar for choosing the difficulty level. Correspondingly, a button can be configured to confirm the input or selected difficulty level, displaying options such as "OK" or "Generate Test Questions." Here, the difficulty level can be a fixed value or a difficulty range.

[0033] In this embodiment of the application, the test question generation request may also carry operation steps. Here, the operation steps may simply be the sequence number of the operation steps, or they may include a brief description of the operation steps such as "power on / power off" or "open the back cover".

[0034] In this embodiment of the application, the difficulty coefficient can also be determined by selecting the operation difficulty of the operation object in the operation video to the processing object based on the recognition result of the operation video.

[0035] Here, since the recognition results of the operation video can include multiple operation steps, and the operation difficulty of the object in each operation step is a definite difficulty, to avoid conflicts between the input operation steps and the operation difficulty, it can be set so that only one of the operation steps and operation difficulty can be selected or input. Alternatively, after determining the operation video to be examined, options for operation steps and corresponding examination difficulty coefficients can be generated. After selecting one operation step, the examination difficulty coefficient field displays the examination difficulty coefficient corresponding to the operation difficulty of the object in that operation step. After selecting an examination difficulty coefficient, the operation step field can only select operation steps that match that examination difficulty coefficient.

[0036] Figure 2 A schematic diagram of the input interface for a test question generation request in this embodiment of the present application is shown. It should be noted that... Figure 2 This is merely one example for reference. In actual applications, the input interface for the test question generation request can be configured as needed.

[0037] In operation 102, the examination content that matches the test question generation request is determined. The examination content is related to the difficulty of the operation object to the processing object in the recognition result of the operation video to be examined.

[0038] In this embodiment of the application, the recognition result of the operation video to be examined can be completed in advance. That is, the recognition result obtained by completing one operation video can be applied in multiple question generation processes for the same video.

[0039] The recognition results of operation videos can include multiple operation steps and the difficulty of the operation between the operation object and the processing object in each step. Operation videos can be repair videos of electronic devices such as mobile phones or computers, or videos of equipment assembly processes. The operation object can be a person, a robot, etc., and the processing object can be electronic equipment, etc. The method of identifying the difficulty of the operation between the operation object and the processing object can be set according to actual needs.

[0040] The process of recognizing the operation video will be combined below. Figure 4 The following is an example illustration, which will not be elaborated further here.

[0041] In this embodiment of the application, the following operation can be used to determine the examination content that matches the test question generation request: determine the operation steps that match the test question generation request, and then determine the examination content based on the determined operation steps.

[0042] In this embodiment of the application, the test question generation request may carry only the test difficulty coefficient or operation steps, or it may carry both the test difficulty coefficient and operation steps.

[0043] In this embodiment of the application, if the test question generation request only carries the test difficulty coefficient, the test question generation request can be parsed to obtain the test difficulty coefficient, and an operation step can be selected from the operation steps that meet the test difficulty coefficient.

[0044] Here, the difficulty level can be a specific value or a range of values. Furthermore, the difficulty level can also be categorized as low, medium, high, or extremely high.

[0045] In this embodiment of the application, each operation step may include multiple assessment points. After determining the assessment step that matches the question generation request, one of the multiple assessment points included in that operation step can be randomly selected as the assessment content that matches the question generation request.

[0046] In Operation 103, test questions are generated based on the content to be tested.

[0047] In this embodiment of the application, the question generation request carries the question type. Accordingly, the examination content can be processed in accordance with the question type to generate examination questions based on the examination content.

[0048] In this embodiment of the application, the question type carried in the question generation request may include multiple-choice questions, true / false questions, open-ended questions, fill-in-the-blank questions, or analytical questions, etc. The question type can also be displayed through an input box or selection bar, and is entered by the user.

[0049] Figure 3 A schematic diagram of the input interface for requesting test questions is shown. Similarly, Figure 3 This is merely one example for reference. In actual applications, the input interface for the question generation request can be configured as needed.

[0050] Here, you can select or input a single operation video, or select or input a collection of operation videos, such as those from a specific series of mobile phone repair videos. For operation steps, you can select or input a specific operation step, or select or input a set number of operation steps, etc.

[0051] Furthermore, in this embodiment of the application, the method for requesting test questions can be configured to require input of at least one of the following: operation video, operation steps, examination difficulty coefficient, and test question type. Alternatively, it can be configured to require input of two or more. It can also be configured to retrieve other selections corresponding to the input content after one of the inputs is entered. Specifically, if operation video 3 is selected, a drop-down menu of operation steps will be displayed, temporarily showing the operation steps included in the recognition results of operation video 3. The examination difficulty coefficient column will display the processing difficulty of the operation object relative to the processing object in each operation step. The test question type can be displayed relatively independently.

[0052] Figure 3 and the preceding text Figure 2 The "Reset" option displayed can be used to instruct users to clear the content already entered in options such as "Operation Video", "Operation Steps", "Examination Difficulty Level" and "Question Type".

[0053] In this embodiment of the application, a question generation model can be generated based on a large number of operation video samples that have already been labeled with operation difficulty. Specifically, it can include questions such as, "What tools are used in operation step X?". Based on the recognition results of the pre-identified operation videos, questions that meet the expected difficulty can be generated quickly, and the difficulty of the questions has strong interpretability.

[0054] Figure 4 This diagram illustrates the implementation flow of the video recognition process in the test question generation method of this application.

[0055] like Figure 4 As shown in this embodiment of the present application, the operation video recognition process in the test question generation method of this application embodiment may include: operation 401, acquiring multiple frames of operation video images; operation 402, performing image recognition on the multiple frames of video images to obtain a first state change of the operation object and a second state change of the processing object; operation 403, determining multiple operation steps of the operation object on the processing object based on the second state change; operation 404, determining the operation difficulty of the operation object on the processing object in the operation steps based on the first state change in the operation steps.

[0056] In operation 401, multiple frames of video images of the operation video are acquired.

[0057] In operation 402, image recognition is performed on multiple frames of video images to obtain the first state change of the object being operated on and the second state change of the object being processed.

[0058] In this embodiment of the application, the following operation can be used to perform image recognition on multiple frames of video images: perform image recognition on the video images to obtain the first positional relationship between the operation object and the processing object and the second positional relationship between the processing object and the processing tool, and determine the first state change based on the first positional relationship and the second positional relationship in the video image of the first set frame.

[0059] Figure 5 This illustration shows a frame of video image in which the processing object is processed according to an embodiment of this application.

[0060] Figure 6 Another frame of video image is shown in an embodiment of this application, showing the operation of processing the object.

[0061] refer to Figure 5 and Figure 6 In this embodiment of the application, the object of operation is a person, which can be obtained by performing hand recognition on the video image. The processing object is the repair object in the figure: the mobile phone, and the processing tool is the repair tool in the figure: the hot air blower. The multi-frame video image also includes multiple images related to... Figure 5 Similar video images, these video images are Figure 5 The difference lies in the change in the position of the hot air blower on the surface of the phone.

[0062] from Figures 5 to 6 These two video frames reveal a change in the initial positional relationship between the manipulated object and the processed object, from... Figure 5 The handheld hot air blower in the middle has changed to Figure 6 There is no hot air blower in the hand. The second positional relationship between the object being processed and the processing tool has changed; the relationship between the phone and the hot air blower has changed from overlapping to unrelated. Therefore, the first state change of the object being processed has changed from "moving on the phone surface" to "leaving the phone surface." This change can be identified as an operation step – the hot air blower on the back of the phone.

[0063] It should be noted that this is only based on Figure 5 and Figure 6 As an example, in actual applications, there are various types of operation videos, and the results that can be identified are consistent with the actual examination requirements. This application does not impose any further limitations on this.

[0064] In operation 403, based on the second state change, multiple operation steps of the operation object on the processing object are determined.

[0065] In this embodiment of the application, the following operation can be used to determine multiple operation steps of the operation object on the processing object based on the second state change: detect a first image including the processing object in a multi-frame video image, and when the second state change of the first image in the second set frame meets the first condition, determine the operation of the operation object on the processing object in the second set frame as an operation step.

[0066] Figure 7 This illustrates another frame of video image showing the operation of processing the object in an embodiment of this application.

[0067] refer to Figure 7 In this embodiment of the application, the object of operation is a person, which can be obtained by performing hand recognition on the video image; the object being processed is the repair object in the figure: the mobile phone. Figure 7 Image recognition can detect changes in the state of the object being repaired, such as a change from an on state to an off state. Therefore, based on... Figure 7 This frame of video image recognition obtains the "shutdown" operation steps of the operation object on the processing object.

[0068] It should be noted that, Figure 7 This frame image can be compared to... Figure 5 and Figure 6 They belong to the same operation video. Figure 7 The video images in the sequence are located in time. Figure 5 and Figure 6 Previously, the operation instructions in the image were text descriptions of the video itself, and the text recognition results in the video image could also be used as a reference for identifying the operation steps. The identification of the operation object, processing object, and processing tool can be achieved using image recognition and other technologies commonly used in this field.

[0069] In operation 404, the difficulty of the operation on the processing object is determined based on the first state change in the operation step.

[0070] In this embodiment of the application, the following operation can be used to determine the operation difficulty of the operation object on the processing object in the operation step based on the first state change in the operation step: based on the second state change of the operation object in the operation step, determine the number of hand shape changes, finger operation precision, and hand coordination state of the operation object in the operation step; assign values ​​to the number of hand shape changes, finger operation precision, and hand coordination state according to the set assignment rules; and perform a weighted summation of the assigned values ​​of the number of hand shape changes, finger operation precision, and hand coordination state to determine the operation difficulty of the operation step.

[0071] Return to reference Figures 5-7Based on the initial state change of the object being operated on, the difficulty of the operation is determined in each step, i.e., the repair difficulty is identified based on the changes in the repairer's operation state on the phone. Here, the difficulty of the operation can be judged by comprehensively considering the number of hand gesture changes, finger operation precision, and hand coordination in the "opening the back cover" step. Specifically, the average of the three factors—the number of hand gesture changes, finger operation precision, and hand coordination—can be calculated as y = 1 / 3(a + b + c), where:

[0072] 'a' represents the number of hand shape changes. In this example of the application, the repairman's hand shape changes were detected 3 times by image recognition, so 'a' is 3.

[0073] b represents the precision of finger operation, which is the reciprocal of the ratio of the distance of change in the range of the repairman's finger operation to the length of the finger. Here, if the range of the finger operation is 0.2cm and the circumference of the finger is 1cm, then the precision of operation is 1 / (0.2 / 1) = 5.

[0074] c represents the state of cooperating with both hands. In this embodiment of the application, the following settings can be made: if the right hand is the main operator in this step and the left hand is in the state of holding the phone, the difficulty of the operation is 1; if there are 3 instances of the left hand moving and the right hand holding the phone in this step, the difficulty increases by 3; if there are 2 instances of both hands operating simultaneously in this step, the difficulty increases by 2×2=4; therefore, the difficulty of the state of cooperating with both hands is 1+3+4=8.

[0075] Therefore, the difficulty of the operation between the operation object and the processing object in this operation step is y = (3 + 5 + 8) / 3 = 5.3.

[0076] Here, different weights can be assigned to the number of hand gesture changes, finger operation precision, and hand coordination state, and a weighted average can be calculated for the number of hand gesture changes, finger operation precision, and hand coordination state.

[0077] In the test question generation method, apparatus, and device of this application embodiment, a test question generation request is received; examination content matching the test question generation request is determined, wherein the examination content is correlated with the difficulty of the operation of the object to be processed in the recognition result of the operation video to be examined; and examination questions are generated based on the examination content. Thus, the operation video is automatically recognized in advance, and during the test question generation process, the examination content is determined by combining the difficulty of the operation of the object to be processed in the recognition result of the operation video, automatically generating test questions with controllable difficulty. This effectively avoids the process of manually generating examination questions after interpreting and summarizing the operation video, significantly saving labor costs. Furthermore, the difficulty of the test questions is highly interpretable, and the examination content for the entire operation video is relatively balanced.

[0078] Similarly, based on the above-described question generation method, this application embodiment also provides a computer-readable storage medium storing a program. When the program is executed by a processor, the processor performs at least the following operation steps: operation 101, receiving a question generation request; operation 102, determining examination content that matches the question generation request, wherein the examination content is related to the difficulty of the operation object to the processing object in the recognition result of the operation video to be examined; operation 103, generating examination questions based on the examination content.

[0079] Furthermore, based on the question generation method described above, this application also provides a question generation device, such as... Figure 8 The device 80 includes: a request receiving module 801 for receiving a test question generation request; a content determination module 802 for determining the examination content that matches the test question generation request, wherein the examination content is related to the difficulty of the operation of the object to the processing object in the recognition result of the operation video to be examined, and the recognition result includes the processing difficulty of the operation steps of the object to the processing object; and a generation module 803 for generating examination questions based on the examination content.

[0080] According to one embodiment of this application, the content determination module 802 includes: a step submodule, used to determine the operation steps that match the test question generation request; and a content submodule, used to determine the examination content based on the determined operation steps.

[0081] According to one embodiment of this application, the step submodule determines the operation steps that match the test question generation request, including: parsing the test question generation request to obtain the examination difficulty coefficient; and selecting an operation step from the operation steps that match the examination difficulty coefficient.

[0082] According to one embodiment of this application, the test question generation request carries a test question type; correspondingly, the generation module 803 includes: a content processing submodule, used to process the test content corresponding to the test question type.

[0083] According to an embodiment of this application, the recognition result is obtained in advance through the following operations: acquiring multiple frames of video images of the operation video; performing image recognition on the multiple frames of video images to obtain a first state change of the operation object and a second state change of the processing object; determining multiple operation steps of the operation object on the processing object based on the second state change; and determining the operation difficulty of the operation object on the processing object in the operation steps based on the first state change in the operation steps.

[0084] According to an embodiment of this application, the step of performing image recognition on the multi-frame video images includes: performing image recognition on the video images to obtain a first positional relationship between the operation object and the processing object and a second positional relationship between the processing object and the processing tool; and determining the first state change based on the first positional relationship and the second positional relationship in the video images of a first set frame.

[0085] According to one embodiment of this application, the step of determining multiple operation steps of the operation object on the processing object based on the second state change includes: detecting a first image including the processing object in the multi-frame video images; and determining the operation of the operation object on the processing object in the second set frame as an operation step when the second state change of the first image in the second set frame meets a first condition.

[0086] According to an embodiment of this application, determining the operational difficulty of the operation object for the processing object in the operation step based on the first state change in the operation step includes: determining the number of hand shape changes, finger operation precision, and hand coordination state of the operation object in the operation step based on the second state change of the operation object in the operation step; assigning values ​​to the number of hand shape changes, the finger operation precision, and the hand coordination state according to a set assignment rule; and performing a weighted summation of the assigned values ​​of the number of hand shape changes, the finger operation precision, and the hand coordination state to determine the operational difficulty of the operation step.

[0087] Furthermore, based on the question generation method described above, embodiments of this application also provide a device, such as... Figure 9 The device 90 includes: at least one processor 901, and at least one memory 902 and bus 903 connected to the processor 901; wherein the processor 901 and the memory 902 communicate with each other through the bus 903; the processor 901 is used to call program instructions in the memory 902 to execute the above-mentioned test question generation method.

[0088] It should be noted here that the above description of the embodiments of the test question generation device and equipment is consistent with the foregoing Figures 1 to 7 The method embodiments shown are described similarly and have the same characteristics as described above. Figures 1 to 7 The beneficial effects of the methods illustrated are similar and will not be described in detail here. For technical details not disclosed in the embodiments of the test question generation apparatus and device of this application, please refer to the foregoing description of this application. Figures 1 to 7 The method embodiments shown are for understanding purposes only and will not be described in detail here for the sake of brevity.

[0089] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0091] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0092] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0093] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0094] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0095] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for generating test questions, the method comprising: Receive a request to generate test questions; Determine the examination content that matches the test question generation request, wherein the examination content is related to the difficulty of the operation object to the processing object in the recognition result of the operation video to be examined; Based on the content to be examined, generate examination questions; The difficulty of the operation of the object to be processed in the recognition result is obtained by image recognition based on multiple frames of video images.

2. The method according to claim 1, wherein determining the examination content matching the test question generation request includes: Determine the operational steps that match the question generation request; The examination content is determined based on the established operational steps.

3. The method according to claim 1, wherein the step of determining the operation that matches the test question generation request includes: The question generation request is parsed to obtain the difficulty coefficient of the examination; Select one operation step from the operation steps that meet the stated difficulty level.

4. The method according to claim 1, wherein the question generation request carries a question type; correspondingly, generating examination questions based on the examination content includes: The examination content is processed to correspond to the question type.

5. The method according to claim 1, wherein the identification result is obtained in advance through the following operations: Acquire the multiple video frames of the operation video; The image recognition is performed on the multi-frame video images to obtain the first state change of the operation object and the second state change of the processing object; Based on the second state change, determine multiple operation steps of the operation object on the processing object; Based on the first state change in the operation steps, the operation difficulty of the operation object on the processing object in the operation steps is determined.

6. The method according to claim 5, wherein performing image recognition on the multi-frame video images comprises: Image recognition is performed on the video image to obtain a first positional relationship between the operation object and the processing object and a second positional relationship between the processing object and the processing tool; The first state change is determined based on the first positional relationship and the second positional relationship in the video image of the first set frame.

7. The method according to claim 5, wherein determining the multiple operation steps of the operation object on the processing object based on the second state change includes: Detect a first image that includes the object to be processed in the multi-frame video images; When the second state change of the first image in the second setting frame meets the first condition, the operation of the operation object on the processing object in the second setting frame is determined as an operation step.

8. The method according to claim 5, wherein determining the operational difficulty of the operation object on the processing object in the operation step based on the first state change in the operation step includes: Based on the second state change of the object being operated on in the operation steps, determine the number of hand shape changes, finger operation precision, and hand coordination state of the object being operated on in the operation steps. According to the set assignment rules, values ​​are assigned to the number of hand shape changes, the finger operation precision, and the hand coordination state, respectively. The difficulty of the operation step is determined by weighted summation of the number of hand shape changes, the precision of finger operation, and the state of hand coordination.

9. A test question generation device, the device comprising: The request receiving module is used to receive requests for test question generation; The content determination module is used to determine the examination content that matches the test question generation request. The examination content is related to the difficulty of the operation of the operation object to the processing object in the recognition result of the operation video to be examined. The difficulty of the operation of the operation object to the processing object in the recognition result is obtained by image recognition based on multiple frames of video images. The generation module is used to generate examination questions based on the examination content.

10. An apparatus comprising at least one processor, and at least one memory and a bus connected to the processor; wherein, The processor and the memory communicate with each other via the bus; The processor is used to call program instructions in the memory to execute the test question generation method according to any one of claims 1-8.

Images