Problem-solving video generation method, device, equipment, and storage medium

Abstract

The embodiment of the present application discloses a method and apparatus, device, and storage medium for generating a problem-solving video, including: obtaining target question information corresponding to a problem to be solved, the target question information including target known information and target solving information corresponding to the problem to be solved; matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solving information, the target problem-solving information including target knowledge points and target solving steps corresponding to the problem to be solved; generating a problem-solving video according to the target known information, the target solving information, the target knowledge points, and the target solving steps. A problem-solving video can be generated according to the acquired target known information, target solving information, target knowledge points, and target solving steps corresponding to the problem to be solved, thereby improving the efficiency of video production and reducing the cost of manually producing videos, and helping students understand and master the knowledge points and problem-solving steps of the problem to be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to data processing technology, and relate to but are not limited to a method and apparatus, device, and storage medium for generating a problem-solving video. Background Art

[0002] In the field of education, with the popularization of online education, automatic answers to students' questions during the learning process will be the inevitable direction of intelligent education. It will not only relieve the problem-solving pressure of teachers or parents, but also allow students to choose the time to ask questions and arrange their study time reasonably.

[0003] The solutions to the questions mainly include the following methods: text solutions and video solutions. Among them, the text solution is to generate the corresponding text solution ideas or steps after obtaining the problem to be solved. This method lacks a visual demonstration and is not easy for students to understand the problem. The video solution can provide a more intuitive solution, which has a significant effect on some problems that require understanding of the process. However, the traditional video production of the solution requires manual participation, has a long production cycle and high cost, and cannot meet the video needs of a large number of students for different questions.

[0004] In the prior art, existing text-based solution ideas or steps, or solution ideas or steps generated by corresponding AI, can be converted into video form and corresponding audio can be added. However, this conversion method is relatively rigid and does not actually add new content compared to pure text form, and cannot effectively help students understand the problem. Summary of the invention

[0005] In view of this, the problem-solving video generation method, device, equipment, and storage medium provided in the embodiments of the present application obtain the target question information of the problem to be solved, and generate a problem-solving video by matching the target question information to the target problem-solving information. It can improve the production efficiency of the problem-solving video and reduce the cost of manually producing videos. The problem-solving video generation method, device, equipment, and storage medium provided in the embodiments of the present application are implemented as follows:

[0006] The problem-solving video generation method provided in the embodiment of the present application includes:

[0007] Obtain target question information corresponding to the problem to be solved, wherein the target question information includes target known information and target solution information corresponding to the problem to be solved;

[0008] According to the target known information and the target solution information, target solution information corresponding to the problem to be solved is matched, and the target solution information includes target knowledge points and target solution steps corresponding to the problem to be solved;

[0009] A problem-solving video is generated based on the target known information, the target solution information, the target knowledge points and the target problem-solving steps.

[0010] In some embodiments, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes:

[0011] Determine the target knowledge point according to the target known information and the target solution information;

[0012] The target problem-solving steps are determined according to the target knowledge points and a first knowledge base, wherein the first knowledge base includes a correspondence between preset knowledge points and preset problem-solving steps.

[0013] In some embodiments, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes:

[0014] The target problem-solving information is determined based on the target known information, the target solution information and a second knowledge base, wherein the second knowledge base includes a correspondence between preset known information, preset solution information, preset knowledge points and preset problem-solving steps.

[0015] In some embodiments, the problem-solving video includes a question review sub-video, a question explanation sub-video, and an answer sub-video; wherein, the question review sub-video is used to demonstrate the target question information corresponding to the question to be solved, the question explanation sub-video is used to demonstrate the target knowledge points and the target problem-solving steps corresponding to the question to be solved, and the answer sub-video is used to demonstrate the target answer corresponding to the question to be solved, and the target answer is determined based on the target known information, the target solving information, and the target problem-solving steps.

[0016] In some embodiments, generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps includes:

[0017] Generate the question review sub-video according to the target known information and the target solution information;

[0018] Generate the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps;

[0019] The answer sub-video is generated according to the target known information, the target solution information and the target problem-solving steps.

[0020] In some embodiments, generating the question review sub-video according to the target known information and the target solution information includes:

[0021] Acquire the text data of the question to be solved, and generate a question reading image frame and a question reading audio;

[0022] Generate a question review image frame and a question review audio according to the target known information and the target solution information;

[0023] The question review sub-video is generated according to the question reading image frame, the question reading audio, the question review image frame and the question review audio.

[0024] In some embodiments, the target problem-solving step includes at least one target problem-solving sub-step;

[0025] The step of generating the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps includes:

[0026] According to the target knowledge point, generate a knowledge point explanation image frame and a knowledge point explanation audio;

[0027] Generate a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step; the number of the at least one problem-solving image frame is positively correlated with the number of the at least one target problem-solving sub-step;

[0028] The topic explanation sub-video is generated according to the knowledge point explanation image frame, the knowledge point explanation audio, the at least one problem-solving image frame and the problem-solving audio.

[0029] In some embodiments, the target problem-solving step includes at least two target problem-solving sub-steps;

[0030] The step of generating a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step comprises:

[0031] Generate a problem-solving audio and at least two problem-solving image frames, the number of which is the same as the number of the at least two target problem-solving sub-steps;

[0032] Among the at least two problem-solving image frames, when two adjacent pre-selected problem-solving image frames meet a preset fusion condition, the two adjacent pre-selected problem-solving image frames are subjected to image fusion as a new problem-solving image frame, and the preset fusion condition includes that the proportion of blank parts in the two adjacent pre-selected problem-solving image frames is greater than a preset threshold.

[0033] In some embodiments, generating the answer sub-video according to the target known information, the target solution information and the target problem-solving steps includes:

[0034] Obtain a target answer template for the question to be solved;

[0035] Generate an answer image frame and a corresponding answer audio according to the target known information, the target solution information, the target problem-solving steps and the target answer template;

[0036] The answer sub-video is generated according to the answer image frame and the answer audio.

[0037] In some embodiments, the answer sub-video further includes a summary image frame and a summary audio. After obtaining the target answer template for the question to be solved, the method further includes:

[0038] According to the target knowledge point, generating a summary image frame and a corresponding summary audio;

[0039] The step of generating the answer sub-video according to the answer image frame and the answer audio comprises:

[0040] The answer sub-video is generated according to the answer image frame, the answer audio, the summary image frame and the summary audio.

[0041] In some embodiments, the problem-solving video further includes a knowledge point review sub-video, wherein the knowledge point review sub-video is used to demonstrate target review knowledge, and the target review knowledge points are at least part of the target knowledge points;

[0042] The generating a problem-solving video according to the target known information, the target solution information, the target knowledge points and the target problem-solving steps also includes:

[0043] Acquire the target review knowledge points;

[0044] Review the knowledge points according to the target, and generate summary image frames and summary audio;

[0045] The review sub-video is generated according to the summary image frame and the summary audio.

[0046] In some embodiments, the problem-solving video is a problem-solving video that highlights key content; wherein, the key content includes the target known information and the target knowledge points, and the highlighting includes increasing the text font size of the key content, changing the text color of the key content, or adding animation effects to highlight the key content.

[0047] In some embodiments, generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps includes:

[0048] According to the target knowledge point, a matching operation is performed in a preset image template library to obtain a target matching result, wherein the preset image template library includes a correspondence between a plurality of preset knowledge points and preset image templates;

[0049] When the target matching result is a successful match, obtain the target image template corresponding to the target question identifier; add the target known information, the target solution information, the target knowledge points and the target problem-solving steps to the target image template to generate the problem-solving video.

[0050] In some embodiments, after generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes:

[0051] Get video control information;

[0052] According to the video control information, a target sub-video in the problem-solving video is selected to obtain a new problem-solving video, wherein the target sub-video includes at least part of the sub-videos in the problem-examination sub-video, the problem-explaining sub-video, the answer sub-video, and the video review sub-video;

[0053] Control the new problem-solving video to play.

[0054] In some embodiments, after generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes:

[0055] Generate an interactive interface, the interactive interface is used to obtain a jump video according to an interactive video control signal input by a user; wherein the jump video includes an associated problem-solving video corresponding to an associated problem of the problem to be solved and a target problem-solving information detailed explanation video.

[0056] In some embodiments, the problem-solving video generates an interactive button set at a preset position in the problem-solving video during playback, and the interactive button is used to feedback questions or post comments.

[0057] The problem-solving video generation device provided in the embodiment of the present application includes:

[0058] A question parsing module is used to obtain target question information corresponding to the question to be solved, wherein the target question information includes target known information and target solution information corresponding to the question to be solved;

[0059] A problem-solving matching module, used to match the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, wherein the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved;

[0060] The video generation module is used to generate a problem-solving video based on the target known information, the target solution information, the target knowledge points and the target problem-solving steps.

[0061] The computer device provided in the embodiment of the present application includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the embodiment of the present application is implemented.

[0062] The computer-readable storage medium provided in the embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0063] The problem-solving video generation method, device, computer equipment and computer-readable storage medium provided in the embodiments of the present application provide a basis for subsequent problem-solving steps by obtaining target problem information corresponding to the problem to be solved, including target known information and target solution information; then, according to the target known information and target solution, the target problem-solving information corresponding to the problem to be solved is matched, wherein the target problem-solving information includes target knowledge points and target problem-solving steps corresponding to the problem to be solved, which helps to generate a problem-solving video to help students understand the knowledge points and problem-solving ideas behind the problem to be solved; according to the obtained target known information, target solution information, target knowledge points and marked problem-solving steps, a problem-solving video is generated. In this way, the obtained target known information, target solution information and the matched problem-solving methods and knowledge points are presented in the form of a video, which improves the generation efficiency of the problem-solving video, reduces the cost of manually producing such problem-solving videos, and facilitates students to understand and master the problem-solving methods and knowledge points of the problem to be solved when watching the problem-solving video. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0065] Figure 1 A schematic diagram of the basic flow of the problem-solving video generation method provided in an embodiment of the present application;

[0066] Figure 2 A detailed flow chart of the method for generating a problem-solving video provided in an embodiment of the present application;

[0067] Figure 3A schematic diagram of a question reading image frame and a question review image frame in a question review sub-video generated by the question-solving video generation method provided in an embodiment of the present application;

[0068] Figure 4 A schematic diagram of a knowledge point explanation image frame and a problem-solving image frame in a problem-solving sub-video generated by the problem-solving video generation method provided in an embodiment of the present application;

[0069] Figure 5 A schematic diagram of an answer image frame and a summary image frame in an answer sub-video generated by the problem-solving video generation method provided in an embodiment of the present application;

[0070] Figure 6 A schematic diagram of summarizing image frames in a knowledge point review sub-video generated by the problem-solving video generation method provided in an embodiment of the present application;

[0071] Figure 7 Another detailed flow chart of the method for generating a problem-solving video provided in an embodiment of the present application;

[0072] Figure 8 A schematic diagram of a portion of image frames of a problem-solving video generated by the problem-solving video generation method provided in an embodiment of the present application;

[0073] Fig. 9 A schematic diagram of the structure of a problem-solving video generating device provided in an embodiment of the present application;

[0074] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0076] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0077] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0078] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0079] With the popularity of online education, students have an increasing need to solve problems in the learning process. However, in the traditional online education model, when students encounter problems that they cannot solve on their own, they often need to wait for answers from teachers or other classmates, which undoubtedly increases the time cost of learning and the pressure on learners. There is no guarantee that they will always get timely answers. Waiting too long for answers will cause students to get bored and forget past knowledge.

[0080] Therefore, students need a more efficient and convenient way to solve problems. Answering questions in the form of videos is a more intuitive and vivid way than traditional paper answers. Through videos, students can see the problem-solving steps and ideas more clearly, so that they can better understand and master the problem-solving methods. After the video is produced, students can view it at any time according to their own learning progress and needs. However, traditional lecture video production requires manual participation, has a long production cycle, and is costly, and cannot meet the needs of a large number of students.

[0081] In the prior art, existing text-based solution ideas or steps, or solution ideas or steps generated by AI, can be converted into video form and corresponding audio can be added. However, this conversion method is rather rigid, and is simply a simple conversion of text content into video form. Compared to pure text form, it does not actually add new content and cannot effectively help students understand the problem.

[0082] In view of this, the embodiment of the present application provides a method for generating a problem-solving video, which can quickly generate a problem-solving video according to the needs of students and provide students with timely and accurate answers. At the same time, it can also reduce the production cost of the problem-solving video, improve the production efficiency, and meet the needs of a large number of students. The method provided by the present application will be described below in conjunction with the accompanying drawings.

[0083] Please refer to Figure 1 , Figure 1 The following is a basic flow chart of the method for generating a problem-solving video according to an embodiment of the present application. Figure 1 As shown, the method may include the following steps 101 to 103.

[0084] Step 101, obtaining target question information corresponding to the problem to be solved, wherein the target question information includes target known information and target solution information corresponding to the problem to be solved.

[0085] In an embodiment of the present application, target question information corresponding to the problem to be solved is obtained, and the target question information includes target known information and target solution information corresponding to the problem to be solved.

[0086] It is understandable that in order to generate a problem-solving video corresponding to the problem to be solved, it is first necessary to process the problem to be solved to obtain the target problem information of the problem to be solved. The target problem information obtained provides a basis for the generation of subsequent problem-solving steps or ideas. Among them, the target known information corresponding to the problem to be solved refers to the known conditions, facts or premises in the problem to be solved. These known information are the basis for solving the problem and describe the background of the problem to be solved. The target solution information refers to the goal or problem to be solved by the problem to be solved. The problem to be solved often contains a lot of text content, such as long narratives, complex background descriptions, etc. By obtaining the target problem information corresponding to the problem to be solved, it is possible to filter out unnecessary information in the problem to be solved, such as adjectives that are only used for modification, irrelevant background information, etc., so that the target problem information obtained, including the target known information and the target solution information, pays more attention to the core content of the problem solving.

[0087] In some embodiments, in order to obtain the target title information corresponding to the problem to be solved, it is first necessary to obtain the text data corresponding to the problem to be solved. The text data can be directly input by the user in the form of text into the computer device using the method provided by the present application through input devices such as keyboards and touch screens. When the user inputs the text data of the problem to be solved through input devices such as keyboards or touch screens, the computer device can receive and store these data in real time. Subsequently, the computer device can process and analyze these text data to extract the target title information. It can also be obtained in the form of pictures, audio, etc. For example, the user can obtain a picture containing the content of the problem to be solved through a scanning device or a computer device with a camera function, and use image recognition technology to identify and extract the text in the picture. Or, use a voice input function to input the content of the problem to be solved into the computer device in the form of audio, and use voice recognition technology to identify and convert the voice in the audio to obtain the text data of the problem to be solved, and the specific form is not limited here.

[0088] In some embodiments, after obtaining the text data of the problem to be solved, the input text data is converted into a machine-readable format through natural language processing technology, and lexical analysis and syntactic analysis are performed on it to extract the target problem information including target known information and target solution information. Further, natural language processing technology will perform lexical analysis and syntactic analysis on the input text data. Lexical analysis mainly focuses on word-level information, such as part-of-speech tagging, such as verbs, nouns, adjectives, etc. and named entity recognition such as names, place names, organization names, etc. This information helps to understand the basic composition and meaning of the text data of the problem to be solved, and the corresponding target problem information can be obtained after processing.

[0089] In one embodiment, the problem to be solved is "The two ports of Dalian and Yantai are 87 nautical miles apart. Ships A and B set out from the two ports at the same time, heading towards each other, and meet after 3 hours. Ship B travels 15 nautical miles per hour, how many nautical miles does Ship A travel per hour?", and the target problem information corresponding to the problem to be solved is obtained. The target known information obtained includes "A and B are 87 nautical miles apart, heading towards each other, meeting in three hours, and Ship B travels 15 nautical miles per hour", and the target solution information includes "Ship A's speed". According to the problem to be solved, the text content of the problem to be solved is processed through natural language processing. During the processing, non-essential information is filtered out, such as background or scene introduction, to obtain the target problem information.

[0090] Step 102, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved.

[0091] In an embodiment of the present application, target problem-solving information corresponding to the problem to be solved is matched based on the target known information and the target solution information, and the target problem-solving information includes target knowledge points and target problem-solving steps corresponding to the problem to be solved.

[0092] It should be noted that, according to the target known information and the target solution information, the target problem-solving information including the target knowledge points and the target problem-solving steps corresponding to the problem to be solved can be matched. The target knowledge points refer to the core knowledge points or concepts directly related to the problem to be solved, and the target problem-solving steps provide the steps required to solve the problem to be solved. By matching the target problem-solving information including the target knowledge points and the target problem-solving steps, the subsequent problem-solving video generated based on the target problem-solving information can cover the target knowledge points used to solve the problem, and deduce the problem to be solved according to the clear target problem-solving steps. This not only makes it possible to efficiently produce videos and reduce the cost of manually producing videos, but also makes the content of the generated problem-solving videos richer, helping students to establish a complete knowledge system and deepen their understanding of related concepts.

[0093] In some embodiments, the target problem-solving steps corresponding to the problem to be solved may include general solutions, steps or formulas corresponding to the type of problem to be solved, that is, general solutions for a type of problem. Taking the speed problem as an example, the knowledge points applied include the speed formula "speed equals distance divided by time", and then the required distance and time are obtained to obtain the required speed. When the target problem-solving steps are obtained, the complete process of solving the problem to be solved can be obtained by substituting the target known information and the target solution information, and a corresponding problem-solving video can be generated.

[0094] In some embodiments, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes:

[0095] Determine the target knowledge point according to the target known information and the target solution information;

[0096] The target problem-solving steps are determined according to the target knowledge points and a first knowledge base, wherein the first knowledge base includes a correspondence between preset knowledge points and preset problem-solving steps.

[0097] It should be noted that in some implementations, the target known information and the target solution information are processed in order to extract the core target knowledge points from the problem to be solved. Next, the target problem-solving steps are determined from the first knowledge base according to the target knowledge points. The first knowledge base here is a relationship base between preset knowledge points and preset problem-solving steps. By first obtaining the target knowledge points and then using them as a benchmark to obtain the target problem-solving steps, the structure of the first knowledge base is clear and easy to construct. The generated problem-solving video is strongly related to the target knowledge points, which helps to establish a complete knowledge system and help users deepen their understanding of related concepts.

[0098] However, since the problem-solving steps in the first knowledge base are determined based on preset knowledge points, some of the target question information may be ignored. For example, when faced with some unconventional questions, the target problem-solving steps obtained cannot be well dealt with or substituted into the previously acquired target known information and target solution information. To alleviate this situation, in some embodiments, multiple problem-solving steps associated with the target knowledge points can be obtained by obtaining the matching similarity between the target knowledge points and the preset problem-solving steps in the first knowledge base, and then multiple problem-solving videos can be generated and left to the user to choose and watch, thereby improving the flexibility and adaptability of video generation.

[0099] In some embodiments, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes:

[0100] The target problem-solving information is determined based on the target known information, the target solution information and a second knowledge base, wherein the second knowledge base includes a correspondence between preset known information, preset solution information, preset knowledge points and preset problem-solving steps.

[0101] It should be noted that the above-mentioned second knowledge base includes the corresponding relationship between preset known information, preset solution information, preset knowledge points and preset problem-solving steps. Compared with the above-mentioned first knowledge base, in some embodiments, the target problem-solving information can be directly determined according to the target known information, the target solution information and the second knowledge base. In this way, the consistency of the target problem-solving information, especially the target problem-solving steps and the target title information is ensured, thereby improving the accuracy of the generated problem-solving video. However, this method depends on the integrity and accuracy of the second knowledge base. Once the information in the knowledge base is wrong or missing, it will directly affect the accuracy and reliability of the problem-solving steps. In some embodiments, the problems of the generated problem-solving video can be detected by establishing a user feedback mechanism to help improve the above-mentioned second knowledge base.

[0102] Step 103, generating a problem-solving video based on target known information, target solution information, target knowledge points, and target problem-solving steps.

[0103] In an embodiment of the present application, a problem-solving video is generated based on the target known information, the target solution information, the target knowledge points, and the target problem-solving steps.

[0104] In some embodiments, after the problem-solving video is generated, it will be output to a designated platform or device for students to watch and learn. This helps students to independently choose the time and place to watch the problem-solving video, enhances the flexibility of students' learning, and helps students to understand and master relevant knowledge points more deeply.

[0105] By implementing the above technical solution, it is possible to obtain the target question information corresponding to the to-be-solved question, including the target known information and the target solution information, and match the target problem-solving information including the target knowledge points and the target problem-solving steps corresponding to the to-be-solved question according to the target question information, and generate a problem-solving video according to the target question information and the target problem-solving information. The problem-solving video generated in this way can intuitively display the problem-solving process and the applied knowledge points, thereby helping students better understand and master the relevant knowledge. In addition, in the process of generating the problem-solving video, manual participation is reduced, the efficiency of video production is improved, and the cost of video production is reduced.

[0106] In order to meet the personalized needs of different users, the problem-solving video can be divided into multiple sub-videos according to the content. In this way, partial video content of the problem-solving video can be generated in a targeted manner according to the different needs of users, helping users to study their weak links, so as to save time and improve learning efficiency. The following will illustrate the generation of different sub-videos in the method provided in this application with reference to the accompanying drawings.

[0107] See also Figure 2 , Figure 2 A detailed flow chart of the method for generating a problem-solving video provided in the embodiment of the present application. Figure 2 As shown, the method may include the following steps 201 to 205.

[0108] Step 201, obtaining target problem information corresponding to the problem to be solved, wherein the target problem information includes target known information and target solution information corresponding to the problem to be solved.

[0109] Step 202, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved.

[0110] It should be noted that steps 201 to 202 are similar to steps 101 to 102 in the above description and are not described in detail here.

[0111] In some embodiments, the problem-solving video includes a question review sub-video, a question explanation sub-video, and an answer sub-video; wherein, the question review sub-video is used to demonstrate the target question information corresponding to the question to be solved, the question explanation sub-video is used to demonstrate the target knowledge points and the target problem-solving steps corresponding to the question to be solved, and the answer sub-video is used to demonstrate the target answer corresponding to the question to be solved, and the target answer is determined based on the target known information, the target solving information, and the target problem-solving steps.

[0112] By including a sub-video of question review, a sub-video of question explanation, and a sub-video of answer, the content structure of the generated video can be made more reasonable, which helps students better understand the background information of the question, master the key knowledge points and skills of problem solving, and demonstrate and explain the specific steps, while being able to review the relevant knowledge points. At the same time, the video of problem solving is divided into multiple sub-videos, so that some sub-videos can be selectively generated according to user needs, thereby providing more personalized videos and improving the video learning experience.

[0113] In some embodiments, generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps includes:

[0114] Generate the question review sub-video according to the target known information and the target solution information;

[0115] Generate the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps;

[0116] The answer sub-video is generated according to the target known information, the target solution information and the target problem-solving steps.

[0117] It should be noted that by selectively generating different sub-videos included in the problem-solving video based on the target known information, target solution information, target knowledge points, and target problem-solving steps, the content of each sub-video is differentiated to meet the learning needs of different students. For example, for students with poor foundation, they can choose to watch the question review sub-video to understand the background and requirements of the question; for students with good foundation, they can choose to watch the question explanation sub-video to deeply understand the knowledge points and problem-solving skills involved in the question; for students who have already mastered the problem-solving method, they can choose to watch the answer sub-video to verify their own problem-solving ideas and learn more problem-solving skills.

[0118] The following will explain in steps the process of generating the question review sub-video, question explanation sub-video and answer sub-video in this application.

[0119] Step 203, generating a question review sub-video based on the target known information and the target solution information.

[0120] In some embodiments, generating the question review sub-video according to the target known information and the target solution information includes:

[0121] Acquire the text data of the question to be solved, and generate a question reading image frame and a question reading audio;

[0122] Generate a question review image frame and a question review audio according to the target known information and the target solution information;

[0123] The question review sub-video is generated according to the question reading image frame, the question reading audio, the question review image frame and the question review audio.

[0124] It should be noted that the question reading image frame may be an image frame corresponding to the text data of the question to be solved, and is used to present the question to be solved and the target question information including the target known information and the target solution information. The question reading audio may be an audio for reading the corresponding content generated based on the above question and target question information, and is used to enrich the content of the generated question review sub-video. This helps students understand the question.

[0125] Step 204, generating a lecture sub-video according to the target known information, target knowledge points and target problem-solving steps.

[0126] In some embodiments, the target problem-solving step includes at least one target problem-solving sub-step;

[0127] The step of generating the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps includes:

[0128] According to the target knowledge point, generate a knowledge point explanation image frame and a knowledge point explanation audio;

[0129] Generate a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step; the number of the at least one problem-solving image frame is positively correlated with the number of the at least one target problem-solving sub-step;

[0130] The topic explanation sub-video is generated according to the knowledge point explanation image frame, the knowledge point explanation audio, the at least one problem-solving image frame and the problem-solving audio.

[0131] It should be noted that the knowledge point explanation image frames are used to explain the target knowledge points corresponding to the questions to be solved, and the knowledge point explanation audio is the voice interpretation of the above knowledge point explanation image frames. The content of the target knowledge points can be converted into audio form through corresponding algorithms, such as corresponding speech synthesis algorithms, to obtain the knowledge point explanation audio.

[0132] The method for generating the problem-solving image frame and the problem-solving audio is to obtain the key steps involved in the problem-solving process of the to-be-solved problem based on the target known information and at least one target problem-solving sub-step included in the target problem-solving step, and generate the corresponding problem-solving image frame and problem-solving audio content based on these key steps. Among them, dividing the target problem-solving step into at least one target problem-solving sub-step helps to generate a more detailed problem-solving video by splitting the overall problem-solving step into smaller sub-steps, reducing the complexity of each problem-solving step, and helping students master the entire problem-solving process.

[0133] In some embodiments, the target problem-solving step includes at least two target problem-solving sub-steps;

[0134] The step of generating a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step comprises:

[0135] Generate a problem-solving audio and at least two problem-solving image frames, the number of which is the same as the number of the at least two target problem-solving sub-steps;

[0136] Among the at least two problem-solving image frames, when two adjacent pre-selected problem-solving image frames meet a preset fusion condition, the two adjacent pre-selected problem-solving image frames are subjected to image fusion as a new problem-solving image frame, and the preset fusion condition includes that the proportion of blank parts in the two adjacent pre-selected problem-solving image frames is greater than a preset threshold.

[0137] It should be noted that, when the target problem-solving step includes at least two target problem-solving sub-steps, at least two problem-solving image frames are generated according to the target problem-solving sub-steps, the number of which is the same as the number of at least two target problem-solving sub-steps. Due to the different importance of each target problem-solving sub-step, different knowledge points used or different difficulty, the amount of information contained in them is also different.

[0138] It is understandable that for some important target problem-solving sub-steps, the corresponding problem-solving image frames may contain more details and information to answer the problem to be solved. For some relatively minor target problem-solving sub-steps, the corresponding image frames will be simplified accordingly. By pre-setting the content and conditions, when the proportion of the blank part in two adjacent pre-selected problem-solving image frames is greater than the preset threshold, the two adjacent pre-selected problem-solving image frames are image-fused to obtain a new problem-solving image frame, which can reduce the blank part in the final generated problem-solving video to a certain extent, thereby improving the quality of the video and the viewing experience.

[0139] In some embodiments, when there is only one pre-selected problem-solving image frame, or all two adjacent pre-selected problem-solving image frames do not meet the pre-set fusion conditions, all the pre-selected problem-solving image frames are determined to be problem-solving image frames, and the pre-selected problem-solving audios corresponding to all the pre-selected problem-solving image frames are determined to be problem-solving audios, that is, the image fusion operation on the adjacent pre-selected problem-solving image frames is stopped.

[0140] Step 205, generating an answer sub-video based on the target known information, the target solution information and the target problem-solving steps.

[0141] In some embodiments, generating the answer sub-video according to the target known information, the target solution information and the target problem-solving steps includes:

[0142] Obtain a target answer template for the question to be solved;

[0143] Generate an answer image frame and a corresponding answer audio according to the target known information, the target solution information, the target problem-solving steps and the target answer template;

[0144] The answer sub-video is generated according to the answer image frame and the answer audio.

[0145] Among them, the target answer template can be based on the type of questions to be solved, such as multiple-choice questions, fill-in-the-blank questions, short-answer questions, etc., or it can be based on the subject of the questions to be solved, such as mathematics, physics, English, etc., to provide the format requirements of the answer. Substituting the target known information, target solution information and target problem-solving steps into the target answer template, it is possible to generate an answer image frame and the corresponding answer audio, and generate an answer sub-video based on the answer image frame and the answer audio. Ensure that the answer sub-video generated based on the target known information, target solution information and target problem-solving steps to demonstrate the target answer corresponding to the question to be solved is accurate and complete, helping students to better understand and master the knowledge points and problem-solving methods involved in the question, and verify whether their own problem-solving ideas are correct.

[0146] In some embodiments, the answer sub-video further includes a summary image frame and a summary audio. After obtaining the target answer template for the question to be solved, the method further includes:

[0147] According to the target knowledge point, generating a summary image frame and a corresponding summary audio;

[0148] The step of generating the answer sub-video according to the answer image frame and the answer audio comprises:

[0149] The answer sub-video is generated according to the answer image frame, the answer audio, the summary image frame and the summary audio.

[0150] By obtaining the target answer template for the question to be solved, a summary image frame and a corresponding summary audio are generated according to the target knowledge points, so that the generated answer sub-video can not only show the target answer to the question to be solved, but also summarize and review the target knowledge points, thereby improving the quality of the generated problem-solving video, making the final problem-solving video close to the steps of a real teacher's lecture, and reducing the cost of manually produced videos, which can help students better understand and master the knowledge points and problem-solving methods involved in the question.

[0151] In some embodiments, the problem-solving video further includes a knowledge point review sub-video, wherein the knowledge point review sub-video is used to demonstrate target review knowledge, and the target review knowledge points are at least part of the target knowledge points;

[0152] The generating a problem-solving video according to the target known information, the target solution information, the target knowledge points and the target problem-solving steps also includes:

[0153] Acquire the target review knowledge points;

[0154] Review the knowledge points according to the target, and generate summary image frames and summary audio;

[0155] The review sub-video is generated according to the summary image frame and the summary audio.

[0156] It should be noted that, in addition to the above-mentioned question review sub-video, question explanation sub-video and answer sub-video, in some embodiments, the problem-solving video generated by the method provided by the present application also includes a knowledge point review sub-video, which is used to demonstrate the target review knowledge, improve the quality of the generated video, and help students better consolidate and understand the relevant content. Among them, the target review knowledge point is at least part of the target knowledge point, and the target knowledge point with the highest priority among multiple target knowledge points can be determined as the target review knowledge point by setting the priorities of different preset knowledge points in the preset knowledge base. A corresponding interactive feedback mechanism can also be set, and users who have watched the problem-solving video corresponding to the problem to be solved select the more important target knowledge points among multiple target knowledge points as the target review knowledge points, and save the target review knowledge points, so that in the case of the subsequent need to generate a knowledge point review sub-video, the corresponding review knowledge points can be quickly obtained, so that the generated knowledge point review sub-video meets the actual needs of the user.

[0157] In some embodiments, after generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes:

[0158] Get video control information;

[0159] According to the video control information, a target sub-video in the problem-solving video is selected to obtain a new problem-solving video, wherein the target sub-video includes at least part of the sub-videos in the problem-examination sub-video, the problem-explaining sub-video, the answer sub-video, and the video review sub-video;

[0160] Control the new problem-solving video to play.

[0161] It should be noted that the video control information may include video control information input by the user, default video control information, or video control information automatically acquired based on historical problem-solving video records, which is not limited here. Afterwards, select the target sub-video in the problem-solving video. According to the video control information, select the corresponding target sub-video from the question review sub-video, question explanation sub-video, answer sub-video, and knowledge point review sub-video. The target sub-video may be a separate sub-video or a combination of multiple sub-videos. In this way, a new problem-solving video containing a target sub-video can be acquired and controlled for playback, customized according to the user's needs and preferences, and a more personalized problem-solving video can be generated to meet the needs of learners at different levels and needs.

[0162] By implementing the above technical solution, the problem-solving video corresponding to the question to be solved is divided into multiple sub-videos for demonstrating different contents, including question review sub-video, question explanation sub-video, answer sub-video and knowledge point review sub-video. It is possible to automatically and selectively generate explanation videos of different forms and contents according to the different needs of students, which helps to improve the quality and effect of the generated videos.

[0163] See also Figure 3 , Figure 3 A schematic diagram of a question-reading image frame and a question-reviewing image frame in a question-reviewing sub-video generated by the question-solving video generation method provided in an embodiment of the present application.

[0164] In one embodiment, the text data of the problem to be solved is obtained as follows: "In order to further popularize gas safety knowledge to teachers and students, improve teachers' and students' awareness of safe gas use, and prevent and reduce the occurrence of gas accidents. A school held a "Gas Safety into Campus, Safety Knowledge Taken Home" publicity activity. There are 100 students in the sixth grade, of which 2 students asked for leave and did not come. What is the attendance rate of the sixth grade students this time?".

[0165] The obtained text data of the problem-solving video is used to generate a problem-reading image frame and a problem-reading audio, wherein the problem-reading image frame is as follows: Figure 3 As shown in (a), the text data corresponding to the problem to be solved is displayed.

[0166] According to the problem-solving video generation method provided in the present application, the target question information corresponding to the problem to be solved is first obtained, wherein the target known information corresponding to the problem to be solved includes "there are 100 students in the sixth grade" and "2 students have taken leave and are absent", and the target solution information includes "the attendance rate of sixth grade students".

[0167] According to the target known information and the target solution information, a question review image frame and a question review audio are generated, wherein the question review image frame is as follows: Figure 3 As shown in (b), the target known information and target solution information corresponding to the problem to be solved are listed and displayed.

[0168] In some embodiments, in order to improve the video quality of the question review sub-video generated based on the question reading image frames, question reading audio, question review image frames and question review audio, a machine learning algorithm is used to obtain relevant features of the text data, and these features are used to optimize and adjust the produced video. For example, based on the extracted text features, the semantic information of the text is obtained, the part including the target question information is obtained, the speed or tone of the produced audio is adjusted, or animation effects are added between different image frames, and the target question information is highlighted, such as changing the font color, adjusting the font size, etc.

[0169] See also Figure 4 , Figure 4A schematic diagram of knowledge point explanation image frames and problem-solving image frames in a problem-solving sub-video generated by the problem-solving video generation method provided in an embodiment of the present application.

[0170] In one embodiment, the text data of the problem to be solved is obtained as follows: "In order to further popularize gas safety knowledge to teachers and students, improve teachers' and students' awareness of safe gas use, and prevent and reduce the occurrence of gas accidents. A school held a "Gas Safety into Campus, Safety Knowledge Taken Home" publicity activity. There are 100 students in the sixth grade, of which 2 students asked for leave and did not come. What is the attendance rate of the sixth grade students this time?".

[0171] According to the problem-solving video generation method provided in the present application, the target question information corresponding to the problem to be solved is first obtained, wherein the target known information corresponding to the problem to be solved includes "there are 100 students in the sixth grade" and "2 students have taken leave and are absent", and the target solution information includes "the attendance rate of sixth grade students".

[0172] Through the problem-solving video generation method provided by the present application, the target problem-solving information corresponding to the problem to be solved is matched according to the target known information and the target solution information. It can be that the target knowledge point is first determined according to the target known information and the target solution information in the above description, and then the target problem-solving steps are determined according to the target knowledge point and the first knowledge base. It can also be that the target knowledge point and the target problem-solving steps are determined according to the target known information, the target solution information and the second knowledge base in the above description, which is not limited here.

[0173] Through the method provided by the present application, the "attendance rate" of the target knowledge point corresponding to the problem to be solved in this embodiment is obtained, and the knowledge point explanation image frame and the knowledge point explanation audio are generated according to the target knowledge point, wherein the knowledge point explanation image frame is as follows: Figure 4 Then, in this embodiment, since the problem to be solved is relatively simple, a target problem-solving sub-step is included, and the problem-solving audio and the like are generated according to the target known information and the target problem-solving sub-step. Figure 4 (b) The problem-solving image frame shown.

[0174] It should be noted that the above-generated knowledge point explanation image frames and problem-solving image frames are only used as an example of the problem-solving video generation method provided by this application. In actual applications, the expression method of each image frame in the problem-solving video may be different depending on the specific questions and requirements.

[0175] See also Figure 5 , Figure 5 A schematic diagram of an answer image frame and a summary image frame in an answer sub-video generated by the problem-solving video generation method provided in an embodiment of the present application.

[0176] In one embodiment, the text data of the problem to be solved is obtained as follows: "In order to further popularize gas safety knowledge to teachers and students, improve teachers' and students' awareness of safe gas use, and prevent and reduce the occurrence of gas accidents. A school held a "Gas Safety into Campus, Safety Knowledge Taken Home" publicity activity. There are 100 students in the sixth grade, of which 2 students asked for leave and did not come. What is the attendance rate of the sixth grade students this time?".

[0177] According to the target answer template, target known information, target solution information and target solution steps of the question to be solved, the following can be generated: Figure 5 (a) The answer image frame and the corresponding answer audio.

[0178] In some embodiments, in order to help students better understand and master the knowledge points and problem-solving methods involved in the question, the answer sub-video also includes a summary image frame and a summary audio. Figure 5 The summary image frame shown displays the target knowledge points for answering the question on the basis of the original answer image frame. Figure 5 The summary image frame shown in (b) is used only as an example. In some embodiments, the target knowledge point may be displayed separately according to the content length of the target knowledge point contained in the summary image frame.

[0179] See also Figure 6 , Figure 6 A schematic diagram of summarizing image frames in a knowledge point review sub-video generated by the problem-solving video generation method provided in an embodiment of the present application.

[0180] In one embodiment, the text data of the problem to be solved is obtained as follows: "In order to further popularize gas safety knowledge to teachers and students, improve teachers' and students' awareness of safe gas use, and prevent and reduce the occurrence of gas accidents. A school held a "Gas Safety into Campus, Safety Knowledge Taken Home" publicity activity. There are 100 students in the sixth grade, of which 2 students asked for leave and did not come. What is the attendance rate of the sixth grade students this time?".

[0181] According to the target question information of the problem to be solved, the target knowledge points corresponding to the problem to be solved are obtained, which may include "attendance rate calculation formula" and "number of attendees calculation formula", and at least some of the target knowledge points corresponding to the problem to be solved are obtained as target review knowledge points. In this embodiment, "attendance rate calculation formula" is selected as the target review knowledge point. According to the selected target review knowledge point, the following is generated: Figure 6 The summarized image frames and the summarized audio are shown, and a review sub-video is generated.

[0182] See also Figure 7 , Figure 7 Another detailed flow chart of the method for generating a problem-solving video provided in the embodiment of the present application. Figure 7As shown, the following steps 701 to 704 may be included.

[0183] Step 701, obtaining target question information corresponding to the problem to be solved, wherein the target question information includes target known information and target solution information corresponding to the problem to be solved.

[0184] Step 702, matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved.

[0185] It should be noted that steps 701 to 702 are similar to steps 101 to 102 in the above description and are not described in detail here.

[0186] Step 703, generating a problem-solving video based on target known information, target solution information, target knowledge points, and target problem-solving steps.

[0187] In some embodiments, generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps includes:

[0188] According to the target knowledge point, a matching operation is performed in a preset image template library to obtain a target matching result, wherein the preset image template library includes a correspondence between a plurality of preset knowledge points and preset image templates;

[0189] When the target matching result is a successful match, obtain the target image template corresponding to the target question identifier; add the target known information, the target solution information, the target knowledge points and the target problem-solving steps to the target image template to generate the problem-solving video.

[0190] It should be noted that through the pre-set image template library, it is possible to quickly match the target image templates corresponding to some common types of unsolved problems. In this way, adding the target known information, target solution information, target knowledge points and target problem-solving steps to the target image template can provide a more intuitive and vivid graphical display, enrich the content of the video, and clearly display the target knowledge points and target problem-solving steps. At the same time, this graphical display can also enhance students' understanding and memory of the questions, and improve learning effects and interests.

[0191] In some embodiments, by setting up an image template library, a video of a problem-solving problem is generated for a problem to be solved in science subjects such as mathematics and physics, and a better demonstration effect can be obtained. For example, for the common speed-related problem of the encounter problem, by obtaining the target knowledge points such as "encounter problem" and "speed", the target image template corresponding to it is matched in the pre-set image template library, and the corresponding endpoint images are set for the multiple solving objects corresponding to the target known information, and the corresponding line segment images are set for the distance information. The basic concepts and situations of the encounter problem can be clearly displayed, and the specific content of the target question information is displayed in the target image template to form a more complete and specific problem-solving video. In this way, the generated video is optimized, and the quality of the video and the viewing experience are improved.

[0192] In some embodiments, the problem-solving video is a problem-solving video that highlights key content; wherein, the key content includes the target known information and the target knowledge points, and the highlighting includes increasing the text font size of the key content, changing the text color of the key content, or adding animation effects to highlight the key content.

[0193] The purpose of this is to highlight the key points in the generated problem-solving video, making it easier to attract the attention of users who watch the problem-solving video. By increasing the text size, changing the text color, or adding animation effects, the key points can be made more eye-catching and noticeable. This can help users better understand and remember relevant knowledge points.

[0194] It should be noted that in some embodiments, the content included in the key content can be changed and the highlighting method can be set according to the personalized needs of the user. For example, if the user's target problem-solving steps are the key content, the method adopted by this application can highlight the target problem-solving steps included in the problem-solving video.

[0195] In some embodiments, the position of the content corresponding to the current audio in the image frame of the problem-solving video at the current moment is detected by a corresponding algorithm, and an animation effect that can change with the audio playback is set at the corresponding position. The animation effect can be in the form of an arrow, a cursor, etc., which is used to point to the content corresponding to the current audio in real time to guide the attention of the viewer of the problem-solving video.

[0196] Step 704: Generate an interactive interface, where the interactive interface is used to obtain a jump video according to an interactive video control signal input by a user.

[0197] In some embodiments, after generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes:

[0198] Generate an interactive interface, the interactive interface is used to obtain a jump video according to an interactive video control signal input by a user; wherein the jump video includes an associated problem-solving video corresponding to an associated problem of the problem to be solved and a target problem-solving information detailed explanation video.

[0199] In this way, users can input control signals through the interactive interface to complete interactive operations with the problem-solving video, such as selecting related questions of the question according to user needs, viewing detailed explanations of the target problem-solving information, etc., to help better understand and master relevant knowledge points. Among them, the acquisition of related questions can be obtained by performing similarity comparison based on the target question information through the corresponding question recommendation algorithm, or automatically recommending questions related to the current problem to be solved based on the user's historical learning data.

[0200] In some embodiments, the problem-solving video generates an interactive button set at a preset position in the problem-solving video during playback, and the interactive button is used to feedback questions or post comments.

[0201] By setting interactive buttons at preset positions during the playback of the problem-solving video, users can ask questions or make comments at any time while watching the problem-solving video. This instant feedback mechanism can promote interaction between users and video production background technicians or other viewers, making the learning process more active and participatory, or provide feedback on the currently playing problem-solving video to help the background-related technicians deal with errors in the video and continuously improve the video quality.

[0202] By implementing the above technical solutions, the process of generating problem-solving videos is improved, which can achieve interactive effects with users, improve video quality, meet the needs of different users, promote users' learning interest and enthusiasm, and at the same time better understand user needs and feedback, helping to continuously optimize and improve video content.

[0203] It should be understood that, although the steps in the above-mentioned flowcharts are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flowcharts may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0204] See also Figure 8 , Figure 8 A schematic diagram of some image frames of a problem-solving video generated by the problem-solving video generation method provided in an embodiment of the present application.

[0205] In one embodiment, the text data of the problem to be solved is "The two ports of Dalian and Yantai are 87 nautical miles apart. Ships A and B set out from the two ports at the same time, heading towards each other, and meet after 3 hours. Ship B travels 15 nautical miles per hour, how many nautical miles does Ship A travel per hour?".

[0206] Through the corresponding natural language processing, the target question information corresponding to the to-be-solved question can be obtained directly or indirectly based on the text data of the to-be-solved question, and the target known information includes "ship A and ship B are 87 nautical miles apart, heading in opposite directions, meeting in three hours, and ship B is traveling at 15 nautical miles per hour", and the target solution information includes "ship A's speed", generating the following: Figure 8 (a) shows the question review image frame.

[0207] The target known information and target solution information are matched to the target solution information including the target knowledge point and the target solution steps corresponding to the problem to be solved, wherein the target knowledge point may include "walking towards each other" and "speed calculation formula", and the target image template corresponding to the knowledge point is matched according to the preset image template library including the correspondence between multiple preset knowledge points and preset image templates, so as to generate the following Figure 8 The knowledge point shown in (b) is an example of an image frame, in which the knowledge point of “walking towards each other” is explained.

[0208] Then, the target known information, target solution information, target knowledge points and target problem-solving steps are added to the target image template to generate Figure 8 (c) shows a problem-solving image frame. Figure 8 As shown in (c), the image frame of the problem-solving image adds an animation effect to highlight the key content. Figure 8 In (c), the key content is the target known information "A and B are 87 nautical miles apart", and the animation effect is displayed with a graphic pointing to the key content. It should be noted that the problem-solving video corresponding to the problem to be solved may include multiple problem-solving image frames. Figure 8 (c) is only used as an example of the generated problem-solving image frame.

[0209] In addition, in this embodiment, according to the target knowledge points "distance calculation formula" and "speed calculation formula" matched to the problem to be solved and the corresponding target image template, the following is generated: Figure 8 The summary image frame shown in (d) summarizes and reviews the target knowledge points, thereby improving the quality of the generated problem-solving video.

[0210] It should be noted that, in the above description, unless explicitly stated, the generation of various image frames is not independent of each other. For example, Figure 4 The problem-solving image frame shown in (b) is Figure 4 On the basis of the knowledge point explanation image frame shown in (a), the target known information and part of the content included in the target problem-solving steps are added, which can improve the coherence of the various parts of the generated problem-solving video and improve the quality of video generation.

[0211] Based on the foregoing embodiments, an embodiment of the present application provides a problem-solving video generation device, which includes the modules included and the units included in the modules, and can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0212] Fig. 9 A schematic diagram of the structure of the problem-solving video generation device provided in the embodiment of the present application, such as Fig. 9 As shown, the problem-solving video generating device 900 includes a problem-solving module 901, a problem-solving matching module 902 and a video generating module 903, wherein:

[0213] The question parsing module 901 is used to obtain target question information corresponding to the question to be solved, wherein the target question information includes target known information and target solution information corresponding to the question to be solved;

[0214] A problem-solving matching module 902 is used to match the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, wherein the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved;

[0215] The video generation module 903 is used to generate a problem-solving video based on the target known information, the target solution information, the target knowledge points and the target problem-solving steps.

[0216] In some embodiments, the problem-solving matching module 902 is also used to determine the target knowledge points based on the target known information and the target solving information; determine the target problem-solving steps based on the target knowledge points and the first knowledge base, wherein the first knowledge base includes the correspondence between preset knowledge points and preset problem-solving steps.

[0217] In some embodiments, the problem-solving matching module 902 is also used to determine the target problem-solving information based on the target known information, the target solving information and a second knowledge base, wherein the second knowledge base includes a correspondence between preset known information, preset solving information, preset knowledge points and preset problem-solving steps.

[0218] In some embodiments, the problem-solving video generated by the video generation module 903 includes a question review sub-video, a question explanation sub-video and an answer sub-video; wherein the question review sub-video is used to demonstrate the target question information corresponding to the question to be solved, the question explanation sub-video is used to demonstrate the target knowledge points and the target problem-solving steps corresponding to the question to be solved, and the answer sub-video is used to demonstrate the target answer corresponding to the question to be solved, and the target answer is determined based on the target known information, the target solution information and the target problem-solving steps. The video generation module 903 is also used to generate the question review sub-video based on the target known information and the target solution information; generate the question explanation sub-video based on the target known information, the target knowledge points and the target problem-solving steps; and generate the answer sub-video based on the target known information, the target solution information and the target problem-solving steps.

[0219] In some embodiments, the video generation module 903 is also used to obtain the text data of the question to be solved, generate question reading image frames and question reading audio; generate question review image frames and question review audio according to the target known information and the target solving information; generate the question review sub-video according to the question reading image frames, the question reading audio, the question review image frames and the question review audio.

[0220] In some embodiments, the target problem-solving step includes at least one target problem-solving sub-step, and the video generation module 903 is also used to generate knowledge point explanation image frames and knowledge point explanation audio according to the target knowledge points; generate problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step; the number of the at least one problem-solving image frame is positively correlated with the number of the at least one target problem-solving sub-step; generate the explanation sub-video according to the knowledge point explanation image frame, the knowledge point explanation audio, the at least one problem-solving image frame and the problem-solving audio.

[0221] In some embodiments, the target problem-solving step includes at least two target problem-solving sub-steps, and the video generation module 903 is also used to generate problem-solving audio and at least two problem-solving image frames, the number of which is the same as the number of the at least two target problem-solving sub-steps; among the at least two problem-solving image frames, when two adjacent pre-selected problem-solving image frames meet a preset fusion condition, the two adjacent pre-selected problem-solving image frames are image fused as a new problem-solving image frame, and the preset fusion condition includes that the proportion of blank parts in the two adjacent pre-selected problem-solving image frames is greater than a preset threshold.

[0222] In some embodiments, the video generation module 903 is also used to obtain the target answer template for the question to be solved; generate an answer image frame and corresponding answer audio based on the target known information, the target solving information, the target solving steps and the target answer template; and generate the answer sub-video based on the answer image frame and the answer audio.

[0223] In some embodiments, the answer sub-video also includes a summary image frame and a summary audio. After obtaining the target answer template for the question to be solved, the video generation module 903 is also used to generate a summary image frame and a corresponding summary audio according to the target knowledge point; generating the answer sub-video according to the answer image frame and the answer audio includes: generating the answer sub-video according to the answer image frame, the answer audio, the summary image frame and the summary audio.

[0224] In some embodiments, the problem-solving video also includes a knowledge point review sub-video, wherein the knowledge point review sub-video is used to demonstrate target review knowledge, and the target review knowledge points are at least part of the target knowledge points. The video generation module 903 is also used to obtain the target review knowledge points; generate summary and induction image frames and summary and induction audio based on the target review knowledge points; and generate the review sub-video based on the summary and induction image frames and the summary and induction audio.

[0225] In some embodiments, the problem-solving video generated by the video generation module 903 is a problem-solving video that highlights key content; wherein the key content includes the target known information and the target knowledge points, and the highlighting includes increasing the text font size of the key content, changing the text color of the key content, or adding animation effects to highlight the key content.

[0226] In some embodiments, the video generation module 903 is also used to perform a matching operation in a pre-set image template library according to the target knowledge point to obtain a target matching result, wherein the pre-set image template library includes a correspondence between multiple preset knowledge points and preset image templates; when the target matching result is a successful match, obtain the target image template corresponding to the target question identifier; add the target known information, the target solution information, the target knowledge point and the target problem-solving steps to the target image template to generate the problem-solving video.

[0227] In some embodiments, after generating a problem-solving video based on the target known information, the target solving information, the target knowledge points and the target problem-solving steps, the video generation module 903 is also used to obtain video control information; based on the video control information, select a target sub-video in the problem-solving video to obtain a new problem-solving video, the target sub-video including at least part of the sub-videos in the question review sub-video, the question explanation sub-video, the answer sub-video and the video review sub-video; and control the playback of the new problem-solving video.

[0228] In some embodiments, after generating a problem-solving video based on the target known information, the target solving information, the target knowledge points and the target problem-solving steps, the video generation module 903 is also used to generate an interactive interface, and the interactive interface is used to obtain a jump video based on an interactive video control signal input by a user; wherein the jump video includes an associated problem-solving video corresponding to an associated question of the problem to be solved and a detailed explanation video of the target problem-solving information.

[0229] In some embodiments, the problem-solving video generated by the video generation module 903 is a problem-solving video that generates interactive buttons set at preset positions in the problem-solving video during playback, and the interactive buttons are used to feedback questions or post comments.

[0230] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0231] It should be noted that in the embodiments of this application Fig. 9The division of modules in the problem-solving video generation device shown is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. It may also be implemented in the form of a combination of software and hardware.

[0232] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0233] The embodiment of the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0234] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the method provided in the above embodiment are implemented.

[0235] An embodiment of the present application provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0236] Those skilled in the art will understand that Fig.10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0237] In one embodiment, the problem-solving video generation device provided by the present application can be implemented in the form of a computer program. The computer program can be Fig.10 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the above-mentioned device. The computer program composed of various program modules enables the processor to execute the steps in the method of each embodiment of the present application described in this specification.

[0238] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0239] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. For the sake of brevity, this article will not repeat them.

[0240] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0241] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0242] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0243] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0244] In addition, all functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may be a separate unit, or two or more modules may be integrated into one unit; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0245] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0246] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0247] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0248] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0249] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0250] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for generating a problem-solving video, characterized in that: The method comprises: Obtain target question information corresponding to the problem to be solved, wherein the target question information includes target known information and target solution information corresponding to the problem to be solved; According to the target known information and the target solution information, target solution information corresponding to the problem to be solved is matched, and the target solution information includes target knowledge points and target solution steps corresponding to the problem to be solved; Generate a problem-solving video according to the target known information, the target solution information, the target knowledge point and the target problem-solving steps, the problem-solving video includes a question review sub-video, a question explanation sub-video, an answer sub-video and a knowledge point review sub-video, the question review sub-video is used to demonstrate the target problem information corresponding to the problem to be solved, the question explanation sub-video is used to demonstrate the target knowledge point and the target problem-solving steps corresponding to the problem to be solved, the answer sub-video is used to demonstrate the target answer corresponding to the problem to be solved, and the knowledge point review sub-video is used to demonstrate the target review knowledge point; After generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes: Acquire video control information, wherein the video control information includes video control information input by a user, default video control information, or video control information automatically acquired based on historical problem-solving video records; According to the video control information, a target sub-video in the problem-solving video is selected to obtain a new problem-solving video, wherein the target sub-video includes at least part of the sub-videos of the problem-examination sub-video, the problem-explaining sub-video, the answer sub-video, and the knowledge point review sub-video; Control the new problem-solving video to play.

2. The method according to claim 1, characterized in that The step of matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes: Determine the target knowledge point according to the target known information and the target solution information; The target problem-solving steps are determined according to the target knowledge points and a first knowledge base, wherein the first knowledge base includes a correspondence between preset knowledge points and preset problem-solving steps.

3. The method according to claim 1, characterized in that The step of matching the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information includes: The target problem-solving information is determined based on the target known information, the target solution information and a second knowledge base, wherein the second knowledge base includes a correspondence between preset known information, preset solution information, preset knowledge points and preset problem-solving steps.

4. The method according to claim 1, characterized in that: The generating a problem-solving video according to the target known information, the target solution information, the target knowledge points and the target problem-solving steps includes: Generate the question review sub-video according to the target known information and the target solution information; Generate the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps; The answer sub-video is generated according to the target known information, the target solution information and the target problem-solving steps.

5. The method according to claim 4, characterized in that The step of generating the question review sub-video according to the target known information and the target solution information includes: Acquire the text data of the question to be solved, and generate a question reading image frame and a question reading audio; Generate a question review image frame and a question review audio according to the target known information and the target solution information; The question review sub-video is generated according to the question reading image frame, the question reading audio, the question review image frame and the question review audio.

6. The method according to claim 4, characterized in that The target problem-solving step includes at least one target problem-solving sub-step; The step of generating the topic sub-video according to the target known information, the target knowledge points and the target problem-solving steps includes: According to the target knowledge point, generate a knowledge point explanation image frame and a knowledge point explanation audio; Generate a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step; the number of the at least one problem-solving image frame is positively correlated with the number of the at least one target problem-solving sub-step; The topic explanation sub-video is generated according to the knowledge point explanation image frame, the knowledge point explanation audio, the at least one problem-solving image frame and the problem-solving audio.

7. The method according to claim 6, characterized in that The target problem-solving step includes at least two target problem-solving sub-steps; The step of generating a problem-solving audio and at least one problem-solving image frame according to the target known information and each target problem-solving sub-step comprises: Generate a problem-solving audio and at least two problem-solving image frames, the number of which is the same as the number of the at least two target problem-solving sub-steps; Among the at least two problem-solving image frames, when two adjacent pre-selected problem-solving image frames meet a preset fusion condition, the two adjacent pre-selected problem-solving image frames are subjected to image fusion as a new problem-solving image frame, and the preset fusion condition includes that the proportion of blank parts in the two adjacent pre-selected problem-solving image frames is greater than a preset threshold.

8. The method according to claim 4, characterized in that The step of generating the answer sub-video according to the target known information, the target solution information and the target problem-solving steps includes: Obtain a target answer template for the question to be solved; Generate an answer image frame and a corresponding answer audio according to the target known information, the target solution information, the target problem-solving steps and the target answer template; The answer sub-video is generated according to the answer image frame and the answer audio.

9. The method according to claim 8, characterized in that The answer sub-video also includes a summary image frame and a summary audio. After obtaining the target answer template of the question to be solved, the method further includes: According to the target knowledge point, generating a summary image frame and a corresponding summary audio; The step of generating the answer sub-video according to the answer image frame and the answer audio comprises: The answer sub-video is generated according to the answer image frame, the answer audio, the summary image frame and the summary audio.

10. The method according to claim 4, characterized in that The target review knowledge points are at least some of the target knowledge points; The generating a problem-solving video according to the target known information, the target solution information, the target knowledge points and the target problem-solving steps also includes: Acquire the target review knowledge points; Review the knowledge points according to the target, and generate summary image frames and summary audio; The review sub-video is generated according to the summary image frame and the summary audio.

11. The method according to claim 1, characterized in that: The problem-solving video is a problem-solving video that highlights key content; wherein the key content includes the target known information and the target knowledge points, and the highlighting includes increasing the text font size of the key content, changing the text color of the key content, or adding animation effects for highlighting the key content.

12. The method according to claim 1, characterized in that The generating a problem-solving video according to the target known information, the target solution information, the target knowledge points and the target problem-solving steps includes: According to the target knowledge point, a matching operation is performed in a preset image template library to obtain a target matching result, wherein the preset image template library includes a correspondence between a plurality of preset knowledge points and preset image templates; When the target matching result is a successful match, obtain the target image template corresponding to the target question identifier; add the target known information, the target solution information, the target knowledge points and the target problem-solving steps to the target image template to generate the problem-solving video.

13. The method according to claim 1, characterized in that After generating a problem-solving video according to the target known information, the target solution information, the target knowledge points, and the target problem-solving steps, the method further includes: Generate an interactive interface, the interactive interface is used to obtain a jump video according to an interactive video control signal input by a user; wherein the jump video includes an associated problem-solving video corresponding to an associated problem of the problem to be solved and a target problem-solving information detailed explanation video.

14. The method according to claim 1, characterized in that The problem-solving video is a problem-solving video that generates an interactive button set at a preset position in the problem-solving video during playback, and the interactive button is used to feedback questions or post comments.

15. A problem-solving video generating device, characterized in that: include: A question parsing module is used to obtain target question information corresponding to the question to be solved, wherein the target question information includes target known information and target solution information corresponding to the question to be solved; A problem-solving matching module, used to match the target problem-solving information corresponding to the problem to be solved according to the target known information and the target solution information, wherein the target problem-solving information includes the target knowledge points and target problem-solving steps corresponding to the problem to be solved; A video generation module is used to generate a problem-solving video according to the target known information, the target solution information, the target knowledge point and the target problem-solving steps, wherein the problem-solving video includes a question review sub-video, a question explanation sub-video, an answer sub-video and a knowledge point review sub-video, wherein the question review sub-video is used to demonstrate the target question information corresponding to the problem to be solved, the question explanation sub-video is used to demonstrate the target knowledge point and the target problem-solving steps corresponding to the problem to be solved, the answer sub-video is used to demonstrate the target answer corresponding to the problem to be solved, and the knowledge point review sub-video is used to demonstrate the target review knowledge point; The video generation module is also used to obtain video control information, which includes video control information input by the user, default video control information, or video control information automatically obtained based on historical problem-solving video records; based on the video control information, select a target sub-video in the problem-solving video to obtain a new problem-solving video, wherein the target sub-video includes at least part of the sub-videos in the question review sub-video, the question explanation sub-video, the answer sub-video, and the knowledge point review sub-video; and control the new problem-solving video to be played.

16. A computer device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 14 are implemented.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 14 is implemented.

Images