Image processing-based teaching data storage method and system

Abstract

The application discloses a kind of teaching data storage method and system based on image processing, it is related to big data technical field, main purpose is to solve the problem of low data storage efficiency of existing smart campus platform. Including: obtaining the image teaching data uploaded by user, image teaching data is based on image terminal and is bound to the text content, user object and at least one in teaching environment It is collected;Key features are extracted from image teaching data, and the image frame number corresponding to key features is counted, key features include pixel features, contour features, text features, face features;If image frame number is greater than preset frame threshold, then according to key features, image teaching data is compressed, and the compressed image teaching data is stored according to compression index;If image frame number is less than or equal to preset frame threshold, then determine the storage location corresponding to key features, and store image teaching data according to storage location.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a teaching data storage method and system based on image processing. Background Technology

[0002] With the popularization of big data technology, various industries are increasingly focusing on the application of big data scenarios to better serve different users. In particular, platforms with a large number of users, such as schools and training institutions, need to use big data technology to process data accurately. For example, the teaching data in smart campuses is updated daily and is enormous in volume, which can be managed through big data processing methods.

[0003] Currently, when storing teaching data, smart campus platforms typically store it in log format or with timestamps from user units. However, with the diversification of teaching data formats, image-based teaching data wastes a significant amount of storage space due to inconsistent user upload formats and sizes. Furthermore, the lack of a unified image processing mechanism results in the data storage of smart campus platforms consuming substantial system resources and significantly reducing the data processing efficiency of the smart campus platform. Summary of the Invention

[0004] In view of this, the present invention provides a teaching data storage method and system based on image processing, the main purpose of which is to solve the problem of low data storage efficiency of existing smart campus platforms.

[0005] According to one aspect of the present invention, a teaching data storage method based on image processing is provided, comprising:

[0006] The image teaching data uploaded by the user is obtained, and the image teaching data is collected by binding at least one of the text content, user object and teaching environment based on the image terminal;

[0007] Key features are extracted from the image teaching data, and the number of image frames corresponding to the key features is counted. The key features include pixel features, contour features, text features, and face features.

[0008] If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index.

[0009] If the number of image frames is less than or equal to a preset frame threshold, the storage location corresponding to the key feature is determined, and the image teaching data is stored according to the storage location.

[0010] According to another aspect of the present invention, a teaching data storage system based on image processing is provided, comprising:

[0011] The acquisition module is used to acquire image teaching data uploaded by users. The image teaching data is collected by binding at least one of the following based on the image terminal: text content, user object, and teaching environment.

[0012] An extraction module is used to extract key features from the image teaching data and count the number of image frames corresponding to the key features. The key features include pixel features, contour features, text features, and face features.

[0013] The first storage module is used to compress the image teaching data according to the key features and store the compressed image teaching data according to the compression index if the number of image frames is greater than a preset frame threshold.

[0014] The second storage module is used to determine the storage location corresponding to the key feature if the number of image frames is less than or equal to a preset frame threshold, and to store the image teaching data according to the storage location.

[0015] According to another aspect of the present invention, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described teaching data storage method based on image processing.

[0016] According to another aspect of the present invention, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0017] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described teaching data storage method based on image processing.

[0018] By employing the above-described technical solutions, the technical solutions provided by the embodiments of the present invention have at least the following advantages:

[0019] This invention provides a teaching data storage method and system based on image processing. Compared with existing technologies, this invention acquires user-uploaded image teaching data, which is collected by binding at least one of text content, user objects, and the teaching environment using an image terminal. Key features are extracted from the image teaching data, and the number of image frames corresponding to the key features is counted. The key features include pixel features, contour features, text features, and facial features. If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index. If the number of image frames is less than or equal to the preset frame threshold, the storage location corresponding to the key features is determined, and the image teaching data is stored according to the storage location. This achieves flexibility and convenience in storing teaching data in image form, reduces storage space waste, avoids excessive system resource consumption for data storage on the smart campus platform, and thus greatly improves the data processing efficiency of the smart campus platform.

[0020] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0021] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0022] Figure 1 This invention provides a flowchart of a teaching data storage method based on image processing.

[0023] Figure 2 This diagram illustrates a block diagram of a teaching data storage system based on image processing, provided by an embodiment of the present invention.

[0024] Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present invention is shown. Detailed Implementation

[0025] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0026] This invention provides a teaching data storage method based on image processing, such as... Figure 1 As shown, the method includes:

[0027] 101. Obtain image teaching data uploaded by users.

[0028] In this embodiment, the current execution terminal, as the execution subject for storing teaching data, can be a teaching data processing server to acquire teaching data in image form in real time, i.e., image teaching data. At this time, the image teaching data is collected by binding at least one of the following to an image terminal: text content, user objects, and the teaching environment. The image terminal can be a student user's or teacher user's mobile phone or mobile personal computer, etc., and the teaching data to be uploaded is captured by the image terminal's camera. The text content may include, but is not limited to, test paper text and homework text; the user objects may include, but are not limited to, students and teachers; and the teaching environment may include, but is not limited to, classroom environments and library environments. For example, a student user can upload a selfie of themselves waiting to attend class, or a teacher user can upload photos of students' graded homework. This embodiment does not impose specific limitations.

[0029] It should be noted that when the current execution terminal acquires the image teaching data uploaded by users, it can do so through real-time monitoring. That is, as soon as each user uploads the image teaching data, the data is acquired immediately to execute the method in step 102 for storage. Additionally, the image terminal can allow different users' devices to download the corresponding smart campus application, acting as a server for data upload with the smart campus platform of the current execution terminal, thereby ensuring the integrity of data interaction.

[0030] In another embodiment of this application, for further definition and explanation, the steps also include:

[0031] After the data connection of the image terminal is completed, the image terminal performs data acquisition according to the acquisition time instruction to obtain image teaching data.

[0032] To ensure that the image terminal can effectively and accurately collect teaching data, the current execution terminal needs to establish a data connection with the image terminal. This data connection can be achieved, but is not limited to, logging into the smart teaching platform of the current execution terminal through the image terminal's application. It is also necessary to ensure that the image terminal's camera permissions are open so that images can be captured at any time. This embodiment does not impose specific limitations on this. After establishing a data connection with the image terminal, the current execution terminal pre-configures a collection time, for example, 5 or 10 seconds. Within this collection time, the image terminal is instructed to collect multiple frames of images to obtain image teaching data. This ensures that the collected image teaching data contains multiple frames, improving the recognition of features in the image teaching data and effectively establishing a storage index.

[0033] 102. Extract key features from the image teaching data and count the number of image frames corresponding to the key features.

[0034] In this embodiment, to construct a more effective and accurate storage index and increase the speed of storing and retrieving teaching data, the current execution end extracts key features from the image teaching data. These key features include pixel features, contour features, text features, and facial features. Pixel features represent the content extracted by pixels, including but not limited to pixels whose grayscale or color values ​​meet preset conditions. Contour features represent the content extracted by image contours, including but not limited to special marker contours, building contours, etc. Text features represent the content extracted by text or words, including but not limited to Chinese characters or other language characters, numbers, etc. Facial features represent the content extracted by faces, including but not limited to the faces of different teachers or students. Furthermore, after extracting the key features, the number of image frames containing these key features is counted across multiple frames to serve as the basis for storing the image teaching data. For example, if 10 frames of image teaching data are collected, after extracting the key feature (facial features) from all images sequentially, the specific number of image frames from which facial features can be extracted is counted, such as 2 images. This embodiment does not impose a specific limitation.

[0035] In another embodiment of this application, for further definition and explanation, the step of extracting key features from the image teaching data includes:

[0036] The image teaching data is traversed according to pixel position relationships, and at least one pixel that matches the pixel position relationships is extracted to obtain pixel features; or,

[0037] The image teaching data is then used to identify contour features based on a contour recognition model that has already been trained; or,

[0038] The image teaching data is identified based on a text recognition model that has already been trained, and text features are determined; or,

[0039] The face recognition model, which has already been trained, is used to identify the face features in the image teaching data.

[0040] In order to achieve effective storage of teaching data in the form of images and thus accelerate the efficiency of teaching data retrieval, the current execution terminal adopts different extraction methods for different key features.

[0041] In some embodiments, for pixel features, the current execution end traverses all pixels of the image teaching data according to the pixel position relationship, and extracts at least one pixel that conforms to the pixel position relationship to obtain pixel features. At this time, the pixel position relationship includes adjacent pixel relationship, separated pixel relationship, and connected pixel relationship, that is, it includes pixel features that match grayscale values ​​or color values ​​extracted according to adjacent positions, pixel features that match grayscale values ​​or color values ​​extracted according to separated positions, and pixel features that match grayscale values ​​or color values ​​extracted according to the connection positions between multiple pixels. This application embodiment does not make specific limitations.

[0042] In some embodiments, for contour features, the current execution end identifies the image teaching data based on a contour recognition model that has been trained, and determines the contour features. In this case, the contour recognition model is trained based on pre-labeled contour samples. The contour recognition model includes, but is not limited to, convolutional neural networks (CNN), encoder-decoder structure models, and transformers, etc., and is not specifically limited in this application embodiment.

[0043] In some embodiments, for text features, the current execution end identifies the image teaching data based on a text recognition model that has been trained, and determines the text features. In this case, the text recognition model is trained based on a preset text library. The text recognition model may include, but is not limited to, Hidden Markov Models (HMMs), Recurrent Neural Networks (RNNs), and semantic recognition models such as BERT; this application embodiment does not specifically limit it.

[0044] In some embodiments, for facial features, the current execution end identifies the facial features based on a pre-trained facial recognition model using the image teaching data. In this case, the facial recognition model is trained based on a facial database. The facial recognition model may include, but is not limited to, Transformer-CNN hybrid, VGGFace, DeepFace, etc., and this application embodiment does not impose specific limitations.

[0045] In another embodiment of this application, for further definition and explanation, the step of counting the number of image frames corresponding to the key features includes:

[0046] The total number of image frames in the image teaching data is determined according to the length of the acquisition time.

[0047] The number of image frames is calculated from the number of image frames based on the image teaching data that identifies the key features.

[0048] To improve the storage and retrieval efficiency of image-based teaching data by using image frame count as the storage basis, the current execution terminal first determines the total number of image frames collected for the image-based teaching data according to the acquisition time length. For example, if the total number of image frames collected within 3 seconds is 30 frames, it means that 30 images are collected per second as image-based teaching data. Furthermore, after extracting key features, the frames for which key features are extracted are counted. For example, if the number of frames for which key features are extracted is 10, it means that the number of frames extracted according to key features from the 30 images is 10. This embodiment does not impose specific limitations.

[0049] 103. If the number of image frames is greater than the preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index.

[0050] In this embodiment, a preset frame threshold is used as the basis for determining whether image teaching data should be compressed and stored. The preset frame threshold can be 5 frames or 7 frames, configured to be less than the total number of frames of all image teaching data collected during the acquisition time. This embodiment does not impose a specific limitation. When the number of image frames exceeds the preset frame threshold, it indicates that there are many key features that can be extracted from the image teaching data. Therefore, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index. The compression index is generated based on the key features to quickly locate the corresponding storage location of the image teaching data during subsequent queries.

[0051] In another embodiment of this application, for further definition and explanation, the steps of compressing the image teaching data according to the key features and storing the compressed image teaching data according to the compression index include:

[0052] If the key feature is a pixel feature, then the compression object of the image teaching data is determined according to the pixel feature, and a first compression index is constructed according to the compression object, so as to store the compressed image teaching data according to the first compression index. The compression object is determined from the pixels of the image teaching data according to the pixel position and the number of pixels.

[0053] If the key feature is a contour feature, then the image teaching data is extended according to the contour feature to obtain an extended contour, and a second compression index is constructed according to the extended contour to store the compressed image teaching data according to the second compression index. The extended contour is obtained by extending the contour feature according to a preset extension length.

[0054] If the key feature is a text feature, then keywords are extracted from the text feature, and a third compression index is constructed based on the keywords, so that the compressed image teaching data is stored according to the third compression index, wherein the keywords are determined according to the importance coefficient of the text feature;

[0055] If the key feature is a facial feature, then the user's identity information is determined based on the facial feature, and a fourth compression index is constructed based on the user's identity information, so that the compressed image teaching data is stored according to the fourth compression index, wherein the user's identity information is obtained by recognizing and matching the facial feature.

[0056] In some embodiments, if the key feature is a pixel feature, in order to build an index from a pixel perspective to improve the diversity and effectiveness of image teaching data storage, the current execution end determines the compression object of the image teaching data according to the pixel feature and constructs a first compression index according to the compression object. The compression object is the pixel to be compressed. In this case, the compression object is determined from the pixels of the image teaching data according to the pixel position and the number of pixels. Specifically, the pixel position is the position corresponding to the extracted pixel feature, and the number of pixels is the number of extracted pixel features. This application embodiment does not impose specific limitations. Furthermore, when determining the compression object, it can be based on pre-configured pixel positions, such as the pixel feature and the surrounding pixels of the pixel feature, and the number of pixels, such as four (front, back, left, right), or eight (front, back, left, right, left front, right front, left back, right back), etc. This application embodiment does not impose specific limitations. In addition, when constructing the first compression index according to the compressed object, specifically, the pixels are extracted according to their positions in the entire image teaching data, so as to obtain the first compression index according to the extracted pixel positions, and the compressed image teaching data is stored according to the first compression index. This application embodiment does not make specific limitations.

[0057] In some embodiments, if the key feature is a contour feature, in order to build an index based on the contour angle to improve the diversity and effectiveness of image teaching data storage, the current execution end extends the image teaching data according to the contour feature to obtain an extended contour, and then constructs a second compressed index according to the extended contour. The extended contour can be obtained by extending the contour feature according to a preset extension length. For example, the contour feature is the contour of a hammer made in an internship; the hammer contour is extended by a preset extension length of 2 mm. This application embodiment does not specifically limit this. Furthermore, the construction of the second compressed index according to the extended contour involves first identifying the shape of the extended contour feature, including but not limited to squares, rectangles, circles, irregular polygons, etc., and generating a corresponding compressed index according to the identified shape and a preset shape sort (e.g., square sort 1, rectangle sort 2, etc.). For example, irregular polygon 1, curve and straight line combination 1-2, i.e., the compressed index created by the contour feature is 1-2, so that the compressed image teaching data is stored according to the second compressed index. This application embodiment does not specifically limit this.

[0058] In some embodiments, if the key feature is a text feature, in order to build an index from a text perspective and improve the diversity and effectiveness of image teaching data storage, the current execution end extracts keywords from the text feature and builds a third compressed index based on the keywords. Since the extracted keywords are obtained through pre-training based on natural language processing technology, the current execution end can build the index according to the importance coefficient of the text feature when creating the third compressed index. Specifically, firstly, the alphabetical order of each character in the text feature is determined as the first-level index, and the number of keywords in the text feature is calculated. The importance coefficient is obtained by comparing the counted number of keywords with the total number in the entire keyword database, and this coefficient serves as the second-level index. The first-level index and the second-level index are combined into the third compressed index, and the compressed image teaching data is stored according to the third compressed index. This embodiment of the application does not impose specific limitations.

[0059] In some embodiments, if the key feature is a facial feature, in order to build an index based on the facial features to improve the diversity and effectiveness of image teaching data storage, the current execution terminal determines the user identity information based on the facial features and builds a fourth compressed index based on the user identity information. The user identity information is obtained by recognizing and matching the facial features; that is, a compressed index can be built based on the user identity information. For example, if the user is a student, the student's major, class, student ID, etc., are retrieved to build an index, and the compressed image teaching data is stored according to the fourth compressed index. This application embodiment does not impose specific limitations.

[0060] It should be noted that when the current execution end stores the compressed image teaching data according to each compression index, it first compresses the image teaching data. During compression, the current execution end can choose to extract and compress the identified key features, while deleting non-key features to reduce storage redundancy. Then, the compressed image teaching data containing key features is named according to the compression index and stored in the corresponding storage location. When an administrator requests a query, the interpretation of different compression indexes can be displayed to the administrator. For example, the interpretation of the first compression index is the pixel positions corresponding to the front, back, left, and right sides, respectively, so that the administrator can enter all the pixel features to be queried and retrieve the corresponding image teaching data from the corresponding storage location.

[0061] 104. If the number of image frames is less than or equal to a preset frame threshold, then determine the storage location corresponding to the key feature, and store the image teaching data according to the storage location.

[0062] In this embodiment, a preset frame threshold is used as the basis for determining whether image teaching data should be compressed and stored. The preset frame threshold can be 5 frames or 7 frames, configured to be less than the total number of frames of all image teaching data collected during the acquisition time. This embodiment does not impose a specific limitation. When the number of image frames is less than or equal to the preset frame threshold, it indicates that few key features can be extracted from the image teaching data. Therefore, the storage location corresponding to the key features is directly determined, and the image teaching data is stored according to this storage location.

[0063] In another embodiment of this application, for further definition and explanation, the step of determining the storage location corresponding to the key feature and storing the image teaching data according to the storage location includes:

[0064] The storage location is determined from the teaching data storage according to the storage capacity, storage update time, and storage cycle;

[0065] When a storage instruction is received at the storage location, the image teaching data is stored in the storage location.

[0066] To ensure storage effectiveness and increase storage efficiency, the current execution end first determines the storage location from the teaching data storage based on the storage capacity, storage update time, and storage rounds. Here, storage capacity refers to the amount of data already stored in each storage location within the teaching data storage; storage update time is the time the data in each storage location is updated; and storage rounds are the number of storage cycles completed by the teaching data storage. When determining the storage location, a preset matching strategy can be used to match storage locations from all storage locations based on storage capacity, storage update time, and storage rounds. The preset matching strategy can be to use at least one of the following as filtering conditions to determine whether each storage location meets the criteria: maximum storage capacity, longest storage update time, and smallest storage rounds. In this case, the storage location corresponding to the maximum storage capacity, longest storage update time, and smallest storage rounds is selected as the optimal storage location. That is, storage capacity is the optimal judgment condition, storage update time is the secondary judgment condition, and storage rounds are the final judgment condition. This embodiment does not impose specific limitations on this.

[0067] It should be noted that when a storage instruction for a storage location is detected, the image teaching data can be stored in the designated storage location. This storage location is a pre-allocated fixed storage space in the memory, and this embodiment does not impose specific limitations on it. Furthermore, the storage instruction is triggered after the current execution terminal has successfully verified the identity. For example, after the current execution terminal determines that a teacher or student user has completed genuine identity verification, it generates a storage instruction. This can be based on phone number verification code verification or facial verification, and this embodiment does not impose specific limitations on it.

[0068] This invention provides a teaching data storage method based on image processing. Compared with existing technologies, this invention acquires user-uploaded image teaching data, which is collected by binding at least one of text content, user objects, and the teaching environment using an image terminal. Key features are extracted from the image teaching data, and the number of image frames corresponding to the key features is counted. The key features include pixel features, contour features, text features, and facial features. If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index. If the number of image frames is less than or equal to the preset frame threshold, the storage location corresponding to the key features is determined, and the image teaching data is stored according to the storage location. This achieves flexibility and convenience in storing teaching data in image form, reduces storage space waste, avoids excessive system resource consumption for data storage on the smart campus platform, and thus greatly improves the data processing efficiency of the smart campus platform.

[0069] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this invention provides a teaching data storage system based on image processing, such as... Figure 2 As shown, the system includes:

[0070] The acquisition module 21 is used to acquire image teaching data uploaded by the user. The image teaching data is collected by binding at least one of the following based on the image terminal: text content, user object, and teaching environment.

[0071] Extraction module 22 is used to extract key features from the image teaching data and count the number of image frames corresponding to the key features. The key features include pixel features, contour features, text features, and face features.

[0072] The first storage module 23 is used to compress the image teaching data according to the key features and store the compressed image teaching data according to the compression index if the number of image frames is greater than a preset frame threshold.

[0073] The second storage module 24 is used to determine the storage location corresponding to the key feature if the number of image frames is less than or equal to a preset frame threshold, and to store the image teaching data according to the storage location.

[0074] Further, the extraction module is specifically used to traverse all pixels of the image teaching data according to pixel position relationships, extract at least one pixel that conforms to the pixel position relationships, and obtain pixel features. The pixel position relationships include adjacent pixel relationships, separated pixel relationships, and connected pixel relationships. Alternatively, it can identify the image teaching data based on a contour recognition model that has been trained to determine contour features. The contour recognition model is trained based on pre-labeled contour samples. Alternatively, it can identify the image teaching data based on a text recognition model that has been trained to determine text features. The text recognition model is trained based on a preset text library. Alternatively, it can identify the image teaching data based on a face recognition model that has been trained to determine face features. The face recognition model is trained based on a face database.

[0075] Further, the first storage module is specifically configured to: if the key feature is a pixel feature, determine the compression object of the image teaching data according to the pixel feature, and construct a first compression index according to the compression object, so as to store the compressed image teaching data according to the first compression index, wherein the compression object is determined from the pixels of the image teaching data according to the pixel position and the number of pixels; if the key feature is a contour feature, extend the image teaching data according to the contour feature to obtain an extended contour, and construct a second compression index according to the extended contour, so as to store the compressed image teaching data according to the second compression index, wherein the extended contour... The extended contour is obtained by extending the contour feature according to a preset extension length; if the key feature is a text feature, then keywords are extracted from the text feature, and a third compression index is constructed based on the keywords, so as to store the compressed image teaching data according to the third compression index, wherein the keywords are determined according to the importance coefficient of the text feature; if the key feature is a facial feature, then user identity information is determined based on the facial feature, and a fourth compression index is constructed based on the user identity information, so as to store the compressed image teaching data according to the fourth compression index, wherein the user identity information is obtained by recognizing and matching the facial feature.

[0076] Furthermore, the second storage module is specifically used to determine the storage location from the teaching data storage according to the storage capacity, storage update time, and storage cycle; when a storage instruction for the storage location is detected, the image teaching data is stored in the storage location.

[0077] Furthermore, the extraction module is also used to determine the total number of image frames of the image teaching data according to the acquisition time length; and to count the number of image frames from the number of image frames according to the image teaching data that has identified the key features.

[0078] Furthermore, the system also includes:

[0079] The acquisition module is used to acquire image teaching data by instructing the image terminal to acquire data according to the acquisition time after the data connection of the image terminal is completed.

[0080] This invention provides an image processing-based teaching data storage system. Compared with existing technologies, this invention acquires user-uploaded image teaching data, which is collected by binding at least one of text content, user objects, and the teaching environment using an image terminal. Key features are extracted from the image teaching data, and the number of image frames corresponding to these key features is counted. These key features include pixel features, contour features, text features, and facial features. If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to a compression index. If the number of image frames is less than or equal to the preset frame threshold, the storage location corresponding to the key features is determined, and the image teaching data is stored according to that storage location. This system achieves flexibility and convenience in storing teaching data in image form, reducing storage space waste and avoiding excessive system resource consumption by the smart campus platform, thereby greatly improving the data processing efficiency of the smart campus platform.

[0081] According to one embodiment of the present invention, a storage medium is provided, the storage medium storing at least one executable instruction, the computer-executable instruction being able to execute the image processing-based teaching data storage method in any of the above method embodiments.

[0082] Figure 3 The diagram shows a structural schematic of a terminal according to an embodiment of the present invention. The specific implementation of the terminal is not limited by the specific embodiments of the present invention.

[0083] like Figure 3 As shown, the terminal may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0084] The processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308.

[0085] Communication interface 304 is used to communicate with other network elements such as clients or other servers.

[0086] The processor 302 is used to execute program 310, specifically to perform the relevant steps in the above-described embodiment of the teaching data storage method based on image processing.

[0087] Specifically, program 310 may include program code that includes computer operation instructions.

[0088] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The terminal may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0089] Memory 306 is used to store program 310. Memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0090] Specifically, program 310 can be used to cause processor 302 to perform the following operations:

[0091] The image teaching data uploaded by the user is obtained, and the image teaching data is collected by binding at least one of the text content, user object and teaching environment based on the image terminal;

[0092] Key features are extracted from the image teaching data, and the number of image frames corresponding to the key features is counted. The key features include pixel features, contour features, text features, and face features.

[0093] If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index.

[0094] If the number of image frames is less than or equal to a preset frame threshold, the storage location corresponding to the key feature is determined, and the image teaching data is stored according to the storage location.

[0095] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing systems. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0096] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A teaching data storage method based on image processing, characterized in that, include: The image teaching data uploaded by the user is obtained, and the image teaching data is collected by binding at least one of the text content, user object and teaching environment based on the image terminal; Key features are extracted from the image teaching data, and the number of image frames corresponding to the key features is counted. The key features include pixel features, contour features, text features, and face features. If the number of image frames is greater than a preset frame threshold, the image teaching data is compressed according to the key features, and the compressed image teaching data is stored according to the compression index. If the number of image frames is less than or equal to a preset frame threshold, then the storage location corresponding to the key feature is determined, and the image teaching data is stored according to the storage location. The extraction of key features from the image teaching data includes: The image teaching data is traversed according to pixel position relationships. At least one pixel that conforms to the pixel position relationships is extracted to obtain pixel features. The pixel position relationships include adjacent pixel relationships, separated pixel relationships, and connected pixel relationships; or, The image teaching data is then used to identify contour features based on a pre-trained contour recognition model, wherein the contour recognition model is trained based on pre-labeled contour samples; or, The image teaching data is recognized based on a pre-trained text recognition model to determine text features. The text recognition model is trained on a pre-defined text database. The face recognition model, which has been trained, is used to identify the face features in the image teaching data. The face recognition model is trained based on a face database. The step of compressing the image teaching data according to the key features and storing the compressed image teaching data according to the compression index includes: If the key feature is a pixel feature, then the compression object of the image teaching data is determined according to the pixel feature, and a first compression index is constructed according to the compression object, so as to store the compressed image teaching data according to the first compression index. The compression object is determined from the pixels of the image teaching data according to the pixel position and the number of pixels. If the key feature is a contour feature, then the image teaching data is extended according to the contour feature to obtain an extended contour, and a second compression index is constructed according to the extended contour to store the compressed image teaching data according to the second compression index. The extended contour is obtained by extending the contour feature according to a preset extension length. If the key feature is a text feature, then keywords are extracted from the text feature, and a third compression index is constructed based on the keywords, so that the compressed image teaching data is stored according to the third compression index, wherein the keywords are determined according to the importance coefficient of the text feature; If the key feature is a facial feature, then the user's identity information is determined based on the facial feature, and a fourth compression index is constructed based on the user's identity information, so that the compressed image teaching data is stored according to the fourth compression index, wherein the user's identity information is obtained by recognizing and matching the facial feature.

2. The method according to claim 1, characterized in that, The step of determining the storage location corresponding to the key feature and storing the image teaching data according to the storage location includes: The storage location is determined from the teaching data storage according to the storage capacity, storage update time, and storage cycle; When a storage instruction is received at the storage location, the image teaching data is stored in the storage location.

3. The method according to claim 2, characterized in that, The number of image frames corresponding to the key features includes: The total number of image frames in the image teaching data is determined according to the length of the acquisition time. The number of image frames is calculated from the number of image frames based on the image teaching data that identifies the key features.

4. The method according to claim 3, characterized in that, The method further includes: After the data connection of the image terminal is completed, the image terminal performs data acquisition according to the acquisition time instruction to obtain image teaching data.

5. A teaching data storage system based on image processing, characterized in that, include: The acquisition module is used to acquire image teaching data uploaded by users. The image teaching data is collected by binding at least one of the following based on the image terminal: text content, user object, and teaching environment. An extraction module is used to extract key features from the image teaching data and count the number of image frames corresponding to the key features. The key features include pixel features, contour features, text features, and face features. The first storage module is used to compress the image teaching data according to the key features and store the compressed image teaching data according to the compression index if the number of image frames is greater than a preset frame threshold. The second storage module is used to determine the storage location corresponding to the key feature if the number of image frames is less than or equal to a preset frame threshold, and to store the image teaching data according to the storage location. The extraction module is specifically used to traverse all pixels of the image teaching data according to the pixel position relationship, and extract at least one pixel that conforms to the pixel position relationship to obtain pixel features. The pixel position relationship includes adjacent pixel relationship, separated pixel relationship, and connected pixel relationship. Alternatively, the image teaching data can be identified based on a pre-trained contour recognition model to determine contour features, wherein the contour recognition model is trained based on pre-labeled contour samples; or, the image teaching data can be identified based on a pre-trained text recognition model to determine text features, wherein the text recognition model is trained based on a preset text database; or, the image teaching data can be identified based on a pre-trained face recognition model to determine face features, wherein the face recognition model is trained based on a face database. The first storage module is specifically configured to: if the key feature is a pixel feature, determine the compression object of the image teaching data according to the pixel feature, and construct a first compression index according to the compression object, so as to store the compressed image teaching data according to the first compression index; the compression object is determined from the pixels of the image teaching data according to the pixel position and the number of pixels; if the key feature is a contour feature, extend the image teaching data according to the contour feature to obtain an extended contour, and construct a second compression index according to the extended contour, so as to store the compressed image teaching data according to the second compression index. The outline is obtained by extending the outline feature according to a preset extension length; if the key feature is a text feature, then keywords are extracted from the text feature, and a third compression index is constructed based on the keywords, so as to store the compressed image teaching data according to the third compression index, wherein the keywords are determined according to the importance coefficient of the text feature; if the key feature is a facial feature, then user identity information is determined based on the facial feature, and a fourth compression index is constructed based on the user identity information, so as to store the compressed image teaching data according to the fourth compression index, wherein the user identity information is obtained by recognizing and matching the facial feature.

6. A storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the image processing-based teaching data storage method as described in any one of claims 1-4.

7. A terminal, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the image processing-based teaching data storage method as described in any one of claims 1-4.

Images